Task management method, task management system, robot and computer program product

Abstract

The invention is suitable for the technical field of robots, and provides a task management method and system, a robot and a computer program product, and the method comprises the steps: obtaining task information of a to-be-executed task; the task information is input into the large model for task analysis, and a conflict prediction result is obtained; starting an adaptive algorithm to generate a conflict solution according to a conflict prediction result and a robot state; adjusting a task execution plan according to the conflict solution, executing the task according to the adjusted task execution plan, utilizing a large model to deeply analyze the task, predicting a possible conflict task, and dynamically generating an optimal conflict solution of the conflict task through an adaptive algorithm. The task is executed based on the optimized task execution sequence and the resource allocation scheme in the conflict solution, so that the occurrence of task conflicts can be effectively reduced, the task execution efficiency is improved, the resource waste and execution delay caused by the task conflicts are reduced, and the reliability and stability of a task scheduling system are improved.

Description

Technical Field

[0001] This application belongs to the field of robot technology, and particularly relates to a task management method, a task management system, a robot, and a computer program product. Background Art

[0002] With the continuous development of robot technology, intelligent robots are widely used in various fields, such as hotel services, mall guidance, hospital guidance, etc. In the actual application process, robots usually need to execute multiple tasks simultaneously, and there may be task conflicts between multiple tasks, such as resource conflicts, path conflicts, etc. Traditional task management systems usually rely on preset scheduling rules and simple scheduling algorithms to achieve task scheduling. However, this method cannot dynamically adapt to the actual situations encountered by robots during task execution, such as environmental changes, resource shortages, etc., which will affect the flexibility and real-time nature of task scheduling, and may even lead to task delays or failures. Summary of the Invention

[0003] Embodiments of this application provide a task management method, a task management system, a robot, and a computer program product, which can predict task conflicts in advance and intelligently generate a scheduling plan that can solve the conflicts, thereby improving the flexibility of task scheduling and enhancing the reliability and stability of task execution.

[0004] In a first aspect, embodiments of this application provide a task management method, including:

[0005] Obtain the task information of the task to be executed;

[0006] Input the task information into a large model for task analysis to obtain a conflict prediction result;

[0007] Start an adaptive algorithm to generate a conflict solution according to the conflict prediction result and the robot state;

[0008] Adjust the task execution plan according to the conflict solution, and execute the task according to the adjusted task execution plan.

[0009] In this application, the large model can be used to deeply analyze tasks, so as to predict possible conflicting tasks. Then, an adaptive algorithm is used to dynamically generate an optimal conflict solution for the conflicting tasks. The task is executed based on the optimized task execution order and resource allocation plan obtained from the conflict solution of the adaptive algorithm, which can effectively reduce the occurrence of task conflicts, thereby improving task execution efficiency, reducing resource waste and execution delays caused by task conflicts, and effectively improving the reliability and stability of the task scheduling system.

[0010] In a possible implementation manner of the first aspect, the method further includes:

[0011] Obtain external environment information and robot status information;

[0012] Input the task information, the external environment information, and the robot status information into the large model for task analysis to obtain the priority adjustment results for each task;

[0013] Generate a task scheduling plan according to the priority adjustment results of each task;

[0014] Correspondingly, the adjusting the task execution plan according to the conflict resolution solution and executing the task according to the adjusted task execution plan includes:

[0015] Generate a task execution plan according to the task scheduling plan and the conflict resolution solution, and issue the task to the execution mechanism of the robot according to the task execution plan.

[0016] In this application, by utilizing the deep learning ability and context analysis function of the trained large model, combining the robot status information, external environment information, and task information, the priority of the task is adjusted in real time and dynamically. Compared with the traditional task scheduling method, it can more flexibly adapt to the complex environment of actual applications, improve the accuracy and adaptability of task scheduling, and thus improve the rationality and reliability of task execution.

[0017] In a possible implementation manner of the first aspect, the method further includes:

[0018] Monitor the task execution status of the robot in real time, and generate execution status data according to the task execution status of the robot;

[0019] Adjust the parameters of the large model according to the execution status data.

[0020] In this application, by constructing an effective feedback mechanism, continuously learn and optimize the task scheduling strategy of the large model according to the actual effect of task execution. The large model continuously optimizes the decision-making ability of the task management system according to the feedback situation, so that the task management system can perform task management more intelligently and efficiently when facing new tasks and environmental changes, so that the task management system can continuously adapt to the complex and changeable operating environment and improve the long-term operation performance of the system.

[0021] In a possible implementation manner of the first aspect, the generating the execution status data according to the task execution status of the robot includes:

[0022] Input the task execution status of the robot into the large model for analysis to obtain the execution status data.

