Inspection task real-time optimization scheduling method based on artificial intelligence

Abstract

The invention discloses an inspection task real-time optimization scheduling method based on artificial intelligence, and relates to the technical field of data processing, and the method comprises the steps: carrying out the total-factor space-time perception mapping for an inspection site, and determining an inspection view; supervising and training the scheduling optimization model based on the inspection view; receiving an inspection task, performing task collision analysis under high concurrency, generating an optimization instruction of inspection scheduling, performing balanced scheduling distribution of the inspection task in combination with the scheduling optimization model, determining a task scheduling strategy, transmitting and releasing the task scheduling strategy to an inspection target, and performing execution and tracking management of the inspection task. The technical problems of inflexible task scheduling and low resource utilization rate caused by the fact that a traditional inspection task scheduling method in the prior art is generally static and cannot adapt to field environment change in real time are solved, and the purposes of dynamically adjusting the task scheduling strategy according to real-time data of an inspection field and improving the task scheduling efficiency are achieved. And the real-time performance, the flexibility and the resource utilization efficiency of the inspection task are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a real-time optimization scheduling method for inspection tasks based on artificial intelligence. Background Art

[0002] In modern intelligent inspection systems, with the improvement of industrial automation and intelligence levels, real-time optimization and scheduling of inspection tasks has become a key technology to improve inspection efficiency, reduce labor costs, and improve equipment management levels.

[0003] However, in the existing technology, most inspection task scheduling schemes use optimization methods based on static planning, which usually fail to fully consider factors such as the dynamic location of inspection targets (such as inspection personnel, robots, etc.), the urgency of tasks, and the availability of resources. In addition, traditional scheduling methods have weak real-time monitoring and dynamic adjustment capabilities for the task execution process, and are unable to handle conflicts between tasks under high concurrency conditions, resulting in low utilization of inspection resources, and even task delays or resource waste. Summary of the invention

[0004] The present application provides a real-time optimization scheduling method for inspection tasks based on artificial intelligence, which is used to solve the technical problems in the prior art that traditional inspection task scheduling methods are usually static and cannot adapt to changes in the on-site environment in real time, resulting in inflexible task scheduling and low resource utilization.

[0005] The present application provides a real-time optimization and scheduling method for inspection tasks based on artificial intelligence, the method comprising: performing full-element spatiotemporal perception mapping for the inspection site and determining an inspection view, wherein the inspection view comprises an invariant map and a variable map, and the inspection view is updated in real time; based on the inspection view, supervising the training of a scheduling optimization model, wherein the scheduling optimization model performs data-driven training in a two-step scheduling optimization mode; receiving inspection tasks, performing task collision analysis under high concurrency, and generating optimization instructions for inspection scheduling; receiving the optimization instructions, executing balanced scheduling allocation of the inspection tasks in combination with the scheduling optimization model, and determining a task scheduling strategy; transmitting and delegating the task scheduling strategy to the inspection target, and performing execution and tracking management of the inspection tasks.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: The present application provides an artificial intelligence-based real-time optimization and scheduling method for inspection tasks, which relates to the field of data processing technology. Through real-time updated inspection views and a two-step scheduling optimization model, the scheduling of inspection tasks is dynamically optimized based on spatiotemporal perception mapping and task collision analysis. Data-driven training is used to generate a balanced scheduling strategy to ensure efficient task allocation and transmission to inspection targets. This solves the technical problem that traditional inspection task scheduling methods in the prior art are usually static and cannot adapt to changes in the on-site environment in real time, resulting in inflexible task scheduling and low resource utilization. This achieves the technical effect of dynamically adjusting task scheduling strategies based on real-time data from the inspection site to improve the real-time, flexibility and resource utilization efficiency of inspection tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0008] Figure 1 A flowchart of a method for real-time optimization and scheduling of inspection tasks based on artificial intelligence provided in an embodiment of the present application; Figure 2 A schematic diagram of a process for determining a task scheduling strategy in a real-time optimization scheduling method for inspection tasks based on artificial intelligence provided in an embodiment of the present application. DETAILED DESCRIPTION

[0009] The present application provides a real-time optimization scheduling method for inspection tasks based on artificial intelligence, which is used to solve the technical problems in the prior art that traditional inspection task scheduling methods are usually static and cannot adapt to changes in the on-site environment in real time, resulting in inflexible task scheduling and low resource utilization.

[0010] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0011] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0012] Embodiment 1, as Figure 1 As shown, the present application provides a real-time optimization scheduling method for inspection tasks based on artificial intelligence, the method comprising: P10: For the inspection site, full-element spatiotemporal perception mapping is performed to determine the inspection view, wherein the inspection view includes invariant mapping and variable mapping, and the inspection view is updated in real time.

