Multi-monomer engineering intelligent time sequence optimization method, system and device and storage medium
By using component spatiotemporal matrices and AI optimization algorithms, the problems of spatiotemporal conflicts and resource inefficiency in large-scale engineering projects have been solved, enabling intelligent optimization and dynamic adjustment of construction progress.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-10
- Publication Date
- 2026-03-27
AI Technical Summary
In large and complex engineering projects, the cross-construction of multiple units, disciplines, and processes leads to frequent time and space conflicts, inefficient resource allocation, and difficulty in predicting and optimizing the potential for schedule delays.
A spatiotemporal matrix is generated by using component numbers, spatial information, and temporal information. AI intelligent software is used to calculate potential conflict points, and reinforcement learning algorithms are combined to adjust the construction schedule and optimize the construction sequence.
Early detection of potential conflicts reduces resource waiting time, improves construction efficiency and schedule reliability, and dynamically adapts to changes in the construction site.
Smart Images
Figure CN121745526A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intelligent construction and engineering construction management technology, and specifically to a method, system, equipment and storage medium for intelligent time-series optimization of multi-unit engineering projects. Background Technology
[0002] In large and complex engineering projects, the overlapping construction of multiple units, disciplines, and processes is extremely common. Traditional construction schedules (such as Gantt charts and network diagrams) rely heavily on the experience of the project manager, making it difficult to fully consider the coupling relationship between spatial and temporal conflicts. This often leads to the following problems on the construction site: Frequent spatial and temporal conflicts: Conflicts in the operation of different professional teams in the same spatial area at different time periods lead to idle time and rework. Inefficient resource allocation: Resources such as hoisting equipment and construction access are waiting due to space conflicts, resulting in low utilization rates; Potential delays: Hidden bottlenecks (such as errors in process logic or overlapping space usage) are difficult to detect in advance, causing a chain reaction of delays.
[0003] While existing 4D-BIM technology can simulate progress, it is mostly limited to visualization and lacks the ability to intelligently predict and automatically optimize for spatiotemporal conflicts. Summary of the Invention
[0004] The purpose of this invention is to overcome the shortcomings of existing technologies and provide a method, system, device, and storage medium for intelligent time-series optimization of multi-unit engineering projects. This addresses the problems of frequent spatiotemporal conflicts at construction sites, inefficient resource allocation, and difficulty in detecting potential schedule delays. The technical solution to achieve the above objective is as follows:
[0005] A method for intelligent time-series optimization of multi-unit engineering projects includes the following steps: numbering components according to a construction schedule and obtaining spatial and temporal information of the components; inputting the component numbers, spatial information, and temporal information into a BIM model to generate a spatiotemporal matrix; calculating spatiotemporal intersection points using AI intelligent software based on the spatiotemporal matrix to obtain potential conflict points; identifying key bottlenecks among the potential conflict points based on construction logic relationships; adjusting the time sequence of the components associated with the key bottlenecks based on a reinforcement learning algorithm to optimize the construction schedule and outputting the optimized construction schedule.
[0006] In this invention, a method for intelligent time-series optimization of multi-unit engineering projects is proposed. By calculating the spatiotemporal matrix of components, hidden conflicts that are difficult to identify manually can be discovered in advance. Based on reinforcement learning algorithms, a time-series optimized construction schedule is automatically generated, reducing resource waiting time and improving the reliability of the construction period.
[0007] A further improvement of the intelligent time-series optimization method for multi-unit engineering of the present invention is that the time information includes start time, end time, time interval and resource requirement type.
[0008] A further improvement of the intelligent temporal optimization method for multi-unit engineering of the present invention is that the step of inputting the component's number, spatial information and temporal information into the BIM model to generate a spatiotemporal matrix includes: in the BIM model, mapping the temporal information of the component to the spatial information.
[0009] A further improvement of the intelligent temporal optimization method for multi-unit engineering of the present invention is that the step of calculating the spatiotemporal intersection point and obtaining the potential conflict point by using AI intelligent software based on the spatiotemporal matrix includes: obtaining the temporal overlap of different components in the same space based on the spatial information and the temporal information corresponding to the components.
[0010] A further improvement of the intelligent time-series optimization method for multi-unit engineering projects of the present invention is that finding key bottlenecks in the potential conflict points according to the construction logic relationship includes: analyzing the construction logic relationship using a graph neural network, screening out the key bottlenecks, and generating an analysis report.
