Task scheduling method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a task scheduling method and device, electronic equipment and a storage medium. The method comprises the steps that conventional inspection tasks are formulated according to the growth stage of a target crop to obtain a task queue, and the task queue comprises the conventional inspection tasks; issuing the conventional inspection task to an inspection robot to be executed by the inspection robot; based on the execution result of the conventional inspection task, adjusting the inspection tasks in the task queue, and sorting the inspection tasks in the adjusted task queue according to a target sorting strategy to obtain a task execution list; and issuing the inspection task in the task execution list to the inspection robot so as to be executed by the inspection robot. According to the scheme, the problem that a traditional static scheduling scheme is disjointed with the crop growth stage and the execution result of the inspection task can be solved, dynamic generation and adjustment of the inspection task are achieved through a two-dimensional task driving algorithm based on the growth stage and the execution result, and therefore the intelligent and extensible inspection task management capacity is achieved.

Description

Technical Field

[0001] This invention relates to the field of smart agriculture technology, and more specifically to a task scheduling method and apparatus, electronic device and storage medium. Background Technology

[0002] In smart agriculture, inspection robots are responsible for collecting key parameters such as crop health status, environmental data, pests and diseases, and fruit ripeness. Traditional agricultural inspections are conducted at a fixed frequency, failing to dynamically respond to the actual growth status of crops, leading to problems such as repeated data collection, missed inspections, and resource waste. Current agricultural planting systems have weak support for "task scheduling," mainly focusing on image recognition and environmental perception, lacking intelligent and scalable inspection task management capabilities. Summary of the Invention

[0003] The present invention addresses the aforementioned problems. The present invention provides a task scheduling method, a task scheduling device, an electronic device, and a storage medium.

[0004] According to one aspect of the present invention, a task scheduling method is provided, comprising: formulating routine inspection tasks according to the growth stage of a target crop to obtain a task queue, the task queue including routine inspection tasks; distributing routine inspection tasks to inspection robots for execution by the inspection robots; adjusting the inspection tasks in the task queue based on the execution results of the routine inspection tasks, and sorting the inspection tasks in the adjusted task queue according to a target sorting strategy to obtain a task execution list; and distributing the inspection tasks in the task execution list to the inspection robots for execution by the inspection robots.

[0005] For example, based on the execution results of routine inspection tasks, adjustments are made to the inspection tasks in the task queue, including: if the execution result of any routine inspection task indicates an anomaly in the inspection area, an anomaly review task is generated and added to the task queue; and / or, if, within a first preset time period preceding the current time, the execution results of any group of routine inspection tasks for N consecutive times all indicate no anomalies in the inspection area, the execution frequency of unexecuted inspection tasks in that group of routine inspection tasks is reduced, or the unexecuted inspection tasks in that group of routine inspection tasks are merged with at least one inspection task in the task queue, wherein routine inspection tasks with the same inspection area and task type belong to the same group, and N is an integer greater than or equal to 2; and / or, if any routine inspection task fails to execute, and the routine inspection task fails to execute, the adjustment is made to adjust the inspection tasks in the task queue. If the number of consecutive failures of an inspection task within the second preset time period preceding the current time does not reach a preset threshold, the next execution time of the regular inspection task is calculated, and the regular inspection task is re-added to the task queue. If any regular inspection task fails to execute, and the number of consecutive failures of the regular inspection task within the second preset time period reaches the preset threshold, the execution log of the regular inspection task is recorded and / or a first warning message is output; and / or, if the execution of any regular inspection task is interrupted, the regular inspection task is frozen and the execution log of the regular inspection task is recorded. When the preset recovery conditions are met, the regular inspection task continues to be executed based on the breakpoint information in the execution log. Freezing includes keeping the regular inspection task in the task queue and prohibiting the regular inspection task from participating in sorting and distribution.

[0006] For example, adjusting the inspection tasks in the task queue based on the execution results of routine inspection tasks further includes: if the execution of any routine inspection task is interrupted and the freeze time of the routine inspection task exceeds a preset duration threshold, then initiating a re-evaluation of the routine inspection task to determine whether it is necessary to continue executing the routine inspection task, and / or outputting a second warning message, wherein the operation of continuing to execute the routine inspection task based on the breakpoint information when the preset recovery conditions are met is executed when it is determined that the routine inspection task needs to continue executing.

[0007] For example, the anomaly review task is configured with a corresponding urgency level, which is one of multiple preset urgency levels. Each of the multiple preset urgency levels has a corresponding response requirement. The target sorting strategy is one of at least one preset sorting strategy, which includes an urgency priority strategy. The urgency priority strategy sorts the inspection tasks according to the response requirements corresponding to the urgency level of the inspection task.

[0008] For example, the operation of routine inspection tasks based on the growth stage of the target crop is executed periodically according to preset inspection time windows. Multiple preset emergency levels include high emergency level and general emergency level. The response requirements for high emergency level include: the corresponding inspection task is executed at the nearest reachable point after the currently executing inspection task. The response requirements for general emergency level include: if the user-set time window is not received, the corresponding inspection task is executed in the next inspection time window; if the user-set time window is received, the corresponding inspection task is executed within the user-set time window.

[0009] For example, the target sorting strategy is one of at least one preset sorting strategy, which includes a scoring-first strategy. The scoring-first strategy sorts inspection tasks according to their priority scoring results. When the target sorting strategy is a scoring-first strategy, sorting the inspection tasks in the adjusted task queue according to the target sorting strategy includes: for each inspection task in the adjusted task queue, scoring the priority of various data corresponding to the inspection task according to preset priority scoring rules to obtain the priority score corresponding to each of the various data; weighting and summing the priority scores corresponding to the various data according to preset weights to obtain the priority scoring result of the inspection task; and sorting the inspection tasks in the adjusted task queue according to the priority scoring result; wherein, the various data... The priority scoring criteria include at least two of the following: the pest and disease level of the inspection area, the urgency of the crop growth stage in the inspection area, the historical frequency of anomalies in the inspection area, the distance between the inspection area and the current travel path, the difference between the estimated power required to perform the inspection task and the remaining power of the inspection robot, and the test level of the inspection area. The preset priority scoring rules include at least two of the following: the higher the pest and disease level, the higher the priority score; the higher the urgency of the growth stage, the higher the priority score; the higher the historical frequency of anomalies, the higher the priority score; the closer the distance, the higher the priority score; the greater the power difference, the lower the priority score; and the higher the test level, the higher the priority score.

[0010] For example, sorting the inspection tasks in the adjusted task queue according to the target sorting strategy further includes: adjusting the preset weights corresponding to at least some of the data among various data in response to the user's weight setting instruction; and / or, determining the data to participate in the priority scoring in response to the user's data selection instruction.

[0011] For example, sorting the inspection tasks in the adjusted task queue according to the target sorting strategy includes: sorting the inspection tasks in the adjusted task queue according to the target sorting strategy based on constraints and task allocation mechanism; wherein, the constraints include one or more of the following: the power safety threshold of the inspection robot, the safe range of the motor parameters of the inspection robot, the restricted entry time of the target plot, the restricted entry time of the target point, and the adjacency of the planned path; the task allocation mechanism is a concurrent allocation mechanism or a serial allocation mechanism.

[0012] For example, the target sorting strategy is one of at least two preset sorting strategies. Sorting the inspection tasks in the adjusted task queue according to the target sorting strategy includes: in response to the user's strategy selection instruction, determining the preset sorting strategy selected by the user as the target sorting strategy, or, when a preset trigger condition is met, determining the preset sorting strategy corresponding to the preset trigger condition as the target sorting strategy; and sorting the remaining unexecuted inspection tasks in the adjusted task queue according to the latest determined target sorting strategy.

[0013] For example, after the inspection tasks in the task execution list are sent to the inspection robot, the method further includes: tracking the execution status of the inspection tasks and feeding back the execution status to the remote task system in real time. The execution status includes execution completed, execution failed, execution interrupted, and execution skipped.

[0014] For example, after the inspection tasks in the task execution list are sent to the inspection robot, the method further includes: recording the execution log of the inspection task and uploading the execution log to a preset database. The execution log includes the execution result of the inspection task. In the next execution of the operation of formulating a regular inspection task based on the growth stage of the target crop, the regular inspection task is optimized based on the execution log stored in the preset database.