[0013] Furthermore, step P10 of the embodiment of the present application further includes: P11: Setting a preset migration amount, wherein the preset migration amount is the average change of an element per unit time; P12: Dividing the invariant elements and variable elements in the inspection site according to the preset migration amount; P13: Performing three-dimensional mapping for the invariant elements to determine a first layer view, performing three-dimensional mapping for the variable elements to determine a second layer view, and integrating the first layer view with the second layer view to determine the inspection view.

[0014] It should be understood that for the inspection site, the inspection view is constructed and updated in real time through full-element spatiotemporal perception mapping to support the dynamic scheduling of inspection tasks.

[0015] Specifically, first, a preset migration amount is set, which represents the average change of each element in the inspection site per unit time. Elements can be fixed facilities in the environment (such as electrical equipment, buildings, etc.) or dynamic objects (such as inspection personnel, inspection robots, etc.). The setting of the preset migration amount helps to quantify the changes and serves as the basis for subsequent element classification and view construction. Through the dynamic adjustment of the migration amount, it is possible to accurately determine which elements need to be updated frequently and which can maintain a lower update frequency.

[0016] Then, according to the preset migration amount, all elements in the inspection site are divided into immutable elements and variable elements. Immutable elements usually refer to elements in the site that do not change over time or change very slowly, such as fixed equipment and buildings, while variable elements refer to elements that change greatly over time, such as dynamic objects such as inspection personnel and robots. Through this division, the system can update different types of elements in a targeted manner, optimize the efficiency of resource use, and improve the accuracy of inspection task scheduling.

[0017] For invariant elements, a first-layer view is constructed using 3D mapping technology. This layer of view will show the structural characteristics of fixed facilities and sites, ensuring that inspection tasks can be reasonably planned based on stable and unchanging information. For variable elements, 3D mapping is also used, but considering the mobility of these elements in space and time, a dynamic second-layer view is constructed. The second-layer view can reflect the real-time position, status and activity path of the inspection personnel or robots.

[0018] Finally, the invariant view and the variable view are merged to form a comprehensive inspection view. This view can be updated in real time to ensure that the execution of inspection tasks in a changing environment is not affected. Through view fusion, the system obtains a real-time monitoring platform that comprehensively considers static and dynamic elements, allowing task scheduling to make decisions based on comprehensive and dynamically changing data.

[0019] The key to this step is to accurately classify the element types, cooperate with 3D mapping and view fusion technology, and update the spatiotemporal information of all elements of the inspection site in real time, so as to provide accurate basic data support for subsequent scheduling optimization. The technical support of this method includes 3D mapping algorithms, spatiotemporal perception mapping models, and dynamic element tracking and updating mechanisms to ensure that inspection tasks can be efficiently scheduled and executed in a real-time changing environment.

[0020] Furthermore, step P13 of the embodiment of the present application also includes: P13-1: For the variable elements, dynamic data is transmitted back in real time, wherein the dynamic data includes position and posture information and observation data; P13-2: The second-layer view is constructed with the position and posture as nodes and the observation data as edges, wherein the second-layer view is updated in real time, and the first-layer view has cumulative drift updates under loop detection based on the second-layer view.

[0021] Optionally, the method of constructing the inspection view is further refined, especially for the real-time update and fusion of variable elements, to form a first- and second-layer dynamically updated inspection scenario.

[0022] First, for variable elements (such as inspection personnel, inspection robots, etc.), sensors are used to transmit their position and posture information and observation data in real time. Position and posture information mainly includes the specific position, orientation, and posture state of the inspection personnel or robots in three-dimensional space. These data are crucial for path planning and task scheduling. Observation data includes environmental information and equipment status collected by sensors. This information helps the system perceive changes on site in real time and update the execution plan of inspection tasks.

[0023] Next, based on the real-time dynamic data, a second-layer view is constructed with the position and posture information as nodes and the observation data as edges. The second-layer view here is a dynamically updated model that represents all the changing inspection elements and their relationships. Each node represents a variable element (such as inspection personnel, equipment, etc.), and the edge represents the interaction or temporal continuity between them. Since these elements will change during the inspection process, the second-layer view must be continuously updated in real time to ensure the accuracy and immediacy of the scheduling task.

[0024] In order to maintain the accuracy of the second-layer view, the second-layer view is frequently updated and adjusted according to the location and status updates of the inspection personnel or robots, as well as the dynamic changes in the environment. Through the continuously updated second-layer view, it can dynamically adapt to sudden changes in the inspection tasks and adjust the scheduling strategy in time.

