Method and apparatus for determining server change information, computer device, and storage medium

Abstract

The application relates to a server change information determination method and device, computer equipment and a storage medium. The application relates to big data and artificial intelligence technology means. The method comprises the following steps: acquiring three-dimensional structure image information of a server room server, feature identification information of all servers contained in the server room server, and current state information of the servers, and collecting real-time change image information of the server room server; the change image information is image information corresponding to a change operation on the server; a feature image of the server contained in each change image information is extracted, and target servers corresponding to each change image information are identified based on the three-dimensional structure image information of the server room server, the feature identification information of the servers, and the feature image of each change image information; and change information of each target server is determined based on the current state information of each target server. The method can improve the determination efficiency of the server change information.

Description

Methods, devices, computer equipment, and storage media for determining server change information Technical Field

[0001] This application relates to the fields of big data and artificial intelligence technology, and in particular to a method, apparatus, computer equipment, and storage medium for determining server change information. Background Technology

[0002] With the continuous development of server technology, a large number of enterprises own their own data center servers. The sheer number and variety of servers in large data center servers increase the complexity of statistical analysis of server changes such as server deployment, replacement, maintenance, and return. Moreover, the servers have a high degree of similarity in appearance. Therefore, ensuring the accuracy of server quantity change statistics is a current research problem.

[0003] The traditional method involves staff manually compiling statistics on server changes after each change is completed. However, due to the high degree of similarity between servers and the tendency to miss some server change information after manually performing a large number of server change tasks, the efficiency of determining server change information is low. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer device, computer-readable storage medium, and computer program product for determining server change information to address the aforementioned technical problems.

[0005] Firstly, this application provides a method for determining server change information. The method includes:

[0006] The system acquires three-dimensional structural image information of the data center server, feature identification information of all servers included in the data center server, and current status information of each server, and collects real-time image information of each change of the data center server; the image information of the change is the image information corresponding to the change operation of the server.

[0007] Extract the feature images of the server contained in each of the changed image information, and identify the target server corresponding to each of the changed image information based on the three-dimensional structural image information of the data center server, the feature identification information of each of the servers, and the feature images of each of the changed image information;

[0008] Based on the current status information of each target server, the change information of each target server is determined.

[0009] Optionally, the real-time acquisition of various changing image information of the data center server includes:

[0010] When personnel are detected entering the server room, the first status information of each server is obtained, and when personnel leave the server room, the second status information of each server is obtained again.

[0011] In the case where the first state information of the server differs from the second state information of the server, the system collects image information of the actions of the personnel during the time period from when the personnel enter the server in the computer room to when the personnel leave the server in the computer room.

[0012] Based on the action image information, the operation information of the personnel is identified, and when the operation information meets the server change operation conditions, the target action image information corresponding to the operation features of the operation information is filtered from the action image information and used as the change image information of the data center server.

[0013] Optionally, the step of identifying the person's operation information based on each of the motion image information includes:

[0014] Using an image feature recognition network, personnel feature images and server feature images are extracted from each of the action image information.

[0015] According to the time sequence of the acquisition time of each action image information, the target feature images and the server feature images are sorted to obtain the personnel action sequence and the server change sequence.

[0016] Based on the personnel action sequence, identify the personnel's action content information; and based on the server change sequence, identify the server's change content information.

[0017] Based on the action content information and the change content information, the operator's operation information is identified.

[0018] Optionally, filtering the target action image information corresponding to the operation features of the operation information from each of the action image information includes:

[0019] Identify the human action images and server images in each of the action image information, and filter a preset number of action image information as the first action image information set according to the order of the area ratio of the server image in the action image information from large to small.

[0020] Extract the motion feature information of each person's motion image, and cluster the motion feature information according to the similarity of the motion feature information to obtain multiple motion feature groups;

[0021] In each action feature group, the action feature information with the highest average similarity to other action feature information is selected as the target action feature information, and the action image information corresponding to the target action feature information is used as the second action image information set.

[0022] Select identical motion image information from each of the first motion image information sets and each of the second motion image information sets as initial target motion images, and use all initial target motion images as target motion image information.

