Data management method based on distributed experimental equipment and related equipment

Abstract

The invention belongs to the field of data processing, and particularly relates to a data management method based on distributed experimental equipment and related equipment, and the method comprises the steps: obtaining real-time operation data of a distributed experimental equipment management and control system; performing automatic update packet management processing on the real-time operation data to obtain a plurality of real-time operation data streams corresponding to the real-time operation data; inputting the plurality of real-time operation data streams into an operation state monitoring model for real-time stream data analysis and intelligent management path analysis so as to obtain a plurality of real-time operation data packets; and respectively adding the plurality of real-time operation data packets into different service components so as to complete automatic management of the real-time operation data packets. According to the method, the advantages of real-time data analysis and intelligent management path analysis are combined, the operation efficiency and the management level of the equipment are improved, and the stability and the reliability of the distributed experimental equipment are improved.

Description

Technical Field

[0001] The present application belongs to the field of data processing, and in particular, relates to a data 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, the data generated by distributed experimental equipment often contains various formats and types, and its structure may change dynamically. Traditional systems may be inefficient when processing such diverse and unstructured data, with limited processing capabilities and slow responses, and cannot meet the management of these data, causing difficulties in the management of distributed experimental equipment. For example, distributed experimental equipment may generate data in various formats and types, such as text, images, videos, sensor data, etc. These data may have different structures and semantics, and traditional systems are difficult to process and manage in a unified manner. In addition, the data structure generated by distributed experimental equipment may change dynamically with changes in time, tasks or environment. Traditional systems need to constantly adjust and adapt to these changes, which increases the complexity and maintenance cost of the system.

[0004] Therefore, it is urgent to design a data 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 a data management method and related equipment based on distributed experimental equipment, which combines the advantages of real-time data analysis and intelligent management path analysis, helps to improve the operating efficiency and management level of the equipment, and enhances the stability and reliability of the distributed experimental equipment.

[0006] In a first aspect, the present application provides a data 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 data management method based on distributed experimental equipment includes:

[0007] Acquire the real-time operation data of the distributed experimental equipment management and control system; the real-time operation data at least includes: host information deployed in the system, real-time operation status, equipment operation log information, and real-time port monitoring information;

[0008] Performing automatic update package management processing on the real-time operation data to obtain multiple real-time operation data streams corresponding to the real-time operation data;

[0009] Inputting multiple real-time operation data streams into an operation status monitoring model to perform real-time flow data analysis and intelligent management path analysis to obtain multiple real-time operation data packets;

[0010] Adding the multiple real-time operation data packets to different service components respectively to complete the automatic management of the real-time operation data packets;

[0011] Among them, the multiple real-time operation data packets include at least: a first real-time operation data packet for adding an operation status component, and a second real-time operation data packet for adding a non-operation status component; the non-operation status component includes at least: an audit log component, a file library, a software library, and an experimental parameter signaling library.

[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] An acquisition unit is configured to acquire real-time operation data of the distributed experimental equipment management and control system; the real-time operation data at least includes: host information deployed in the system, real-time operation status, equipment operation log information, and real-time port monitoring information;

[0014] an automatic updating unit, configured to perform automatic updating package management processing on the real-time operation data to obtain a plurality of real-time operation data streams corresponding to the real-time operation data;

[0015] An analysis unit configured to input a plurality of real-time operation data streams into an operation status monitoring model to perform real-time flow data analysis and intelligent management path analysis to obtain a plurality of real-time operation data packets;

[0016] A management unit, configured to add the plurality of real-time operation data packets to different service components respectively, so as to complete the automatic management of the real-time operation data packets;

[0017] Among them, the multiple real-time operation data packets include at least: a first real-time operation data packet for adding an operation status component, and a second real-time operation data packet for adding a non-operation status component; the non-operation status component includes at least: an audit log component, a file library, a software library, and an experimental parameter signaling library.

[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 data management method based on distributed experimental equipment of the first aspect, 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 data 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 real-time operation data of the distributed experimental equipment management and control system is obtained. Among them, the real-time operation data at least includes: host information deployed in the system, real-time operation status, equipment operation log information, and real-time port monitoring information. Then, the real-time operation data is automatically updated package management processing to obtain multiple real-time operation data streams corresponding to the real-time operation data. Then, the multiple real-time operation data streams are input into the operation status monitoring model for real-time flow data analysis and intelligent management path analysis to obtain multiple real-time operation data packets. Finally, the multiple real-time operation data packets are added to different service components respectively to complete the automatic management of the real-time operation data packets. Among them, the multiple real-time operation data packets at least include: a first real-time operation data packet for adding an operation status component, and a second real-time operation data packet for adding a non-operation status component; the non-operation status component at least includes: an audit log component, a file library, a software library, and an experimental parameter signaling library.

