Intelligent inspection method and system, electronic equipment, storage medium and program product

Abstract

The invention discloses an intelligent inspection method and system, electronic equipment, a storage medium and a program product, and relates to the technical field of intelligent inspection, and the method comprises the steps: enabling a central agent to split an inspection task into at least one subtask, and distributing the subtask to an associated execution agent for execution, the execution agent returns target information obtained in the subtask execution process, the central agent constructs a directed topological graph according to the execution agent associated with the inspection task, updates the directed topological graph according to the target information returned by the execution agent, determines a node with in-degree being zero in the directed topological graph as a fault root cause node, and sends the fault root cause node to the central agent; the whole inspection process does not need manual participation, intelligent inspection of the production workshop is achieved through cooperative work of multiple agents, faults occurring in the production process can be found in time, the inspection efficiency and accuracy are greatly improved, the probability of missed inspection is reduced, and therefore the inspection efficiency is improved. The technical problems of low efficiency, poor accuracy and missing inspection in manual inspection of the production workshop can be solved.

Description

Technical Field

[0001] The present application relates to the field of intelligent inspection technology in intelligent manufacturing, and in particular to an intelligent inspection method, system, electronic equipment, storage medium and program product. Background Art

[0002] Intelligent manufacturing is the deep integration of advanced manufacturing technology, new generation information technology and artificial intelligence technology. Intelligent manufacturing equipment refers to manufacturing equipment with perception, analysis, reasoning, decision-making and control functions. It comprehensively uses control system design, sensing technology, precision manufacturing technology, intelligent identification technology and other technologies. Compared with traditional production models, intelligent manufacturing has the advantages of high production rate, high product quality and high production flexibility.

[0003] Inspection is a key part of intelligent manufacturing. Currently, manual inspection is usually used to check the equipment in the production workshop. However, faced with massive and complex data in the production workshop, the manual inspection method has problems such as low efficiency, poor accuracy, and missed inspections. Summary of the invention

[0004] The present application provides an intelligent inspection method, system, electronic device, storage medium and program product to at least solve the problems of low efficiency, poor accuracy and missed inspections in manual inspections of production workshops in the related art.

[0005] This application provides an intelligent inspection method, including: Decompose the current inspection task into at least one subtask, and determine the device to be monitored associated with the at least one subtask; According to the execution agent corresponding to the device to be monitored, a directed topological graph is constructed, wherein one device to be monitored uniquely corresponds to one execution agent; Sending the at least one subtask to the corresponding execution agent, so that the execution agent executes the assigned subtask and returns the target information obtained during the execution of the subtask; Updating the directed topological graph according to the target information; When the in-degree of at least one node in the updated directed topological graph is zero, the at least one node is determined to be the fault root cause node corresponding to the current inspection task.

[0006] The present application also provides an intelligent inspection system, comprising: a central intelligent agent and at least one device, wherein one device uniquely corresponds to one sub-intelligent agent; The central agent is configured to: decompose the current inspection task into at least one subtask, and determine the equipment to be monitored associated with the at least one subtask; construct a directed topological graph according to the execution agent corresponding to the equipment to be monitored; send the at least one subtask to the corresponding execution agent, and the execution agent executes the assigned subtask and returns the target information obtained during the execution of the subtask; update the directed topological graph according to the target information; and determine the at least one node as the fault root cause node corresponding to the current inspection task when the in-degree of at least one node in the updated directed topological graph is zero; The sub-agent is configured to: execute the assigned sub-task and return the target information obtained during the execution of the sub-task to the central agent.

[0007] The present application also provides an intelligent inspection device, comprising: A task planning module, used to decompose the current inspection task into at least one subtask and determine the equipment to be monitored associated with the at least one subtask; An intelligent networking module, used to construct a directed topology graph according to the execution agent corresponding to the device to be monitored, wherein one device to be monitored uniquely corresponds to one execution agent; A task issuing module, used for sending the at least one subtask to the corresponding execution agent, so that the execution agent executes the assigned subtask and returns the target information obtained during the execution of the subtask; An updating module, used for updating the directed topology graph according to the target information; The determination module is used to determine that at least one node in the updated directed topology graph is a fault root cause node corresponding to the current inspection task when the in-degree of the at least one node is zero.

[0008] The present application also provides an electronic device, comprising: a memory for storing a computer program; and a processor for implementing the steps of any of the above-mentioned intelligent inspection methods when executing the computer program.

[0009] The present application also provides a computer-readable storage medium, in which a computer program is stored, wherein when the computer program is executed by a processor, the steps of any of the above-mentioned intelligent inspection methods are implemented.

[0010] The present application also provides a computer program product, including a computer program, which implements the steps of any of the above-mentioned intelligent inspection methods when executed by a processor.

[0011] Through this application, the central intelligent agent splits the inspection task into at least one sub-task and assigns it to the associated execution intelligent agent for execution. The execution intelligent agent returns the target information obtained during the execution of the sub-task, and the central intelligent agent constructs a directed topological graph based on the execution intelligent agent associated with the inspection task, and updates the directed topological graph based on the target information returned by the execution intelligent agent. The nodes with zero in-degree in the directed topological graph are determined as the root cause nodes of the fault. The entire inspection process does not require human participation. Through the collaborative work of multiple intelligent agents, intelligent inspection of the production workshop is realized, and faults occurring in the production process can be discovered in time, which greatly improves the inspection efficiency and accuracy and reduces the probability of missed detection. Therefore, the technical problems of low efficiency, poor accuracy and missed detection in manual inspection of production workshops can be solved, and the technical effects of reducing labor costs, improving inspection efficiency and quality, and improving the level of intelligent manufacturing can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0013] Figure 1 A schematic diagram of the application environment architecture of intelligent inspection according to an exemplary embodiment of the present application is shown; Figure 2 A flowchart of an intelligent inspection method provided in an embodiment of the present application; Figure 3 A schematic diagram of a directed topological graph of an exemplary embodiment of the present application; Figure 4 A flowchart of another intelligent inspection method provided in an embodiment of the present application; Figure 5 A schematic diagram of importance factors of directed edges of an exemplary embodiment of the present application; Figure 6 A flowchart of another intelligent inspection method provided in an embodiment of the present application; Figure 7 A schematic diagram of a prediction process of a cycle of an exemplary embodiment of the present application; Figure 8 A flowchart of another intelligent inspection method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0014] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0015] It should be noted that, in the description of this application, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. The terms "first", "second", etc. in this application are used to distinguish similar objects, and are not used to describe a specific order or sequence.

