Method and device for determining fault removal information of server, equipment and storage medium

Abstract

The invention discloses a method, device and equipment for determining fault removal information of a server and a storage medium, and belongs to the field of operation and maintenance. According to the embodiment, the MR equipment is used for collecting server fault data; generating a 3D model of a server fault scene according to the data, and marking fault information of the fault server based on the data; obtaining a knowledge graph of troubleshooting including the fault scene of the server, the fault information of the server and the troubleshooting information from the cloud server; matching the fault information with fault information in a knowledge graph to obtain first fault information and fault removal information corresponding to the first fault information; comparing the 3D model with a fault scene in the knowledge graph to determine second fault information of the server; and determining the troubleshooting information corresponding to the first fault information which is the same as the second fault information as the target troubleshooting information so as to carry out troubleshooting on the server based on the target troubleshooting information, thereby improving the efficiency and accuracy of server fault diagnosis and operation and maintenance.

Description

Technical Field

[0001] The present application belongs to the field of operation and maintenance, and in particular, relates to a method, apparatus, device, computer-readable storage medium, and computer program product for determining server troubleshooting information. Background Art

[0002] With the rapid development of the Internet and cloud computing, the demand for data processing is increasing. As the core equipment for data processing, the stability of the server is crucial. Therefore, it is necessary to conduct server fault diagnosis and operation and maintenance in a timely and effective manner. The application of Mixed Reality (MR) technology and point cloud 3D reconstruction technology in fault diagnosis and maintenance scenarios is gradually showing great potential.

[0003] The existing methods of fault diagnosis and maintenance using MR technology and point cloud 3D reconstruction technology are mainly focused on the intelligent operation and maintenance of building mechanical and electrical facilities. For example, the remote fault diagnosis system of air conditioning system based on MR technology has been developed and applied to a certain extent. However, the existing fault diagnosis and maintenance methods are less applicable when applied to the application scenario of server troubleshooting, which leads to the inability to accurately operate and maintain server faults. Summary of the invention

[0004] Embodiments of the present application provide a method, apparatus, device, computer-readable storage medium, and computer program product for determining server fault troubleshooting information, which can accurately perform operation and maintenance on server faults.

[0005] In a first aspect, an embodiment of the present application provides a method for determining server troubleshooting information, the method comprising:

[0006] Use mixed reality MR devices to collect data on server failures;

[0007] Generate a 3D model of the server failure scenario based on the data, and annotate the fault information of the faulty server based on the data;

[0008] Obtain a troubleshooting knowledge graph from the cloud server, the knowledge graph including server failure scenarios, server failure information, and troubleshooting information;

[0009] Matching the fault information with the fault information in the knowledge graph to obtain first fault information and fault troubleshooting information corresponding to the first fault information;

[0010] Compare the 3D model with the fault scenario in the knowledge graph to determine the second fault information of the server;

[0011] The troubleshooting information corresponding to the first fault information that is the same as the second fault information is determined as the target troubleshooting information, so as to troubleshoot the server based on the target troubleshooting information.

[0012] In an achievable implementation, after collecting the data of the server failure by using the MR device, the method further includes:

[0013] Convert the data into target data of the target coordinate system;

[0014] The target data is sent to the cloud server, so that the cloud server updates the knowledge graph for troubleshooting based on the target data to obtain a knowledge graph.

[0015] In one practicable implementation, the data includes point cloud data, environmental data, and structural attribute data of the server; and generating a 3D model of the server failure scenario based on the data includes:

[0016] According to the data correspondence between point cloud data, environmental data and structural attribute data, the regional global features of the server in the data are extracted through a point cloud processing network model based on deep learning;

[0017] According to the regional global features and the environmental features and structural attribute features of the server, the self-attention mechanism is used to fuse the time series and space to obtain the regional fusion features of the server. The environmental features are determined by the environmental data, and the structural attribute features are determined by the structural attribute data.

[0018] According to the regional fusion features corresponding to the point cloud data, the point cloud data is segmented into point cloud data of different regions using a segmentation network, and the point cloud data of different regions are classified to obtain the corresponding attribute information;

[0019] Based on the point cloud data in the cloud server, the point cloud data in different areas are completed to obtain the completed point cloud data, and the point cloud data in the cloud server is determined by the attribute information of the point cloud data in different areas;

[0020] Three-dimensional reconstruction is performed based on the completed point cloud data to obtain a 3D model.

[0021] In an achievable implementation, before extracting the regional global features of the server in the data through a deep learning-based point cloud processing network model according to the data correspondence between the point cloud data and the environmental data and the structural attribute data, the method further includes:

[0022] The point cloud data, environment data and structure attribute data of the server are preprocessed, wherein the preprocessing includes at least one of filtering, denoising, and spatial and temporal data registration.

[0023] In an achievable implementation, the fault information includes a fault type and a fault location; the fault information is matched with the fault information in the knowledge graph to obtain first fault information, including:

[0024] Match the fault type with the fault type in the knowledge graph;

[0025] Match the fault location with the fault location in the knowledge graph;

[0026] The fault type and fault location that match the fault type and fault location in the knowledge graph are used as the first fault information.

[0027] In an achievable implementation, after determining that the troubleshooting information corresponding to the first fault information that is the same as the second fault information is the target troubleshooting information, the method further includes:

[0028] Displays the 3D model and target troubleshooting information on the Display page.

[0029] In an achievable implementation, after the display page displays the 3D model and the target troubleshooting information, the method further includes:

[0030] Rendering of 3D models and target troubleshooting information;

[0031] The rendered 3D model and target troubleshooting information are displayed on the display interface.

[0032] In one possible implementation, the method further includes:

[0033] Obtain the location information of the MR device and the point cloud location information of the server;

[0034] Determining force feedback information based on the position of the MR device and the point cloud position information;

[0035] Rendering force feedback information;

[0036] The rendered 3D model, target troubleshooting information, and force feedback information are displayed on the display interface.