[0025] At the same time, the first-layer view (fixed scene elements, such as buildings, equipment, etc.) may also experience cumulative drift. For this reason, loop detection is required, that is, by detecting the overlap between the current position and the historical position, the drift caused by sensor errors, environmental interference, etc. is identified and corrected. Whenever the inspection personnel or equipment arrives at the location where they were last inspected, the scene elements in the first-layer view are adjusted based on the updated data of the second-layer view to ensure that they are consistent with the actual situation. This process helps reduce errors and ensure the accuracy of task planning.

[0026] Ultimately, the first-layer view and the second-layer view together form a complete inspection scene model. Changes in the second-layer view trigger necessary updates to the first-layer view, ensuring that the entire inspection scene can reflect the actual situation in real time. This dynamic view fusion enables the system to flexibly respond to on-site changes during inspection tasks and achieve real-time task scheduling and path planning.

[0027] Through the above steps, not only can the inspection scene be updated in real time, but also rapid response and adjustment can be made to dynamically changing inspection elements. The core of this process is to build and update the second-layer view in the form of a node directed graph by combining position and posture information with observation data, thereby effectively supporting the intelligent scheduling and path optimization of inspection tasks.

[0028] Furthermore, the cumulative drift update under the loop detection, step P13-2 of the embodiment of the present application further includes: P13-21: Using the same-position inspection visit as the loop detection group, determine the first observation data and the second observation data, wherein the second observation data is real-time observation data, and the first observation data is the observation data of the upper time node; P13-22: For the invariant element, measure the element drift of the second observation data compared with the first observation data; P13-23: Based on the element drift, update the one-layer view.

[0029] Specifically, the accuracy and real-time performance of the inspection view can be ensured through cumulative drift updates under loop detection, especially in the update of immutable elements (such as fixed equipment, building structures, etc.).

[0030] First, the loop detection mechanism is used to identify multiple visits to the same location during the inspection process. At the inspection site, inspectors or inspection robots may visit the same location at different time points. At this time, these locations are regarded as loop detection groups. By comparing the first observation data (i.e., the observation data at the last visit) and the second observation data (i.e., the real-time observation data at the current time point), it is possible to evaluate whether the state of the invariant element has changed. The second observation data is usually the data collected by the sensor in real time, while the first observation data is the previous record saved by the system based on historical data. Through this comparison, the loop detection mechanism can identify the accumulated errors that occur during the inspection process, especially the deviations related to environmental changes or sensor errors.

[0031] In the loop detection comparison process, it is necessary to measure the drift of the elements, that is, the change of the second observation data relative to the first observation data. This drift can be calculated by the difference analysis method to measure the error or change between two time nodes. For invariant elements (such as fixed facilities, equipment, etc.), the drift reflects the actual changes caused by sensor errors, environmental changes or model accumulation errors.

[0032] The measurement of feature drift not only considers the drift in position, but also may include changes in angle, attitude, and environmental characteristics. Accurately measuring this drift helps to ensure the accuracy of invariant features in subsequent view updates and prevent the accumulation of errors.

[0033] Then, based on the calculated drift of the elements, the first layer view is updated. The first layer view mainly describes the fixed elements in the inspection site, which usually do not change frequently, so their update frequency is low. However, during the inspection process, the fixed elements of the first layer view may drift due to factors such as environmental changes, equipment wear or sensor errors. Through loop detection and drift calculation, the first layer view is dynamically corrected to ensure the accuracy and real-time performance of the view. This update process not only maintains the accuracy of the inspection scene, but also eliminates the long-term drift caused by inspection equipment or sensor errors, thereby improving the accuracy of task scheduling and the reliability of inspection task execution.

[0034] Through this cumulative drift update method under loop detection, the invariant elements can be finely adjusted, making the update of the inspection view on the time axis more stable and reliable, and improving the intelligence level of the entire inspection task scheduling. This strategy is particularly suitable for long-term inspection tasks, ensuring that the drift effect will not cause deviations in task scheduling during the data accumulation process.

[0035] P20: Based on the inspection view, supervise the training of the scheduling optimization model, and the scheduling optimization model is data-driven trained in a two-step scheduling optimization mode.

[0036] It should be understood that the scheduling optimization model is trained based on the inspection view, and a two-step scheduling optimization method is used for data-driven training.

[0037] During the inspection task execution process, the spatiotemporal data in the inspection view (including real-time data of invariant elements and variable elements) is collected to provide training data for the scheduling optimization model. The inspection view contains detailed environmental information, equipment status, the location of inspection personnel and robots, and real-time observation data. These multi-dimensional data are used as input to train the model using supervised learning, that is, by providing known labeled data (such as ideal task scheduling results), the model can learn the relationship between input data and expected output. Supervised learning helps the system automatically extract patterns and rules in the data, so that the scheduling optimization model can make intelligent decisions based on real-time data.

