Construction engineering multi-work-type collaborative operation system driven by intelligent construction platform

Abstract

The invention discloses a building engineering multi-work-type collaborative operation system driven by an intelligent construction platform, and relates to the field of building engineering multi-work-type collaborative operation, and the system comprises a data obtaining module which is used for obtaining the spatial data, equipment resource occupation time data and environmental parameter data of each work type operation region; the data processing module is used for constructing a three-dimensional geometric model of a work type operation area and generating time sequence distribution occupied by equipment resources; the conflict judgment module is used for calculating the geometric overlapping degree and the time window overlapping degree of the working areas of different types of work and judging the space conflict and the time conflict; the conflict resolution module is used for executing space redivision and time window redistribution based on the priority ranking table; the output control module is used for outputting a control instruction to adjust operation parameters of the construction equipment; the dynamic optimization module is used for carrying out iterative calculation according to the updated data and triggering an optimization loop; according to the invention, the efficiency of collaborative operation of multiple types of work can be improved on the premise of ensuring the construction safety.

Description

Technical Field

[0001] The present invention relates to the field of multi-trade collaborative operations in construction engineering, and specifically to a multi-trade collaborative operation system in construction engineering driven by an intelligent construction platform. Background Art

[0002] With the exponential growth in the scale and complexity of modern construction projects, ensuring the efficiency and safety of multi-disciplinary collaborative work has become a core challenge for the industry. Driven by the wave of new urbanization and intelligent construction, the construction industry is undergoing a critical transition from extensive management to digital and intelligent management. The integrated application of technologies such as intelligent construction platforms, the Internet of Things (IoT), and Building Information Modeling (BIM) provides the technical foundation for refined construction management.

[0003] However, in complex projects such as super high-rise buildings and large complexes, the frequency of cross-operation of multiple trades has increased sharply, and characteristics such as three-dimensional construction space, dynamic equipment resources, and environmental safety sensitivity have become increasingly prominent. The traditional construction management model can no longer meet the needs of real-time collaboration and risk prediction. Summary of the Invention

[0004] In response to the deficiencies in the prior art, the present invention provides a multi-trade collaborative work system for construction projects driven by an intelligent construction platform.

[0005] In order to achieve the above object, the technical solution of the present invention is as follows:

[0006] In a first aspect, the present invention discloses a construction engineering multi-trade collaborative operation system driven by an intelligent construction platform, comprising:

[0007] The data acquisition module is used to obtain spatial data of each work area, equipment resource occupancy time data and environmental parameter data through a multi-dimensional sensing unit;

[0008] A data processing module is used to construct a three-dimensional geometric model of the work area based on the spatial data and the equipment resource occupancy time data, and generate a time series distribution of the equipment resource occupancy;

[0009] A conflict judgment module is used to calculate the geometric overlap A of different types of work areas based on the three-dimensional geometric model, and to calculate the time window overlap B based on the time series distribution of equipment resource occupancy; when the geometric overlap A exceeds a preset spatial threshold, it is determined that a spatial conflict exists; when the time window overlap B exceeds a preset time threshold, it is determined that a time conflict exists;

[0010] The conflict resolution module is used to combine environmental parameter data with preset safety thresholds to perform multi-dimensional coupling analysis and calculate the collaborative work feasibility coefficient C. If the feasibility coefficient C exceeds the preset collaborative work threshold, a priority ranking table containing conflicting work types is generated. Based on the priority ranking table, the work areas of work types with time and space conflicts are spatially re-divided and time windows are reallocated.

[0011] An output control module, configured to output control instructions to the construction equipment and adjust the division of the working area and the working time window of the equipment according to the control instructions;

[0012] The dynamic optimization module is used to re-collect the updated spatial data and environmental parameter data after executing the control instructions and input them into the three-dimensional geometric model for iterative calculation to generate new geometric overlap A' and time window overlap B'; when A' or B' exceeds the corresponding preset percentage, the dynamic optimization cycle of the collaborative operation plan is triggered.

[0013] In a second aspect, the present invention discloses a method for collaborative multi-type construction work in a construction project driven by an intelligent construction platform, comprising the following steps:

[0014] Acquire spatial data of each work area, equipment resource occupancy time data, and environmental parameter data through multi-dimensional sensing units;

[0015] Constructing a three-dimensional geometric model of the work area based on the spatial data and the equipment resource occupancy time data, and generating a time series distribution of equipment resource occupancy;

[0016] Calculate the geometric overlap A of different types of work areas based on the three-dimensional geometric model, and calculate the time window overlap B based on the time series distribution of equipment resource occupancy;

[0017] When the geometric overlap A exceeds the preset spatial threshold, it is determined that there is a spatial conflict; when the time window overlap B exceeds the preset time threshold, it is determined that there is a temporal conflict;

[0018] Combine environmental parameter data with preset safety thresholds to conduct multi-dimensional coupling analysis and calculate the collaborative operation feasibility coefficient C;

[0019] If the feasibility coefficient C exceeds the preset collaborative work threshold, a priority ranking table containing conflicting work types is generated, and the work areas of the work types with time and space conflicts are spatially redistributed and time windows are reallocated based on the priority ranking table;

[0020] Output control instructions to construction equipment, and adjust the work area division and equipment working time window according to the control instructions;

[0021] After executing the control command, the updated spatial data and environmental parameter data are re-collected and input into the 3D geometric model for iterative calculation to generate a new geometric overlap A' and time window overlap B'. When A' or B' exceeds the corresponding preset percentage, the dynamic optimization cycle of the collaborative operation plan is triggered:

[0022] Compared with the prior art, the present invention has the following beneficial effects:

[0023] 1. Based on dual analysis of 3D geometric models and time series data, it captures in real time the risks of three-dimensional spatial interference and equipment resource timing conflicts in different work areas. Compared with traditional static models, the system significantly improves the comprehensiveness and timeliness of conflict detection through spatial projection overlap calculation and time window overlap analysis, effectively avoiding construction interruptions caused by human experience misjudgment.

[0024] 2. Dynamically generate a work type priority list based on multi-dimensional indicators such as construction progress, quality impact, and resource scarcity. Through standardized evaluation and weight allocation mechanisms, the system can flexibly adjust resource allocation strategies based on the characteristics of the project stage, ensuring the continuity of key processes while optimizing resource utilization efficiency for low-priority work types.

