Operation and maintenance task processing method and device, equipment, readable storage medium and product

Abstract

The application relates to an operation and maintenance task processing method and device, equipment, a readable storage medium and a product. The method comprises the following steps: for each operation and maintenance task in a current scheduling period, evaluating a tension value of the operation and maintenance task based on a task tuple of the operation and maintenance task, the task tuple at least comprising a task type, an expected task period, a capability demand vector and a task position of the operation and maintenance task; determining a target capability template of each agent in the current scheduling period based on the tension values of the operation and maintenance tasks, the target capability template being used for indicating an operation and maintenance capability configured for the corresponding agent; for each operation and maintenance task, determining a cost score of each agent for executing the operation and maintenance task based on the task tuple of the operation and maintenance task and the target capability templates of the agents; and selecting an agent for executing the operation and maintenance task from the multiple agents based on the cost scores of the agents, and executing the operation and maintenance task according to the selected agent, thereby improving the operation and maintenance task processing efficiency.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, device, readable storage medium, and product for processing operation and maintenance tasks. Background Technology

[0002] With the development of computer technology, the expansion of industrial system scale and the continuous improvement of intelligence, complex operation and maintenance scenarios have put forward unprecedented requirements for task orchestration and resource coordination.

[0003] In typical scenarios such as power line inspection, rail transit maintenance, petrochemical equipment support, and smart factory production line management, maintenance tasks often exhibit strong heterogeneity, dynamism, and structural dependencies. These tasks not only come from diverse sources, including periodic inspections, emergency repairs, anomaly verification, data collection, and equipment cleaning, but also have strict logical constraints and execution sequences. For example, inspection tasks must be completed before maintenance tasks, and certain verification operations depend on data collection results. To smoothly manage maintenance tasks in these scenarios, maintenance personnel typically need to orchestrate the tasks to determine their execution order. However, this orchestration method is inefficient and fails to improve the overall efficiency of maintenance task processing. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, equipment, readable storage medium, and product for handling operation and maintenance tasks that can improve the efficiency of operation and maintenance task processing, in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a method for processing operation and maintenance tasks, including:

[0006] Obtain the set of tasks to be scheduled within the current scheduling period, wherein the set of tasks to be scheduled includes multiple operation and maintenance tasks;

[0007] For each operation and maintenance task, the tension value of the operation and maintenance task is evaluated based on the task tuple of the operation and maintenance task. The task tuple includes at least the task type, expected task time period, capacity requirement vector, and task location of the operation and maintenance task. The tension value is used to characterize the urgency of the operation and maintenance task.

[0008] Based on the tension value of each operation and maintenance task, the target capability template of each agent is determined in the current scheduling cycle. The target capability template is used to indicate the operation and maintenance capabilities configured by the corresponding agent.

[0009] For each operation and maintenance task, based on the task tuple of the operation and maintenance task and the target capability template of each agent, the cost score of each agent executing the operation and maintenance task is determined. Based on the cost score of each agent, an agent is selected from multiple agents to execute the operation and maintenance task, and the operation and maintenance task is executed according to the selected agent.

[0010] Secondly, this application also provides an operation and maintenance task processing device, including:

[0011] The task set acquisition module is used to acquire the set of tasks to be scheduled within the current scheduling period, and the set of tasks to be scheduled includes multiple operation and maintenance tasks.

[0012] The task tension determination module is used to evaluate the tension value of each operation and maintenance task based on the task tuple of the operation and maintenance task. The task tuple includes at least the task type, expected task time period, capacity requirement vector, and task location of the operation and maintenance task. The tension value is used to characterize the urgency of the operation and maintenance task.

[0013] The capability template determination module is used to determine the target capability template of each agent in the current scheduling cycle based on the tension value of each operation and maintenance task. The target capability template is used to indicate the operation and maintenance capabilities configured by the corresponding agent.

[0014] The operation and maintenance task execution module is used to determine the cost score of each intelligent agent for each operation and maintenance task based on the task tuple of the operation and maintenance task and the target capability template of each intelligent agent. Based on the cost score of each intelligent agent, the module selects an intelligent agent from multiple intelligent agents to execute the operation and maintenance task and executes the operation and maintenance task according to the selected intelligent agent.

[0015] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0016] Obtain the set of tasks to be scheduled within the current scheduling period, wherein the set of tasks to be scheduled includes multiple operation and maintenance tasks;

[0017] For each operation and maintenance task, the tension value of the operation and maintenance task is evaluated based on the task tuple of the operation and maintenance task. The task tuple includes at least the task type, expected task time period, capacity requirement vector, and task location of the operation and maintenance task. The tension value is used to characterize the urgency of the operation and maintenance task.

[0018] Based on the tension value of each operation and maintenance task, the target capability template of each agent is determined in the current scheduling cycle. The target capability template is used to indicate the operation and maintenance capabilities configured by the corresponding agent.

[0019] For each operation and maintenance task, based on the task tuple of the operation and maintenance task and the target capability template of each agent, the cost score of each agent executing the operation and maintenance task is determined. Based on the cost score of each agent, an agent is selected from multiple agents to execute the operation and maintenance task, and the operation and maintenance task is executed according to the selected agent.

[0020] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0021] Obtain the set of tasks to be scheduled within the current scheduling period, wherein the set of tasks to be scheduled includes multiple operation and maintenance tasks;

[0022] For each operation and maintenance task, the tension value of the operation and maintenance task is evaluated based on the task tuple of the operation and maintenance task. The task tuple includes at least the task type, expected task time period, capacity requirement vector, and task location of the operation and maintenance task. The tension value is used to characterize the urgency of the operation and maintenance task.

[0023] Based on the tension value of each operation and maintenance task, the target capability template of each agent is determined in the current scheduling cycle. The target capability template is used to indicate the operation and maintenance capabilities configured by the corresponding agent.

[0024] For each operation and maintenance task, based on the task tuple of the operation and maintenance task and the target capability template of each agent, the cost score of each agent executing the operation and maintenance task is determined. Based on the cost score of each agent, an agent is selected from multiple agents to execute the operation and maintenance task, and the operation and maintenance task is executed according to the selected agent.