[0015] For example, the method further includes: if the remaining power of the inspection robot is less than or equal to the power safety threshold, then stop issuing the inspection task and control the inspection robot to return to the preset charging location for charging.

[0016] According to another aspect of the present invention, a task scheduling device is also provided, comprising: a formulation module for formulating routine inspection tasks according to the growth stage of a target crop to obtain a task queue, the task queue including routine inspection tasks; a first distribution module for distributing routine inspection tasks to inspection robots for execution by the inspection robots; an adjustment module for adjusting the inspection tasks in the task queue based on the execution results of the routine inspection tasks, and sorting the inspection tasks in the adjusted task queue according to a target sorting strategy to obtain a task execution list; and a second distribution module for distributing the inspection tasks in the task execution list to the inspection robots for execution by the inspection robots.

[0017] According to another aspect of the present invention, an electronic device is also provided, including a processor and a memory, wherein the memory stores computer program instructions, which are executed by the processor to perform the task scheduling method described above.

[0018] According to another aspect of the present invention, a storage medium is also provided, on which program instructions are stored, wherein the program instructions are used to execute the above-described task scheduling method when running.

[0019] The task scheduling method, apparatus, electronic device, and storage medium according to embodiments of the present invention can automatically generate routine inspection tasks based on the growth stage of the target crop, and automatically adjust and sort the inspection tasks according to the real-time execution results of the routine inspection tasks to obtain a task execution list, and assign each inspection task in the task execution list to the inspection robot for execution. This task scheduling scheme can solve the problem of the disconnect between traditional static scheduling schemes and crop growth stages and the execution results of inspection tasks. Through a two-dimensional task-driven algorithm based on growth stages and execution results, it realizes the dynamic generation and adjustment of inspection tasks, thereby achieving intelligent and scalable inspection task management capabilities. Attached Figure Description

[0020] The above and other objects, features, and advantages of the present invention will become more apparent from the more detailed description of the embodiments of the invention in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same parts or steps.

[0021] Figure 1 A schematic flowchart of a task scheduling method according to an embodiment of the present invention is shown;

[0022] Figure 2 A schematic block diagram of a task scheduling apparatus according to an embodiment of the present invention is shown; and

[0023] Figure 3 A schematic block diagram of an electronic device according to an embodiment of the present invention is shown. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the present invention more apparent, exemplary embodiments according to the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely a part of the embodiments of the present invention, and not all of the embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein. Based on the embodiments of the present invention described herein, all other embodiments obtained by those skilled in the art without inventive effort should fall within the protection scope of the present invention.

[0025] Traditional agricultural inspection employs a static task scheduling mechanism, which generates inspection tasks in a single way, fails to consider the actual growth cycle (i.e., growth stage) of crops, and lacks a dynamic adjustment mechanism. The execution results of inspection tasks cannot automatically influence subsequent task scheduling. To at least partially address these problems, this invention provides a task scheduling method. This method utilizes a two-dimensional task-driven algorithm based on growth stage and execution results to achieve dynamic generation and adjustment of inspection tasks. This task scheduling scheme is applicable to various planting scenarios such as greenhouse agriculture, orchards, and facility agriculture.

[0026] Figure 1 A schematic flowchart illustrating a task scheduling method 100 according to an embodiment of the present invention is shown. The task scheduling method 100 described herein can be applied to any electronic device with data processing capabilities and / or instruction execution capabilities, i.e., it is executed by an electronic device. This electronic device may include, but is not limited to, personal computers, servers, mobile terminals, inspection robots, etc. Exemplarily and not limitingly, the task scheduling method 100 can be deployed on an inspection robot, or on an edge node or a cloud server. Exemplarily, the task scheduling method 100 can also be partially deployed on an inspection robot and partially deployed on an edge node and / or a cloud server. The electronic device used to execute the task scheduling method 100 can be referred to as a task scheduling system. Figure 1 As shown, the model management method 100 includes steps S110, S120, S130 and S140.

[0027] In step S110, routine inspection tasks are formulated according to the growth stage of the target crop to obtain a task queue, which includes routine inspection tasks.

[0028] The target crop is the crop to be inspected, which can be any type of crop, such as grapes, cucumbers, cabbage, apples, etc. The target crop can include only one type of crop or multiple different types. The target crop is located within the target planting area. The target planting area can be any area, including but not limited to open fields, greenhouses, plastic tunnels, and orchards. The target planting area can include one or more plots, and each plot can include one or more points. The "plot" described in this document is a logical plot; each plot can be defined by a set of boundary coordinates and has unique identification information. Each plot can be further divided into several points, and each point can also have unique identification information and be bound to a single crop. The crop types within the same plot can be the same or different. It is preferable that the crop types within the same plot are the same. The growth stages of the same crop located in different plots or points can be the same or different. The growth stage is the growth cycle, such as germination, seedling, fruiting, flowering, and maturity. Each inspection task is a task instance, which can be represented by unique identification information (e.g., task ID). Each inspection task can correspond to a specific location to be inspected (referred to as the inspection area in this document). The inspection area for each task can include at least a portion of the target planting area, i.e., one or more plots. The inspection area for each task can also include at least a portion of the points within any plot, i.e., one or more locations within that plot. Each inspection task can correspond to a task type. Task types can be distinguished based on the inspection purpose of the task. For example, task types can include one or more of the following: pest and disease identification, weed identification, flower count, fruit count, nitrogen content measurement, water content measurement, chlorophyll content measurement, leaf area index measurement, leaf temperature measurement, fruit sweetness measurement, etc. Each inspection task can also correspond to an execution time, which can be a specific point in time or a time period. Different inspection tasks may correspond to different inspection areas and / or task types and / or execution times. The number of regular inspection tasks included in the task queue can be one or more, depending on the actual situation.

[0029] Routine inspection tasks are periodic inspection tasks performed according to a preset inspection cycle. Step S110, i.e., formulating routine inspection tasks, can be executed by the task rule engine. For example, routine inspection tasks for the inspection robot can be automatically generated by combining the target crop type, the target crop's growth stage, the Geographic Information System (GIS) of the target planting area, the plot calendar, and inspection templates. The inspection template can store preset inspection cycles and task types corresponding to at least one crop type at different growth stages. For example, the inspection template can store information such as "Grapes - Flowering stage - Daily inspection - (Pest and disease identification + flower count)" and "Cucumber - Seedling stage - Inspection every three days - Weed identification." Therefore, by querying the inspection template based on the target crop type and growth stage, the preset inspection cycle and task type for the target crop at the current growth stage can be determined. Simultaneously, by combining the GIS and the plot calendar, the required inspection location (i.e., inspection area) and specific execution time for each routine inspection task can be determined, thereby generating the corresponding routine inspection task. The task type and preset inspection cycle for each routine inspection task are determined based on the crop type and growth stage of the corresponding inspection area. Step S110 can be executed according to a basic cycle, such as following an inspection template for the target crop (e.g., every 3 days during the seedling stage, daily during the flowering stage). Step S110 can also be dynamically triggered; for example, an incremental task can be generated immediately when a significant change in the resource status of the inspection robot is detected. Step S110 can also be executed in batch mode, such as refreshing the task queue at 00:00 daily.

[0030] In step S120, the routine inspection task is sent to the inspection robot for execution.

[0031] The inspection tasks described herein (including routine inspection tasks and anomaly review tasks) are used to instruct inspection robots to collect data to analyze the growth status of target crops and / or the environmental conditions surrounding the target crops (e.g., light intensity). The data collected by the inspection robot (which may be referred to as planting data) may include crop data of the target crop and / or environmental data of the target planting area. For example, crop data may include one or more of color (RGB) images, depth images, thermal infrared images, hyperspectral images, etc. Each of the RGB images, depth images, thermal infrared images, and hyperspectral images can be a static image or a continuous dynamic image, i.e., a video stream. Environmental data may include meteorological data reflecting the air conditions inside and / or outside the target planting area. For example, environmental data may include one or more of air temperature, air humidity, light intensity, air carbon dioxide concentration, etc.