[0025] 3. Through the accumulation and analysis of historical adjustment data, the system constructs a dynamic performance evaluation model and autonomously generates classification optimization strategies. Based on the collaborative mechanism of spatial adjustment and time window compression, the construction plan is continuously optimized, forming a closed-loop chain of "perception-decision-execution-verification", gradually improving the adaptability and stability of multi-type collaborative operations;

[0026] 4. This effectively addresses the technical issue of mismatching adjustment range and safety effectiveness during control instruction adjustments, avoids equipment operation risks caused by excessive space compression, and eliminates idle resources caused by rigid time window cuts. Through data-driven classification optimization strategies, the efficiency of multi-task collaborative work is improved while ensuring construction safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0028] Figure 1 This is an overall system block diagram of the first embodiment of the present invention;

[0029] Figure 2 This is a flow chart of the first embodiment of the present invention;

[0030] Figure 3 This is a block diagram of the overall method of embodiment 2 of the present invention. DETAILED DESCRIPTION

[0031] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0032] Application Overview: In the field of construction engineering, the efficiency and safety of collaborative work among multiple trades have always been the core issues of technological innovation in the industry. With the exponential growth in the scale and complexity of modern construction projects, the inherent information barriers in the traditional construction management model have gradually been exposed. Systemic defects such as isolated work data of various trades, delayed dynamic resource scheduling, and insufficient prediction of environmental safety risks have led to frequent process conflicts and resource mismatches during the construction process, seriously restricting the overall efficiency of the project. Although the existing BIM-based construction management system has achieved three-dimensional visual modeling, its static data update mechanism and one-way information transmission mode are difficult to support the dynamic collaboration needs of real-time linkage among multiple trades.

[0033] The core challenges currently facing the industry are concentrated in three dimensions: First, construction data is scattered across separate management subsystems (such as schedule planning, equipment monitoring, and environmental sensing), and there is a lack of an intelligent central platform for global data integration, resulting in the inability to form a collaborative analysis of key parameters such as space occupancy status, equipment operation timing, and environmental safety thresholds; second, traditional scheduling strategies rely too much on manual experience and prediction, and often fall into a lag cycle of passive response conflicts when faced with dynamic scenarios such as sudden changes in tower crane trajectories and cross-operation of multiple trades; third, the rules for determining the priority of trades lack flexibility and fail to form dynamic adaptation with the characteristics of the project stages (such as the difference in the weight of trades in the main structure construction and decoration installation stages), resulting in a structural deviation between resource scheduling strategies and actual construction needs.

[0034] In order to solve the above problems, this application proposes the following technical solutions.

[0035] Example 1:

[0036] like Figure 1-2As shown, the multi-trade collaborative operation system for construction projects driven by an intelligent construction platform includes: a data acquisition module, which is used to obtain spatial data, equipment resource occupancy time data and environmental parameter data of each trade operation area through a multi-dimensional sensing unit; a data processing module, which is used to construct a three-dimensional geometric model of the trade operation area based on the spatial data and equipment resource occupancy time data, and generate a time series distribution of equipment resource occupancy; a conflict judgment module, which is used to calculate the geometric overlap of different trade operation areas based on the three-dimensional geometric model, calculate the time window overlap based on the time series distribution, and determine spatial conflict and time conflict through threshold comparison; a conflict resolution module, which is used to perform multi-dimensional analysis and calculate the feasibility coefficient based on environmental parameters and safety thresholds, and perform spatial redivision and time window reallocation based on a priority sorting table; an output control module, which is used to output control instructions to adjust the operation parameters of construction equipment; and a dynamic optimization module, which is used to iteratively calculate and trigger an optimization cycle based on updated data.

[0037] Among them, multidimensional sensing units refer to IoT sensing devices deployed at construction sites. Specifically, they can be implemented using a combination of lidar, RFID tags, and vibration sensors to capture spatial coordinates, equipment operating status, and environmental monitoring data in real time. A three-dimensional geometric model refers to a digital image that contains spatial topological relationships. Specifically, it can be implemented using a point cloud data fusion algorithm, constructing a spatially correlated three-dimensional model through vertex coordinate interpolation. A time series distribution refers to a dataset of temporal characteristics of equipment resource usage. Specifically, it can be implemented using a timestamp tagging method, recording the device identifier, start time, and duration to form a computable set of time intervals. A feasibility coefficient is a quantitative indicator of the safety risk of collaborative work. Specifically, it can be implemented using a normalized weighted algorithm, which normalizes the deviations of environmental parameters such as dust concentration and noise intensity to generate a risk level parameter. A priority ranking table refers to the dynamic assessment results of work scheduling priorities. Specifically, it can be implemented using a multi-indicator weighted scoring method, generating a dynamically adjustable ranking sequence based on parameters such as construction progress and quality impact.

[0038] Specifically, spatial data is converted into a point cloud dataset through lidar scanning, and equipment resource usage time data is uploaded with timestamp information by the equipment controller. The data processing module converts the point cloud data into a 3D geometric model and integrates temporal data to generate a time series distribution graph. The conflict determination module calculates the percentage of overlapping 3D projections of different work areas. When this percentage exceeds a preset threshold, a spatial conflict warning is triggered. Simultaneously, the overlap ratio of equipment time windows is calculated, and when this percentage exceeds a temporal threshold, a temporal conflict warning is triggered. The conflict resolution module compares environmental monitoring data with safety thresholds. When dust concentration exceeds the limit or noise intensity exceeds the standard, the feasibility coefficient assessment is reduced. By constructing a multidimensional assessment system that incorporates the impact of construction progress and quality, a dynamic priority ranking table is generated to guide spatial area reduction and time window adjustment. The output control module sends trajectory offset and time interval commands to equipment such as tower cranes and concrete pump trucks. The dynamic optimization module continuously collects adjusted work data. When the new geometric overlap or temporal overlap exceeds a preset percentage, the conflict resolution process is restarted, forming an optimization closed loop.

