Operation and maintenance factory visualization system based on data processing

Abstract

The invention relates to an operation and maintenance factory visualization system based on data processing, belongs to the field of data processing specially suitable for administrative, commercial, financial, management, supervision or prediction purposes, and particularly relates to the field of big data processing. Based on data processing and artificial intelligence technologies, the operation and maintenance factory visualization system is developed, intelligent analysis and prediction are carried out by collecting and analyzing the IT equipment of the IDC machine room and mass operation and maintenance data of applications in real time and utilizing an AI algorithm realized based on an intelligent analysis and prediction model, and the operation and maintenance efficiency is improved. The equipment fault information and the application fault information of the set IDC machine room in the next time segment of the current time segment are obtained, so that the equipment fault information and the application fault information are synchronously displayed when the IDC machine room operation and maintenance system carries out transparent factory type assembly line visual display on various operation and maintenance works of the set IDC machine room on a visual interface. Therefore, operation and maintenance personnel are helped to master and set the running state of the IDC machine room in time.

Description

TECHNICAL FIELD

[0001] The data processing for administrative, commercial, financial, management, supervision or prediction purposes of the present application relates to big data processing, and particularly relates to an operation and maintenance factory visualization system based on data processing. BACKGROUND

[0002] Internet Data Center (IDC) refers to a kind of perfect equipment (including high-speed Internet access bandwidth, high-performance local area network, safe and reliable computer room environment, etc.), professional management, perfect application service platform, its operation and monitoring are based on big data processing. On the basis of this platform, the IDC service provider provides Internet basic platform services (server hosting, virtual host, mail cache, virtual mail, etc.) and various value-added services (site rental services, domain name system services, load balancing system, database system, data backup services, etc.) for customers. As the main body of IDC operation, the progress of each operation work of IDC computer room is the focus and focus of people's attention.

[0003] For example, Chinese invention patent publication CN119782006A proposes a device operation and maintenance monitoring method, device, medium and electronic equipment for IDC machine room, which includes: obtaining original messages from a target time series database, the original messages being generated by the target time series database according to target time series database stored device related index data, the device related index data including original index data corresponding to original indexes and / or statistical index data corresponding to statistical indexes calculated from multiple original index data; generating target messages of a target topic according to the original messages, and sending the target messages to a message queue corresponding to the target topic in a message bus, so that the message bus determines each subscription end corresponding to the target topic according to stored subscription information, and pushes the target messages to each subscription end corresponding to the target topic, the message bus including a message queue corresponding to at least one topic. This application can be applied to the digital twin scene, and can realize efficient and accurate monitoring of the equipment in the IDC machine room. For example, Chinese invention patent publication CN117010665A proposes a smart operation and maintenance IDC machine room management system in the technical field of machine room management, which includes a master control center and the following modules: real-time monitoring and alarm module: the real-time monitoring and alarm module uses advanced monitoring equipment and sensors, and combines intelligent algorithms to realize real-time monitoring and anomaly detection of important parameters inside the IDC machine room; resource allocation and optimization module: the resource allocation and optimization module is committed to maximizing the use of resources in the IDC machine room. The beneficial effects of the present application are: real-time monitoring and alarm function, which can timely discover and solve machine room faults, and improve the reliability of the machine room; resource allocation and optimization based on big data analysis and machine learning algorithms, which can improve resource utilization and reduce operation and maintenance costs; remote maintenance and operation function, which improves the work efficiency and operation convenience of operation and maintenance personnel; data analysis and visualization function, which helps operation and maintenance personnel better understand the specific data and operation of the machine room.

[0004] As can be seen, the various technical solutions in the above-mentioned prior art are only limited to analyzing the current operation and maintenance data of the IDC machine room to obtain the current operation and maintenance state of the IDC machine room, lacking an intelligent prediction mechanism for device fault information and application fault information of the IDC machine room in future time segments, resulting in the inability to provide reference basis for fault response strategies of the IDC machine room in future time segments, reducing the system performance and fault response speed of the IDC machine room, and delaying the decision efficiency of the operation and maintenance system. At the same time, lacking a synchronous display mechanism for the operation and maintenance state of the future time segment and the current time segment, when the IDC machine room operation and maintenance system displays the set IDC machine room operation work in a transparent factory type pipeline visual display on the visual interface, it cannot visually customize the visual display of the operation and maintenance state of the future time segment and the current time segment, increasing the work burden of the operation and maintenance personnel. SUMMARY

[0005] In order to solve the technical problems in the prior art, the application provides an operation and maintenance factory visualization system based on data processing, which develops an operation and maintenance factory visualization system on the basis of customizing a structural design intelligent analysis and prediction model for a set IDC machine room and targeted screening of various basic data for intelligent analysis and prediction, the system realizes intelligent analysis and prediction by using an AI algorithm realized by the intelligent analysis and prediction model, completes intelligent prediction of equipment fault information and application fault information of the set IDC machine room in future time segments, thereby providing a reference basis for fault response strategies of the set IDC machine room in future time segments, accelerating the reaction speed of system performance and fault conditions of the IDC machine room, improving the decision-making efficiency of the operation and maintenance system, and simultaneously fusing a synchronous display mechanism of operation and maintenance states of future time segments and current time segments, so that the IDC machine room operation and maintenance system can visually and customarily display the operation and maintenance states of future time segments and current time segments when performing transparent factory type pipeline visual display of various operation and maintenance works of the set IDC machine room on the visualization interface, thereby reducing the work burden of operation and maintenance personnel.

[0006] Therefore, the operation and maintenance factory visualization system based on data processing has the following advantages: first, data-driven accurate monitoring can reflect the system performance and fault conditions of the set IDC machine room in real time; second, AI-enabled intelligent analysis can automatically identify abnormalities and predict potential risks; and third, intuitive visualization display can reduce the work burden of operation and maintenance personnel and improve decision-making efficiency.