[0032] The inspection robot can be equipped with one or more cameras and / or environmental sensors to collect data. The camera of the inspection robot can include one or more of the following: color (RGB) camera, color depth (RGBD) camera, thermal infrared camera, hyperspectral camera, etc. Correspondingly, the crop data can include one or more of the following: RGB images acquired by an RGB camera, RGB images acquired by an RGBD camera, depth images acquired by an RGBD camera, thermal infrared images acquired by a thermal infrared camera, hyperspectral images acquired by a hyperspectral camera, etc. The RGB camera can be, for example, a high-resolution RGB camera with at least 12 million effective pixels. Details of the target crop, such as color, texture, and small lesions, can be clearly identified from the RGB images acquired by the high-resolution RGB camera. The hyperspectral camera of the inspection robot can dynamically adjust imaging parameters through an adaptive spectral selection algorithm to optimize the quality of crop data acquisition. The environmental sensors of the inspection robot can collect environmental data. Environmental sensors can include one or more of the following: air temperature sensor, air humidity sensor, light sensor, carbon dioxide concentration sensor, etc. Each of the environmental sensors can exist independently or multiple sensors can be integrated together; for example, the air temperature sensor and air humidity sensor can be implemented using an integrated air temperature and humidity sensor. For example, environmental data may include one or more of the following: air temperature collected by an air temperature sensor, air humidity collected by an air humidity sensor, light intensity collected by a light sensor, and air carbon dioxide concentration collected by a carbon dioxide concentration sensor.

[0033] The inspection robot described herein can be any type of robot capable of performing inspection tasks, including but not limited to one or more of ground inspection robots, aerial inspection robots (e.g., drones), and underwater inspection robots. In step S120, the inspection robots corresponding to any two routine inspection tasks, i.e., the inspection robots used to perform these two routine inspection tasks, can be the same or different. The number of inspection robots used to receive routine inspection tasks in step S120 can be one or more.

[0034] In step S130, based on the execution results of regular inspection tasks, the inspection tasks in the task queue are adjusted, and the inspection tasks in the adjusted task queue are sorted according to the target sorting strategy to obtain a task execution list.

[0035] For example, adjustments can include adding, deleting, and updating the execution time of inspection tasks in the task queue. That is, the task scheduling system can automatically add, delete, or update subsequent inspection tasks based on the execution results. For instance, if an anomaly (such as yellowing leaves or lesion coverage) is identified based on the execution results, an anomaly review task can be automatically generated. Both anomaly review tasks and regular inspection tasks are inspection tasks. As another example, if the same group of regular inspection tasks (regular inspection tasks with the same inspection area and task type belong to one group) fails to identify anomalies in three consecutive executions (each execution result corresponds to one regular inspection task), its inspection frequency can be reduced or the group of regular inspection tasks can be merged with other inspection tasks. Furthermore, if the inspection area of ​​a regular inspection task is inaccessible or temporarily restricted due to obstacles, the regular inspection task can be temporarily frozen and breakpoint information recorded. The execution time of an inspection task in the task queue can be represented by an execution timestamp associated with the inspection task. After adjustments, the inspection tasks in the task queue can be sorted according to the target sorting strategy. The target ranking strategy can be such as an energy consumption priority strategy or an urgency priority strategy. For example, the target ranking strategy can be implemented using a deep learning model, where inspection tasks are input into the deep learning model, which can automatically rank them to obtain a ranked inspection task list. This approach requires high training costs. Alternatively, the order of inspection tasks can be manually adjusted by the user. The ranked inspection tasks can then be used as a task execution list.

[0036] In step S140, the inspection tasks in the task execution list are sent to the inspection robot for execution.

[0037] The task scheduling system can distribute the sorted inspection tasks to the inspection robots for execution. In step S140, the inspection robots corresponding to any two inspection tasks in the task execution list, i.e., the inspection robots used to execute these two inspection tasks, can be the same or different. The number of inspection robots used to receive inspection tasks in step S140 can be one or more. The inspection robots used to receive inspection tasks in step S140 can be exactly the same as, or completely different from, the inspection robots used to receive regular inspection tasks in step S120, or they can be partially the same and partially different.

[0038] The aforementioned task scheduling method can automatically generate routine inspection tasks based on the growth stage of the target crop, and automatically adjust and sort the inspection tasks according to the real-time execution results of the routine inspection tasks to obtain a task execution list, and then assign each inspection task in the task execution list to the inspection robot for execution. This task scheduling scheme can solve the problem of the disconnect between traditional static scheduling schemes and crop growth stages and the execution results of inspection tasks. Through a two-dimensional task-driven algorithm based on growth stages and execution results, it realizes the dynamic generation and adjustment of inspection tasks, thereby achieving intelligent and scalable inspection task management capabilities.

[0039] According to a first embodiment of the present invention, the inspection tasks in the task queue are adjusted based on the execution results of routine inspection tasks, including: if the execution result of any routine inspection task indicates that there is an anomaly in the inspection area, an anomaly review task is generated and added to the task queue.

[0040] The execution result can include the data collected by the inspection robot. If the execution result includes all the data required for this inspection task, it indicates that the inspection task has been completed. If the execution result is that no data was collected or only a portion of the data required for this inspection task was collected, it indicates that the inspection task failed, was interrupted, or was skipped. Execution failure means that an error occurred at a certain step of the inspection task and it cannot continue (e.g., the inspection robot has a equipment malfunction). In this case, the execution log can be recorded directly and / or a warning message can be issued (referred to as the first warning message in this article). It can also be retried once or multiple times. If it fails continuously, the execution log can be recorded again and / or a warning message can be issued. Execution interruption means that external factors interrupt the process (e.g., insufficient remaining power, temporary restriction on the inspection area, manual pause, etc.). In this case, the execution log can be recorded, and the execution log contains breakpoint information. Execution can be resumed when the external factors are eliminated. Skipping execution means that execution is explicitly not performed within the current inspection time window. This is usually done manually by the user, and execution will not continue afterward.

[0041] Upon completion of a routine inspection task, the results analysis engine can analyze the execution results to determine if any anomalies exist in the inspected area. If anomalies are found, an anomaly review task with the same inspection area and task type as the routine inspection task can be generated. The anomaly review task involves re-inspecting the identified anomaly area for verification. Anomalies in the inspection area can include anomalies in the crop itself within the inspection area, and / or anomalies in the internal and / or external environment of the inspection area. For example, if the execution results (data collected by the inspection robot) identify lesions in the crop within the inspection area, where the confidence level of the lesions is greater than or equal to a preset confidence threshold (e.g., 0.8), and the proportion of the lesion area to the crop surface area is greater than a preset proportion threshold, then an anomaly can be determined, and an anomaly review task can be generated for that inspection area for re-inspection. For example, if the execution results identify a rapid drop in air temperature within the inspection area over a short period, such as exceeding a preset temperature threshold (e.g., 10°C) within a preset time period (e.g., 3 minutes), an environmental anomaly can be identified. An anomaly review task can then be generated for this inspection area, and a re-inspection can be performed. The task scheduling system can add the anomaly review task to the task queue for distribution to the inspection robot. By automatically generating and adding anomaly review tasks, inspection areas with anomalies can be automatically re-inspected, forming a closed-loop management system and effectively improving the accuracy of agricultural production management and risk control capabilities.

[0042] According to a second embodiment of the present invention, the inspection tasks in the task queue are adjusted based on the execution results of routine inspection tasks, including: if, within a first preset time period preceding the current time, the execution results of any group of routine inspection tasks for N consecutive times indicate that there are no abnormalities in the inspection area, then the execution frequency of the unexecuted inspection tasks in that group of routine inspection tasks is reduced, or the unexecuted inspection tasks in that group of routine inspection tasks are merged with at least one inspection task in the task queue, wherein routine inspection tasks with the same inspection area and task type belong to the same group, and N is an integer greater than or equal to 2.