[0039] Compared to existing technologies, traditional BIM systems only enable static model construction and are incapable of real-time spatial conflict detection. This solution combines the computation of 3D geometric models with time series to achieve dual early warning of dynamic spatial and temporal conflicts. Existing scheduling systems rely on manual experience to adjust priorities. This solution generates a dynamic ranking table using multi-dimensional evaluation indicators, enabling data-driven intelligent decision-making. Traditional methods lack closed-loop verification mechanisms. This solution, through a dynamic optimization module, forms a complete control chain of "perception-decision-execution-verification," ensuring continuous optimization of scheduling strategies.

[0040] Through the above technical solutions, this application achieves real-time situational awareness and conflict prediction in multi-type workspaces, effectively reducing the probability of process conflicts. By deeply coupling environmental safety parameters with scheduling decisions, forced collaborative work in high-risk environments is avoided. The dynamic priority assessment mechanism can automatically adapt the scheduling strategy according to the characteristics of the project stage, improving the rationality of resource allocation. The closed-loop optimization system ensures that the system can continuously adapt to the dynamic changes of the construction site, forming a progressively optimized collaborative work plan.

[0041] This application further proposes that the process of constructing a three-dimensional geometric model includes converting the spatial data of the work area into a set of polygon vertex coordinates, using a vertex coordinate interpolation algorithm when constructing the three-dimensional geometric model, and generating a three-dimensional geometric model with a topological relationship; the time series distribution includes a device resource identifier, a start timestamp, and a duration period.

[0042] The polygon vertex coordinate set refers to discretizing the geometric shape of the work area into a sequence of vertex coordinate data. Specifically, vertex coordinates can be obtained through LiDAR scanning or BIM model export. The topological connectivity of these vertex coordinates accurately describes the three-dimensional boundaries of the work area. The vertex coordinate interpolation algorithm performs nonlinear interpolation calculations on the spatial coordinates between adjacent vertices. Specifically, cubic spline interpolation can be used to fill in the surface morphology between vertices, ensuring that the generated geometric model has continuous and smooth surface properties, supporting accurate spatial overlap calculations. A topologically related 3D geometric model refers to a model with clear adjacency relationships and surface continuity between vertices. Specifically, a topological data structure can be implemented through a vertex index list and an edge connectivity table, ensuring that the model maintains geometric integrity during dynamic adjustments. The equipment resource identifier is a coded sequence used to uniquely identify construction equipment. Specifically, RFID tags or QR codes can be used to bind equipment entities, enabling accurate association of equipment with time data. The start timestamp records the precise start moment of the equipment's operation cycle. Specifically, a GPS-synchronized clock can be used to generate millisecond-level timestamps, supporting high-precision time window calculations. The duration period refers to the continuous time period during which the equipment occupies resources. Specifically, the start and end times of the operation cycle can be collected through the equipment start and stop sensors to form exclusive time interval data of the equipment resources.

[0043] Specifically, when constructing a three-dimensional geometric model, the point cloud data obtained by lidar scanning is processed by boundary fitting and converted into a polygon set consisting of vertex coordinates. The space between adjacent vertices is reconstructed using a cubic spline interpolation algorithm to form a three-dimensional model with a continuous surface. This model maintains the logical association of the geometric structure of the work area through a topological connection relationship table between vertices, so that subsequent spatial overlap calculations can accurately reflect the overlapping state of the real physical space. For time series distribution, each device resource is assigned a unique identifier, and the operation start timestamp is recorded by a high-precision clock. Combined with the device operation status detected by the pressure sensor, the duration period data is generated to form an exclusive time occupancy record of the device resource.

[0044] Compared with existing technologies, traditional BIM systems use discrete point clouds to construct static three-dimensional models, lacking topological connections between vertices, which easily leads to geometric structural breaks when the model is adjusted. This solution generates a continuous surface model with topological relationships through a vertex coordinate interpolation algorithm, significantly improving the accuracy of spatial conflict detection. In terms of time data processing, existing systems only record the rough time period of equipment operation. However, this solution achieves refined calculation of time window overlap by binding device identifiers to millisecond-level timestamps, effectively avoiding misjudgments caused by insufficient time precision in traditional methods.

[0045] Through the above technical solution, this application solves the problem of conflict detection errors caused by insufficient geometric accuracy of three-dimensional models in traditional construction management systems, and realizes the dynamic maintenance of spatial topological relationships in the work area; by associating equipment resource identifiers with high-precision time data, an accurate time window overlap calculation benchmark is established, avoiding missed detection of time conflicts in collaborative operations of multiple devices; the continuous surface model generated by the interpolation algorithm provides accurate input data for subsequent geometric overlap calculations, ensuring the reliability of spatial conflict judgment.

[0046] This application further proposes a dual quantitative calculation mechanism of geometric overlap and time window overlap in the collaborative work system, wherein the geometric overlap A is calculated by the ratio of the intersection and union of the three-dimensional spatial projection areas of the work areas of different types of work, and the time window overlap B is calculated by the ratio of the intersection of the time intervals occupied by different equipment resources to the total occupied time. When the geometric overlap exceeds the preset spatial threshold, the spatial conflict judgment is triggered, and when the time window overlap exceeds the preset time threshold, the time conflict judgment is triggered.

[0047] The geometric overlap degree A is calculated as A = Σ(S_i ∩ S_j) / ΣS_i, where S_i and S_j represent the three-dimensional spatial projection areas of different types of work areas. This can be achieved by calculating the polygon area overlap after the three-dimensional model surface is projected onto the same reference plane. Accurate intersection area data is generated through vertex coordinate interpolation and polygon Boolean operation algorithms. The time window overlap degree B is calculated as B = Σ(T_m ∩ T_n) / ΣT_m, where T_m and T_n represent the time intervals occupied by different device resources. This can be achieved by comparing timestamp intervals and accumulating overlapping durations. Conflict analysis results within continuous time periods are generated through device resource identifier matching and timeline mapping technology.