[0011] A further improvement of the intelligent time-series optimization method for multi-unit engineering of the present invention is that finding key bottlenecks in the potential conflict points according to the construction logic relationship includes: providing dynamic early warning for the key bottlenecks that appear.
[0012] A further improvement of the intelligent time-series optimization method for multi-unit engineering projects of the present invention is that the step of adjusting the time sequence of the components associated with the key bottleneck based on the reinforcement learning algorithm, optimizing the construction schedule, and outputting the optimized construction schedule includes: when adjusting the time sequence of the components, using a reward function to evaluate the construction period and resource efficiency corresponding to the adjustment, and selecting the optimal solution as the optimized construction schedule.
[0013] This invention discloses a multi-unit engineering intelligent time-series optimization system, comprising: a spatiotemporal data management module, which generates a spatiotemporal matrix by mapping the spatial and temporal information of construction components; a spatiotemporal conflict detection module connected to the spatiotemporal data management module, which calculates spatiotemporal intersection points based on the spatiotemporal matrix and identifies potential conflict points; an AI intelligent analysis module connected to the spatiotemporal conflict detection module, which integrates graph neural network (GNN) and reinforcement learning (RL) algorithms to find key bottlenecks among the potential conflict points and optimize the construction schedule; and a dynamic monitoring and early warning module connected to the AI intelligent analysis module and the spatiotemporal data management module, which collects data to update the spatiotemporal matrix and provides dynamic early warnings for the key bottlenecks that appear.
[0014] The present invention provides a timing optimization device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the aforementioned intelligent timing optimization method for multi-unit engineering.
[0015] The present invention discloses a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the above-described intelligent timing optimization method for multi-unit engineering. Attached Figure Description
[0016] Figure 1 This is a flowchart illustrating a multi-unit engineering intelligent timing optimization method according to the present invention.
[0017] Figure 2 This is a flowchart illustrating step S120 of the present invention.
[0018] Figure 3 This is a flowchart illustrating step S130 of the present invention.
[0019] Figure 4 This is a flowchart illustrating step S140 of the present invention.
[0020] Figure 5 This is another schematic diagram of step S140 of the present invention.
[0021] Figure 6 This is a flowchart illustrating step S150 of the present invention.
[0022] Figure 7 This is a schematic diagram of the structure of a multi-unit engineering intelligent timing optimization system according to the present invention.
[0023] Figure 8 This is a schematic diagram of the structure of a timing optimization device according to the present invention. Detailed Implementation
[0024] The present invention will be further described below with reference to the accompanying drawings and specific embodiments. (See attached drawings.) Figure 1 The diagram shows a flowchart of a multi-unit engineering intelligent timing optimization method according to the present invention.
[0025] This invention provides a multi-unit engineering intelligent timing optimization method, comprising:
[0026] Step S110: Number the components according to the construction schedule and obtain the spatial and temporal information of the components.
[0027] During the construction process, each construction component has a corresponding time attribute and associated spatial coordinate information. The component can be a beam or a column on the construction site, without specific restrictions. Next, step S120 is executed.
[0028] Step S120: Input the component number, spatial information and time information into the BIM model to generate a spatiotemporal matrix.
[0029] In the BIM model, each component is assigned corresponding spatial coordinates and time attributes, a spatiotemporal matrix is constructed, and time information is associated with spatial information. Then, step S130 is executed.
[0030] Step S130: Based on the spatiotemporal matrix, use AI intelligent software to calculate the spatiotemporal intersection points to obtain potential conflict points.
[0031] Among them, based on the spatial coordinates and temporal attributes of the components, the spatiotemporal intersection points are calculated to identify potential conflicts. The spatiotemporal intersection points are conflicts caused by multiple trades working simultaneously in the same area or by equipment passage occupancy, such as the cross-interference between high-altitude operations and ground transportation during construction, which can easily affect the construction progress and make it difficult to ensure construction safety. Then, step S140 is executed.
[0032] In this implementation method, during spatiotemporal cross-analysis, spatiotemporal cross-points can be identified quickly and efficiently using computational geometry algorithms, such as AABB bounding box cross-detection, to initially screen out all spatially overlapping component pairs and their time intervals. This significantly reduces the computational scope of subsequent complex algorithms and improves overall efficiency.
[0033] Step S140: Based on the construction logic, identify the key bottlenecks among potential conflict points.