[0016] Intelligent manufacturing equipment refers to manufacturing equipment with perception, analysis, reasoning, decision-making and control functions. It has the characteristics of rapid technology updates, capital intensiveness, and multi-field product applications. It is a manufacturing industry with strong technical comprehensiveness, integrating advanced manufacturing, information technology, artificial intelligence and other fields. It comprehensively uses control system design, sensing technology, precision manufacturing technology, intelligent identification technology and other technologies. Compared with traditional production models, intelligent manufacturing has the advantages of high production rate, high product quality and high production flexibility.

[0017] Inspection is a key part of smart manufacturing. Faced with massive and complex data in factories, traditional manual inspection methods are time-consuming and labor-intensive, and cannot achieve a complete smart inspection mode, namely image recognition and intelligent detection, resulting in high labor costs, low efficiency, and susceptibility to human factors.

[0018] Nowadays, with the increasing scale of automated and intelligent production factories, the complexity of production lines is increasing, which increases the difficulty and cost of manual inspections. Problems such as low efficiency, poor accuracy and missed inspections have gradually become key factors affecting the intelligent transformation of factories. Therefore, there is an urgent need for an efficient, automatic and intelligent inspection method to help improve the intelligence level of production workshop inspections, liberate manpower, reduce false alarm rates, and meet the needs of future intelligent factories. Therefore, how to improve the intelligence level of production and manufacturing inspections has become a research hotspot in the current field of intelligent manufacturing.

[0019] At present, in the relevant technologies, intelligent inspection mainly uses modern information technology, such as the Internet of Things, big data and intelligent algorithms, to conduct automated and intelligent inspection and monitoring of equipment, facilities or specific areas to improve inspection efficiency and quality. However, the existing intelligent inspection methods are mainly implemented by combining manual and intelligent algorithms. Although the inspection efficiency has been improved to a certain extent with the help of intelligent algorithms, the inspection process still relies heavily on manual operation. With the increase in the number and types of inspection objects and the requirement for real-time performance, the labor cost has increased, and there are still serious problems with inspection efficiency and quality.

[0020] In response to the above problems, the present application provides an intelligent inspection solution. On the one hand, this solution makes full use of the ability of the underlying large model in the intelligent agent to understand the environment, analyzes the input data of different modes, and obtains the status indicator information of the current equipment. The use of large models to analyze and process information helps to improve inspection efficiency; on the other hand, based on the coordinated work of multiple agents, automatic and intelligent analysis and processing of the environment, equipment and other data of the production workshop is realized. The central intelligent agent constructs a directed topological graph of multiple agents, and dynamically updates the information of nodes and edges in the directed topological graph according to the data reported by multiple agents, further analyzes the fault transmission path, determines the root cause node of the fault, and thus finds the faulty equipment, realizing intelligent inspection, reducing labor costs, and improving the level of intelligent inspection. It solves the current problems of low efficiency and high false detection rate in manual inspection, and can serve the field of intelligent manufacturing well and meet the inspection needs in extreme environments.

[0021] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0022] In conjunction with the specific application environment architecture or specific hardware architecture on which the execution of the intelligent inspection method depends, the specific application environment architecture or specific hardware architecture is described here.

[0023] Figure 1 A schematic diagram of the application environment architecture of the intelligent inspection of an exemplary embodiment of the present application is shown. Figure 1 As shown, the application environment architecture includes a central intelligent agent and multiple sub-intelligent agents, where one sub-intelligent agent uniquely corresponds to one device. The sub-intelligent agent can be integrated into the corresponding device or exist as an independent intelligent device. The central intelligent agent is responsible for disassembling, planning, and allocating inspection tasks according to certain template definitions. The central intelligent agent can be an intelligent inspection robot or a central control device. This application does not limit the existence of the central intelligent agent and the sub-intelligent agent. Figure 1 As shown, each sub-agent can interact with the central agent, and although Figure 1Although not shown in the figure, sub-agents can also interact with each other through a unified and standardized interface. Each device is equipped with relevant sensors to obtain the device's operating indicator data and internal log data. It should be noted that Figure 1 The present application is only explained by taking the example that the sub-agent is integrated in the device and the central agent is connected to 5 devices, and it cannot be used as a limitation of the present application.

[0024] An agent, or an intelligent entity, is an agent that can perceive the environment and take actions to achieve specific goals. It has strong understanding and processing capabilities, and is autonomous, adaptable, and interactive. The agent perceives changes in the environment (such as through sensors or data input), makes judgments and decisions based on the knowledge and algorithms it has learned, and then performs actions to affect the environment or achieve predetermined goals. It should be noted that in this embodiment, both the central agent and the sub-agent are agents. By utilizing the powerful information understanding and processing advantages of the agent, it is possible to realize intelligent inspections of the production workshop, promptly discover faults in the production process, greatly reduce labor costs, and improve inspection efficiency and quality.

[0025] The embodiment of the present application provides an intelligent inspection method, and the method is described in detail in conjunction with the execution process of the intelligent inspection method.

[0026] Figure 2 A flowchart of an intelligent inspection method provided in an embodiment of the present application is provided. The method can be executed by a central intelligent agent in an embodiment of the present application and can be integrated in an electronic device.

[0027] like Figure 2 As shown, the intelligent inspection method comprises the following steps: Step 101: decompose the current inspection task into at least one subtask, and determine the device to be monitored associated with at least one subtask.

[0028] The current inspection task may be an inspection task currently received, or a scheduled inspection task that has reached its execution time.

[0029] In this embodiment, the central agent can decompose the current inspection task into at least one subtask and determine the device to be monitored associated with at least one subtask. It can be understood that the device to be monitored is at least one device among all devices in the current inspection area, and is the device associated with the decomposed subtask among all devices. Figure 1 As shown in the example, the device to be monitored is Figure 1 At least one device among all devices in .

[0030] As an example, the central intelligent agent can use the powerful understanding and processing capabilities of its own integrated task decomposition model to decompose the current inspection task according to the task description of the current inspection task to obtain at least one subtask.

[0031] Step 102: construct a directed topology graph according to the execution agents corresponding to the devices to be monitored, wherein one device to be monitored uniquely corresponds to one execution agent.

[0032] In this embodiment, Figure 1 As shown, one device uniquely corresponds to one sub-agent, so one device to be monitored uniquely corresponds to one sub-agent. Since the sub-agent corresponding to the device to be monitored is assigned a subtask and executed, in this embodiment, the sub-agent corresponding to the device to be monitored is called an execution agent. Then, the central agent can construct a directed topology graph based on the determined execution agent to realize intelligent networking.