[0023] The technical solution of this application can achieve timely acquisition and accurate analysis of real-time operation data of distributed experimental equipment through automatic update package management processing and real-time stream data analysis, so that managers can understand the status and operation of the equipment in a timely manner. The application of the operation status monitoring model makes the management path analysis more intelligent. The model can analyze the changing trend of real-time operation data and historical data, predict possible problems of the equipment, and provide intelligent management suggestions, which helps to improve the stability and reliability of the equipment. By performing intelligent management path analysis on real-time operation data, the optimal configuration of resources can be achieved. According to the suggestions of the model, managers can adjust and optimize different components to improve resource utilization and reduce energy consumption. Allocating real-time operation data packets to different service components can realize the automated management of real-time data. This reduces the workload of managers and improves management efficiency and response speed. Through intelligent analysis of real-time operation data, possible failures and problems of equipment can be discovered in advance, preventive maintenance measures can be implemented, equipment failure rate can be reduced, equipment service life can be extended, and maintenance costs can be saved. The technical solution of this application combines the advantages of real-time data analysis and intelligent management path analysis, which helps to improve the operation efficiency and management level of equipment and enhance the stability and reliability of distributed experimental equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] 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:

[0025] Figure 1 It is a flow chart of a data management method based on distributed experimental equipment according to an embodiment of the present application;

[0026] Figure 2 It is a structural schematic diagram of a distributed experimental equipment control system according to an embodiment of the present application;

[0027] Figure 3 It is a structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] 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.

[0029] 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.

[0030] In order to promote the popularization of intelligent applications in various industries and fields, distributed experimental equipment generates a large amount of data.

[0031] In the related art, the data generated by distributed experimental equipment often contains various formats and types, and its structure may change dynamically. Traditional systems may be inefficient when processing such diverse and unstructured data, with limited processing capabilities and slow responses, and cannot meet the management of these data, causing difficulties in the management of distributed experimental equipment. For example, distributed experimental equipment may generate data in various formats and types, such as text, images, videos, sensor data, etc. These data may have different structures and semantics, and traditional systems are difficult to process and manage in a unified manner. In addition, the data structure generated by distributed experimental equipment may change dynamically with changes in time, tasks or environment. Traditional systems need to constantly adjust and adapt to these changes, which increases the complexity and maintenance cost of the system.

[0032] Therefore, it is urgent to design a data management solution based on distributed experimental equipment to solve at least one of the above technical problems.

[0033] The embodiments of the present application provide a data management method based on distributed experimental equipment and related equipment.

[0034] Specifically, the data management solution 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 solution, first, the real-time operation data of the distributed experimental equipment management and control system is obtained. Among them, the real-time operation data at least includes: host information deployed in the system, real-time operation status, equipment operation log information, and real-time port monitoring information. Then, the real-time operation data is automatically updated and managed to obtain multiple real-time operation data streams corresponding to the real-time operation data. Then, the multiple real-time operation data streams are input into the operation status monitoring model for real-time flow data analysis and intelligent management path analysis to obtain multiple real-time operation data packets. Finally, the multiple real-time operation data packets are respectively added to different service components to complete the automatic management of the real-time operation data packets. Among them, the multiple real-time operation data packets include at least:

[0035] A first real-time operation data packet is used to add a running state component, and a second real-time operation data packet is used to add a non-running state component; the non-running state component at least includes: an audit log component, a file library, a software library, and an experimental parameter signaling library.

[0036] In the data management scheme based on distributed experimental equipment, the real-time operation data of distributed experimental equipment can be obtained and accurately analyzed in time through automatic update package management processing and real-time stream data analysis, so that managers can understand the status and operation of the equipment in time. The application of the operation status monitoring model makes the management path analysis more intelligent. The model can analyze the changing trend of real-time operation data and historical data, predict possible problems of the equipment, and provide intelligent management suggestions, which helps to improve the stability and reliability of the equipment. By performing intelligent management path analysis on real-time operation data, the optimal configuration of resources can be achieved. According to the suggestions of the model, managers can adjust and optimize different components to improve resource utilization and reduce energy consumption. Allocating real-time operation data packets to different service components can realize the automatic management of real-time data. This reduces the workload of managers and improves management efficiency and response speed. Through intelligent analysis of real-time operation data, possible failures and problems of equipment can be discovered in advance, preventive maintenance measures can be implemented, equipment failure rate can be reduced, equipment service life can be extended, and maintenance costs can be saved. This data management scheme combines the advantages of real-time data analysis and intelligent management path analysis, which helps to improve the operation efficiency and management level of equipment and enhance the stability and reliability of distributed experimental equipment.

[0037] The data management scheme based on distributed experimental equipment provided in the embodiment of the present application can also be performed 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 a data management system based on distributed experimental equipment). The chip introduced in the above embodiment can also be carried in these electronic devices. Alternatively, these electronic devices can also be installed with a service program for executing a data management scheme based on distributed experimental equipment.

[0038] In the embodiment of the present application, the distributed experimental equipment management and control system is mainly responsible for the storage of various relevant data such as input data, calculation results, observation data, visualization data, etc. of the advanced computing platform. These data may come from different applications and need to be uniformly managed and stored for subsequent analysis and processing.

[0039] Figure 1 A schematic diagram of a data management method based on distributed experimental equipment provided in an embodiment of the present application is shown in FIG. Figure 1, the method comprises the following steps:

[0040] 101, obtaining real-time operation data of the distributed experimental equipment management and control system.

[0041] 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.

[0042] Further optionally, the real-time operation data includes at least: host information deployed in the system, real-time operation status, device operation log information, and real-time port monitoring information.