[0048] Specifically, during collaborative work, the three-dimensional geometric model reflects the three-dimensional boundary information of each type of work area in real time. After mapping the three-dimensional space to a two-dimensional plane through a projection algorithm, the polygon vertex coordinate set is used to calculate the area, dynamically capturing the physical interference areas of different types of work areas. At the same time, the equipment resource occupancy time data is analyzed through timestamp marking and duration period analysis to form an occupancy interval sequence based on the time axis. The time window overlap calculation model is used to quantify the competitive relationship of equipment resources in the time dimension. When the geometric overlap calculation result exceeds the preset threshold, it indicates that there is a non-negligible spatial interference risk; when the time window overlap calculation result exceeds the preset threshold, it indicates that there is an equipment resource scheduling conflict, and the system will trigger the conflict resolution mechanism.

[0049] Compared with existing technologies, traditional methods often use manual visual inspection or static schedules to determine conflicts, lacking quantitative calculations of the degree of interference in three-dimensional space, and relying solely on empirical estimates for equipment time window conflicts. This solution uses a dynamic calculation model of geometric overlap and time window overlap to convert the degree of spatial interference into a quantifiable proportional parameter and converts time conflicts into precise overlapping duration ratios, significantly improving the objectivity and accuracy of conflict detection. For example, existing technologies typically rely on two-dimensional plan drawings to determine spatial conflicts between tower crane booms and scaffolding work areas, which cannot reflect dynamic height changes during actual construction. However, this solution can accurately identify potential interference areas within a three-dimensional space through three-dimensional projection area calculations.

[0050] Through the above technical solution, this application effectively solves the technical problem of insufficient accuracy in detecting spatial and temporal conflicts in traditional construction management. It realizes the objective evaluation of the degree of conflict through a dual quantitative calculation model, provides precise input parameters for subsequent priority sorting and resource scheduling optimization, reduces the risk of process delays caused by human judgment errors, and improves the safety and efficiency of collaborative operations of multiple trades.

[0051] The present application further proposes that the generation process of the collaborative operation feasibility coefficient C includes: environmental parameter data including real-time monitoring values ​​of noise intensity, dust concentration and vibration amplitude; normalizing the deviation values ​​of each environmental parameter data from the preset safety threshold to generate a standardized deviation coefficient; obtaining the collaborative operation feasibility coefficient C by weighted fusion calculation of the deviation value and the standardized deviation coefficient; wherein C∈[0,1], a higher value indicates a higher risk of collaborative operation.

[0052] Environmental parameter data refers to the noise, dust, and vibration indicators of the construction site collected in real time by sensors. This can be achieved using decibel meters, particle concentration detectors, and accelerometers to quantify the safety impact of the working environment on the collaboration of multiple types of work. The standardized deviation coefficient refers to converting the difference between the measured value of each environmental parameter and the safety threshold into a dimensionless value. This can be achieved using the range method or the Z-score normalization algorithm to eliminate the interference of different physical dimensions on the comprehensive evaluation. Weighted fusion calculation refers to assigning weight coefficients based on the degree of impact of environmental parameters on construction safety. The weight ratio can be determined using the hierarchical analysis method or the entropy weight method to achieve coupled analysis of multi-dimensional parameters.

[0053] Specifically, during the collaborative work feasibility assessment, noise intensity, dust concentration, and vibration amplitude are monitored in real time and transmitted to the data processing module. When the instantaneous noise level in a particular work area exceeds a preset safety threshold, the deviation of that parameter is extracted and normalized, converting it into a comparable value between 0 and 1. The system then calculates the weighted sum of the normalized deviations of these three environmental parameters, based on the weight of dust's impact on visibility and vibration's effect on equipment stability, to generate the collaborative work feasibility coefficient, C.

[0054] Compared with existing technologies, traditional methods typically monitor only a single environmental parameter or employ fixed threshold alarm mechanisms, failing to quantify the impact of multiple coupled factors on collaborative operations. This solution, through normalization and weighted fusion, achieves a comprehensive, cross-dimensional analysis of noise, dust, and vibration parameters, generating dynamic risk assessment indicators.

[0055] Through the above technical solution, this application can identify environmental safety risks in real time during the collaborative operation of multiple trades, and accurately judge the feasibility of the operation through the quantitative evaluation coefficient C. When the C value exceeds the preset threshold, the system automatically triggers the priority sorting and resource reallocation mechanism to avoid work interruptions or safety accidents caused by deteriorating environmental conditions. For example, in the scenario of parallel operation of concrete pouring and steel structure installation, by continuously monitoring the impact of vibration amplitude on equipment positioning accuracy, the operation sequence of the two trades can be dynamically adjusted to ensure construction quality and personnel safety.

[0056] The present application further proposes that the generation process of the priority ranking table includes: constructing a multi-dimensional evaluation index system, including a construction progress urgency parameter, a quality impact weight coefficient, a resource scarcity index and a process complexity level; configuring the evaluation weight of each evaluation index, wherein the construction progress urgency parameter is inversely correlated with the remaining construction period, and the quality impact weight coefficient is positively correlated with the structural safety level; converting the evaluation indicators of each type of work into an evaluation value of a unified dimension through a standardization module; weightedly fusing the evaluation value and the evaluation weight to obtain a comprehensive score for each type of work, and generating a priority ranking table including conflicting types of work, in which the types of work in the table are arranged in descending order according to the comprehensive score.

[0057] Among them, the construction progress urgency parameter refers to a quantitative indicator that is dynamically adjusted based on the difference between the remaining construction period and the planned construction period. Specifically, the reverse time decay function can be used to map the remaining construction period into an urgency score interval. The quality impact weight coefficient refers to a parameter that is assigned according to the degree of influence of the work type on the safety level of the building structure. Specifically, a structural mechanics analysis model can be used to quantify the load transfer impact of different processes on key components. The resource scarcity index refers to a dynamic indicator that reflects the supply and demand relationship of equipment resources in a specific construction phase. Specifically, it can be generated by statistically analyzing the average waiting time and call frequency of similar resources through historical scheduling data. The process complexity level refers to a level parameter divided based on the process connection density and technical specification requirements in the work type operation process. Specifically, a process decomposition tree model can be used to count the number of standard operation steps and parallel operation constraints. The standardization module refers to a data processing unit that converts evaluation indicators of different dimensions into dimensionless values. Specifically, the range normalization algorithm or the Z-score normalization algorithm can be used to eliminate dimensional differences.