[0033] The directed topology graph is a fully connected directed graph, denoted as G(V, E), where V is the node set, that is, the set of all executing agents, and each node represents an executing agent; E is the directed edge set, and the directed edge<a1,a2> and<a2,a1> Represents two different directed edges corresponding to two identical nodes (a1 and a2).

[0034] For example, suppose the subtask set after decomposition is recorded as: {t1, t2, …, t k}, a subtask is associated with a device to be monitored, so the set of executing agents on the device to be monitored corresponding to each subtask is recorded as: {a1, a2,…, a k Taking k=5 as an example, the directed topology graph generated after networking the execution agents corresponding to all the monitored devices is as follows: Figure 3 shown.

[0035] Step 103: Send at least one subtask to a corresponding execution agent, and the execution agent executes the assigned subtask and returns target information obtained during the execution of the subtask.

[0036] In this embodiment, after the central agent determines the execution agent associated with each subtask, at least one subtask can be sent to the corresponding execution agent. After receiving the subtask assigned by the central agent, the execution agent executes the subtask, obtains target information during the execution of the subtask, and returns the target information to the central agent.

[0037] The target information may be different types of data. The central intelligent agent processes the target information differently according to the type of target information returned. The specific explanation will be described in detail in subsequent embodiments and will not be repeated here.

[0038] Step 104: Update the directed topology graph according to the target information.

[0039] In this embodiment, after the central agent obtains the target information returned by the execution agent, it can find all the corresponding source nodes for each endpoint in the directed topological graph, and determine the importance factor (IF) of each of these source nodes to the endpoint according to the target information and update it, thereby realizing the update of the directed topological graph.

[0040] Step 105: When the in-degree of at least one node in the updated directed topology graph is zero, determine that the at least one node is the fault root cause node corresponding to the current inspection task.

[0041] In this embodiment, after all nodes in the directed topology graph are traversed, the update of the directed topology graph is completed. At this time, the central agent can detect whether there is a node with an in-degree of zero in the directed topology graph, where the in-degree refers to the sum of the number of times a node in the directed topology graph is the end point of an edge. In the directed topology graph, each edge has a source node and an end point. For any node, the in-degree refers to the number of edges with the point as the end point. If there is at least one node in the directed topology graph with an in-degree of zero, all nodes with an in-degree of zero are determined as the root cause nodes corresponding to the current inspection task, and the device corresponding to the root cause node is the device detected to have a fault, so that the central agent can automatically generate a solution based on the relevant information of the device to be monitored corresponding to the root cause node.

[0042] It can be understood that in this embodiment, the process of updating the directed topology map is repeatedly executed, the execution agent can periodically collect data and return target information, and the central agent continuously updates the directed topology map according to the returned target information until the root cause node of the fault is determined, or until the subtask execution is completed and it is determined that all devices are fault-free. Therefore, in an optional implementation of the present application, the intelligent inspection method may also include: when the in-degree of any node in the updated directed topology map is not zero, sending an information acquisition instruction to the execution agent so that the execution agent returns new target information in response to the information acquisition instruction; then, the central agent updates the directed topology map according to the new target information, and again detects whether there are nodes with an in-degree of zero in the directed topology map. Repeat the above process until a node with an in-degree of zero appears in the updated directed topology map, or until the task execution is completed.

[0043] As an example, the information acquisition instruction can be a single instruction that does not carry other information, and is only used to instruct the executing agent to upload a new round of acquired target information. After receiving the information acquisition instruction, the executing agent collects data according to its own configured period and sampling frequency and returns the target information.

[0044] As another example, the information acquisition instruction may be an instruction carrying a data collection period and a sampling frequency within the period, and is used to instruct the executing agent to collect data according to the carried period and sampling frequency and return target information.

[0045] In this embodiment, when no node with in-degree zero appears in the updated directed topological graph, an information acquisition instruction is sent to the execution agent to obtain new target information, and the directed topological graph is updated according to the new target information. In this way, the directed topological graph is continuously updated, which helps to detect faulty equipment in a timely manner.

[0046] The intelligent inspection method of the embodiment of the present application is that the central intelligent agent splits the inspection task into at least one sub-task and assigns it to the associated execution intelligent agent for execution, the execution intelligent agent returns the target information obtained during the execution of the sub-task, and the central intelligent agent constructs a directed topological graph according to the execution intelligent agent associated with the inspection task, and updates the directed topological graph according to the target information returned by the execution intelligent agent, and determines the nodes with zero in-degree in the directed topological graph as the root cause nodes of the fault. The entire inspection process does not require human participation, and intelligent inspection of the production workshop is achieved through the collaborative work between multiple intelligent agents. Faults occurring in the production process can be discovered in a timely manner, which greatly improves the inspection efficiency and accuracy and reduces the probability of missed detection. Therefore, the technical problems of low efficiency, poor accuracy and missed detection in manual inspection of production workshops can be solved, and the technical effects of reducing labor costs, improving inspection efficiency and quality, and improving the level of intelligent manufacturing can be achieved.

[0047] In an optional implementation of the present application, in order to achieve collaborative interaction among multiple agents, it is necessary to standardize the mode specification of the sub-agent interaction interface. That is, in the embodiment of the present application, the central agent and the sub-agent corresponding to at least one device in the current inspection area use a unified and standardized interface to interact. Figure 1 Taking the shown architecture as an example, the central agent and all sub-agents use a unified and standardized interface. The sub-agents can receive messages from the central agent through the interface and return information to the central agent. In addition, an executive agent can also collect data from other agents or have other agents collect data through the interface.

[0048] In the interface mode definition specification, each agent has four basic attributes: (1) type: used to indicate the agent type, the type is Agent; (2) name: used to indicate the name of the device corresponding to the agent, which can be customized; (3) description: used to indicate the description information, function introduction and other information of the device corresponding to the agent, which helps the central agent select the most relevant execution agent when planning tasks); (4) parameters: used to define the parameter information of the agent interface. The number and type of parameters can be customized according to the device properties. The required attribute in the parameter indicates a list of required parameters.

[0049] For example, taking the standardized unified definition interface in Json format as an example, the agent interaction interface mode definition specification is as follows:

[0050] In this embodiment, by configuring a unified and standardized interface for the central agent and sub-agents, the central agent and sub-agents, and sub-agents and sub-agents can interact through a unified and standardized interface, thereby achieving collaborative interaction between multiple agents and laying the foundation for realizing the solution of this application.

[0051] Furthermore, in an optional embodiment of the present application, when the central agent determines the device to be monitored associated with each subtask, it can obtain device description information of at least one device through an interface between the central agent and the sub-agent of at least one device; and then, based on the device description information, determine the device to be monitored associated with at least one subtask.