[0023] In a possible implementation of the first aspect, the execution status data includes an abnormal execution status and a normal execution status. Adjusting the parameters of the large model according to the execution status data includes:

[0024] Taking the task scheduling scheme corresponding to the abnormal execution status as negative feedback and the task scheduling scheme corresponding to the normal execution status as positive feedback, and inputting them into the large model to adjust the parameters of the large model.

[0025] In a possible implementation of the first aspect, generating a task execution plan according to the task scheduling scheme and the conflict resolution scheme, and issuing tasks to the execution mechanism of the robot according to the task execution plan includes:

[0026] Generating the task execution plan according to the task scheduling scheme;

[0027] Adjusting the content of the task execution plan according to the conflict resolution scheme to obtain the adjusted task execution plan;

[0028] Issuing tasks to the execution mechanism of the robot according to the adjusted task execution plan.

[0029] In a possible implementation of the first aspect, the task execution plan includes the execution time of the task, resource allocation, and path planning.

[0030] In a second aspect, an embodiment of the present application provides a task management system, including:

[0031] A task receiving module, configured to receive task information input externally;

[0032] A large model task analysis module, connected to the task receiving module, and a trained large model is configured in the large model task analysis module, which is used to perform task analysis according to the task information, predict task conflict situations, and generate a conflict prediction result when there is a task conflict situation;

[0033] A conflict resolution module, connected to the large model task analysis module, configured to start an adaptive algorithm to generate a conflict resolution scheme when receiving the conflict prediction result;

[0034] A task scheduling module, connected to the conflict resolution module, configured to generate a task execution plan according to the task scheduling scheme and the conflict resolution scheme, and issue tasks to the execution mechanism of the robot according to the task execution plan.

[0035] In an implementation of the second aspect, the task scheduling module is further connected to the large model task analysis module;

[0036] The large model task analysis module is further configured to: dynamically adjust the priority of the task according to the task information, external environment information, and robot status information, generate the task scheduling plan, and send the task scheduling plan to the task scheduling module.

[0037] In an implementation manner of the second aspect, the task management system further includes:

[0038] An execution monitoring module, configured to monitor the task execution status of the robot in real time and generate execution status data according to the task execution status of the robot;

[0039] A feedback adjustment module, configured to perform feedback adjustment on the parameters of the large model according to the execution status data.

[0040] In a third aspect, an embodiment of the present application provides a robot, including:

[0041] An acquisition module, configured to acquire the task information of the task to be executed;

[0042] A planning module, configured to input the task information into a large model for task analysis to obtain a conflict prediction result;

[0043] A selection module, configured to start an adaptive algorithm to generate a conflict solution according to the conflict prediction result and the robot status;

[0044] An execution module, configured to adjust the task execution plan according to the conflict solution and execute the task according to the adjusted task execution plan.

[0045] In a fourth aspect, an embodiment of the present application provides a robot, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method described in the first aspect is implemented.

[0046] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0047] In a sixth aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on a robot, the robot is enabled to execute the method described in the first aspect above.

[0048] It can be understood that the beneficial effects of the above second aspect to sixth aspect can refer to the relevant descriptions in the first aspect above, and will not be elaborated here. Description of the Drawings

[0049] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the accompanying drawings required for use in the embodiments or the description of the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0050] Figure 1 is a schematic structural diagram of a task management system provided by an embodiment of the present application;

[0051] Figure 2 is a schematic structural diagram of another task management system provided by an embodiment of the present application

[0052] Figure 3 is a schematic implementation flowchart of a task management method provided by an embodiment of the present application;

[0053] Figure 4 is a schematic implementation flowchart of another task management method provided by an embodiment of the present application;

[0054] Figure 5 is a schematic implementation flowchart of yet another task management method provided by an embodiment of the present application;

[0055] Figure 6 is a schematic structural diagram of a robot provided by an embodiment of the present application;

[0056] Figure 7 is a schematic structural diagram of another robot provided by an embodiment of the present application. Detailed implementation manners

[0057] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures and technologies are presented to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0058] It should be understood that when used in the specification and the appended claims of the present application, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0059] It should also be understood that the term "and / or" used in the specification and the appended claims of the present application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0060] As used in the specification and claims of this application, the term "if" may be construed, depending on the context, as "when", "once", "in response to determining", or "in response to detecting". Similarly, the phrases "if determined" or "if [the described condition or event] is detected" may be construed, depending on the context, to mean "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]".

[0061] In addition, in the description of the specification and claims of this application, the terms "first", "second", "third", etc. are only used for differential description and cannot be construed as indicating or implying relative importance.