[0058] Specifically, during the collaborative work of multiple construction projects, when spatiotemporal conflicts are detected and the feasibility coefficient falls below a threshold, the system initiates a prioritization mechanism. First, the remaining construction period, structural safety relevance, equipment call records, and process parameters of each conflicting construction project are extracted from the project management database. The construction schedule urgency parameter, quality impact weight coefficient, resource scarcity index, and process complexity level are calculated. The construction schedule urgency parameter is calculated in descending order based on the remaining construction period. For example, processes with a remaining construction period of less than three days are assigned a higher urgency score. The quality impact weight coefficient is matched using a structural safety level mapping table. For example, processes involving load-bearing wall construction are assigned a higher weight. Subsequently, a standardization module converts the raw data from the four dimensions into evaluation values ​​ranging from 0 to 1 to ensure comparability across different indicators. During the weighted fusion phase, the system dynamically adjusts the weighting based on the current project stage, for example, increasing the weighting of the quality impact coefficient during the main structure construction phase. The resulting priority ranking table is sorted in descending order by comprehensive score, providing a basis for subsequent decision-making regarding spatial repartitioning and time window reallocation.

[0059] Compared to existing technologies, traditional construction management systems typically use fixed priority rules or single-dimensional indicators to prioritize conflicting work types, failing to dynamically adapt to changes in project phases and the impact of multiple factors. This solution, by building a multidimensional evaluation system encompassing progress, quality, resources, and process, combined with standardization and a dynamic weighting mechanism, achieves multi-dimensional quantification and dynamic adaptation of priority determination, effectively addressing the significant deviation in priority decision-making in complex construction scenarios often associated with traditional methods.

[0060] Through the above technical solution, this application can generate an accurate priority ranking table based on a multi-dimensional dynamic evaluation system when conflicts occur in collaborative work of multiple trades, provide an objective decision-making basis for resource reallocation, thereby reducing the subjective errors of manual experience judgment, improving the collaborative efficiency of space planning and time scheduling, and ensuring that the quality control and progress requirements of key processes are prioritized.

[0061] This application further proposes that the process of spatial redivision includes retaining the original work area topology for jobs with a priority higher than a preset level, and performing area shrinkage operations on low-priority jobs, with the shrinkage amplitude being inversely proportional to the comprehensive score difference; the process of time window redistribution includes allocating continuous time window core segments to high-priority jobs, and allocating discrete time periods containing buffer intervals to low-priority jobs.

[0062] The priority ranking table is a ranked list of conflicting work types generated based on multidimensional evaluation indicators. This can be achieved using a weighted fusion algorithm that combines construction schedule urgency parameters, quality impact weight coefficients, resource scarcity indexes, and process complexity levels. This algorithm quantifies the decision weights of different work types in the conflict resolution process. Topological structure preservation during spatial redivision maintains the spatial form and geometric relationships of the original work areas of high-priority work types. This can be achieved through a polygon vertex coordinate interpolation algorithm to avoid secondary conflicts caused by spatial adjustments to high-value processes. The magnitude of the area shrinkage operation is inversely proportional to the difference in comprehensive scores, meaning that the reduction ratio of the work area of ​​low-priority work types decreases as the difference in their comprehensive scores increases compared to high-priority work types. This can be achieved by setting a piecewise linear function to constrain the shrinkage amount, ensuring that resource adjustments adhere to the principle of maximizing project efficiency. The core segment of the continuous time window allocates uninterrupted, continuous work periods to high-priority work types. This can be achieved through a time series sliding window algorithm to extract the periods with the lowest equipment resource occupancy density, ensuring the continuous construction of critical processes. Among them, the discrete period buffer interval refers to the mandatory insertion of idle time between the working periods of low-priority jobs. Specifically, the time axis segmentation algorithm can be used to generate non-continuous periods containing preset safety intervals to prevent conflicts in the use of equipment resources.

[0063] Specifically, when a spatial or temporal conflict is detected, the system first calls a priority sorting table to determine the decision order for the conflicting work types. For spatial conflicts, the topological structure of the work area for high-priority work types is retained, while dynamic area contraction is performed on low-priority work types based on the comprehensive score difference. The contraction magnitude is automatically calculated using a preset score difference-contraction amount mapping relationship, ensuring that high-value processes are not affected by spatial compression. For temporal conflicts, a time window segmentation strategy is adopted, dividing the equipment resource occupancy time axis into core segments and buffer interval segments. High-priority work types are preferentially assigned continuous core segments, while low-priority work types can only select discrete windows containing buffer intervals within the remaining time period. The duration of these buffer intervals is negatively correlated with the work type's comprehensive score. For example, in a conflict scenario between concrete pouring and steel structure installation, if the pouring process receives higher priority due to schedule urgency, its work area boundaries remain unchanged, while the steel structure installation area contracts in proportion to the score difference. Simultaneously, the pouring equipment receives continuous crane resource usage, while the steel structure installation process is assigned to fragmented time periods containing equipment cooling intervals.

[0064] Compared to existing technologies, traditional approaches often employ fixed-ratio compression strategies when adjusting space, forcing high-value processes to cede operating space. This solution, by dynamically controlling the contraction amplitude, optimizes resources while ensuring the spatial integrity of critical processes. Existing scheduling technologies often rely on first-come, first-served or manually assigned priorities, failing to dynamically allocate continuous operating windows based on real-time evaluation metrics. This solution incorporates a buffer interval generation mechanism that effectively avoids safety hazards caused by competition for equipment resources.

[0065] Through the above technical solution, this application solves the problem of process interruption and resource waste caused by rigid adjustment strategies in the collaborative operation of multiple types of work, and realizes the flexible allocation of spatial resources and time windows in the conflict resolution process. Through the coordinated control of dynamic shrinkage amplitude and buffer interval, it not only guarantees the continuous operation conditions of high-priority processes, but also provides low-priority types of work with an operation window that complies with safety regulations, effectively reducing the construction safety risks caused by spatial overlap or equipment preemption. At the same time, the nonlinear adjustment mechanism based on the score difference avoids the loss of engineering benefits caused by traditional equal resource allocation.

[0066] The present application further proposes output control instructions including generating trajectory offset instructions for construction equipment with spatial conflicts, the instructions including the equipment movement direction and minimum safety distance; generating operation interval instructions for equipment resources with time conflicts, the instructions including the start and end marks of the buffer time period.

