IT equipment operation and maintenance method, device and equipment based on multiple modes

Abstract

The embodiment of the invention provides an IT equipment operation and maintenance method, device and equipment based on multiple modes. The method comprises the following steps: collecting multi-mode operation data of IT equipment; according to the multi-mode operation data, obtaining operation characteristics of the IT equipment; calculating autonomy degree grade indexes of the IT equipment according to the operation characteristics, wherein the autonomy degree grade indexes comprise a software exception accumulated value, a network stability coefficient and a hardware load balance degree; and according to the autonomy level index, generating a decision instruction set of the IT device, the decision instruction set comprising a repair priority and a resource allocation strategy of the IT device. In this way, the repair priority and the resource allocation strategy of the IT equipment can be intelligently and rapidly determined based on the multi-mode operation data of the IT equipment, so that the operation and maintenance efficiency and accuracy of the IT equipment are improved.

Description

Technical Field

[0001] This disclosure relates to the field of IT operations and maintenance, and in particular to the field of IT equipment operations and maintenance technology based on multimodal operation and maintenance. Background Technology

[0002] Traditional IT operations and maintenance systems often rely on single-modal data logs or network traffic for anomaly detection. Furthermore, such anomaly detection and maintenance largely depend on manual experience for configuration and repair, resulting in low efficiency and accuracy in the operation and maintenance of IT equipment, making it difficult to meet the intelligent operation and maintenance needs of IT facilities. Summary of the Invention

[0003] This disclosure provides a method, apparatus, device, and storage medium for the operation and maintenance of IT equipment based on multimodality.

[0004] According to a first aspect of this disclosure, a multimodal IT equipment operation and maintenance method is provided. The method includes:

[0005] Collect multimodal operational data from IT equipment;

[0006] Based on the multimodal operation data, the operating characteristics of the IT equipment are obtained;

[0007] The autonomy level index of the IT equipment is calculated based on the operational characteristics. The autonomy level index includes: software anomaly accumulation value, network stability coefficient, and hardware load balancing degree.

[0008] Based on the autonomy level index, a decision instruction set for the IT equipment is generated, which includes the repair priority and resource allocation strategy of the IT equipment.

[0009] In addition to the aspects and any possible implementations described above, a further implementation is provided, wherein the acquisition of multimodal operational data of IT devices includes:

[0010] Access the exception logs of the IT equipment;

[0011] Extract the error type, frequency of occurrence, and stack trace from the exception log;

[0012] Collect network traffic time-series data of the IT equipment;

[0013] Based on the network traffic time-series data, calculate the self-similarity coefficient and burst traffic percentage of the IT device;

[0014] Determine whether a virtual machine is installed on the IT device;

[0015] If virtual machines are installed on the IT equipment, the frequency and time distribution of virtual machine hot migration are statistically analyzed.

[0016] In addition to the aspects and any possible implementations described above, a further implementation is provided in which the operating characteristics of the IT device include: a first operating characteristic, a second operating characteristic, and a third operating characteristic;

[0017] The step of obtaining the operating characteristics of the IT equipment based on the multimodal operating data includes:

[0018] The cumulative risk value is calculated by performing a three-dimensional weighted average of the error type, occurrence frequency, and stack trace in the anomaly log.

[0019] The cumulative risk value is determined as the first operational characteristic;

[0020] Based on the historical traffic data of the IT device, determine the average traffic data of the IT device;

[0021] Calculate the traffic offset based on the network traffic time-series data and the average traffic data;

[0022] Based on the self-similarity coefficient and the proportion of burst traffic, calculate the joint contribution of the IT device to network congestion;

[0023] The combined contribution of the traffic offset and the IT device to network congestion is determined as the second operational characteristic;

[0024] Calculate the resource liquidity index based on the virtual machine hot migration frequency and the migration time distribution;

[0025] The resource liquidity index is determined as the third operating characteristic;

[0026] The calculation of the autonomy level index of the IT equipment based on the operational characteristics includes:

[0027] The autonomy level index of the IT device is calculated based on the first operating characteristic, the second operating characteristic, and the third operating characteristic.