[0062] Reference to "one embodiment" or "some embodiments" or the like described in the specification of this application means that a particular feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized.

[0063] With the continuous development of robotics, intelligent robots are widely used in various fields, such as hotel services, mall guidance, hospital guidance, and so on. In the actual application process, robots usually need to execute multiple tasks simultaneously, and there may be task conflicts between multiple tasks, such as resource conflicts, path conflicts, etc. Traditional task management systems usually rely on preset scheduling rules and simple scheduling algorithms to implement task scheduling. However, this method cannot dynamically adapt to the actual situations encountered by robots during task execution, such as environmental changes, resource shortages, etc., which will affect the flexibility and real-time nature of task scheduling, and may even lead to task delays or failures.

[0064] Based on this, the embodiments of this application provide a task management method and a task management system, which can predict task conflicts in advance and intelligently generate a scheduling plan that can resolve conflicts, thereby improving the flexibility of task scheduling and enhancing the reliability and stability of task execution.

[0065] The following will describe in detail the task management method and the task management system provided by the embodiments of this application with reference to the accompanying drawings.

[0066] Please refer to Figure 1 , Figure 1The figure shows a schematic structural diagram of a task management system provided by an embodiment of the present application. As Figure 1 shown, the above-mentioned task management system 10 may include: a task receiving module 11, a large model task analysis module 12, a conflict resolution module 13, and a task scheduling module 14.

[0067] Among them, the task receiving module 11 may be used to receive task information input from the outside. The above-mentioned task information may include, but is not limited to, information such as task descriptions, dependencies, task priorities, and resource requirements.

[0068] The task information may be input by the user, or may be generated by the control center of the robot based on the states of various sensors in the robot according to user instructions and according to the robot state. The embodiments of the present application do not make a unique limitation on this.

[0069] It can be understood that the above-mentioned task receiving module 11 is the entrance of the task management system 10. The task receiving module 11 can be connected to the large model task analysis module 12 and can send the received task information to the large model task analysis module 12 for further processing.

[0070] The above-mentioned large model task analysis module 12 may be configured with a trained large model. The above-mentioned large model can dynamically adjust the priority of the task according to the task information, external environment information, and robot state information, and generate a task scheduling plan.

[0071] The above-mentioned large model task analysis module 12 may be respectively connected to the above-mentioned task receiving module 11, conflict resolution module 13, and task scheduling module 14.

[0072] The large model task analysis module 12 may send the generated task scheduling plan to the task scheduling module 14 for execution.

[0073] In specific applications, the above-mentioned large model may be a deep neural network model or a large language model. The embodiments of the present application use a trained large model to deeply analyze tasks, that is, use the large model to deeply analyze tasks, not only according to the task information of the task, such as task descriptions and resource requirements, but also in combination with robot state information and external environment information to dynamically adjust the priority of the task.

[0074] Specifically, the application of the above-mentioned large model in task priority evaluation can be mainly realized through the context analysis function provided by the large model and the enhanced real-time evaluation function of the large model.

[0075] In specific applications, the above external environment information is the relevant information of the current external environment, which may specifically include but is not limited to the distribution of obstacles in the environment, the positions of targets in the environment, etc. The above robot state information is the information related to the robot state, such as the remaining battery power, the current position, the current posture, and so on.

[0076] By leveraging the deep learning capabilities and context analysis functions of the trained large model, combining the robot state information, external environment information, and task information, the priority of the task is dynamically adjusted in real time. Compared with traditional task scheduling methods, it can more flexibly adapt to the complex environment of actual applications, improve the accuracy and adaptability of task scheduling, and thus improve the rationality and reliability of task execution.

[0077] In some embodiments, the above large model task analysis module 12 can also be used to predict the conflict situation between multiple tasks, obtain the conflict prediction result, and feedback the conflict prediction result to the conflict resolution module 13 when it is confirmed that there is a task conflict.

[0078] The conflict resolution module 13 is used to start the adaptive algorithm to automatically generate a conflict resolution plan when receiving the conflict prediction result.

[0079] In the embodiments of the present application, the above conflict resolution plan includes an optimized task execution order and resource allocation plan.

[0080] Here, the conflict resolution module 13 can optimize the task execution order and resource allocation in the task scheduling plan obtained by the large model task analysis module 12 to obtain the above conflict resolution plan. By executing tasks through the optimized task execution order and resource allocation plan in the conflict resolution plan obtained based on the adaptive algorithm, the occurrence of task conflicts can be effectively reduced, thereby improving task execution efficiency, reducing resource waste and execution delays caused by task conflicts, and effectively improving the reliability and stability of the task scheduling system.