[0007] According to the application, an operation and maintenance factory visualization system based on data processing is provided, which comprises: A real-time acquisition mechanism is configured to acquire various pieces of equipment operation and maintenance data respectively corresponding to various IT equipment used in a set IDC machine room in a current time segment and various pieces of application operation and maintenance data respectively corresponding to various IT applications, as massive operation and maintenance data of the IT equipment and the applications in the set IDC machine room in the current time segment, the IT applications running on the IT equipment; A fault extraction mechanism is configured to extract equipment fault information and application fault information respectively corresponding to equipment fault types and application fault types occurring in the set IDC machine room in the current time segment; A multiple assembly mechanism is configured to perform multiple training on the convolutional neural network to obtain the convolutional neural network after the multiple training, and output the convolutional neural network as an intelligent analysis and prediction model; The prediction execution mechanism is connected with the real-time collection mechanism, the fault extraction mechanism and the multiple assembly mechanism respectively, and is used for predicting the equipment fault information and the application fault information of the set IDC room in the next time segment in the current time segment by using an intelligent analysis prediction model according to the massive operation and maintenance data of IT equipment and applications in the current time segment, the massive operation and maintenance data of IT equipment and applications in the same time segment of the previous day and the next time segment of the current time segment, the equipment fault information and the application fault information in the current time segment and the total number of operation and maintenance parameter types. The visual display mechanism is connected with the prediction execution mechanism, and is used for visually displaying the equipment fault information and the application fault information of the set IDC room in the next time segment in the current time segment together with the transparent factory type pipeline while visually displaying each operation and maintenance work of the set IDC room in the transparent factory type pipeline.

[0008] Therefore, the present application has at least the following five outstanding substantive features: Substantive feature A: while visually displaying each operation and maintenance work of the set IDC room in the transparent factory type pipeline, the massive operation and maintenance data of IT equipment and IT applications in the current time segment and the massive operation and maintenance data of IT equipment and IT applications in the same time segment of the previous day and the next time segment of the current time segment existing in the set IDC room are collected and analyzed in real time, an AI algorithm based on an intelligent analysis prediction model is used for intelligent analysis and prediction to obtain the equipment fault information and the application fault information of the set IDC room in the next time segment in the current time segment, and the equipment fault information and the application fault information of the set IDC room in the current time segment are displayed synchronously on the visual interface of the transparent factory type pipeline for visually displaying each operation and maintenance work of the set IDC room, so that complex data is converted into an intuitive visual interface, the system operation state is quickly mastered by the operation and maintenance personnel, reference information is configured in advance for fault troubleshooting and fault response in the subsequent time segment, the operation and maintenance efficiency of the set IDC room is improved, potential problems are found and solved in time, and the stable operation of the business system of the set IDC room is ensured; Essential feature B: in order to realize the intelligent analysis and prediction of the equipment failure information and application failure information of the set IDC machine room in the next time segment under the current time segment, an intelligent analysis and prediction model customized for the structure design of the set IDC machine room is introduced, the intelligent analysis and prediction model is a convolutional neural network after multiple training, and the number of convolutional neural network training is positively correlated with the sum of the total number of IT equipment and the total number of IT applications in the set IDC machine room, so as to customize intelligent analysis and prediction models with different structures for different IDC machine rooms, achieve the AI algorithm implementation of intelligent analysis and prediction of equipment and application failure information in the future time segment, and ensure the effectiveness and stability of intelligent analysis and prediction; Essential feature C: in order to realize the intelligent analysis and prediction of the equipment failure information and application failure information of the set IDC machine room in the next time segment under the current time segment, the basic data is screened, the basic data includes the massive operation and maintenance data of the IT equipment and application of the set IDC machine room in the current time segment, the massive operation and maintenance data of the IT equipment and application in the same time segment as the previous day and the next time segment under the current time segment, the equipment failure information and application failure information in the current time segment, and the total number of operation parameter types, the screening of the above basic data further ensures the effectiveness and stability of intelligent analysis and prediction; Essential feature D: specifically, the massive operation and maintenance data of the IT equipment and application of the set IDC machine room in the current time segment is the operation and maintenance data of each IT equipment used in the set IDC machine room in the current time segment and the application operation and maintenance data of each IT application, the operation and maintenance data of each IT equipment in the current time segment is the customized visual data of each frame of overhead picture of the IT equipment at each imaging time point in the current time segment, the customized visual data of each frame of overhead picture is the depth value, brightness value, horizontal coordinate value and vertical coordinate value of each pixel point of the image block occupied by the IT equipment in the frame of overhead picture, the operation and maintenance data of each IT application in the current time segment is each piece of operation and maintenance log information of the IT application in the current time segment, application type number, application type number of associated other IT applications, upper limit value and lower limit value of operation and maintenance parameters related to the set IDC machine room, and temporary data associated with the set IDC machine room, and the equipment failure information includes equipment failure type number and IT equipment number of equipment failure, and the application failure information includes application failure type number and IT application number of application failure, so as to complete the data structure design of the basic data; Essential feature E: in each training performed on the convolutional neural network, known IDC machine room equipment failure information and application failure information in a certain time segment are taken as the item-by-item output of the convolutional neural network, and the mass operation and maintenance data of IT equipment and applications of the IDC machine room in a previous time segment of the certain time segment, the mass operation and maintenance data of IT equipment and applications in a simultaneous time segment of the day before the date of the certain time segment and the simultaneous time segment, the equipment failure information and application failure information in the previous time segment of the certain time segment, and the total number of operation and maintenance parameter types are taken as the item-by-item input of the convolutional neural network, the current training of the convolutional neural network is completed, and the training effect of each training of the convolutional neural network is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0009] The embodiments of the present application will be described below with reference to the accompanying drawings, in which: Figure 1 A working scene schematic diagram of a data processing-based operation and maintenance factory visualization system according to the present application is shown.

[0010] Figure 2 An internal structure diagram of a data processing-based operation and maintenance factory visualization system according to the first embodiment of the present application is shown.

[0011] Figure 3 An internal structure diagram of a data processing-based operation and maintenance factory visualization system according to the second embodiment of the present application is shown.

[0012] Figure 4 An internal structure diagram of a data processing-based operation and maintenance factory visualization system according to the third embodiment of the present application is shown.

[0013] Figure 5 An internal structure diagram of a data processing-based operation and maintenance factory visualization system according to the fourth embodiment of the present application is shown.