[0028] In addition to the aspects and any possible implementations described above, a further implementation is provided, wherein calculating the autonomy level index of the IT device based on the first operational characteristic, the second operational characteristic, and the third operational characteristic includes:

[0029] The cumulative risk value is dynamically weighted with a preset anomaly threshold to obtain the cumulative software anomaly value of the IT equipment;

[0030] A network stability coefficient is constructed based on the traffic offset and the joint contribution of the IT device to network congestion.

[0031] Calculate the hardware load balancing degree based on the resource liquidity index.

[0032] In addition to the aspects and any possible implementations described above, a further implementation is provided, wherein the resource allocation strategy includes: a network topology adjustment instruction, wherein the allocation is based on the autonomy level index.

[0033] Generate the decision instruction set for the IT device, including:

[0034] The software anomaly accumulation value, the network stability coefficient, and the hardware load balancing degree are input into a multi-objective optimization model, and the repair priority is calculated using the ideal values ​​of preset key indicators as constraints.

[0035] The IT equipment is repaired according to the repair priority, and redundant service nodes are allocated to the IT equipment based on the resource liquidity index.

[0036] Calculate the stability difference between the network stability coefficient and the preset stability threshold;

[0037] Determine the dynamic topology of the IT device;

[0038] Based on the stability difference and the dynamic topology map, a network topology adjustment instruction is generated, which includes path rerouting and bandwidth reallocation.

[0039] In addition to the aspects and any possible implementations described above, a further implementation is provided, wherein the method further includes:

[0040] Execute the decision instruction set of the IT equipment;

[0041] Recalculate the time latency fluctuation range of the aforementioned IT equipment;

[0042] Obtain the preset network response latency time of the IT device;

[0043] Determine whether the time delay fluctuation range exceeds the preset network response delay time;

[0044] If the preset network response delay time is exceeded, the decision instruction set of the IT equipment will be adjusted again.

[0045] In addition to the aspects and any possible implementations described above, a further implementation is provided, wherein the method further includes:

[0046] The multimodal operation data is stored in correspondence with the decision instruction set of the IT equipment to form a decision instruction log;

[0047] The IT equipment is marked on the decision log.

[0048] According to a second aspect of this disclosure, a multimodal IT equipment operation and maintenance device is provided. The device includes:

[0049] The data acquisition module is used to collect multimodal operational data from IT equipment.

[0050] The acquisition module is used to acquire the operating characteristics of the IT equipment based on the multimodal operating data;

[0051] The calculation module is used to calculate the autonomy level index of the IT equipment based on the operating characteristics. The autonomy level index includes: software anomaly accumulation value, network stability coefficient, and hardware load balancing degree.

[0052] The generation module is used to generate a set of decision instructions for the IT equipment based on the autonomy level index. The set of decision instructions includes the repair priority and resource allocation strategy of the IT equipment.

[0053] According to a third aspect of this disclosure, an electronic device is provided. The electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the program to implement the method described above.

[0054] According to a fourth aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the method according to a first aspect of this disclosure.

[0055] In this disclosure, after collecting multimodal operation data of IT equipment, the operating characteristics of the IT equipment can be obtained based on the multimodal operation data. Then, the autonomy level index of the IT equipment can be calculated based on the operating characteristics. Furthermore, the decision instruction set of the IT equipment can be automatically generated based on the autonomy level index. In this way, the repair priority and resource allocation strategy of the IT equipment can be determined intelligently and quickly based on the multimodal operation data of the IT equipment, so as to improve the operation and maintenance efficiency and accuracy of the IT equipment.