[0025] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0026] Obtain the set of tasks to be scheduled within the current scheduling period, wherein the set of tasks to be scheduled includes multiple operation and maintenance tasks;

[0027] For each operation and maintenance task, the tension value of the operation and maintenance task is evaluated based on the task tuple of the operation and maintenance task. The task tuple includes at least the task type, expected task time period, capacity requirement vector, and task location of the operation and maintenance task. The tension value is used to characterize the urgency of the operation and maintenance task.

[0028] Based on the tension value of each operation and maintenance task, the target capability template of each agent is determined in the current scheduling cycle. The target capability template is used to indicate the operation and maintenance capabilities configured by the corresponding agent.

[0029] For each operation and maintenance task, based on the task tuple of the operation and maintenance task and the target capability template of each agent, the cost score of each agent executing the operation and maintenance task is determined. Based on the cost score of each agent, an agent is selected from multiple agents to execute the operation and maintenance task, and the operation and maintenance task is executed according to the selected agent.

[0030] The aforementioned operation and maintenance task processing method, apparatus, equipment, readable storage medium, and product obtain a set of tasks to be scheduled within the current scheduling cycle. This set includes multiple operation and maintenance tasks. For each operation and maintenance task, based on its task tuple, the tension value of the task is evaluated. The task tuple includes at least the task type, expected task time period, capability requirement vector, and task location. The tension value characterizes the urgency of the operation and maintenance task. Thus, the urgency of the operation and maintenance task can be reflected based on the tension value. Then, based on the tension value of each operation and maintenance task, the target capability template for each agent within the current scheduling cycle is adaptively determined. The target capability template indicates the operation and maintenance capabilities configured by the corresponding agent. Therefore, for each operation and maintenance task, based on the task tuple and the target capability template of each agent, the cost score for each agent executing the operation and maintenance task is determined. Finally, based on the cost scores of each agent, the agent to execute the operation and maintenance task can be automatically and accurately selected from multiple agents from the cost dimension, and the operation and maintenance task is executed according to the selected agent. In this way, by considering the urgency of the operation and maintenance tasks and the operation and maintenance capabilities of each agent, not only are the operation and maintenance capabilities that agents should be configured during operation and maintenance, but also the operation and maintenance tasks are accurately assigned to agents. This allows each agent to execute the appropriate operation and maintenance tasks with the appropriate operation and maintenance capabilities. The entire process is completed accurately and automatically without the need for manual arrangement by personnel, thus improving the efficiency of operation and maintenance task processing. Attached Figure Description

[0031] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0032] Figure 1 This is an application environment diagram of an operation and maintenance task processing method in one embodiment;

[0033] Figure 2 This is a flowchart illustrating a method for handling operation and maintenance tasks in one embodiment;

[0034] Figure 3This is a structural block diagram of the operation and maintenance task processing device in one embodiment;

[0035] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0037] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0038] The operation and maintenance task processing method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104, or it can be located in the cloud or on another network server.

[0039] In some embodiments, after the server 104 receives scheduling requests uploaded by each terminal 102, the server 104 obtains a set of tasks to be scheduled within the current scheduling period based on each scheduling request. The set of tasks to be scheduled includes multiple maintenance tasks. For each maintenance task, the server 104 evaluates the tension value of the maintenance task based on the task tuple of the maintenance task. The task tuple includes at least the task type, expected task time period, capability requirement vector, and task location of the maintenance task. The tension value is used to characterize the urgency of the maintenance task. Based on the tension value of each maintenance task, the server 104 determines the target capability template of each agent within the current scheduling period. The target capability template is used to indicate the maintenance capabilities configured by the corresponding agent. For each maintenance task, the server 104 determines the cost score of each agent executing the maintenance task based on the task tuple of the maintenance task and the target capability template of each agent. Based on the cost score of each agent, the server 104 selects an agent from multiple agents to execute the maintenance task and executes the maintenance task according to the selected agent.

[0040] The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, etc. The server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0041] In one exemplary embodiment, such as Figure 2 As shown, a method for processing operation and maintenance tasks is provided, which can be applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps S202 to S208. Wherein:

[0042] Step S202: Obtain the set of tasks to be scheduled within the current scheduling period. The set of tasks to be scheduled includes multiple operation and maintenance tasks.

[0043] The current scheduling period is the current period for scheduling operation and maintenance tasks, and the set of tasks to be scheduled includes multiple operation and maintenance tasks to be performed.

[0044] Optionally, after receiving scheduling requests from various terminals, the server parses each request to obtain a total set of tasks to be scheduled. During scheduling, in the current scheduling cycle, the server removes completed maintenance tasks from the total set of tasks to be scheduled, retrieves maintenance tasks that meet the scheduling conditions of the current scheduling cycle from the removed set, and obtains a set of tasks to be scheduled within the current scheduling cycle based on the retrieved maintenance tasks. The scheduling conditions for the first scheduling cycle can be randomly selecting a preset number of maintenance tasks from the total set of tasks to be scheduled, or maintenance tasks without preceding maintenance tasks. For example, if the execution of one maintenance task requires the execution of another maintenance task first, then the other maintenance task is the maintenance task of that first maintenance task. The scheduling conditions for subsequent scheduling cycles are that the current time is not earlier than the expected start time of the maintenance task, and the preceding maintenance task of that maintenance task has been completed.

[0045] For example, the server obtains scheduling requests sent by different terminals to get a set of scheduling requests. , arrive This represents n scheduling requests. These requests can be automatically triggered (e.g., periodic detection tasks generated by a timed scheduling unit), generated by equipment anomaly detection feedback (e.g., edge nodes automatically reporting "voltage fluctuation anomaly" tasks through a status monitoring interface), or generated by manual input from the scheduling system (e.g., maintenance personnel manually entering "Please inspect the temperature control module in Zone C"). Each scheduling request is encapsulated by the scheduling system into a standard task tuple, including task number, task type number, expected task time period, capacity requirement vector, spatial location, and dependency code. The start and end times within the expected task time period are the expected start time and the latest completion time, respectively. The expected task time period can be understood as a time window, automatically set according to the task source. For example, periodic tasks have fixed time windows, and abnormal tasks can be automatically set to "start immediately and complete as soon as possible." To further refine the expected start time and latest completion time, the task tuple can also be represented as... Task tuple These represent the task number, task type number, expected start time, latest completion time, capacity requirement vector, spatial location, and dependency encoding, respectively. The expected start time to latest completion time is used to determine the expected task time period. Task type... The capability requirement vector is a finite set defined in the configuration, such as types like detection, repair, collection, and verification. The capability requirement vector is defined as the capability dimension required to complete the task, such as "temperature sensing," "tool capture," and "fault identification," represented as a fixed-dimensional binary vector, where 1 indicates the capability is required and 0 indicates it is not. Therefore, the capability requirement vector can be considered as a required capability vector. Spatial location is provided by the device or area coordinates bound to the maintenance task and read through the GIS device management system. Dependency encoding indicates whether the maintenance task must be completed before it can begin execution, such as... Need to be Then execute, Otherwise, it will be null (empty).