[0052] In the embodiment of the present application, the unified specification of the exchange interface of the intelligent body includes the attribute "description", which is used to indicate the description information and function introduction of the corresponding device of the intelligent body. Therefore, the central intelligent body can obtain the description information and function introduction of the corresponding device through the interface of each sub-intelligent body, and then combine each subtask to select the device that is most suitable for executing each subtask as the monitored device associated with the corresponding subtask. Therefore, by obtaining the device description information of each device and determining the monitored device associated with the subtask according to the device description information, the accuracy of the determined monitored device can be improved, laying the foundation for improving the accuracy of intelligent inspection.

[0053] In an optional embodiment of the present application, Figure 4 As shown, based on the above embodiment, step 102 may include the following sub-steps: Step 201, traverse the execution agent, determine the current traversal execution agent and use it as the end point.

[0054] In this embodiment, for the execution agents corresponding to the determined devices to be monitored, the central agent traverses each execution agent, determines the currently traversed execution agent, and uses the currently traversed execution agent as the endpoint.

[0055] Step 202: other executing agents among the executing agents except the currently traversing executing agent are used as source nodes of the currently traversing executing agent.

[0056] In this embodiment, for the determined current traversal execution agent, all execution agents except the current traversal execution agent among all execution agents are determined as source nodes of the current traversal execution agent, and the current traversal execution agent is the end point.

[0057] Step 203: construct a directed edge from the source node to the end node, and set an initial importance factor for the directed edge as an edge attribute.

[0058] In this embodiment, for the current traversal execution agent (ie, the endpoint), after the corresponding source node is determined, a directed edge from the source node to the endpoint can be constructed, and an initial importance factor can be set for the directed edge as an edge attribute.

[0059] Exemplarily, the edge attribute of each directed edge may be initialized to 1 as the initial importance factor of the edge.

[0060] Among them, the importance factor is the attribute corresponding to each edge, which is used to describe an edge<s,t> The importance of the source node s to the terminal node t, such as Figure 5 As shown. The importance factor is asymmetric, that is, IF<s,t> with IF<t,s> There is a fundamental difference, IF<s,t> Indicates the importance of node s to node t, IF<t,s> Indicates the importance of node t to node s.

[0061] Step 204, after traversing all executing agents, a directed topology graph is obtained.

[0062] In this embodiment, after traversing all the execution agents, a constructed directed topology graph is obtained. That is to say, when constructing the directed topology graph, each execution agent is a node in the directed topology graph, which is both a terminal point and a source node of other execution agents.

[0063] The intelligent inspection method of this embodiment, after determining the execution agent associated with the subtask, takes each execution agent as an endpoint, and other execution agents as source nodes of the endpoint and constructs directed edges from the source node to the endpoint, thereby obtaining a directed topology graph. This can clearly show the relationship between the execution agents, and provides convenience for subsequently determining the root cause node of the fault by updating the directed topology graph.

[0064] As mentioned above, the central agent processes the received target information differently according to the type of target information, which are explained below.

[0065] In an optional implementation of the present application, the target information includes sampled data collected by the first execution agent from the second execution agent at a preset sampling frequency within at least one cycle, wherein the first execution agent is each of all execution agents, the second execution agent is an execution agent that interacts with the first execution agent, the number of second execution agents may be one or more, the first execution agent performs at least one cycle of data collection on the second execution agent, the sampling frequency within one cycle is preset, and the sampled data is obtained through data collection. It can be understood that the central agent obtains the sampled data returned by all execution agents respectively. Thus, in this embodiment, Figure 6 As shown, based on the above embodiment, step 104 may include the following sub-steps: Step 301, traverse the nodes in the directed topological graph, determine the current traversal node, the target source node corresponding to the current traversal node, and the target edge from the target source node to the current traversal node.

[0066] In this embodiment, when the central intelligent agent updates the directed topological graph according to the obtained target information (sampling data), it can traverse each node in the directed topological graph to determine the current traversed node, and based on the directed topological graph, it can determine the source node corresponding to the current traversed node (for the convenience of description and distinction, referred to as the target source node), and determine the directed edge from the target source node to the current traversed node (for the convenience of description and distinction, referred to as the target edge).

[0067] by Figure 3 Taking the directed topological graph shown in the figure as an example, for the currently traversed node a3, the target source nodes can be determined to be a1, a2, a4 and a5, and the target edges include<a1,a3> ,<a2,a3> ,<a4,a3> and<a5,a3> .

[0068] Step 302: determine the target sampling data of the target execution agent corresponding to the current traversal node from the sampling data.

[0069] In this embodiment, the central agent can filter out the sampling data of the target execution agent corresponding to the current traversal node from all the received sampling data based on the determined current traversal node and target source node (referred to as target sampling data for ease of description and distinction), that is, the sampling data collected by the target execution agent from the execution agents corresponding to each target source node.

[0070] Exemplarily, there is a one-to-one correspondence between each node in the directed topological graph and the execution agent. Based on the correspondence and the determined current traversal node, the target execution agent corresponding to the current traversal node can be determined, so that the sampling data returned by the target execution agent can be filtered out from the sampling data, that is, the target sampling data can be obtained.

[0071] In an optional implementation of the present application, when the central agent determines the target sampling data, if the target sampling data corresponding to the target edge is not determined from the target information (i.e., the sampling data), the target edge is deleted from the directed topological graph. Figure 3 For example, for the directed edge from source node a1 to current traversal node a3, if the sampled data collected by the target execution agent corresponding to a3 from the execution agent corresponding to a1 is not determined from the sampled data, the importance factor of source node a1 to current traversal node a3 cannot be determined. Figure 3 The directed edge from a1 to a3 is deleted. Thus, the directed edge from the source node with missing sampling data to the current traversal node in the directed topological graph is updated, avoiding the situation where the directed topological graph cannot be accurately updated due to lack of data, thereby helping to reduce the probability of missed detection.

[0072] Step 303: Determine the target importance factor of the target source node to the current traversal node according to the target sampling data.

[0073] In this embodiment, the central intelligent agent can determine the importance factor of each target source node to the current traversal node based on the determined target sampling data by utilizing its own powerful understanding and processing capabilities (for ease of description and distinction, referred to as the target importance factor).

[0074] Exemplarily, an importance factor prediction model can be pre-trained to predict the importance factor of the source node to the terminal node. The input of the importance factor prediction model is the sampled data of the source node, and the output is the predicted importance factor. For example, the importance factor prediction model can be obtained by training a support vector machine (SVM). Thus, in this embodiment, the central agent inputs the sampled data corresponding to each target source node into the importance factor prediction model, and the target importance factor of each target source node to the current traversal node can be obtained.