[0056] It should be understood that the description in the Summary of the Invention section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0057] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. The drawings are provided for a better understanding of the invention and are not intended to limit the scope of this disclosure. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0058] Figure 1 A flowchart illustrating a multimodal-based IT equipment operation and maintenance method according to an embodiment of the present disclosure is shown;

[0059] Figure 2 A block diagram of a multimodal IT equipment operation and maintenance apparatus according to an embodiment of the present disclosure is shown;

[0060] Figure 3 A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. Detailed Implementation

[0061] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0062] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0063] Figure 1 A flowchart of a multimodal IT equipment operation and maintenance method 100 according to an embodiment of the present disclosure is shown. Method 100 may include:

[0064] Step 110: Collect multimodal operation data of IT equipment;

[0065] Multimodal operational data includes, but is not limited to, the runtime, usage frequency, and anomaly frequency of software in IT equipment, and may also include the usage of hardware in IT equipment, such as CPU utilization and memory utilization.

[0066] IT equipment can be one or more devices.

[0067] IT equipment includes, but is not limited to, servers, storage devices, and network equipment.

[0068] Step 120: Obtain the operating characteristics of the IT equipment based on the multimodal operating data;

[0069] Step 130: Calculate the autonomy level index of the IT equipment based on the operating characteristics. The autonomy level index includes: software anomaly accumulation value, network stability coefficient, and hardware load balancing degree.

[0070] Step 140: Generate a decision instruction set for the IT device based on the autonomy level index. The decision instruction set includes the repair priority and resource allocation strategy of the IT device.

[0071] After collecting multimodal operational data of IT equipment, the operational characteristics of the IT equipment can be obtained based on the multimodal operational data. Then, the autonomy level index of the IT equipment can be calculated based on the operational characteristics. Furthermore, the decision instruction set of the IT equipment can be automatically generated based on the autonomy level index. In this way, the repair priority and resource allocation strategy of the IT equipment can be determined intelligently and quickly based on the multimodal operational data of the IT equipment, so as to improve the operation and maintenance efficiency and accuracy of the IT equipment, and thus meet the intelligent operation and maintenance needs of the IT equipment.

[0072] In some embodiments, the collection of multimodal operational data from IT devices includes:

[0073] Access the exception logs of the IT equipment;

[0074] Extract the error type, frequency of occurrence, and stack trace from the exception log;

[0075] Regularly collect anomaly logs from IT devices such as servers, storage devices, and network devices. Use log parsing tools or custom scripts to extract error types from the logs, including but not limited to memory leaks, disk I / O errors, frequency of occurrence, stack traces, and function call stack information when the error occurred.

[0076] Collect network traffic time-series data of the IT equipment;

[0077] Network traffic time-series data for IT devices refers to the network traffic of IT devices that changes over time, or the network traffic of different ports or different software within IT devices that changes over time.

[0078] Based on the network traffic time-series data, calculate the self-similarity coefficient and burst traffic percentage of the IT device;

[0079] The self-similarity coefficient is the stability of the traffic patterns of IT devices, such as the stability of the WIFI used by IT devices.

[0080] The percentage of sudden traffic spikes refers to the degree of drastic change in traffic to IT devices.

[0081] Determine whether a virtual machine is installed on the IT device; the virtual machine can be an Android virtual machine, a virtual machine of a computer operating system, etc.

[0082] If virtual machines are installed on the IT equipment, the frequency and time distribution of virtual machine hot migration are statistically analyzed.

[0083] By statistically analyzing the frequency of virtual machine live migrations and the time required for each migration (i.e., the migration time distribution), the results can be presented in the form of charts or reports.

[0084] In some embodiments, the operating characteristics of the IT equipment include: a first operating characteristic, a second operating characteristic, and a third operating characteristic;

[0085] The step of obtaining the operating characteristics of the IT equipment based on the multimodal operating data includes:

[0086] The cumulative risk value is calculated by performing a three-dimensional weighted average of the error type, occurrence frequency, and stack trace in the anomaly log.