[0038] The training process uses a two-step scheduling optimization method for data-driven training. Two-step scheduling optimization refers to optimizing the scheduling of inspection tasks through two stages: in the first stage, by analyzing the priority, urgency, resource requirements and other characteristics of the inspection tasks, the tasks are reasonably allocated to different inspection personnel or equipment. Task allocation not only takes into account the availability of resources, but also requires dynamic adjustment of the priority and urgency of tasks to ensure that high-priority tasks can be completed in a timely manner. The goal of this stage is to reduce task conflicts and idle time and improve resource utilization through reasonable resource allocation.

[0039] In the second stage, the path planning of the inspectors or robots is optimized to reduce unnecessary movement distance during the inspection process. Path planning should not only take into account the order of tasks, but also be optimized in combination with the position and capabilities of the inspectors or robots to ensure efficient execution of inspection tasks. By dynamically adjusting the path, it is possible to effectively avoid ineffective movement of inspectors or equipment, reduce energy consumption, and improve work efficiency.

[0040] The training of the two-step scheduling optimization model adopts a data-driven approach, that is, the model is continuously optimized through historical data and real-time data. Through the feedback mechanism, the scheduling strategy is gradually improved, making the scheduling model more accurate and efficient under different inspection environments and task requirements. The model training process not only relies on traditional algorithm optimization, but also allows the model to continuously self-adjust and evolve in actual inspection tasks through technologies such as reinforcement learning.

[0041] Through this series of steps, the system can adjust the task allocation and path planning in real time during the actual execution of the inspection task, ensuring the optimal execution of the inspection task under resource constraints, improving overall efficiency and reducing unnecessary energy consumption.

[0042] P30: Receive inspection tasks, perform task collision analysis under high concurrency, and generate optimization instructions for inspection scheduling.

[0043] Optionally, after receiving the inspection task, perform task collision analysis under high concurrency and generate optimization instructions for inspection scheduling.

[0044] First, the inspection task information is received from the inspection scheduling system. These inspection tasks include the equipment to be inspected, the inspection area, the priority and urgency of the task, and the resources required for each task (such as personnel, equipment, time, etc.). Each inspection task contains multiple key parameters, such as task type, location, execution time window, etc. The received task information will provide input data for subsequent task collision analysis.

[0045] In the actual inspection process, there may be multiple tasks that need to be performed in the same time period, which may lead to conflicts between tasks, especially when the inspection personnel or robot resources are limited. For example, if multiple tasks involve the same inspection area or the same equipment, and the resources cannot meet the demand, conflicts will occur between tasks.

[0046] In order to solve this problem, collision analysis is required for high-concurrency tasks. The goal of collision analysis is to predict and identify pairs of tasks that may compete or conflict with resources, especially when resources are limited. The specific collision analysis process includes: First, by analyzing the time, space, and resource requirements of the tasks, detect which tasks may conflict at the same time and place. Then, according to the urgency, importance, and resource availability of the tasks, the execution order of the tasks is automatically adjusted. For high-priority tasks, the time or location of other low-priority tasks is adjusted to ensure that high-priority tasks can be completed first. In addition, in the case of task conflicts, the allocation of resources can be optimized based on the availability of inspection personnel or equipment to ensure that each task can be executed efficiently.

[0047] After completing the task collision analysis, optimization instructions are generated based on the analysis results to guide the inspection personnel or inspection robots on how to perform the tasks. These instructions include task allocation strategies, priority adjustments, path planning, time scheduling, etc. The goal of the optimization instructions is to ensure that the inspection tasks can be performed efficiently and without conflict with limited resources, thereby improving the overall inspection efficiency. For example, if the inspection task involves the movement of inspection personnel or robots, path planning optimization can be performed based on real-time environmental data to reduce the invalid movement distance during the inspection process and avoid unnecessary waste of resources. In addition, the time scheduling of tasks can be optimized to reduce the idle time between tasks and improve work efficiency.

[0048] P40: Receive the optimization instruction, perform balanced scheduling and allocation of the inspection task in combination with the scheduling optimization model, and determine the task scheduling strategy.

[0049] Further, such as Figure 2 As shown, step P40 of the embodiment of the present application also includes: P41: Determine a two-step scheduling optimization method, wherein the two-step scheduling optimization method includes a one-step scheduling optimization based on global random adjustment and a two-step scheduling optimization based on local directional adjustment; P42: Determine a first scheduling strategy, based on the two-step scheduling optimization method, with the first scheduling strategy as the initial strategy, perform iterative optimization until convergence, and select the maximum fitness strategy as the task scheduling strategy.

[0050] It should be understood that after receiving the optimization instruction, the balanced scheduling allocation of the inspection tasks is performed in combination with the scheduling optimization model, and the task scheduling strategy is determined.

