Virtual desktop fault processing method, electronic device, storage medium and program product

Abstract

Embodiments of the present application provide a virtual desktop fault processing method, an electronic device, a storage medium and a program product. The method comprises: obtaining structured information and unstructured information of a virtual desktop; inputting the structured information and the unstructured information into a preset fault processing model for prediction processing to obtain fault information and fault solution mode information of the virtual desktop; and sending the fault information and / or the fault solution mode information of the virtual desktop to a client. The method is used to achieve the technical effect of improving the virtual desktop fault processing efficiency.

Description

Technical Field

[0001] This application relates to the field of virtual desktops, and more particularly to a virtual desktop fault handling method, electronic device, storage medium, and program product. Background Technology

[0002] With the continuous development of big data and cloud computing technologies, virtual desktop technology is becoming increasingly mature. A virtual desktop, also known as virtual desktop infrastructure or hosted desktop, is a server-based computing model. In this model, the user's desktop environment is not stored on their local computer but is centrally hosted on a remote server. Users can access their personalized virtual desktop via a network connection using any network-connected device.

[0003] In existing technologies, troubleshooting virtual desktops mainly relies on operations and maintenance administrators to make manual judgments and handle issues based on alarm information and user feedback.

[0004] However, in existing technologies, historical operation and maintenance data and administrator experience have not been scientifically and systematically integrated, making it difficult to transform them into structured, effective, and usable information. Relying solely on manual processing of fault information is both time-consuming and inefficient. Summary of the Invention

[0005] This application provides a virtual desktop fault handling method, electronic device, storage medium, and program product to achieve the technical effect of improving the efficiency of virtual desktop fault handling.

[0006] In a first aspect, embodiments of this application provide a virtual desktop fault handling method, including:

[0007] Obtain structured and unstructured information of the virtual desktop; where structured information represents data of the virtual desktop with a preset format, and unstructured information represents data generated during the operation of the virtual desktop;

[0008] Structured and unstructured information are input into a pre-defined fault handling model for predictive processing to obtain fault information and fault resolution information of the virtual desktop. The fault information includes at least one fault problem of the virtual desktop, and the fault problem has a fault type. The fault resolution information includes one or more of the following: fault solution information, fault troubleshooting mind map, and health status information.

[0009] Send virtual desktop fault information and / or fault resolution information to the client.

[0010] Secondly, embodiments of this application provide a fault handling device for a virtual desktop, comprising:

[0011] The acquisition module is used to acquire structured and unstructured information about the virtual desktop.

[0012] The processing module is used to input structured and unstructured information into a preset fault handling model for predictive processing, so as to obtain fault information and fault resolution information of the virtual desktop.

[0013] The sending module is used to send virtual desktop fault information and / or fault resolution information to the client.

[0014] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0015] The memory stores computer-executed instructions;

[0016] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0017] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0018] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0019] The virtual desktop fault handling method, electronic device, storage medium, and program product provided in this application obtain structured and unstructured information about the virtual desktop to achieve comprehensive information about the virtual desktop, thereby more accurately locating fault problems. Furthermore, the structured and unstructured information are input into a preset fault handling model for predictive processing to obtain fault information and fault resolution information of the virtual desktop. The fault handling model can quickly and accurately predict faults and solutions, improving the efficiency of fault handling. Finally, the fault information and / or fault resolution information of the virtual desktop are sent to the client, realizing real-time information sharing. By sending the fault information and fault resolution information to the client in a timely manner, the efficiency of virtual desktop fault handling is accelerated. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0021] Figure 1Flowchart of the virtual desktop troubleshooting method provided in this application Figure 1 ;

[0022] Figure 2 Flowchart of the virtual desktop troubleshooting method provided in this application Figure 2 ;

[0023] Figure 3 A flowchart illustrating the process of constructing a fault problem knowledge base for the virtual desktop fault handling method provided in this application;

[0024] Figure 4 A schematic diagram of the structure of the fault handling device for the virtual desktop provided in this application;

[0025] Figure 5 A hardware diagram of the fault handling device for the virtual desktop provided in this application.

[0026] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0027] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of methods and approaches consistent with some aspects of this application as detailed in the appended claims.