[0043] In the embodiment of the present application, the data 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:

[0044] 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.

[0045] 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.

[0046] 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.

[0047] 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.

[0048] 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.

[0049] 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, device management, information management, test parameter management, file management, software management, and remote control. The client realizes the interaction between users and the system and data management through communication with the server.

[0050] In summary, the data management method based on the distributed test equipment safety management and control system combines the C / S architecture, microservice architecture and QT development technology, realizes the real-time management and intelligent control of distributed test equipment, and provides strong support for the safety, stability and reliability of the test equipment.

[0051] 102 , perform automatic update package management processing on the real-time operation data to obtain a plurality of real-time operation data streams corresponding to the real-time operation data.

[0052] Specifically, the automatic update package management and processing of real-time operation data refers to the real-time update and management of real-time generated data to ensure the timeliness and accuracy of the data. First, it is necessary to collect real-time operation data through distributed experimental equipment or sensors and other equipment. These data may include sensor data, equipment status information, production indicators, etc. Then, the collected real-time data needs to be preprocessed and cleaned, including data format conversion, noise removal, outlier processing, etc., to ensure data quality and accuracy. According to the changes and updates of real-time operation data, the system will automatically generate update packages, which contain the latest data content and change information. The process of managing update packages includes operations such as storage, indexing, and version management of update packages for subsequent data processing and access. According to the generated update packages, the system will process the real-time operation data to obtain multiple real-time operation data streams. These data streams may include original data streams, cleaned data streams, aggregated data streams, etc., for different application scenarios and analysis purposes. Finally, the processed real-time operation data streams can be distributed to different data storage or analysis systems for subsequent data analysis, monitoring, and decision-making.

[0053] Through the automatic update package management and processing of real-time running data, dynamic management and processing of real-time data can be achieved, ensuring the real-time and accuracy of data, and providing an effective solution for data management of distributed experimental equipment.

[0054] 103 , input the multiple real-time operation data streams into the operation status monitoring model to perform real-time flow data analysis and intelligent management path analysis to obtain multiple real-time operation data packets.

[0055] In the embodiment of the present application, the multiple real-time operation data packets include a first real-time operation data packet for adding an operation state component and a second real-time operation data packet for adding a non-operation state component. At the same time, the non-operation state component at least includes an audit log component, a file library, a software library, and an experimental parameter signaling library. The following examples will introduce the roles and functions of these components:

[0056] The first real-time operation data packet (used to add the operation status component), the operation status component refers to the data associated with the current operation status of the device, such as the operation time, working status, temperature, pressure, etc. of the device. The first real-time operation data packet may include these key operation status parameters, which are used to monitor the operation status of the device in real time and make corresponding management and control.

[0057] For example, the first real-time operation data packet may include the real-time working status of each distributed experimental device, such as the online / offline status of the device, the operating time, the current working mode and other information.

[0058] The second real-time operation data packet (used to add non-operation status components), the non-operation status components include data that are not directly related to the device operation status but are of great significance to the device management and operation, such as audit logs, file libraries, software libraries, experimental parameter signaling libraries, etc.

[0059] For example, the audit log component records the operation history, event records and other information of the device for troubleshooting, security auditing and other purposes. The file library stores documents, manuals, reports and other files related to the device for users to access and use. The software library contains the software programs and drivers required by the device for the control, operation and management of the device. The experimental parameter signaling library stores the experimental parameters, signal commands and other information of the device for the configuration and control of the device.

[0060] The combination of these real-time running data packets and non-running state components can provide comprehensive equipment management and monitoring functions, while meeting users' different needs for equipment running status and management. By comprehensively utilizing these data packets and components, effective management and optimized operation of distributed experimental equipment can be achieved.

[0061] In the embodiment of the present application, the operation status monitoring model is a model specially designed for real-time stream data analysis and intelligent management path analysis. The operation status monitoring model is mainly used to monitor the operation status of distributed experimental equipment, analyze real-time operation data streams, and provide intelligent management path analysis to obtain key operation indicators and information. In an optional example, the operation status monitoring model generally includes the following main components:

[0062] Data receiving and processing module: responsible for receiving and preprocessing data obtained from multiple real-time running data streams, including data cleaning, format conversion, removal of outliers and other operations to ensure data quality and accuracy.

[0063] Real-time data analysis module: Use various data analysis algorithms and technologies to analyze real-time operation data in real time and extract key operation indicators and performance parameters, such as equipment status, fault prediction, production efficiency, etc.

[0064] Intelligent management path analysis module: Based on real-time analysis results, it performs intelligent path analysis to identify optimized operation paths and management strategies to improve the operating efficiency and reliability of equipment.

[0065] Result display and reporting module: displays analysis results and intelligent management paths to users or system administrators, provides intuitive data visualization interface and detailed reports, and helps users understand the operating status and performance of the equipment.

[0066] In this example, the operation status monitoring model is designed to monitor the operation status of distributed experimental equipment in real time. By analyzing multiple real-time operation data streams, it provides intelligent management path analysis to help users optimize the operation management of equipment and improve the operation efficiency and reliability of equipment. This model integrates advanced technologies such as data analysis, machine learning, and intelligent optimization, providing powerful real-time monitoring and management capabilities for distributed experimental equipment.