[0075] In an optional implementation of the present application, when the central agent determines the target importance factor of the target source node to the current traversal node according to the target sampling data, it can first determine the candidate importance factor of the target source node to the current traversal node in at least one cycle according to the target sampling data, and then determine the target importance factor of the target source node to the current traversal node according to the candidate importance factor. That is to say, in this embodiment, for the target sampling data in at least one cycle obtained, the importance factor (called the candidate importance factor) of the target source node to the current traversal node in the corresponding cycle is determined according to the sampling data in each cycle. For example, the sampling data in one cycle can be input into a pre-trained importance factor prediction model to obtain the candidate importance factor of the corresponding cycle. When there are multiple target source nodes, the sampling data of multiple target source nodes in the same cycle can be simultaneously input into the importance factor prediction model, and the candidate importance factor of each target source node to the current traversal node in the corresponding cycle is obtained; then, according to the candidate importance factor of each cycle, the final target importance factor of each target source node to the current traversal node is determined. Therefore, by first determining the candidate importance factors of the target source node to the current traversed node in each cycle, and then determining the target importance factor based on the candidate importance factors of each cycle, it helps to ensure the reliability and accuracy of the ultimately determined importance factor, thereby helping to improve the accuracy of fault inspection.

[0076] As an example, when determining the target importance factor based on the candidate importance factor, if the cycle is one, that is, the target collection data only includes data collected in one cycle, the candidate importance factor can be determined as the target importance factor; if the cycle is multiple, the average value of the candidate importance factors of the target source node to the current traversal node in multiple cycles can be determined for the same target source node, and then the obtained average value is determined as the target importance factor of the target source node to the current traversal node. For example, assuming that the cycle is 3, for a target source node, the average value of the candidate importance factors of the target source node in these three cycles is calculated, and the obtained average value is used as the target importance factor of the target source node to the current traversal node. By calculating the average value of the candidate importance factors of the same target source node in each cycle as its target importance factor to the current traversal node when the cycle is multiple, it helps to ensure the rationality of the determined target importance factor, thereby helping to improve the accuracy of fault inspection.

[0077] Step 304: Update the target edge in the directed topological graph based on the target importance factor.

[0078] In this embodiment, after the central intelligent agent determines the target importance factor of the target source node to the currently traversed node, it can update the target edge in the directed topological graph based on the determined target importance factor, thereby realizing real-time updating of the directed topological graph according to the data collected by the executing intelligent agent, and realizing status update between the monitored devices in order to find the faulty equipment.

[0079] In an optional implementation of the present application, when updating a target edge in a directed topological graph, the target importance factor can be compared with a preset importance factor threshold, wherein the importance factor threshold can be pre-set according to actual needs, for example, the importance factor threshold is set to 0.2; when the target importance factor is greater than or equal to the importance factor threshold, the edge attribute of the target edge in the directed topological graph is updated to the target importance factor, and the target edge is retained; when the target importance factor is less than the importance factor threshold, the target edge in the directed topological graph is deleted.

[0080] It can be understood that when updating the target edge in the directed topology graph, the target importance factor of each target source node to the current traversal node is traversed one by one. If the target importance factor is greater than or equal to the importance factor threshold, the directed edge from the target source node to the current traversal node in the directed topology graph is retained and its edge attribute is updated to the corresponding target importance factor. Otherwise, the directed edge from the target source node to the current traversal node in the directed topology graph is deleted. Figure 3 Taking the directed topology graph shown in the figure as an example, the target source node is a1, the current traversal node is a3, and the target importance factor of a1 to a3 is determined to be 0.5, which is greater than the importance factor threshold of 0.2, so it is retained. Figure 3 Directed edge from a1 to a3 in the graph; if the target importance factor of a1 to a3 is 0.1, which is less than the importance factor threshold of 0.2, then delete it. Figure 3 There is a directed edge from a1 to a3 in .

[0081] In this embodiment, by comparing the determined target importance factor with the importance factor threshold, only the directed edges in the directed topology graph whose target importance factor is greater than or equal to the importance factor threshold are retained, and the directed edges whose target importance factor is less than the importance factor threshold are deleted. As a result, only the directed edges with greater correlation are retained in the updated directed topology graph, thereby achieving a simplification of the directed topology graph and providing a traversal for determining the root cause node of the fault through the directed topology graph.

[0082] The intelligent inspection method of this embodiment returns the sampling data collected at a preset sampling frequency within at least one cycle to the central agent by the execution agent, and the central agent determines the target sampling data of the target execution agent corresponding to the current traversal node from the sampling data, and then determines the target importance factor of the target source node to the current traversal node based on the target sampling data and updates the target edge in the directed topology graph. As a result, the execution agent only needs to collect data according to the cycle and sampling frequency, and there is no need to analyze and process the collected data, thereby reducing the algorithm complexity and processing difficulty of the execution agent.

[0083] In an optional embodiment of the present application, the target information includes an importance factor, wherein the third execution agent collects data from the fourth execution agent at a preset sampling frequency within at least one cycle, and determines the importance factor of the fourth execution agent to the third execution agent based on the collected data, and returns the importance factor to the central agent, the third execution agent is each of all execution agents, the fourth execution agent is an execution agent that interacts with the third execution agent, the number of third execution agents can be one or more, the third execution agent collects data from the fourth execution agent for at least one cycle, the sampling frequency within one cycle is preset, and the importance factor of each fourth execution agent to the third execution agent is determined based on the collected data. It can be understood that the central agent obtains the importance factors returned by all execution agents respectively.

[0084] That is to say, in this embodiment, each executing agent collects data from other executing agents, and determines the importance factors of other executing agents to itself based on the collected data, and then feeds back to the central agent, which updates the directed topology graph based on the received importance factors.

[0085] Exemplarily, when each execution agent, as an endpoint, calculates the importance factor of other execution agents to it, it can use the artificial intelligence prediction model to complete it. Among them, the artificial intelligence prediction model is pre-trained, and its input is the characteristics of the sampled data of the source node s (corresponding to a fourth execution agent) under the preset sampling frequency conditions within a cycle. The dimension of the feature can be at least one of the mean, variance, standard deviation, maximum value, minimum value, median, peak value, skewness, etc. The output is the predicted probability vector of the data characteristics of the endpoint t (i.e., the third execution agent) in the same sampling cycle and sampling frequency, recorded as , The dimension is , m represents the number of dimensions of the feature, and the value of m can be preset according to actual needs. By using artificial intelligence prediction models to process input data features, the efficiency of data processing can be improved.