[0046] For example, consider a typical task: the "B3 cooling pump" monitoring unit reports abnormal parameter fluctuations, and the system automatically generates a maintenance task. The corresponding task type is "fault review". Expected task time period The capability requirement vector illustrates the corresponding capability dimensions as "visual recognition + remote communication," and spatial location. Represents GIS coordinates, and depends on the operation and maintenance tasks. (That is, the inspection report can only be reviewed after it is generated), therefore The above task information is encapsulated by the scheduling center in the task generation module. All fields are internal system structure fields with clear interfaces.

[0047] For example, after obtaining the scheduling requests from each node, the server parses each scheduling request to obtain the task tuples for each operation and maintenance task, and constructs a task graph based on the task tuples for each operation and maintenance task. Task Map This serves as the foundational structure for subsequent scheduling logic; and a set of node attributes. This serves as the input feature set for subsequent agent capability matching and path scheduling. Each node in the graph... The attribute vector of a node represents an operation and maintenance task (i.e., an atomic task). definition: The dependencies between operation and maintenance tasks exist in the form of directed edges. Each edge... Indicates maintenance tasks The start of execution depends on the operation and maintenance tasks. The completion of this process. Dependencies are established through fields. Derivation generation, if Then add a path from the task graph. point to The edges of a graph. Therefore, the set of edges of a graph is defined as: .

[0048] Task graph after construction This can be viewed as a multi-task execution network, where nodes represent operation and maintenance tasks, and edges represent the execution dependency chains between these tasks. This task graph... The task graph is stored as a directed adjacency structure for subsequent retrieval of the set of tasks to be scheduled. The completeness of the task graph is reflected not only in the rich representation of task attributes but also in the dynamic scalability of dependent edges. It also allows for dynamic modification of the task graph during the scheduling cycle as task states are updated, such as adding nodes, deleting edges, or merging multiple tasks into composite nodes. All graph modification operations follow graph state machine constraints, ensuring the graph structure maintains its directed acyclic property and supporting topology analysis.

[0049] Therefore, during the scheduling process, for the current scheduling period that is not the first scheduling period, the server updates the task status table from the storage within the current scheduling period. The process involves identifying the previous maintenance tasks that were completed in the previous scheduling cycle, filtering out maintenance tasks from the task graph that meet the scheduling conditions of the current scheduling cycle, and generating a set of tasks to be scheduled within the current scheduling cycle based on the filtered maintenance tasks. .

[0050] Step S204: For each operation and maintenance task, evaluate the tension value of the operation and maintenance task based on the task tuple of the operation and maintenance task. The task tuple includes at least the task type, expected task time period, capability requirement vector, and task location of the operation and maintenance task. The tension value is used to characterize the urgency of the operation and maintenance task.

[0051] The tension value refers to the numerical value of the tension index for the corresponding operation and maintenance task. In some embodiments, the tension value is used to characterize the urgency of the operation and maintenance task.

[0052] In some embodiments, evaluating the stress value of an operation and maintenance task based on the task tuple of the operation and maintenance task includes: obtaining the expected task time period of the operation and maintenance task from the task tuple of the operation and maintenance task; determining the expected completion time of the operation and maintenance task based on the expected task time period; and determining the stress value of the operation and maintenance task based on the expected completion time, wherein the stress value is negatively correlated with the expected completion time.

[0053] For example, for each operation and maintenance task, the server obtains the expected task time period of the operation and maintenance task from the task tuple of the operation and maintenance task; based on the expected task time period, the server determines the expected completion time of the operation and maintenance task. The server calculates the time difference between the expected completion time and the current time, and determines the tension value of the operation and maintenance task based on the reciprocal of the time difference.

[0054] In this embodiment, the tension value of the operation and maintenance task can be automatically assessed by the expected completion time of the operation and maintenance task, so as to reasonably assess the urgency of the operation and maintenance task.

[0055] In some embodiments, the tension value is used to characterize the urgency of the operation and maintenance task. Further, the tension value is used to comprehensively reflect the structural criticality and time urgency of the corresponding operation and maintenance task. For any operation and maintenance task, the task path in the task graph is determined, and the distance between the operation and maintenance task and the last operation and maintenance task in the task path is used as the value of the structural criticality of the operation and maintenance task. The latest completion time of the operation and maintenance task is related to the corresponding time urgency. Therefore, the operation and maintenance task can be calculated based on the following formula (1). Tension value:

[0056] (1)

[0057] in, It is an operation and maintenance task. The latest completion time, It is the current time. This is the maintenance task. The distance from the last maintenance task in this task path. It is an index term that controls sensitivity to time urgency (usually taken as 1 or 2). The structural influence weight (can be set to 0.3~0.7).

[0058] Step S206: Based on the tension value of each operation and maintenance task, determine the target capability template of each agent in the current scheduling cycle. The target capability template is used to indicate the operation and maintenance capabilities configured by the corresponding agent.

[0059] The target capability template indicates the operational capabilities of the corresponding agent in different capability dimensions configured within the current scheduling cycle. For example, if the target capability template supports repair and data collection, then the corresponding configured operational capabilities include repair and data collection.

[0060] For example, for each agent, the server obtains the set of capability templates corresponding to the agent. Based on the tension value of each operation and maintenance task and the set of capability templates, the server generates capability screening prompt text, calls a large language model to perform semantic understanding on the capability screening prompt text, and selects the target capability template of the agent from the set of capability templates.

[0061] In some embodiments, based on the tension value of each operation and maintenance task, the target capability template of each agent in the current scheduling cycle is determined, including: for each agent, obtaining the capability template set corresponding to the agent; for each agent, based on the template data of each capability template in the corresponding capability template set and the tension value of each operation and maintenance task, constructing a matching score prediction function for capability and task, and selecting the target capability template from the capability template set with the goal of maximizing the matching score prediction function.