[0087] Assign a weight to each error type, for example, assign higher weight to high-frequency error types based on their occurrence frequency; analyze stack traces to identify critical call paths in IT equipment and give higher weight to errors involving critical paths;

[0088] Error types, occurrence frequencies, and stack traces in the exception log can be standardized and then assigned different indices (i.e., 0 to 1). Then, different weight coefficients are assigned to the error types, occurrence frequencies, and stack traces in the exception log. Finally, the different indices are weighted with the different weight coefficients to obtain the weighted sum of indices, which is the cumulative risk value.

[0089] The cumulative risk value is determined as the first operational characteristic;

[0090] Based on the historical traffic data of the IT device, determine the average traffic data of the IT device;

[0091] Calculate the traffic offset based on the network traffic time-series data and the average traffic data;

[0092] Based on the self-similarity coefficient and the proportion of burst traffic, calculate the joint contribution of the IT device to network congestion;

[0093] When calculating the joint contribution of self-similarity coefficient and burst traffic percentage to network congestion, a weighted average or product method can be used. This combines the values ​​of the two characteristics, namely the self-similarity coefficient and the burst traffic percentage, to obtain a comprehensive index, namely the joint contribution of IT devices to network congestion. This joint contribution reflects the comprehensive impact of the network traffic characteristics of IT devices on network congestion, and helps to predict the occurrence and extent of network congestion.

[0094] The combined contribution of the traffic offset and the IT device to network congestion is determined as the second operational characteristic;

[0095] Calculate the resource liquidity index based on the virtual machine hot migration frequency and the migration time distribution;

[0096] Based on the hot migration frequency and migration time distribution, the resource liquidity index can be automatically calculated. For example, the ratio of migration frequency to migration time distribution can be used as the resource liquidity index. This resource liquidity index reflects the flow efficiency of resources in the virtualization environment, such as the changes in the virtual machine's use of CPU, memory, and ports.

[0097] The resource liquidity index is determined as the third operating characteristic;

[0098] The calculation of the autonomy level index of the IT equipment based on the operational characteristics includes:

[0099] The autonomy level index of the IT device is calculated based on the first operating characteristic, the second operating characteristic, and the third operating characteristic.

[0100] Based on the first operating characteristic, the second operating characteristic, and the third operating characteristic mentioned above, the autonomy level index of the IT equipment can be accurately calculated.

[0101] In some embodiments, calculating the autonomy level index of the IT device based on the first operating characteristic, the second operating characteristic, and the third operating characteristic includes:

[0102] The cumulative risk value is dynamically weighted with a preset anomaly threshold to obtain the cumulative software anomaly value of the IT equipment;

[0103] The preset anomaly threshold can be set based on historical data and experience. The weight of the anomaly threshold can be dynamically adjusted according to factors such as the operating status of IT equipment and the importance of business. For example, during periods of high IT equipment load or business criticality, the cumulative risk value can be given a higher weight, and the preset anomaly threshold can be given a lower weight, so as to more sensitively capture software anomalies in IT equipment.

[0104] The cumulative software anomaly value is obtained by dynamically weighting the cumulative risk value with a preset anomaly threshold. The higher the cumulative software anomaly value, the more serious the software anomaly accumulation.

[0105] A network stability coefficient is constructed based on the traffic offset and the joint contribution of the IT device to network congestion.

[0106] The network stability coefficient is constructed by combining the contribution of traffic offset and network congestion; a higher value indicates better network stability.

[0107] Calculate the hardware load balancing degree based on the resource liquidity index.

[0108] Hardware load balancing is negatively correlated with the resource liquidity index; that is, the higher the resource liquidity index, the lower the hardware load balancing.

