Project management method and system based on AI large model technology

Abstract

The invention is suitable for the technical field of project management, and particularly relates to a project management method and system based on an AI large model technology, and the method comprises the steps: segmenting a project site into a plurality of blocks, configuring a key node in each block, determining the completion time of each key node, and generating a progress schedule; according to the method, video monitoring data of a project site are collected, resources of each block are determined, the resources at least comprise personnel and construction time, monitoring periods are set, and snapshots of two adjacent monitoring periods are intercepted from the video monitoring data. By determining the defect item and the priority item, resource configuration can be optimized, resources can be adjusted in time according to the progress schedule, it is guaranteed that the project is completed on time, by constructing the resource management pool, the project bottleneck can be visually displayed, the resources can be adjusted in real time, the overall progress of the project is accelerated, project management is continuously optimized, and the project management efficiency is improved. And the project management efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of project management, and in particular to a project management method and system based on AI big model technology. Background Art

[0002] A project refers to a systematic work with clear objectives, specific start and end dates, a unique combination of activities and limited resources, including but not limited to construction projects, traffic management projects, etc.; however, existing project schedule management often relies on preset plans and linear schedules, and the actual progress of the project is often affected by various external and internal factors, such as changes in customer demand, technical problems, personnel turnover and supply chain disruptions, etc. These factors will cause deviations between the original plan and the actual progress, making it impossible to complete the project on time.

[0003] In order to complete the project on time, project managers often schedule resources such as manpower and materials according to the project progress during the project, such as transferring personnel who complete the indicators first in the project to other parts; however, such manual scheduling process not only consumes a lot of manpower and material resources, but also cannot be scheduled in real time.

[0004] Therefore, “real-time scheduling of resources according to project progress” is the technical problem that the present invention needs to solve. Summary of the invention

[0005] The purpose of the present invention is to provide a project management method and system based on AI big model technology to solve the problem of "how to schedule resources in real time according to project progress" raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: A project management method based on AI big model technology, the method comprising: Divide the project site into several blocks, configure the key nodes in each block, determine the completion time of each key node, and generate a schedule; Collect video surveillance data from the project site, determine the resources of each block, where the resources include at least personnel and construction time, set the monitoring cycle, extract snapshots of two adjacent monitoring cycles from the video surveillance data, and segment them, determine the correspondence between the snapshots and the blocks, and input the snapshots into the AI ​​model built using the convolutional neural network, read out the real-time progress of each block, compare the real-time progress with the progress schedule, and traverse the defective items and priority items; Construct a resource management pool and divide it into scheduling areas, synchronize the resources corresponding to the defective items and priority items into the scheduling areas, link the defective items and priority items to the two sides of the resource management pool respectively, configure the inclination angle of the resource management pool, divide the inclination angle into several levels, configure the adjustment strategy corresponding to each level, and use the adjustment strategy to correct the inclination angle.

[0007] Furthermore, the step of "dividing the project site into a number of blocks and configuring key nodes in each of the blocks" includes: Find out several dimensions of the project site, where the dimensions include: function, location and construction difficulty, and merge or re-divide the blocks based on the dimensions; Dependencies between blocks are set, and resources are adjusted based on the dependencies.

[0008] Furthermore, the step of "determining the completion time of each of the key nodes and generating a schedule" includes: Locate the bottlenecks of each key node, determine potential risks, integrate bottlenecks and potential risks, and generate buffer periods; The buffer period is added to the schedule.

[0009] Furthermore, the step of "determining the resources of each block" includes: Generating a tag using the resource and inserting the tag into the block; Obtain the change of the resource and use the real-time progress to determine whether the progress schedule can be completed.

[0010] Furthermore, the method further comprises: Using AI models, quantify the real-time progress of the blocks; Establishing a progress queue, transferring the blocks into the progress queue, and adjusting the arrangement of the blocks according to the order of the real-time progress from high to low; Selecting a preset number of blocks from the front row of the progress queue to determine them as precedent items, finding out the resources corresponding to the precedent items, and dividing them into core elements and auxiliary elements; The auxiliary elements are synchronized into the scheduling area.

[0011] Furthermore, the step of "traversing defective items and priority items" includes: Determine whether the real-time progress of the block exceeds the progress schedule, if so, define the block as a priority item, otherwise, define it as a defective item; The schedule is iterated using the deficient items and the prioritized items.