[0062] The template data for each capability template illustrates the operational capabilities configured for that capability template, and this template data can be represented in the form of a binary vector.

[0063] For example, for each agent, a matching score prediction function is constructed based on the tension value of each operation and maintenance task and the template data in the agent's capability template set. The specific construction process can be referred to formula (2):

[0064] (2)

[0065] in, Capability templates in the set of capability templates for intelligent agents The initial matching score prediction function is as shown in formula (3):

[0066] (3)

[0067] Regarding formulas (2) and (3) above, For maintenance tasks The tension value; Representation of capability template Can it meet the operation and maintenance tasks? Capability requirements, when the capability requirement vector of operation and maintenance tasks Template capabilities The result of multiplying the template data item by item is 1 if all items are 1, otherwise it is 0; For distance attenuation factor, The rate of spatial decay reflects the increasing importance of tasks that are physically closer to the agent template. The set of tasks to be scheduled. Formula (3) simultaneously considers task structure tension, spatial distribution and capability matching, so that the template selection process and the scheduling environment are dynamically coupled. Representation of capability template With the set of capability templates Average capability vector The cosine similarity is used to measure the degree of redundancy. This is the penalty coefficient, such as 0.2; the second term. It is a sparse matching constraint on the capability requirements of high-pressure task types, where This represents the capability vector required for the task type with the highest current stress, i.e., the type capability requirement vector for high-pressure task types. The adjustment coefficient is 0.5; 1 represents the norm; this regularization term ensures that the capability template selection is biased towards the high-pressure capability direction of the task, while inhibiting the repeated selection of highly similar templates, thereby achieving a dynamic balance between capability diversity and task orientation.

[0068] Then, with the goal of maximizing the matching score prediction function, the target capability template is selected from the energy template set according to the following formula (4):

[0069] (4)

[0070] The argmax() function returns a template that maximizes the matching score prediction function.

[0071] In the above embodiments, by utilizing the tension value of each operation and maintenance task and combining the template data of each capability template in the capability template set, the target capability template matching the current scheduling cycle in the capability template set can be accurately evaluated.

[0072] Step S208: For each operation and maintenance task, based on the task tuple of the operation and maintenance task and the target capability template of each agent, determine the cost score of each agent for executing the operation and maintenance task. Based on the cost score of each agent, select the agent to execute the operation and maintenance task from multiple agents, and execute the operation and maintenance task according to the selected agent.

[0073] The cost score represents the scheduling cost of an agent performing maintenance tasks.

[0074] For example, for each operation and maintenance task, based on the task tuple of the operation and maintenance task and the template data of the target capability templates of each agent, a cost evaluation model is used to determine the cost score for each agent to execute the operation and maintenance task. For example, based on the cost scores of each agent, the server selects an agent from multiple agents to execute the operation and maintenance task, and executes the task according to the selected agent. The cost evaluation model is used to evaluate the scheduling cost of the agent executing the operation and maintenance task, and the cost evaluation model can be built based on a neural network model.

[0075] For example, for each operation and maintenance task, before determining the cost score, the method further includes: for each agent, comparing the template data of the agent's target capability template with the capability requirement vector of the operation and maintenance task to determine whether the agent has the capability to execute the operation and maintenance task. Based on the comparison results of each agent, agents capable of executing the operation and maintenance task are selected from multiple agents. For example, the template data is a binary vector, and the template data and the capability requirement vector have the same dimension, which is determined by comparing each element. This involves comparing the vector values ​​of the template data in the same dimension with the vector values ​​of the capability requirement vector for the operation and maintenance task. If both are greater than or equal to the vector values, the task is determined to be capable of being executed; otherwise, it is determined to be incapable of being executed. Then, based on the task tuple of the operation and maintenance task and the template data of the target capability templates of the selected agents, a cost evaluation model is used to determine the cost score for each selected agent to execute the operation and maintenance task. For example, based on the cost scores of each agent, the server selects the agent from the selected agents to execute the operation and maintenance task and executes the task according to the selected agent. It should be noted that the above agent selection process essentially compares the capability requirement vector of each operation and maintenance task with the template data of each agent to obtain a task-capability matching matrix. ,in Represents intelligent agents Target Capability Template Meet the operation and maintenance tasks capability requirements That is, comparing each element one by one. .

[0076] In some embodiments, based on the task tuple of the operation and maintenance task and the target capability template of each agent, the cost score for each agent to execute the operation and maintenance task is determined, including: for each agent, obtaining the task position of the operation and maintenance task from the task tuple of the operation and maintenance task, and determining the agent position where the agent is currently located; calculating the position difference between the task position and the agent position, and determining the cost score for the agent to execute the operation and maintenance task based on the position difference, wherein the position difference is positively correlated with the cost score.

[0077] For example, for each agent, the task position of the operation and maintenance task is obtained from the task tuple of the operation and maintenance task, and the agent's current position is determined; the position difference between the task position and the agent position is calculated, and based on the position difference, the position cost sub-score of the agent executing the operation and maintenance task is determined, and based on the position cost sub-score, the cost score is determined. The position difference is positively correlated with the position cost sub-score, and the position cost sub-score is positively correlated with the cost score.

[0078] In some embodiments, determining the cost score of an agent performing an operation and maintenance task based on location differences includes: determining the type tension value matched to the task type of the operation and maintenance task, whereby the type tension value reflects the urgency of the corresponding task type; determining the type cost sub-score based on the type tension value, and determining the corresponding location cost sub-score based on location differences; and fusing the type cost sub-score and the location cost sub-score to obtain the cost score of the agent performing the operation and maintenance task.

[0079] Among them, the type cost sub-score is negatively correlated with the cost score, while the location cost sub-score is positively correlated with the cost score. The type tension value can reflect the scheduling pressure of the corresponding task type during operation and maintenance.

[0080] Optionally, for each task type, the corresponding type tension value determination step includes: obtaining each operation and maintenance task under the task type; for each operation and maintenance task under the task type, determining the type sub-tension value corresponding to the operation and maintenance task based on the difference between the tension value of the operation and maintenance task and the total number of operation and maintenance tasks under the task type; and superimposing the type sub-tension values ​​of each operation and maintenance task under the task type to obtain the type tension value of the task type.