[0067] As an optional embodiment, in 103, multiple real-time operation data streams are input into the operation status monitoring model to perform real-time flow data analysis and intelligent management path analysis to obtain multiple real-time operation data packets, which can be implemented as follows:

[0068] 201, converting the preprocessed multiple real-time running data streams into time series data to obtain multiple real-time running data sequences;

[0069] 202, inputting a plurality of real-time operation data sequences into the multi-input interface module of the operation status monitoring model respectively, and distributing them to the corresponding branch path analysis modules for real-time data analysis and processing, so as to obtain a plurality of real-time data prediction results;

[0070] 203 , based on the multiple real-time data prediction results, intelligently packetize the real-time operation data sequences containing different types of real-time operation data to obtain corresponding real-time operation data packets.

[0071] In step 201, first, multiple real-time running data streams are preprocessed, including missing value filling, outlier correction, data normalization and other operations to ensure data quality and consistency. Then, the preprocessed multiple real-time running data streams are converted into time series data. For example, the data collected by different sensors are organized into a time series in chronological order, and each time point corresponds to a data record.

[0072] In step 202, multiple real-time operation data sequences are respectively input into the multi-input interface module of the operation status monitoring model. These data may include various operation parameters of the equipment, such as temperature, pressure, humidity, etc. In the multi-input interface module, each data sequence is assigned to a corresponding branch path analysis module for real-time data analysis and processing. These branch path analysis modules may be specially designed and optimized for different types of data.

[0073] In step 203, based on multiple real-time data prediction results, the real-time operation data sequence containing different types of real-time operation data is intelligently sub-packaged. This means that according to the prediction results, the data in the data sequence is divided into different groups to form corresponding real-time operation data packets. The sub-package processing may be optimized according to the relevance, importance or business needs of the data. For example, data related to temperature, humidity, etc. are combined into one real-time operation data packet, and data related to pressure, flow, etc. are combined into another real-time operation data packet.

[0074] For example, suppose there is an industrial production line that needs to monitor multiple real-time operating data such as temperature, humidity, and pressure. In step 201, the data collected by each sensor is converted into time series data to ensure the continuity and analyzability of the data. In step 202, these time series data are input into the operation status monitoring model for real-time data analysis, such as predicting the status of the production line, detecting abnormal conditions, etc. In step 203, according to the prediction results of the model, different types of data are intelligently packaged and processed, such as combining temperature and humidity data into a real-time operation data packet, and combining pressure data into a real-time operation data packet. In this way, by converting the data into a time series and performing package processing according to the prediction results of the model, the data can be better utilized and redundant information can be reduced. According to the analysis results of the model, the data is intelligently packaged so that each data packet contains data with certain correlations, which is convenient for subsequent management and analysis. The real-time and accuracy of production line monitoring are enhanced: through real-time data analysis and intelligent package processing, abnormal conditions of the production line can be discovered and responded to in a timely manner, thereby improving the operating efficiency and safety of the production line.

[0075] Further optionally, in 202, the multiple real-time operation data sequences are respectively input into the multi-input interface module of the operation status monitoring model, and are assigned to the corresponding branch path analysis modules for real-time data analysis and processing to obtain multiple real-time data prediction results, which can be implemented as the following steps:

[0076] 301, receiving a real-time operation data sequence routed to a branch path analysis module through each input interface module;

[0077] 302, for each real-time operation data sequence, divide it according to the time window size to obtain a corresponding real-time operation data time series;

[0078] 303, according to each time window in the real-time operation data time series, learning the time dependency relationship of the data points in each time window, and predicting the real-time operation status corresponding to the data points in each time window;

[0079] 304 , outputting the real-time operation status corresponding to the data points in each time window as the discrete state prediction label corresponding to each real-time operation data sequence.

[0080] Further optionally, in 203, based on multiple real-time data prediction results, intelligent packet processing is performed on the real-time operation data sequence containing different types of real-time operation data to obtain respective corresponding real-time operation data packets, which can be implemented as the following steps:

[0081] 305, obtaining the path allocation identifier contained in each discrete state prediction label corresponding to each real-time operation data sequence;

[0082] 306, routing corresponding real-time operation data sequences to corresponding intelligent management paths based on the path allocation identifiers;

[0083] 307 , through the real-time management strategy dynamically set in each intelligent management path, each real-time operation data sequence is intelligently packaged to obtain the corresponding real-time operation data packets.

[0084] In an embodiment of the present application, the discrete state prediction labels corresponding to each real-time operation data sequence include at least one of the following: path allocation identification, data type, equipment operation status, and data source information corresponding to each real-time operation data sequence. For example, suppose there is an industrial production system that includes multiple sensors to monitor parameters such as temperature, humidity, and pressure. For this system, real-time data analysis and intelligent management path analysis can be performed, in which each real-time operation data sequence corresponds to a different discrete state prediction label, including at least one of the following:

[0085] Path allocation identification, which identifies which intelligent management path the data sequence should be assigned to for processing. For example, if the data sequence comes from a specific production line or equipment, the path allocation identification can indicate that it should be assigned to the corresponding production line management path. Data type, which identifies the type of data contained in the data sequence. For example, different types of data such as temperature data, humidity data, and pressure data can be distinguished. Equipment operating status, which identifies the operating status of the equipment corresponding to the data sequence. For example, the normal operation of the equipment, abnormal status, or a status that requires maintenance, etc. Data source information, which identifies the source information of the data sequence, including the location of the sensor, the time of data collection, etc. For example, you can record which sensor the data comes from and the time information of data collection. Taking these tags into consideration, you can better understand and manage real-time operating data, which helps to detect problems in a timely manner, optimize the production process, and improve the efficiency and reliability of the system.