[0034] In this process, by combining the spatiotemporal matrix, key bottlenecks are predicted, such as resource bottlenecks and process logic errors. Then, step S150 is executed.
[0035] Execution step S150: Based on the reinforcement learning algorithm, adjust the timing of components associated with key bottlenecks, optimize the construction schedule, and output the optimized construction schedule.
[0036] Among them, based on reinforcement learning algorithms, with the goal of minimizing the total project duration and balancing resources, the timing is automatically adjusted, and the optimized schedule and space usage scheme are output.
[0037] In this implementation, the optimized construction schedule is executed, and the data within the spatiotemporal matrix is dynamically updated based on construction progress feedback. This supports real-time updates and re-optimization of construction progress data, enabling it to handle unforeseen on-site situations and demonstrating strong adaptability. By optimizing the construction schedule through the above steps until construction is completed, potential conflicts can be identified in advance, reducing resource waiting time, improving construction efficiency, and shortening construction time.
[0038] This invention provides a method for intelligent time-series optimization of multi-unit engineering projects, where time information includes start time, end time, time interval, and resource requirement type.
[0039] The start time and end time correspond to the earliest start time and the latest end time of construction, respectively. The time interval corresponds to the construction period of the component, and the time unit is uniformly set to hours or days.
[0040] See Figure 2 The diagram shows a flowchart of step S120 of the present invention. The present invention provides a multi-unit engineering intelligent timing optimization method, step S120 including:
[0041] Step S121: In the BIM model, map the time information of the components to their spatial information.
[0042] This involves exporting a model containing geometric information from BIM software (such as Revit), exporting time data from scheduling software (such as Project / P6), and then linking and mapping them through the spatiotemporal data management module.
[0043] The spatiotemporal matrix displays the occupancy status of a component in a specific spatial region at a specific point in time from multiple dimensions. The time unit in the time dimension can be either hours or days, each with a corresponding date sequence; no specific restrictions are imposed here.
[0044] See Figure 3 The diagram shows a flowchart of step S130 of the present invention. The present invention provides a multi-unit engineering intelligent timing optimization method, wherein step S130 includes:
[0045] Execution step S131: Based on the spatial and temporal information corresponding to the components, obtain the temporal overlap of different components in the same space.
[0046] The spatiotemporal conflict detection engine calculates the daily spatial occupancy of each component, identifies overlapping time periods and spatial regions, and generates a preliminary conflict list. Based on the spatial coordinates and temporal attributes of the components, it calculates the temporal overlap of different components in the same spatial region and identifies potential conflict points.
[0047] In this embodiment, all space-occupying components are statistically obtained each day, and the components are checked in pairs to determine whether there is any space overlap. The components, dates, and regions corresponding to the conflict events are recorded and arranged in chronological order to generate a preliminary conflict list.
[0048] See Figure 4 The diagram shows a flowchart of step S140 of the present invention. The present invention provides a multi-unit engineering intelligent timing optimization method, wherein step S140 includes:
[0049] Step S141: Use graph neural networks to analyze the construction logic relationships, identify key bottlenecks, and generate an analysis report.
[0050] Specifically, the process involves using GNN to analyze logical relationships and identify all potential conflict points. Reinforcement learning algorithms are then used to iteratively optimize the timing sequence and output the optimal solution, thus identifying the key bottlenecks. The analysis report can be presented through simulated animations.
[0051] In this embodiment, a graph neural network (GNN) is used to treat the construction schedule as a graph consisting of "process nodes" and "logical relationship edges". GNN can deeply analyze the network topology, not only identifying surface conflicts, but also predicting chain reaction bottlenecks that may be caused by process logical constraints, such as resource squeeze caused by critical path delays.
[0052] See Figure 5 This illustrates another flowchart of step S140 of the present invention. The present invention provides a multi-unit engineering intelligent timing optimization method, wherein step S140 further includes:
[0053] Execution step S142: Provide dynamic early warning for key bottlenecks that appear.
[0054] During the construction process, early warnings are issued for components related to key bottlenecks.
[0055] In this implementation, during construction, actual progress data can be compared with planned progress data. If the deviation exceeds a preset threshold, an early warning is automatically triggered, and management personnel are notified via mobile device. Furthermore, based on new on-site data, a re-optimization process can be automatically initiated to quickly generate an optimized construction schedule based on the current situation, thereby dynamically adapting to various uncertainties on the construction site (such as weather, equipment failure, and material delays).