[0012] Furthermore, the step of “linking the defective item and the priority item to two sides of the resource management pool respectively” includes: Configuring a priority for each defect item, wherein the priority is divided into high, medium, and low; The quota of each priority level is determined, and resources corresponding to the quota are selected from the scheduling area to process the defective items.

[0013] Furthermore, the system comprises: A generation module is used to divide the project site into several blocks, configure the key nodes in each block, determine the completion time of each key node, and generate a schedule; A traversal module is used to collect video surveillance data from the project site, determine the resources of each block, where the resources include at least personnel and construction time, set a monitoring cycle, extract snapshots of two adjacent monitoring cycles from the video surveillance data, and segment them, determine the corresponding relationship between the snapshots and the blocks, and input the snapshots into an AI model built using a convolutional neural network, read out the real-time progress of each block, compare the real-time progress with the progress schedule, and traverse the defective items and priority items; The correction module is used to construct a resource management pool and divide it into a scheduling area, synchronize the resources corresponding to the defective items and the priority items into the scheduling area, link the defective items and the priority items to the two sides of the resource management pool respectively, configure the inclination angle of the resource management pool, divide the inclination angle into several levels, configure the adjustment strategy corresponding to each level, and use the adjustment strategy to correct the inclination angle.

[0014] Furthermore, the generation module includes: A search unit, used to search for several dimensions of the project site, wherein the dimensions include: function, location and construction difficulty, and merge or re-divide the blocks based on the dimensions; An adjustment unit, used to set dependencies between blocks and adjust resources based on the dependencies; Positioning unit, used to locate the bottleneck of each key node, determine potential risks, integrate bottlenecks and potential risks, and generate buffer periods; An adding unit is used to add the buffer period to the progress schedule.

[0015] Furthermore, the traversal module includes: An inserting unit, configured to generate a label using the resource and insert the label into the block; A judgment unit, used to obtain the change of the resource and use the real-time progress to judge whether the progress schedule can be completed; A definition unit, used for judging whether the real-time progress of the block exceeds the progress schedule, and if so, defining the block as a priority item, otherwise, defining it as a defect item; An iteration unit is used to iterate the schedule using the defect items and priority items.

[0016] Compared with the prior art, the present invention has the following beneficial effects: By dividing the project site into several blocks, it is possible to achieve refined management of the project, optimize project management, and ensure that the project is completed on time. By taking snapshots, the real-time progress of the project can be determined so that problems can be discovered and adjusted in time, which greatly improves the controllability of the project. By identifying defective items and priority items, resource allocation can be optimized, and resources can be adjusted in time according to the schedule to ensure that the project is completed on time. By building a resource management pool, not only can the project bottlenecks be displayed intuitively, but also resources can be adjusted in real time, accelerating the overall progress of the project, continuously optimizing project management, and improving project management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flowchart of a project management method based on AI big model technology provided by an embodiment of the present invention; Figure 2 A first sub-process flowchart of a project management method based on AI big model technology provided by an embodiment of the present invention; Figure 3 A second sub-process flowchart of the project management method based on AI big model technology provided by an embodiment of the present invention; Figure 4 A third sub-process flowchart of the project management method based on AI big model technology provided by an embodiment of the present invention; Figure 5 A block diagram of the composition of a project management system based on AI big model technology provided by an embodiment of the present invention; Figure 6 A block diagram of the composition of the generation module in the project management system based on the AI ​​big model technology provided by an embodiment of the present invention; Figure 7 A block diagram of the composition of the traversal module in the project management system based on the AI ​​big model technology provided by an embodiment of the present invention; Figure 8 A block diagram of the composition of the correction module in the project management system based on AI big model technology provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0019] In Example 1, Figure 1 The implementation process of the project management method based on AI big model technology provided by the embodiment of the present invention is shown, and is described in detail below: S100: Divide the project site into several blocks, configure the key nodes in each block, determine the completion time of each key node, and generate a schedule.

[0020] Divide the project site into multiple relatively independent or clearly bounded parts. The specific division rules may be physical space and task modules, etc. Determine the personnel and equipment corresponding to each block; determine the key nodes of each block. Key nodes are similar to indicators. If a project completes all key nodes, it means the completion of the project. Determine the completion time of each key node. The completion time here is calculated based on experience and historical data. Develop a schedule based on the key nodes and completion time.