[0081] For example, for each task type, the corresponding type tension value can be determined based on formula (5):

[0082] (5)

[0083] in, This represents the total number of maintenance tasks belonging to task type k in the set of tasks to be scheduled. For maintenance tasks The tension value. This is a regularization weighting coefficient to prevent type frequency from misleading the tension aggregation value. Generally, it is set to a small value, such as 0.1~0.2, so that the operation and maintenance tasks with high dependency structure have higher priority in the tension calculation, and suppress the problem of single task type tasks "crowding out scheduling resources" due to their large number.

[0084] For example, the cost score is determined using the following formula (6):

[0085] (6)

[0086] in, Score the type cost sub-score; The Euclidean distance can be understood as a positional difference, reflecting the positional cost sub-score. This is the path conflict penalty value, representing the increase in path cost required to insert the maintenance task into the currently planned path of the agent, to avoid scheduling delays caused by path overlap. Therefore, the weights of the type cost sub-score, location cost sub-score, and path conflict penalty value are respectively (i.e., respectively) The cost score for the agent performing the maintenance task is obtained by weighting the type cost sub-score, the location cost sub-score, and the path conflict penalty value. The weights typically satisfy the following conditions: For example: Operations and maintenance tasks It is an emergency repair task. ), its tension value The task location is A certain intelligent agent The target capability template supports repair tasks, and the agent's current agent position. The distance between the two points is 0.86, and it is known that the agent's current path already has 3 tasks. Inserting this task will add approximately 1.5 kilometers to the path. .exist The coefficient is set to In this case, the maintenance task Assigned to intelligent agents The cost is: .

[0087] In this embodiment, by fusing the type cost sub-score and the location cost sub-score, the cost score of the agent executing each operation and maintenance task can be accurately evaluated, so as to facilitate the allocation of subsequent operation and maintenance tasks.

[0088] In the above embodiments, by utilizing the task location of the operation and maintenance task and the location difference between the agents, the cost score of the agent executing each operation and maintenance task can be automatically evaluated. Therefore, based on the cost score of each agent for the operation and maintenance task, a suitable agent can be accurately assigned to the operation and maintenance task.

[0089] In some embodiments, based on the cost scores of each agent, an agent is selected from multiple agents to perform the operation and maintenance task, including: determining the minimum cost score from multiple cost scores; selecting the agent corresponding to the minimum cost score from multiple agents, and the selected agent is used to perform the operation and maintenance task.

[0090] For example, for each operation and maintenance task, the server obtains the cost score of each agent for the operation and maintenance task, determines the minimum cost score, and selects the agent with the minimum cost score as the agent to execute the operation and maintenance task.

[0091] In this embodiment, the agent with the lowest cost score can be quickly identified by the cost score of each agent. Therefore, the agent with the lowest cost score is selected as the agent to perform the operation and maintenance task, thereby reducing the scheduling cost.

[0092] In the above-described operation and maintenance task processing method, a set of tasks to be scheduled within the current scheduling cycle is obtained. This set includes multiple operation and maintenance tasks. For each operation and maintenance task, the tension value of the task is evaluated based on its task tuple. The task tuple includes at least the task type, expected task time period, capability requirement vector, and task location. The tension value characterizes the urgency of the operation and maintenance task. Thus, the urgency of the operation and maintenance task can be reflected based on the tension value. Then, based on the tension value of each operation and maintenance task, the target capability template for each agent within the current scheduling cycle is adaptively determined. The target capability template indicates the operation and maintenance capabilities configured by the corresponding agent. Therefore, for each operation and maintenance task, based on the task tuple and the target capability template of each agent, the cost score for each agent to execute the operation and maintenance task is determined. Finally, based on the cost scores of each agent, the agent to execute the operation and maintenance task can be automatically and accurately selected from multiple agents from the cost dimension, and the operation and maintenance task is executed according to the selected agent. In this way, by considering the urgency of the operation and maintenance tasks and the operation and maintenance capabilities of each agent, not only are the operation and maintenance capabilities that agents should be configured during operation and maintenance, but also the operation and maintenance tasks are accurately assigned to agents. This allows each agent to execute the appropriate operation and maintenance tasks with the appropriate operation and maintenance capabilities. The entire process is completed accurately and automatically without the need for manual arrangement by personnel, thus improving the efficiency of operation and maintenance task processing.

[0093] In some embodiments, after determining the agent corresponding to each maintenance task in the set of tasks to be scheduled, the method further includes: the server counting the maintenance tasks to be executed by each agent; for each agent, the server determining a path set for the agent based on the maintenance tasks to be executed by the agent using the TSP heuristic algorithm, the path set including the execution order of the maintenance tasks of the corresponding agent. Combining the path set, a control instruction sequence is constructed for the corresponding agent. Specifically, for each agent, the server constructs a corresponding control instruction for each maintenance task to be executed by the agent, the control instruction including six parts of information: ① Task number ②Task location ③Task type number ④ Capability requirement vector ⑤ Task execution parameters This includes task duration, accuracy requirements, tool selection, etc.; ⑥ Structured execution sequence tags This is used to optimize the local execution order of operation and maintenance tasks. Among them, structured execution sequence tags... You can refer to formula (7) to determine:

[0094] (7)

[0095] in, Indicates the task in the path set Sequential index in This indicates the reverse topology depth of the operation and maintenance task in the task graph. It is an adjustable coefficient, usually set to 0.6~0.8, used to balance the weighted proportion of the path order of operation and maintenance tasks and the logical importance in the graph structure.

[0096] Considering that in actual execution, some maintenance tasks may require the agent to switch the current capability template before execution, for example, switching from a target capability template that allows "inspection" to another capability template that runs in "mode," capability activation judgment logic is also set in the control instructions. If the capability requirement vector of the maintenance task to be executed now includes a new target capability template... For uncovered dimensions, a capability activation command is automatically inserted before it, and the corresponding capability preparation delay is calculated. The logical expression for this judgment is as follows: (8)

[0097] (8)

[0098] in, This indicates a non-zero logical condition. It is a bitwise AND operation. This indicates the inactive capability dimensions in the target capability template. If... Then, an activation command for the capability module (such as activating the visual perception unit or switching the manipulator tool head) is inserted, and a preparation delay is inserted into the scheduling clock, i.e., a time delay is inserted. .