[0023] Optionally, the extraction of the feature images of the server included in each of the modified image information includes:

[0024] For each changing image information, the server features of the server image in each initial target action image of the changing image information are extracted using an image feature extraction algorithm, and used as the initial feature image;

[0025] Each initial feature image is divided into feature image groups according to the server region corresponding to each initial feature image. In each feature image group, the initial feature image with the largest server area is selected as the feature image.

[0026] Optionally, the step of identifying the target server corresponding to each of the changing image information based on the three-dimensional structural image information of the data center server, the feature identification information of each of the servers, and the feature image of each of the changing image information includes:

[0027] For each feature image corresponding to the changing image information, a three-dimensional server structure feature information is established according to the server area corresponding to each feature image, and the motion trajectory information of the server in each initial target action image of the changing image information in the three-dimensional structure image information of the server in the computer room is identified.

[0028] Based on the three-dimensional server structural feature information and the feature identification information of each server, the initial target server corresponding to the three-dimensional server structural feature information is identified, and based on the motion trajectory information of the initial target server, the type information of the initial target server is identified.

[0029] Based on the type information of the initial target server and the initial target server, the target server corresponding to the changed image information is determined.

[0030] Optionally, the motion trajectory information of the server in each initial target motion image of the identified changing image information within the three-dimensional structural image information of the server in the data center includes:

[0031] Each of the initial target motion images is projected onto the three-dimensional structure image information, and the three-dimensional position information of the server in each of the initial target motion images in the data center server is identified;

[0032] The three-dimensional position information is connected according to the time sequence of the acquisition time points corresponding to each initial target motion image to obtain the motion trajectory information of the server in the computer room.

[0033] Optionally, determining the change information of each target server based on the current status information of each target server includes:

[0034] Based on the movement trajectory information of each target server in the data center server and the operation information of the personnel corresponding to each target server, the change operation information of each target server is identified, and based on the current status information of each target server and the change operation information of each target server, the change information of each target server is determined.

[0035] Secondly, this application also provides a device for determining server change information. The device includes:

[0036] The acquisition module is used to acquire the three-dimensional structural image information of the data center server, the feature identification information of all servers included in the data center server, and the current status information of each server, and to collect the changing image information of the data center server in real time; the changing image information is the image information corresponding to the change operation of the server.

[0037] The identification module is used to extract the feature images of the server contained in each of the changing image information, and to identify the target server corresponding to each of the changing image information based on the three-dimensional structural image information of the data center server, the feature identification information of each of the servers, and the feature images of each of the changing image information.

[0038] The determination module is used to determine the change information of each target server based on the current status information of each target server.

[0039] Optionally, the acquisition module is specifically used for:

[0040] When personnel are detected entering the server room, the first status information of each server is obtained, and when personnel leave the server room, the second status information of each server is obtained again.

[0041] In the case where the first state information of the server differs from the second state information of the server, the system collects image information of the actions of the personnel during the time period from when the personnel enter the server in the computer room to when the personnel leave the server in the computer room.

[0042] Based on the action image information, the operation information of the personnel is identified, and when the operation information meets the server change operation conditions, the target action image information corresponding to the operation features of the operation information is filtered from the action image information and used as the change image information of the data center server.

[0043] Optionally, the acquisition module is specifically used for:

[0044] Using an image feature recognition network, personnel feature images and server feature images are extracted from each of the action image information.

[0045] According to the time sequence of the acquisition time of each action image information, the target feature images and the server feature images are sorted to obtain the personnel action sequence and the server change sequence.

[0046] Based on the personnel action sequence, identify the personnel's action content information; and based on the server change sequence, identify the server's change content information.

[0047] Based on the action content information and the change content information, the operator's operation information is identified.

[0048] Optionally, the acquisition module is specifically used for:

[0049] Identify the human action images and server images in each of the action image information, and filter a preset number of action image information as the first action image information set according to the order of the area ratio of the server image in the action image information from large to small.