[0021] S200: Collect video surveillance data from the project site, determine the resources of each block, where the resources include at least personnel and construction time, set a monitoring cycle, extract snapshots of two adjacent monitoring cycles from the video surveillance data, and split them, determine the correspondence between the snapshots and the blocks, and input the snapshots into an AI model built using a convolutional neural network, read out the real-time progress of each block, compare the real-time progress with the progress schedule, and traverse the defective items and priority items.

[0022] By analyzing the video surveillance data, we extract features such as personnel and daily construction duration, and define these features as resources. We update the resources according to the monitoring cycle, where the monitoring cycle is pre-determined by the management personnel. In each monitoring cycle, snapshots are taken from the video surveillance data, where a snapshot refers to a "static display" of the real-time progress of a block at a certain moment.

[0023] The snapshots are divided into parts corresponding to each block, and the snapshots of two adjacent monitoring cycles are input into the AI ​​model in natural time order. The real-time progress of each block is output and compared with the schedule to find out the defective items and priority items. A defective item means that the real-time progress of the block lags behind the schedule. Otherwise, it is a priority item. The number of defective items and priority items may be 0 or more.

[0024] In the subsequent processing, part of the resources of the priority item can be transferred to the defective item to ensure that the defective item can catch up with the schedule; if the defective item is 0, it means that the overall progress of the project is ahead of the schedule.

[0025] S300: Construct a resource management pool and divide it into scheduling areas, synchronize the resources corresponding to the defect items and priority items into the scheduling areas, link the defect items and priority items to the two sides of the resource management pool respectively, configure the tilt angle of the resource management pool, divide the tilt angle into several levels, configure the adjustment strategy corresponding to each level, and use the adjustment strategy to correct the tilt angle.

[0026] Construct a resource management pool, where the resource management pool is similar to a centralized management platform for overall management, allocation and monitoring of all resources in the project; in this embodiment, the resource management pool is used to schedule resources for defective items and priority items to ensure that the defective items can complete the schedule on time.

[0027] The defective item and the priority item are linked to the two sides of the resource management pool respectively, and the difference between the real-time progress of the defective item and the priority item is calculated, and the tilt angle corresponding to the difference is determined, and the resource management pool is tilted toward the defective item, wherein the greater the difference between the real-time progress of the defective item and the priority item, the greater the tilt angle; by setting the tilt angle, the progress difference of the defective item can be intuitively displayed so that targeted adjustment measures can be taken; the tilt angle is divided into several levels, and the adjustment strategy for each level is determined, wherein the adjustment strategy is the specific response method to the difference in real-time progress, and the adjustment strategy is used to eliminate the tilt angle.

[0028] For example, in a road construction project, the project site is divided into multiple blocks such as civil engineering, traffic signs and enclosures, and the progress indicators (key nodes) of each block are determined. If the real-time progress of the civil engineering block is 80%, and the real-time progress of the enclosure block is 30%, the civil engineering block is defined as a priority item, and the enclosure block is defined as a defective item. If the inclination angle corresponding to the real-time progress difference (50%) between the two is 15° (the relationship between the real-time progress difference, the inclination angle and the grade can be presented through a comparison table), the resource management pool will be tilted toward the block corresponding to the enclosure, and the inclination angle will be corrected using an adjustment strategy, where the adjustment strategy can be to extract a preset number of workers from the priority item to the defective item. The comparison table and the preset number are pre-determined by the project management personnel.

[0029] In Example 2, Figure 2 The implementation process of the project management method based on the AI ​​big model technology provided by the embodiment of the present invention is shown. The steps of "dividing the project site into several blocks and configuring the key nodes in each of the blocks" are described in detail as follows: S101: Find out several dimensions of the project site, where the dimensions include: function, location and construction difficulty, and merge or re-divide the blocks based on the dimensions.

[0030] After the project site is divided according to space and tasks, the divided blocks can be merged or re-divided based on the specific location of the blocks or the difficulty of construction.

[0031] S102: Setting dependencies between blocks, and adjusting resources based on the dependencies.

[0032] According to the dependencies between blocks, the resources invested in each block are further adjusted, where the dependencies can be process dependency, resource dependency, space dependency, etc.