[0067] Among them, trajectory offset instructions refer to eliminating physical interference between devices through spatial position adjustment. Specifically, this can be achieved by using the Beidou navigation differential positioning system or UWB ultra-wideband positioning technology to realize vector calculation of the device movement direction. In combination with the minimum safe distance parameters in the BIM model, the device movement path is generated, which is used to plan the device obstacle avoidance trajectory in three-dimensional space. Operation interval instructions refer to avoiding timing conflicts of equipment resources through time segment adjustment. Specifically, this can be achieved by using a discrete event scheduling algorithm to realize dynamic allocation of buffer time periods. In combination with the Gantt chart model of the construction schedule, time window start and end marks are generated to embed safe intervals in the process connection.

[0068] Specifically, when a spatial conflict is determined, the process for generating trajectory offset instructions includes: extracting the spatial coordinate sets of the conflicting devices based on a three-dimensional geometric model, calculating the interference area between devices using a convex hull collision detection algorithm, and iteratively solving the optimal solution for the device's movement direction using a gradient descent method so that the path after movement meets the minimum safe distance constraint. For temporal conflict scenarios, the process for generating operation interval instructions includes: identifying overlapping time periods in the time series distribution, dividing the continuous operation time periods using a sliding window algorithm, shifting the operation time periods of low-priority tasks to the rear based on the device resource priority, and inserting buffer interval markers between adjacent operation windows to avoid timing confusion caused by the superposition of device start and stop actions.

[0069] Compared with existing technologies, traditional construction scheduling systems often rely on manual marking of conflict areas and adjustment of equipment positions, which suffers from low adjustment accuracy and slow response speed. This solution automatically generates vectorized movement directions and precise time window markers, achieving millimeter-level calibration of equipment trajectories and second-level optimization of process connections, eliminating the risk of secondary conflicts caused by manual intervention. Furthermore, the dynamic adaptation mechanism of the minimum safety distance parameter and the buffer time period is more adaptable to the dynamic changes in complex construction scenarios than fixed-threshold conflict resolution strategies.

[0070] Through the above technical solution, this application can effectively eliminate the risk of physical interference during equipment movement, ensuring safe operation of equipment in cross-operation areas. It also precisely controls the timing of equipment starts and stops, avoiding resource competition caused by multiple types of work performed in parallel. The spatial constraints of trajectory offset instructions and the temporal constraints of operation interval instructions form a dual guarantee mechanism, improving the reliability and execution efficiency of construction collaboration in multiple dimensions.

[0071] The present application further proposes that the process of the dynamic optimization cycle includes: constructing a historical record library of work area adjustment, storing a set of adjustment parameters for each spatial redivision, including the spatial adjustment amount ΔS, the time window offset ΔT and the corresponding feasibility coefficient change ΔC, and associating and recording the geometric overlap A' and environmental parameter data when the adjustment parameters are triggered; establishing an adjustment efficiency evaluation function E = α·ΔS+β·ΔT-γ·ΔC based on the correlation relationship between ΔS, ΔT and ΔC, where α and β are the spatial and temporal adjustment weight coefficients, respectively, and γ is the feasibility improvement sensitivity coefficient; screening historical parameter groups that meet the ΔC_preset improvement threshold and ΔS_current area ratio constraints, and generating a classification optimization strategy from the historical parameter groups.

[0072] Among them, the adjustment parameter set refers to the quantitative adjustment indicators generated in each spatial redivision operation. Specifically, a database can be used to store the spatial adjustment amount, time window offset, and feasibility coefficient change of each adjustment, and a structured data table can be used to achieve persistent storage of historical operation records. The adjustment efficiency evaluation function refers to a mathematical model that quantitatively evaluates the impact of spatial and temporal adjustments on the feasibility of collaborative operations. Specifically, a linear weighted method can be used to correlate and calculate the spatial adjustment amount, time window offset, and feasibility coefficient change. The coefficient configuration of parameters α, β, and γ can be used to achieve adjustment efficiency evaluation in different dimensions. The classification optimization strategy refers to a differentiated optimization scheme generated based on historical adjustment data. Specifically, a data mining algorithm can be used to perform cluster analysis on historical parameter groups that meet preset conditions, and spatial optimization strategies and temporal optimization strategies can be generated based on the correlation between parameters.

[0073] Specifically, during the dynamic optimization cycle, the historical record library continuously accumulates the spatial adjustment value ΔS, the time window offset ΔT, and the feasibility coefficient change ΔC for each adjustment operation. It also associates and stores the geometric overlap A' and environmental parameter data at the time the adjustment was triggered. The adjustment effectiveness evaluation function E = α·ΔS + β·ΔT - γ·ΔC quantifies and integrates the impact of adjustments in different dimensions through coefficient configuration. The spatial adjustment weight coefficient α and the temporal adjustment weight coefficient β are dynamically adjusted based on the characteristics of the project phase, and the feasibility improvement sensitivity coefficient γ is used to balance the adjustment amplitude with the safety threshold. The screening module extracts valid parameter sets from historical data based on the constraints of ΔC_preset improvement threshold and ΔS_region area ratio. By analyzing the correlation patterns among ΔS, ΔT, and ΔC in the parameter sets, it generates gradient adjustment schemes for spatial optimization or phase control rules for temporal optimization, forming a data-driven classification optimization strategy.

[0074] Compared to existing technologies, traditional construction management systems lack mechanisms for accumulating and analyzing historical operational data for optimization decisions. Adjustment strategies are often isolated and based on single conflict scenarios. This solution, by building a historical record library and performance evaluation model, can identify the impact of different adjustment parameters on the feasibility of collaborative work. This allows for the generation of a classification strategy with continuous optimization capabilities, avoiding repeated and inefficient adjustment operations.

[0075] Through the above technical solution, this application can implement dynamic optimization strategy iteration based on historical data, effectively improving the decision-making efficiency of spatial redivision and time window reallocation. By quantitatively evaluating the impact of adjustment parameters on the feasibility coefficient, high-value adjustment patterns can be accurately identified, reducing resource loss caused by ineffective adjustments. The generation mechanism of classified optimization strategies enables the system to automatically adapt the optimal adjustment plan for different conflict types, significantly shortening the response period of the dynamic optimization loop.

