Asset management method based on distributed experimental equipment and related equipment

Abstract

The invention belongs to the field of data processing, and particularly relates to an asset management method based on distributed experimental equipment and related equipment, and the method comprises the steps: monitoring an equipment deployment condition in a distributed experimental equipment management and control system; inputting the equipment deployment condition into an intelligent editing model to execute automatic topology collection and task mode recognition processing so as to obtain an equipment topology editing task matched with the distributed experimental equipment management and control system; constructing or updating an equipment topology network of the distributed experimental equipment management and control system based on the equipment topology editing task; carrying out asset comparison check on the equipment topology network and a historical equipment topology network; and asset management information corresponding to the distributed experimental equipment management and control system is updated based on the asset ratio check result. According to the method, the asset management efficiency and the asset discovery accuracy of the distributed experimental equipment can be improved, the operation risk of the system is reduced, and the stability and reliability of the system are enhanced.

Description

Technical Field

[0001] The present application belongs to the field of data processing, and in particular, relates to an asset management method based on distributed experimental equipment and related equipment. Background Art

[0002] In order to promote the popularization of intelligent applications in various industries and fields, distributed experimental equipment generates a large amount of data.

[0003] In the related art, many different types of experimental equipment are deployed in the laboratory, and each device may have different usage and maintenance requirements. The diversity and complexity of this equipment makes asset management difficult, especially when multiple devices need to be updated and monitored simultaneously. In addition, experimental equipment often requires high-cost maintenance and regular inspections. Failure to detect or deal with equipment problems in a timely manner may result in expensive repair or replacement costs, as well as loss of experimental data.

[0004] Therefore, it is urgent to design an asset management solution based on distributed experimental equipment to solve at least one of the above technical problems. Summary of the invention

[0005] The present application provides an asset management method and related equipment based on distributed experimental equipment to improve the asset management efficiency of distributed experimental equipment, the accuracy of asset discovery, reduce system operation risks, and enhance the stability and reliability of the system.

[0006] In a first aspect, the present application provides an asset management method based on distributed experimental equipment, which is applied to a distributed experimental equipment management and control system, wherein the distributed experimental equipment management and control system is used to operate and manage experimental equipment, and the experimental equipment includes different types of equipment; the asset management method based on distributed experimental equipment includes:

[0007] Monitor the equipment deployment status in the distributed experimental equipment management and control system;

[0008] Input the equipment deployment situation into the intelligent editing model to perform automatic topology collection and task pattern recognition processing to obtain the equipment topology editing task that matches the distributed experimental equipment management and control system;

[0009] Based on the device topology editing task, construct or update the device topology network of the distributed experimental equipment management and control system;

[0010] Performing asset comparison check on the device topology network and the historical device topology network;

[0011] Based on the asset comparison inspection results, the asset management information corresponding to the distributed experimental equipment management and control system is updated.

[0012] In a second aspect, an embodiment of the present application provides a distributed experimental equipment management and control system, the distributed experimental equipment management and control system is used to operate and manage experimental equipment, the experimental equipment includes different types of equipment, and the distributed experimental equipment management and control system includes:

[0013] A monitoring unit, configured to monitor the equipment deployment status in the distributed experimental equipment management and control system;

[0014] A generating unit is configured to input the equipment deployment situation into an intelligent editing model to perform automatic topology aggregation and task pattern recognition processing to obtain equipment topology editing tasks that match the distributed experimental equipment management and control system;

[0015] An editing unit, configured to construct or update a device topology network of the distributed experimental device management and control system based on the device topology editing task;

[0016] A comparison unit configured to perform an asset comparison check on the device topology network and a historical device topology network;

[0017] The management unit is configured to update the asset management information corresponding to the distributed experimental equipment management and control system based on the asset comparison inspection result.

[0018] In a third aspect, an embodiment of the present application provides an intelligent computing platform, the intelligent computing platform comprising:

[0019] at least one processor, memory, and input-output unit;

[0020] Among them, the memory is used to store computer programs, the processor is used to call the computer program stored in the memory to execute the first aspect of the asset management method based on distributed experimental equipment, and the input and output unit is used to receive user input and display output information of the computer program stored in the memory.

[0021] In a fourth aspect, a computer-readable storage medium is provided, which includes instructions, and when the instructions are executed on a computer, the computer executes the asset management method based on distributed experimental equipment of the first aspect.

[0022] The technical solution provided in the embodiment of the present application can be applied to a distributed experimental equipment management and control system. The distributed experimental equipment management and control system is used to operate and manage experimental equipment. These experimental equipment include different types of equipment. In this solution, first, the equipment deployment in the distributed experimental equipment management and control system is monitored. Then, the equipment deployment situation is input into the intelligent editing model to perform automatic topology collection and task pattern recognition processing to obtain the equipment topology editing task matched by the distributed experimental equipment management and control system. In this way, by monitoring the equipment deployment situation and inputting it into the intelligent editing model, the system can automatically perform automatic topology collection and task pattern recognition processing. This intelligent management makes equipment management more efficient and accurate, reduces the need for manual intervention, and improves management efficiency. Then, based on the equipment topology editing task, the equipment topology network of the distributed experimental equipment management and control system is constructed or updated. Here, based on the equipment topology editing task, the system can construct or update the equipment topology network of the distributed experimental equipment management and control system in real time. This real-time update ensures that the system always reflects the actual equipment layout and connection relationship, which is conducive to timely discovery and resolution of problems in the topology network. Furthermore, an asset comparison check is performed on the equipment topology network and the historical equipment topology network. Here, by performing an asset comparison check on the device topology network and the historical device topology network, the system can promptly detect any changes or anomalies. This comparison check helps to discover potential configuration errors, equipment failures or security vulnerabilities, so that timely measures can be taken to repair or prevent them. Finally, the asset management information corresponding to the distributed experimental equipment control system is updated based on the asset comparison check results. In this way, according to the asset comparison check results, the system can update the asset management information corresponding to the distributed experimental equipment control system. This timely information update ensures the accuracy and completeness of the asset management information and provides reliable data support for subsequent decision-making. The technical solution of the present application improves the asset management efficiency of distributed experimental equipment, the accuracy of asset discovery, reduces system operation risks, and enhances the stability and reliability of the system through intelligent equipment management, real-time topology network updates, asset comparison checks, and asset management information updates. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0024] Figure 1 It is a flow chart of an asset management method based on distributed experimental equipment according to an embodiment of the present application;

[0025] Figure 2 It is a structural schematic diagram of a distributed experimental equipment control system according to an embodiment of the present application;

[0026] Figure 3 It is a structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are 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.