[0033] In Example 3, Figure 2 The implementation process of the project management method based on the AI ​​big model technology provided by the embodiment of the present invention is shown. The steps of "determining the completion time of each of the key nodes and generating a schedule" are described in detail as follows: S103: Locate the bottleneck of each key node, determine the potential risks, integrate the bottlenecks and potential risks, and generate a buffer period.

[0034] Identify the bottleneck of each key node, where the bottleneck is the difficulty in completing the key node; based on the difficulty, determine the possible risks, that is, potential risks, and generate a buffer period by combining the bottleneck and potential risks.

[0035] S104: Add the buffer period to the progress schedule.

[0036] A buffer period is added to a designated position in the schedule; in this embodiment, the schedule includes at least: a key node item, a completion time item, and a buffer period item.

[0037] In Example 4, Figure 3 The implementation process of the project management method based on the AI ​​big model technology provided by the embodiment of the present invention is shown. The step of "determining the resources of each block" is described in detail as follows: S201: Generate a tag using the resource, and insert the tag into a block.

[0038] The advantage of inserting tags consisting of resources into chunks is that the resource usage of each chunk can be quickly determined.

[0039] S202: Obtain the change of the resource, and use the real-time progress to determine whether the progress plan can be completed.

[0040] Determine whether the schedule can be completed on time based on the changes in resources in each block; in other words, by monitoring the real-time status of resources such as manpower, materials and equipment, timely discover resource shortages or surpluses to determine whether they affect the real-time progress; and compare the actual progress of the project with the original schedule to evaluate whether the current work arrangement is reasonable. If the real-time progress lags behind the schedule and there are resource bottlenecks, it is necessary to adjust resource allocation or re-optimize the schedule to ensure that the schedule can be completed on schedule.

[0041] In Example 5, different from Example 1, in this embodiment of the present invention, the method further includes: Using AI models, quantify the real-time progress of the blocks; Establishing a progress queue, transferring the blocks into the progress queue, and adjusting the arrangement of the blocks according to the order of the real-time progress from high to low; Selecting a preset number of blocks from the front row of the progress queue to determine them as precedent items, finding out the resources corresponding to the precedent items, and dividing them into core elements and auxiliary elements; The auxiliary elements are synchronized into the scheduling area.

[0042] Input the snapshot into the AI ​​model, and output the digital real-time progress of each block. Establish a progress queue arranged from high to low according to the real-time progress. Select a preset number of blocks from the progress queue and define them as precedent items, where the precedent items are the blocks in the project with faster completion progress. Divide the resources of the precedent items into core elements and auxiliary elements, where the core elements are the key resources to ensure that the progress schedule of the block can be realized.

[0043] Continuing to elaborate on the example in S300, if the antecedent item is the block corresponding to civil engineering, then the personnel in the resources are divided into core elements and auxiliary elements, where the core elements include rebar workers, scaffolders, crane operators and welders, etc., while the auxiliary elements include handymen, maintenance workers and some logistics personnel, etc.

[0044] In Example 6, Figure 3 The implementation process of the project management method based on the AI ​​big model technology provided by the embodiment of the present invention is shown. The steps of "traversing defective items and priority items" are described in detail as follows: S203: Determine whether the real-time progress of the block exceeds the progress schedule. If so, define the block as a priority item; otherwise, define it as a defect item.

[0045] If the real-time progress of a block exceeds the schedule, then the block will be determined as a priority item, otherwise, it will be determined as a defective item.

[0046] S204: Iterating the schedule using the defect items and priority items.

[0047] Fine-tuning the schedule to make the project more coordinated as a whole can help avoid an unachievable or unrealistic schedule.

[0048] In Example 7, Figure 4 The implementation process of the project management method based on the AI ​​big model technology provided by an embodiment of the present invention is shown. The step of "linking the defect item and the priority item to both sides of the resource management pool respectively" is described in detail as follows: S301: configuring a priority of each defect item, wherein the priority is divided into high, medium and low.

[0049] Determine the priority level of each defect item based on the severity of the defect item, its impact on the project progress, and the urgency of completing the defect item.

[0050] S302: Determine the quota of each priority level, select resources corresponding to the quota from the scheduling area, and process the defective item.

