A resource scheduling method and system for an intelligent agent

Abstract

This invention provides a resource scheduling method and system for intelligent agents. The method includes: creating a corresponding intelligent agent cluster in real time based on several intelligent agents, and inputting a target task into the intelligent agent cluster accordingly; during the execution of the target task by the intelligent agent cluster, determining in real time whether there is a target intelligent agent in the cluster that cannot execute the target task; if it is determined in real time that there is a target intelligent agent in the cluster that cannot execute the target task, then creating a corresponding target edge cloud in real time based on preset rules according to the intelligent agent cluster, and completing the target task through the target edge cloud. This invention can effectively process the corresponding target task through the edge cloud created in real time, thereby improving work efficiency.

Description

Technical Field

[0001] This invention relates to the field of intelligent agent control technology, and in particular to a resource scheduling method and system for intelligent agents. Background Technology

[0002] With the advancement of technology and the rapid development of productivity, people have made significant progress in the field of industrial manufacturing and have developed intelligent agents such as drones and industrial robots, which have facilitated people's work.

[0003] In practice, all existing intelligent agents require certain resources. Specifically, some agents may require storage resources, while others may require computing resources. Furthermore, in scenarios where multiple agents work together to execute tasks, different agents can handle different amounts of storage and computing resources. Therefore, it is necessary to schedule the resources used by each agent accordingly.

[0004] Furthermore, in the actual process of scheduling intelligent agent resources, most existing technologies require the collection of a large amount of historical data and the training of a resource scheduling model based on this historical data. The resource allocation is then completed through this resource scheduling model. However, although this method can ultimately complete the allocation of resources to a certain extent, it requires a lot of resources to build the resource scheduling model in the early stage, which has certain limitations. At the same time, the allocation cost is high, which reduces work efficiency. Summary of the Invention

[0005] Based on this, the purpose of the present invention is to provide a resource scheduling method and system for intelligent agents, so as to solve the problem that the prior art requires a lot of resources to build a resource scheduling model in the early stage, resulting in certain limitations in use and high allocation costs.

[0006] The first aspect of the present invention proposes:

[0007] A resource scheduling method for intelligent agents, wherein the method includes:

[0008] A corresponding intelligent agent cluster is created in real time based on several intelligent agents, and the target task is input into the intelligent agent cluster accordingly;

[0009] During the execution of the target task by the intelligent agent cluster, it is determined in real time whether there is a target intelligent agent in the intelligent agent cluster that is unable to execute the target task;

[0010] If it is determined in real time that there is a target agent in the agent cluster that cannot perform the target task, then a corresponding target edge cloud is created in real time based on the agent cluster according to preset rules, and the target task is completed through the target edge cloud.

[0011] The beneficial effects of this invention are: by detecting several intelligent agents in real time, an intelligent agent cluster for processing data can be created in real time. Based on this, by simply inputting the target task into the intelligent agent cluster, it is possible to determine in real time whether there are target intelligent agents that cannot perform the task. Based on this, a target edge cloud capable of processing the current target task can be created in real time based on the current target intelligent agent, thereby enabling reasonable resource scheduling between intelligent agents, eliminating limitations in use, and significantly improving work efficiency.

[0012] Furthermore, the step of determining in real time whether there is a target agent in the agent cluster that is unable to perform the target task includes:

[0013] When the target task is acquired in real time, a full scan of the target task is performed to detect the corresponding processing items contained in the target task in real time.

[0014] The subtasks corresponding to each of the aforementioned processing items are detected in real time, and each of the aforementioned subtasks is unique;

[0015] Based on each subtask, it is determined in real time whether the target intelligent agent exists in the intelligent agent cluster, and the target intelligent agent is unique.

[0016] Furthermore, the step of determining in real time whether the target agent exists in the agent cluster based on each subtask includes:

[0017] When each subtask is acquired in real time, the task attributes corresponding to each subtask are detected in real time, and an initial agent that is adapted to each subtask is matched in the agent cluster according to the task attributes.

[0018] The amount of data processing corresponding to each initial intelligent agent is detected in real time, and the amount of task corresponding to each subtask is detected in real time.

[0019] The presence of the target intelligent agent in the intelligent agent cluster is determined in real time based on the data processing volume and the task volume, where the data processing volume and the task volume are specific numerical values.

[0020] Furthermore, the step of determining in real time whether the target intelligent agent exists in the intelligent agent cluster based on the data processing volume and the task volume includes:

[0021] When the data processing volume corresponding to the initial intelligent agent and the task volume corresponding to its subtask are obtained in real time, it is determined in real time whether the data processing volume is greater than the task volume.