[0086] In step 301, the real-time operation data sequence in the branch path analysis module is routed to each input interface module to ensure that the data can be processed and analyzed according to the predefined branch path. In step 302, each real-time operation data sequence is divided according to the time window size to obtain the corresponding real-time operation data time series. This helps to divide the data into smaller time periods, which is convenient for learning and predicting time dependencies. In step 303, the time dependencies of the data points in each time window in the real-time operation data time series are learned, and the real-time operation status corresponding to the data points in each time window is predicted. This helps to understand the time correlation between data and improve the accuracy of state prediction. In step 304, the real-time operation status corresponding to the data points in each time window is output as the discrete state prediction label corresponding to each real-time operation data sequence. These labels may include path allocation identifiers, data types, equipment operation status, data source information, etc. In step 305, the path allocation identifiers contained in each discrete state prediction label corresponding to each real-time operation data sequence are obtained. The path allocation identifier can indicate which intelligent management path the data should be assigned to for processing. In step 306, based on the identifiers assigned to each path, the corresponding real-time operation data sequence is routed to the corresponding intelligent management path. This ensures that different types of data can be sent to the corresponding management path for special processing and management. In step 307, through the real-time management strategy dynamically set in each intelligent management path, each real-time operation data sequence is intelligently packaged to obtain the corresponding real-time operation data packets. This helps to adopt appropriate processing strategies according to the characteristics and requirements of real-time data and improve the efficiency and quality of data processing.

[0087] In this way, by allocating paths and selecting intelligent management paths based on the prediction results of real-time data, personalized processing can be performed according to the characteristics and needs of the data, improving the intelligence and adaptability of data processing. By intelligently subpackaging real-time data, data can be classified and processed according to different management paths, which improves the efficiency of data management and analysis in a targeted manner. By learning and predicting the time dependency of data, the correlation and change rules between data can be understood more accurately, thereby improving the accuracy of data processing and state prediction.

[0088] 104 , respectively adding the multiple real-time operation data packets to different service components to complete automatic management of the real-time operation data packets.

[0089] As an optional embodiment, in 104, before inputting multiple real-time operation data streams into the operation status monitoring model for real-time flow data analysis and intelligent management path analysis to obtain multiple real-time operation data packets, it is also possible to detect whether the multiple real-time operation data streams meet the data availability conditions.

[0090] If the data availability condition is not met, at least one of the following preprocessing operations is performed on the corresponding data of the multiple real-time running data streams: locating data segments with missing data in the multiple real-time running data streams, and filling missing values ​​in the located data segments; or deleting the located data segments; locating data segments with outliers in the multiple real-time running data streams, and performing context learning on the located data segments; correcting the outliers based on the learning results; deleting duplicate records in the multiple real-time running data streams; and performing data normalization on the multiple real-time running data streams to obtain multiple real-time running data streams at a unified scale.

[0091] In 104, data availability conditions refer to the fact that multiple real-time running data streams must meet certain quality and integrity standards to ensure their reliability and effectiveness. Specifically, data availability conditions may include the following aspects:

[0092] Data integrity: The data in the data stream should be complete, without any missing or omissions. If there is missing data or missing data fragments in the data stream, these missing data need to be processed to ensure that subsequent analysis and management can be based on complete data.

[0093] Data accuracy: The data in the data stream should be accurate, without outliers or errors. If there are outliers or abnormal data fragments in the data stream, these abnormal data need to be identified and corrected to ensure the reliability and accuracy of subsequent analysis and management results.

[0094] Data consistency: Data in a data stream should have a consistent format and scale to facilitate unified processing and analysis. If there are inconsistent data formats or scales in the data stream, then the data needs to be normalized so that subsequent data analysis and management can be based on unified data standards.

[0095] In summary, data availability conditions require that multiple real-time data streams must be complete, accurate, and consistent to ensure data reliability and validity. If the data stream does not meet these conditions, it is necessary to perform corresponding preprocessing operations, such as filling missing values, correcting outliers, deleting duplicate records, or performing data normalization to ensure that the data meets availability conditions before subsequent analysis and management.

[0096] As an optional embodiment, in 104, after multiple real-time operation data streams are input into the operation status monitoring model for real-time flow data analysis and intelligent management path analysis to obtain multiple real-time operation data packets, the real-time performance indicator parameters of the operation status monitoring model can also be monitored and stored in the monitoring database; the change trend of the real-time performance indicator parameters is predicted to obtain change trend information; based on the change trend information, it is identified whether there is room for improvement or potential risks in the operation status monitoring model, and the model parameters and data processing flow in the operation status monitoring model are dynamically adjusted according to the identification results.