[0014] Figure 6 An internal structure diagram of a data processing-based operation and maintenance factory visualization system according to the fifth embodiment of the present application is shown. DETAILED DESCRIPTION

[0015] As shown in Figure 1 , a working scene schematic diagram of a data processing-based operation and maintenance factory visualization system according to the present application is shown, and the data processing of the present application suitable for administrative, commercial, financial, management, supervision or prediction purposes relates to big data processing.

[0016] The specific technical process of the present application is as follows: Technical Process 1: To achieve intelligent analysis and prediction of equipment and application failure information in a designated IDC data center for the current time segment and the next time segment, an intelligent analysis and prediction model tailored to the specific IDC data center's structure is introduced, such as... Figure 1 As shown; Specifically, once the duration of a time segment is selected, the duration of each time segment is equal, for example, 20 minutes. For example, the customized structural design of the intelligent analysis and prediction model is mainly reflected in the following aspects: Aspect 1: The intelligent analysis and prediction model is a convolutional neural network that has been trained multiple times. A convolutional neural network is a feedforward neural network that includes convolution calculations and has a deep structure. It is one of the representative algorithms of deep learning. Internally, it consists of an input layer, a hidden layer and an output layer, with the hidden layer set between the input layer and the output layer. Aspect 2: The number of times the convolutional neural network is trained is positively correlated with the sum of the total number of IT devices and the total number of IT applications in the set IDC data center, thereby enabling the customization of intelligent analysis and prediction models with different structures for different IDC data centers, and achieving the AI ​​algorithm implementation of intelligent analysis and prediction of device application failure information in future time segments; For example, when the total number of IT devices in the IDC data center is set to 100 and the total number of IT applications in the IDC data center is set to 150, the number of training iterations of the convolutional neural network is selected to be 800. When the total number of IT devices in the IDC data center is set to 100 and the total number of IT applications in the IDC data center is set to 200, the number of training iterations of the convolutional neural network is selected to be 900. When the total number of IT devices in the IDC data center is set to 150 and the total number of IT applications in the IDC data center is set to 200, the number of training iterations of the convolutional neural network is selected to be 1000. When the total number of IT devices in the IDC data center is set to 200 and the total number of IT applications in the IDC data center is set to 300, the number of training iterations of the convolutional neural network is selected to be 1200, and so on. Aspect three: in each training performed on the convolutional neural network, known IDC machine room setting device fault information and application fault information in a certain time segment are taken as the item-by-item output content of the convolutional neural network, and the massive operation and maintenance data of IT devices and applications of the IDC machine room setting in a previous time segment of the certain time segment, the massive operation and maintenance data of IT devices and applications in a simultaneous time segment of the day before the date of the certain time segment and the certain time segment, the device fault information and application fault information in the previous time segment of the certain time segment, and the total number of operation and maintenance parameter types are taken as the item-by-item input content of the convolutional neural network, the current training of the convolutional neural network is completed, thereby ensuring the training effect of each training of the convolutional neural network; In this way, through the above-mentioned customized structure design, the effectiveness and stability of intelligent analysis and prediction are ensured. Technical process two: in order to realize intelligent analysis and prediction of device fault information and application fault information of the IDC machine room setting in the next time segment of the current time segment, each item of basic data is screened; Specifically, the basic data includes the massive operation and maintenance data of IT devices and applications of the IDC machine room setting in the current time segment, the massive operation and maintenance data of IT devices and applications in a simultaneous time segment of the day before the date of the current time segment and the next time segment, the device fault information and application fault information in the current time segment, and the total number of operation and maintenance parameter types. As shown in Figure 1 The basic data input into the intelligent analysis and prediction model customized for the IDC machine room setting includes the massive operation and maintenance data of the current time segment, the massive operation and maintenance data of the simultaneous time segment, the classified fault information of the current time segment, and the total number of operation and maintenance parameter types, wherein the massive operation and maintenance data of the current time segment is the massive operation and maintenance data of IT devices and applications of the IDC machine room setting in the current time segment, the massive operation and maintenance data of the simultaneous time segment is the massive operation and maintenance data of IT devices and applications of the IDC machine room setting in the simultaneous time segment of the day before the date of the current time segment and the next time segment, and the classified fault information of the current time segment is the device fault information and application fault information in the current time segment. Further specifically, the mass operation and maintenance data of the IT equipment and applications of the IDC machine room in the current time segment are set as each piece of equipment operation and maintenance data corresponding to each piece of IT equipment used in the current time segment of the IDC machine room and each piece of application operation and maintenance data corresponding to each IT application, the equipment operation and maintenance data corresponding to each piece of IT equipment in the current time segment is the customized visual data of each frame of bird's-eye view picture of the IT equipment at each imaging moment uniformly spaced in the current time segment, the customized visual data of each frame of bird's-eye view picture is the depth value, brightness value, horizontal coordinate value and vertical coordinate value corresponding to each pixel point of the image block occupied by the IT equipment in the frame of bird's-eye view picture, the application operation and maintenance data corresponding to each IT application in the current time segment is each piece of operation and maintenance log information of the IT application in the current time segment, application type number, application type number of other IT applications associated, upper limit value and lower limit value of the operation and maintenance parameter of the set IDC machine room involved, and the temporary data associated with the set IDC machine room, and the device fault information includes device fault type number and IT equipment number of device fault occurrence, and the application fault information includes application fault type number and IT application number of application fault occurrence, thereby completing the data structure design of each basic data; In this way, through the targeted screening of each basic data described above, the effectiveness and stability of intelligent analysis and prediction are further ensured; Technical process three: applying each basic data screened by the technical process two to the intelligent analysis and prediction model for the set IDC machine room customized structure design in the technical process one to obtain the device fault information and application fault information of the set IDC machine room in the next time segment of the current time segment, i.e. Figure 1 the predicted device fault information and the predicted application fault information as shown in the figure; Specifically, each basic data screened by the technical process two is synchronously input into the intelligent analysis and prediction model according to, and the intelligent analysis and prediction model according to is executed to obtain the device fault information and application fault information of the set IDC machine room in the next time segment of the current time segment output by the intelligent analysis and prediction model; Further specifically, the device fault information and application fault information of the set IDC machine room in the next time segment of the current time segment output by the intelligent analysis and prediction model are the device fault type number and IT equipment number of device fault occurrence of the set IDC machine room in the next time segment of the current time segment, and the application fault type number and IT application number of application fault occurrence of the set IDC machine room in the next time segment of the current time segment; Technical process four: on the visual interface of transparent factory type pipeline visual display of various operation and maintenance work of the set IDC machine room, auxiliary display of the device fault information and application fault information of the set IDC machine room in the next time segment under the current time segment obtained by technical process three; For example, while displaying the device fault information and application fault information of the set IDC machine room in the next time segment under the current time segment on the visual interface of transparent factory type pipeline visual display of various operation and maintenance work of the set IDC machine room, the device fault information and application fault information of the set IDC machine room in the current time can also be displayed synchronously. In this way, the complex data is converted into an intuitive visual interface, so that the IDC machine room operation and maintenance system can visually display the operation and maintenance status of the future time segment and the current time segment when the various operation and maintenance work of the set IDC machine room is visually displayed in the transparent factory type pipeline, thereby helping the operation and maintenance personnel to quickly master the current system operation state and the future system operation state, reducing the work burden of the operation and maintenance personnel, and improving the decision-making efficiency.