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0029] In order to promote the popularization of intelligent applications in various industries and fields, distributed experimental equipment generates a large amount of data.

[0030] In the related art, many different types of experimental equipment are deployed in the laboratory, and each device may have different usage and maintenance requirements. The diversity and complexity of this equipment makes asset management difficult, especially when multiple devices need to be updated and monitored simultaneously. In addition, experimental equipment often requires high-cost maintenance and regular inspections, and failure to detect or deal with equipment problems in a timely manner may result in expensive repair or replacement costs, as well as loss of experimental data.

[0031] Therefore, it is urgent to design an asset management solution based on distributed experimental equipment to solve at least one of the above technical problems.

[0032] The embodiments of the present application provide an asset management method based on distributed experimental equipment and related equipment.

[0033] Specifically, the asset management scheme based on distributed experimental equipment can be applied to the distributed experimental equipment management and control system. The distributed experimental equipment management and control system is used to operate and manage experimental equipment. These experimental equipment include different types of equipment. In this scheme, first, the equipment deployment in the distributed experimental equipment management and control system is monitored. Then, the equipment deployment situation is input into the intelligent editing model to perform automatic topology collection and task pattern recognition processing to obtain the equipment topology editing task matched by the distributed experimental equipment management and control system. In this way, by monitoring the equipment deployment situation and inputting it into the intelligent editing model, the system can automatically perform automatic topology collection and task pattern recognition processing. This intelligent management makes equipment management more efficient and accurate, reduces the need for manual intervention, and improves management efficiency. Then, based on the equipment topology editing task, the equipment topology network of the distributed experimental equipment management and control system is constructed or updated. Here, based on the equipment topology editing task, the system can construct or update the equipment topology network of the distributed experimental equipment management and control system in real time. This real-time update ensures that the system always reflects the actual equipment layout and connection relationship, which is conducive to timely discovery and resolution of problems in the topology network. Then, an asset comparison check is performed on the equipment topology network and the historical equipment topology network. Here, by performing an asset comparison check on the device topology network and the historical device topology network, the system can promptly detect any changes or anomalies. This comparison check helps to discover potential configuration errors, equipment failures, or security vulnerabilities, so that timely measures can be taken to repair or prevent them. Finally, based on the results of the asset comparison check, the asset management information corresponding to the distributed experimental equipment control system is updated. In this way, based on the results of the asset comparison check, the system can update the asset management information corresponding to the distributed experimental equipment control system. This timely information update ensures the accuracy and completeness of the asset management information, and provides reliable data support for subsequent decision-making.

[0034] In the asset management solution based on distributed experimental equipment, through intelligent equipment management, real-time topology network update, asset comparison check and asset management information update, the asset management efficiency of distributed experimental equipment and the accuracy of asset discovery are improved, the system operation risk is reduced, and the stability and reliability of the system are enhanced.

[0035] The asset management scheme based on distributed experimental equipment provided in the embodiment of the present application can also be executed by an electronic device, which can be a server, a server cluster, or a cloud server. The electronic device can also be a terminal device such as a mobile phone, a computer, a tablet computer, a wearable device, or a special device (such as a special terminal device with an asset management system based on distributed experimental equipment). The chips introduced in the above embodiments can also be carried in these electronic devices. Alternatively, these electronic devices can also be installed with a service program for executing an asset management scheme based on distributed experimental equipment.

[0036] Figure 1 A schematic diagram of an asset management method based on distributed experimental equipment provided in an embodiment of the present application, such as Figure 1 , the method comprises the following steps:

[0037] 101, monitor the equipment deployment status in the distributed experimental equipment management and control system.

[0038] In the embodiment of the present application, the distributed experimental equipment management and control system is used to operate and manage experimental equipment. These experimental equipment include different types of equipment.

[0039] In the embodiment of the present application, the asset management method based on the distributed test equipment safety management system involves a relatively complex system architecture, which needs to fully consider the communication, data transmission, security and other aspects between the server and the client. The following is an introduction to the technical background of the system and related equipment:

[0040] Further optionally, the distributed test equipment safety management and control system is designed based on a C / S architecture. C / S architecture refers to a client / server architecture, which separates the user interface and application logic. The user communicates with the server through the client, and the server processes the request and returns the result. This architecture is usually used for applications that require complex logic processing and large amounts of data storage.

[0041] Microservice architecture is an architectural pattern that splits an application into a series of small, independently deployed services. Each microservice can be independently developed, deployed, and expanded, and communicate through lightweight communication protocols, thus achieving a highly cohesive and loosely coupled system architecture.

[0042] QT is a cross-platform C++ application development framework that can be used to develop graphical user interface applications. It provides a wealth of GUI components and tools that can simplify the development process of cross-platform applications while having good performance and scalability.

[0043] Distributed test equipment refers to test equipment deployed at different locations or nodes. These devices can collaborate with each other to complete test tasks and communicate and exchange data through the network. Distributed test equipment is usually highly flexible and scalable, and can be dynamically configured and deployed as needed.

[0044] The server is the core of the entire system, responsible for the implementation of various functional modules and data processing. In this system, the server adopts a microservice architecture design, which includes multiple independent functional modules, such as operation status monitoring, audit log collection and analysis, ledger management, resource management, etc. Each functional module can be deployed and expanded independently, and interact through a lightweight communication mechanism.

[0045] The client is the interface for users to interact with the system. It is responsible for receiving user input, displaying information and sending requests to the server. In this system, the client is developed based on QT and includes functional modules such as user authentication, equipment management, information management, test parameter management, file management, software management, and remote control. The client realizes the interaction between users and the system and asset management through communication with the server.

[0046] In summary, the asset management method based on the distributed test equipment safety management and control system combines the C / S architecture, microservice architecture and QT development technology to realize real-time management and intelligent control of distributed test equipment, providing strong support for the safety, stability and reliability of the test equipment.

[0047] As an optional embodiment, in 101, the equipment deployment in the distributed experimental equipment management and control system is monitored. Monitoring the equipment deployment in the distributed experimental equipment management and control system generally involves the following aspects:

[0048] Equipment online status monitoring: The system will monitor the online status of each device in real time, including whether the device is in operation, standby or fault state. By monitoring the online status, the operation status of the device can be discovered in time to ensure the normal connection and operation of the device.

[0049] Device connection monitoring: The system monitors the connection between different devices, including the network connection status between devices, whether the communication protocol is normal, etc. This helps to understand the communication status between devices and promptly discover connection problems or communication failures.

[0050] Device resource utilization monitoring: Monitor the resource utilization of the device, including the utilization of CPU, memory, storage and other resources. By monitoring resource utilization, the device load can be adjusted in time to avoid excessive resource utilization leading to system performance degradation or device failure.