[0028] With the widespread application of desktop cloud technology, virtual desktop fault handling has become a crucial component of operations and maintenance management. Traditional fault handling methods primarily rely on operations administrators manually judging and processing information based on alarms and user feedback. This inefficiency has long been a major pain point in the field. Non-critical alarm information is abundant and lacks strong relevance, requiring processing for effective utilization; therefore, it is often underutilized in actual operations and maintenance. Furthermore, historical operations and maintenance data and administrator experience have not been scientifically and systematically integrated; this valuable information remains in a raw state, difficult to transform into structured and effective information. Therefore, existing technologies suffer from low efficiency in virtual desktop fault handling.

[0029] To address the aforementioned technical issues, the virtual desktop fault handling method, electronic device, storage medium, and program product provided in this application acquire structured and unstructured information about the virtual desktop to achieve comprehensive information about the virtual desktop, thereby more accurately locating fault problems. Furthermore, the structured and unstructured information are input into a preset fault handling model for predictive processing to obtain fault information and fault resolution methods for the virtual desktop. The fault handling model can quickly and accurately predict faults and resolution methods, improving the efficiency of fault handling. Finally, the fault information and / or fault resolution methods of the virtual desktop are sent to the client, achieving real-time information sharing. By promptly sending fault information and fault resolution methods to the client, the efficiency of virtual desktop fault handling is accelerated.

[0030] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0031] Figure 1 Flowchart of the virtual desktop troubleshooting method provided in this application Figure 1 ,like Figure 1 As shown, the method includes:

[0032] S101. Obtain structured and unstructured information about the virtual desktop;

[0033] In this embodiment, structured information represents virtual desktop data with a preset format. Structured information refers to data with a fixed format and predefined model, typically stored in a relational database. This type of information can be easily searched, classified, and analyzed through database queries. Structured information usually follows certain rules and standards, making the relationships between data clear and explicit. The storage method of structured information makes data retrieval and analysis relatively simple and efficient. Unstructured information represents data generated during the operation of the virtual desktop. Unstructured information does not have a fixed format or model. It includes all formatted and unformatted data, such as text, images, audio, and video. Unstructured information is usually more complex and diverse, making it difficult to search and analyze using traditional database query methods. Through text mining techniques, we can extract useful information from large amounts of text data.

[0034] S102. Input structured and unstructured information into a preset fault handling model for predictive processing to obtain fault information and fault resolution information of the virtual desktop.

[0035] In this embodiment, the acquired structured and unstructured information are input into a trained fault handling model. This model can use this information to quickly and accurately locate potential faults in the virtual desktop and provide effective methods for resolving these problems. The fault information includes at least one fault of the virtual desktop, and each fault has a fault type. The fault resolution information includes one or more of the following: fault solution information, a troubleshooting mind map, and health status information.

[0036] S103. Send the virtual desktop fault information and / or fault resolution information to the client.

[0037] In this embodiment, the information sent to the client may be virtual desktop fault information, virtual desktop fault information and fault resolution information, or one or more of the following: virtual desktop fault information and fault resolution information.

[0038] The virtual desktop fault handling method provided in this application acquires structured and unstructured information about the virtual desktop to achieve comprehensive information about the virtual desktop, thereby more accurately locating the fault. Furthermore, the structured and unstructured information is input into a preset fault handling model for predictive processing to obtain fault information and fault resolution methods for the virtual desktop. The fault handling model can quickly and accurately predict faults and solutions, improving the efficiency of fault handling. Finally, the fault information and / or fault resolution methods of the virtual desktop are sent to the client, realizing real-time information sharing. By promptly sending fault information and fault resolution methods to the client, the efficiency of virtual desktop fault handling is accelerated.