[0022] If it is determined in real time that the amount of data processed is less than the amount of task, then the initial agent corresponding to the current amount of data processed being less than the amount of task is set as the target agent, wherein one initial agent corresponds to only one subtask.

[0023] Furthermore, the step of creating the corresponding target edge cloud in real time based on the intelligent agent cluster according to preset rules includes:

[0024] When the target intelligent agent is identified in real time, the communication range corresponding to the target intelligent agent is detected in real time, and the communication range includes a specific length;

[0025] Based on the communication range, the target edge cloud is created in real time according to the target intelligent agent, and the target edge cloud is unique.

[0026] Furthermore, the step of creating the target edge cloud in real time based on the communication range according to the target intelligent agent includes:

[0027] When the communication range of the target intelligent agent is determined in real time, a communication area corresponding to the target intelligent agent is created in real time in the intelligent agent cluster based on the communication range, with the target intelligent agent as the center. The communication area is circular.

[0028] A full scan of the communication area is performed to detect, in real time, several neighboring agents contained within the communication area, and the target edge cloud is created in real time based on the target agent and several neighboring agents, with each neighboring agent being unique.

[0029] Furthermore, the step of creating the target edge cloud in real time based on the target agent and several neighboring agents includes:

[0030] When several neighboring intelligent agents are acquired in real time, a corresponding target communication network is created in real time based on the target intelligent agent and the several neighboring intelligent agents.

[0031] The target communication network and the preset edge algorithm are fused to generate a corresponding target edge network in real time, and the target edge network is uploaded to the cloud in real time to generate the target edge cloud in real time. The target edge network is unique.

[0032] The second aspect of the present invention proposes:

[0033] A resource scheduling system for intelligent agents, wherein the system comprises:

[0034] The input module is used to create a corresponding intelligent agent cluster in real time based on several intelligent agents, and input the target task into the intelligent agent cluster accordingly;

[0035] The judgment module is used to determine in real time whether there is a target intelligent agent in the intelligent agent cluster that cannot execute the target task during the execution of the target task in the intelligent agent cluster;

[0036] The execution module is used to, if it is determined in real time that there is a target agent in the agent cluster that cannot perform the target task, create a corresponding target edge cloud in real time based on the agent cluster according to preset rules, and complete the target task through the target edge cloud.

[0037] Furthermore, the determination module is specifically used for:

[0038] When the target task is acquired in real time, a full scan of the target task is performed to detect the corresponding processing items contained in the target task in real time.

[0039] The subtasks corresponding to each of the aforementioned processing items are detected in real time, and each of the aforementioned subtasks is unique;

[0040] Based on each subtask, it is determined in real time whether the target intelligent agent exists in the intelligent agent cluster, and the target intelligent agent is unique.

[0041] Furthermore, the determination module is specifically used for:

[0042] When each subtask is acquired in real time, the task attributes corresponding to each subtask are detected in real time, and an initial agent that is adapted to each subtask is matched in the agent cluster according to the task attributes.

[0043] The amount of data processing corresponding to each initial intelligent agent is detected in real time, and the amount of task corresponding to each subtask is detected in real time.

[0044] The presence of the target intelligent agent in the intelligent agent cluster is determined in real time based on the data processing volume and the task volume, where the data processing volume and the task volume are specific numerical values.

[0045] Furthermore, the determination module is specifically used for:

[0046] When the data processing volume corresponding to the initial intelligent agent and the task volume corresponding to its subtask are obtained in real time, it is determined in real time whether the data processing volume is greater than the task volume.

[0047] If it is determined in real time that the amount of data processed is less than the amount of task, then the initial agent corresponding to the current amount of data processed being less than the amount of task is set as the target agent, wherein one initial agent corresponds to only one subtask.

[0048] Furthermore, the execution module is specifically used for:

[0049] When the target intelligent agent is identified in real time, the communication range corresponding to the target intelligent agent is detected in real time, and the communication range includes a specific length;

[0050] Based on the communication range, the target edge cloud is created in real time according to the target intelligent agent, and the target edge cloud is unique.

[0051] Furthermore, the execution module is specifically used for:

[0052] When the communication range of the target intelligent agent is determined in real time, a communication area corresponding to the target intelligent agent is created in real time in the intelligent agent cluster based on the communication range, with the target intelligent agent as the center. The communication area is circular.