[0076] This application further proposes that the process of generating a classification optimization strategy from a historical parameter group includes: a spatial optimization strategy: extracting a parameter group with positive correlation between ΔS and ΔC, and generating a spatial redivision scheme for the gradient adjustment step; a temporal optimization strategy: extracting a parameter group with negative correlation between ΔT and ΔC, and generating a time window compression scheme containing phase control rules.

[0077] The spatial optimization strategy is a spatial adjustment plan based on the positive correlation between the amount of spatial adjustment and the degree of feasibility improvement in historical adjustment parameters. This can be implemented using a gradient adjustment step size algorithm, dynamically setting the magnitude of each spatial contraction or expansion based on the strength of the correlation between ΔS and ΔC. This strategy achieves precise optimization of spatial partitioning by quantifying the impact of spatial adjustments on the feasibility of collaborative operations.

[0078] A time optimization strategy is a time scheduling scheme based on the negative correlation between time window offsets and feasibility improvements. This strategy can be implemented using phase control rules. By compressing time windows during high-conflict periods and reallocating discrete time slots, it reduces overlap in equipment operations. This strategy leverages the ability of time adjustments to suppress safety risks and establishes a dynamic compression mechanism for time windows.

[0079] Specifically, during the execution of the spatial optimization strategy, if the system detects a positive correlation between ΔS (spatial adjustment) and ΔC (feasibility coefficient change), indicating that larger spatial adjustments lead to more significant feasibility improvements, a repartitioning scheme with a gradient adjustment step size will be automatically generated. For example, if there is a spatial conflict between the tower crane operation area and the rebar processing area, the system analyzes the correlation between area contraction and safety risk reduction in historical adjustment records to calculate the optimal gradient step size, gradually reducing the spatial scope of the low-priority work area.

[0080] The implementation of the time optimization strategy is reflected in the processing of the negatively correlated parameter group ΔT (time window offset) and ΔC. When the system discovers an inverse correlation between time window compression and improved feasibility, such as in scenarios where there is a time conflict between concrete pouring equipment and transportation equipment, it uses phase control rules to break the core operation period into multiple discrete windows and insert buffer intervals between them. This approach ensures the continuous operation requirements of high-priority jobs while reducing environmental safety risks through time fragmentation.

[0081] Compared to existing technologies, traditional optimization methods typically use fixed adjustment steps or empirical time window partitioning, lacking quantitative analysis of historical adjustment effects. Existing time scheduling schemes often only consider equipment utilization metrics and fail to dynamically link changes in environmental safety parameters with time adjustments. This solution achieves precise matching of spatial and temporal optimization by constructing a correlation model between adjustment parameters and feasibility coefficients.

[0082] Through the above-mentioned technical solution, this application effectively solves the technical problem of mismatch between adjustment amplitude and safety effect during dynamic optimization, avoids equipment operation risks caused by excessive space compression, and eliminates idle resources caused by rigid time window cutting. Through a data-driven classification optimization strategy, this solution improves the efficiency of multi-task collaborative work while ensuring construction safety.

[0083] Example 2:

[0084] like Figure 3 As shown, the multi-trade collaborative operation method for construction engineering driven by the intelligent construction platform includes the following steps:

[0085] Acquire spatial data of each work area, equipment resource occupancy time data, and environmental parameter data through multi-dimensional sensing units;

[0086] Build a 3D geometric model of the work area based on spatial data and equipment resource occupancy time data, and generate a time series distribution of equipment resource occupancy;

[0087] The geometric overlap A of different types of work areas is calculated based on the 3D geometric model, and the time window overlap B is calculated based on the time series distribution of equipment resource usage.

[0088] When the geometric overlap A exceeds the preset spatial threshold, it is determined that there is a spatial conflict; when the time window overlap B exceeds the preset time threshold, it is determined that there is a temporal conflict;

[0089] A multi-dimensional coupling analysis is performed by combining environmental parameter data with preset safety thresholds to calculate the collaborative work feasibility coefficient C. If the feasibility coefficient C exceeds the preset collaborative work threshold, a priority ranking table containing conflicting work types is generated. Based on the priority ranking table, the work areas of work types with time and space conflicts are spatially redistributed and time windows reallocated.

[0090] Output control instructions to construction equipment, and adjust the work area division and equipment working time window according to the control instructions;

[0091] After executing the control instructions, the updated spatial data and environmental parameter data are re-collected and input into the three-dimensional geometric model for iterative calculation to generate a new geometric overlap A' and time window overlap B'; when A' or B' exceeds the corresponding preset percentage, the dynamic optimization cycle of the collaborative operation plan is triggered.

[0092] The above content is merely an example and explanation of the structure of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the scope of protection of the present invention.

[0093] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0094] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. The multi-type collaborative operation system for construction projects driven by the intelligent construction platform is characterized by: include: The data acquisition module is used to obtain spatial data of each work area, equipment resource occupancy time data and environmental parameter data through a multi-dimensional sensing unit; A data processing module is used to construct a three-dimensional geometric model of the work area based on the spatial data and the equipment resource occupancy time data, and generate a time series distribution of the equipment resource occupancy; A conflict judgment module is used to calculate the geometric overlap A of different types of work areas based on the three-dimensional geometric model, and to calculate the time window overlap B based on the time series distribution of equipment resource usage; when the geometric overlap A exceeds a preset spatial threshold, it is determined that a spatial conflict exists; When the time window overlap B exceeds the preset time threshold, it is determined that there is a time conflict; The conflict resolution module is used to combine environmental parameter data with preset safety thresholds for multi-dimensional coupling analysis and calculate the collaborative operation feasibility coefficient C; If the feasibility coefficient C exceeds the preset collaborative work threshold, a priority ranking table containing conflicting work types is generated, and the work areas of the work types with time and space conflicts are spatially redistributed and time windows are reallocated based on the priority ranking table; An output control module, configured to output control instructions to the construction equipment and adjust the division of the working area and the working time window of the equipment according to the control instructions; The dynamic optimization module is used to re-collect the updated spatial data and environmental parameter data after executing the control instructions and input them into the three-dimensional geometric model for iterative calculation to generate new geometric overlap A' and time window overlap B'; when A' or B' exceeds the corresponding preset percentage, the dynamic optimization cycle of the collaborative operation plan is triggered.