[0039] Figure 2 Flowchart of the virtual desktop troubleshooting method provided in this application Figure 2 ,like Figure 2 As shown, in this embodiment... Figure 1 Based on the embodiments, the virtual desktop fault handling method is described in detail. The acquisition of unstructured and structured information is implemented according to step S201; the input of structured and unstructured information into a preset fault handling model to obtain virtual desktop fault information and fault resolution methods is implemented according to steps S202-S204; and the sending of the obtained prediction information to the client is implemented according to step S205. Figure 2 As shown, the virtual desktop fault handling method provided in this embodiment includes:

[0040] S201. Detect structured and unstructured information of the virtual desktop at a preset time interval; and / or, receive unstructured information of the virtual desktop sent by the client and obtain structured information of the virtual desktop;

[0041] In this embodiment, there are two main approaches to acquiring unstructured and structured information: one is active detection, which involves detecting the virtual desktop at preset time intervals to obtain both structured and unstructured information, and then predicting virtual desktop faults based on this information; the other is passive acquisition, which involves the server providing a ChatOps-based intelligent operation and maintenance assistant to the virtual desktop client. This involves integrating team collaboration, workflows, and automation tools into a chat tool. Through ChatOps, team members can perform operations, view system status, and initiate automated tasks within the chat application, thereby improving team collaboration efficiency and transparency. The client can directly provide unstructured information about the virtual desktop to the server through the intelligent operation and maintenance assistant. This unstructured information represents virtual desktop faults. After receiving unstructured information from the client, the server acquires the structured information of the virtual desktop. Then, the acquired structured information and the unstructured information sent by the client are input into a preset fault handling model for predictive processing to obtain the fault type and the solution for the virtual desktop fault. Optionally, unstructured information includes one or more of the following: historical user feedback information, virtual desktop cloud corpus and thesaurus, virtual desktop forums, and historical operation and maintenance platform alarm information; structured information includes one or more of the following: performance indicators, historical operation and maintenance data, virtual machine configuration data, application data, and resource usage data. By actively investigating virtual desktop faults and passively obtaining fault issues provided by clients, the combination of these two investigation methods can fundamentally and effectively improve the timeliness and accuracy of virtual desktop fault handling.

[0042] S202. Input structured and unstructured information into a preset fault handling model for predictive processing to obtain information on the fault problems of the virtual desktop and the fault solutions for the fault problems.

[0043] In this embodiment, the fault handling model can be trained in the following way, by collecting a training dataset; wherein, the training dataset includes historical unstructured information and historical structured information; the historical unstructured information includes, but is not limited to, historical user feedback information, virtual desktop cloud corpus and thesaurus, virtual desktop forum, and historical operation and maintenance platform alarm information; the historical structured data includes, but is not limited to, performance indicators, historical operation and maintenance data, virtual machine configuration data, application data, and resource usage data; at the same time, sensitive information in the training dataset needs to be desensitized. Furthermore, feature extraction and data cleaning are performed on both historical unstructured and historical structured information to obtain processed historical unstructured and processed historical structured information. Feature extraction on the historical structured data includes, but is not limited to, statistical features of numerical data and one-hot encoding of categorical data. Unstructured data is processed using techniques such as the bag-of-words model for text processing and image processing feature extraction. Data cleaning includes, but is not limited to, handling missing values, outliers, duplicate values, and noise. Further, feature fusion is performed on the processed historical unstructured and processed historical structured information to determine the fused feature data. Data transformation is then performed on the fused feature data to better suit model training. Fusion includes, but is not limited to, standardizing the data (scaling it to a similar range to eliminate the influence of different dimensions) and converting categorical data into numerical data. After data transformation of the fused feature data, a target training set is obtained. At this point, the unstructured data has been transformed into structured data. The target training set, obtained through data processing, includes multiple fault problems and corresponding fault solutions for each fault problem. Further, data analysis is performed on the target training set. By performing predictive modeling and regression analysis on the structured data and text classification and image recognition on the unstructured data, a fault problem knowledge base is constructed. The fault problem knowledge base includes multiple clusters of similar problems. The initial fault handling model is trained based on the target training set to obtain the preset fault handling model.

[0044] Optionally, the flowchart for constructing a fault problem knowledge base is as follows: Figure 3 As shown, the target training set includes multiple fault problems and fault solution information corresponding to each fault problem. The similarity between each fault problem in the target training set is calculated to obtain the similarity results between multiple fault problems. The similarity results between multiple fault problems are used to classify faults to obtain multiple similar problem clusters. Each similar problem cluster represents a fault type, and each similar problem cluster includes multiple fault problems and fault solution information corresponding to each fault problem.

[0045] S203. Calculate the similarity between fault problems, determine the cluster of similar problems, determine the fault type of the fault problem based on the cluster of similar problems, and send the fault type of the fault problem and the fault solution information of other fault problems in the fault problem to the client.