[0017] Therefore, the operation and maintenance factory visualization system based on data processing has the following advantages: first, data-driven accurate monitoring can reflect the system performance and fault condition of the set IDC machine room in real time; second, AI-enabled intelligent analysis can automatically identify abnormalities and predict potential risks; third, intuitive visual display can reduce the work burden of the operation and maintenance personnel and improve the decision-making efficiency.

[0018] The key points of the present application are: transparent factory type pipeline visual display of various operation and maintenance work of the set IDC machine room, synchronous visual display of the current operation state and future operation state of the entire system of the set IDC machine room, customized structure of the intelligent analysis and prediction model for intelligent analysis and prediction of the IT device fault information and IT application fault information of the future time segment of the set IDC machine room, and targeted selection of various basic data, targeted design of each training of the convolutional neural network.

[0019] In the following, the operation and maintenance factory visualization system based on data processing will be described in the form of an embodiment. Embodiment

[0020] Figure 2 An internal structure diagram of an operation and maintenance factory visualization system based on data processing according to the first embodiment of the present application is shown.

[0021] As Figure 2 shown, the operation and maintenance factory visualization system based on data processing includes the following components: The real-time collection mechanism is configured to collect device operation and maintenance data corresponding to each IT device and application operation and maintenance data corresponding to each application in the IDC room, so as to obtain massive operation and maintenance data of the IT devices and applications in the IDC room at the current time segment, and the applications run on the IT devices. For example, the collection of the device operation and maintenance data corresponding to each IT device and the application operation and maintenance data corresponding to each application in the IDC room at the current time segment to obtain the massive operation and maintenance data of the IT devices and applications in the IDC room at the current time segment, and the applications run on the IT devices includes that the duration of each time segment is equal once the duration of the time segment is selected, for example, 20 minutes. The fault extraction mechanism is configured to extract device fault information and application fault information corresponding to a device fault type and an application fault type occurring in the IDC room at the current time segment. For example, the current time segment is a time segment with the current time as the starting point, when the duration of the time segment is selected as 20 minutes, and the current time is 4:00 pm, the current time segment is from 4:00 pm to 4:20 pm. The multiple construction mechanism is configured to perform multiple training on the convolutional neural network to obtain a convolutional neural network after the multiple training, and output the intelligent analysis and prediction model. Specifically, the convolutional neural network is a feedforward neural network containing convolutional calculation and having a deep structure, is one of the representative algorithms of deep learning, and is internally composed of an input layer, a hidden layer, and an output layer, and the hidden layer is arranged between the input layer and the output layer. The prediction execution mechanism is connected with the real-time collection mechanism, the fault extraction mechanism, and the multiple construction mechanism, respectively, and is configured to use the intelligent analysis and prediction model to predict device fault information and application fault information in the next time segment of the current time segment in the IDC room according to the massive operation and maintenance data of the IT devices and applications in the IDC room at the current time segment, the massive operation and maintenance data of the IT devices and applications in the simultaneous time segment of the previous day and the next time segment of the current time segment, the device fault information and the application fault information in the current time segment, and the total number of operation and maintenance parameter types. For example, the current time segment is a time segment with the current time as the starting point, when the duration of the time segment is selected as 20 minutes, and the current time is 4:00 pm, the current time segment is from 4:00 pm to 4:20 pm, the current time segment is from 4:20 pm to 4:40 pm on the same day, and the simultaneous time segment of the previous day and the next time segment of the current time segment is from 4:20 pm to 4:40 pm on the previous day. The visual display mechanism is connected with the prediction execution mechanism, and is used for visually displaying the equipment failure information and the application failure information of the set IDC room in the current time segment and the next time segment, and the transparent factory type pipeline of the set IDC room at the same time; Specifically, the intelligent analysis prediction model outputs the equipment failure information and the application failure information of the set IDC room in the current time segment and the next time segment, which are the equipment failure type number and the IT equipment number of the equipment failure of the set IDC room in the current time segment and the next time segment, and the application failure type number and the IT application number of the application failure of the set IDC room in the current time segment and the next time segment. The visual display mechanism can use the first visualization interface to display the equipment failure type number and the IT equipment number of the equipment failure of the set IDC room in the current time segment and the next time segment, and the application failure type number and the IT application number of the application failure of the set IDC room in the current time segment and the next time segment at the same time. As shown later, the visual display mechanism also uses the second visualization interface to display the equipment failure type number and the IT equipment number of the equipment failure of the set IDC room in the current time segment, and the application failure type number and the IT application number of the application failure of the set IDC room in the current time segment at the same time. In this way, complex data is converted into intuitive visualization interfaces, helping operation and maintenance personnel quickly master the current system running state and the future system running state, reducing the work burden of operation and maintenance personnel, and improving the decision-making efficiency. Specifically, the imaging feature of the outside of the IT equipment in the overhead mode can be used to identify the image block occupied by the IT equipment in the frame of the overhead picture, and the value range of the brightness value corresponding to each pixel point is between 0 and 255. Specifically, the imaging feature of the outside of the IT equipment in the overhead mode can be used to identify the image block occupied by the IT equipment in the frame of the overhead picture, and the value range of the brightness value corresponding to each pixel point is between 0 and 255. Specifically, the imaging feature of the outside of the IT equipment in the overhead mode can be used to identify the image block occupied by the IT equipment in the frame of the overhead picture, and the value range of the brightness value corresponding to each pixel point is between 0 and 255. The device fault information includes a device fault type number and an IT device number where the device fault occurs, and the application fault information includes an application fault type number and an IT application number where the application fault occurs. The device fault types include downtime, black screen, appearance damage, overheating, smoking, dislocation, and disconnected line. The application fault types include data overflow, operation and maintenance parameter tampering, process suspension, network intrusion, data backup failure, error log recording, and non-response operation. Obviously, different device fault types correspond to different device fault type numbers, and similarly, different application fault types correspond to different application fault type numbers. The device operation and maintenance data and the application operation and maintenance data are used as the mass operation and maintenance data of the IT devices and the applications in the set IDC machine room in the current time segment. The IT applications run on the IT devices, including running more than one IT application on each IT device simultaneously. The number of times of training the convolutional neural network is positively correlated with the sum of the total number of IT devices and the total number of IT applications in the set IDC machine room. For example, when the total number of IT devices in the set IDC machine room is 100 and the total number of IT applications in the set IDC machine room is 150, the number of times of training the selected convolutional neural network is 800. When the total number of IT devices in the set IDC machine room is 100 and the total number of IT applications in the set IDC machine room is 200, the number of times of training the selected convolutional neural network is 900. When the total number of IT devices in the set IDC machine room is 150 and the total number of IT applications in the set IDC machine room is 200, the number of times of training the selected convolutional neural network is 1000. When the total number of IT devices in the set IDC machine room is 200 and the total number of IT applications in the set IDC machine room is 300, the number of times of training the selected convolutional neural network is 1200, and so on. That is, the number of times of training the convolutional neural network is positively correlated with the sum of the total number of IT devices and the total number of IT applications in the set IDC machine room. And wherein in each training performed on the convolutional neural network, known device fault information and application fault information of the set IDC room within a certain time segment are taken as item-by-item output content of the convolutional neural network, and mass operation and maintenance data of IT devices and applications of the set IDC room in a previous time segment of the certain time segment, mass operation and maintenance data of IT devices and applications in a simultaneous time segment one day before the date of the certain time segment and simultaneously with the certain time segment, device fault information and application fault information within the previous time segment of the certain time segment, and the total number of operation and maintenance parameter types are taken as item-by-item input content of the convolutional neural network, to complete this training of the convolutional neural network. Embodiment