[0043] A group of routine inspection tasks includes routine inspection tasks with the same inspection area and task type. For example, if crop data is collected every other day for plot A to identify pests and diseases, then a routine inspection task of pest and disease identification is performed every other day. These routine inspection tasks can be considered as a group. Between two adjacent routine inspection tasks in each group, there may be routine inspection tasks from other groups (i.e., different inspection areas and / or task types), or there may be no other routine inspection tasks, depending on the actual task scheduling. The first preset time period can be set to any suitable value as needed, such as 3 days, 7 days, 10 days, etc. N can be an integer greater than or equal to 2, and it can be set as needed, for example, N can be equal to 3, 4, 5, etc. For example, if any group of routine inspection tasks has no abnormalities in the results of three consecutive executions within the most recent (i.e., from the current time backward) 7 days (each execution result is obtained by a routine inspection task), then the subsequent inspection frequency of that group of routine inspection tasks can be reduced, that is, the execution frequency of unexecuted inspection tasks in that group of routine inspection tasks can be reduced. Alternatively, unexecuted inspection tasks within the same inspection group can be merged with other inspection tasks. This means reducing the inspection frequency, which updates the execution time of subsequent regular inspection tasks, and lengthens the interval between two consecutive executions. The merging of inspection tasks can be performed according to preset merging rules. For example, similar inspection tasks for the same or adjacent plots can be merged. Similar inspection tasks are those with the same task type. Using this approach, the inspection frequency or number of inspection tasks can be dynamically adjusted based on feedback from the execution results, thus evenly distributing the inspection robot's workload and saving inspection time.

[0044] According to a third embodiment of the present invention, the inspection tasks in the task queue are adjusted based on the execution results of routine inspection tasks, including: if any routine inspection task fails to execute, and the number of consecutive failures of the routine inspection task within a second preset time period prior to the current time does not reach a preset number threshold, then the next execution time of the routine inspection task is calculated, and the routine inspection task is added back to the task queue; if any routine inspection task fails to execute, and the number of consecutive failures of the routine inspection task within the second preset time period reaches a preset number threshold, then the execution log of the routine inspection task is recorded and / or a first warning message is output.

[0045] The preset threshold number of attempts can be set to any suitable value as needed, such as 3, 4, or 5 times. The second preset time period can also be set to any suitable value as needed, such as 3 days, 7 days, or 10 days. The second preset time period can be equal to or different from the first preset time period. As mentioned above, an error may occur when the inspection task reaches a certain step and cannot continue (e.g., the inspection robot has a equipment malfunction), causing the task to fail. It can be understood that when counting the number of failures of any regular inspection task in the second preset time period from the current moment forward after any regular inspection task fails, the failure of this execution is also included in the count. For example, if any regular inspection task has not failed 3 times consecutively in the most recent 7 days (i.e., from the current moment forward), the next execution time can be calculated according to the exponential backoff algorithm, and the regular inspection task can be added back to the task queue according to the next execution time, thereby retrying to execute the regular inspection task. If any routine inspection task fails three times consecutively within the last seven days, it can be confirmed that the routine inspection task has indeed failed. The execution log of the routine inspection task can be saved to a preset database, and / or a first warning message can be output. For example, the execution log may include one or more of the following: the identification information of the routine inspection task (e.g., task ID), failure time, failure reason, failure location, number of retries, task progress for each execution, and the identification information of the inspection robot executing the routine inspection task (e.g., robot ID). The failure location is the specific location where the failure occurred, such as a specific plot of land and / or point. Task progress may include collected blocks and / or points, collected data, uncollected blocks and / or points, and uncollected data. Saving the execution log of the routine inspection task to the preset database facilitates subsequent viewing and understanding of the task's execution status by users. Outputting the first warning message may include, for example, pushing the first warning message to the user's mobile terminal (e.g., mobile phone), or outputting the first warning message through locally set flashlights, speakers, etc. The first warning message can prompt manual intervention. According to this embodiment, for routine inspection tasks that fail to execute, retrying is possible until the number of consecutive failures within a second preset time period reaches a preset number. This approach can improve the fault tolerance of task scheduling.

[0046] According to the fourth embodiment of the present invention, the inspection tasks in the task queue are adjusted based on the execution results of the routine inspection tasks, including: if the execution of any routine inspection task is interrupted, the routine inspection task is frozen and the execution log of the routine inspection task is recorded, and when the preset recovery conditions are met, the routine inspection task is continued to be executed based on the breakpoint information in the execution log. The freezing includes keeping the routine inspection task in the task queue and prohibiting the routine inspection task from participating in sorting and distribution.

[0047] There are various reasons why an inspection task might be interrupted, such as the inspection area being temporarily inaccessible due to obstacles, the inspection area being temporarily restricted, insufficient resources for the inspection robot (e.g., insufficient battery power), or manual suspension of the inspection task. When a regular inspection task is interrupted, it can be temporarily frozen and the breakpoint information recorded. Execution can then be resumed (i.e., continue execution) when preset recovery conditions are met. Freezing means keeping the regular inspection task in the task queue but not participating in sorting or distribution. Recovery includes allowing the regular inspection task to participate in sorting and distribution. Triggers for recovery may include, for example, the inspection area's path becoming accessible again, the restricted period for the inspection area ending, sufficient resources for the inspection robot being restored (e.g., remaining battery power greater than or equal to a preset battery threshold), or manual unfreezing of the inspection task. For example, breakpoint information may include one or more of the following: interruption time, interruption location, interruption reason, task progress at the time of interruption, and a snapshot of the site. Interruption time is the moment the interruption occurred. Interruption location is the specific location at the time of interruption, such as a specific plot of land and / or point. Interruptions can be caused by various factors, such as sudden thunderstorms, drone disconnection, insufficient battery power, or the discovery of a major epidemic requiring urgent reporting. Task progress can include collected blocks and / or points, collected data, uncollected blocks and / or points, and uncollected data. On-site snapshots can include photos or videos of the on-site environment (such as weather conditions and crop status) at the time of interruption. Using this embodiment, when an inspection task is interrupted, execution can automatically resume from the breakpoint, achieving intelligent breakpoint continuation inspection, i.e., an intelligent fault recovery mechanism, thereby improving task scheduling efficiency.

[0048] Any two or more of the first, second, third, and fourth embodiments described above can be combined in the same embodiment.

[0049] According to an embodiment of the present invention, adjusting the inspection tasks in the task queue based on the execution results of routine inspection tasks further includes: if the execution of any routine inspection task is interrupted and the freeze time of the routine inspection task exceeds a preset duration threshold, then initiating a re-evaluation of the routine inspection task to determine whether it is necessary to continue executing the routine inspection task, and / or, outputting a second warning message, wherein the operation of continuing to execute the routine inspection task based on the breakpoint information when the preset recovery conditions are met is executed when it is determined that it is necessary to continue executing the routine inspection task.

[0050] The preset duration threshold can be set to any suitable duration as needed, such as 24 hours, 48 ​​hours, 36 hours, etc. For example, if the freeze time of a routine inspection task exceeds 48 hours, a reassessment of the routine inspection task can be initiated to determine whether it needs to continue, and / or, a second warning message can be output. The operation of continuing the routine inspection task based on breakpoint information when preset recovery conditions are met is executed when it is determined that the routine inspection task needs to continue. Reassessment may include determining whether the routine inspection task is still worth continuing based on preset assessment conditions. For example, preset assessment conditions may include one or more of the following: current environment, task value, and resource availability. The current environment can be determined based on current environmental data, and the task value can be determined based on the importance of the routine inspection task. For example, if the current temperature is below a preset temperature threshold, it indicates that the conditions for executing the interrupted routine inspection task are no longer met, and execution can be stopped. As another example, if the task scheduling system assesses that the importance of the interrupted routine inspection task is not high, execution can also be stopped. Resource availability refers to the availability of resources required for the execution of routine inspection tasks. Resources may include, for example, the remaining battery power of the inspection robot and the status of its motors. The motor status of the inspection robot can be represented by its motor parameters. Motor parameters may include one or more of the following: drive current, drive voltage, speed, temperature, and pulse width modulation (PWM) duty cycle. For example, if the task scheduling system evaluates that the motor status of the inspection robot does not meet preset requirements, the interrupted routine inspection task can be discontinued. Re-evaluation ensures task integrity and accuracy of execution results. Outputting a second warning message may include, for example, pushing the second warning message to the user's mobile terminal (e.g., a mobile phone), or outputting the second warning message through locally set flashlights, speakers, etc. The second warning message can prompt manual intervention.