[0046] In this embodiment, as Figure 3 As shown, by calculating the similarity between each fault problem and each fault problem in the fault problem knowledge base, similar problem clusters are identified. The fault type is then determined based on these clusters. Furthermore, each similar problem contains corresponding historical fault solution information. This method can predict the fault of the current virtual desktop, identify multiple similar problems using the fault problem knowledge base in the fault handling model, and provide comprehensive solution information to the client by combining historical solution information, ensuring the comprehensiveness of the virtual desktop's fault handling. Simultaneously, after providing the predicted information to the client, this method aggregates the user's processing and feedback information into new fault problems, optimizes the similar problem clusters, and updates the fault problem knowledge base, achieving timely updates to the knowledge base.

[0047] S204. Based on the fault handling model and fault problems, structured and unstructured information are processed to generate a mind map for fault troubleshooting and health status information.

[0048] In this embodiment, the fault handling model can utilize an NLP analysis engine. Natural Language Processing (NLP) is an interdisciplinary field combining artificial intelligence and linguistics, aiming to enable computers to understand, analyze, and generate human language. Using NLP as a tool, the fault handling model can generate a troubleshooting mind map and virtual desktop health status information from the acquired structured and unstructured information, as well as a fault problem knowledge base. The troubleshooting mind map includes a detailed troubleshooting process and a location view. The troubleshooting process visually demonstrates the troubleshooting approach for virtual desktop faults. This troubleshooting approach helps operations and maintenance administrators fundamentally solve fault problems. In one possible implementation, the virtual desktop health status can be divided into different health levels, such as first health level, second health level, third health level, and fourth health level. The lower the health level, the more severe the fault. When the health status reaches below the third health level, a corresponding emergency alarm service is provided to the operations and maintenance administrator's client to ensure the normal operation of the virtual desktop.

[0049] S205. Send the fault solution information from the fault information and fault resolution information of the virtual desktop to the client corresponding to the ordinary user; send the fault information and fault resolution information of the virtual desktop to the client corresponding to the administrator user.

[0050] In this embodiment, the server provides a ChatOps-based intelligent operation and maintenance assistant for the virtual desktop clients. This assistant offers two types of intelligent support: after predicting a virtual desktop fault using a fault handling model, the server sends the fault type and solution information to the client for regular users, enabling them to resolve the problem independently. Simultaneously, the server sends the fault information and solution details to the client for administrators, allowing administrators to gain a more comprehensive understanding of the virtual desktop faults and improve efficiency and accuracy. By providing this information to different clients, regular users can quickly resolve virtual desktop problems, accelerating the troubleshooting process, while administrators gain a comprehensive understanding of the issues and can use troubleshooting mind maps and other methods to pinpoint the problem, ultimately resolving the virtual desktop faults at their root.

[0051] The virtual desktop fault handling method provided in this application obtains virtual desktop information through two methods: actively detecting structured and unstructured information of the virtual desktop at preset time intervals; and / or receiving unstructured information of the virtual desktop sent by the client and obtaining structured information of the virtual desktop. The structured and unstructured information are input into a preset fault handling model for predictive processing to obtain the virtual desktop fault problem and fault solution information. Similarity calculations are performed between fault problems to determine similar problem clusters, and the fault type of the fault problem is determined based on the similar problem clusters. The fault type of the fault problem and fault solution information of other fault problems within the fault problem are sent to the client. Based on the fault handling model and the fault problem, the structured and unstructured information are processed to generate a fault troubleshooting mind map and health status information. This enables the sending of fault solution information from the virtual desktop fault information and fault solution information to the client corresponding to ordinary users, and the sending of virtual desktop fault information and fault solution information to the client corresponding to administrator users. This method combines proactive troubleshooting of virtual desktops with reactive troubleshooting based on client-provided fault reports. By acquiring virtual desktop information through a combination of these two approaches, and determining the fault details and solutions based on a fault handling model, this method enables ordinary users to quickly resolve virtual desktop issues, accelerating the problem-solving process. Simultaneously, it allows operations and maintenance administrators to gain a comprehensive understanding of the problems, enabling them to pinpoint faults using troubleshooting mind maps and other methods, thereby fundamentally resolving virtual desktop issues.