[0053] A full scan of the communication area is performed to detect, in real time, several neighboring agents contained within the communication area, and the target edge cloud is created in real time based on the target agent and several neighboring agents, with each neighboring agent being unique.

[0054] Furthermore, the execution module is specifically used for:

[0055] When several neighboring intelligent agents are acquired in real time, a corresponding target communication network is created in real time based on the target intelligent agent and the several neighboring intelligent agents.

[0056] The target communication network and the preset edge algorithm are fused to generate a corresponding target edge network in real time, and the target edge network is uploaded to the cloud in real time to generate the target edge cloud in real time. The target edge network is unique.

[0057] The third aspect of the present invention proposes:

[0058] A computer includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the resource scheduling method for intelligent agents as described above.

[0059] The fourth aspect of the present invention proposes:

[0060] A readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the resource scheduling method for intelligent agents as described above.

[0061] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0062] Figure 1 A flowchart of a resource scheduling method for an intelligent agent provided in the first embodiment of the present invention;

[0063] Figure 2 This is a structural block diagram of a resource scheduling system for intelligent agents provided in the third embodiment of the present invention.

[0064] The following detailed description, in conjunction with the accompanying drawings, will further illustrate the present invention. Detailed Implementation

[0065] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Several embodiments of the invention are illustrated in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0066] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0067] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0068] Please see Figure 1The figure shows a resource scheduling method for intelligent agents provided in the first embodiment of the present invention. The resource scheduling method for intelligent agents provided in this embodiment can promptly process target tasks that intelligent agents cannot complete by creating an edge cloud in real time, thereby greatly improving work efficiency.

[0069] Specifically, this embodiment provides:

[0070] A resource scheduling method for intelligent agents specifically includes the following steps:

[0071] Step S10: Create a corresponding intelligent agent cluster in real time based on several intelligent agents, and input the target task into the intelligent agent cluster accordingly;

[0072] Step S20: During the execution of the target task by the intelligent agent cluster, it is determined in real time whether there is a target intelligent agent in the intelligent agent cluster that cannot execute the target task;

[0073] Step S30: If it is determined in real time that there is a target agent in the agent cluster that cannot perform the target task, then a corresponding target edge cloud is created in real time according to the agent cluster based on preset rules, and the target task is completed through the target edge cloud.

[0074] Specifically, in this embodiment, it should first be noted that in order to successfully execute each target task, it is necessary to obtain the required task information and agent information in real time. At this time, it is necessary to analyze and process the working status of the existing agents. Specifically, it should be noted that the resource scheduling method provided by this invention is mainly implemented for existing agent clusters, that is, it is used to schedule the resources in the existing agent cluster in real time. It should be noted that the resources specifically include computing resources and storage resources. Based on this, in order to improve work efficiency in practical applications, this invention will integrate the several agents detected in real time, that is, create a corresponding agent cluster in real time based on the current agents. Based on this, the corresponding tasks can be issued to the current agent cluster. Specifically, during the execution of tasks by the agent cluster, it is inevitable that a certain agent will be unable to complete the task. Based on this, this invention will mark the tasks that the current agent cannot complete and set them as the required target tasks for subsequent processing.

[0075] Furthermore, after determining the required target task in real time through the above steps, the server set up in the background can immediately create the corresponding target edge cloud based on the current intelligent agent cluster according to the pre-set rules. It should be noted that the existing edge cloud is a data processing system, but its characteristic is that it can be set up on edge devices. Edge devices can complete a large amount of data processing with less resources. Based on this, the target edge cloud created in real time by the present invention can effectively meet the processing requirements of the above target task and execute it smoothly, thereby enabling the intelligent agent cluster to be in a stable working state continuously and effectively, which greatly improves work efficiency and enhances the user experience.

[0076] Second Embodiment

[0077] Furthermore, the step of determining in real time whether there is a target agent in the agent cluster that is unable to perform the target task includes:

[0078] When the target task is acquired in real time, a full scan of the target task is performed to detect the corresponding processing items contained in the target task in real time.

[0079] The subtasks corresponding to each of the aforementioned processing items are detected in real time, and each of the aforementioned subtasks is unique;

[0080] Based on each subtask, it is determined in real time whether the target intelligent agent exists in the intelligent agent cluster, and the target intelligent agent is unique.

[0081] Furthermore, the step of determining in real time whether the target agent exists in the agent cluster based on each subtask includes:

[0082] When each subtask is acquired in real time, the task attributes corresponding to each subtask are detected in real time, and an initial agent that is adapted to each subtask is matched in the agent cluster according to the task attributes.