[0022] Figure 3 An internal structure diagram of a data processing-based operation and maintenance factory visualization system according to a second embodiment of the present application is shown.

[0023] As shown in Figure 3 , compared with Figure 2 , the data processing-based operation and maintenance factory visualization system further comprises: A display cache mechanism, connected with the fault extraction mechanism and the visual display mechanism respectively, for pushing the cached device fault information and application fault information corresponding to the device fault types and application fault types occurring in the set IDC room within the current time segment to the visual display mechanism for synchronous display while the visual display mechanism visually displays the device fault information and application fault information of the set IDC room within the next time segment of the current time segment; Wherein, the display cache mechanism is used to acquire the device fault information and application fault information corresponding to the device fault types and application fault types occurring in the set IDC room within the current time segment from the fault extraction mechanism and perform cache processing. For example, the display cache mechanism uses different physical addresses to cache the device fault information and application fault information corresponding to the device fault types and application fault types occurring in the set IDC room within the current time segment respectively. Embodiment

[0024] Figure 4 An internal structure diagram of a data processing-based operation and maintenance factory visualization system according to a third embodiment of the present application is shown.

[0025] As shown in Figure 4 , compared with Figure 3 , the data processing-based operation and maintenance factory visualization system further comprises: A field timing mechanism, connected with the real-time collection mechanism, is configured to provide timing service for the collection of each piece of device operation and maintenance data corresponding to each piece of IT equipment used by the IDC room in the current time segment and each piece of application operation and maintenance data corresponding to each IT application. The field timing mechanism is connected with the real-time collection mechanism, and is configured to provide timing service for the collection of each piece of device operation and maintenance data corresponding to each piece of IT equipment used by the IDC room in the current time segment and each piece of application operation and maintenance data corresponding to each IT application. The field timing mechanism is connected with the real-time collection mechanism, and is configured to provide timing service for the collection of each piece of device operation and maintenance data corresponding to each piece of IT equipment used by the IDC room in the current time segment and each piece of application operation and maintenance data corresponding to each IT application. Embodiment

[0026] Figure 5 An internal structure diagram of a data processing-based operation and maintenance factory visualization system according to a fourth embodiment of the present application is shown.

[0027] As shown in Figure 5 , compared with Figure 4 , the data processing-based operation and maintenance factory visualization system further includes: A wireless transmission mechanism, connected with the prediction execution mechanism, is configured to wirelessly transmit the device fault information and the application fault information of the IDC room in the next time segment of the current time segment to a remote fault management network element through a wireless communication link. The wireless transmission mechanism wirelessly transmits the device fault information and the application fault information of the IDC room in the next time segment of the current time segment to a remote fault management network element through a wireless communication link. The wireless transmission mechanism obtains the device fault information and the application fault information of the IDC room in the next time segment of the current time segment from the prediction execution mechanism. Embodiment

[0028] Figure 6 An internal structure diagram of a data processing-based operation and maintenance factory visualization system according to a fifth embodiment of the present application is shown.

[0029] As shown in Figure 6 , compared with Figure 5 , the data processing-based operation and maintenance factory visualization system further includes: A target establishment mechanism, connected with the multiple assembly mechanism, is configured to receive and store the intelligent analysis prediction model. The target establishing mechanism is connected with the multiple establishing mechanism, and is configured to receive and store the intelligent analysis and prediction model. Specifically, the target establishing mechanism can use different physical addresses to store the model parameters of the intelligent analysis and prediction model respectively.