[0037] In one possible implementation, the method further includes:

[0038] After troubleshooting the server based on the target troubleshooting information is completed, receiving correction information of the target troubleshooting information from the user;

[0039] The target troubleshooting information is corrected based on the correction information.

[0040] In a second aspect, an embodiment of the present application provides a device for determining server troubleshooting information, the device comprising:

[0041] A collection module, used for collecting data of server failures by using MR equipment;

[0042] A generation module is used to generate a 3D model of the server failure scenario based on the data, and to annotate the failure information of the failed server based on the data;

[0043] An acquisition module is used to acquire a knowledge graph for troubleshooting from a cloud server, wherein the knowledge graph includes server failure scenarios, server failure information, and troubleshooting information;

[0044] A matching module, used to match the fault information with the fault information in the knowledge graph to obtain first fault information and fault elimination information corresponding to the first fault information;

[0045] A comparison module, used to compare the 3D model with the fault scenario in the knowledge graph to determine the second fault information of the server;

[0046] The determination module is used to determine that the troubleshooting information corresponding to the first fault information that is the same as the second fault information is the target troubleshooting information, so as to troubleshoot the server based on the target troubleshooting information.

[0047] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement a method for determining server troubleshooting information as in any one of the implementations of the first aspect.

[0048] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, a method for determining server troubleshooting information as in any one of the embodiments of the first aspect is implemented.

[0049] In a fifth aspect, an embodiment of the present application provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes a method for determining server troubleshooting information as described in any one of the implementations of the first aspect.

[0050] The method, apparatus, device, computer-readable storage medium and computer program product for determining server troubleshooting information in the embodiments of the present application. The embodiment uses MR equipment to collect data on server failures, generates a 3D model of the server failure scenario based on the data, and annotates the fault information of the faulty server based on the data; the generated 3D model can more intuitively display the status of the server and its surrounding environment, and the annotation of the fault information makes the key faults more obvious, speeding up the troubleshooting. Afterwards, a knowledge graph for troubleshooting is obtained from the cloud server, the knowledge graph includes the failure scenario of the server, the failure information of the server and the troubleshooting information; then the fault information is matched with the fault information in the knowledge graph to obtain the first fault information and the troubleshooting information corresponding to the first fault information, and the 3D model is compared with the fault scenario in the knowledge graph to determine the second fault information of the server; finally, the troubleshooting information corresponding to the first fault information that is the same as the second fault information is determined as the target troubleshooting information, so as to troubleshoot the server based on the target troubleshooting information. Through information matching, we can quickly find historical cases and solutions similar to the current fault, improve the efficiency of troubleshooting, and by comparing the 3D model with the historical fault scenarios, we can further verify the accuracy of the fault judgment and ensure that the measures taken are effective solutions to practical problems. This effectively solves the problem of poor applicability of existing fault diagnosis and operation methods when applied to server troubleshooting scenarios, improves the efficiency and accuracy of server fault diagnosis and operation and maintenance, and provides a new solution for server troubleshooting. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0052] Figure 1 It is a flowchart of a method for determining server troubleshooting information provided by an embodiment of the present application;

[0053] Figure 2 It is a flowchart of a method for generating a 3D model of a server failure scenario provided by an embodiment of the present application;

[0054] Figure 3 is a schematic diagram of a server troubleshooting information system provided by an embodiment of the present application;

[0055] Figure 4 It is a structural diagram of an apparatus for determining server troubleshooting information provided by an embodiment of the present application;

[0056] Figure 5It is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0057] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0058] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0059] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0060] With the rapid development of the Internet and cloud computing, the demand for data processing is increasing. As the core equipment for data processing, the stability of the server is crucial. Therefore, it is necessary to conduct server fault diagnosis and operation and maintenance in a timely and effective manner. The application of Mixed Reality (MR) technology and point cloud 3D reconstruction technology in fault diagnosis and maintenance scenarios is gradually showing great potential.

[0061] The existing methods of fault diagnosis and maintenance using MR technology and point cloud 3D reconstruction technology are mainly focused on the intelligent operation and maintenance of building mechanical and electrical facilities. For example, the remote fault diagnosis system of air conditioning system based on MR technology has been developed and applied to a certain extent. However, the existing fault diagnosis and maintenance methods are less applicable when applied to the application scenario of server troubleshooting, which leads to the inability to accurately operate and maintain server faults.

[0062] In order to solve the problems of the prior art, the embodiments of the present application provide a method, apparatus, device, computer storage medium and computer program product for determining server fault troubleshooting information. The method for determining server fault troubleshooting information provided by the embodiments of the present application is first introduced below.

[0063] Figure 1 FIG. 1 is a flow chart showing a method for determining server troubleshooting information provided by an embodiment of the present application. Figure 1 As shown, the method includes steps S110 to S160.

[0064] S110: Collecting server failure data using MR equipment.

[0065] Various types of sensors on the MR device are used to collect data of server fault information such as server device information, scene information, and weather information at the fault site. The data type can be in various formats such as image data, video data, audio data, and depth data. Exemplarily, the MR device can be MR glasses, and a depth sensor (such as a Time-of-Flight camera or a LiDAR device) can be used to collect depth information of the fault site environment.

[0066] S120: Generate a 3D model of the server failure scenario according to the data, and annotate the failure information of the failed server based on the data.

[0067] Based on the collected server fault information data, a 3D model of the server fault scene is constructed. The construction process may include data preprocessing, feature extraction, feature fusion, semantic segmentation, point cloud data completion and other steps to complete the reconstruction of the server fault scene. The collected server fault data is annotated through automated tools to identify key parameters such as the specific type, location, and impact range of the fault to obtain the server fault information.