[0083] The amount of data processing corresponding to each initial intelligent agent is detected in real time, and the amount of task corresponding to each subtask is detected in real time.

[0084] The presence of the target intelligent agent in the intelligent agent cluster is determined in real time based on the data processing volume and the task volume, where the data processing volume and the task volume are specific numerical values.

[0085] Furthermore, the step of determining in real time whether the target intelligent agent exists in the intelligent agent cluster based on the data processing volume and the task volume includes:

[0086] When the data processing volume corresponding to the initial intelligent agent and the task volume corresponding to its subtask are obtained in real time, it is determined in real time whether the data processing volume is greater than the task volume.

[0087] If it is determined in real time that the amount of data processed is less than the amount of task, then the initial agent corresponding to the current amount of data processed being less than the amount of task is set as the target agent, wherein one initial agent corresponds to only one subtask.

[0088] Furthermore, the step of creating the corresponding target edge cloud in real time based on the intelligent agent cluster according to preset rules includes:

[0089] When the target intelligent agent is identified in real time, the communication range corresponding to the target intelligent agent is detected in real time, and the communication range includes a specific length;

[0090] Based on the communication range, the target edge cloud is created in real time according to the target intelligent agent, and the target edge cloud is unique.

[0091] Furthermore, the step of creating the target edge cloud in real time based on the communication range according to the target intelligent agent includes:

[0092] When the communication range of the target intelligent agent is determined in real time, a communication area corresponding to the target intelligent agent is created in real time in the intelligent agent cluster based on the communication range, with the target intelligent agent as the center. The communication area is circular.

[0093] A full scan of the communication area is performed to detect, in real time, several neighboring agents contained within the communication area, and the target edge cloud is created in real time based on the target agent and several neighboring agents, with each neighboring agent being unique.

[0094] Furthermore, the step of creating the target edge cloud in real time based on the target agent and several neighboring agents includes:

[0095] When several neighboring intelligent agents are acquired in real time, a corresponding target communication network is created in real time based on the target intelligent agent and the several neighboring intelligent agents.

[0096] The target communication network and the preset edge algorithm are fused to generate a corresponding target edge network in real time, and the target edge network is uploaded to the cloud in real time to generate the target edge cloud in real time. The target edge network is unique.

[0097] Furthermore, in this embodiment, it should be noted that after obtaining the required target task in real time through the above steps, it is necessary to immediately parse and process the current target task. That is, it is necessary to determine in real time whether there is a problem within the intelligent agent cluster that cannot process the target task. Based on this, the present invention will first perform a full scan of the current target task. It should be pointed out that since existing target tasks are composed of a series of events, that is, a target task usually contains several processing items, the present invention will again detect the sub-tasks corresponding to each processing item in real time, and each sub-task is unique. Based on this, in order to objectively and accurately determine whether each sub-task can be executed, the present invention will detect the task attributes corresponding to each sub-task in real time. Specifically, for ease of understanding, for example, the task attributes can be data caching tasks, data... Encryption tasks and data transmission tasks, etc., can directly match the initial intelligent agent that is suitable for each subtask within the aforementioned intelligent agent cluster based on the current task attributes. At the same time, it can also synchronously detect the amount of data processing that each initial intelligent agent can complete, and the amount of tasks contained within each subtask. Based on this, it can determine in real time whether there is a situation where the data processing amount of an initial intelligent agent within the current intelligent agent cluster is less than the amount of tasks of the current subtask. Specifically, if not, it can be directly stated that each subtask can be completed. Conversely, if yes, it can be directly determined that there is a phenomenon where an intelligent agent cannot complete a subtask. Based on this, it is necessary to mark the initial intelligent agent that cannot complete the corresponding subtask in real time, and set the marked initial intelligent agent as the aforementioned target intelligent agent for subsequent processing.