[0051] Device topology monitoring: Monitor the topology of devices, including the logical connection relationship and physical connection path between devices. By monitoring the topology, you can understand the relationship between devices, find topology anomalies or connection problems, and ensure normal communication between devices.

[0052] Equipment operation log monitoring: Monitor the equipment operation log and record the equipment operation and operation status. By monitoring the operation log, abnormal equipment behavior or operation errors can be discovered in time, and timely processing can be carried out to ensure the normal operation of the equipment.

[0053] To summarize, monitoring the equipment deployment in the distributed experimental equipment management and control system includes real-time monitoring of the equipment's online status, connection status, resource utilization, topology structure, and operation logs. These monitoring can help the system detect potential problems in a timely manner and ensure the normal operation and management of the equipment.

[0054] 102. Input the equipment deployment situation into the intelligent editing model to perform automatic topology collection and task pattern recognition processing to obtain the equipment topology editing task that matches the distributed experimental equipment management and control system.

[0055] As an optional embodiment, the intelligent editing model at least includes the following structures: feature extraction layer, topology collection layer, task pattern recognition layer, and task generation layer. Specifically, the feature extraction layer is used to extract key feature information from the input device deployment data for subsequent processing and analysis. These features may include device type, device status, connection relationship, resource utilization, etc. Through feature extraction, the original data can be converted into feature representations that can be processed by the model. The topology collection layer is responsible for organizing the extracted feature information into a device topology structure and performing the process of automatic topology collection. This includes determining the connection relationship between devices, the network topology structure, the device hierarchical relationship, etc. Through topology collection, the topological relationship between devices can be established, providing a basis for subsequent task pattern recognition. The task pattern recognition layer analyzes and recognizes the collected device topology structure to determine the device topology editing task that the system needs to perform. This includes identifying anomalies or problems in the topology, determining the best editing strategy or optimization plan, etc. Through task pattern recognition, corresponding editing tasks can be generated according to the system status and requirements. The task generation layer generates actual device topology editing tasks based on the results of task pattern recognition, including operations such as adding new devices, deleting old devices, and adjusting connection relationships. This layer is responsible for converting the task mode into specific operation steps to achieve the update and optimization of the device topology. The generated tasks will be used to update the device topology network in the distributed experimental equipment management and control system to maintain the normal operation and management of the system. In summary, the structure of the intelligent editing model includes feature extraction layer, topology collection layer, task pattern recognition layer and task generation layer. These layers cooperate with each other to complete the processing and analysis of the device deployment situation to achieve intelligent editing and management of the device topology.

[0056] Based on the above model structure, in 102, the device deployment situation is input into the intelligent editing model to perform automatic topology collection and task pattern recognition processing to obtain the device topology editing task that matches the distributed experimental equipment management and control system, which can be implemented as follows:

[0057] 201, extracting device deployment features of the distributed experimental device management and control system from the device deployment situation through a feature extraction layer;

[0058] 202, through a topology aggregation layer, automatically aggregate the topology of the distributed experimental equipment management and control system based on the equipment deployment characteristics to obtain a target network structure to be updated or constructed;

[0059] 203, performing task identification on the target network structure to be updated or constructed through the task pattern identification layer to obtain the type of topology editing task to be executed;

[0060] 204 , creating a device topology editing task that matches the target network structure to be updated or constructed based on the type of the topology editing task to be executed through the task generation layer.

[0061] In the embodiment of the present application, the device deployment characteristics at least include: device access status, device connection characteristics, device subnet characteristics, and device attribute characteristics. Specifically, the device deployment characteristics are key information extracted from the device deployment situation, which are used to perform automatic topology aggregation and task mode recognition processing in the intelligent editing model.

[0062] Device access status: This feature describes the current access status of the device, including online, offline, standby, or faulty. This feature can indicate whether the device is available and its current operating status.

[0063] Device connection characteristics: This characteristic describes the connection relationship between devices, including the connection method in the network topology, connection type (such as wired connection or wireless connection), connection rate and other information. This characteristic is very important for determining the communication path and connection nature between devices.

[0064] Device subnet feature: This feature describes the subnet or network area to which the device belongs, and is used to distinguish device deployments in different network areas. This helps to partition and optimize large-scale networks.

[0065] Device attribute characteristics: This characteristic describes the attribute information of the device, including device type, manufacturer, model, hardware configuration, software version, etc. This attribute information is very important for the identification, classification and management of devices, and also helps to perform tasks for specific types of devices.

[0066] By extracting these device deployment features, the intelligent editing model can more accurately understand the device deployment situation, thereby performing effective topology automatic classification and task pattern recognition processing, and then generating topology editing tasks suitable for updating or building the target network structure. The extraction and use of these features enables the system to dynamically adjust the device topology according to the actual situation, ensuring the stability and performance optimization of the system.

[0067] For example, suppose there is a distributed experimental equipment management and control system, which includes several devices, each of which is connected to a central server. In step 201, the following features are extracted from the device deployment situation: Assume the device access status: device 1 is online, device 2 is online, device 3 is offline, and device 4 is online. Assume the device connection characteristics: device 1 is connected via a wired connection, device 2 is connected via a wireless connection, device 3 is not connected, and device 4 is connected via a wired connection. Assume the subnet characteristics to which the devices belong: device 1 and device 2 belong to subnet A, device 3 belongs to subnet B, and device 4 belongs to subnet A. Assume the device attribute characteristics: device 1 is a server, device 2 is a sensor, device 3 is a storage device, and device 4 is a server. In step 202, according to the extracted features, the devices are grouped into corresponding subnets, and the connection relationship between the devices is established to form a topological structure. For example, subnet A includes device 1 and device 4, which are connected via a wired connection. Subnet B only has device 3, which is not connected to other devices. Device 1 in subnet A is a server, and device 4 is also a server. In step 203, the aggregated topology is analyzed to identify the type of task that needs to be performed. For example, there are a large number of server devices in subnet A, and server resource allocation may need to be optimized. The devices in subnet B are offline, and may need to be reconnected or replaced. In step 204, corresponding topology editing tasks are generated based on the identified task types. For example, reallocate resources for server devices in subnet A to make the load more balanced. Diagnose faults on devices in subnet B, fix connection problems or replace devices. Through this example, you can see how to extract features from device deployment situations, aggregate topologies, identify task types, and generate corresponding editing tasks through each level of the intelligent editing model to optimize the topology of the distributed experimental equipment management and control system.