[0068] S130: Obtain a troubleshooting knowledge graph from the cloud server, where the knowledge graph includes server failure scenarios, server failure information, and troubleshooting information.

[0069] Obtain the existing knowledge graph for server troubleshooting from the cloud server. The knowledge graph may include server failure scenarios, server failure information, and troubleshooting information. Among them, the server failure scenarios may be typical scenarios where different types of failures may occur, including environmental conditions, server status, etc. The server failure information may be specific manifestations such as the type, location, and impact range of various failures, such as error codes, abnormal logs, and temperature anomalies. Troubleshooting information may be troubleshooting methods, steps, and suggestions for each failure, including common troubleshooting solutions and best practices. A knowledge graph may be a structured form of knowledge storage that organizes data in the form of a graph, with nodes representing entities (such as servers, failure types, etc.) and edges representing relationships between entities.

[0070] S140: Match the fault information with the fault information in the knowledge graph to obtain first fault information and troubleshooting information corresponding to the first fault information.

[0071] Compare the annotated fault information with the fault information in the knowledge graph to find the matching fault type and the corresponding troubleshooting solution. The specific process can be as follows: extract the key features of the fault information, such as error code, temperature anomaly, etc.; use the comparison algorithm to compare the fault information collected on site with the fault information in the knowledge graph to find the best matching fault type; generate the matching result to obtain the first fault information, that is, the fault information in the knowledge graph that best matches the on-site fault information.

[0072] According to the matched first fault information, the corresponding troubleshooting information is obtained from the knowledge graph. The troubleshooting information may include detailed troubleshooting steps and operation guides, recommended best practices and precautions, and similar fault handling cases for reference and reference.

[0073] S150: Compare the 3D model with the fault scenario in the knowledge graph to determine the second fault information of the server.

[0074] The generated 3D model of the server failure scenario is compared with the standard failure scenario in the knowledge graph. The specific process can be as follows: extract the key features of the 3D model of the server failure scenario, such as the physical structure of the server, the failure location, the temperature distribution, etc.; based on the key features of the 3D model of the server failure scenario and the features of the standard failure scenario in the knowledge graph, compare the 3D model with the standard failure scenario in the knowledge graph to determine the differences and similarities between the 3D model of the server failure scenario and the most matching standard failure scenario, and then confirm the fault type and specific location to obtain the second fault information, and obtain the corresponding troubleshooting information from the knowledge graph based on the second fault information obtained by comparison.

[0075] S160: Determine the troubleshooting information corresponding to the first fault information that is the same as the second fault information as the target troubleshooting information, so as to troubleshoot the server based on the target troubleshooting information.

[0076] The fault information corresponding to the first fault information or the second fault information may include multiple corresponding troubleshooting information, that is, the first fault information and the second fault information correspond to a troubleshooting information set, and the troubleshooting information in the troubleshooting information set is screened to determine the consistent troubleshooting information as the target troubleshooting information. The target troubleshooting information may include detailed troubleshooting steps, operation guides, best practices and related cases, etc., to troubleshoot the server based on the target troubleshooting information and complete the maintenance of the server.

[0077] This embodiment uses MR equipment to collect data on server failures, generates a 3D model of the server failure scenario based on the data, and annotates the fault information of the faulty server based on the data; the generated 3D model can more intuitively display the status of the server and its surrounding environment, and the annotation of the fault information makes the key faults more obvious, which speeds up the troubleshooting. After that, a knowledge graph for troubleshooting is obtained from the cloud server, and the knowledge graph includes the server's failure scenario, the server's failure information, and troubleshooting information; then the fault information is matched with the fault information in the knowledge graph to obtain the first fault information and the troubleshooting information corresponding to the first fault information, and the 3D model is compared with the fault scenario in the knowledge graph to determine the second fault information of the server; finally, the troubleshooting information corresponding to the first fault information that is the same as the second fault information is determined as the target troubleshooting information, so as to troubleshoot the server based on the target troubleshooting information. Through information matching, we can quickly find historical cases and solutions similar to the current fault, improve the efficiency of troubleshooting, and by comparing the 3D model with the historical fault scenarios, we can further verify the accuracy of the fault judgment and ensure that the measures taken are effective solutions to practical problems. This effectively solves the problem of poor applicability of existing fault diagnosis and operation methods when applied to server troubleshooting scenarios, improves the efficiency and accuracy of server fault diagnosis and operation and maintenance, and provides a new solution for server troubleshooting.

[0078] In an achievable implementation, after step S110: using an MR device to collect data of the server failure, the method further includes:

[0079] Convert the data into target data of the target coordinate system;

[0080] The target data is sent to the cloud server, so that the cloud server updates the knowledge graph for troubleshooting based on the target data to obtain a knowledge graph.

[0081] The MR device collects server equipment information, scene information, weather information and other server fault information data at the fault site. The server fault information data is usually in the local coordinate system, and it is necessary to convert these server fault information data into the global coordinate system to obtain the target data, that is, the server fault information data with unified spatial coordinates, so as to facilitate the subsequent further processing of the server fault information data with unified spatial coordinates.

[0082] The data of the server fault information after the spatial coordinates are unified is sent to the cloud server. The cloud server updates the existing troubleshooting knowledge graph based on the received server fault information to obtain the latest troubleshooting knowledge graph.

[0083] The specific formula for the data coordinate system conversion of server fault information is shown in formula (1):

[0084] P global =R·P local +T (1)

[0085] Among them, P global is the global coordinate, P local are local coordinates, R is the rotation matrix, and T is the translation vector.

[0086] In one embodiment, the data of the server fault information may include point cloud data representing depth information of the fault site environment, image data and temperature data representing environmental information of the fault site environment, and server structure parameter data representing server attribute information of the fault site environment. The data of server fault information of different types and in different coordinate systems may be converted to the same coordinate system by using coordinate system conversion, so that the spatial points of the point cloud data correspond to the specific image data, temperature data, and server structure parameter data.