[0099] Each control command carries a scheduling timestamp and a task ID. After execution, the agent will proactively return a completion status to the scheduling center via the feedback link. If an operation and maintenance task fails or times out during execution, the scheduling center will trigger the task recovery unit to reassign the task based on the failure flag and mark the status of the operation and maintenance task in the task graph.

[0100] In one specific embodiment, the specific steps are as follows:

[0101] First, the server obtains the set of tasks to be scheduled within the current scheduling period, which includes multiple operation and maintenance tasks.

[0102] Secondly, for each operation and maintenance task, the server obtains the expected task time period from the task tuple of the operation and maintenance task; based on the expected task time period, it determines the expected completion time of the operation and maintenance task; based on the expected completion time, it determines the tension value of the operation and maintenance task, the tension value being negatively correlated with the expected completion time. The task tuple includes at least the task type, expected task time period, capacity requirement vector, and task location of the operation and maintenance task, and the tension value is used to characterize the urgency of the operation and maintenance task.

[0103] Next, for each agent, the server obtains the set of capability templates corresponding to the agent; for each agent, the server constructs a matching score prediction function for capabilities and tasks based on the template data of each capability template in the corresponding capability template set and the tension value of each operation and maintenance task, and selects the target capability template from the capability template set with the goal of maximizing the matching score prediction function.

[0104] Then, for each operation and maintenance task and each agent, the server obtains the task position of the operation and maintenance task from the task tuple of the operation and maintenance task, and determines the current agent position of the agent; the server calculates the position difference between the task position and the agent position; the server determines the type tension value matching the task type of the operation and maintenance task, the type tension value reflecting the urgency of the corresponding task type; based on the type tension value, the server determines the type cost sub-score, and based on the position difference, the server determines the corresponding position cost sub-score; the server merges the type cost sub-score and the position cost sub-score to obtain the cost score for the agent to execute the operation and maintenance task.

[0105] Finally, for the operation and maintenance task, the server selects the agent with the minimum cost score from multiple agents, and the selected agent is used to execute the operation and maintenance task.

[0106] In the above embodiments, a set of tasks to be scheduled within the current scheduling period is obtained, which includes multiple operation and maintenance tasks. For each operation and maintenance task, the tension value of the task is evaluated based on its task tuple. The task tuple includes at least the task type, expected task time period, capability requirement vector, and task location. The tension value is used to characterize the urgency of the operation and maintenance task. Thus, the urgency of the operation and maintenance task can be reflected based on the tension value. Then, based on the tension value of each operation and maintenance task, the target capability template of each agent within the current scheduling period is adaptively determined. The target capability template is used to indicate the operation and maintenance capabilities configured by the corresponding agent. In view of this, for each operation and maintenance task, based on the task tuple and the target capability template of each agent, the cost score for each agent to execute the operation and maintenance task is determined. Finally, based on the cost score of each agent, the agent to be used to execute the operation and maintenance task can be automatically and accurately selected from multiple agents from the cost dimension, and the operation and maintenance task is executed according to the selected agent. In this way, by considering the urgency of the operation and maintenance tasks and the operation and maintenance capabilities of each agent, not only are the operation and maintenance capabilities that agents should be configured during operation and maintenance, but also the operation and maintenance tasks are accurately assigned to agents. This allows each agent to execute the appropriate operation and maintenance tasks with the appropriate operation and maintenance capabilities. The entire process is completed accurately and automatically without the need for manual arrangement by personnel, thus improving the efficiency of operation and maintenance task processing.

[0107] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0108] Based on the same inventive concept, this application also provides an operation and maintenance task processing device for implementing the operation and maintenance task processing method described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more operation and maintenance task processing device embodiments provided below can be found in the limitations of the operation and maintenance task processing method above, and will not be repeated here.

[0109] In one exemplary embodiment, such as Figure 3 As shown, an operation and maintenance task processing device 300 is provided, including: a task set acquisition module 302, a task tension determination module 304, a capability template determination module 306, and an operation and maintenance task execution module 308, wherein:

[0110] The task set acquisition module 302 is used to acquire the set of tasks to be scheduled within the current scheduling period. The set of tasks to be scheduled includes multiple operation and maintenance tasks.

[0111] The task tension determination module 304 is used to evaluate the tension value of each operation and maintenance task based on the task tuple of the operation and maintenance task. The task tuple includes at least the task type, expected task time period, capacity requirement vector, and task location of the operation and maintenance task. The tension value is used to characterize the urgency of the operation and maintenance task.

[0112] The capability template determination module 306 is used to determine the target capability template of each intelligent agent in the current scheduling cycle based on the tension value of each operation and maintenance task. The target capability template is used to indicate the operation and maintenance capabilities configured by the corresponding intelligent agent.

[0113] The operation and maintenance task execution module 308 is used to determine the cost score of each intelligent agent for each operation and maintenance task based on the task tuple of the operation and maintenance task and the target capability template of each intelligent agent. Based on the cost score of each intelligent agent, the module selects the intelligent agent to execute the operation and maintenance task from multiple intelligent agents and executes the operation and maintenance task according to the selected intelligent agent.

[0114] In one embodiment, the task tension determination module 304 is used to obtain the expected task time period of the operation and maintenance task from the task tuple of the operation and maintenance task; determine the expected completion time of the operation and maintenance task based on the expected task time period; and determine the tension value of the operation and maintenance task based on the expected completion time, wherein the tension value is negatively correlated with the expected completion time.

[0115] In one embodiment, the capability template determination module 306 is used to obtain a set of capability templates corresponding to each agent; for each agent, based on the template data of each capability template in the corresponding capability template set and the tension value of each operation and maintenance task, construct a matching score prediction function for capability and task, and select the target capability template from the capability template set with the goal of maximizing the matching score prediction function.

[0116] In one embodiment, the operation and maintenance task execution module 308 is used to obtain the task position of the operation and maintenance task from the task tuple of the operation and maintenance task for each agent, and determine the current agent position of the agent; calculate the position difference between the task position and the agent position, and determine the cost score of the agent executing the operation and maintenance task based on the position difference, wherein the position difference is positively correlated with the cost score.