[0109] Of course, in addition to the three indicators of software anomaly accumulation value, network stability coefficient, and hardware load balancing degree, the autonomy level index can also be represented by a comprehensive value calculated from these three indicators as the self-consistency level index. For example, the calculated hardware load balancing degree, software anomaly accumulation value, and network stability coefficient can be used as inputs, and the final autonomy level index of IT equipment can be calculated through weighted average, fuzzy comprehensive evaluation, and other methods. The autonomy level index can reflect the comprehensive autonomy capability of IT equipment at the hardware, software, and network levels. The stronger the autonomy capability, the better the IT equipment can perform automatic operation and maintenance.

[0110] In some embodiments, the resource allocation strategy includes: network topology adjustment instructions, wherein generating a set of decision instructions for the IT equipment based on the autonomy level index includes:

[0111] The software anomaly accumulation value, the network stability coefficient, and the hardware load balancing degree are input into a multi-objective optimization model, and the repair priority is calculated using the ideal values ​​of preset key indicators as constraints.

[0112] The target optimization model can be a convolutional neural network, etc.

[0113] Preset key metrics can be CPU utilization, memory utilization, etc.

[0114] Setting lower or upper limits for the weights of certain key indicators can ensure that the calculation of repair priorities conforms to the overall system strategy and resource constraints.

[0115] Repair priority indicates the urgency of repairing the IT equipment. The higher the repair priority of an IT equipment, the more urgent it needs to be repaired.

[0116] The IT equipment is repaired according to the repair priority, and redundant service nodes are allocated to the IT equipment based on the resource liquidity index.

[0117] In the dynamic topology of the network area (such as LAN, MAN, WAN, etc.) where the IT equipment is located, there may be multiple nodes that can serve the IT equipment. The higher the resource mobility index, the weaker the load balancing capability of the IT equipment. Therefore, when allocating redundant service nodes based on the resource mobility index, service nodes with low resource mobility index in the dynamic topology can be prioritized for the IT equipment.

[0118] Suppose that the dynamic topology of the network area where the IT equipment is located has two redundant computing nodes, Node1 and Node2, and their resource mobility indices are RLI and RLI, respectively. Node1 =0.8, RLI Node2 If the value is 0.6, then Node2 is selected as the redundant service node to ensure that the IT equipment can be processed in a timely manner.

[0119] Calculate the stability difference between the network stability coefficient and the preset stability threshold;

[0120] Determine the dynamic topology of the IT device;

[0121] Based on the stability difference and the dynamic topology map, a network topology adjustment instruction is generated, which includes path rerouting and bandwidth reallocation.

[0122] By calculating the stability difference between the network stability coefficient and the preset stability threshold, and determining the dynamic topology map where the IT device is located, a network topology adjustment instruction can be generated based on the stability difference and the dynamic topology map, thereby improving the network stability of the IT device. If the stability difference between the network stability coefficient of the IT device and the preset stability threshold is less than the preset stability threshold, it indicates that the IT device node is not very stable and belongs to a congested node. Therefore, path rerouting can be performed, that is, a new path can be selected from the dynamic topology map to bypass the congested or faulty node, or the bandwidth of the link can be reallocated directly according to the network traffic demand of the IT device, such as widening the bandwidth allocated to the IT device.

[0123] If the difference between the network stability coefficient NSC and the preset stability threshold NST is ΔNSC<0, it means that the network stability is lower than the threshold and the network topology needs to be adjusted. This can be done by rerouting paths and / or reallocating bandwidth, selecting a new path to bypass congested or faulty nodes (i.e. bypassing congested or faulty IT equipment), or reallocating the bandwidth of the link where the IT equipment is located to directly increase the bandwidth of the poorly stable equipment according to network traffic demand.

[0124] In some embodiments, the method further includes:

[0125] Execute the decision instruction set of the IT equipment;

[0126] Recalculate the time latency fluctuation range of the aforementioned IT equipment;

[0127] Obtain the preset network response latency time of the IT device;

[0128] Determine whether the time delay fluctuation range exceeds the preset network response delay time;

[0129] If the preset network response delay time is exceeded, the decision instruction set of the IT equipment will be adjusted again.