[0068] In an optional embodiment, in the above step 202, the topology collection layer is used to automatically collect the topology of the distributed experimental equipment management and control system based on the equipment deployment characteristics to obtain the target network structure to be updated or constructed, which can be implemented as follows:

[0069] 301, selecting a starting device as the starting point of a depth-first search; the starting device is any device in the distributed experimental device management and control system;

[0070] 302, starting from the starting device, performing a depth-first search on the distributed experimental device management and control system to obtain a connection relationship between various devices in the distributed experimental device management and control system;

[0071] 303, constructing a candidate topology network structure between the devices based on the connection relationship between the devices;

[0072] 304 , determining a target network structure that needs to be updated or constructed based on the candidate topology network structures between the various devices.

[0073] Specifically, in 302, during the depth-first search process, a local optimal solution search is performed on the branch to which each device belongs, from the top-level device in the branch to the bottom-level device in the branch, so that the branch reaches local search exhaustion.

[0074] Then, after reaching the bottom-level device, jump to the branch to which other adjacent devices belong to execute the same local exhaustive search process until the connection relationship between each device is established.

[0075] In the above optional embodiment, step 202 involves using the topology aggregation layer to automatically topologically aggregate the devices in the distributed experimental equipment control system. This process is intended to build or update the target network structure. In step 301, the system first selects a starting device as the starting point of a depth-first search (DFS). This starting device can be any device in the control system, and the selection criteria can be based on the importance, location, functionality or any other appropriate criteria of the device in the network. In step 302, starting from the selected starting device, the system uses a depth-first search method to explore and record the connection relationship between devices. Depth-first search is an algorithm for traversing or searching a tree or graph, which expands along the depth of the tree first and searches the branches of the tree as deeply as possible. In this process, the system searches for local optimal solutions for the branches to which each device belongs, which means starting the search from the top-level device of each branch to the bottom-level device of the branch to ensure that the connection relationship within the branch is fully explored and recorded. In step 303, based on the connection relationship between devices obtained by depth-first search, the system constructs one or more candidate topological network structures. This step is based on the actual device connection situation, and may form several different network topological structures for subsequent selection and optimization. In step 304, the target network structure to be updated or constructed is finally determined based on the constructed candidate topology network structure. This may involve selecting an optimal structure, or optimizing one of multiple structures according to specific application requirements and parameters.

[0076] The key to this process is the effective execution of depth-first search and the precise construction of the connection relationship between devices. In this way, all possible network connections can be systematically explored to ensure that the constructed network structure not only reflects the actual device deployment situation, but also meets the requirements of system operation. In addition, local optimal search can ensure that during the construction process, the configuration of each branch or connection point can reach the local optimality, thereby optimizing network performance and resource allocation as a whole.

[0077] As an optional embodiment, in 302, for the current device, the current device is accessed, and a hierarchical priority search is performed on the branch to which the current device belongs to obtain a local optimal solution search, and the search is performed from the top-level device in the branch to the bottom-level device in the branch to make the branch reach local search exhaustion. After obtaining the local optimal solution search result of the current device, or after searching the bottom-level device to complete the hierarchical priority search of the branch to which the current device belongs, the current device and the branch to which the current device belongs are marked as visited. And, jump to another device adjacent to the current device, access the other device, and determine whether the other device is in the visited state.

[0078] If another device adjacent to the current device is not in an accessed state, then a hierarchical priority search is performed on the other device adjacent to the current device to obtain a local optimal solution search step. If another device adjacent to the current device is in an accessed state, continue to jump to the next device adjacent to the current device. After searching all devices adjacent to the current device, trace back to another device that is not adjacent to the current device, and perform a hierarchical priority search on the branch to which the other device that is not adjacent to the current device belongs to obtain a local optimal solution search step. Finally, the above search process is performed on all known devices in the distributed experimental equipment management and control system to obtain the connection relationship between the various devices in the distributed experimental equipment management and control system.

[0079] The method of combining the depth-first search and the level-first search of the above optional embodiment in the distributed experimental equipment management and control system can bring multiple beneficial effects. For example, obtaining the local optimal solution through the level-first search can optimize the resources and connections within each branch, which not only improves the efficiency of each branch, but also helps to improve the performance of the entire system level. The connection relationship between devices is closer and more efficient, which can reduce delays and increase data processing speed. Through the depth-first search, the connection method between all devices can be explored in detail to ensure the comprehensiveness and accuracy of the network topology. This accurate topology mapping is very important, especially in experimental environments that require high network reliability, to ensure correct data transmission and collaborative operation between devices. This search mechanism allows the system to quickly locate fault points or performance bottlenecks in the network, facilitating timely fault diagnosis and repair. Marking visited devices and branches helps avoid repeated inspections and waste of resources, effectively improving maintenance efficiency.

[0080] For example, suppose in a large-scale laboratory environment with multiple sensors, servers, and storage devices, a key data analysis server suddenly cannot receive data from other sensor devices. Using the above search method, the system can start from this server and deeply search the connected branches to quickly find that the data failed to reach the server because a sensor connection was disconnected. By performing a hierarchical priority search on the disconnected sensor branch, it can be further determined whether it is a hardware failure or a configuration error, so that measures can be taken quickly to fix the problem and restore the normal operation of the entire experimental equipment.

[0081] Through this example, we can see that this search technology not only helps to quickly locate and solve problems, but also improves the efficiency and stability of the overall network by optimizing device connections and resource allocation.

[0082] Further optionally, in the above steps, for the current device, the devices in the branch to which the current device belongs are sorted according to the relevance weight and the level to which they are located, and after the search queue of the branch to which the current device belongs is constructed based on the sorting results, the search queue of the branch to which the current device belongs can also be predicted through a real-time learning model based on historical search behavior data and real-time operation data of each device in the branch to which the current device belongs, so as to obtain a local search probability distribution. The local search probability distribution is used to indicate the probability of the local optimal solution search results appearing in each device node in the search queue. Furthermore, based on the local search probability distribution, redundant path invalidation processing is performed on each device in the search queue, and / or a pruning strategy is executed to screen and delete device nodes whose probability of appearing local optimal solution search results is lower than a set probability threshold, so as to obtain an optimized search queue for the branch to which the current device belongs.

[0083] Thus, in the above optional embodiment, the system not only uses depth-first and level-first search techniques to explore the connections between devices, but also introduces device sorting based on relevance weights and levels, and combines historical search data and real-time operation data to predict the local search probability distribution of the search queue through a real-time learning model. This method improves search efficiency and optimizes network resource allocation. The following examples illustrate the beneficial effects of these measures:

[0084] Consider a laboratory that contains hundreds of servers and switches and needs to regularly check and optimize the network structure. By sorting devices using relevance weights and hierarchies, the system can prioritize key devices and high-level devices that often have a greater impact on network performance. Combined with the local search probability distribution predicted by the real-time learning model, the system can focus on devices that are more likely to have problems or need adjustment, thereby significantly improving the efficiency and effectiveness of the search.