[0051] If the freeze time of a routine inspection task is too long (i.e., exceeds the preset time threshold), the environmental conditions around the target crop may have changed, and the necessity of executing the routine inspection task may also change. Therefore, when the freeze time of a routine inspection task exceeds the preset time threshold, the routine inspection task can be re-evaluated to determine whether it still needs to be executed. If it does, it can continue; otherwise, it can be abandoned, for example, by deleting it from the task queue. Optionally, if the freeze time of a routine inspection task is too long, a second warning message can be sent to alert the user so that the user can determine whether the routine inspection task needs to continue or whether it needs to be adjusted. Optionally, the above re-evaluation and output of the second warning message can be performed simultaneously.

[0052] By adopting the above solution, when the freeze time of routine inspection tasks is too long, the tasks can be re-evaluated and / or a second warning message can be output to avoid unnecessary execution of routine inspection tasks, thereby reducing the waste of resources.

[0053] According to an embodiment of the present invention, the anomaly review task is configured with a corresponding urgency level. The urgency level belongs to one of multiple preset urgency levels. Each of the multiple preset urgency levels has a corresponding response requirement. The target sorting strategy is one of at least one preset sorting strategy. The at least one preset sorting strategy includes an urgency priority strategy. The urgency priority strategy sorts the inspection tasks according to the response requirements corresponding to the urgency level of the inspection task.

[0054] For example, an anomaly review task can be configured with a corresponding urgency level based on the severity of the anomaly in its inspected area. The urgency level is one of several preset urgency levels. These preset urgency levels can be set as needed, and may include, for example, high urgency and general urgency levels. For instance, a "high urgency level" task can be set for severe anomalies (e.g., high-risk pests and diseases, rapidly spreading pests and diseases), and a "general urgency level" task can be set for general anomalies (e.g., the presence of weeds). Each preset urgency level can have corresponding response requirements, such as immediate response, response within a preset time window, or response during idle periods. For example, at least some regular inspection tasks in the task queue can also be configured with corresponding urgency levels as needed. Optionally, at least some regular inspection tasks in the task queue can be configured with the lowest urgency level by default. The lowest urgency level can be a general urgency level or lower.

[0055] The target sorting strategy is one of at least one preset sorting strategy. When there is only one preset sorting strategy, it can be directly determined as the target sorting strategy. When there are multiple preset sorting strategies, they can be switched as needed, and the preset sorting strategy switched to each time becomes the target sorting strategy. During the sorting of inspection tasks in the task queue, the sorting strategy can be switched at any time. At least one preset sorting strategy may include one or more of the following: urgency priority strategy, energy consumption priority strategy, and rating priority strategy. In this embodiment, at least one preset sorting strategy may include an urgency priority strategy. An urgency priority strategy is a decision principle that sorts inspection tasks according to the response requirements corresponding to the urgency level of the inspection tasks. It can be understood that the higher the urgency level, the faster the response speed can be required, i.e., the shorter the response time. An energy consumption priority strategy is a decision principle that takes minimizing the total energy consumption of the system as the highest optimization goal in task planning and execution. A rating priority strategy is a decision principle that sorts inspection tasks according to the priority rating results of the inspection tasks.

[0056] By adopting the above scheme, when generating anomaly review tasks, a corresponding urgency level is configured for each task. This allows the task scheduling system to prioritize tasks based on their urgency level when switching to an urgency-first strategy. This approach enables the task scheduling system to adjust the order of tasks according to their urgency, prioritizing more urgent tasks and thus improving its ability to handle risks.

[0057] According to an embodiment of the present invention, the operation of routine inspection tasks based on the growth stage of the target crop is executed periodically according to a preset inspection time window. Multiple preset emergency levels include high emergency level and general emergency level. The response requirements corresponding to the high emergency level include: the corresponding inspection task is executed at the nearest reachable point after the currently executing inspection task. The response requirements corresponding to the general emergency level include: if the user-set time window is not received, the corresponding inspection task is executed in the next inspection time window; if the user-set time window is received, the corresponding inspection task is executed within the user-set time window.

[0058] The operation of routine inspection tasks based on the growth stage of the target crop is executed periodically according to the preset inspection time window. For example, if the inspection time window is 24 hours (0:00 to 24:00 every day), then the operation of routine inspection tasks based on the growth stage of the target crop can be executed once every 24 hours. High-urgency inspection tasks can be executed in advance. For example, for serious anomalies (such as high-risk pests and diseases, rapidly spreading pests and diseases, etc.), an "high-urgency" anomaly review task can be set and executed in advance in the task queue, that is, the closest reachable point after the current task node is executed first. For general anomalies, a "general-urgency" anomaly review task can be set, which is inserted by default in the time window of the next routine inspection task (i.e., the next inspection time window). For example, users can customize the review time window (i.e., the user-defined window), which can override the time window set by the default strategy (i.e., the next inspection time window), and the anomaly review task can be inserted and executed in the user-defined time window first.

[0059] By adopting the above technical solution, high-urgency inspection tasks can be responded to and executed immediately, while general-level inspection tasks can be executed within a suitable time window. This allows for timely response to high-risk emergency tasks and further improves the risk resistance of the task scheduling system.

[0060] According to an embodiment of the present invention, the target sorting strategy is one of at least one preset sorting strategy, which includes a scoring priority strategy. The scoring priority strategy sorts the inspection tasks according to their priority scoring results. When the target sorting strategy is a scoring priority strategy, sorting the inspection tasks in the adjusted task queue according to the target sorting strategy may include: for each inspection task in the adjusted task queue, scoring the priority of various data corresponding to the inspection task according to preset priority scoring rules to obtain the priority score corresponding to each of the various data; weighting and summing the priority scores corresponding to each of the various data according to preset weights to obtain the priority scoring result of the inspection task; and sorting the inspection tasks in the adjusted task queue according to the priority scoring result. The various data include at least two of the following: the pest and disease level of the inspection area of ​​the inspection task, the urgency of the crop growth stage of the inspection area of ​​the inspection task, the historical frequency of anomalies in the inspection area of ​​the inspection task, the distance between the inspection area of ​​the inspection task and the current travel path, the difference between the estimated power required to perform the inspection task and the remaining power of the inspection robot, and the test level to which the inspection area of ​​the inspection task belongs. The preset priority scoring rules include at least two of the following: the higher the level of pests and diseases, the greater the corresponding priority score; the higher the urgency of the growth stage, the greater the corresponding priority score; the higher the frequency of historical anomalies, the greater the corresponding priority score; the closer the distance, the greater the corresponding priority score; the greater the difference in power, the smaller the corresponding priority score; and the higher the test level, the greater the corresponding priority score.