[0130] After executing the decision instruction set of the IT device, the time delay fluctuation range of the IT device can be re-statistically analyzed, and the preset network response delay time of the IT device can be obtained. Then, it is determined whether the time delay fluctuation range exceeds the preset network response delay time. If it exceeds the preset network response delay time, it indicates that the IT device is still a congested or faulty node. Therefore, the decision instruction set of the IT device can be adjusted again to perform precise maintenance on the IT device, ensuring that maintenance can be performed automatically and in a timely manner when the IT device is faulty or congested.

[0131] The predicted time delay fluctuation range is compared with the preset network response delay time LT. If the predicted delay exceeds the tolerance threshold LT, a secondary resource migration strategy is triggered. Assuming the maximum predicted delay is Latency max = 200ms and the tolerance threshold is LT = 150ms, a secondary resource migration is triggered to readjust resource allocation, i.e., readjust the decision instruction set to reduce latency.

[0132] In some embodiments, the method further includes:

[0133] The multimodal operation data is stored in correspondence with the decision instruction set of the IT equipment to form a decision instruction log;

[0134] The IT equipment is marked on the decision log.

[0135] By storing multimodal operational data in correspondence with the decision instruction set of the IT equipment, a decision instruction log can be automatically generated. Then, the IT equipment's identifier can be marked on the decision log, making it easy to call the decision logs of different IT equipment at any time for timely and accurate maintenance of the IT equipment.

[0136] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this disclosure is not limited to the described order of actions, because according to this disclosure, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this disclosure.

[0137] The above is an introduction to the method embodiments. The following describes the solution described in this disclosure further through device embodiments.

[0138] Figure 2A block diagram of a multimodal IT equipment operation and maintenance apparatus 200 according to an embodiment of the present disclosure is shown. Figure 2 As shown, the device 200 includes:

[0139] Acquisition module 210 is used to acquire multimodal operating data of IT equipment;

[0140] The acquisition module 220 is used to acquire the operating characteristics of the IT equipment based on the multimodal operating data;

[0141] The calculation module 230 is used to calculate the autonomy level index of the IT equipment based on the operating characteristics. The autonomy level index includes: software anomaly accumulation value, network stability coefficient, and hardware load balancing degree.

[0142] The generation module 240 is used to generate a set of decision instructions for the IT equipment based on the autonomy level index. The set of decision instructions includes the repair priority and resource allocation strategy of the IT equipment.

[0143] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the described module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0144] According to embodiments of the present disclosure, the present disclosure also provides an electronic device and a non-transitory computer-readable storage medium storing computer instructions.

[0145] Figure 3 A schematic block diagram of an electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0146] Device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 802 or a computer program loaded from storage unit 808 into random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0147] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0148] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as method 100. For example, in some embodiments, method 100 may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of method 100 described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform method 100 by any other suitable means (e.g., by means of firmware).

[0149] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0150] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0151] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0152] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0153] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0154] Computing systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0155] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0156] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A multimodal IT equipment operation and maintenance method, characterized in that, include: Collect multimodal operational data from IT equipment; Based on the multimodal operation data, the operating characteristics of the IT equipment are obtained; The autonomy level index of the IT equipment is calculated based on the operational characteristics. The autonomy level index includes: software anomaly accumulation value, network stability coefficient, and hardware load balancing degree. Based on the autonomy level index, a decision instruction set for the IT equipment is generated, which includes the repair priority and resource allocation strategy of the IT equipment.

2. The method as described in claim 1, characterized in that, The multimodal operation data of the collected IT equipment includes: Access the exception logs of the IT equipment; Extract the error type, frequency of occurrence, and stack trace from the exception log; Collect network traffic time-series data of the IT equipment; Based on the network traffic time-series data, calculate the self-similarity coefficient and burst traffic percentage of the IT device; Determine whether a virtual machine is installed on the IT device; If virtual machines are installed on the IT equipment, the frequency and time distribution of virtual machine hot migration are statistically analyzed.