[0052] Figure 4 A schematic diagram of the structure of the fault handling device for the virtual desktop provided in this application is shown below. Figure 4 As shown, the virtual desktop fault handling device 40 provided in this embodiment includes:

[0053] The acquisition module 401 is used to acquire structured and unstructured information about the virtual desktop.

[0054] The processing module 402 is used to input structured information and unstructured information into a preset fault handling model for predictive processing, so as to obtain fault information and fault resolution information of the virtual desktop.

[0055] The sending module 403 is used to send the virtual desktop's fault information and / or fault resolution information to the client.

[0056] In one possible implementation, the acquisition module 401 is further used for:

[0057] Detect structured and unstructured information of the virtual desktop at preset time intervals; and / or,

[0058] Receive unstructured information about the virtual desktop sent by the client, and obtain structured information about the virtual desktop.

[0059] In one possible implementation, the processing module 402 is further configured to:

[0060] Based on a pre-defined fault handling model, structured and unstructured information are processed to obtain information on virtual desktop faults and fault solutions.

[0061] Calculate the similarity between fault problems to determine similar problem clusters, where similar problem clusters include other fault problems with a similarity greater than a preset similarity to the fault problem.

[0062] Determine the fault type of the fault problem based on similar problem clusters;

[0063] Send the fault type and fault solution information for other faults within the fault to the client;

[0064] Based on the fault handling model and fault problems, structured and unstructured information are processed to generate a fault troubleshooting mind map and health status information; the fault troubleshooting mind map includes the fault troubleshooting process and location view.

[0065] In one possible implementation, the processing module 402 is further configured to:

[0066] Collect a training dataset; the training dataset includes historical unstructured information and historical structured information;

[0067] Feature extraction and data cleaning are performed on both the unstructured and structured historical information to obtain the processed unstructured and structured historical information, respectively.

[0068] Feature fusion is performed on the processed unstructured historical information and the processed structured historical information to determine the fused feature data. After data transformation, the fused feature data is used to obtain the target training set. The target training set includes multiple fault problems and fault solution information corresponding to each fault problem.

[0069] Data analysis is performed on the target training set to construct a fault problem knowledge base; the fault problem knowledge base includes multiple clusters of similar problems;

[0070] The initial fault handling model is trained based on the target training set to obtain the preset fault handling model.

[0071] In one possible implementation, the processing module 402 is further configured to:

[0072] For each fault problem in the target training set, calculate the similarity between problems to obtain the similarity results between multiple fault problems;

[0073] Fault classification is performed on the similarity results among multiple fault problems to obtain multiple similar problem clusters. Each similar problem cluster represents a fault type and includes multiple fault problems and fault solution information corresponding to each fault problem.

[0074] In one possible implementation, the processing module 402 is further configured to:

[0075] Acquire unstructured information, which includes one or more of the following: historical user feedback information, virtual desktop cloud corpus and thesaurus, virtual desktop forum, and historical operation and maintenance platform alarm information;

[0076] Obtain structured information, which includes one or more of the following: performance metrics, historical operation and maintenance data, virtual machine configuration data, application data, and resource usage data.

[0077] In one possible implementation, the sending module 403 is further used for:

[0078] The fault information and troubleshooting methods of the virtual desktop are sent to the corresponding client of the ordinary user.

[0079] The system sends the virtual desktop's fault information and troubleshooting methods to the corresponding client of the administrator user.

[0080] In one possible implementation, the acquisition module 401 and the processing module 402 are further used for:

[0081] Receive unstructured information sent by the client, in which the unstructured information sent by the client indicates a problem with the virtual desktop;

[0082] Obtain structured information about the virtual desktop;

[0083] The acquired structured information and the unstructured information sent by the client are input into a preset fault handling model for predictive processing to obtain information on the fault type and the solution for the virtual desktop.

[0084] The fault handling device for the virtual desktop provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0085] Figure 5A hardware diagram of the fault handling device for the virtual desktop provided in this application. Figure 5 As shown, the electronic device 50 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the device 50 further includes a communication component 503. The processor 501, memory 502, and communication component 503 are connected via a bus 504.

[0086] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0087] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0088] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0089] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0090] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0091] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0092] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0093] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0094] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0095] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, methods, or units, and may be electrical, mechanical, or other forms.