[0087] This embodiment ensures the consistency and standardization of data by converting the collected data into target data in a target coordinate system, facilitates subsequent data processing and analysis, and improves the accuracy and reliability of fault diagnosis.

[0088] In one possible implementation, Figure 2 The flowchart of the method for generating a 3D model of a server failure scenario provided by an embodiment of the present application is shown. The data includes point cloud data, environmental data and structural attribute data of the server; Figure 2 As shown, step S120 generates a 3D model of the server failure scenario according to the data, including steps S210 to S250.

[0089] S210: According to the data correspondence between the point cloud data and the environmental data and the structural attribute data, the regional global features of the server in the data are extracted through a point cloud processing network model based on deep learning.

[0090] The data of server fault information may include point cloud data, environmental data and structural attribute data of the server. Point cloud data may be the three-dimensional geometric information of the server, which may be obtained by collecting the server and its surrounding environment through devices such as laser radar and depth camera. Environmental data may include information such as temperature, humidity, infrared thermal imaging, etc. of the server fault scene, which may be obtained by collecting environmental data of the server fault scene through devices such as temperature sensors, humidity sensors, infrared sensors, etc. Structural attribute data may include server operating status data representing detailed information and operating status of the server, server structural parameters, etc., and structural attribute data may be obtained from the cloud server.

[0091] The correspondence between point cloud data and environmental data and structural attribute data can be established through spatial transformation, spatial registration, etc., and each point in the point cloud data can be associated with its corresponding temperature, humidity, structural parameters and other information.

[0092] According to the data correspondence between point cloud data and environmental data and structural attribute data, the regional global features of the server in the data are extracted through a point cloud processing network model based on deep learning. Specifically, the point cloud processing network model based on deep learning can be a PointNet++ network model. Each point in the point cloud data and its corresponding temperature, humidity, structural parameters and other information are input into the PointNet++ network model, and the point cloud data is locally sampled and regionalized. In each local area, each point cloud data and its corresponding temperature, humidity, structural parameters and other information are feature extracted to obtain the local features of each point, such as geometric shape, texture, etc. According to the extracted local features, the scope is expanded and higher-level features of each local area are extracted to obtain the global features of each local area of ​​the server. Finally, the global features of the point cloud data of the entire server are extracted to form the global feature vector of the point cloud data of the server.

[0093] In one embodiment, point cloud data, image data, temperature data, structural parameters, etc. can be identified in a set as the input of the PointNet++ network. i and server structure parameters S i The server environment data and structural attribute data improve the system's ability to perceive environmental status and device structure changes. For example, the local global features of each area of ​​the server's point cloud data are extracted using the improved PointNet++ network as shown in formula (2).

[0094]

[0095] Among them, h i It's point p i Features, It's point p i Neighborhood point set, T i It's point p i The temperature value at S i It's point p i is the server structure parameter at , and f is the feature extraction function.

[0096] S220: Based on the regional global features and the environmental features and structural attribute features of the server, the self-attention mechanism is used to perform temporal and spatial fusion to obtain the regional fusion features of the server. The environmental features are determined by the environmental data, and the structural attribute features are determined by the structural attribute data.

[0097] The environmental features of each local area of ​​the server can be obtained by extracting the environmental data of the server, and the structural attribute features of each local area of ​​the server can be obtained by extracting the structural attribute data of the server. According to the regional global features, environmental features and structural attribute features of each area of ​​the server, the self-attention mechanism is used to fuse the temporal and spatial features to obtain the regional fusion features of each area of ​​the server. The self-attention mechanism fuses the regional global features, environmental features and structural attribute features by capturing the temporal and spatial dependencies of the regional global features, environmental features and structural attribute features. The regional fusion features can more comprehensively describe the state of the server, including geometric shape, environmental conditions and structural attributes. The regional fusion features of each area of ​​the server are merged with the original point cloud data of the server, so that the point cloud data of each area of ​​the server corresponds to the regional fusion features of each area of ​​the server, and the regional fusion features of each area of ​​the point cloud data of the server are obtained.

[0098] In one embodiment, the local global feature data extracted from each region of the server are merged into a set H, where H is the merged global feature set. For example, the features of multimodal data such as regional global features, environmental features, and structural attribute features of each region of the server can be fused in time and space through Transformer to obtain each region of the server. The feature fusion process improves the model's perception of the dynamically changing environment. The fusion process is shown in formula (3):

[0099] H final = Transformer(H,W,E,T,S) (3)

[0100] Among them, H final is the regional fusion feature, H is the global feature set, W is the server structure feature, E is the environmental information feature, T is the time feature, and S is the server structure parameter.

[0101] S230: According to the regional fusion features corresponding to the point cloud data, the point cloud data is segmented into point cloud data of different regions using a segmentation network, and the point cloud data of different regions are classified to obtain corresponding attribute information.

[0102] According to the regional fusion features corresponding to the point cloud data of the server, the point cloud data of the server is segmented into different segmented regions using a deep learning segmentation network, each segmented region containing a set of point cloud data and its corresponding regional fusion features. Exemplarily, the deep learning segmentation network can be a Mask R-CNN network, which can accurately divide different components and regions of the server and improve the accuracy of point cloud data classification and completion. The process of segmenting point cloud data into point cloud data of different regions using the Mask R-CNN network is shown in formula (4).

[0103] {R i}=Mask R-CNN(H final ) (4)

[0104] Among them, {R i} is the set of segmented regions after segmentation, H final It is a feature of regional integration.