[0030] Next, the various embodiments of the present application will be further described.

[0031] In the above various embodiments, optionally, in the data processing-based operation and maintenance factory visualization system: The visual display of the device fault information and the application fault information of the IDC machine room in the current time segment and the next time segment includes: the visual display of the device fault information and the application fault information of the IDC machine room in the current time segment and the next time segment is the fault type number, the IT equipment number of the device fault, and the application fault type number, the IT application number of the application fault in the current time segment and the next time segment. For example, the current time segment is a time segment starting from the current time, when the duration of the time segment is selected as 20 minutes, and the current time is 4:00 pm, then the current time segment is from 4:00 pm to 4:20 pm, and the next time segment of the current time segment is from 4:20 pm to 4:40 pm.

[0032] In the above various embodiments, optionally, in the data processing-based operation and maintenance factory visualization system: The use of the intelligent analysis and prediction model to predict the device fault information and the application fault information of the set IDC machine room in the current time segment and the next time segment according to the massive operation and maintenance data of the IT equipment and the application of the set IDC machine room in the current time segment, the massive operation and maintenance data of the IT equipment and the application in the same time segment of the previous day and the current time segment and the next time segment, the device fault information and the application fault information in the current time segment, and the total number of operation and maintenance parameter types includes: the position of the same time segment on the time axis of the previous day is the same as the position of the current time segment and the next time segment on the time axis of the current day. For example, the same time segment is from 4:20 pm to 4:40 pm of the previous day, and the current time segment and the next time segment is from 4:20 pm to 4:40 pm of the current day, so the position of the same time segment on the time axis of the previous day is the same as the position of the current time segment and the next time segment on the time axis of the current day. The method further comprises: collecting each piece of device operation data corresponding to each IT device used in the IDC room and each piece of application operation data corresponding to each IT application in the IDC room in the same time segment as the current time segment, as the mass operation data of the IT devices and applications in the IDC room in the same time segment as the current time segment. The method further comprises: collecting each piece of device operation data corresponding to each IT device used in the IDC room and each piece of application operation data corresponding to each IT application in the IDC room in the same time segment as the current time segment, as the mass operation data of the IT devices and applications in the IDC room in the same time segment as the current time segment. The method further comprises: collecting each piece of device operation data corresponding to each IT device used in the IDC room and each piece of application operation data corresponding to each IT application in the IDC room in the same time segment as the current time segment, as the mass operation data of the IT devices and applications in the IDC room in the same time segment as the current time segment. The IDC machine room in the current time segment, the mass operation and maintenance data of the IT equipment and application in the current time segment, the mass operation and maintenance data of the IT equipment and application in the simultaneous time segment of the next time segment of the previous day and the current time segment, the equipment failure information and application failure information in the current time segment, and the total number of operation and maintenance parameters are synchronously input into the intelligent analysis and prediction model, and the intelligent analysis and prediction model is executed according to the synchronous input, so that the equipment failure information and application failure information of the IDC machine room in the next time segment of the current time segment output by the intelligent analysis and prediction model are obtained, and the equipment failure information and application failure information of the IDC machine room in the next time segment of the current time segment are in the form of octal numerical values. The IDC machine room in the current time segment, the mass operation and maintenance data of the IT equipment and application in the current time segment, the mass operation and maintenance data of the IT equipment and application in the simultaneous time segment of the next time segment of the previous day and the current time segment, the equipment failure information and application failure information in the current time segment, and the total number of operation and maintenance parameters are synchronously input into the intelligent analysis and prediction model, and the intelligent analysis and prediction model is executed according to the synchronous input, so that the equipment failure information and application failure information of the IDC machine room in the next time segment of the current time segment output by the intelligent analysis and prediction model are obtained, and the equipment failure information and application failure information of the IDC machine room in the next time segment of the current time segment are in the form of octal numerical values.

[0033] In the above various embodiments, optionally, in the operation and maintenance factory visualization system based on data processing: The multiple times of training of the convolutional neural network are performed to obtain the convolutional neural network after the multiple times of training, and the convolutional neural network after the multiple times of training is output as the intelligent analysis and prediction model, and the information mapping function with double inputs and single output is used to represent the information mapping relationship between the number of times of training of the convolutional neural network and the sum of the total number of IT equipment and the total number of IT applications in the set IDC machine room. Specifically, the simulation and test of the data processing process of the information mapping relationship between the number of times of training of the convolutional neural network and the sum of the total number of IT equipment and the total number of IT applications in the set IDC machine room represented by the information mapping function with double inputs and single output can be selected to be implemented by using a numerical simulation mode. The information mapping function with double input and single output represents a positive correlation between the number of times of training of the convolutional neural network and the sum of the total number of IT equipment and the total number of IT applications in the IDC room, and the information mapping relationship includes: in the information mapping function, the total number of IT equipment and the total number of IT applications in the IDC room are double inputs of the information mapping function. The information mapping function with double input and single output represents a positive correlation between the number of times of training of the convolutional neural network and the sum of the total number of IT equipment and the total number of IT applications in the IDC room, and the information mapping relationship further includes: in the information mapping function, the number of times of training of the convolutional neural network positively correlated with the sum of the total number of IT equipment and the total number of IT applications in the IDC room is the single output of the information mapping function.

[0034] In addition, in the operation and maintenance factory visualization system based on data processing according to the present application: The multiple training of the convolutional neural network to obtain the convolutional neural network after the multiple training is completed and output as an intelligent analysis prediction model further includes: the convolutional neural network is a feedforward neural network containing convolution calculation and having a deep structure, is one of the representative algorithms of deep learning, and is internally composed of a single input layer, N hidden layers and a single output layer, and the N hidden layers are arranged between the single input layer and the single output layer; The convolutional neural network is a feedforward neural network containing convolution calculation and having a deep structure, is one of the representative algorithms of deep learning, and is internally composed of a single input layer, N hidden layers and a single output layer, and the N hidden layers are arranged between the single input layer and the single output layer, and the number of layers of the hidden layer, i.e. the value of N, is positively correlated with the total number of operation and maintenance parameter types of the IDC room; For example, the data mapping relationship between the number of layers of the hidden layer, i.e. the value of N, and the total number of operation and maintenance parameter types of the IDC room is represented by a data mapping formula; For further example, in the data mapping formula, the value of N positively correlated with the total number of operation and maintenance parameter types of the IDC room is the output data of the data mapping formula, and the total number of operation and maintenance parameter types of the IDC room is the input data of the data mapping formula.