[0117] In one embodiment, the operation and maintenance task execution module 308 is used to determine the type tension value matched by the task type of the operation and maintenance task, the type tension value reflecting the urgency of the corresponding task type; based on the type tension value, determine the type cost sub-score, and based on the location difference, determine the corresponding location cost sub-score; and fuse the type cost sub-score and the location cost sub-score to obtain the cost score of the agent executing the operation and maintenance task.

[0118] In one embodiment, the operation and maintenance task execution module 308 is used to determine the minimum cost score from multiple cost scores; select the agent corresponding to the minimum cost score from multiple agents, and use the selected agent to execute the operation and maintenance task.

[0119] Each module in the aforementioned operation and maintenance task processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0120] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 4 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and databases. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media to run. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for handling operational and maintenance tasks.

[0121] Those skilled in the art will understand that Figure 4The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0122] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: obtaining a set of tasks to be scheduled within the current scheduling period, the set of tasks to be scheduled including multiple maintenance tasks; for each maintenance task, evaluating the tension value of the maintenance task based on the task tuple of the maintenance task, the task tuple including at least the task type, expected task time period, capability requirement vector, and task location of the maintenance task, the tension value being used to characterize the urgency of the maintenance task; determining the target capability template of each agent within the current scheduling period based on the tension value of each maintenance task, the target capability template being used to indicate the maintenance capabilities configured by the corresponding agent; for each maintenance task, determining the cost score of each agent executing the maintenance task based on the task tuple of the maintenance task and the target capability template of each agent; selecting an agent from multiple agents to execute the maintenance task based on the cost score of each agent, and executing the maintenance task according to the selected agent.

[0123] In one embodiment, when the processor executes the computer program, it further performs the following steps: obtaining the expected task time period of the operation and maintenance task from the task tuple of the operation and maintenance task; determining the expected completion time of the operation and maintenance task based on the expected task time period; and determining the tension value of the operation and maintenance task based on the expected completion time, wherein the tension value is negatively correlated with the expected completion time.

[0124] In one embodiment, when the processor executes the computer program, it further performs the following steps: for each agent, obtain the set of capability templates corresponding to the agent; for each agent, based on the template data of each capability template in the corresponding capability template set and the tension value of each operation and maintenance task, construct a matching score prediction function for capability and task, and select the target capability template from the capability template set with the goal of maximizing the matching score prediction function.

[0125] In one embodiment, when the processor executes the computer program, it further performs the following steps: for each agent, obtains the task position of the operation and maintenance task from the task tuple of the operation and maintenance task, and determines the agent position where the agent is currently located; calculates the position difference between the task position and the agent position, and determines the cost score of the agent executing the operation and maintenance task based on the position difference, wherein the position difference is positively correlated with the cost score.

[0126] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the type tension value that matches the task type of the maintenance task, the type tension value reflecting the urgency of the corresponding task type; determining the type cost sub-score based on the type tension value, and determining the corresponding location cost sub-score based on the location difference; fusing the type cost sub-score and the location cost sub-score to obtain the cost score for the agent to perform the maintenance task.

[0127] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the minimum cost score from multiple cost scores; selecting the agent corresponding to the minimum cost score from multiple agents, and using the selected agent to perform the operation and maintenance task.

[0128] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When executed by a processor, the computer program performs the following steps: obtaining a set of tasks to be scheduled within the current scheduling period, the set of tasks to be scheduled including multiple maintenance tasks; for each maintenance task, evaluating the tension value of the maintenance task based on the task tuple of the maintenance task, the task tuple including at least the task type, expected task time period, capability requirement vector, and task location of the maintenance task, the tension value being used to characterize the urgency of the maintenance task; determining the target capability template of each agent within the current scheduling period based on the tension value of each maintenance task, the target capability template being used to indicate the maintenance capabilities configured by the corresponding agent; for each maintenance task, determining the cost score of each agent executing the maintenance task based on the task tuple of the maintenance task and the target capability template of each agent; selecting an agent from multiple agents to execute the maintenance task based on the cost score of each agent, and executing the maintenance task according to the selected agent.

[0129] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining the expected task time period of the operation and maintenance task from the task tuple of the operation and maintenance task; determining the expected completion time of the operation and maintenance task based on the expected task time period; and determining the tension value of the operation and maintenance task based on the expected completion time, wherein the tension value is negatively correlated with the expected completion time.

[0130] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: for each agent, obtain the set of capability templates corresponding to the agent; for each agent, based on the template data of each capability template in the corresponding capability template set and the tension value of each operation and maintenance task, construct a matching score prediction function for capability and task, and select the target capability template from the capability template set with the goal of maximizing the matching score prediction function.

[0131] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: for each agent, obtain the task position of the operation and maintenance task from the task tuple of the operation and maintenance task, and determine the agent position where the agent is currently located; calculate the position difference between the task position and the agent position, and determine the cost score of the agent performing the operation and maintenance task based on the position difference, wherein the position difference is positively correlated with the cost score.

[0132] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the type tension value that matches the task type of the maintenance task, the type tension value reflecting the urgency of the corresponding task type; determining the type cost sub-score based on the type tension value, and determining the corresponding location cost sub-score based on the location difference; fusing the type cost sub-score and the location cost sub-score to obtain the cost score for the agent to perform the maintenance task.

[0133] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the minimum cost score from multiple cost scores; selecting the agent corresponding to the minimum cost score from multiple agents, and using the selected agent to perform the operation and maintenance task.

[0134] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps: obtaining a set of tasks to be scheduled within the current scheduling period, the set of tasks to be scheduled including multiple maintenance tasks; for each maintenance task, evaluating the tension value of the maintenance task based on the task tuple of the maintenance task, the task tuple including at least the task type, expected task time period, capability requirement vector, and task location of the maintenance task, the tension value being used to characterize the urgency of the maintenance task; determining the target capability template of each agent within the current scheduling period based on the tension value of each maintenance task, the target capability template being used to indicate the maintenance capabilities configured by the corresponding agent; for each maintenance task, determining the cost score for each agent to execute the maintenance task based on the task tuple of the maintenance task and the target capability template of each agent, selecting an agent from multiple agents to execute the maintenance task based on the cost score of each agent, and executing the maintenance task according to the selected agent.