[0086] The calculation formula of the artificial intelligence prediction model is shown in formula (1). According to the prediction probability vector output by the artificial intelligence prediction model The calculation formula for determining the single-cycle importance factor (denoted as w) of the source node s to the terminal t is shown in formula (2):

[0087] Among them, Model represents the pre-trained artificial intelligence prediction model; the time span of the sampling period is T, and the sampling frequency during this time is recorded as N T , that is, N sampling times in one cycle; F(s) represents the time span T of one cycle, N T The characteristics of the sampling sequence data; F(t) represents the data characteristics of the predicted endpoint t, and w represents the single-cycle importance factor, that is, the importance factor determined based on the sampling data of one cycle; Represents the predicted probability vector The transposed vector of .

[0088] For a terminal point t with multiple in-degree edges, the features of the sampled data of the source nodes of each edge can be simultaneously input into the artificial intelligence prediction model, and the artificial intelligence prediction model outputs the prediction probability vector corresponding to each source node. For example, assuming that the terminal point t corresponds to the source nodes s1, s2, s3 and s4, the prediction process of a cycle is as follows: Figure 7 As shown in Figure 1, it can be seen that the features of the sampling data corresponding to each source node are input into the artificial intelligence prediction model Model to predict the data features F(t) of the endpoint t in the same sampling period and sampling frequency, and output the prediction vector probability corresponding to each source node. , , and .

[0089] Therefore, in this embodiment, when the third execution agent (end point) determines the importance factor of each corresponding fourth execution agent (source node) to it, it can collect data from each fourth execution agent according to the number of collection cycles and the sampling frequency in each cycle. Usually, the collection frequency of each cycle is the same, and then use the collected data to determine the importance factor of each source node to the end point. The specific execution process is as follows: Step 1: Set the number of acquisition cycles to k and the sampling frequency in the i-th cycle to N i .

[0090] Step 2: Let i=1.

[0091] Step 3: Collect the data of the i-th cycle from each fourth execution agent, and use the above artificial intelligence prediction model and formula (2) to determine the single-cycle importance factor of each fourth execution agent to the third execution agent, denoted as IF1={ , ,……, }, where g is the number of the fourth execution agent, Indicates the single-cycle importance factor of the fourth execution agent g in the first sampling cycle. Optionally, the central agent can send the identification information of other execution agents associated with the execution agent to the execution agent according to the source node corresponding to each node in the directed topology graph as the terminal point, that is, the fourth execution agent corresponding to the execution agent, and the number of the fourth execution agents represents the in-degree of the terminal point in the directed topology graph.

[0092] Step4: i=i+1.

[0093] Step 5: Loop through Step 3 until i=k, and get the single-cycle importance factor of each fourth execution agent in the kth cycle, i.e., IF k ={ , ,……, }.

[0094] Step 6: Calculate the final importance factor (denoted as IF) of each fourth execution agent to the third execution agent in k cycles. The calculation formula is shown in formula (3):

[0095] That is to say, for a fourth executing agent, its final importance factor to the third executing agent is the average value of its single-cycle importance factors in k cycles.

[0096] Through the above steps Step 1-Step 6, the importance factor of each fourth execution agent associated with a third execution agent to the third execution agent can be obtained, and the importance factor can be returned to the central agent. Figure 8 As shown, based on the above embodiment, step 104 may include the following sub-steps: Step 401, traverse the nodes in the directed topological graph, determine the current traversal node, the target source node corresponding to the current traversal node, and the target edge from the target source node to the current traversal node.

[0097] In this embodiment, when the central intelligent agent updates the directed topological graph according to the obtained target information (importance factor), it can traverse each node in the directed topological graph to determine the current traversed node, and based on the directed topological graph, it can determine the source node corresponding to the current traversed node (for the convenience of description and distinction, referred to as the target source node), and determine the directed edge from the target source node to the current traversed node (for the convenience of description and distinction, referred to as the target edge).

[0098] by Figure 3 Taking the directed topological graph shown in the figure as an example, for the currently traversed node a3, the target source nodes can be determined to be a1, a2, a4 and a5, and the target edges include<a1,a3> ,<a2,a3> ,<a4,a3> and<a5,a3> .

[0099] Step 402, according to the target edge from the target source node to the currently traversed node, determine the target importance factor corresponding to the target edge from the importance factors.

[0100] It can be understood that a target edge is associated with a target source node and a current traversal node. According to the two nodes associated with the target edge, that is, the correspondence between each node and the executing agent, the target importance factor corresponding to the target edge can be determined from the importance factors returned by each executing agent.

[0101] In an optional implementation of the present application, when the central agent determines the target importance factor, if the central agent fails to determine the target importance factor corresponding to the target edge from the target information (i.e., the importance factor returned by the executing agent), the target edge is deleted from the directed topological graph. Figure 3 For example, for the directed edge from source node a1 to current traversal node a3, if the importance factor of a1 to a3 is not determined from the importance factor, then Figure 3 The directed edge from a1 to a3 is deleted. Thus, the directed edge from the source node with missing importance factor to the current traversal node in the directed topological graph is updated, avoiding the situation that the directed topological graph cannot be accurately updated due to lack of data, thereby helping to reduce the probability of missed detection.

[0102] Step 403: Update the target edge in the directed topological graph based on the target importance factor.

[0103] In this embodiment, after the central intelligent agent determines the target importance factor of the target edge, it can update the target edge in the directed topological graph based on the determined target importance factor, thereby realizing real-time updating of the directed topological graph according to the importance factor returned by the executing intelligent agent, and realizing status update between the monitored devices to find the faulty device.

[0104] In an optional implementation of the present application, when updating a target edge in a directed topological graph, the target importance factor can be compared with a preset importance factor threshold, wherein the importance factor threshold can be pre-set according to actual needs, for example, the importance factor threshold is set to 0.2; when the target importance factor is greater than or equal to the importance factor threshold, the edge attribute of the target edge in the directed topological graph is updated to the target importance factor, and the target edge is retained; when the target importance factor is less than the importance factor threshold, the target edge in the directed topological graph is deleted.

[0105] It can be understood that when updating the target edge in the directed topological graph, the target importance factor of each target source node to the currently traversed node is traversed one by one. If the target importance factor is greater than or equal to the importance factor threshold, the directed edge from the target source node to the currently traversed node in the directed topological graph is retained, and its edge attribute is updated to the corresponding target importance factor. Otherwise, the directed edge from the target source node to the currently traversed node in the directed topological graph is deleted.