[0050] Extract the motion feature information of each person's motion image, and cluster the motion feature information according to the similarity of the motion feature information to obtain multiple motion feature groups;

[0051] In each action feature group, the action feature information with the highest average similarity to other action feature information is selected as the target action feature information, and the action image information corresponding to the target action feature information is used as the second action image information set.

[0052] Select identical motion image information from each of the first motion image information sets and each of the second motion image information sets as initial target motion images, and use all initial target motion images as target motion image information.

[0053] Optionally, the identification module is specifically used for:

[0054] For each changing image information, the server features of the server image in each initial target action image of the changing image information are extracted using an image feature extraction algorithm, and used as the initial feature image;

[0055] Each initial feature image is divided into feature image groups according to the server region corresponding to each initial feature image. In each feature image group, the initial feature image with the largest server area is selected as the feature image.

[0056] Optionally, the identification module is specifically used for:

[0057] For each feature image corresponding to the changing image information, a three-dimensional server structure feature information is established according to the server area corresponding to each feature image, and the motion trajectory information of the server in each initial target action image of the changing image information in the three-dimensional structure image information of the server in the computer room is identified.

[0058] Based on the three-dimensional server structural feature information and the feature identification information of each server, the initial target server corresponding to the three-dimensional server structural feature information is identified, and based on the motion trajectory information of the initial target server, the type information of the initial target server is identified.

[0059] Based on the type information of the initial target server and the initial target server, the target server corresponding to the changed image information is determined.

[0060] Optionally, the identification module is specifically used for:

[0061] Each of the initial target motion images is projected onto the three-dimensional structure image information, and the three-dimensional position information of the server in each of the initial target motion images in the data center server is identified;

[0062] The three-dimensional position information is connected according to the time sequence of the acquisition time points corresponding to each initial target motion image to obtain the motion trajectory information of the server in the computer room.

[0063] Optionally, the determining module is specifically used for:

[0064] Based on the movement trajectory information of each target server in the data center server and the operation information of the personnel corresponding to each target server, the change operation information of each target server is identified, and based on the current status information of each target server and the change operation information of each target server, the change information of each target server is determined.

[0065] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in any one of the first aspects.

[0066] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0067] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0068] The aforementioned method, apparatus, computer equipment, and storage medium for determining server change information acquire three-dimensional structural image information of the data center server, feature identification information of all servers included in the data center server, and current status information of each server, and collects change image information of the data center server in real time; the change image information is image information corresponding to the change operation of the server; extracts the feature image of the server contained in each change image information, and identifies the target server corresponding to each change image information based on the three-dimensional structural image information of the data center server, the feature identification information of each server, and the feature image of each change image information; and determines the change information of each target server based on the current status information of each target server. By collecting change image information of the data center server, the target server with change operation is accurately identified, and the change information of each target server is determined based on the current status information of the server, avoiding omissions in manual statistics of change information and improving the accuracy of server change information statistics. Furthermore, the real-time collection of change image information and real-time statistics of change information of each target server improve the efficiency of determining server change information. Attached Figure Description

[0069] Figure 1 is a flowchart illustrating a method for determining server change information in one embodiment;

[0070] Figure 2 is a flowchart illustrating an example of determining server change information in one embodiment;

[0071] Figure 3 is a structural block diagram of a device for determining server change information in one embodiment;

[0072] Figure 4 is an internal structure diagram of a computer device in one embodiment. Detailed Implementation

[0073] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0074] The method for determining server change information provided in this application can be applied to terminals, servers, and systems including both terminals and servers, and is implemented through interaction between the terminals and servers. The server can be a standalone server or a server cluster composed of multiple servers. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, tablets, etc. The terminal accurately identifies target servers with changes by collecting change image information from servers in the data center, and determines the change information of each target server based on the server's current status information. This avoids omissions in manual change information statistics and improves the accuracy of server change information statistics. Furthermore, by collecting change image information in real time and statistically analyzing the change information of each target server in real time, the efficiency of determining server change information is improved.