[0135] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining the expected task time period of the operation and maintenance task from the task tuple of the operation and maintenance task; determining the expected completion time of the operation and maintenance task based on the expected task time period; and determining the tension value of the operation and maintenance task based on the expected completion time, wherein the tension value is negatively correlated with the expected completion time.

[0136] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: for each agent, obtain the set of capability templates corresponding to the agent; for each agent, based on the template data of each capability template in the corresponding capability template set and the tension value of each operation and maintenance task, construct a matching score prediction function for capability and task, and select the target capability template from the capability template set with the goal of maximizing the matching score prediction function.

[0137] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: for each agent, obtain the task position of the operation and maintenance task from the task tuple of the operation and maintenance task, and determine the agent position where the agent is currently located; calculate the position difference between the task position and the agent position, and determine the cost score of the agent performing the operation and maintenance task based on the position difference, wherein the position difference is positively correlated with the cost score.

[0138] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the type tension value that matches the task type of the maintenance task, the type tension value reflecting the urgency of the corresponding task type; determining the type cost sub-score based on the type tension value, and determining the corresponding location cost sub-score based on the location difference; fusing the type cost sub-score and the location cost sub-score to obtain the cost score for the agent to perform the maintenance task.

[0139] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the minimum cost score from multiple cost scores; selecting the agent corresponding to the minimum cost score from multiple agents, and using the selected agent to perform the operation and maintenance task.

[0140] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0141] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0142] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0143] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for handling operation and maintenance tasks, characterized in that, The method includes: Obtain the set of tasks to be scheduled within the current scheduling period, wherein the set of tasks to be scheduled includes multiple operation and maintenance tasks; For each operation and maintenance task, the tension value of the operation and maintenance task is evaluated based on the task tuple of the operation and maintenance task. The task tuple includes at least the task type, expected task time period, capability requirement vector, and task location of the operation and maintenance task. The tension value is used to characterize the urgency of the operation and maintenance task. For any operation and maintenance task, the task path of the operation and maintenance task in the task graph is determined. The distance of the operation and maintenance task from the last operation and maintenance task in the task path is used as the structural criticality value of the operation and maintenance task. The latest completion time of the operation and maintenance task is related to the corresponding time urgency. Based on formula (1), the operation and maintenance task is calculated. Tension value: （1）； in, It is an operation and maintenance task. The latest completion time, It is the current time. The aforementioned operation and maintenance task The distance from the last maintenance task in the task path. It is an index term for controlling sensitivity to time urgency. The structure affects the weight; For each agent, obtain the capability template set corresponding to the agent; for each agent, based on the template data of each capability template in the corresponding capability template set and the tension value of each operation and maintenance task, construct a matching score prediction function for capability and task, with the goal of maximizing the matching score prediction function, filter out the target capability template from the capability template set, the target capability template is used to indicate the operation and maintenance capabilities configured by the corresponding agent; For each agent, the task position of the operation and maintenance task is obtained from the task tuple of the operation and maintenance task, and the agent's current position is determined; the position difference between the task position and the agent's position is calculated to determine the type tension value matching the task type of the operation and maintenance task, where the type tension value reflects the urgency of the corresponding task type; based on the type tension value, a type cost sub-score is determined, and based on the position difference, a corresponding position cost sub-score is determined; the type cost sub-score and the position cost sub-score are fused to obtain the cost score for the agent to execute the operation and maintenance task, where the position difference is positively correlated with the cost score; Based on the cost scores of each agent, an agent is selected from multiple agents to perform the operation and maintenance task, and the operation and maintenance task is performed according to the selected agent.

2. The method according to claim 1, characterized in that, The process of selecting the agent to perform the operation and maintenance task from multiple agents based on the cost scores of each agent includes: Determine the minimum cost score from multiple cost scores; The agent with the lowest cost score is selected from multiple agents, and the selected agent is used to execute the operation and maintenance task.

3. A maintenance task processing device, characterized in that, The device includes: The task set acquisition module is used to acquire the set of tasks to be scheduled within the current scheduling period, and the set of tasks to be scheduled includes multiple operation and maintenance tasks. The task tension determination module is used to evaluate the tension value of each operation and maintenance task based on the task tuple of the operation and maintenance task. The task tuple includes at least the task type, expected task time period, capability requirement vector, and task location of the operation and maintenance task. The tension value is used to characterize the urgency of the operation and maintenance task. For any operation and maintenance task, the task path of the operation and maintenance task in the task graph is determined. The distance of the operation and maintenance task from the last operation and maintenance task in the task path is used as the structural criticality value of the operation and maintenance task. The latest completion time of the operation and maintenance task is related to the corresponding time urgency. Based on formula (1), the operation and maintenance task is calculated. Tension value: （1）； in, It is an operation and maintenance task. The latest completion time, It is the current time. The aforementioned operation and maintenance task The distance from the last maintenance task in the task path. It is an index term for controlling sensitivity to time urgency. The structure affects the weight; The capability template determination module is used to obtain the capability template set corresponding to each intelligent agent; for each intelligent agent, based on the template data of each capability template in the corresponding capability template set and the tension value of each operation and maintenance task, construct a matching score prediction function for capability and task, and with the goal of maximizing the matching score prediction function, filter out the target capability template from the capability template set, and the target capability template is used to indicate the operation and maintenance capabilities configured by the corresponding intelligent agent; The operation and maintenance task execution module is used to, for each agent, obtain the task position of the operation and maintenance task from the task tuple of the operation and maintenance task, and determine the agent's current position; calculate the position difference between the task position and the agent's position, determine the type tension value matching the task type of the operation and maintenance task, the type tension value reflecting the urgency of the corresponding task type; determine the type cost sub-score based on the type tension value, and determine the corresponding position cost sub-score based on the position difference; fuse the type cost sub-score and the position cost sub-score to obtain the cost score for the agent to execute the operation and maintenance task, the position difference being positively correlated with the cost score; and select an agent from multiple agents to execute the operation and maintenance task based on the cost scores of each agent, and execute the operation and maintenance task according to the selected agent.

4. The apparatus according to claim 3, characterized in that, The operation and maintenance task execution module is used to determine the minimum cost score from multiple cost scores; select the agent corresponding to the minimum cost score from multiple agents, and the selected agent is used to execute the operation and maintenance task.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 2.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 2.

7. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 2.

Images