[0061] As described above, at least one preset sorting strategy may include a scoring priority strategy. A scoring priority strategy is a decision principle that sorts inspection tasks according to their priority scoring results. The priority scoring results of inspection tasks can be obtained by weighted summation of the priority scores of various data corresponding to the inspection task, and the priority score of each data can be determined according to preset priority scoring rules. The various data are multi-dimensional data. For example, the various data may include the pest and disease level of the inspection area of ​​the inspection task. The pest and disease level can be identified and determined based on the execution results of historical inspection tasks within a previous preset time period (which may be called the third preset time period). The third preset time period can be set as needed, such as 7 days, 14 days, 30 days, or 90 days. For example, 7 days can be used as the default historical statistical window for scoring (i.e., the third preset time period). The third preset time period can be user-defined or allowed to be adjusted based on the default settings. The third preset time period can be the same as or different from either the first or second preset time period mentioned above. After each inspection task is executed, the task scheduling system can save its corresponding execution log in a preset database. For example, the preset database can save execution logs in a first-in, first-out (FIFO) manner, for example, retaining execution logs for 180 days or more. The execution logs include the results of the inspection tasks, such as the collected data. Based on the data collected by the inspection tasks, the pest and disease severity level of the inspection area can be identified. The classification method for pest and disease severity can be set as needed, and this document does not limit it. It is understood that a higher pest and disease severity level indicates a more severe pest and disease problem, and its priority score can be set higher. For example, various data can include the urgency of the crop growth stage in the inspection area of ​​the inspection task. Each growth stage of the crop can correspond to a preset growth stage urgency. Based on the current growth stage of the crop in the inspection area, the urgency of the growth stage corresponding to that current growth stage can be determined (i.e., the urgency of the crop growth stage in the inspection area). The urgency of the growth stage corresponding to each growth stage of the crop can be set as needed, for example, the flowering stage has the highest urgency, the seedling stage has the second highest urgency, the fruiting stage has the lowest urgency, and so on. The higher the urgency of the growth stage, the higher the corresponding priority score can be. For example, various data may include the historical anomaly frequency of the inspection area in the inspection task. The historical anomaly frequency can be determined based on the execution results of historical inspection tasks within a previous preset time period (which may be referred to as the fourth preset time period). The fourth preset time period can be set as needed, such as 7 days, 14 days, 30 days, or 90 days. For example, 7 days can be used as the default historical statistics window for scoring (i.e., the fourth preset time period). The fourth preset time period can be customized by the user or allowed to be adjusted based on the default settings. The fourth preset time period can be the same as or different from any of the first, second, and third preset time periods mentioned above.The higher the frequency of historical anomalies, the higher the corresponding priority score can be. For example, various data may include the distance between the inspection area of ​​the inspection task and the current travel path. The task scheduling system can store a navigation map of the target planting area. Based on the map, path planning can be performed for each inspection task, and the distance between the inspection area of ​​each inspection task and the current travel path of the inspection robot executing that task can be determined in real time. The closer the distance, the higher the corresponding priority score can be. For example, various data may include the difference between the estimated power required to execute the inspection task and the remaining power of the inspection robot. The task scheduling system can monitor the status of the inspection robot in real time, including its remaining power. The task scheduling system can compare the remaining power with the estimated power required to execute the inspection task. When the remaining power is insufficient to support the execution of the inspection task, the execution of the inspection task can be delayed; that is, the larger the aforementioned power difference, the lower the corresponding priority score can be. For example, various data may include the trial level to which the inspection area of ​​the inspection task belongs. Trial levels can be divided as needed. For example, areas used for variety comparison trials and cultivation technique trials have a higher priority than ordinary non-trial areas. That is, the higher the trial level, the greater the corresponding priority score. The data types corresponding to any two different inspection tasks can be all the same, all different, or partially the same and partially different. The number of data types corresponding to any two different inspection tasks can be the same or different. The sum of the preset weights for the various data types is 1.

[0062] Table 1 below shows the preset weights and priority scoring rules for various types of data according to an embodiment of the present invention.

[0063] Table 1. Preset weights and priority scoring rules for various data types

[0064]

[0065]

[0066] After determining the priority score of the inspection tasks using the aforementioned preset weights and priority scoring rules, the inspection tasks can be sorted according to the priority score. For example, the higher the priority score, the earlier the inspection task will be executed.

[0067] By adopting the above technical solution, multi-dimensional information, such as crop growth stage, historical anomaly frequency, distance of inspection area, and power estimation, can be combined to comprehensively evaluate the priority of inspection tasks and then sort them. This sorting method takes into account all aspects and can improve the rationality of inspection task scheduling.

[0068] According to an embodiment of the present invention, sorting the inspection tasks in the adjusted task queue according to the target sorting strategy further includes: adjusting the preset weights corresponding to at least some of the data among multiple data in response to the user's weight setting instruction; and / or, determining the data to participate in the priority scoring in response to the user's data selection instruction.

[0069] Users can adjust the preset weights of all or some of the data from various datasets as needed. For each type of data, the user can directly set the initial preset weight, or the system's default weight can be used. Users can further adjust the initial preset weights as needed. Furthermore, users can select data to participate in priority scoring. For example, checkboxes corresponding to each data type can be provided on the display interface (e.g., the user's mobile app interface), allowing users to select data for priority scoring. The above embodiments for adjusting preset weights and selecting data can be implemented individually or in the same embodiment.

[0070] The above technical solution allows users to select data and / or set preset weights according to their own needs, making it convenient for users to choose appropriate data types and / or weights based on local crop conditions, thereby improving the adaptability of the task scheduling system and expanding its application scope.

[0071] According to an embodiment of the present invention, sorting the inspection tasks in the adjusted task queue according to the target sorting strategy includes: sorting the inspection tasks in the adjusted task queue according to the target sorting strategy based on constraints and a task allocation mechanism; wherein, the constraints include one or more of the following: the power safety threshold of the inspection robot, the safe range of the motor parameters of the inspection robot, the restricted entry time of the target plot, the restricted entry time of the target point, and the adjacency of the planned path; the task allocation mechanism is a concurrent allocation mechanism or a serial allocation mechanism.

[0072] The preset conditions also include constraints, which include one or more of the following: the battery safety threshold of the inspection robot, the safe range of the motor parameters of the inspection robot, the restricted entry time of the target plot, the restricted entry time of the target point, and the adjacency of the planned path; the inspection tasks in the adjusted task queue are sorted according to the preset conditions, including: for each inspection task in the adjusted task queue, a priority score is given to the inspection task according to the preset priority scoring rules to obtain the priority score result of the inspection task; and the inspection tasks are sorted according to the priority score results and constraints of each inspection task.

[0073] In addition to target sorting strategies, the sequencing and assignment of inspection tasks can also consider constraints and task allocation mechanisms. For example, constraints may include one or more of the following: the inspection robot's battery safety threshold, the inspection robot's motor parameter safety range, the restricted entry time periods for the target plot, the restricted entry time periods for the target location, and the adjacency of the planned path. The battery safety threshold can be set to any suitable value as needed, such as 5%, 10%, or 20% of the inspection robot's maximum battery level. When the inspection robot's remaining battery level drops to the battery safety threshold (i.e., from above the battery safety threshold to equal to the battery safety threshold), it indicates insufficient battery power. At this point, the sequencing and assignment of inspection tasks for that robot can be optionally paused (e.g., frozen as described above). The motor parameter safety range can be set to any suitable range as needed. As mentioned above, motor parameters may include one or more of the following: motor drive current, drive voltage, speed, temperature, PWM duty cycle, etc. Accordingly, the safe range of motor parameters can include the safe range of current corresponding to the drive current, the safe range of voltage corresponding to the drive voltage, the safe range of speed corresponding to the rotational speed, the safe range of temperature corresponding to the temperature, and the safe range of duty cycle corresponding to the PWM duty cycle. When the motor parameters of the inspection robot do not fall within the safe range, it indicates that there is a problem with its motor status. At this time, the sorting and distribution of inspection tasks for the inspection robot can be optionally suspended. In the prior art, task scheduling does not coordinate with the health status and power status of the inspection robot. However, according to this embodiment, the motor status (which can represent the health status of the equipment) and / or power status of the inspection robot can be taken into consideration, enabling the task scheduling system to adjust the inspection tasks based on the motor status and / or power status of the inspection robot. During the restricted entry period of the target plot, the execution of inspection tasks whose inspection area falls within the target plot and whose execution time falls within the restricted entry period can be suspended. During the restricted entry period of the target point, the execution of inspection tasks whose inspection area is the target point and whose execution time falls within the restricted entry period can be suspended. The adjacency of the planned path refers to the requirement that continuous work points (or sub-path segments) on the path be spatially adjacent and sequentially connected when generating the travel path of the inspection robot, so as to avoid large-scale jumps or repeated crossings.

[0074] The task allocation mechanism can be either concurrent or sequential. Concurrent allocation allows multiple inspection robots to work collaboratively, with their inspection tasks executed in parallel. Sequential allocation, on the other hand, requires each inspection task to be executed serially and sequentially. The specific task allocation mechanism can be either the system default settings or user-defined.

[0075] Using the above scheme, inspection tasks in the adjusted task queue can be sorted according to the target sorting strategy based on constraints and task allocation mechanisms. This scheme can combine multi-dimensional principles to sort inspection tasks, thereby better optimizing the sorting results and achieving load balancing.

[0076] According to an embodiment of the present invention, the target sorting strategy is one of at least two preset sorting strategies. Sorting the inspection tasks in the adjusted task queue according to the target sorting strategy includes: in response to the user's strategy selection instruction, determining the preset sorting strategy selected by the user as the target sorting strategy, or, when a preset trigger condition is met, determining the preset sorting strategy corresponding to the preset trigger condition as the target sorting strategy; and sorting the remaining unexecuted inspection tasks in the adjusted task queue according to the latest determined target sorting strategy.