[0097] In this optional embodiment, by monitoring the real-time performance indicator parameters of the running state monitoring model and predicting and analyzing the change trend of these parameters, dynamic optimization and improvement of the model performance can be achieved. First, key real-time performance indicator parameters are obtained from the running state monitoring model, which may include data processing delay, analysis speed, accuracy index, etc. These parameters can reflect the real-time running state and effect of the model. The acquired real-time performance indicator parameters are stored in the monitoring database for subsequent data analysis and processing. The monitoring database can be used to persistently store these parameters and support subsequent trend analysis and model optimization. Using the historical performance indicator data in the monitoring database, time series analysis or machine learning models are applied to predict the change trend of these performance indicators. This helps to identify potential changes and trends in model performance. Based on the change trend information, identify the improvement space or potential risks that may exist in the running state monitoring model. For example, if the performance indicator shows a trend of deterioration, it may be necessary to further investigate and optimize certain aspects of the model. According to the identified improvement space or potential risks, the model parameters and data processing flow in the running state monitoring model are dynamically adjusted. This may include adjusting data preprocessing steps, updating analysis algorithms, optimizing model parameters, and other measures to improve the performance and adaptability of the model.

[0098] Through this process, the operation status monitoring model can achieve self-optimization and dynamic adjustment, maintaining efficient monitoring and management capabilities for the operation status of distributed experimental equipment. Continuous monitoring and improvement of performance indicators enable the system to respond to changes and optimization needs in a timely manner, and improve the intelligence level and efficiency of equipment management.

[0099] In the embodiment of the present application, through automatic update package management processing and real-time stream data analysis, timely acquisition and accurate analysis of real-time operation data of distributed experimental equipment can be achieved, so that managers can understand the status and operation of the equipment in a timely manner. The application of the operation status monitoring model makes the management path analysis more intelligent. The model can analyze the changing trend of real-time operation data and historical data, predict possible problems of the equipment, and provide intelligent management suggestions, which helps to improve the stability and reliability of the equipment. By performing intelligent management path analysis on real-time operation data, optimal configuration of resources can be achieved. According to the suggestions of the model, managers can adjust and optimize different components to improve resource utilization and reduce energy consumption. Allocating real-time operation data packets to different service components can realize the automated management of real-time data. This reduces the workload of managers and improves management efficiency and response speed. Through intelligent analysis of real-time operation data, possible faults and problems of equipment can be discovered in advance, preventive maintenance measures can be implemented, equipment failure rate can be reduced, the service life of equipment can be extended, and maintenance costs can be saved. In the embodiment of this application, the advantages of real-time data analysis and intelligent management path analysis are combined, which helps to improve the operation efficiency and management level of equipment and enhance the stability and reliability of distributed experimental equipment.

[0100] In another embodiment of the present application, a distributed experimental equipment management and control system is provided, wherein the distributed experimental equipment management and control system is used to operate and manage experimental equipment, wherein the experimental equipment includes different types of equipment, see Figure 3 The distributed experimental equipment management and control system includes the following units:

[0101] An acquisition unit is configured to acquire real-time operation data of the distributed experimental equipment management and control system; the real-time operation data at least includes: host information deployed in the system, real-time operation status, equipment operation log information, and real-time port monitoring information;

[0102] an automatic updating unit, configured to perform automatic updating package management processing on the real-time operation data to obtain a plurality of real-time operation data streams corresponding to the real-time operation data;

[0103] An analysis unit configured to input a plurality of real-time operation data streams into an operation status monitoring model to perform real-time flow data analysis and intelligent management path analysis to obtain a plurality of real-time operation data packets;

[0104] A management unit, configured to add the plurality of real-time operation data packets to different service components respectively, so as to complete the automatic management of the real-time operation data packets;

[0105] Among them, the multiple real-time operation data packets include at least: a first real-time operation data packet for adding an operation status component, and a second real-time operation data packet for adding a non-operation status component; the non-operation status component includes at least: an audit log component, a file library, a software library, and an experimental parameter signaling library.

[0106] Further optionally, the analysis unit inputs the multiple real-time operation data streams into the operation status monitoring model to perform real-time flow data analysis and intelligent management path analysis to obtain multiple real-time operation data packets, and is configured as follows:

[0107] Convert the preprocessed multiple real-time running data streams into time series data to obtain multiple real-time running data sequences;

[0108] Inputting multiple real-time operation data sequences into the multi-input interface module of the operation status monitoring model respectively, and distributing them to the corresponding branch path analysis modules for real-time data analysis and processing, so as to obtain multiple real-time data prediction results;

[0109] Based on multiple real-time data prediction results, the real-time operation data sequences containing different types of real-time operation data are intelligently packetized to obtain corresponding real-time operation data packets.