[0106] In this embodiment, by comparing the determined target importance factor with the importance factor threshold, only the directed edges in the directed topology graph whose target importance factor is greater than or equal to the importance factor threshold are retained, and the directed edges whose target importance factor is less than the importance factor threshold are deleted. As a result, only the directed edges with greater correlation are retained in the updated directed topology graph, thereby achieving a simplification of the directed topology graph and providing a traversal for determining the root cause node of the fault through the directed topology graph.

[0107] The intelligent inspection method of this embodiment is that each execution agent collects data from other execution agents at a preset sampling frequency within at least one cycle, and determines the importance factor of the fourth execution agent to the third execution agent based on the collected data and returns it to the central agent to update the directed topology graph. Each execution agent independently calculates the importance of other execution agents to itself without interfering with each other, thereby improving the calculation efficiency of the importance factor, which helps to improve the efficiency of intelligent inspection.

[0108] For example, assuming that each execution agent uses sensors to collect data information of the equipment to be monitored and uses support vector machine SVM as the prediction model, the complete inspection process is as follows: (1) Inspection task description: Perform daily routine inspections of the server production workshop.

[0109] (2) The central agent breaks down the inspection task according to the inspection task description, involving 5 devices to be monitored, and automatically and intelligently forms a network to obtain a directed topology diagram as shown in the figure. Figure 3As shown, the importance factor of each edge is initialized to 1. The execution agent on each device to be monitored analyzes and processes the data on the device to generate data defined by the interface specification.

[0110] (3) Define the collection cycle length as 5 minutes, the collection frequency as 20 times, the importance factor threshold as 0.2, and the number of collection cycles k=1. Use SVM to calculate the importance factor of the source node of each edge to the terminal node. The final importance factor after k cycles can be expressed in the matrix as follows, where the diagonal elements are 0: .

[0111] (4) Update according to the above matrix Figure 3 In the directed topological graph shown in FIG. 1 , assuming that in the updated graph, the node with in-degree 0 is a3, then a3 is the root cause node of the failure.

[0112] (5) The central agent analyzes and processes the data and related information of the device corresponding to node a3 and provides a solution to the fault.

[0113] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method.

[0114] The embodiment of the present application also provides an intelligent inspection system, including a central intelligent agent and at least one device, wherein one device uniquely corresponds to one sub-intelligent agent. The architecture diagram of the intelligent inspection system is as follows: Figure 1 shown.

[0115] The central agent is configured to: decompose the current inspection task into at least one subtask, and determine the equipment to be monitored associated with at least one subtask; construct a directed topological graph according to the execution agent corresponding to the equipment to be monitored; send at least one subtask to the corresponding execution agent, and the execution agent executes the assigned subtask and returns the target information obtained during the execution of the subtask; update the directed topological graph according to the target information; and determine at least one node as the fault root cause node corresponding to the current inspection task when the in-degree of at least one node in the updated directed topological graph is zero; The sub-agent is configured to: execute the assigned sub-task and return the target information obtained during the execution of the sub-task to the central agent.

[0116] It can be understood that the specific execution operations of the central agent and the sub-agents can refer to the relevant descriptions of the embodiments corresponding to the aforementioned intelligent inspection method, and will not be repeated here.

[0117] The embodiment of the present application also provides an intelligent inspection device, including: A task planning module is used to decompose the current inspection task into at least one subtask and determine the equipment to be monitored associated with at least one subtask; The intelligent networking module is used to construct a directed topology graph according to the execution agents corresponding to the monitored devices, wherein one monitored device uniquely corresponds to one execution agent; The task issuing module is used to send at least one subtask to the corresponding execution agent, and the execution agent executes the assigned subtask and returns the target information obtained during the execution of the subtask; An updating module, used for updating the directed topology graph according to target information; The determination module is used to determine at least one node as a fault root cause node corresponding to the current inspection task when the in-degree of at least one node in the updated directed topology graph is zero.

[0118] Optionally, the central agent and the sub-agent corresponding to at least one device in the current inspection area interact using a unified and standardized interface.

[0119] Optionally, the mission planning module is further used to: Obtaining device description information of at least one device through an interface with a sub-agent of at least one device; According to the device description information, a device to be monitored associated with at least one subtask is determined.

[0120] Optionally, the intelligent networking module is further used to: Traverse the execution agent, determine the current traversal execution agent and use it as the endpoint; The other executing agents except the currently traversing executing agent are used as the source nodes of the currently traversing executing agent; Construct a directed edge from the source node to the end node, and set the initial importance factor for the directed edge as an edge attribute; After traversing the executing agents, a directed topological graph is obtained.

[0121] Optionally, the target information includes sampled data collected by the first execution agent from the second execution agent at a preset sampling frequency within at least one cycle; the updating module includes: The first traversal unit is used to traverse the nodes in the directed topological graph, determine the current traversal node, the target source node corresponding to the current traversal node, and the target edge from the target source node to the current traversal node; A first determining unit is used to determine target sampling data of a target execution agent corresponding to a current traversal node from the sampling data; A second determination unit is used to determine the target importance factor of the target source node to the current traversal node according to the target sampling data; The first updating unit is used to update the target edge in the directed topological graph based on the target importance factor.

[0122] Optionally, the second determining unit is further configured to: Determine, based on the target sampling data, a candidate importance factor of the target source node to the current traversal node within at least one cycle; Based on the candidate importance factors, determine the target importance factor of the target source node to the current traversal node.

[0123] Further optionally, the second determining unit is further configured to: For the same target source node, determine the average value of the candidate importance factors of the target source node to the current traversal node in multiple cycles; The average value is determined as the target importance factor of the target source node to the current traversal node.

[0124] Optionally, the target information includes an importance factor; wherein the third execution agent collects data from the fourth execution agent at a preset sampling frequency within at least one cycle, determines the importance factor of the fourth execution agent to the third execution agent based on the collected data, and returns the importance factor to the central agent; the updating module includes: A second traversal unit is used to traverse the nodes in the directed topological graph, determine the current traversal node, the target source node corresponding to the current traversal node, and the target edge from the target source node to the current traversal node; A third determining unit is used to determine a target importance factor corresponding to the target edge from the importance factors according to the target edge from the target source node to the currently traversed node; The second updating unit is used to update the target edge in the directed topological graph based on the target importance factor.

[0125] Further optionally, the updating unit (including the first updating unit and the second updating unit) is further configured to: comparing the target importance factor with a preset importance factor threshold; When the target importance factor is greater than or equal to the importance factor threshold, the edge attribute of the target edge in the directed topological graph is updated to the target importance factor; When the target importance factor is less than the importance factor threshold, the target edge in the directed topological graph is deleted.

[0126] Optionally, the update module further includes: The third updating unit is configured to delete the target edge from the directed topological graph when the target information corresponding to the target edge is not determined from the target information.