[0035] The various embodiments in the specification are described in a related manner, and the same and similar parts of each embodiment can be referred to each other. Each embodiment focuses on the difference from other embodiments. In particular, for the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiments. The above is only the preferred embodiment of the present application, and is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application is included in the protection scope of the present application.

Claims

1. A data processing-based operation and maintenance factory visualization system, characterized in that, The system includes: The real-time data collection mechanism is used to collect the equipment operation and maintenance data corresponding to each IT device used in the current time segment of the IDC data center, as well as the application operation and maintenance data corresponding to each IT application. This data serves as the massive operation and maintenance data of the IT devices and applications in the current time segment of the IDC data center, with the IT applications running on the IT devices. The fault extraction mechanism is used to extract equipment fault information and application fault information corresponding to the equipment fault types and application fault types that occur in the designated IDC data center within the current time segment. Multiple sets of structures are used to perform multiple training operations on the convolutional neural network to obtain a convolutional neural network after multiple training operations, which is then used as the output of an intelligent analysis and prediction model. The prediction execution mechanism is connected to the real-time data collection mechanism, the fault extraction mechanism, and the multiple assembly mechanism, respectively. It is used to use the intelligent analysis and prediction model to predict the equipment failure information and application failure information of the set IDC data center in the next time segment based on the massive operation and maintenance data of IT equipment and applications in the current time segment, the massive operation and maintenance data of IT equipment and applications in the same time segment as the previous day and the next time segment, the equipment failure information and application failure information in the current time segment, and the total number of operation and maintenance parameter types. The visual display unit, connected to the predictive execution unit, is used to visually display the various operation and maintenance tasks of the designated IDC data center in a transparent factory-like pipeline, while simultaneously displaying the equipment failure information and application failure information of the designated IDC data center in the next time segment along with the transparent factory-like pipeline.

2. The data processing-based operation and maintenance factory visualization system as described in claim 1, characterized in that: The equipment operation and maintenance data corresponding to each IT device in the current time segment is the customized visual data of each frame of the overhead view of the IT device at each imaging time at a uniform interval in the current time segment. The customized visual data of each frame of the overhead view is the depth value, brightness value, horizontal coordinate value and vertical coordinate value of each pixel point of the image block occupied by the IT device in the frame of the overhead view. Among them, the application operation and maintenance data corresponding to each IT application in the current time segment includes each operation and maintenance log information of the IT application in the current time segment, the application type number, the application type number of other related IT applications, the upper limit and lower limit values ​​of the operation and maintenance parameters of the set IDC data center, and the temporary data associated with the set IDC data center. Among them, equipment failure information includes equipment failure type number and IT equipment number of the equipment failure, application failure information includes application failure type number and IT application number of the application failure, equipment failure type includes downtime, black screen, physical damage, overheating, smoke, misalignment and disconnection, application failure type includes data overflow, maintenance parameter tampering, process suspension, network intrusion, data backup failure, error log recording and non-responsive operation; This involves collecting and setting up the operation and maintenance data of each IT device used in the IDC data center during the current time segment, as well as the operation and maintenance data of each IT application. This data serves as the massive operation and maintenance data of the IT devices and applications in the IDC data center during the current time segment. The IT applications running on the IT devices include: running more than one IT application on each IT device simultaneously.

3. The data processing-based operation and maintenance factory visualization system as described in claim 2, characterized in that: The convolutional neural network is trained multiple times to obtain a convolutional neural network after multiple training sessions. The output of the intelligent analysis and prediction model includes: the number of times the convolutional neural network is trained is positively correlated with the sum of the total number of IT devices and the total number of IT applications in the set IDC data center. In each training iteration of the convolutional neural network, the known equipment and application failure information of the designated IDC data center within a certain time segment is used as the output of the convolutional neural network. The massive amounts of IT equipment and application operation and maintenance data of the designated IDC data center in the previous time segment, the massive amounts of IT equipment and application operation and maintenance data in the same time segment as the date before the current time segment, the equipment and application failure information in the previous time segment, and the total number of operation and maintenance parameter types are used as the input of the convolutional neural network to complete this training iteration.

4. The data processing-based operation and maintenance factory visualization system as described in claim 3, characterized in that, The system also includes: The display cache mechanism is connected to the fault extraction mechanism and the visual display mechanism respectively. It is used to push the cached equipment fault information and application fault information corresponding to the equipment fault types and application fault types that occur in the IDC data center in the current time segment to the visual display mechanism for synchronous display while the visual display mechanism visually displays the equipment fault information and application fault information of the IDC data center in the current time segment. The display caching mechanism is used to obtain the equipment fault information and application fault information corresponding to the equipment fault types and application fault types that occur in the current time segment of the set IDC data center from the fault extraction mechanism and to perform caching processing.

5. The data processing-based operation and maintenance factory visualization system as described in claim 3, characterized in that, The system also includes: The on-site timing mechanism, connected to the real-time data acquisition mechanism, is used to provide timing services for the collection of equipment operation and maintenance data corresponding to each IT device used in the IDC data center within the current time segment, as well as application operation and maintenance data corresponding to each IT application. The on-site timing mechanism, connected to the real-time acquisition mechanism, is used to provide timing services for the acquisition of equipment operation and maintenance data corresponding to each IT device used in the IDC data center within the current time segment, as well as application operation and maintenance data corresponding to each IT application. The on-site timing mechanism has a built-in pulse generator to provide reference pulse signals for the timing service.