[0051] Specifically, it is necessary to first determine the two-step scheduling optimization method according to the optimization instruction. The two-step scheduling optimization method is a scheduling optimization method that comprehensively considers global and local information. Specifically, the two-step scheduling optimization is divided into two parts, including a one-step scheduling optimization based on global random adjustment and a two-step scheduling optimization based on local directional adjustment.

[0052] Among them, the one-step scheduling optimization stage based on global random adjustment perturbs the various parameters of the task scheduling strategy through global random adjustment to explore possible scheduling solutions. This process increases the search diversity and flexibility of the system by randomly selecting some possible scheduling strategies in the entire scheduling space. The goal of global random adjustment is to avoid local optimal solutions and improve the exploratory nature of the entire optimization process to ensure that a more efficient scheduling solution can be found.

[0053] The two-step scheduling optimization based on local directional adjustment optimizes the strategy based on local directional adjustment after global random adjustment. At this time, the disturbed strategy points are corrected according to the constraints of the inspection task (such as time limit, resource constraint, etc.). Through local adjustment, the adaptability of the strategy can be refined so that the scheduling plan is more in line with actual needs. The process of local directional adjustment can not only ensure the feasibility of the scheduling strategy, but also improve the adaptability and effect of the strategy. By combining global randomness and local directional adjustment, the two-step scheduling optimization method can effectively take into account the exploration and adaptability of the scheduling strategy, avoid falling into the local optimal solution, and improve the overall efficiency of task scheduling.

[0054] After the two-step scheduling optimization method is determined, the first scheduling strategy is determined based on the optimization method. The first scheduling strategy is a preliminary task scheduling plan, which can be an initial solution obtained through random perturbations and local adjustments in the first stage. Next, the initial strategy is continuously optimized by iterative optimization until the convergence condition is met.

[0055] Exemplarily, the first scheduling strategy is adjusted through multiple iterations to gradually improve the fitness of the scheduling scheme. In each iteration, the effect of the current strategy is evaluated and adjusted according to the execution of the task and the utilization of resources. This process can be aided by optimization algorithms, such as genetic algorithms, simulated annealing algorithms, etc., to gradually find the optimal solution.

[0056] After multiple iterations, the maximum fitness strategy is selected as the final task scheduling strategy. Fitness is an indicator to measure the effectiveness of the scheduling strategy, which may include factors such as the timeliness of task completion, full utilization of resources, and minimization of conflicts. The maximum fitness strategy refers to the scheduling solution that best meets these optimization goals. Through this process, it can be ensured that the task scheduling strategy is not only optimal, but also dynamically adapts to inspection tasks and environmental changes.

[0057] Furthermore, step P42 of the embodiment of the present application also includes: P42-1: Traverse the inspection tasks, combine the real-time positions of the inspection targets in the second-layer view, and determine the first inspection strategy based on the proximity principle, wherein the inspection targets include inspection personnel and inspection robots; P42-2: Perform task priority avoidance based on the real-time status of the inspection targets, and determine the first constraint condition, wherein the real-time status includes the idle status and the inspection status; P42-3: Perform task priority avoidance for the inspection tasks, and determine the second constraint condition; P42-4: Determine the first scheduling strategy based on the first inspection strategy, the first constraint condition and the second constraint condition.

[0058] In a possible embodiment of the present application, the generation process of the task scheduling strategy is further refined, especially by gradually determining the first scheduling strategy by combining the characteristics of the inspection task, the real-time status of the inspection target and the constraints.

[0059] Specifically, first, all inspection tasks are traversed, and the execution order of tasks is determined in combination with the real-time location of the inspection target in the second-layer view. The inspection targets in the second-layer view include dynamic inspection objects such as inspection personnel and inspection robots. Their real-time location and status are crucial to task scheduling. In this process, the system applies the principle of proximity, that is, it gives priority to assigning tasks to the task points closest to the current inspection target, so as to reduce the invalid movement distance during task execution and improve inspection efficiency. The application of the principle of proximity ensures that task scheduling can effectively utilize existing resources (such as personnel and robots) and avoid idle time or invalid waiting caused by excessive resource scheduling. At the same time, it can also improve the flexibility of task scheduling, so that the system can dynamically respond to sudden changes in inspection tasks.

[0060] After determining the first inspection strategy, the next step is to avoid task priorities based on the real-time status of the inspection target (such as whether the inspection personnel or robots are idle or in inspection status). Specifically, when the inspection personnel or robots are idle, tasks can be assigned to these resources first to ensure maximum resource utilization. When the inspection personnel or robots are in inspection status, the system will adjust the scheduling according to the urgency and priority of the task to avoid interference with ongoing tasks. The goal of this step is to ensure that there are no conflicts in resource utilization during the scheduling process, and to effectively avoid task priorities through the first constraint condition, thereby maximizing the utilization of inspection resources and the timeliness of task completion.