[0081] The conflict resolution module 13 can output the conflict resolution plan output by the adaptive algorithm to the task scheduling module 14 for execution.

[0082] In specific applications, starting the adaptive algorithm to automatically generate a conflict resolution plan may specifically include content such as dynamic priority adjustment, resource allocation optimization, and task route replanning.

[0083] Among them, the adaptive algorithm can dynamically adjust the execution order of conflicting tasks according to the priorities of the conflicting tasks and the current environmental state, that is, readjust the priorities of the tasks. The adaptive algorithm can also reallocate the resources of conflicting tasks for various resources of the robot, such as power resources, computing resources, mechanical structures, etc. The adaptive algorithm can also re-plan the tasks, including changing the execution order of the tasks, adjusting the execution time of the tasks, or modifying the execution path of the tasks. For example, in a hotel food delivery task, if there is a conflict in the original task path of the robot, the adaptive algorithm can re-plan the path to avoid congested areas and ensure the smooth progress of the food delivery task.

[0084] It can be understood that the adaptive algorithm can automatically determine the optimal conflict solution. In specific applications, the above-mentioned adaptive algorithm can be an adaptive genetic algorithm, an Adaptive Neuro-Fuzzy Inference System (ANFIS), a Kalman Filter, and its adaptive variants, etc. This application does not make a unique limitation on this.

[0085] The adaptive algorithm first relies on the real-time monitoring of the robot system, including the perception of various states of the robot, such as the position and movement of the robotic arm, the data acquisition of sensors, the progress of task execution, etc. Therefore, when the large model anticipates the existence of conflicting tasks in advance, the adaptive algorithm can adapt the resource information and state information of the robot to generate the optimal conflict solution, and adjust the execution order, execution time, and execution path of the conflicting tasks to reduce the occurrence of conflicts.

[0086] The above-mentioned task scheduling module 14 is used to generate a task execution plan according to the task scheduling scheme and the conflict solution, and issue the task to the execution mechanism of the robot according to the task execution plan.

[0087] In specific applications, the task scheduling module 14 can generate a detailed task execution plan according to the task scheduling scheme analyzed by the large model and the conflict solution determined by the adaptive algorithm, including the execution time of the task, resource allocation, and path planning, etc.

[0088] It can be understood that after receiving the corresponding task execution plan, the above-mentioned robot execution mechanism can execute the task at the arrival of the execution time of the task, using the allocated resources and following the path in the path planning.

[0089] As can be seen above, the task management system provided in the embodiments of the present application can use a large model to deeply analyze tasks, thereby predicting possible conflicting tasks, and then dynamically generating an optimal conflict resolution plan for the conflicting tasks through an adaptive algorithm. Based on the optimized task execution order and resource allocation plan in the conflict resolution plan obtained from the adaptive algorithm, tasks are executed, which can effectively reduce the occurrence of task conflicts, thereby improving task execution efficiency, reducing resource waste and execution delays caused by task conflicts, and effectively improving the reliability and stability of the task scheduling system.

[0090] Please refer to Figure 2 , Figure 2 which shows a schematic structural diagram of another task management system provided in the embodiments of the present application. As Figure 2 shown, in the embodiments of the present application, the task management system 10 may include: a task receiving module 11, a large model task analysis module 12, a conflict resolution module 13, a task scheduling module 14, an execution monitoring module 15, and a feedback adjustment module 16.

[0091] Among them, for the relevant content of the task receiving module 11, the large model task analysis module 12, the conflict resolution module 13, and the task scheduling module 14, please refer to Figure 1 the description of the relevant embodiments, and will not be repeated here.

[0092] The above-mentioned execution monitoring module 15 is used to monitor the task execution status of the robot in real time and generate execution status data according to the task execution status of the robot.

[0093] In the embodiments of the present application, a trained large model may also be configured in the above-mentioned execution monitoring module 15, and the configured large model deeply analyzes whether there are abnormal situations according to the task execution status of the robot, such as path blockage, resource exhaustion, etc.

[0094] It can be understood that the trained large model configured in the execution monitoring module 15 in the embodiments of the present application may be configured separately, or may be jointly configured with the above-mentioned large model task analysis module 12. For example, a trained large model may be configured to implement the functions of the above-mentioned large model task analysis module 12 and the execution monitoring module 15, or large models corresponding to different modules may be configured separately. The present application does not make a unique limitation on this.