[0075] In one embodiment, as shown in Figure 1, a method for determining server change information is provided. Taking the application of this method to a terminal as an example, the method includes the following steps:

[0076] Step S101: Obtain the three-dimensional structural image information of the server in the data center, the feature identification information of all servers included in the data center, the current status information of each server, and collect the changing image information of the server in the data center in real time.

[0077] Among them, the changed image information is the image information corresponding to the change operation on the server.

[0078] In this embodiment, the terminal performs a 3D scan of the entire server room using the monitoring and scanning equipment of the server room, obtaining a 3D structural image of the server room. This 3D structural image is established in a 3D coordinate system with the server room as the coordinate system. Then, in response to the feature identification images of each server uploaded by the user, the terminal obtains feature representation information for each server. These feature representation images include, but are not limited to, external identification images, label identification images, interface identification images, structural identification images, and component identification images. The terminal collects the status information of each server in real time, and when a server change operation is detected, it uses the server status information corresponding to the moment the change operation is detected as the current status information of each server. The server status information includes, but is not limited to, online, abnormal operation, under maintenance, offline, no connection, and connection abnormality status information. Then, the terminal determines whether personnel have performed any changes to the server, thereby collecting the corresponding change image information. The personnel are the staff maintaining the server, and the change operation is the operation performed by the staff to replace hardware on the server. This change operation includes, but is not limited to, operations performed by the staff such as server mounting, replacement, repair, and return to inventory. The specific judgment process and the process of collecting information on changing images will be explained in detail later.

[0079] Step S102: Extract the feature images of the server contained in each changed image information, and identify the target server corresponding to each changed image information based on the three-dimensional structural image information of the server in the data center, the feature identification information of each server, and the feature images of each changed image information.

[0080] In this embodiment, the terminal extracts feature images containing server images from each changing image information using an image feature extraction network. This image feature extraction network is an LBP (Local Binary Pattern) image feature extraction neural network. The specific extraction process will be described in detail later. These feature images are two-dimensional images, and there are multiple feature images. Then, based on the three-dimensional structural image information of the data center server, the feature identification information of each server, and the feature images of each changing image information, the terminal identifies the target server corresponding to each changing image information. The specific identification process will be described in detail later.

[0081] Step S103: Based on the current status information of each target server, determine the change information of each target server.

[0082] In this embodiment, the terminal determines the change information of each target server based on the current status information of each target server. The change information refers to the change operation information corresponding to that target server.

[0083] Based on the above solution, by collecting image information of server changes in the data center, the target servers with changes can be accurately identified. Based on the current status information of these servers, the change information for each target server can be determined, avoiding omissions in manual change information statistics and improving the accuracy of server change information statistics. Furthermore, real-time collection of image information and real-time statistics of change information for each target server improve the efficiency of determining server change information.

[0084] Optionally, real-time acquisition of various changing image information of the server in the data center includes: acquiring the first state information of each server when personnel are detected entering the server in the data center, and reacquiring the second state information of each server when personnel leave the server in the data center; in the case where the first state information and the second state information of the server are different, acquiring the personnel's various action image information during the time period from when personnel enter the server in the data center to when personnel leave the server in the data center; based on the action image information, identifying the personnel's operation information, and if the operation information meets the server change operation conditions, filtering the target action image information corresponding to the operation features of the operation information from the action image information as the changing image information of the server in the data center.

[0085] In this embodiment, the terminal monitors the entry and exit of personnel in the server room in real time using a monitoring camera. When personnel enter the server room, the terminal acquires the first status information of each server, and when the personnel leave, it acquires the second status information of each server. The number of personnel can be one or more. If there are multiple personnel, the terminal performs the above operations individually for each person. Then, the terminal determines whether the first status information of each server differs from the second status information of each secondary weapon. If there is a difference between the first and second status information of a server, the terminal collects the personnel's motion image information for the period from when the personnel enter the server room until when they leave. Each motion image corresponds to a collection time point, and the terminal collects motion image information for multiple time points within the period from when the personnel enter the server room until when they leave, according to a preset collection time interval.