[0061] In addition to considering the inspection target status, more detailed task priority avoidance is also required. That is, the scheduling strategy is further adjusted according to the priority and constraints of each task. For example, if some tasks are urgent, they need to be scheduled and executed first, while other low-priority tasks may need to be postponed or rescheduled. The key to this process is to avoid tasks according to their priorities, ensuring that even if there are many tasks in high concurrency, they can be processed in a reasonable order to avoid delays in higher-priority tasks.

[0062] Finally, based on the previously determined first inspection strategy, the first constraint (priority avoidance from the real-time status of the inspection target) and the second constraint (avoidance from the task priority), comprehensive optimization is performed to finally determine the first scheduling strategy. This strategy will comprehensively consider the spatial distribution of tasks, the allocation of resources and the priority of each task to ensure balanced scheduling and reasonable allocation of tasks. After multiple rounds of optimization, it can ensure maximum resource utilization and minimize task conflicts. At the same time, it can be flexibly adjusted according to real-time conditions to ensure the efficiency of the system and the smooth completion of inspection tasks.

[0063] Furthermore, step P42 of the embodiment of the present application also includes: P42-5: Based on the fitness of the strategy point, set the optimization step size; P42-6: For the first inspection strategy, use the optimization step size to perform global strategy point random perturbation adjustment on the inspection strategy to determine a one-step optimization strategy; P42-7: According to the first constraint condition and the second constraint condition, perform local strategy point directional adjustment on the one-step optimization strategy to determine a two-step optimization strategy; P42-8: Integrate the one-step optimization strategy and the two-step optimization strategy to determine a layer of iterative optimization strategy.

[0064] Optionally, the specific process of iterative optimization with the first scheduling strategy as the initial strategy may be that the optimization step size needs to be set first according to the fitness of the strategy point. The strategy point refers to each specific decision or operation point in the scheduling strategy, such as task allocation, resource scheduling, path planning, etc. Each strategy point is associated with a specific inspection task execution process, representing a specific resource configuration or execution step. By evaluating these strategy points, the scheduling plan is continuously adjusted to achieve the optimal task execution effect. The fitness is an evaluation indicator of the execution effect of the scheduling strategy, which measures the gap between the current strategy and the optimal strategy. The higher the fitness, the closer the current strategy is to the optimal solution. The setting of the optimization step size determines the extent of the strategy adjustment during the optimization process. For example, a larger step size can speed up the optimization process, but may lead to skipping the local optimal solution; a smaller step size can refine the adjustment, but may require more computing time.

[0065] Dynamically adjusting the optimization step size according to the fitness of the strategy point can maintain a balance between global exploration and local refinement, and improve the efficiency and accuracy of strategy optimization. Exemplarily, the fitness of each strategy point is first evaluated. Fitness is a quantitative description of the execution effect of the current strategy, including task completion time, resource utilization efficiency, task priority satisfaction, etc. Strategy points with high fitness indicate that the scheduling is relatively reasonable, resource allocation is effective, and task execution is smooth. Strategy points with low fitness indicate that the current scheduling effect is not good and needs to be adjusted. After calculating the fitness of each strategy point, the fitness gap between the current strategy point and the target optimal strategy can be evaluated. The larger the fitness gap, the larger the gap between the current scheduling strategy and the ideal state, and further optimization is needed. If the gap is small, it means that the current strategy is already close to the optimal and needs fine-tuning and optimization.

[0066] When the fitness gap between the current strategy point and the optimal strategy is large, a larger optimization step size can be set. At this time, the system will make adjustments and explorations on a large scale to quickly change the current strategy and make it develop in a better direction. A larger step size helps to quickly jump out of the local optimal solution and enter the possible global optimal area. When the fitness gap is small, it means that the current strategy is already close to the optimal solution. A smaller optimization step size can be set for fine-grained adjustments. This fine-tuning helps to retain the existing advantages and eliminate small-scale deficiencies during the optimization process, thereby further improving the accuracy and adaptability of the strategy.

[0067] After setting the optimization step size, the first inspection strategy will be randomly perturbed and adjusted based on the step size to generate a one-step optimization strategy. In this process, the task scheduling is globally explored by perturbing the strategy points to find strategy points that are more likely to improve fitness. This perturbation adjustment can break through the local optimal solution, allowing the strategy to search in a wider scheduling space, increasing the diversity and exploration of the strategy. The key to perturbation adjustment lies in randomness. By randomly selecting different strategy points for adjustment, it is ensured that the scheduling strategy can be optimized from different angles, thereby avoiding falling into the local optimal solution.