[0077] As described above, when there are multiple preset sorting strategies, switching between them can be performed as needed. Switching can be triggered by a user strategy selection command or automatically by a preset trigger condition. At least some preset sorting strategies can have their own corresponding preset trigger conditions. For example, for an emergency priority strategy, the preset trigger condition may include generating a high-urgency-level anomaly review task; that is, when generating a high-urgency-level anomaly review task, the current target sorting strategy can be automatically switched to the emergency priority strategy. As another example, for an energy consumption priority strategy, the preset trigger condition may include the remaining battery power of the inspection robot being lower than a preset battery power threshold; that is, when the remaining battery power of the inspection robot is lower than the preset battery power threshold, the current target sorting strategy can be automatically switched to the energy consumption priority strategy. The preset battery power threshold of any inspection robot can be higher than its safe battery power threshold. The safe battery power thresholds of any two different inspection robots can be the same or different. Similarly, the preset battery power thresholds of any two different inspection robots can be the same or different.

[0078] The above technical solution provides multiple preset sorting strategies, which can be switched between different preset sorting strategies as needed. This can meet the operational needs of different growth stages or different environments and help improve the growth quality of crops.

[0079] According to an embodiment of the present invention, after the inspection tasks in the task execution list are sent to the inspection robot, the method further includes: tracking the execution status of the inspection tasks and feeding back the execution status to the remote task system in real time. The execution status includes execution completed, execution failed, execution interrupted, and execution skipped.

[0080] The execution status includes execution completed, execution failed, execution interrupted, and execution skipped. The meaning of each execution status has been described above and will not be repeated here. The task scheduling system may include a task executor, which can distribute inspection tasks to inspection robots. The inspection robots can drive the status updates of the inspection tasks through heartbeat and progress event mechanisms, that is, provide real-time feedback of the execution status to the remote task system. The remote task system can be any hardware and / or software system, such as a mobile terminal (e.g., a mobile phone), a server, etc. The remote task system can provide a display interface that can display a visual execution status graph to show the execution status of each inspection task. For example, the display interface can also show the execution results of abnormalities in the inspection area. In addition, the remote task system can provide a manual intervention interface so that users can control the inspection tasks through this interface.

[0081] By adopting the above technical solution, real-time feedback on the execution status of inspection tasks can be provided, making it convenient for users to manually intervene in inspection tasks that encounter problems in a timely manner.

[0082] According to an embodiment of the present invention, after the inspection tasks in the task execution list are issued to the inspection robot, the method further includes: recording the execution log of the inspection tasks and uploading the execution log to a preset database, wherein the execution log includes the execution results of the inspection tasks; wherein, when performing the operation of formulating regular inspection tasks according to the growth stage of the target crop in the next execution, the formulated regular inspection tasks are optimized based on the execution log stored in the preset database.

[0083] An execution log is a time-series detailed record of various key operations, state changes, environmental data, abnormal events, and intermediate results throughout the entire process of an inspection task, from its generation to its completion. For example, the execution log may include one or more of the following layers: task metadata layer, process trajectory layer, job details layer, and system and event layer. The task metadata layer may include one or more of the following: inspection task identification information (e.g., task ID), inspection robot identification information (e.g., robot ID), task type, planned execution time, actual execution time, execution status, etc. The process trajectory layer may include one or more of the following: high-frequency pose flow, path key points, environmental context, etc. High-frequency pose flow may include, for example, timestamps, GPS / laser SLAM coordinates, velocity, heading angle, etc. Path key points may include, for example, path planning results, replanning events and reasons, etc. Environmental context may include, for example, the light intensity corresponding to the timestamp, air temperature, air humidity, etc. The job details layer may include one or more of the following: point access sequence, action execution record, etc. Point access sequence may include, for example, arrival at a point, departure from a point, dwell time, etc. Action execution records can include, for example, detection type (e.g., infrared thermometry), detection parameters (e.g., camera parameters, environmental sensor parameters), and detection results (e.g., raw planting data, processed planting data, planting data analysis results). The execution results can include detection results. The system and event layer can include one or more of the following: robot health, critical system events, etc. Robot health can include, for example, battery level corresponding to a timestamp, core temperature, motor drive current, etc. Critical system events can include, for example, heartbeat reporting, emergency obstacle avoidance triggering, communication interruption / recovery, etc.

[0084] During the execution of an inspection task, an execution log is recorded and uploaded to a pre-set database. When performing a routine inspection task based on the target crop's growth stage in the next inspection time window, the task can be optimized based on the execution log stored in the pre-set database. For example, the robot's path can be optimized to ensure it reaches the inspection area within the predetermined time while reducing energy consumption and time.

[0085] By adopting the above technical solution, the execution results of the current inspection task can be used to generate and optimize the next round of inspection tasks, thereby realizing closed-loop optimization of task execution and feedback, and improving the performance of the entire task scheduling system.

[0086] According to an embodiment of the present invention, the method further includes: if the remaining power of the inspection robot is less than or equal to the power safety threshold, then the issuance of the inspection task is stopped, and the inspection robot is controlled to return to the preset charging position for charging.

[0087] The preset charging location can be, for example, a pre-set charging station or charging pile location. These locations can be pre-set in the navigation map of the task scheduling system, allowing the inspection robot to automatically navigate to them for autonomous charging when its battery is low. This approach enables the inspection robot to automatically return to its charging station, improving its overall intelligence.

[0088] According to another aspect of the present invention, a task scheduling device is provided. Figure 2 A schematic block diagram of a task scheduling apparatus 200 according to an embodiment of the present invention is shown. Figure 2 As shown, the device 200 may include a design module 210, a first distribution module 220, an adjustment module 230, and a second distribution module 240.

[0089] The formulation module 210 is used to formulate routine inspection tasks based on the growth stage of the target crop to obtain a task queue, which includes routine inspection tasks.

[0090] The first dispatch module 220 is used to dispatch routine inspection tasks to the inspection robot for execution.

[0091] The adjustment module 230 is used to adjust the inspection tasks in the task queue based on the execution results of the regular inspection tasks, and sort the inspection tasks in the adjusted task queue according to the target sorting strategy to obtain the task execution list.

[0092] The second dispatch module 240 is used to dispatch the inspection tasks in the task execution list to the inspection robot for execution.

[0093] According to another aspect of the present invention, an electronic device is also provided. Figure 3 A schematic block diagram of an electronic device 300 according to an embodiment of the present invention is shown, such as Figure 3 As shown, the electronic device 300 may include a processor 310 and a memory 320. The memory 320 stores a computer program, and the processor 310 executes the computer program to implement the task scheduling method described above.

[0094] According to another aspect of the present invention, a storage medium is also provided. It stores a computer program / instructions, which, when executed by a processor, implement the task scheduling method described above. The storage medium may, for example, include a storage component of a tablet computer, a hard disk of a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disc read-only memory (CD-ROM), a USB memory, or any combination of the above storage media. The computer-readable storage medium may be any combination of one or more computer-readable storage media.

[0095] Those skilled in the art can understand the specific implementation schemes and beneficial effects of the above-mentioned task scheduling device, electronic device and storage medium by reading the relevant description of the task scheduling method. For the sake of brevity, they will not be described in detail here.

[0096] Although exemplary embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above exemplary embodiments are merely illustrative and are not intended to limit the scope of the invention. Various changes and modifications can be made therein by those skilled in the art without departing from the scope and spirit of the invention. All such changes and modifications are intended to be included within the scope of the invention as claimed in the appended claims.

[0097] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0098] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed.

[0099] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0100] Similarly, it should be understood that, in order to streamline the invention and aid in understanding one or more of the various aspects of the invention, features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the description of exemplary embodiments of the invention. However, this approach of the invention should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the corresponding claims, its inventive point lies in solving the corresponding technical problem with fewer features than all of those in a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0101] Those skilled in the art will understand that, apart from the mutual exclusion of features, all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or apparatus so disclosed can be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0102] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments can be used in any combination.