[0110] Further optionally, the analysis unit inputs a plurality of real-time operation data sequences into the multi-input interface module of the operation status monitoring model respectively, and distributes them to the corresponding branch path analysis modules for real-time data analysis and processing to obtain a plurality of real-time data prediction results, and is configured as follows:

[0111] receiving a real-time running data sequence routed to the branch path analysis module through each input interface module;

[0112] For each real-time operation data series, divide it according to the time window size to obtain the corresponding real-time operation data time series;

[0113] According to each time window in the real-time operation data time series, the time dependency relationship of the data points in each time window is learned, and the real-time operation status corresponding to the data points in each time window is predicted;

[0114] The real-time operating status corresponding to the data points in each time window is output as the discrete state prediction label corresponding to each real-time operating data sequence.

[0115] Further optionally, the discrete state prediction label corresponding to each real-time operation data sequence includes at least one of the following: a path allocation identifier, a data type, a device operation status, and data source information corresponding to each real-time operation data sequence.

[0116] Further optionally, the analysis unit performs intelligent packet processing on the real-time operation data sequence containing different types of real-time operation data based on the multiple real-time data prediction results to obtain respective corresponding real-time operation data packets, and is configured as follows:

[0117] Obtain the path allocation identifiers contained in each of the discrete state prediction labels corresponding to each real-time operation data sequence;

[0118] Based on each path allocation identifier, each corresponding real-time operation data sequence is routed to the corresponding intelligent management path;

[0119] Through the real-time management strategies dynamically set in each intelligent management path, each real-time operation data sequence is intelligently packetized to obtain the corresponding real-time operation data packets.

[0120] Further optionally, before the analysis unit inputs the multiple real-time operation data streams into the operation status monitoring model to perform real-time flow data analysis and intelligent management path analysis to obtain multiple real-time operation data packets, it is further configured to:

[0121] Check whether multiple real-time running data streams meet data availability conditions;

[0122] If the data availability condition is not met, at least one of the following preprocessing operations is performed on the corresponding data of the multiple real-time running data streams:

[0123] Locate data segments with missing data in multiple real-time running data streams, and perform missing value filling processing on the located data segments; or, delete the located data segments;

[0124] Locate data segments with outliers in multiple real-time running data streams, and perform context learning on the located data segments; correct the outliers based on the learning results;

[0125] Delete duplicate records in multiple real-time running data streams;

[0126] The multiple real-time running data streams are normalized to obtain multiple real-time running data streams at a unified scale.

[0127] Optionally, the system further includes a monitoring unit configured to: the analysis unit inputs a plurality of real-time operation data streams into the operation status monitoring model to perform real-time flow data analysis and intelligent management path analysis, so as to obtain a plurality of real-time operation data packets, monitor the real-time performance indicator parameters of the operation status monitoring model, and store them in the monitoring database;

[0128] Predicting the change trend of the real-time performance indicator parameter to obtain change trend information;

[0129] Based on the change trend information, it is identified whether there is room for improvement or potential risks in the operation status monitoring model, and the model parameters and data processing flow in the operation status monitoring model are dynamically adjusted according to the identification results.

[0130] Further optionally, the management unit adds the multiple real-time operation data packets to different service components respectively to complete the automatic management of the real-time operation data packets, and is configured to:

[0131] transmitting a second real-time operation data packet containing device operation log information to an audit log component in a data storage service;

[0132] After the multiple real-time operation data packets are added to different service components respectively to complete the automatic management of the real-time operation data packets, the method further includes:

[0133] Extracting log operation features of device operation log information from the audit log component;

[0134] The log operation characteristics are input into the real-time log analysis model to perform intelligent audit services to obtain audit warning information to be processed, which is used to trigger the corresponding automated management process.

[0135] In the embodiment of the present application, the advantages of real-time data analysis and intelligent management path analysis are combined, which helps to improve the operating efficiency and management level of the equipment and enhance the stability and reliability of distributed experimental equipment.

[0136] In another embodiment of the present application, an intelligent computing platform is also 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;

[0137] Memory, used to store computer programs;

[0138] The processor is used to implement the data management method based on distributed experimental equipment described in the method embodiment when executing the program stored in the memory.

[0139] 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.

[0140] The embodiment of the present application provides a data management method based on distributed experimental equipment for constructing a low-energy consumption operator.

[0141] 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.

[0142] The communication interface 1120 is used for communication between the above electronic device and other devices.

[0143] 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.

[0144] 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.

[0145] 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.

Claims

1. A data 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, the experimental equipment includes different types of equipment; The data management method based on distributed experimental equipment includes: Acquire the real-time operation data of the distributed experimental equipment management and control system; the real-time operation data at least includes: host information deployed in the system, real-time operation status, equipment operation log information, and real-time port monitoring information; Performing automatic update package management processing on the real-time operation data to obtain multiple real-time operation data streams corresponding to the real-time operation data; Inputting multiple real-time operation data streams into an operation status monitoring model to perform real-time flow data analysis and intelligent management path analysis to obtain multiple real-time operation data packets; Adding the multiple real-time operation data packets to different service components respectively to complete the automatic management of the real-time operation data packets; Among them, the multiple real-time operation data packets include at least: a first real-time operation data packet for adding an operation status component, and a second real-time operation data packet for adding a non-operation status component; the non-operation status component includes at least: an audit log component, a file library, a software library, and an experimental parameter signaling library.