[0056] See Figure 6 The diagram shows a flowchart of step S150 of the present invention. The present invention provides a multi-unit engineering intelligent timing optimization method, step S150 including:
[0057] Step S151: When adjusting the timing of components, use the reward function to evaluate the corresponding construction period and resource efficiency after adjustment, and select the optimal solution as the optimized construction schedule.
[0058] The process involves making decisions on the timing of components by an intelligent agent, analyzing the corresponding construction period and resource efficiency after the adjustments, and adjusting the timing of components based on reward signals to obtain the optimal solution for the construction schedule.
[0059] This invention provides a multi-unit engineering intelligent timing optimization system, comprising:
[0060] The spatiotemporal data management module 100 is used to correlate the spatial and temporal information of construction components and generate a spatiotemporal matrix.
[0061] The spatiotemporal data management module 100 connects to BIM software and scheduling software, exporting models containing geometric information from BIM software (such as Revit) to obtain spatial data, and exporting time data from scheduling software (such as Project / P6).
[0062] The spatiotemporal conflict detection module 200, which is connected to the spatiotemporal data management module 100, is used to calculate spatiotemporal intersection points based on the spatiotemporal matrix and identify potential conflict points.
[0063] Among them, the spatiotemporal conflict detection module 200 calculates the daily space occupancy of each component through the spatiotemporal matrix generated by the spatiotemporal data management module 100, identifies overlapping time periods and spatial areas, obtains potential conflict points, and forms a conflict list.
[0064] The AI intelligent analysis module 300, connected to the spatiotemporal conflict detection module 200, integrates graph neural network (GNN) and reinforcement learning (RL) algorithms to find key bottlenecks in potential conflict points and optimize the construction schedule.
[0065] Among them, the AI intelligent analysis module 300 obtains the conflict list from the spatiotemporal conflict detection module 200, finds the key bottlenecks through graph neural network (GNN), and calculates and outputs the optimal solution in conjunction with reinforcement learning (RL) algorithm to optimize the construction schedule.
[0066] The visualization report generation module 400, connected to the AI intelligent analysis module 300, is used to generate conflict analysis reports based on key bottlenecks.
[0067] The visualization report generation module 400 is connected to the AI intelligent analysis module 300, which can output an optimized construction schedule, space occupancy timeline, and conflict resolution suggestion report.
[0068] The dynamic monitoring and early warning module 500, which is connected to the AI intelligent analysis module 300 and the spatiotemporal data management module 100, is used to collect data to update the spatiotemporal matrix and provide dynamic early warnings for key bottlenecks.
[0069] Among them, the dynamic monitoring and early warning module 500 is connected to the IoT devices installed at the construction site. It collects actual construction progress data through on-site IoT devices (such as cameras and RFID), updates the database of the BIM model in the spatiotemporal data management module 100, generates a new spatiotemporal matrix, and provides early warnings for key bottlenecks generated in the AI intelligent analysis module 300.
[0070] Among them, the real-time collection of actual progress data at the construction site through Internet of Things (IoT) technologies (such as RFID, cameras, sensors, and mobile apps) and dynamic data updates enable responses to unexpected situations on site, thus improving adaptability.
[0071] The present invention provides a timing optimization device, including: a memory 801, a processor 802, and a computer program stored in the memory 801 and executable on the processor 802. The processor 802 executes the program to implement the intelligent timing optimization method for multi-unit engineering provided in the above embodiments.
[0072] Furthermore, the electronic device also includes a communication interface 803 for communication between the memory 801 and the processor 802.
[0073] The memory 801 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.
[0074] If the memory 801, processor 802, and communication interface 803 are implemented independently, they can be interconnected via a bus to communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, only one thick line is used in the diagram, but this does not indicate that there is only one bus or one type of bus.
[0075] Optionally, in a specific implementation, if the memory 801, processor 802, and communication interface 803 are integrated on a single chip, then the memory 801, processor 802, and communication interface 803 can communicate with each other through an internal interface.
[0076] The processor 802 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention.
[0077] The present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a multi-unit engineering intelligent timing optimization method provided in the above embodiments.
[0078] The present invention has been described in detail above with reference to the accompanying drawings and embodiments. Those skilled in the art can make various modifications to the present invention based on the above description. Therefore, certain details in the embodiments should not be construed as limiting the present invention, and the scope of protection of the present invention shall be defined by the appended claims.