[0098] Furthermore, after identifying the target intelligent agent in real time through the above steps, in order to successfully complete this subtask, this invention will create a corresponding target edge cloud in real time based on the current target intelligent agent. Specifically, this invention will first detect the communication range achievable by the current target intelligent agent. Based on this, with the current target intelligent agent as the center, the length of the current communication range will be detected. Simultaneously, with the length of the current communication range as the radius, the required communication area will be divided within the aforementioned intelligent agent cluster. It can be understood that this communication area is circular. Therefore, to facilitate subsequent implementation, this invention will perform a full scan within the current communication area. Furthermore, it can scan the current communication area in real time to identify neighboring intelligent agents that are compatible with the current target intelligent agent, i.e., intelligent agents close to the current target intelligent agent. Based on this, the present invention will immediately create a corresponding target communication network in real time according to the current target intelligent agent and several neighboring intelligent agents. It should be noted that, in order to make the target communication network compatible with existing edge devices, the present invention will also integrate the existing edge algorithms into the internal structure of the current target communication network to form a corresponding target edge network. On this basis, the target edge network will be uploaded to the cloud to form a corresponding target edge cloud, which can then perform corresponding tasks, thereby improving work efficiency.

[0099] Please see Figure 2 The third embodiment of the present invention provides:

[0100] A resource scheduling system for intelligent agents, wherein the system comprises:

[0101] The input module is used to create a corresponding intelligent agent cluster in real time based on several intelligent agents, and input the target task into the intelligent agent cluster accordingly;

[0102] The judgment module is used to determine in real time whether there is a target intelligent agent in the intelligent agent cluster that cannot execute the target task during the execution of the target task in the intelligent agent cluster;

[0103] The execution module is used to, if it is determined in real time that there is a target agent in the agent cluster that cannot perform the target task, create a corresponding target edge cloud in real time based on the agent cluster according to preset rules, and complete the target task through the target edge cloud.

[0104] Furthermore, the determination module is specifically used for:

[0105] When the target task is acquired in real time, a full scan of the target task is performed to detect the corresponding processing items contained in the target task in real time.

[0106] The subtasks corresponding to each of the aforementioned processing items are detected in real time, and each of the aforementioned subtasks is unique;

[0107] Based on each subtask, it is determined in real time whether the target intelligent agent exists in the intelligent agent cluster, and the target intelligent agent is unique.

[0108] Furthermore, the determination module is specifically used for:

[0109] When each subtask is acquired in real time, the task attributes corresponding to each subtask are detected in real time, and an initial agent that is adapted to each subtask is matched in the agent cluster according to the task attributes.

[0110] The amount of data processing corresponding to each initial intelligent agent is detected in real time, and the amount of task corresponding to each subtask is detected in real time.

[0111] The presence of the target intelligent agent in the intelligent agent cluster is determined in real time based on the data processing volume and the task volume, where the data processing volume and the task volume are specific numerical values.

[0112] Furthermore, the determination module is specifically used for:

[0113] When the data processing volume corresponding to the initial intelligent agent and the task volume corresponding to its subtask are obtained in real time, it is determined in real time whether the data processing volume is greater than the task volume.

[0114] If it is determined in real time that the amount of data processed is less than the amount of task, then the initial agent corresponding to the current amount of data processed being less than the amount of task is set as the target agent, wherein one initial agent corresponds to only one subtask.

[0115] Furthermore, the execution module is specifically used for:

[0116] When the target intelligent agent is identified in real time, the communication range corresponding to the target intelligent agent is detected in real time, and the communication range includes a specific length;

[0117] Based on the communication range, the target edge cloud is created in real time according to the target intelligent agent, and the target edge cloud is unique.

[0118] Furthermore, the execution module is specifically used for:

[0119] When the communication range of the target intelligent agent is determined in real time, a communication area corresponding to the target intelligent agent is created in real time in the intelligent agent cluster based on the communication range, with the target intelligent agent as the center. The communication area is circular.

[0120] A full scan of the communication area is performed to detect, in real time, several neighboring agents contained within the communication area, and the target edge cloud is created in real time based on the target agent and several neighboring agents, with each neighboring agent being unique.

[0121] Furthermore, the execution module is specifically used for:

[0122] When several neighboring intelligent agents are acquired in real time, a corresponding target communication network is created in real time based on the target intelligent agent and the several neighboring intelligent agents.

[0123] The target communication network and the preset edge algorithm are fused to generate a corresponding target edge network in real time, and the target edge network is uploaded to the cloud in real time to generate the target edge cloud in real time. The target edge network is unique.

[0124] The fourth embodiment of the present invention provides a computer, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the resource scheduling method for intelligent agents as described above.

[0125] The fifth embodiment of the present invention provides a readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the resource scheduling method for intelligent agents as described above.

[0126] In summary, the resource scheduling method and system for intelligent agents provided by the above embodiments of the present invention can promptly process target tasks that intelligent agents cannot complete through the edge cloud constructed in real time, thereby significantly improving work efficiency.