[0105] The softmax probability distribution function can be used to classify each segmented region and identify its attribute information. The attribute information may include the device type of the server and its components and the server fault type, etc. The classification result can be used for further analysis and fault location. The process of using the softmax probability distribution function to classify each segmented region and identify its attribute information is shown in formula (5).

[0106] Class(R i )=Softmax(W·R i +b)(5)

[0107] Among them, R i is the segmentation area, W and b are the weight and bias of the classifier, which are adaptively adjusted according to different environments.

[0108] S240: completing the point cloud data of different regions based on the point cloud data in the cloud server to obtain completed point cloud data, wherein the point cloud data in the cloud server is determined by attribute information of the point cloud data of different regions.

[0109] The cloud server may include server-associated point cloud data corresponding to the attribute information of the server. For example, the cloud server may include point cloud data of servers of different models and point cloud data of different fault types. The current point cloud data is incomplete point cloud data. Point cloud data corresponding to the attribute information such as device type and server fault type of point cloud data in different areas of the server are found in the cloud server, and these point cloud data are used to complete the current incomplete point cloud data through deep learning capabilities to obtain optimized and completed server point cloud data.

[0110] S250: Perform three-dimensional reconstruction based on the completed point cloud data to obtain a 3D model.

[0111] Based on the completed point cloud data, the simultaneous localization and mapping (SLAM) algorithm technology is used to align and splice multiple frames of point cloud data for 3D reconstruction, generating a complete 3D model to obtain a 3D model of the server failure scene. The 3D model of the server failure scene can be used to merge with the 3D information of the components of the real environment and the troubleshooting solution in the troubleshooting information to form a mixed reality scene.

[0112] This embodiment integrates point cloud data, environmental data and structural attribute data, and uses deep learning methods (such as PointNet++ and Mask R-CNN) to extract and process the regional global features of the server, and combines the self-attention mechanism to realize temporal and spatial feature fusion, and then performs high-precision segmentation and classification on the point cloud data, and then uses the data in the cloud server to complete the incomplete point cloud. Finally, three-dimensional reconstruction is performed based on the completed point cloud data to generate a 3D model of the server fault scene, which not only improves the accuracy and efficiency of fault diagnosis, but also provides intuitive visual assistance for troubleshooting, significantly improving the intelligent level of server operation and maintenance.

[0113] In one feasible implementation, in step S210: before extracting regional global features of the server in the data through a deep learning-based point cloud processing network model based on the data correspondence between the point cloud data and the environmental data and structural attribute data, the method further includes: preprocessing the point cloud data, environmental data and structural attribute data of the server, wherein the preprocessing includes filtering, denoising, and at least one of spatial and temporal data alignment.

[0114] The point cloud data, environmental data and structural attribute data of the server can be filtered by the Kalman filter algorithm. For example, the process of using the Kalman filter algorithm to filter the temperature data in the environmental data of the server is shown in formula (6). The Kalman filter can ensure the smoothness of the temperature data and reduce the impact of transient noise on subsequent modeling.

[0115]

[0116] in, is the estimated temperature at the kth time, K k is the Kalman gain, T k is the measured temperature value, is the measurement matrix.

[0117] The point cloud data of the server can be multi-source point cloud data of different specifications and coordinate systems acquired by different sensors. The iterative closest point (ICP) algorithm can be used to perform spatial registration on the multi-source point cloud data to obtain spatially registered point cloud data. The spatial registration process is shown in formula (7).

[0118]

[0119] Where R is the rotation matrix, t is the translation vector, and p i and q i They are two point cloud sets to be registered, and E(R, t) is the point cloud data after registration.

[0120] This embodiment preprocesses the point cloud data, environmental data and structural attribute data of the server, including filtering, denoising and spatial and temporal data alignment. This process improves the purity and consistency of the data, optimizes the accuracy and robustness of feature extraction, and thus improves the performance and reliability of the entire fault diagnosis system.

[0121] In one feasible implementation, the fault information includes a fault type and a fault location; step S140: matching the fault information with the fault information in the knowledge graph to obtain first fault information, including: matching the fault type with the fault type in the knowledge graph; matching the fault location with the fault location in the knowledge graph; and taking the fault type and fault location that match both the fault type and the fault location in the knowledge graph as the first fault information.

[0122] The fault information in the knowledge graph includes the fault type and the fault location. The fault type in the server's fault information is matched with the fault type in the knowledge graph to find the most similar fault type, and the fault location in the server's fault information is matched with the fault location in the knowledge graph to find the most similar fault type. The fault information in the knowledge graph that best matches both the fault type and the fault location in the server's fault information is determined as the first fault information.

[0123] This embodiment can more accurately locate the fault and determine accurate fault information by matching the fault type and fault location with the data in the knowledge graph, thereby improving the accuracy of the fault diagnosis system in determining the troubleshooting solution.

[0124] In an achievable implementation, after step S160: determining that the troubleshooting information corresponding to the first fault information identical to the second fault information is the target troubleshooting information, the method further includes: displaying the 3D model and the target troubleshooting information on the display page.

[0125] The display interface of the MR glasses can be used to display the 3D model of the server failure scenario and the target troubleshooting information, that is, the determined implementation plan for server troubleshooting.

[0126] This embodiment displays the 3D model and target troubleshooting information on the display page. This process improves the efficiency and accuracy of server troubleshooting by intuitively displaying the fault situation and clear troubleshooting steps.

[0127] In an achievable implementation, after the display page displays the 3D model and the target troubleshooting information, the method further includes: rendering the 3D model and the target troubleshooting information; and displaying the rendered 3D model and the target troubleshooting information on the display interface.

[0128] The 3D model of the server fault scenario and the determined implementation plan for troubleshooting the server fault can be rendered and fused with the real server fault scenario to obtain the MR environment of the server fault scenario and the implementation plan for troubleshooting the server fault after rendering and fusion. The MR environment of the server fault scenario and the implementation plan for troubleshooting the server fault after rendering and fusion are displayed on the display interface of the MR glasses. The user can complete the troubleshooting of the server fault in the MR environment according to the implementation plan for troubleshooting the server fault.