Claims
1. A multi-unit intelligent time-series optimization method for engineering projects, characterized in that, include: According to the construction schedule, the components are numbered, and the spatial and temporal information of the components is obtained. The component's number, spatial information, and time information are input into the BIM model to generate a spatiotemporal matrix; Based on the spatiotemporal matrix, AI intelligent software is used to calculate spatiotemporal intersection points to obtain potential conflict points. Based on the construction logic, identify the key bottlenecks among the potential conflict points; Based on reinforcement learning algorithms, the timing of the components associated with the key bottlenecks is adjusted to optimize the construction schedule and output the optimized construction schedule.
2. The intelligent time-series optimization method for multi-unit engineering projects according to claim 1, characterized in that, The time information includes start time, end time, time interval, and resource requirement type.
3. The intelligent time-series optimization method for multi-unit engineering projects according to claim 1, characterized in that, The step of inputting the component's number, spatial information, and temporal information into the BIM model to generate a spatiotemporal matrix includes: In the BIM model, the time information of the component is mapped to the spatial information.
4. The intelligent time-series optimization method for multi-unit engineering projects according to claim 1, characterized in that, The step of using AI software to calculate the spatiotemporal intersection points based on the spatiotemporal matrix to obtain potential conflict points includes: Based on the spatial and temporal information corresponding to the components, the temporal overlap of different components in the same space is obtained.
5. The intelligent timing optimization method for multi-unit engineering projects according to claim 1, characterized in that, The process of identifying key bottlenecks among potential conflict points based on construction logic includes: The construction logic relationship is analyzed using a graph neural network to identify the key bottlenecks and generate an analysis report.
6. The intelligent time-series optimization method for multi-unit engineering projects according to claim 1, characterized in that, The process of identifying key bottlenecks among potential conflict points based on construction logic includes: Dynamic early warnings will be issued for the aforementioned key bottlenecks.
7. The intelligent time-series optimization method for multi-unit engineering projects according to claim 1, characterized in that, The step of adjusting the timing of the components associated with the key bottlenecks based on reinforcement learning algorithms to optimize the construction schedule and output the optimized construction schedule includes: When adjusting the timing of the components, a reward function is used to evaluate the corresponding construction period and resource efficiency after the adjustment, and the optimal solution is selected as the optimized construction schedule.
8. A multi-unit engineering intelligent timing optimization system, characterized in that, include: The spatiotemporal data management module is used to correlate the spatial and temporal information of construction components and generate a spatiotemporal matrix. The spatiotemporal conflict detection module, connected to the spatiotemporal data management module, is used to calculate spatiotemporal intersection points based on the spatiotemporal matrix and identify potential conflict points. The AI intelligent analysis module, connected to the spatiotemporal conflict detection module, integrates graph neural network (GNN) and reinforcement learning (RL) algorithms to find key bottlenecks in the potential conflict points and optimize the construction schedule. A visualization report generation module connected to the AI intelligent analysis module is used to generate a conflict analysis report based on the key bottlenecks; The dynamic monitoring and early warning module, which is connected to the AI intelligent analysis module and the spatiotemporal data management module, is used to collect data to update the spatiotemporal matrix and to provide dynamic early warnings for the key bottlenecks that appear.
9. A multi-unit engineering intelligent timing optimization system, characterized in that, include: The spatiotemporal data management module is used to correlate the spatial and temporal information of construction components and generate a spatiotemporal matrix. The spatiotemporal conflict detection module, connected to the spatiotemporal data management module, is used to calculate spatiotemporal intersection points based on the spatiotemporal matrix and identify potential conflict points. The AI intelligent analysis module, connected to the spatiotemporal conflict detection module, integrates graph neural network (GNN) and reinforcement learning (RL) algorithms to find key bottlenecks in the potential conflict points and optimize the construction schedule. A visualization report generation module connected to the AI intelligent analysis module is used to generate a conflict analysis report based on the key bottlenecks; The dynamic monitoring and early warning module, which is connected to the AI intelligent analysis module and the spatiotemporal data management module, is used to collect data to update the spatiotemporal matrix and to provide dynamic early warnings for the key bottlenecks that appear.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement a multi-unit engineering intelligent timing optimization method as described in any one of claims 1-7.