3. The method as described in claim 2, characterized in that, The operational characteristics of the IT equipment include: a first operational characteristic, a second operational characteristic, and a third operational characteristic; The step of obtaining the operating characteristics of the IT equipment based on the multimodal operating data includes: The cumulative risk value is calculated by performing a three-dimensional weighted average of the error type, occurrence frequency, and stack trace in the anomaly log. The cumulative risk value is determined as the first operational characteristic; Based on the historical traffic data of the IT device, determine the average traffic data of the IT device; Calculate the traffic offset based on the network traffic time-series data and the average traffic data; Based on the self-similarity coefficient and the proportion of burst traffic, calculate the joint contribution of the IT device to network congestion; The combined contribution of the traffic offset and the IT device to network congestion is determined as the second operational characteristic; Calculate the resource liquidity index based on the virtual machine hot migration frequency and the migration time distribution; The resource liquidity index is determined as the third operating characteristic; The calculation of the autonomy level index of the IT equipment based on the operational characteristics includes: The autonomy level index of the IT device is calculated based on the first operating characteristic, the second operating characteristic, and the third operating characteristic.

4. The method as described in claim 3, characterized in that, The step of calculating the autonomy level index of the IT equipment based on the first operational characteristic, the second operational characteristic, and the third operational characteristic includes: The cumulative risk value is dynamically weighted with a preset anomaly threshold to obtain the cumulative software anomaly value of the IT equipment; A network stability coefficient is constructed based on the traffic offset and the joint contribution of the IT device to network congestion. Calculate the hardware load balancing degree based on the resource liquidity index.

5. The method as described in claim 4, characterized in that, The resource allocation strategy includes: network topology adjustment instructions; the generation of the decision instruction set for the IT equipment based on the autonomy level index includes: The software anomaly accumulation value, the network stability coefficient, and the hardware load balancing degree are input into a multi-objective optimization model, and the repair priority is calculated using the ideal values ​​of preset key indicators as constraints. The IT equipment is repaired according to the repair priority, and redundant service nodes are allocated to the IT equipment based on the resource liquidity index. Calculate the stability difference between the network stability coefficient and the preset stability threshold; Determine the dynamic topology of the IT device; Based on the stability difference and the dynamic topology map, a network topology adjustment instruction is generated, which includes path rerouting and bandwidth reallocation.

6. The method as described in claim 1, characterized in that, The method further includes: Execute the decision instruction set of the IT equipment; Recalculate the time latency fluctuation range of the aforementioned IT equipment; Obtain the preset network response latency time of the IT device; Determine whether the time delay fluctuation range exceeds the preset network response delay time; If the preset network response delay time is exceeded, the decision instruction set of the IT equipment will be adjusted again.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: The multimodal operation data is stored in correspondence with the decision instruction set of the IT equipment to form a decision instruction log; The IT equipment is marked on the decision log.

8. A multimodal IT equipment operation and maintenance device, characterized in that, include: The data acquisition module is used to collect multimodal operational data from IT equipment. The acquisition module is used to acquire the operating characteristics of the IT equipment based on the multimodal operating data; The calculation module is used to calculate the autonomy level index of the IT equipment based on the operating characteristics. The autonomy level index includes: software anomaly accumulation value, network stability coefficient, and hardware load balancing degree. The generation module is used to generate a set of decision instructions for the IT equipment based on the autonomy level index. The set of decision instructions includes the repair priority and resource allocation strategy of the IT equipment.

9. An electronic device, characterized in that, include: Memory and processor The memory stores a computer program, and when the processor executes the program, it implements the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor corresponding to the electronic device, the electronic device is able to implement the multimodal IT equipment operation and maintenance method as described in any one of claims 1-7.

Images