[0129] This embodiment renders the 3D model and target troubleshooting information, and displays the rendered 3D model and target troubleshooting information on a display interface. This process significantly improves the accuracy and efficiency of troubleshooting by enhancing visual effects and user experience, providing more accurate operation guidance and real-time interaction.

[0130] In an achievable implementation, the method further includes: acquiring position information of the MR device and point cloud position information of the server; determining force feedback information based on the position information of the MR device and the point cloud position information; rendering the force feedback information; and displaying the rendered 3D model, target troubleshooting information and force feedback information on a display interface.

[0131] The position information of the MR device and the point cloud position information of the server are obtained. The position information of the MR device can be the posture information of the user operator using the MR device, or the position information of the user operator using the MR device. The point cloud position information can be the position information of the point cloud data of the server. Force feedback information can be determined based on the position information of the user operator of the MR device and the position information of the point cloud data of the server. The force feedback information is used to provide tactile force feedback prompts when implementing the implementation plan of server troubleshooting in the MR scene to improve the accuracy of the operation. The force feedback information is rendered and fused with the real scene; the MR environment of the server fault scene after rendering and fusion, the implementation plan of the server troubleshooting and the feedback information are displayed on the display interface of the MR glasses. Users can assist in troubleshooting the server fault through force feedback information in the MR environment according to the implementation plan of the server troubleshooting.

[0132] This embodiment obtains the position information of the MR device and the point cloud position information of the server, determines the force feedback information based on this information, renders the force feedback information, and displays the rendered 3D model, target troubleshooting information and force feedback information on the display interface, thereby improving the efficiency and reliability of troubleshooting by enhancing the interactive experience and operation accuracy, and optimizing the comprehensiveness and accuracy of fault diagnosis.

[0133] In an achievable implementation, the method further includes: after completing troubleshooting the server based on the target troubleshooting information, receiving correction information of the target troubleshooting information from the user; and correcting the target troubleshooting information based on the correction information.

[0134] Appropriate experts can be automatically dispatched from the expert database to assist in reviewing and modifying the determined server troubleshooting plan based on job level and availability information. Experts and other operators can verify, evaluate and test the server troubleshooting plan in the MR environment that displays the server fault scene after rendering. Through the MR environment, experts can also remotely guide operators to perform actual operations. During the test execution process, feedback and execution results from operators are collected and correction information for troubleshooting information is formulated to adjust and optimize the server troubleshooting plan.

[0135] Receive adjustment and optimization information of the server troubleshooting solution from the user, and optimize the server troubleshooting solution based on the adjustment and optimization information to obtain a final server troubleshooting solution.

[0136] This embodiment receives correction information from users on target troubleshooting information and corrects the target troubleshooting information based on the correction information. This process significantly improves the accuracy of troubleshooting and overall operation and maintenance efficiency by continuously optimizing solutions, improving the level of system intelligence, enhancing user participation and reducing repeated errors.

[0137] In an achievable implementation, the present application provides an embodiment of a server troubleshooting information system, and the method for determining server troubleshooting information of the present application can be applied to the system. Figure 3 A schematic diagram of a server troubleshooting information system provided by an embodiment of the present application is shown. Figure 3 As shown, the system includes mixed reality (MR) glasses, an interactive system, a scene reconstruction module, a fault diagnosis module, a force tactile module and a cloud server.

[0138] Mixed reality (MR) glasses are mainly used to complete data collection by scanning the server equipment information, scene information, weather information, etc. at the fault site through LiDAR. At the same time, they receive information on scene reconstruction, fault diagnosis solutions, and force and tactile feedback to complete mixed reality rendering, and integrate the optimized 3D model with the real environment to form a mixed reality scene.

[0139] The interactive system is mainly used to conduct in-depth analysis and processing of various types of information transmitted by MR glasses, and effectively transmit the information required by subsequent modules. At the same time, for the information sent back by each module, the mixed reality rendering technology is used to achieve a perfect fusion of real world information and virtual world information in the interactive system to complete the final 3D modeling.

[0140] The scene reconstruction module is mainly used to perform 3D modeling of the scene at the fault site, including point cloud feature extraction and matching, scene point cloud language segmentation, scanned point cloud scene completion and human posture recognition. Figure 2 The method for generating the 3D model of the server failure scenario shown is similar and will not be repeated here.

[0141] The fault diagnosis module also includes an expert management module. The fault diagnosis module is mainly used for data collection and preprocessing, data fusion and comparison, intelligent generation of troubleshooting solutions, and intelligent solution deployment and implementation. The specific implementation methods of each function of the fault diagnosis module are similar to the implementation methods in the above embodiments, and will not be repeated here.

[0142] The expert management module is used for expert assistance in review and modification. Appropriate experts are automatically dispatched from the expert database to assist in reviewing and modifying troubleshooting solutions based on job levels and availability information. Experts and operators verify, evaluate, and trial-execute troubleshooting solutions in the mixed reality world generated by the interactive system. Through the MR environment, experts can remotely guide operators to perform actual operations to ensure the effectiveness of the solution. During the trial execution process, feedback and execution results from operators are collected, and the solution is optimized and adjusted to ensure that the final implemented solution is the best. The finalized troubleshooting solution is implemented on-site, with real-time monitoring and guidance through MR glasses and the interactive system. During the implementation process, force feedback information and operation accuracy information are transmitted, and fault handling is adjusted in real time to ensure a smooth troubleshooting process.