[0103] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some modules in the task scheduling apparatus according to embodiments of the present invention. The present invention can also be implemented as an apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such programs implementing the present invention can be stored on a computer-readable medium or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0104] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0105] The above description is merely a specific embodiment of the present invention or an explanation of that embodiment. The scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. The scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A task scheduling method, characterized in that, include: Regular inspection tasks are formulated based on the growth stage of the target crop to obtain a task queue, which includes the regular inspection tasks. The routine inspection task is assigned to the inspection robot for execution. Based on the execution results of the routine inspection tasks, the inspection tasks in the task queue are adjusted, and the inspection tasks in the adjusted task queue are sorted according to the target sorting strategy to obtain the task execution list. The inspection tasks in the task execution list are sent to the inspection robot for execution.

2. The method according to claim 1, characterized in that, The adjustment of inspection tasks in the task queue based on the execution results of the regular inspection tasks includes: If the execution result of any routine inspection task indicates an anomaly in the inspection area, an anomaly review task is generated and added to the task queue; and / or, If, within a first preset time period preceding the current moment, the execution results of N consecutive routine inspection tasks all indicate that the inspected area is free of abnormalities, then the execution frequency of the unexecuted inspection tasks in that group of routine inspection tasks is reduced; or, the unexecuted inspection tasks in that group of routine inspection tasks are merged with at least one inspection task in the task queue, wherein routine inspection tasks with the same inspection area and task type belong to the same group, and N is an integer greater than or equal to 2; and / or, If any routine inspection task fails, and the number of consecutive failures of that routine inspection task within the second preset time period preceding the current time does not reach a preset threshold, then the next execution time of the routine inspection task is calculated, and the routine inspection task is re-added to the task queue. If any routine inspection task fails, and the number of consecutive failures of that routine inspection task within the second preset time period reaches the preset threshold, then the execution log of the routine inspection task is recorded and / or a first warning message is output; and / or, If any routine inspection task is interrupted, the routine inspection task is frozen and its execution log is recorded. When the preset recovery conditions are met, the routine inspection task is resumed based on the breakpoint information in the execution log. The freezing includes keeping the routine inspection task in the task queue and prohibiting it from participating in sorting and distribution.

3. The method according to claim 2, characterized in that, The adjustment of inspection tasks in the task queue based on the execution results of the regular inspection tasks also includes: If any routine inspection task is interrupted and the freeze time of the routine inspection task exceeds a preset duration threshold, a re-evaluation of the routine inspection task is initiated to determine whether it needs to continue, and / or a second warning message is output. The operation of continuing to execute the routine inspection task based on the breakpoint information when the preset recovery conditions are met is performed when it is determined that the routine inspection task needs to continue.

4. The method according to claim 2, characterized in that, The anomaly review task is configured with a corresponding urgency level, which is one of multiple preset urgency levels. Each of the multiple preset urgency levels has a corresponding response requirement. The target sorting strategy is one of at least one preset sorting strategy, which includes an urgency priority strategy. The urgency priority strategy sorts the inspection tasks according to the response requirements corresponding to the urgency level of the inspection task.

5. The method according to claim 4, characterized in that, The operation of formulating routine inspection tasks based on the growth stage of the target crop is carried out periodically according to the preset inspection time window, and the multiple preset emergency levels include high emergency level and general emergency level. The response requirements corresponding to the high urgency level include: the corresponding inspection task should be executed at the nearest reachable point after the currently executing inspection task; The response requirements corresponding to the general emergency level include: if the user-defined time window is not received, the corresponding inspection task shall be executed in the next inspection time window; if the user-defined time window is received, the corresponding inspection task shall be executed within the user-defined time window.

6. The method according to any one of claims 1-5, characterized in that, The target sorting strategy is one of at least one preset sorting strategy, and the at least one preset sorting strategy includes a scoring priority strategy, which sorts the inspection tasks according to the priority scoring results of the inspection tasks. When the target sorting strategy is the scoring priority strategy, sorting the inspection tasks in the adjusted task queue according to the target sorting strategy includes: For each inspection task in the adjusted task queue According to the preset priority scoring rules, the priority scores of various data corresponding to the inspection task are scored separately to obtain the priority scores of each of the various data. The priority scores of the various data are weighted and summed according to preset weights to obtain the priority score result of the inspection task. The inspection tasks in the adjusted task queue are sorted according to the priority scoring results. The various data include at least two of the following: the pest and disease level of the inspection area of ​​the inspection task, the urgency of the crop growth stage of the inspection area of ​​the inspection task, the historical frequency of anomalies in the inspection area of ​​the inspection task, the distance between the inspection area of ​​the inspection task and the current travel path, the difference between the estimated power required to perform the inspection task and the remaining power of the inspection robot, and the test level to which the inspection area of ​​the inspection task belongs. The preset priority scoring rules include at least two of the following: the higher the level of the pest or disease, the greater the corresponding priority score; the higher the urgency of the growth stage, the greater the corresponding priority score; the higher the frequency of historical anomalies, the greater the corresponding priority score; the closer the distance, the greater the corresponding priority score; the greater the difference in power, the smaller the corresponding priority score; and the higher the test level, the greater the corresponding priority score.

7. The method according to claim 6, characterized in that, The step of sorting the inspection tasks in the adjusted task queue according to the target sorting strategy also includes: In response to a user's weight setting instruction, adjust the preset weights corresponding to at least some of the data among the various data; and / or, In response to the user's data selection instruction, the data to be included in the priority scoring is determined.

8. The method according to any one of claims 1-5, characterized in that, The step of sorting the inspection tasks in the adjusted task queue according to the target sorting strategy includes: Based on constraints and task allocation mechanisms, the inspection tasks in the adjusted task queue are sorted according to the target sorting strategy. The constraints include one or more of the following: the battery safety threshold of the inspection robot, the safe range of the motor parameters of the inspection robot, the restricted entry time of the target plot, the restricted entry time of the target point, and the adjacency of the planned path. The task allocation mechanism is either a concurrent allocation mechanism or a serial allocation mechanism.

9. The method according to any one of claims 1-5, characterized in that, The target sorting strategy is one of at least two preset sorting strategies, and sorting the inspection tasks in the adjusted task queue according to the target sorting strategy includes: In response to the user's strategy selection instruction, the user's selected preset sorting strategy is determined as the target sorting strategy; or, when a preset triggering condition is met, the preset sorting strategy corresponding to the preset triggering condition is determined as the target sorting strategy. The remaining unexecuted inspection tasks in the adjusted task queue are sorted according to the latest determined target sorting strategy.

10. The method according to any one of claims 1-5, characterized in that, After issuing the inspection tasks from the task execution list to the inspection robot, the method further includes: The execution status of the inspection task is tracked and fed back to the remote task system in real time. The execution status includes execution completed, execution failed, execution interrupted, and execution skipped.

11. The method according to any one of claims 1-5, characterized in that, After issuing the inspection tasks from the task execution list to the inspection robot, the method further includes: Record the execution log of the inspection task and upload the execution log to a preset database. The execution log includes the execution result of the inspection task. Specifically, when performing the operation of formulating routine inspection tasks based on the growth stage of the target crop the next time, the routine inspection tasks are optimized based on the execution logs stored in the preset database.

12. The method according to any one of claims 1-5, characterized in that, The method further includes: If the remaining battery power of the inspection robot is less than or equal to the battery safety threshold, the issuance of the inspection task will be stopped, and the inspection robot will be controlled to return to the preset charging location for charging.

13. A task scheduling device, characterized in that, include: A planning module is used to plan routine inspection tasks based on the growth stage of the target crop to obtain a task queue, wherein the task queue includes the routine inspection tasks. The first dispatch module is used to dispatch the routine inspection task to the inspection robot for execution by the inspection robot; The adjustment module is used to adjust the inspection tasks in the task queue based on the execution results of the regular inspection tasks, and sort the inspection tasks in the adjusted task queue according to the target sorting strategy to obtain the task execution list. The second dispatch module is used to dispatch the inspection tasks in the task execution list to the inspection robot for execution by the inspection robot.

14. An electronic device comprising a processor and a memory, wherein, The memory stores computer program instructions, which, when executed by the processor, are used to perform the task scheduling method as described in any one of claims 1-12.

15. A storage medium on which program instructions are stored, wherein, The program instructions are used to execute the task scheduling method as described in any one of claims 1-12 when the program is run.

Images