[0086] The terminal identifies the operator's actions based on various action image information. The specific process for identifying this action information will be explained in detail later. This action information characterizes the operator's actions on the server in the data center. Then, the terminal determines whether the action information meets the conditions for a server change operation. If the action information does not meet these conditions, the terminal stops collecting change image information. If the action information meets the conditions, the terminal filters the target action image information corresponding to the action features of this action information from the operator's various action image information, using this as the server change image information. The specific process for acquiring these action features will be explained in detail later. The server change operation information is a summary of images based on the operator's daily task performance habits and action images of routine personnel changing server operations, forming the identification conditions corresponding to the server change operation.

[0087] Based on the above scheme, when the terminal detects changes in a person's server operation, it collects the changes in the person's image information, reducing the amount of data input for statistical server changes and the number of interfering image information, thereby improving the efficiency and accuracy of determining statistical server changes.

[0088] Optionally, based on each action image information, the identification of personnel operation information includes: extracting personnel feature images and server feature images from each action image information through an image feature recognition network; sorting each target feature image and each server feature image according to the time sequence of the acquisition time of each action image information to obtain personnel action sequences and server change sequences; identifying personnel action content information based on personnel action sequences and identifying server change content information based on server change sequences; and identifying personnel operation information based on action content information and change content information.

[0089] In this embodiment, the terminal extracts personnel feature images and server feature images from each action image information through an image feature recognition network. This image feature recognition network is a BackPropagation (BP) neural network. Then, the terminal sorts the target feature images and server feature images according to the chronological order of the acquisition time points of each action image information, obtaining a personnel action sequence and a server change sequence. The terminal then identifies the personnel's action content information based on the personnel action sequence and the server's change content information based on the server change sequence. Finally, the terminal presets the association relationships between multiple combinations of action content information and change information corresponding to operational information, and identifies the personnel's operational information based on the personnel's action content information and the server's change content information. For example, if a person's action information is to pick up an object and carry it away from the server in the data center, and the server's change information is to move from its current location to outside the server in the data center, then the action information and the corresponding person's operation information are "server removal"; if a person's action information is to put down the object in their hand, replace the object, and carry the replaced object away from the server in the data center, and the server's change information is to move from its current location to outside the server in the data center, then the action information and the corresponding person's operation information are "server replacement".

[0090] Based on the above scheme, the terminal identifies action content information and change content information, and presets the association relationship between multiple combinations of action content information and change information corresponding to operation information, thereby determining the operation information of the person. This not only improves the accuracy of identifying the operation information of the person, but also improves the efficiency of identifying the operation information of the person.

[0091] Optionally, in each action image information, the target action image information corresponding to the operation features of the operation information is filtered, including: identifying the personnel action images and server images in each action image information, and filtering a preset number of action image information as a first action image information set according to the order of the area ratio of the server image in the action image information from large to small; extracting the action feature information of each personnel action image, and performing clustering processing on each action feature information according to the similarity of the action feature information to obtain multiple action feature groups; filtering the action feature information with the highest average similarity with other action feature information in each action feature group as the target action feature information, and using the action image information corresponding to the target action feature information as a second action image information set; filtering the same action image information in each first action image information set and each second action image information set as initial target action images, and using all initial target action images as target action image information.

[0092] In this embodiment, the terminal identifies the human action images and server images in each action image information. Then, the terminal calculates the area of ​​each server image as a percentage of the area of ​​the action image information to which the server image belongs. The terminal then selects a number of action image information preset in the terminal as the first action image information set in descending order of the area percentage of the server image in the action image information.

[0093] The terminal extracts motion feature information from images of various people's actions using an image feature extraction network, calculates the similarity between each motion feature, and then clusters these motion feature information according to their similarity to obtain multiple motion feature groups. The image feature extraction network used is the same as the one used in step S102, and the similarity algorithm between each motion feature is the Euclidean distance algorithm. The terminal normalizes the Euclidean distance between every two motion feature pieces to obtain the similarity between them.

[0094] For each action feature group, the terminal calculates the average similarity between each action feature in that group and all other action features, based on the similarity between each action feature within that group. Then, the terminal selects the action feature with the highest average similarity to all other action features in that group as the target action feature, and uses the corresponding action image information as the second action image information set. Finally, the terminal selects action image information that belongs to both the first and second action image information sets as initial target action images, and uses all initial target action images as the target action image information.