[0143] The force feedback module is mainly used to determine force feedback information through the point cloud force rendering algorithm, and use the force feedback mechanism to ensure that the environment and server information in the generated troubleshooting solution are visualized and operable, and provide real operation feedback through physical interaction. The specific implementation method of each function of the force feedback module is similar to the implementation method in the above embodiment, and will not be repeated here.

[0144] The cloud server includes a server information database, an operator posture database, a fault information knowledge graph database, and an expert information database. It is mainly used to transmit, store, query, and send server information, posture information, fault handling knowledge, and expert scheduling information.

[0145] Based on the same concept, the embodiment of the present application provides a device for determining server troubleshooting information. Figure 4 The device for determining server troubleshooting information provided in an embodiment of the present application is described in detail.

[0146] Figure 4 It is a structural block diagram of a device for determining server troubleshooting information shown in an embodiment of the present application.

[0147] like Figure 4 As shown, the apparatus for determining server troubleshooting information may include:

[0148] A collection module 410 is used to collect data of server failures using MR equipment;

[0149] A generation module 420 is used to generate a 3D model of a server failure scenario according to the data, and to mark the failure information of the failed server based on the data;

[0150] An acquisition module 430 is used to acquire a knowledge graph for troubleshooting from a cloud server, wherein the knowledge graph includes a server failure scenario, server failure information, and troubleshooting information;

[0151] A matching module 440 is used to match the fault information with the fault information in the knowledge graph to obtain first fault information and troubleshooting information corresponding to the first fault information;

[0152] A comparison module 450 is used to compare the 3D model with the fault scenario in the knowledge graph to determine the second fault information of the server;

[0153] The determination module 460 is used to determine that the troubleshooting information corresponding to the first fault information that is the same as the second fault information is the target troubleshooting information, so as to troubleshoot the server based on the target troubleshooting information.

[0154] In one embodiment, after using the MR device to collect data on the server failure, the collection module 410 is used to convert the data into target data of the target coordinate system; the target data is sent to the cloud server so that the cloud server can update the troubleshooting knowledge graph based on the target data to obtain the knowledge graph.

[0155] In one embodiment, the data includes point cloud data, environmental data and structural attribute data of the server; the generation module 420 is specifically used to extract the regional global features of the server in the data through a point cloud processing network model based on deep learning according to the data correspondence between the point cloud data and the environmental data and the structural attribute data; according to the regional global features and the environmental features and structural attribute features of the server, the self-attention mechanism is used to perform temporal and spatial fusion to obtain the regional fusion features of the server, the environmental features are determined by the environmental data, and the structural attribute features are determined by the structural attribute data; according to the regional fusion features corresponding to the point cloud data, the segmentation network is used to segment the point cloud data into point cloud data of different regions, and the point cloud data of different regions are classified to obtain corresponding attribute information; based on the point cloud data in the cloud server, the point cloud data of different regions are completed and processed to obtain the completed point cloud data, and the point cloud data in the cloud server is determined by the attribute information of the point cloud data of different regions; three-dimensional reconstruction is performed based on the completed point cloud data to obtain a 3D model.

[0156] In one embodiment, before extracting the regional global features of the server in the data through a deep learning-based point cloud processing network model according to the data correspondence between the point cloud data and the environmental data and structural attribute data, the generation module 420 is also used to preprocess the point cloud data, environmental data and structural attribute data of the server, wherein the preprocessing includes at least one of filtering, denoising, and spatial and temporal data alignment.

[0157] In one embodiment, the fault information includes a fault type and a fault location; the matching module 440 is specifically used to match the fault type with the fault type in the knowledge graph; match the fault location with the fault location in the knowledge graph; and use the fault type and fault location that match both the fault type and the fault location in the knowledge graph as the first fault information.

[0158] In one embodiment, after determining that the troubleshooting information corresponding to the first fault information identical to the second fault information is the target troubleshooting information, the determination module 460 is further configured to display the 3D model and the target troubleshooting information on the display page.

[0159] In one embodiment, after the 3D model and target troubleshooting information are displayed on the display page, the determination module 460 is further used to render the 3D model and target troubleshooting information; and display the rendered 3D model and target troubleshooting information on the display interface.

[0160] In one embodiment, the acquisition module 430 is also used to acquire the position information of the MR device and the point cloud position information of the server; determine the force feedback information based on the position of the MR device and the point cloud position information; render the force feedback information; and display the rendered 3D model, target troubleshooting information and force feedback information on the display interface.

[0161] In one embodiment, the determination module 460 is further configured to receive correction information of the target troubleshooting information from the user after troubleshooting the server based on the target troubleshooting information is completed; and to correct the target troubleshooting information based on the correction information.

[0162] Figure 4 Each module in the device shown has the function of realizing Figure 1 and Figure 2 The functions of each step in the process can achieve the corresponding technical effects, which will not be described in detail here for the sake of brevity.

[0163] Figure 5 A schematic diagram of the hardware structure of an electronic device provided in one embodiment of the present application is shown.

[0164] The electronic device may include a processor 510 and a memory 520 storing computer program instructions.

[0165] Specifically, the processor 510 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0166] The memory 520 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 520 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 520 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 520 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 520 is a non-volatile solid-state memory.

[0167] The memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Therefore, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to the first aspect of the present disclosure.

[0168] The processor 510 implements any one of the methods for determining server troubleshooting information in the above embodiments by reading and executing computer program instructions stored in the memory 520 .

[0169] In one example, the electronic device may further include a communication interface 530 and a bus 540. Figure 5 As shown, the processor 510, the memory 520, and the communication interface 530 are connected via a bus 540 and communicate with each other.

[0170] The communication interface 530 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0171] Bus 540 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 540 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0172] The electronic device can execute the method for determining server troubleshooting information in the embodiment of the present application, thereby realizing the method for determining server troubleshooting information described in combination with Figure xx and Figure xx.