[0068] After the one-step optimization strategy is generated, it is necessary to make directional adjustments to the local strategy points to generate a two-step optimization strategy. This step mainly corrects potential problems in the one-step optimization strategy through fine-grained adjustments, especially local problems such as avoidance of trajectory collisions. Specifically, according to the actual constraints of the task (such as task priority, equipment location, personnel status, etc.), the strategy points are fine-tuned to ensure that there will be no task conflicts, resource contention and other problems during the execution process. For the trajectories of patrol personnel or robots, the system will pay special attention to avoid collisions between them, or conflicts with fixed facilities and obstacles. Through fine directional adjustments, the two-step optimization strategy can better adapt to complex environments and constraints, ensuring the safety and smooth execution of local operations while ensuring global scheduling efficiency.

[0069] After the generation of the first-step and second-step optimization strategies is completed, the two are merged to finally determine a layer of iterative optimization strategy. By fusing the global perturbation and the local adjusted strategies, an optimal scheduling solution can be obtained that has both global optimization effects and can handle local detail issues. This combination of global and local optimization, dynamic adjustment, and feedback correction makes the scheduling system more adaptable and flexible when facing high-concurrency tasks.

[0070] P50: The task scheduling strategy is transmitted and delegated to the inspection target to execute and track the inspection task.

[0071] Furthermore, step P50 of the embodiment of the present application also includes: P51: Traverse the task scheduling strategy, determine the scheduling group of inspection task-inspection target, and identify the task execution limit, which is the initial node of the inspection task execution; P52: Based on the task execution limit, set the timestamp constraint for task decentralization; P53: Based on the timestamp constraint, perform transmission management on the inspection task.

[0072] It should be understood that the optimized task scheduling strategy is transmitted to the inspection target (such as inspection personnel or inspection robots) in order to execute specific inspection tasks and track and manage the tasks.

[0073] First, traverse the generated task scheduling strategy, and determine the inspection target scheduling group corresponding to each inspection task based on the task information in the strategy. This process mainly allocates tasks and inspection targets (such as inspection personnel, robots, etc.) on demand to form a matching group of tasks and targets. Each task will be assigned to the corresponding inspection target and reasonably allocated according to the resource status of the target and the priority of the task.

[0074] During this process, the system also identifies the task execution deadline for each task. The task execution deadline is the initial node when the task must begin execution, which is usually related to the priority of the task. High priority tasks may be given an earlier deadline, while low priority tasks may have a longer execution time window. The identification of task execution deadlines is critical to scheduling management because it determines whether the task can begin execution within the specified time frame.

[0075] After determining the task scheduling group and task execution deadline, set a timestamp constraint for each task according to the task execution deadline. The timestamp constraint defines the maximum delay time before the task is received and executed by the inspection target, that is, the task should be transmitted to the inspection target before this timestamp. The setting of timestamp constraints helps to optimize the transmission timeliness of tasks, ensure that tasks can be issued within the specified time limit, and reduce task scheduling errors or delays caused by communication delays. Through reasonable timestamp constraints, it can ensure that tasks are transmitted to inspection personnel or equipment in a timely manner according to priority and deadline requirements, reducing waiting time and invalid delays in task execution.

[0076] Finally, based on the timestamp constraints set earlier, the task transmission is managed. The goal of this process is to ensure that the task information can be delivered to the inspection target within the appropriate time window to achieve effective scheduling execution. Transmission management not only involves delivering task instructions to inspection personnel or robots, but also includes monitoring the transmission status of the task to ensure that the task instructions can reach the designated target accurately.

[0077] In a high-concurrency environment, transmission management also needs to take into account the communication load of the system, and may adopt strategies such as task priority adjustment and batch transmission to optimize communication efficiency. Through precise task transmission management, the execution of multiple tasks in the same period can be effectively coordinated to ensure that task scheduling can be carried out efficiently and orderly.

[0078] In summary, the embodiments of the present application have at least the following technical effects: This application uses full-element spatiotemporal perception mapping to update the inspection view in real time, and combines invariance and variability mapping to provide dynamic data support for inspection task scheduling. Based on this view, supervise the training of the scheduling optimization model, and use two-step scheduling optimization for data-driven training. Through high-concurrency task collision analysis, optimization instructions are generated, and balanced task allocation is performed in combination with the scheduling optimization model. Finally, the scheduling strategy is transmitted to the inspection target to ensure efficient execution and tracking management of the task.

[0079] The technical effect of dynamically adjusting the task scheduling strategy according to the real-time data of the inspection site and improving the real-time performance, flexibility and resource utilization efficiency of the inspection tasks has been achieved.