[0095] Based on the above scheme, action image information is filtered by the proportion of server image area and the similarity of action features, thereby ensuring that the recognition of server and human action content is the highest among the extracted target action image information.

[0096] Optionally, extract the server feature image contained in each changing image information, including: for each changing image information, extract the server features of the server image in each initial target action image of the changing image information using an image feature extraction algorithm, and use it as the initial feature image; divide each initial feature image according to the server region corresponding to each initial feature image to obtain each feature image group, and select the initial feature image with the largest server area in each feature image group as the feature image.

[0097] In this embodiment, for each changing image information, the terminal uses an image feature extraction algorithm to extract server features from the server image in each initial target action image of the changing image information, and uses these features as initial feature images. This image feature extraction algorithm is an image edge recognition algorithm, which can be, but is not limited to, algorithms corresponding to the Roberts operator, Prewitt operator, Sobel operator, Canny operator, Laplacian operator, etc. The terminal uses the image containing the edges of the identified server feature image as the initial feature image. Then, the terminal divides each initial feature image according to the server region corresponding to each initial feature image, obtaining feature image groups. The server region refers to the region corresponding to each viewpoint of the server, including but not limited to the front region, back region, side region, top region, bottom region, etc. Finally, the terminal selects the initial feature image with the largest server area from each feature image group as the final feature image.

[0098] Based on the above scheme, the terminal selects the server feature image with the largest server area from different perspectives as the feature image, thereby improving the feature recognition rate of each feature image and improving the efficiency of identifying the server corresponding to the feature image.

[0099] Optionally, based on the 3D structural image information of the server in the data center, the feature identification information of each server, and the feature images of each changing image information, the target server corresponding to each changing image information is identified, including: for each feature image corresponding to each changing image information, according to the server area corresponding to each feature image, 3D server structural feature information is established, and the motion trajectory information of the server in each initial target action image of the changing image information in the 3D structural image information of the server in the data center is identified; based on the 3D server structural feature information and the feature identification information of each server, the initial target server corresponding to the 3D server structural feature information is identified, and based on the motion trajectory information of the initial target server, the type information of the initial target server is identified; based on the type information of the initial target server and the initial target server, the target server corresponding to the changing image information is determined.

[0100] In this embodiment, the terminal performs 3D image stitching processing on the feature image corresponding to each changing image information, according to the server region corresponding to each feature image, to obtain the 3D server structure feature information of the server. Then, the terminal identifies the motion trajectory information of the server in the 3D structure image information of the server in the data center server in each initial target motion image of the changing image information corresponding to the server. The process of identifying the motion trajectory information will be described in detail later. Based on the 3D server structure feature information and the feature identification information of each server, the terminal identifies the initial target server corresponding to the 3D server structure feature information. Then, based on the motion trajectory information of the initial target server, the terminal identifies the type information of the initial target server. Specifically, the terminal determines the corresponding server type (i.e., type information) of the server based on the area of ​​the data center server traversed by the motion trajectory information. Finally, the terminal uses the type information of the initial target server and the initial target server as the target server corresponding to the changing image information.

[0101] Based on the above scheme, the terminal obtains a complete three-dimensional image of the server by performing three-dimensional stitching on the server's feature images. Then, the terminal determines the type of the server according to the server's movement trajectory. This improves the accuracy of target server identification by using the server's three-dimensional structural features, feature identification information, and type.

[0102] Optionally, identifying the motion trajectory information of the server in the three-dimensional structural image information of the server in the data center in each initial target motion image of the changing image information includes: projecting each initial target motion image into the three-dimensional structural image information, identifying the three-dimensional position information of the server in the data center in each initial target motion image; and connecting each three-dimensional position information according to the time sequence of the acquisition time point corresponding to each initial target motion image to obtain the motion trajectory information of the server in the data center.