[0095] When the execution monitoring module 15 monitors that there is an abnormality in the task execution status, it can feedback the abnormal situation to the above-mentioned feedback adjustment module 16, and when there is no abnormality, it can also feedback the monitoring result to the above-mentioned feedback adjustment module 16. That is, the execution monitoring module 15 can feedback the execution status data in real time according to the task execution status.

[0096] The above feedback adjustment module 16 adjusts the parameters of the large model according to the execution status data.

[0097] In the embodiments of the present application, by constructing an effective feedback mechanism, the task scheduling strategy of the large model is continuously learned and optimized according to the actual effect of task execution. The large model continuously optimizes the decision-making ability of the task management system according to the feedback situation, so that the task management system can manage tasks more intelligently and efficiently when facing new tasks and environmental changes, so that the task management system can continuously adapt to the complex and changeable operating environment and improve the long-term operation performance of the system.

[0098] The task management system provided by the embodiments of the present application has been introduced above. Next, the task management method provided by the embodiments of the present application will be described in detail with reference to the accompanying drawings.

[0099] Please refer to Figure 3 , Figure 3 which shows a schematic diagram of the implementation process of a task management method provided by the embodiments of the present application. Among them, the execution subject is a robot, specifically the task management system in the robot, that is, it can be the task management system shown in Figures 1 to 2 , as shown in Figure 3 , the above task management method may include S301 to S304, which are described in detail as follows:

[0100] S301: Obtain the task information of the task to be executed.

[0101] In the embodiments of the present application, the above task information may include, but is not limited to, task description, dependency relationship, task priority, and resource requirements and other information.

[0102] In a specific application, after the robot receives a user instruction or a system operation instruction, it can generate a corresponding task to be executed according to the instruction. When generating the task to be executed, the corresponding task information can be obtained, and the task management system can obtain the task information of all tasks to be executed by the robot.

[0103] S302: Input the task information into the large model for task analysis to obtain a conflict prediction result.

[0104] In the embodiments of the present application, the above large model may be a deep neural network model or a large language model. The embodiments of the present application use a trained large model to deeply analyze tasks, that is, use the large model to deeply analyze tasks. Specifically, it can analyze the dependency relationship between tasks, as well as possible resource conflicts and path conflicts, etc. Then, according to the resource conflicts and path conflicts obtained from the analysis, a conflict prediction result is generated.

[0105] Among them, a large model refers to a model with a large number of parameters trained using large-scale data and powerful computing capabilities. It usually has a high degree of generality and generalization ability. In the embodiments of this application, the large model is used to assist in the task conflict prediction of the task management system, which can effectively enhance the intelligence of the task management system, thereby effectively predicting possible conflict situations among multiple tasks and obtaining the conflict prediction results between the tasks to be executed by the robot.

[0106] In specific applications, the training process of the above large model can be implemented in a pre-training and fine-tuning mode. It is pre-trained on a large amount of unsupervised data to enable the model to learn general language knowledge and information extraction capabilities. Then, for the downstream tasks of task information and conflict prediction, a small amount of supervised data is used to fine-tune the large model. For example, using the historical task information data and the corresponding relationship of conflict prediction, so that the large model can deeply analyze the tasks and thus predict possible conflict situations.

[0107] S303: Start the adaptive algorithm to generate a conflict solution according to the conflict prediction result and the robot state.

[0108] In the embodiments of this application, starting the adaptive algorithm to automatically generate a conflict solution may specifically include dynamic priority adjustment, resource allocation optimization, and task route replanning, etc.

[0109] Among them, the adaptive algorithm can dynamically adjust the execution order of the conflict tasks according to the priorities of the conflict tasks and the current environmental state, that is, re-adjust the execution time of the tasks. The adaptive algorithm can also re-allocate the resources of the conflict tasks for various resources of the robot, such as power resources, computing resources, mechanical structures, etc. The adaptive algorithm can also re-plan the tasks, including changing the execution order of the tasks, adjusting the execution time of the tasks, or modifying the execution path of the tasks. For example, in a hotel food delivery task, if there is a conflict in the original task path of the robot, the adaptive algorithm can re-plan the path to avoid congested areas and ensure the smooth progress of the food delivery task.

[0110] It can be understood that the adaptive algorithm can automatically decide the optimal conflict solution. In specific applications, the above adaptive algorithm can be an adaptive genetic algorithm, an Adaptive Neuro-Fuzzy Inference System (ANFIS), a Kalman Filter, and its adaptive variants, etc. This application does not make a unique limitation on this.

[0111] The adaptive algorithm first relies on the real-time monitoring of the robot system, including the perception of various states of the robot, such as the position and movement of the robotic arm, the data acquisition of sensors, the progress of task execution, etc. Therefore, when the large model can predict in advance that there are conflicting tasks, the adaptive algorithm can adapt the resource information and status information of the robot, generate the optimal conflict resolution solution, and adjust the execution order, execution time, execution path, etc. of the conflicting tasks to reduce the occurrence of conflicts.