[0127] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0128] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0129] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0130] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0131] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0132] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the appended claims.

Claims

1. A resource scheduling method for intelligent agents, characterized in that, The method includes: A corresponding intelligent agent cluster is created in real time based on several intelligent agents, and the target task is input into the intelligent agent cluster accordingly; During the execution of the target task by the intelligent agent cluster, it is determined in real time whether there is a target intelligent agent in the intelligent agent cluster that is unable to execute the target task; If it is determined in real time that there is a target agent in the agent cluster that cannot perform the target task, then a corresponding target edge cloud is created in real time based on the agent cluster according to preset rules, and the target task is completed through the target edge cloud. The step of creating the corresponding target edge cloud in real time based on the intelligent agent cluster according to preset rules includes: When the target intelligent agent is identified in real time, the communication range corresponding to the target intelligent agent is detected in real time, and the communication range includes a specific length; Based on the communication range, the target edge cloud is created in real time according to the target intelligent agent, and the target edge cloud is unique; The step of creating the target edge cloud in real time based on the communication range and the target intelligent agent includes: When the communication range of the target intelligent agent is determined in real time, a communication area corresponding to the target intelligent agent is created in real time in the intelligent agent cluster based on the communication range, with the target intelligent agent as the center. The communication area is circular. A full scan of the communication area is performed to detect, in real time, several neighboring agents contained within the communication area, and the target edge cloud is created in real time based on the target agent and several neighboring agents, with each neighboring agent being unique. The step of creating the target edge cloud in real time based on the target agent and several neighboring agents includes: When several neighboring intelligent agents are acquired in real time, a corresponding target communication network is created in real time based on the target intelligent agent and the several neighboring intelligent agents. The target communication network and the preset edge algorithm are fused to generate a corresponding target edge network in real time, and the target edge network is uploaded to the cloud in real time to generate the target edge cloud in real time. The target edge network is unique.

2. The resource scheduling method for intelligent agents according to claim 1, characterized in that: The step of determining in real time whether there is a target agent in the agent cluster that is unable to perform the target task includes: When the target task is acquired in real time, a full scan of the target task is performed to detect the corresponding processing items contained in the target task in real time. The subtasks corresponding to each of the aforementioned processing items are detected in real time, and each of the aforementioned subtasks is unique; Based on each subtask, it is determined in real time whether the target intelligent agent exists in the intelligent agent cluster, and the target intelligent agent is unique.

3. The resource scheduling method for intelligent agents according to claim 2, characterized in that: The step of determining in real time whether the target agent exists in the agent cluster based on each subtask includes: When each subtask is acquired in real time, the task attributes corresponding to each subtask are detected in real time, and an initial agent that is adapted to each subtask is matched in the agent cluster according to the task attributes. The amount of data processing corresponding to each initial intelligent agent is detected in real time, and the amount of task corresponding to each subtask is detected in real time. The presence of the target intelligent agent in the intelligent agent cluster is determined in real time based on the data processing volume and the task volume, where the data processing volume and the task volume are specific numerical values.

4. The resource scheduling method for intelligent agents according to claim 3, characterized in that: The step of determining in real time whether the target intelligent agent exists in the intelligent agent cluster based on the data processing volume and the task volume includes: When the data processing volume corresponding to the initial intelligent agent and the task volume corresponding to its subtask are obtained in real time, it is determined in real time whether the data processing volume is greater than the task volume. If it is determined in real time that the amount of data processed is less than the amount of task, then the initial agent corresponding to the current amount of data processed being less than the amount of task is set as the target agent, wherein one initial agent corresponds to only one subtask.

5. A resource scheduling system for intelligent agents, characterized in that, The system is used to implement the resource scheduling method for an intelligent agent as described in any one of claims 1 to 4, the system comprising: The input module is used to create a corresponding intelligent agent cluster in real time based on several intelligent agents, and input the target task into the intelligent agent cluster accordingly; The judgment module is used to determine in real time whether there is a target intelligent agent in the intelligent agent cluster that cannot execute the target task during the execution of the target task in the intelligent agent cluster; The execution module is used to, if it is determined in real time that there is a target agent in the agent cluster that cannot perform the target task, create a corresponding target edge cloud in real time based on the agent cluster according to preset rules, and complete the target task through the target edge cloud.

6. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the resource scheduling method for intelligent agents as described in any one of claims 1 to 4.

7. A readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the resource scheduling method for intelligent agents as described in any one of claims 1 to 4.

Images