2. The data management method based on distributed experimental equipment according to claim 1 is characterized in that: The step of inputting a plurality of real-time operation data streams into the operation status monitoring model to perform real-time flow data analysis and intelligent management path analysis to obtain a plurality of real-time operation data packets includes: Convert the preprocessed multiple real-time running data streams into time series data to obtain multiple real-time running data sequences; Inputting multiple real-time operation data sequences into the multi-input interface module of the operation status monitoring model respectively, and distributing them to the corresponding branch path analysis modules for real-time data analysis and processing, so as to obtain multiple real-time data prediction results; Based on multiple real-time data prediction results, the real-time operation data sequences containing different types of real-time operation data are intelligently packetized to obtain corresponding real-time operation data packets.

3. The data management method based on distributed experimental equipment according to claim 2 is characterized in that: The multiple real-time operation data sequences are respectively input into the multi-input interface module of the operation status monitoring model, and are distributed to the corresponding branch path analysis modules for real-time data analysis and processing to obtain multiple real-time data prediction results, including: receiving a real-time running data sequence routed to the branch path analysis module through each input interface module; For each real-time operation data series, divide it according to the time window size to obtain the corresponding real-time operation data time series; According to each time window in the real-time operation data time series, the time dependency relationship of the data points in each time window is learned, and the real-time operation status corresponding to the data points in each time window is predicted; The real-time operating status corresponding to the data points in each time window is output as the discrete state prediction label corresponding to each real-time operating data sequence.

4. The data management method based on distributed experimental equipment according to claim 3 is characterized in that: The discrete state prediction labels corresponding to each real-time operation data sequence include at least one of the following: a path allocation identifier, a data type, a device operation status, and data source information corresponding to each real-time operation data sequence.

5. The data management method based on distributed experimental equipment according to claim 4 is characterized in that: Based on the multiple real-time data prediction results, the real-time operation data sequences containing different types of real-time operation data are intelligently packaged to obtain respective corresponding real-time operation data packets, including: Obtain the path allocation identifiers contained in each of the discrete state prediction labels corresponding to each real-time operation data sequence; Based on each path allocation identifier, each corresponding real-time operation data sequence is routed to the corresponding intelligent management path; Through the real-time management strategies dynamically set in each intelligent management path, each real-time operation data sequence is intelligently packetized to obtain the corresponding real-time operation data packets.

6. The data management method based on distributed experimental equipment according to claim 2 is characterized in that: Before inputting the plurality of real-time operation data streams into the operation status monitoring model to perform real-time flow data analysis and intelligent management path analysis to obtain the plurality of real-time operation data packets, the method further includes: Check whether multiple real-time running data streams meet data availability conditions; If the data availability condition is not met, at least one of the following preprocessing operations is performed on the corresponding data of the multiple real-time running data streams: Locate data segments with missing data in multiple real-time running data streams, and perform missing value filling processing on the located data segments; or, delete the located data segments; Locate data segments with outliers in multiple real-time running data streams, and perform context learning on the located data segments; correct the outliers based on the learning results; Delete duplicate records in multiple real-time running data streams; The multiple real-time running data streams are normalized to obtain multiple real-time running data streams at a unified scale.

7. The data management method based on distributed experimental equipment according to claim 1 is characterized in that: After inputting the multiple real-time operation data streams into the operation status monitoring model to perform real-time flow data analysis and intelligent management path analysis to obtain multiple real-time operation data packets, the method further includes: Monitor the real-time performance indicator parameters of the running status monitoring model and store them in the monitoring database; Predicting the change trend of the real-time performance indicator parameter to obtain change trend information; Based on the change trend information, it is identified whether there is room for improvement or potential risks in the operation status monitoring model, and the model parameters and data processing flow in the operation status monitoring model are dynamically adjusted according to the identification results.

8. The data management method based on distributed experimental equipment according to claim 1 is characterized in that: The step of adding the plurality of real-time operation data packets to different service components respectively to complete the automatic management of the real-time operation data packets includes: transmitting a second real-time operation data packet containing device operation log information to an audit log component in a data storage service; After the multiple real-time operation data packets are added to different service components respectively to complete the automatic management of the real-time operation data packets, the method further includes: Extracting log operation features of device operation log information from the audit log component; The log operation characteristics are input into the real-time log analysis model to perform intelligent audit services to obtain audit warning information to be processed, which is used to trigger the corresponding automated management process.

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: An acquisition unit is configured to acquire real-time operation data of the distributed experimental equipment management and control system; the real-time operation data at least includes: host information deployed in the system, real-time operation status, equipment operation log information, and real-time port monitoring information; an automatic updating unit, configured to perform automatic updating package management processing on the real-time operation data to obtain a plurality of real-time operation data streams corresponding to the real-time operation data; An analysis unit configured to input a plurality of real-time operation data streams into an operation status monitoring model to perform real-time flow data analysis and intelligent management path analysis to obtain a plurality of real-time operation data packets; A management unit, configured to add the plurality of real-time operation data packets to different service components respectively, so as to complete the automatic management of the real-time operation data packets; Among them, the multiple real-time operation data packets include at least: a first real-time operation data packet for adding an operation status component, and a second real-time operation data packet for adding a non-operation status component; the non-operation status component includes at least: an audit log component, a file library, a software library, and an experimental parameter signaling library.

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 data 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