6. The data processing-based operation and maintenance factory visualization system as described in claim 3, characterized in that, The system also includes: The wireless transmission mechanism, connected to the prediction execution mechanism, is used to wirelessly transmit equipment fault information and application fault information of the IDC data center in the current time segment and the next time segment to the remote fault management network element via a wireless communication link. The wireless transmission mechanism obtains equipment fault information and application fault information of the set IDC data center in the next time segment from the prediction execution mechanism.

7. The data processing-based operation and maintenance factory visualization system as described in claim 3, characterized in that, The system also includes: The target establishment mechanism connects with multiple establishment mechanisms to receive and store intelligent analysis and prediction models; The target establishment mechanism, connected to the multiple assembly mechanism, is used to receive and store the intelligent analysis and prediction model. This includes: the target establishment mechanism completing the model storage of the intelligent analysis and prediction model by storing various model parameters of the intelligent analysis and prediction model.

8. The data processing-based operation and maintenance factory visualization system as described in any one of claims 3-7, characterized in that: The visual display settings for IDC data center equipment failure information and application failure information in the next time segment of the current time segment include: the failure type number, the IT equipment number of the equipment failure, and the application failure type number and the IT application number of the application failure in the next time segment of the current time segment.

9. The data processing-based operation and maintenance factory visualization system as described in any one of claims 3-7, characterized in that: The intelligent analysis and prediction model uses massive amounts of IT equipment and application operation and maintenance data of the set IDC data center in the current time segment, massive amounts of IT equipment and application operation and maintenance data of the same time segment at the same time as the previous day and the next time segment, equipment failure information and application failure information in the current time segment, and the total number of operation and maintenance parameter types to predict the equipment failure information and application failure information of the set IDC data center in the next time segment. This includes: the position of the same time segment on the time axis of the previous day is the same as the position of the next time segment on the time axis of the current day. The method of using an intelligent analysis and prediction model to predict the equipment failure information and application failure information of the set IDC data center in the next time segment based on the massive operation and maintenance data of the IT equipment and applications in the set IDC data center in the current time segment, the massive operation and maintenance data of the IT equipment and applications in the same time segment as the previous day and the next time segment, the equipment failure information and application failure information in the current time segment, and the total number of operation and maintenance parameter types, also includes: collecting the equipment operation and maintenance data corresponding to each IT equipment used in the set IDC data center in the same time segment and the application operation and maintenance data corresponding to each IT application, as the massive operation and maintenance data of the IT equipment and applications in the set IDC data center in the same time segment; The intelligent analysis and prediction model uses massive amounts of IT equipment and application operation and maintenance data of the set IDC data center in the current time segment, massive amounts of IT equipment and application operation and maintenance data of the same time segment as the previous day and the next time segment, equipment failure information and application failure information in the current time segment, and the total number of operation and maintenance parameter types to predict the equipment failure information and application failure information of the set IDC data center in the next time segment in the current time segment. It also includes: the duration of each time segment is the same, and the current time segment is located on the same day and starts from the current time. The process of using an intelligent analysis and prediction model to predict the equipment and application failure information of the designated IDC data center in the next time segment based on massive amounts of operation and maintenance data of IT equipment and applications in the current time segment, massive amounts of operation and maintenance data of IT equipment and applications in the same time segment as the previous day and the next time segment, equipment failure information and application failure information in the current time segment, and the total number of operation and maintenance parameter types also includes: synchronously inputting massive amounts of operation and maintenance data of IT equipment and applications in the current time segment, massive amounts of operation and maintenance data of IT equipment and applications in the same time segment as the previous day and the next time segment, equipment failure information and application failure information in the current time segment, and the total number of operation and maintenance parameter types into the intelligent analysis and prediction model, and executing the intelligent analysis and prediction model to obtain the equipment failure information and application failure information of the designated IDC data center in the next time segment output by the intelligent analysis and prediction model; The process involves simultaneously inputting massive amounts of IT equipment and application operation and maintenance data from the IDC data center in the current time segment, massive amounts of IT equipment and application operation and maintenance data from the previous day and the next time segment, equipment failure information and application failure information within the current time segment, and the total number of operation and maintenance parameter types into the intelligent analysis and prediction model. The intelligent analysis and prediction model is then executed to obtain the equipment failure information and application failure information of the IDC data center in the next time segment, which includes: massive amounts of IT equipment and application operation and maintenance data from the IDC data center in the current time segment, massive amounts of IT equipment and application operation and maintenance data from the previous day and the next time segment, equipment failure information and application failure information within the current time segment, the total number of operation and maintenance parameter types, and all of these are represented in octal numerical form. The process involves simultaneously inputting massive amounts of IT equipment and application operation and maintenance data from the IDC data center in the current time segment, massive amounts of IT equipment and application operation and maintenance data from the previous day and the next time segment, equipment fault information and application fault information within the current time segment, and the total number of operation and maintenance parameter types into the intelligent analysis and prediction model. The intelligent analysis and prediction model is then executed to obtain the equipment fault information and application fault information of the IDC data center in the next time segment, as output by the intelligent analysis and prediction model. This process also includes using programmable logic devices to implement the synchronous input.

10. The data processing-based operation and maintenance factory visualization system as described in any one of claims 3-7, characterized in that: The process of training a convolutional neural network multiple times to obtain a convolutional neural network after multiple training iterations, and using it as the output of an intelligent analysis and prediction model, also includes: using a dual-input single-output information mapping function to represent the information mapping relationship between the number of training iterations of the convolutional neural network and the sum of the total number of IT devices and the total number of IT applications in the IDC data center; The information mapping function using a dual-input single-output method represents the positive correlation between the number of training iterations of the convolutional neural network and the sum of the total number of IT devices and IT applications in the IDC data center. This includes setting the total number of IT devices and IT applications in the IDC data center as the dual inputs of the information mapping function. The method of using a dual-input single-output information mapping function to represent the information mapping relationship between the number of times the convolutional neural network is trained and the sum of the total number of IT devices and the total number of IT applications in the set IDC data center further includes: in the information mapping function, the number of times the convolutional neural network is trained and the sum of the total number of IT devices and the total number of IT applications in the set IDC data center are the single output of the information mapping function.

Images