[0112] S304: Adjust the task execution plan according to the conflict resolution solution, and execute the task according to the adjusted task execution plan.

[0113] It can be understood that the task management system of the robot can generate a task execution plan according to the priority of the task, that is, according to the task scheduling scheme. After obtaining the conflict resolution solution, the task management system can adjust the original task execution plan according to the content of the conflict resolution solution. For example, if the execution time of task A is changed in the conflict resolution solution, the execution time of task A in the task execution plan is adjusted from the original execution time to the corresponding time in the conflict resolution solution; another example is that if the resource allocation of task B is changed in the conflict resolution solution, the resource allocation of task B in the task execution plan can be adjusted to the resource allocation of task B in the conflict resolution solution.

[0114] In specific applications, the task execution plan may include the execution time of the task, resource allocation, path planning, etc.

[0115] After obtaining the adjusted task execution plan, the task management system can issue an execution command to the corresponding execution mechanism at the execution time according to the task execution plan to execute the tasks in the task execution plan.

[0116] In summary, the task management method provided by the embodiments of the present application can use the large model to deeply analyze tasks, thereby predicting possible conflicting tasks, and then dynamically generate the optimal conflict resolution solution for the conflicting tasks through the adaptive algorithm. Based on the optimized task execution order and resource allocation scheme in the conflict resolution solution obtained by the adaptive algorithm, the tasks are executed, which can effectively reduce the occurrence of task conflicts, thereby improving the task execution efficiency, reducing the resource waste and execution delay caused by task conflicts, and effectively improving the reliability and stability of the task scheduling system.

[0117] Please refer to Figure 4 , in another embodiment of the present application, different from the previous embodiment, Figure 4 In the example shown, the task management method further includes S401 - S403, which are described in detail as follows:

[0118] S401: Obtain external environment information and robot status information.

[0119] The above external environment information can be information related to the current external environment, specifically including but not limited to the distribution of obstacles in the environment, the positions of targets in the environment, etc. The above robot state information is information related to the robot state, such as remaining battery power, current position, current posture, and so on.

[0120] In specific applications, the robot can obtain the robot's state information through various sensors, controllers, and other devices in the robot, that is, the robot can obtain the robot state information through the perception of its own state. The external environment information can be obtained through sensors capable of obtaining external information. For example, it can be obtained through radar sensors, camera devices, and other devices set on the robot.

[0121] S402: Input the task information, external environment information, and robot state information into the large model for task analysis to obtain the priority adjustment results of each task.

[0122] In specific applications, the above large model can be a deep neural network model or a large language model. The embodiments of this application use a trained large model to deeply analyze tasks, that is, use the large model to deeply analyze tasks, not only based on the task information of the task, such as task description and resource requirements, but also combined with the robot state information and external environment information to dynamically adjust the priority of the task.

[0123] Specifically, the application of the above large model in task priority evaluation can be mainly achieved through the context analysis function provided by the large model and the enhanced real-time evaluation function of the large model.

[0124] S403: Generate a task scheduling plan according to the priority adjustment results of each task.

[0125] Among them, the task scheduling plan can include the execution order of each task, that is, the execution order of the task can be determined according to the priority of the task, and the task with a higher priority is executed first.

[0126] Correspondingly, the above S304 specifically includes: generating a task execution plan according to the task scheduling plan and the conflict resolution plan, and issuing the task to the execution mechanism of the robot according to the task execution plan.

[0127] In summary, the task management method provided by the embodiments of this application, by utilizing the deep learning ability and context analysis function of the trained large model, combined with the robot state information, external environment information, and task information, dynamically adjusts the priority of the task in real time. Compared with the traditional task scheduling method, it can more flexibly adapt to the complex environment of actual applications, improve the accuracy and adaptability of task scheduling, and thus improve the execution rationality and reliability of tasks.

[0128] Please refer to Figure 5 , in another embodiment of the present application, different from the previous embodiment, Figure 5 in the example shown, the task management method further includes S501 - S502, which are described in detail as follows:

[0129] S501: Monitor the task execution status of the robot in real - time and generate execution status data according to the task execution status of the robot.

[0130] Among them, a trained large - model can be used to deeply analyze the execution status of the robot according to the task execution status, including analyzing whether there are abnormal situations in task execution, such as resource exhaustion, path blockage, etc.

[0131] S502: Adjust the parameters of the large - model according to the execution status data.