[0085] In complex network structures, especially those with multiple paths and redundant connections, too many exploration paths consume additional computing resources and prolong the search time. By using local search probability distribution to indicate which device nodes are less likely to have problems or have reached an optimized state, the system can effectively prune these paths, avoiding invalid and redundant searches, making the search more efficient and goal-oriented.

[0086] Consider a widely deployed IoT environment with a large number of devices and complex interactions between them. When a device fails, quickly locating the source of the problem is a priority. By analyzing the device's operating data in real time and leveraging historical search behavior data, the system can predict possible failure points and prioritize these points. This not only speeds up fault location, but also ensures stable system operation and service continuity.

[0087] Take the laboratory control system as an example. The system contains thousands of sensors and signal controllers. By using real-time learning models to predict which device nodes may have problems, the system can adjust the working status of the experimental signal controller in real time to respond to real-time experimental needs or unexpected situations, such as accidents or experimental congestion, to ensure smooth and safe experiments.

[0088] This method, which combines real-time learning and optimized search queues, not only improves the efficiency and responsiveness of the entire management and control system, but also reduces maintenance costs and the overall complexity of the system, and improves the reliability of equipment and networks.

[0089] In practical applications, further optionally, the real-time learning model is expressed as the following formula:

[0090]

[0091] Wherein, (P(Y=1|X)) represents the local search probability distribution predicted by the real-time learning model based on the device X in the branch Y to which the current device belongs, x1, x2, ..., x n are the real-time operation data characteristics of each device in branch Y to which the current device belongs, and the historical search behavior data characteristics, β0, β1, ..., β n Indicates the relevance weight corresponding to each feature item.

[0092] In another optional embodiment, in the above step 202, the topology collection layer is used to automatically collect the topology of the distributed experimental equipment management and control system based on the equipment deployment characteristics to obtain the target network structure to be updated or constructed, which can be implemented as follows:

[0093] 401, selecting a starting device as the starting point of a breadth-first search; the starting device is any device in the distributed experimental device management and control system;

[0094] 402, starting from the starting device, using a global priority search queue, traversing all devices connected to the starting device layer by layer until the connection status between the starting device and other connected devices is obtained, and then jumping to the adjacent device connected to the starting device;

[0095] 403, continue to traverse all devices connected to the neighboring device until the connection status between the neighboring device and other connected devices is obtained, and then jump to the secondary neighboring device connected to the neighboring device;

[0096] 404, execute the above traversal process until the search and traversal reaches the outermost device to obtain the global network structure of the distributed experimental equipment management and control system.

[0097] In this embodiment, the topology aggregation layer implements a breadth-first search (BFS) strategy to automatically aggregate and update the network structure in the distributed experimental equipment management and control system, which brings many beneficial effects. This strategy effectively builds the global network structure of the entire system by selecting a starting device and traversing all the devices connected to it layer by layer. The following are some specific benefits and examples of this method:

[0098] By starting from a selected starting device and traversing all devices using a breadth-first search, a network structure diagram of the entire distributed system can be efficiently constructed. This global view is critical to understanding the layout of the entire network, the relationships between devices, and the communication paths.

[0099] Having a complete global network structure allows system administrators and network planners to better optimize the network and allocate resources. For example, when the network capacity needs to be adjusted or enhanced, the best device location or adjustment path can be planned based on the current network structure.

[0100] When a fault occurs in the network, having a complete global network view can quickly and accurately locate the source of the problem. In addition, fault recovery can be carried out more strategically, selecting the best route and alternative equipment to restore normal service as quickly as possible.

[0101] For example, in a large-scale smart laboratory, hundreds of sensors, cameras, control units and other devices are deployed to monitor the production line status, environmental conditions and safety status of the laboratory in real time. By implementing the breadth-first search strategy, a core monitoring device located in the central control room is first selected as the starting point. The system can traverse all the devices connected to this device in the entire laboratory layer by layer to obtain a detailed device connection diagram. This network diagram can not only help laboratory managers monitor the status of equipment in real time, but also quickly locate the problem equipment when a fault occurs, reduce downtime, and ensure production efficiency and employee safety. Through this systematic global search and automatic network aggregation method, faster deployment, more precise control and more efficient fault handling can be achieved when compiling and maintaining large-scale distributed monitoring systems. This is of great significance to improving the operating efficiency and reliability of the entire system.

[0102] 103. Based on the device topology editing task, construct or update the device topology network of the distributed experimental equipment management and control system.

[0103] In the distributed experimental equipment management and control system, building or updating the equipment topology network based on the equipment topology editing task can bring many beneficial effects. This operation is usually aimed at optimizing the structure and performance of the entire management system, improving operational efficiency and system responsiveness. The following are several specific benefits and corresponding examples that can be achieved using this method:

[0104] Updating the topology network can optimize the communication paths between devices, reduce data transmission delays, and increase data processing speed. This is especially important for systems that rely on real-time data analysis. By regularly building or updating the topology network, system administrators can adjust the network structure according to actual needs and device usage. This not only increases the flexibility and scalability of the system, but also allows the network to be optimized according to new security policies or technical standards. An accurate device topology network helps to quickly identify and isolate system failure points, accelerate the fault recovery process, and reduce system downtime. In addition, this can also avoid chain reactions of failures and protect the overall operating status of the system.

[0105] For example, suppose an intelligent experiment management system is deployed in a large city, which covers various experimental monitoring equipment, traffic lights and emergency response units. With the changes in urban experimental needs and the introduction of new technologies, the system network needs to be constantly adjusted and optimized. By editing tasks based on device topology, the system can update its network structure in real time, for example, reconfigure the data aggregation points of experimental monitoring points to cope with the increase in data traffic during the peak period of the experiment. This flexible network adjustment not only ensures the real-time and accuracy of experimental data processing, but also makes experimental control more efficient, thereby effectively alleviating experimental congestion and improving the overall operation efficiency of the urban experimental system. In addition, when new equipment is introduced, by updating the device topology network, the smooth integration of these new technologies can be guaranteed to ensure the smooth operation of the entire system.

[0106] In summary, by updating the system topology based on the device topology editing task, not only can the system performance and reliability be improved, but also the system's ability to adapt to new technologies and changes can be improved, thereby achieving more efficient and intelligent management.

[0107] 104. Update the asset management information corresponding to the distributed experimental equipment control system based on the asset comparison inspection result.