[0103] In this embodiment, the terminal projects each initial target motion image onto a three-dimensional structural image, identifying the three-dimensional position information of the server in each initial target motion image within the data center server. This projection method uses a reference object projection method, where each static server in the initial target motion image is used as a reference object to project the initial target motion image onto the three-dimensional structural image, thus obtaining the three-dimensional position information of the server in the initial target motion image within the data center server. Then, the terminal connects the three-dimensional position information according to the chronological order of the acquisition time points corresponding to each initial target motion image to obtain the server's motion trajectory information within the data center server.

[0104] Based on the above scheme, by projecting a two-dimensional image onto a three-dimensional structural image, the motion trajectory information of the server is obtained, thereby improving the accuracy of identifying the server's motion trajectory information.

[0105] Optionally, based on the current status information of each target server, determine the change information of each target server, including:

[0106] Based on the movement trajectory information of each target server in the data center server and the operation information of the personnel corresponding to each target server, the change operation information of each target server is identified, and based on the current status information of each target server and the change operation information of each target server, the change information of each target server is determined.

[0107] In this embodiment, the terminal identifies the corresponding change operation information for each target server based on the movement trajectory information of each target server in the data center and the operation information of the personnel corresponding to each target server. Then, based on the current status information of each target server, the terminal filters the target change operation information from the change operation information. Finally, the terminal uses the current status information of the server and the target change operation information of the server as the change information of the target server. Among them, when the change operation information is the operation information of replacing or installing a new server, the change information of the target server includes the basic information of the new server.

[0108] Based on the above scheme, the change information of each target server is determined by using the motion trajectory information and the current status information of each target server, thereby improving the accuracy and comprehensiveness of the determined change information of each target server.

[0109] In one embodiment, as shown in Figure 2, an example of determining server change information is provided, which includes the following steps:

[0110] Step S201: Obtain the three-dimensional structural image information of the server in the data center, the feature identification information of all servers included in the data center server, and the current status information of each server.

[0111] Step S202: When personnel are detected entering the server room, the first status information of each server is obtained, and when personnel leave the server room, the second status information of each server is obtained again.

[0112] Step S203: In the case where the first state information of the server is different from the second state information of the server, collect the image information of each action of the personnel during the time period from when the personnel enter the server in the computer room to when the personnel leave the server in the computer room.

[0113] Step S204: Extract the personnel feature images and server feature images from each action image information through the image feature recognition network.

[0114] Step S205: Sort the target feature images and server feature images according to the time sequence of the acquisition time of each action image information to obtain the personnel action sequence and the server change sequence.

[0115] Step S206: Based on the personnel action sequence, identify the personnel action content information, and based on the server change sequence, identify the server change content information.

[0116] Step S207: Identify the operator's operation information based on the action content information and the change content information.

[0117] Step S208: When the operation information meets the server change operation conditions, identify the personnel action images and server images in each action image information, and filter a preset number of action image information as the first action image information set according to the order of the area ratio of the server image in the action image information from large to small.

[0118] Step S209: Extract the motion feature information of each person's motion image, and cluster the motion feature information according to the similarity of the motion feature information to obtain multiple motion feature groups.

[0119] Step S210: In each action feature group, select the action feature information with the highest average similarity to other action feature information as the target action feature information, and take the action image information corresponding to the target action feature information as the second action image information set.

[0120] Step S211: Filter the same motion image information in each first motion image information set and each second motion image information set as the initial target motion image, and use all the initial target motion images as the target motion image information.

[0121] Step S212: For each changed image information, the server features of the server image in each initial target action image of the changed image information are extracted using an image feature extraction algorithm and used as the initial feature image.

[0122] Step S213: Divide each initial feature image into groups according to the server area corresponding to each initial feature image, and select the initial feature image with the largest server area in each feature image group as the feature image.

[0123] Step S214: For each feature image corresponding to the changed image information, establish three-dimensional server structure feature information according to the server region corresponding to each feature image.

[0124] Step S215: Project each initial target motion image onto the three-dimensional structure image information, and identify the three-dimensional position information of the server in the data center server in each initial target motion image.