[0127] Optionally, the intelligent inspection device further includes: An instruction sending module, used for sending an information acquisition instruction to the execution agent when the in-degree of any node in the updated directed topological graph is not zero, so that the execution agent returns new target information in response to the information acquisition instruction; The updating module is also used to: update the directed topology graph according to the new target information.

[0128] For the description of the features in the embodiment corresponding to the intelligent inspection device, please refer to the relevant description of the embodiment corresponding to the intelligent inspection method, which will not be repeated here.

[0129] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any of the above-mentioned intelligent inspection method embodiments.

[0130] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above-mentioned intelligent inspection method embodiments when running.

[0131] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0132] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any of the above-mentioned intelligent inspection method embodiments are implemented.

[0133] An embodiment of the present application also provides another computer program product, including a non-volatile computer-readable storage medium, the non-volatile computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps in any of the above-mentioned intelligent inspection method embodiments are implemented.

[0134] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0135] The above is a detailed introduction to an intelligent inspection method provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and its core idea of ​​the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the claims of the present application.

Claims

1. An intelligent inspection method, characterized in that: Applied to a central agent, the method comprises: Decompose the current inspection task into at least one subtask, and determine the device to be monitored associated with the at least one subtask; According to the execution agent corresponding to the device to be monitored, a directed topological graph is constructed, wherein one device to be monitored uniquely corresponds to one execution agent; Sending the at least one subtask to the corresponding execution agent, so that the execution agent executes the assigned subtask and returns the target information obtained during the execution of the subtask; Updating the directed topological graph according to the target information; When the in-degree of at least one node in the updated directed topological graph is zero, the at least one node is determined to be the fault root cause node corresponding to the current inspection task.

2. The intelligent inspection method according to claim 1, characterized in that: The central intelligent agent and the sub-intelligent agent corresponding to at least one device in the current inspection area interact with each other using a unified and standardized interface.

3. The intelligent inspection method according to claim 2, characterized in that: The determining the device to be monitored associated with the at least one subtask includes: Acquiring device description information of the at least one device through an interface with a sub-agent of the at least one device; The device to be monitored associated with the at least one subtask is determined according to the device description information.

4. The intelligent inspection method according to claim 1, characterized in that: The step of constructing a directed topology graph according to the execution agent corresponding to the device to be monitored includes: Traversing the execution agent, determining the current traversal execution agent as the end point; Using other executing agents among the executing agents except the currently traversing executing agent as the source nodes of the currently traversing executing agent; Constructing a directed edge from the source node to the endpoint, and setting an initial importance factor for the directed edge as an edge attribute; After traversing the execution agents, the directed topological graph is obtained.

5. The intelligent inspection method according to claim 4, characterized in that: The target information includes sampled data collected by the first execution agent from the second execution agent at a preset sampling frequency within at least one cycle; The updating of the directed topological graph according to the target information includes: Traversing the nodes in the directed topological graph, determining a current traversal node, a target source node corresponding to the current traversal node, and a target edge from the target source node to the current traversal node; Determine the target sampling data of the target execution agent corresponding to the current traversal node from the sampling data; Determining, according to the target sampling data, a target importance factor of the target source node to the currently traversed node; Based on the target importance factor, the target edge in the directed topological graph is updated.

6. The intelligent inspection method according to claim 5, characterized in that: The step of determining the target importance factor of the target source node to the current traversal node according to the target sampling data includes: Determining, according to the target sampling data, a candidate importance factor of the target source node to the currently traversed node within the at least one cycle; According to the candidate importance factors, a target importance factor of the target source node to the current traversal node is determined.

7. The intelligent inspection method according to claim 6, characterized in that: There are multiple cycles, and determining the target importance factor of the target source node to the current traversal node according to the candidate importance factor includes: For the same target source node, determining an average value of the candidate importance factors of the target source node to the currently traversed node in multiple cycles; The average value is determined as a target importance factor of the target source node to the current traversal node.

8. The intelligent inspection method according to claim 4, characterized in that: The target information includes an importance factor; The third execution agent collects data from the fourth execution agent at a preset sampling frequency within at least one cycle, determines the importance factor of the fourth execution agent to the third execution agent based on the collected data, and returns the importance factor to the central agent; The updating of the directed topological graph according to the target information includes: Traversing the nodes in the directed topological graph, determining a current traversal node, a target source node corresponding to the current traversal node, and a target edge from the target source node to the current traversal node; According to the target edge from the target source node to the currently traversed node, determining a target importance factor corresponding to the target edge from the importance factors; Based on the target importance factor, the target edge in the directed topological graph is updated.

9. The intelligent inspection method according to claim 5 or 8, characterized in that: The updating of the target edge in the directed topological graph based on the target importance factor includes: Comparing the target importance factor with a preset importance factor threshold; When the target importance factor is greater than or equal to the importance factor threshold, updating the edge attribute of the target edge in the directed topological graph to the target importance factor; When the target importance factor is less than the importance factor threshold, the target edge in the directed topological graph is deleted.

10. The intelligent inspection method according to any one of claims 5 or 8, characterized in that: The method further comprises: When no target information corresponding to the target edge is determined from the target information, the target edge is deleted from the directed topological graph.

11. The intelligent inspection method according to any one of claims 1 to 8, characterized in that: The method further comprises: When the in-degree of any node in the updated directed topological graph is not zero, sending an information acquisition instruction to the execution agent, so that the execution agent returns new target information in response to the information acquisition instruction; The directed topological graph is updated according to the new target information.

12. An intelligent inspection system, characterized in that: It includes a central agent and at least one device, wherein one device uniquely corresponds to one sub-agent; The central agent is configured to: decompose the current inspection task into at least one subtask, and determine the equipment to be monitored associated with the at least one subtask; construct a directed topological graph according to the execution agent corresponding to the equipment to be monitored; send the at least one subtask to the corresponding execution agent, and the execution agent executes the assigned subtask and returns the target information obtained during the execution of the subtask; update the directed topological graph according to the target information; and determine the at least one node as the fault root cause node corresponding to the current inspection task when the in-degree of at least one node in the updated directed topological graph is zero; The sub-agent is configured to: execute the assigned sub-task and return the target information obtained during the execution of the sub-task to the central agent.

13. An electronic device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the intelligent inspection method according to any one of claims 1 to 11 when executing the computer program.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the intelligent inspection method according to any one of claims 1 to 11.

15. A computer program product, characterized in that It comprises a computer program, which, when executed by a processor, implements the steps of the intelligent inspection method according to any one of claims 1 to 11.

Images