[0051] Different levels of priority correspond to different quotas, where the quota refers to the proportion of resources allocated to the defective item; for example, one side of the resource management pool is linked to two defective items, and the allocation of resources in the scheduling area is determined by the quota corresponding to each defective item.

[0052] Figure 5 The following is a structural block diagram of a project management system based on AI big model technology provided by an embodiment of the present invention. The project management system 1 based on AI big model technology includes: The generation module 11 is used to divide the project site into several blocks, configure the key nodes in each block, determine the completion time of each key node, and generate a schedule; The traversal module 12 is used to collect video surveillance data of the project site, determine the resources of each block, wherein the resources include at least: personnel and construction time, set the monitoring cycle, intercept the snapshots of two adjacent monitoring cycles from the video surveillance data, and segment them, determine the corresponding relationship between the snapshots and the blocks, and input the snapshots into the AI ​​model built by the convolutional neural network, read the real-time progress of each block, compare the real-time progress with the progress schedule, and traverse the defective items and priority items; The correction module 13 is used to construct a resource management pool and divide it into a scheduling area, synchronize the resources corresponding to the defective items and the priority items into the scheduling area, link the defective items and the priority items to the two sides of the resource management pool respectively, configure the inclination angle of the resource management pool, divide the inclination angle into several levels, configure the adjustment strategy corresponding to each level, and use the adjustment strategy to correct the inclination angle.

[0053] Figure 6 The structure diagram of the project management system based on AI big model technology provided by an embodiment of the present invention is shown, and the generation module 11 includes: A search unit 111 is used to search for several dimensions of the project site, wherein the dimensions include: function, location and construction difficulty, and merge or re-divide the blocks based on the dimensions; An adjustment unit 112, configured to set dependencies between blocks and adjust resources based on the dependencies; A positioning unit 113 is used to locate the bottleneck of each key node, determine the potential risk, integrate the bottleneck and the potential risk, and generate a buffer period; The adding unit 114 is used to add the buffer period to the progress schedule.

[0054] Figure 7 The structure diagram of the project management system based on the AI ​​big model technology provided by the embodiment of the present invention is shown, and the traversal module 12 includes: An inserting unit 121, configured to generate a label using the resource and insert the label into the block; A judgment unit 122 is used to obtain the change of the resource and use the real-time progress to judge whether the progress schedule can be completed; A definition unit 123, used to determine whether the real-time progress of the block exceeds the progress schedule, if so, define the block as a priority item, otherwise, define it as a defective item; The iteration unit 124 is used to iterate the schedule using the defect items and priority items.

[0055] Figure 8 The structure diagram of the project management system based on AI big model technology provided by an embodiment of the present invention is shown, and the correction module 13 includes: A configuration unit 131, configured to configure a priority of each defect item, wherein the priority is divided into high, medium and low; The processing unit 132 is used to determine the quota of each priority level, select the resources corresponding to the quota from the scheduling area, and process the defective items.

[0056] The generation module 11 is mainly used to complete step S100, the traversal module 12 is mainly used to complete step S200, and the correction module 13 is mainly used to complete step S300; The searching unit 111 is mainly used to complete step S101, the adjusting unit 112 is mainly used to complete step S102, the positioning unit 113 is mainly used to complete step S103, and the adding unit 114 is mainly used to complete step S104; The inserting unit 121 is mainly used to complete step S201, the judging unit 122 is mainly used to complete step S202, the defining unit 123 is mainly used to complete step S203, and the iterating unit 124 is mainly used to complete step S204; The configuration unit 131 is mainly used to complete step S301, and the processing unit 132 is mainly used to complete step S302.

[0057] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0058] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0059] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A project management method based on AI big model technology, characterized in that: The method comprises: Divide the project site into several blocks, configure the key nodes in each block, determine the completion time of each key node, and generate a schedule; Collect video surveillance data from the project site, determine the resources of each block, where the resources include at least personnel and construction time, set the monitoring cycle, extract snapshots of two adjacent monitoring cycles from the video surveillance data, and segment them, determine the correspondence between the snapshots and the blocks, and input the snapshots into the AI ​​model built using the convolutional neural network, read out the real-time progress of each block, compare the real-time progress with the progress schedule, and traverse the defective items and priority items; Construct a resource management pool and divide it into scheduling areas, synchronize the resources corresponding to the defective items and priority items into the scheduling areas, link the defective items and priority items to the two sides of the resource management pool respectively, configure the inclination angle of the resource management pool, divide the inclination angle into several levels, configure the adjustment strategy corresponding to each level, and use the adjustment strategy to correct the inclination angle.