[0132] Specifically, the task scheduling scheme with abnormal situations (i.e., abnormal execution status) is used as negative feedback through the execution status data, and the task scheduling scheme without abnormal situations (i.e., normal execution status) is used as positive feedback and input into the large - model, so that the large - model can perform feedback adjustment of parameters based on the execution status data.

[0133] In summary, the task management method provided by the embodiments of the present application, by constructing an effective feedback mechanism, continuously learns and optimizes the task scheduling strategy of the large - model according to the actual effect of task execution. The large - model continuously optimizes the decision - making ability of the task management system according to the feedback situation, so that the task management system can perform task management more intelligently and efficiently when facing new tasks and environmental changes, so that the task management system can continuously adapt to complex and changeable operating environments and improve the long - term operation performance of the system.

[0134] Corresponding to the task management method described in the above - mentioned embodiment, Figure 6 the block diagram of the robot provided by the embodiments of the present application is shown. For the sake of convenience of description, only the parts related to the embodiments of the present application are shown.

[0135] Refer to Figure 6 , the above - mentioned robot may include: an acquisition module 601, a conflict prediction module 602, a generation module 603, and an execution module 604.

[0136] The acquisition module 601 is used to acquire the task information of the task to be executed;

[0137] The planning module 602 is used to input the task information into the large - model for task analysis to obtain a conflict prediction result;

[0138] The selection module 603 is used to start an adaptive algorithm to generate a conflict solution according to the conflict prediction result and the robot state;

[0139] The execution module 604 is used to adjust the task execution plan according to the conflict resolution solution and execute tasks according to the adjusted task execution plan.

[0140] In a possible implementation, the above-mentioned acquisition module 601 is further used to acquire external environment information and robot status information.

[0141] The above-mentioned robot further includes a priority adjustment module, which is used to input task information, external environment information, and robot status information into a large model for task analysis to obtain the priority adjustment results of each task.

[0142] The above-mentioned generation module is further used to generate a task scheduling plan according to the priority adjustment results of each task.

[0143] Correspondingly, the above-mentioned execution module 604 can be used to generate a task execution plan according to the task scheduling plan and the conflict resolution solution, and issue tasks to the execution mechanism of the robot according to the task execution plan.

[0144] In a possible implementation, the above-mentioned robot further includes a monitoring and feedback module and a parameter adjustment module.

[0145] Among them, the monitoring and feedback module is used to monitor the task execution status of the robot in real time and generate execution status data according to the task execution status of the robot.

[0146] The parameter adjustment module is used to adjust the parameters of the large model according to the execution status data.

[0147] In a possible implementation, the above-mentioned parameter adjustment module is specifically used to use the task scheduling plan with abnormal conditions as negative feedback and the task scheduling plan without abnormal conditions as positive feedback to input into the large model to adjust the parameters of the large model.

[0148] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units, due to being based on the same concept as the method embodiment of the present application, for their specific functions and the technical effects brought, reference can be specifically made to the method embodiment part, and details are not described herein again.

[0149] As can be seen above, the robot provided by the embodiment of the present application can also use the large model to deeply analyze tasks, thereby predicting possible conflicting tasks, and then dynamically generating the optimal conflict resolution solution for the conflicting tasks through an adaptive algorithm. Based on the optimized task execution order and resource allocation plan in the conflict resolution solution obtained by the adaptive algorithm, tasks are executed, which can effectively reduce the occurrence of task conflicts, thereby improving task execution efficiency, reducing resource waste and execution delays caused by task conflicts, and effectively improving the reliability and stability of the task scheduling system.

[0150] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0151] Figure 7 The following is a schematic structural diagram of a robot provided by another embodiment of this application. As Figure 7 shown, the robot 7 of this embodiment includes: at least one processor 70 ( Figure 7 only one is shown in the figure), a processor, a memory 71, and a computer program 72 stored in the memory 71 and executable on the at least one processor 70. When the processor 70 executes the computer program 72, it implements the steps in any of the foregoing method embodiments of the task management method.

[0152] The robot may include, but is not limited to, a processor 70 and a memory 71. Those skilled in the art can understand that Figure 7 the above is only an example of the robot 7 and does not constitute a limitation on the robot 7. It may include more or fewer components than shown in the figure, or combine some components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0153] The so-called processor 70 may be a central processing unit (CPU). The processor 70 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0154] The memory 71 may be an internal storage unit of the robot 7 in some embodiments, such as the hard disk or memory of the robot 7. The memory 71 may also be an external storage device of the robot 7 in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the robot 7. Further, the memory 71 may also include both the internal storage unit of the robot 7 and external storage devices. The memory 71 is used to store an operating system, application programs, a BootLoader, data, and other programs, such as the program code of the computer program. The memory 71 may also be used to temporarily store data that has been output or will be output.