[0108] In a laboratory environment, asset management is essential to ensure efficient and accurate use and maintenance of various valuable instruments and equipment. Updating the asset management information in the distributed laboratory equipment control system based on the results of the asset ratio check can bring a series of beneficial effects and further improve the laboratory's operational efficiency and asset utilization. Here, regular asset ratio checks and updating of asset management information can help laboratory managers accurately track the usage status and location of each piece of equipment. Such accurate data support can avoid the loss and misuse of equipment and ensure that all assets are properly managed and maintained. With updated asset management information, laboratory managers can better understand the frequency of equipment use and maintenance cycle, thereby optimizing the scheduling and use strategy of equipment. This not only improves the efficiency of equipment use, but also extends the service life of equipment. Timely updated asset management information can help laboratories accurately assess equipment maintenance needs and budget plans. By preventing excessive use of equipment and timely repairs, the cost of emergency repairs and equipment replacements caused by failures can be significantly reduced.

[0109] For example, in a university's biotechnology laboratory, various precision instruments are equipped, such as high-speed centrifuges, microscopes, spectrometers, etc. The laboratory manages these devices through a distributed experimental equipment management and control system. At the end of each semester, the laboratory administrator will conduct a comprehensive asset comparison inspection to evaluate the status of all equipment and the corresponding asset records. Based on the inspection results, the administrator updates the asset management information in the system, including the current location of the equipment, status (in use, waiting for repair, obsolete, etc.), maintenance history, etc. Such information updates help laboratories manage assets effectively, such as choosing the right time for equipment maintenance, arranging equipment usage schedules to prevent overuse of certain equipment, and planning funds in advance for future equipment upgrades or replacements.

[0110] By regularly updating the results of asset ratio inspections, the laboratory not only ensures the smooth progress of research work, but also improves the utilization efficiency of equipment, reduces unexpected equipment failures and related costs, thereby ensuring the optimal use of funds and efficient operation of research activities.

[0111] In an embodiment of the present application, the deployment of equipment in the distributed experimental equipment control system is monitored. Then, the equipment deployment is input into the intelligent editing model to perform automatic topology collection and task pattern recognition processing to obtain the equipment topology editing task matched by the distributed experimental equipment control system. In this way, by monitoring the equipment deployment and inputting it into the intelligent editing model, the system can automatically perform automatic topology collection and task pattern recognition processing. This intelligent management makes equipment management more efficient and accurate, reduces the need for manual intervention, and improves management efficiency. Then, based on the equipment topology editing task, the equipment topology network of the distributed experimental equipment control system is constructed or updated. Here, based on the equipment topology editing task, the system can construct or update the equipment topology network of the distributed experimental equipment control system in real time. This real-time update ensures that the system always reflects the actual equipment layout and connection relationship, which is conducive to timely discovery and resolution of problems in the topology network. Then, the equipment topology network is compared with the historical equipment topology network for asset comparison inspection. Here, by comparing the equipment topology network with the historical equipment topology network for asset comparison inspection, the system can promptly discover any changes or anomalies. This comparison inspection helps to discover potential configuration errors, equipment failures or security vulnerabilities, so as to take timely measures to repair or prevent them. Finally, the asset management information corresponding to the distributed experimental equipment management and control system is updated based on the asset comparison inspection results. In this way, according to the asset comparison inspection results, the system can update the asset management information corresponding to the distributed experimental equipment management and control system. This timely information update ensures the accuracy and completeness of the asset management information and provides reliable data support for subsequent decision-making.

[0112] In another embodiment of the present application, a distributed experimental equipment management and control system is also provided, wherein the distributed experimental equipment management and control system is used to operate and manage experimental equipment, and the experimental equipment includes different types of equipment, see Figure 2 The distributed experimental equipment management and control system includes the following units:

[0113] A monitoring unit, configured to monitor the equipment deployment status in the distributed experimental equipment management and control system;

[0114] A generating unit is configured to input the equipment deployment situation into an intelligent editing model to perform automatic topology aggregation and task pattern recognition processing to obtain equipment topology editing tasks that match the distributed experimental equipment management and control system;

[0115] An editing unit, configured to construct or update a device topology network of the distributed experimental device management and control system based on the device topology editing task;

[0116] A comparison unit configured to perform an asset comparison check on the device topology network and a historical device topology network;

[0117] The management unit is configured to update the asset management information corresponding to the distributed experimental equipment management and control system based on the asset comparison inspection result.

[0118] Further optionally, the intelligent editing model includes at least the following structures: a feature extraction layer, a topology aggregation layer, a task pattern recognition layer, and a task generation layer;

[0119] The generating unit inputs the equipment deployment situation into the intelligent editing model to perform automatic topology aggregation and task pattern recognition processing to obtain the equipment topology editing task matched by the distributed experimental equipment management and control system, and is configured as follows:

[0120] Through the feature extraction layer, the device deployment features of the distributed experimental equipment management and control system are extracted from the device deployment situation; the device deployment features at least include: device access status, device connection features, device subnet features, and device attribute features;

[0121] Through the topology aggregation layer, the distributed experimental equipment management and control system is automatically topologically aggregated based on the equipment deployment characteristics to obtain a target network structure to be updated or constructed;

[0122] Through the task pattern recognition layer, the target network structure to be updated or constructed is identified to obtain the type of topology editing task to be performed;

[0123] Through the task generation layer, based on the type of topology editing task to be executed, a device topology editing task matching the target network structure to be updated or constructed is created.

[0124] Further optionally, the generating unit automatically aggregates the topology of the distributed experimental equipment management and control system based on the equipment deployment characteristics through a topology aggregation layer to obtain a target network structure to be updated or constructed, and is configured as follows:

[0125] Selecting a starting device as the starting point of a depth-first search; the starting device is any device in the distributed experimental device management and control system;

[0126] Starting from the starting device, a depth-first search is performed on the distributed experimental equipment control system to obtain the connection relationship between the various devices in the distributed experimental equipment control system; wherein, during the depth-first search process, a local optimal solution search is performed on the branch to which each device belongs, from the top-level device in the branch to the bottom-level device in the branch, so that the branch reaches local search exhaustion; after reaching the bottom-level device, jump to the branch to which other adjacent devices belong to perform the same local search exhaustion process until a connection relationship between the various devices is established;

[0127] Based on the connection relationship between various devices, a candidate topology network structure between various devices is constructed;

[0128] According to the candidate topology network structures between various devices, a target network structure that needs to be updated or constructed is determined.