2. The project management method based on AI big model technology according to claim 1 is characterized in that: The step of "dividing the project site into several blocks and configuring key nodes in each block" includes: Find out several dimensions of the project site, where the dimensions include: function, location and construction difficulty, and merge or re-divide the blocks based on the dimensions; Dependencies between blocks are set, and resources are adjusted based on the dependencies.

3. The project management method based on AI big model technology according to claim 1 is characterized in that: The step of "determining the completion time of each of the key nodes and generating a schedule" includes: Locate the bottlenecks of each key node, determine potential risks, integrate bottlenecks and potential risks, and generate buffer periods; The buffer period is added to the schedule.

4. The project management method based on AI big model technology according to claim 1 is characterized in that: The step of "determining the resources of each block" includes: Generating a tag using the resource and inserting the tag into the block; Obtain the change of the resource and use the real-time progress to determine whether the schedule can be completed.

5. The project management method based on AI big model technology according to claim 4 is characterized in that: The method further comprises: Using AI models, quantify the real-time progress of the blocks; Establishing a progress queue, transferring the blocks into the progress queue, and adjusting the arrangement of the blocks according to the order of the real-time progress from high to low; Selecting a preset number of blocks from the front row of the progress queue to determine them as precedent items, finding out the resources corresponding to the precedent items, and dividing them into core elements and auxiliary elements; The auxiliary elements are synchronized into the scheduling area.

6. The project management method based on AI big model technology according to claim 5 is characterized in that: The step of "traversing defective items and priority items" includes: Determine whether the real-time progress of the block exceeds the progress schedule, if so, define the block as a priority item, otherwise, define it as a defective item; The schedule is iterated using the deficient items and the prioritized items.

7. The project management method based on AI big model technology according to claim 6 is characterized in that: The step of "linking the defective item and the priority item to both sides of the resource management pool respectively" includes: Configuring a priority for each defect item, wherein the priority is divided into high, medium, and low; The quota of each priority level is determined, and resources corresponding to the quota are selected from the scheduling area to process the defective items.

8. A project management system based on AI big model technology, characterized in that: The system comprises: A generation module is used to divide the project site into several blocks, configure the key nodes in each block, determine the completion time of each key node, and generate a schedule; A traversal module is used to collect video surveillance data from the project site, determine the resources of each block, where the resources include at least personnel and construction time, set a monitoring cycle, extract snapshots of two adjacent monitoring cycles from the video surveillance data, and segment them, determine the corresponding relationship between the snapshots and the blocks, and input the snapshots into an AI model built using a convolutional neural network, read out the real-time progress of each block, compare the real-time progress with the progress schedule, and traverse the defective items and priority items; The correction module is used to construct a resource management pool and divide it into a scheduling area, synchronize the resources corresponding to the defective items and the priority items into the scheduling area, link the defective items and the priority items to the two sides of the resource management pool respectively, configure the inclination angle of the resource management pool, divide the inclination angle into several levels, configure the adjustment strategy corresponding to each level, and use the adjustment strategy to correct the inclination angle.

9. The project management system based on AI big model technology according to claim 8 is characterized in that: The generation module comprises: A search unit, used to search for several dimensions of the project site, wherein the dimensions include: function, location and construction difficulty, and merge or re-divide the blocks based on the dimensions; An adjustment unit, used to set dependencies between blocks and adjust resources based on the dependencies; Positioning unit, used to locate the bottleneck of each key node, determine potential risks, integrate bottlenecks and potential risks, and generate buffer periods; An adding unit is used to add the buffer period to the progress schedule.

10. The project management system based on AI big model technology according to claim 8, characterized in that: The traversal module includes: An inserting unit, configured to generate a label using the resource and insert the label into the block; A judgment unit, used to obtain the change of the resource and use the real-time progress to judge whether the progress schedule can be completed; A definition unit, used for judging whether the real-time progress of the block exceeds the progress schedule, and if so, defining the block as a priority item, otherwise, defining it as a defect item; An iteration unit is used to iterate the schedule using the defect items and priority items.

Images