[0173] In addition, in combination with the method for determining server troubleshooting information in the above embodiment, the embodiment of the present application may provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any one of the methods for determining server troubleshooting information in the above embodiment is implemented.

[0174] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed, implements any one of the methods for determining server troubleshooting information in the above embodiments.

[0175] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0176] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0177] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0178] The above reference is according to the method of the embodiment of the present application, the flow chart of the device (system) and the computer program product and / or the block diagram described various aspects of the present application.It should be understood that each square box in the flow chart and / or the block diagram and the combination of each square box in the flow chart and / or the block diagram can be realized by computer program instructions.These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the realization of the function / action specified in one or more square boxes of the flow chart and / or the block diagram.Such a processor can be but is not limited to a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit.It can also be understood that each square box in the block diagram and / or the flow chart and the combination of the square boxes in the block diagram and / or the flow chart can also be realized by the dedicated hardware that performs the specified function or action, or can be realized by the combination of dedicated hardware and computer instructions.

[0179] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A method for determining server troubleshooting information, characterized in that, The method comprises: Use mixed reality MR devices to collect data on server failures; Generate a 3D model of the server failure scenario according to the data, and annotate the failure information of the failed server based on the data; Obtain a knowledge graph for troubleshooting from a cloud server, wherein the knowledge graph includes a server failure scenario, server failure information, and troubleshooting information; Matching the fault information with the fault information in the knowledge graph to obtain first fault information and troubleshooting information corresponding to the first fault information; Compare the 3D model with the fault scenario in the knowledge graph to determine second fault information of the server; The troubleshooting information corresponding to the first troubleshooting information that is the same as the second troubleshooting information is determined as the target troubleshooting information, so as to troubleshoot the server based on the target troubleshooting information.

2. The method according to claim 1, characterized in that After collecting the data of the server failure by using the MR device, the method further includes: Converting the data into target data of a target coordinate system; The target data is sent to a cloud server, so that the cloud server updates a knowledge graph for troubleshooting based on the target data to obtain the knowledge graph.

3. The method according to claim 1, characterized in that The data includes point cloud data, environmental data and structural attribute data of the server; and generating a 3D model of the server failure scenario according to the data includes: According to the data correspondence between the point cloud data and the environmental data and the structural attribute data, extracting the regional global features of the server in the data through a point cloud processing network model based on deep learning; According to the regional global features and the environmental features and structural attribute features of the server, a self-attention mechanism is used to perform temporal and spatial fusion to obtain the regional fusion features of the server, wherein the environmental features are determined by the environmental data, and the structural attribute features are determined by the structural attribute data; According to the regional fusion features corresponding to the point cloud data, the point cloud data is segmented into point cloud data of different regions using a segmentation network, and the point cloud data of different regions are classified to obtain corresponding attribute information; Completing the point cloud data of the different regions based on the point cloud data in the cloud server to obtain the completed point cloud data, wherein the point cloud data in the cloud server is determined by the attribute information of the point cloud data of the different regions; Three-dimensional reconstruction is performed based on the completed point cloud data to obtain the 3D model.

4. The method according to claim 3, characterized in that Before extracting the regional global features of the server in the data through a point cloud processing network model based on deep learning according to the data correspondence between the point cloud data and the environmental data and the structural attribute data, the method further includes: The point cloud data, environmental data and structural attribute data of the server are preprocessed, wherein the preprocessing includes at least one of filtering, denoising, and spatial and temporal data registration.

5. The method according to claim 1, characterized in that The fault information includes a fault type and a fault location; the matching the fault information with the fault information in the knowledge graph to obtain the first fault information includes: Matching the fault type with the fault type in the knowledge graph; Matching the fault location with the fault location in the knowledge graph; The fault type and the fault location that match the fault type and the fault location in the knowledge graph are used as the first fault information.

6. The method according to claim 1, characterized in that After determining that the troubleshooting information corresponding to the first fault information that is the same as the second fault information is the target troubleshooting information, the method further includes: The 3D model and the target troubleshooting information are displayed on a display page.

7. The method according to claim 6, characterized in that After displaying the 3D model and the target troubleshooting information on the display page, the method further includes: rendering the 3D model and the target troubleshooting information; The rendered 3D model and target troubleshooting information are displayed on the display interface.

8. The method according to claim 7, characterized in that The method further comprises: Acquire the position information of the MR device and the point cloud position information of the server; determining force feedback information based on the position information of the MR device and the point cloud position information; Rendering the force feedback information; The rendered 3D model, target troubleshooting information, and force feedback information are displayed on the display interface.

9. The method according to any one of claims 1 to 8, characterized in that: The method further comprises: After troubleshooting the server based on the target troubleshooting information is completed, receiving correction information of the target troubleshooting information from the user; The target troubleshooting information is modified based on the modification information.

10. A device for determining server troubleshooting information, characterized in that: The device comprises: A collection module, used for collecting data of server failures by using MR equipment; A generation module, used to generate a 3D model of the server failure scenario according to the data, and to mark the failure information of the failed server based on the data; An acquisition module, used to acquire a knowledge graph for troubleshooting from a cloud server, wherein the knowledge graph includes a server failure scenario, server failure information, and troubleshooting information; A matching module, used to match the fault information with the fault information in the knowledge graph to obtain first fault information and troubleshooting information corresponding to the first fault information; A comparison module, used to compare the 3D model with the fault scenario in the knowledge graph to determine second fault information of the server; The determination module is used to determine that the troubleshooting information corresponding to the first fault information that is the same as the second fault information is the target troubleshooting information, so as to troubleshoot the server based on the target troubleshooting information.

11. An electronic device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the method for determining server troubleshooting information according to any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the method for determining server troubleshooting information according to any one of claims 1 to 9 is implemented.

13. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the method for determining server troubleshooting information as described in any one of claims 1-9.

Images