[0129] Further optionally, the generating unit, starting from the starting device, performs a depth-first search on the distributed experimental device control system to obtain a connection relationship between each device in the distributed experimental device control system, and is configured to:

[0130] For the current device, access the current device, perform a hierarchical priority search on the branch to which the current device belongs to obtain a local optimal solution search, and search from the top-level device in the branch to the bottom-level device in the branch to exhaust the local search of the branch;

[0131] After obtaining the local optimal solution search result of the current device, or after searching the lowest-level device to complete the hierarchical priority search of the branch to which the current device belongs, marking the current device and the branch to which the current device belongs as visited; and,

[0132] Jump to another device adjacent to the current device, access the other device, and determine whether the other device is in an accessed state;

[0133] If another device adjacent to the current device is not in an accessed state, a step of performing a hierarchical priority search on another device adjacent to the current device to obtain a local optimal solution search;

[0134] If another device adjacent to the current device is in the visited state, continue to jump to the next device adjacent to the current device;

[0135] After searching all devices adjacent to the current device, backtrack to another device not adjacent to the current device, and perform a step of performing a hierarchical priority search on the branch to which the other device not adjacent to the current device belongs to obtain a local optimal solution search;

[0136] The above search process is performed on all known devices in the distributed experimental equipment management and control system to obtain the connection relationship between the various devices in the distributed experimental equipment management and control system.

[0137] Further optionally, before the generating unit performs a depth-first search on the distributed experimental equipment control system starting from the starting device to obtain the connection relationship between the devices in the distributed experimental equipment control system, it is further configured to:

[0138] Obtaining the association weights between the various devices; the association weights are used to measure the degree of task association between the devices;

[0139] For the current device, sort the devices in the branch to which the current device belongs according to the relevance weight and the level, and build a search queue for the branch to which the current device belongs based on the sorting results;

[0140] The search queue of the branch to which the current device belongs is used to indicate the search order of each device in the branch to which the current device belongs.

[0141] Further optionally, the generating unit, for the current device, sorts the devices in the branch to which the current device belongs according to the relevance weight and the level, and after constructing the search queue of the branch to which the current device belongs based on the sorting result, is further configured to:

[0142] Based on historical search behavior data and the real-time operation data of each device in the branch to which the current device belongs, the search queue of the branch to which the current device belongs is predicted through a real-time learning model to obtain the local search probability distribution;

[0143] The local search probability distribution is used to indicate the probability of a local optimal solution search result appearing in each device node in the search queue;

[0144] Based on the local search probability distribution, redundant paths of each device in the search queue are invalidated, and / or a pruning strategy is executed to screen and delete device nodes whose probability of appearing in local optimal solution search results is lower than a set probability threshold, so as to obtain an optimized search queue for the branch to which the current device belongs.

[0145] Further optionally, the real-time learning model is expressed as the following formula:

[0146]

[0147] Wherein, (P(Y=1|X)) represents the local search probability distribution predicted by the real-time learning model based on the device X in the branch Y to which the current device belongs, x1, x2, ..., x n are the real-time operation data characteristics of each device in branch Y to which the current device belongs, and the historical search behavior data characteristics, β0, β1, ..., β n Indicates the relevance weight corresponding to each feature item.

[0148] Further optionally, the generating unit automatically aggregates the topology of the distributed experimental equipment management and control system based on the equipment deployment characteristics through a topology aggregation layer to obtain a target network structure to be updated or constructed, and is configured as follows:

[0149] Selecting a starting device as the starting point of a breadth-first search; the starting device is any device in the distributed experimental device management and control system;

[0150] Starting from the starting device, a global priority search queue is used to traverse all devices connected to the starting device layer by layer until the connection status between the starting device and other connected devices is obtained, and then jump to the adjacent device connected to the starting device;

[0151] Continue to traverse all devices connected to the neighboring device until the connection status between the neighboring device and other connected devices is obtained, and then jump to the secondary neighboring device connected to the neighboring device;

[0152] The above traversal process is executed until the search and traversal reaches the outermost device to obtain the global network structure of the distributed experimental equipment management and control system.

[0153] In the embodiments of the present application, through intelligent equipment management, real-time topology network update, asset comparison check and asset management information update, the asset management efficiency of distributed experimental equipment is improved, the accuracy of asset discovery is improved, the system operation risk is reduced, and the stability and reliability of the system are enhanced.

[0154] In another embodiment of the present application, an intelligent computing platform is further provided, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0155] Memory, used to store computer programs;

[0156] The processor is used to implement the asset management method based on distributed experimental equipment described in the method embodiment when executing the program stored in the memory.

[0157] The communication bus 1140 mentioned in the above electronic device may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus 1140 may be divided into an address bus, a data bus, a control bus, etc.

[0158] The embodiment of the present application provides an asset management method based on distributed experimental equipment for constructing a low-energy consumption operator.

[0159] For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0160] The communication interface 1120 is used for communication between the above electronic device and other devices.

[0161] The memory 1130 may include a random access memory (RAM) or a non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0162] The above-mentioned processor 1110 can be a general-purpose processor, including an artificial intelligence processor, a graphics processing unit (GPU), an artificial intelligence processor card (Machine Learning Unit, MLU), a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0163] Accordingly, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed, can implement each step that can be executed by an electronic device in the above method embodiment.

[0164] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the field can easily think of various equivalent modifications or substitutions within the technical scope disclosed by the present invention, and these modifications or substitutions should all be covered within the protection scope of the present invention.

Claims

1. An asset management method based on distributed experimental equipment, characterized in that: Applied to a distributed experimental equipment management and control system, the distributed experimental equipment management and control system is used to operate and manage experimental equipment, and the experimental equipment includes different types of equipment; the method includes: Monitor the equipment deployment status in the distributed experimental equipment management and control system; Input the equipment deployment situation into the intelligent editing model to perform automatic topology collection and task pattern recognition processing to obtain the equipment topology editing task that matches the distributed experimental equipment management and control system; Based on the device topology editing task, construct or update the device topology network of the distributed experimental equipment management and control system; Performing asset comparison check on the device topology network and the historical device topology network; Based on the asset comparison inspection results, the asset management information corresponding to the distributed experimental equipment management and control system is updated.

2. The asset management method based on distributed experimental equipment according to claim 1 is characterized in that: The intelligent editing model at least includes the following structures: feature extraction layer, topology aggregation layer, task pattern recognition layer, and task generation layer; The device deployment situation is input into the intelligent editing model to perform automatic topology collection and task pattern recognition processing to obtain the device topology editing task matched by the distributed experimental equipment management and control system, including: Through the feature extraction layer, the device deployment features of the distributed experimental equipment management and control system are extracted from the device deployment situation; the device deployment features at least include: device access status, device connection features, device subnet features, and device attribute features; Through the topology aggregation layer, the distributed experimental equipment management and control system is automatically topologically aggregated based on the equipment deployment characteristics to obtain a target network structure to be updated or constructed; Through the task pattern recognition layer, the target network structure to be updated or constructed is identified to obtain the type of topology editing task to be performed; Through the task generation layer, based on the type of topology editing task to be executed, a device topology editing task matching the target network structure to be updated or constructed is created.