[0096] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0097] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0098] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0099] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0100] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for handling virtual desktop malfunctions, characterized in that, include: Obtain structured and unstructured information of the virtual desktop; wherein, the structured information represents data of the virtual desktop with a preset format, and the unstructured information represents data generated during the operation of the virtual desktop, and the unstructured information includes one or more of the following: historical user feedback information, virtual desktop cloud corpus and thesaurus, virtual desktop forum, and historical operation and maintenance platform alarm information; The structured information and the unstructured information are input into a preset fault handling model for predictive processing to obtain fault information and fault resolution information of the virtual desktop; wherein, the fault information includes at least one fault problem of the virtual desktop, and the fault problem has a fault type; the fault resolution information includes one or more of the following: fault solution information, fault troubleshooting mind map, health status information; The fault information of the virtual desktop, and / or the fault resolution information, are sent to the client; The structured information and the unstructured information are input into a preset fault handling model for prediction processing to obtain fault information and fault resolution methods for the virtual desktop, including: Based on the preset fault handling model, the structured information and the unstructured information are processed to obtain the fault problems of the virtual desktop and the fault solutions for the fault problems; The similarity between the fault problems is calculated to determine the similar problem clusters of the fault problems, wherein the similar problem clusters of the fault problems include other fault problems with a similarity greater than a preset similarity with the fault problems; The fault type of the fault problem is determined based on the cluster of similar problems; Send the fault type of the fault problem and fault solution information for other fault problems within the fault problem to the client; Based on the fault handling model and the fault problem, the structured information and the unstructured information are processed to generate the fault troubleshooting mind map and the health status information; wherein, the fault troubleshooting mind map includes a fault troubleshooting process and a location view. Sending the fault information of the virtual desktop, and / or the fault resolution information, to the client includes: The fault information of the virtual desktop and the fault solution information in the fault resolution information are sent to the client corresponding to the ordinary user; The fault information of the virtual desktop and the fault resolution information are sent to the client corresponding to the administrator user.

2. The method according to claim 1, characterized in that, Obtain structured and unstructured information about the virtual desktop, including: Detect the structured and unstructured information of the virtual desktop at preset time intervals; and / or, Receive unstructured information about the virtual desktop sent by the client, and obtain structured information about the virtual desktop.

3. The method according to claim 1, characterized in that, The method further includes: Collect a training dataset; wherein the training dataset includes historical unstructured information and historical structured information; Feature extraction and data cleaning are performed on the unstructured historical information and the structured historical information respectively to obtain the processed unstructured historical information and the processed structured historical information. Feature fusion is performed on the processed unstructured historical information and the processed structured historical information to determine the fused feature data. After data transformation, the fused feature data is used to obtain the target training set. The target training set includes multiple fault problems and fault solution information corresponding to each fault problem. Data analysis is performed on the target training set to construct a fault problem knowledge base; wherein, the fault problem knowledge base includes multiple clusters of similar problems; The initial fault handling model is trained based on the target training set to obtain the preset fault handling model.

4. The method according to claim 3, characterized in that, Data analysis is performed on the target training set to construct a fault problem knowledge base, including: For each fault problem in the target training set, calculate the similarity between problems to obtain the similarity results between multiple fault problems; The similarity results among the multiple fault problems are classified to obtain multiple similar problem clusters, wherein each similar problem cluster represents a fault type, and each similar problem cluster includes multiple fault problems and fault solution information corresponding to each fault problem.

5. The method according to any one of claims 1-4, characterized in that, The structured information includes one or more of the following: performance metrics, historical operation and maintenance data, virtual machine configuration data, application data, and resource usage data.

6. The method according to any one of claims 1-4, characterized in that, The method further includes: The system receives unstructured information sent by the client, wherein the unstructured information sent by the client indicates a malfunction of the virtual desktop. Obtain the structured information of the virtual desktop; The acquired structured information and the unstructured information sent by the client are input into the preset fault handling model for prediction processing to obtain the fault type of the fault problem and the fault resolution method information of the virtual desktop.

7. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-6.

9. A computer program product, characterized in that, Includes a computer program, which, when executed by a processor, is used to implement the method as described in any one of claims 1-6.

Images