[0080] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0081] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0082] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A real-time optimization and scheduling method for inspection tasks based on artificial intelligence, characterized in that: The method comprises: For the inspection site, full-element spatiotemporal perception mapping is carried out to determine the inspection view, wherein the inspection view includes invariant mapping and variable mapping, and the inspection view is updated in real time; Based on the inspection view, supervise and train a scheduling optimization model, wherein the scheduling optimization model is data-driven trained in a two-step scheduling optimization mode; Receive inspection tasks, perform task collision analysis under high concurrency, and generate optimized instructions for inspection scheduling; Receive the optimization instruction, perform balanced scheduling and allocation of the inspection tasks in combination with the scheduling optimization model, and determine the task scheduling strategy; The task scheduling strategy is transmitted and delegated to the inspection target to perform the execution and tracking management of the inspection task.

2. The method for real-time optimization and scheduling of inspection tasks based on artificial intelligence according to claim 1, characterized in that: The full-element spatiotemporal perception mapping and inspection view determination include: Setting a preset migration amount, wherein the preset migration amount is an average change of the element per unit time; According to the preset migration amount, the invariant elements and variable elements in the inspection site are divided; A three-dimensional map is constructed for the invariant elements to determine a first-layer view, a three-dimensional map is constructed for the variable elements to determine a second-layer view, and the first-layer view and the second-layer view are integrated to determine the inspection view.

3. The method for real-time optimization and scheduling of inspection tasks based on artificial intelligence as claimed in claim 2 is characterized in that: Build 3D maps for variable elements and determine the second-layer view, including: For the variable elements, dynamic data is transmitted back in real time, wherein the dynamic data includes position and posture information and observation data; The second-layer view is constructed with the position and posture as nodes and the observation data as edges, wherein the second-layer view is updated in real time, and the first-layer view has cumulative drift updates under loop detection based on the second-layer view.

4. The method for real-time optimization and scheduling of inspection tasks based on artificial intelligence as claimed in claim 3 is characterized in that: The cumulative drift update under the loop detection includes: Taking the same-position inspection visit as the loop detection group, determining the first observation data and the second observation data, wherein the second observation data is the real-time observation data, and the first observation data is the observation data of the upper time node; For the invariant element, measure the element drift of the second observation data compared with the first observation data; Based on the element drift amount, the one-layer view is updated.

5. The method for real-time optimization and scheduling of inspection tasks based on artificial intelligence as claimed in claim 2 is characterized in that: The balanced scheduling allocation of the inspection tasks is performed in combination with the scheduling optimization model to determine the task scheduling strategy, including: Determine a two-step scheduling optimization method, wherein the two-step scheduling optimization method includes a one-step scheduling optimization based on global random adjustment and a two-step scheduling optimization based on local directional adjustment; Determine a first scheduling strategy, based on the two-step scheduling optimization method, take the first scheduling strategy as the initial strategy, perform iterative optimization until convergence, and select the maximum fitness strategy as the task scheduling strategy.

6. The method for real-time optimization and scheduling of inspection tasks based on artificial intelligence according to claim 5, characterized in that: The determining of the first scheduling strategy includes: Traversing the inspection tasks, combining the real-time positions of the inspection targets in the second-layer view, and determining a first inspection strategy based on the proximity principle, wherein the inspection targets include inspection personnel and inspection robots; Perform task priority avoidance based on the real-time status of the inspection target and determine the first constraint condition, wherein the real-time status includes an idle state and an inspection state; Performing task priority avoidance for the inspection task and determining a second constraint condition; A first scheduling strategy is determined based on the first inspection strategy, the first constraint condition and the second constraint condition.

7. The method for real-time optimization and scheduling of inspection tasks based on artificial intelligence according to claim 6 is characterized in that: Based on the two-step scheduling optimization method, the first scheduling strategy is used as the initial strategy to perform iterative optimization, including: Based on the fitness of the strategy point, set the optimization step size; For the first inspection strategy, perform a global strategy point random perturbation adjustment on the inspection strategy with the optimization step size to determine a one-step optimization strategy; According to the first constraint condition and the second constraint condition, the one-step optimization strategy is adjusted locally at the strategy point to determine the two-step optimization strategy; The one-step optimization strategy and the two-step optimization strategy are integrated to determine a layer of iterative optimization strategy.

8. The method for real-time optimization and scheduling of inspection tasks based on artificial intelligence according to claim 1, characterized in that: The task scheduling strategy is transmitted and delegated to the inspection target, including: Traversing the task scheduling strategy, determining the scheduling group of inspection task-inspection target, and identifying the task execution time limit, wherein the task execution time limit is the initial node of the inspection task execution; Based on the task execution time limit, set a timestamp constraint for task delegation; Based on the timestamp constraint, the inspection task is managed for transmission.

Images