3. The asset management method based on distributed experimental equipment according to claim 2 is characterized in that: The topology collection layer automatically collects the topology of the distributed experimental equipment management and control system based on the equipment deployment characteristics to obtain the target network structure to be updated or constructed, including: Selecting a starting device as the starting point of a depth-first search; the starting device is any device in the distributed experimental device management and control system; Starting from the starting device, a depth-first search is performed on the distributed experimental equipment control system to obtain the connection relationship between the various devices in the distributed experimental equipment control system; wherein, during the depth-first search process, a local optimal solution search is performed on the branch to which each device belongs, from the top-level device in the branch to the bottom-level device in the branch, so that the branch reaches local search exhaustion; after reaching the bottom-level device, jump to the branch to which other adjacent devices belong to perform the same local search exhaustion process until a connection relationship between the various devices is established; Based on the connection relationship between various devices, a candidate topology network structure between various devices is constructed; According to the candidate topology network structures between various devices, a target network structure that needs to be updated or constructed is determined.

4. The asset management method based on distributed experimental equipment according to claim 3 is characterized in that: The step of performing a depth-first search on the distributed experimental equipment management and control system starting from the starting device to obtain a connection relationship between various devices in the distributed experimental equipment management and control system includes: For the current device, access the current device, perform a hierarchical priority search on the branch to which the current device belongs to obtain a local optimal solution search, and search from the top-level device in the branch to the bottom-level device in the branch to exhaust the local search of the branch; After obtaining the local optimal solution search result of the current device, or after searching the lowest-level device to complete the hierarchical priority search of the branch to which the current device belongs, marking the current device and the branch to which the current device belongs as visited; and, Jump to another device adjacent to the current device, access the other device, and determine whether the other device is in an accessed state; If another device adjacent to the current device is not in an accessed state, a step of performing a hierarchical priority search on another device adjacent to the current device to obtain a local optimal solution search; If another device adjacent to the current device is in the visited state, continue to jump to the next device adjacent to the current device; After searching all devices adjacent to the current device, backtrack to another device not adjacent to the current device, and perform a step of performing a hierarchical priority search on the branch to which the other device not adjacent to the current device belongs to obtain a local optimal solution search; The above search process is performed on all known devices in the distributed experimental equipment management and control system to obtain the connection relationship between the various devices in the distributed experimental equipment management and control system.

5. The asset management method based on distributed experimental equipment according to claim 4 is characterized in that: Before performing a depth-first search on the distributed experimental equipment management and control system from the starting device to obtain the connection relationship between the various devices in the distributed experimental equipment management and control system, the method further includes: Obtaining the association weights between the various devices; the association weights are used to measure the degree of task association between the devices; For the current device, sort the devices in the branch to which the current device belongs according to the relevance weight and the level, and build a search queue for the branch to which the current device belongs based on the sorting result; The search queue of the branch to which the current device belongs is used to indicate the search order of each device in the branch to which the current device belongs.

6. The asset management method based on distributed experimental equipment according to claim 5 is characterized in that: After sorting the devices in the branch to which the current device belongs according to the relevance weight and the level, and building the search queue of the branch to which the current device belongs based on the sorting result, the method further includes: Based on historical search behavior data and the real-time operation data of each device in the branch to which the current device belongs, the search queue of the branch to which the current device belongs is predicted through a real-time learning model to obtain the local search probability distribution; Wherein, the local search probability distribution is used to indicate the probability of a local optimal solution search result appearing in each device node in the search queue; Based on the local search probability distribution, redundant paths of each device in the search queue are invalidated, and / or a pruning strategy is executed to screen and delete device nodes whose probability of appearing in local optimal solution search results is lower than a set probability threshold, so as to obtain an optimized search queue for the branch to which the current device belongs.

7. The asset management method based on distributed experimental equipment according to claim 6 is characterized in that: The real-time learning model is expressed as the following formula: Wherein, (P(Y=1|X)) represents the local search probability distribution predicted by the real-time learning model based on the device X in the branch Y to which the current device belongs, x1, x2, ..., x n are the real-time operation data characteristics of each device in branch Y to which the current device belongs, and the historical search behavior data characteristics, β0, β1, ..., β n Indicates the relevance weight corresponding to each feature item.

8. The asset management method based on distributed experimental equipment according to claim 2 is characterized in that: The topology collection layer automatically collects the topology of the distributed experimental equipment management and control system based on the equipment deployment characteristics to obtain the target network structure to be updated or constructed, including: Selecting a starting device as the starting point of a breadth-first search; the starting device is any device in the distributed experimental device management and control system; Starting from the starting device, a global priority search queue is used to traverse all devices connected to the starting device layer by layer until the connection status between the starting device and other connected devices is obtained, and then jump to the adjacent device connected to the starting device; Continue to traverse all devices connected to the neighboring device until the connection status between the neighboring device and other connected devices is obtained, and then jump to the secondary neighboring device connected to the neighboring device; The above traversal process is executed until the search and traversal reaches the outermost device to obtain the global network structure of the distributed experimental equipment management and control system.

9. A distributed experimental equipment management and control system, characterized in that: The distributed experimental equipment management and control system is used to operate and manage experimental equipment, and the experimental equipment includes different types of equipment. The distributed experimental equipment management and control system includes: A monitoring unit, configured to monitor the equipment deployment status in the distributed experimental equipment management and control system; A generating unit is configured to input the equipment deployment situation into an intelligent editing model to perform automatic topology aggregation and task pattern recognition processing to obtain equipment topology editing tasks that match the distributed experimental equipment management and control system; An editing unit, configured to construct or update a device topology network of the distributed experimental device management and control system based on the device topology editing task; A comparison unit configured to perform an asset comparison check on the device topology network and a historical device topology network; The management unit is configured to update the asset management information corresponding to the distributed experimental equipment management and control system based on the asset comparison inspection result.

10. An intelligent computing platform, characterized in that: The intelligent computing platform includes: at least one processor, memory, and input-output unit; In which, the memory is used to store computer programs, the processor is used to call the computer program stored in the memory to execute the asset management method based on distributed experimental equipment as described in any one of claims 1 to 8, and the input and output unit is used to receive user input and display output information of the computer program stored in the memory.

Images