[0155] An embodiment of the present application also provides a computer-readable storage medium storing a computer program, which when executed by a processor, can implement the steps in the above-mentioned method embodiments.

[0156] An embodiment of the present application provides a computer program product, which when running on a robot, enables the robot to implement the steps in the above-mentioned method embodiments.

[0157] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-mentioned method embodiments of the present application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium may at least include: any entity or device capable of carrying the computer program code to the robot, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium may not be an electrical carrier signal and a telecommunication signal.

[0158] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For parts not described or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0159] Those of ordinary skill in the art will realize that the units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A professional technician may use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0160] In the embodiments provided in this application, it should be understood that the disclosed device / network device and method can be implemented in other ways. For example, the device / network device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the device or unit can be in electrical, mechanical or other forms.

[0161] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0162] The above-described embodiments are only used to illustrate the technical solutions of this application, rather than to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included in the protection scope of this application.

Claims

1. A task management method, characterized in that: include: Get the task information of the task to be executed; Inputting the task information into the large model to perform task analysis and obtain conflict prediction results; Starting an adaptive algorithm to generate a conflict resolution method according to the conflict prediction result and the robot state; Adjust the task execution plan according to the conflict resolution plan, and execute the task according to the adjusted task execution plan.

2. The task management method according to claim 1, characterized in that: The method further comprises: Obtain external environment information and robot status information; Inputting the task information, the external environment information and the robot state information into the large model to perform task analysis and obtain the priority adjustment result of each task; Generating a task scheduling plan according to the priority adjustment results of each task; Accordingly, adjusting the task execution plan according to the conflict resolution method and executing the task according to the adjusted task execution plan includes: A task execution plan is generated according to the task scheduling scheme and the conflict resolution scheme, and the task is issued to the robot's execution mechanism according to the task execution plan.

3. The task management method according to claim 1 or 2, characterized in that: The method further comprises: Monitor the task execution status of the robot in real time, and generate execution status data according to the task execution status of the robot; According to the execution status data, the parameters of the large model are adjusted.

4. The task management method according to claim 3, characterized in that: The generating execution status data according to the task execution status of the robot comprises: The task execution status of the robot is input into the large model for analysis to obtain the execution status data.

5. The task management method according to claim 3, characterized in that: The execution status data includes an abnormal execution status and a normal execution status, and adjusting the parameters of the large model according to the execution status data includes: The task scheduling scheme corresponding to the abnormal execution state is used as negative feedback, and the task scheduling scheme corresponding to the normal execution state is used as positive feedback, which are input into the large model to adjust the parameters of the large model.

6. The task management method according to claim 2, characterized in that: The step of generating a task execution plan according to the task scheduling scheme and the conflict resolution scheme, and issuing the task to the robot's execution mechanism according to the task execution plan, includes: Generate the task execution plan according to the task scheduling scheme; Adjust the content of the task execution plan according to the conflict resolution method to obtain the adjusted task execution plan; The task is sent to the robot's actuator according to the adjusted task execution plan.

7. The task management method according to claim 1, characterized in that: The task execution plan includes the task execution time, resource allocation and path planning.

8. A task management system, characterized in that: include: A task receiving module is used to receive external input task information; A large model task analysis module is connected to the task receiving module. The large model task analysis module is configured with a trained large model for performing task analysis based on the task information, predicting task conflicts, and generating conflict prediction results when there are task conflicts. A conflict resolution module, connected to the large model task analysis module, is used to start an adaptive algorithm to generate a conflict resolution solution when a conflict prediction result is received; The task scheduling module is connected to the conflict resolution module and is used to generate a task execution plan according to the task scheduling scheme and the conflict resolution scheme, and send the task to the robot's execution mechanism according to the task execution plan.

9. The task management system according to claim 8, characterized in that: The task scheduling module is also connected to the large model task analysis module; The large model task analysis module is also used to dynamically adjust the priority of the task according to the task information, external environment information and robot state information, generate the task scheduling plan, and send the task scheduling plan to the task scheduling module.

10. The task management system according to claim 8 or 9, characterized in that: Also includes: An execution monitoring module, used to monitor the task execution status of the robot in real time and generate execution status data according to the task execution status of the robot; A feedback adjustment module is used to perform feedback adjustment on the parameters of the large model according to the execution status data.

11. A robot comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

12. A computer program product, characterized in that When the computer program product runs on a robot, the robot is caused to perform the method according to any one of claims 1 to 7.

Images