2. The multi-trade collaborative operation system for construction projects driven by an intelligent construction platform according to claim 1 is characterized in that: The construction process of the three-dimensional geometric model includes: The spatial data of the work area is converted into a set of polygon vertex coordinates. When constructing a three-dimensional geometric model, a vertex coordinate interpolation algorithm is used to generate a three-dimensional geometric model with topological relationships. The time series distribution includes a device resource identifier, a start timestamp, and a duration period.

3. The multi-trade collaborative operation system for construction engineering driven by an intelligent construction platform according to claim 1 is characterized in that: The calculation formula of the geometric overlap degree A is A=Σ(S_i∩S_j) / ΣS_i, where S_i and S_j represent the three-dimensional spatial projection area of ​​the working areas of different types of work respectively; The calculation formula of the time window overlap B is B=Σ(T_m∩T_n) / ΣT_m, where T_m and T_n represent the time intervals occupied by different device resources respectively.

4. The multi-trade collaborative operation system for construction engineering driven by an intelligent construction platform according to claim 1 is characterized in that: The process of generating the collaborative operation feasibility coefficient C includes: The environmental parameter data includes real-time monitoring values ​​of noise intensity, dust concentration and vibration amplitude; Normalize the deviation of each environmental parameter data from the preset safety threshold to generate a standardized deviation coefficient; The collaborative operation feasibility coefficient C is obtained by weighted fusion calculation of the deviation value and the standardized deviation coefficient; where C∈[0,1], a higher value indicates a higher risk of collaborative operation.

5. The construction engineering multi-trade collaborative operation system driven by the intelligent construction platform according to claim 1 is characterized in that: The process of generating a priority list includes: Construct a multi-dimensional evaluation index system, including construction progress urgency parameters, quality impact weight coefficients, resource scarcity index and process complexity level; Configure the evaluation weights of each evaluation indicator, where the construction progress urgency parameter is inversely correlated with the remaining construction period, and the quality impact weight coefficient is positively correlated with the structural safety level; Convert the evaluation indicators of each type of work into evaluation values ​​of unified dimensions through the standardization module; The evaluation value and the evaluation weight are weighted and integrated to obtain the comprehensive score of each type of work, and a priority ranking table containing conflicting types of work is generated, in which the types of work are arranged in descending order according to the comprehensive score.

6. The multi-trade collaborative operation system for construction projects driven by an intelligent construction platform according to claim 5 is characterized in that: The spatial redivision process includes: retaining the original work area topology for jobs with a priority higher than a preset level, and performing a region shrinking operation on jobs with a lower priority, with the shrinkage being inversely proportional to the difference in the comprehensive score; The time window reallocation process includes: allocating continuous time window core segments to high-priority jobs, and allocating discrete time periods including buffer intervals to low-priority jobs.

7. The construction engineering multi-trade collaborative operation system driven by the intelligent construction platform according to claim 1 is characterized in that: The output control instructions include: Generate a trajectory offset instruction for construction equipment with spatial conflicts, the instruction including the equipment movement direction and minimum safety distance; A job interval instruction is generated for the device resource with time conflict, wherein the instruction includes the start and end marks of the buffer time period.

8. The intelligent construction platform-driven construction engineering multi-trade collaborative operation system according to claim 1 is characterized in that: The process of the dynamic optimization cycle includes: Build a history record library of work area adjustment, store the adjustment parameter set for each spatial redivision, including the spatial adjustment amount ΔS, the time window offset ΔT, and the corresponding feasibility coefficient change ΔC, and associate the geometric overlap A' and environmental parameter data when the adjustment parameters are triggered; Based on the correlation between ΔS, ΔT and ΔC, the adjustment effectiveness evaluation function E = α·ΔS + β·ΔT - γ·ΔC is established, where α and β are the spatial and temporal adjustment weight coefficients, respectively, and γ is the feasibility improvement sensitivity coefficient. The historical parameter groups that satisfy the constraints of ΔC>preset improvement threshold and ΔS<current regional area ratio are screened, and the classification optimization strategy is generated based on the historical parameter groups.

9. The intelligent construction platform-driven construction engineering multi-trade collaborative operation system according to claim 8 is characterized in that: The process of generating a classification optimization strategy from a historical parameter group includes: Spatial optimization strategy: extract the parameter group with positive correlation between ΔS and ΔC, and generate a spatial redivision scheme for gradient adjustment step size; Time optimization strategy: Extract the parameter group with negative correlation between ΔT and ΔC and generate a time window compression scheme containing phase control rules.

10. A method for collaborative working of multiple types of construction projects driven by an intelligent construction platform based on the system according to any one of claims 1 to 9, characterized in that: The following steps are involved: Acquire spatial data of each work area, equipment resource occupancy time data, and environmental parameter data through multi-dimensional sensing units; Constructing a three-dimensional geometric model of the work area based on the spatial data and the equipment resource occupancy time data, and generating a time series distribution of equipment resource occupancy; Calculate the geometric overlap A of different types of work areas based on the three-dimensional geometric model, and calculate the time window overlap B based on the time series distribution of equipment resource occupancy; When the geometric overlap A exceeds the preset spatial threshold, it is determined that there is a spatial conflict; When the time window overlap B exceeds the preset time threshold, it is determined that there is a time conflict; Combine environmental parameter data with preset safety thresholds to conduct multi-dimensional coupling analysis and calculate the collaborative operation feasibility coefficient C; If the feasibility coefficient C exceeds the preset collaborative work threshold, a priority ranking table containing conflicting work types is generated, and the work areas of the work types with time and space conflicts are spatially redistributed and time windows are reallocated based on the priority ranking table; Output control instructions to construction equipment, and adjust the work area division and equipment working time window according to the control instructions; After executing the control instructions, the updated spatial data and environmental parameter data are re-collected and input into the three-dimensional geometric model for iterative calculation to generate a new geometric overlap A' and time window overlap B'; when A' or B' exceeds the corresponding preset percentage, the dynamic optimization cycle of the collaborative operation plan is triggered.

Images