[0125] Step S216: Connect the three-dimensional position information according to the time sequence of the acquisition time points corresponding to each initial target motion image to obtain the motion trajectory information of the server in the computer room.

[0126] Step S217: Based on the three-dimensional server structure feature information and the feature identification information of each server, identify the initial target server corresponding to the three-dimensional server structure feature information, and based on the motion trajectory information of the initial target server, identify the type information of the initial target server.

[0127] Step S218: Based on the type information of the initial target server and the initial target server, determine the target server corresponding to the changed image information.

[0128] Step S219: Based on the movement trajectory information of each target server in the computer room server and the operation information of the personnel corresponding to each target server, identify the change operation information of each target server, and determine the change information of each target server based on the current status information of each target server and the change operation information of each target server.

[0129] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0130] Based on the same inventive concept, this application also provides a device for determining server change information to implement the method for determining server change information described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the device for determining server change information provided below can be found in the limitations of the method for determining server change information above, and will not be repeated here.

[0131] In one embodiment, as shown in FIG3, a device for determining server change information is provided, comprising: an acquisition module 310, an identification module 320, and a determination module 330, wherein:

[0132] The acquisition module 310 is used to acquire the three-dimensional structural image information of the data center server, the feature identification information of all servers included in the data center server, and the current status information of each server, and to collect the changing image information of the data center server in real time; the changing image information is the image information corresponding to the change operation of the server.

[0133] The identification module 320 is used to extract the feature image of the server contained in each of the changing image information, and to identify the target server corresponding to each of the changing image information based on the three-dimensional structural image information of the data center server, the feature identification information of each of the servers, and the feature image of each of the changing image information.

[0134] The determination module 330 is used to determine the change information of each target server based on the current status information of each target server.

[0135] Optionally, the acquisition module 310 is specifically used for:

[0136] When personnel are detected entering the server room, the first status information of each server is obtained, and when personnel leave the server room, the second status information of each server is obtained again.

[0137] In the case where the first state information of the server differs from the second state information of the server, the system collects image information of the actions of the personnel during the time period from when the personnel enter the server in the computer room to when the personnel leave the server in the computer room.

[0138] Based on the action image information, the operation information of the personnel is identified, and when the operation information meets the server change operation conditions, the target action image information corresponding to the operation features of the operation information is filtered from the action image information and used as the change image information of the data center server.

[0139] Optionally, the acquisition module 310 is specifically used for:

[0140] Using an image feature recognition network, personnel feature images and server feature images are extracted from each of the action image information.

[0141] According to the time sequence of the acquisition time of each action image information, the target feature images and the server feature images are sorted to obtain the personnel action sequence and the server change sequence.

[0142] Based on the personnel action sequence, identify the personnel's action content information; and based on the server change sequence, identify the server's change content information.

[0143] Based on the action content information and the change content information, the operator's operation information is identified.

[0144] Optionally, the acquisition module 310 is specifically used for:

[0145] Identify the human action images and server images in each of the action image information, and filter a preset number of action image information as the first action image information set according to the order of the area ratio of the server image in the action image information from large to small.

[0146] Extract the motion feature information of each person's motion image, and cluster the motion feature information according to the similarity of the motion feature information to obtain multiple motion feature groups;

[0147] In each action feature group, the action feature information with the highest average similarity to other action feature information is selected as the target action feature information, and the action image information corresponding to the target action feature information is used as the second action image information set.

[0148] Select identical motion image information from each of the first motion image information sets and each of the second motion image information sets as initial target motion images, and use all initial target motion images as target motion image information.

[0149] Optionally, the identification module 320 is specifically used for:

[0150] For each changing image information, the server features of the server image in each initial target action image of the changing image information are extracted using an image feature extraction algorithm, and used as the initial feature image;

[0151] Each initial feature image is divided into feature image groups according to the server region corresponding to each initial feature image. In each feature image group, the initial feature image with the largest server area is selected as the feature image.

[0152] Optionally, the identification module 320 is specifically used for:

[0153] For each feature image corresponding to the changing image information, a three-dimensional server structure feature information is established according to the server area corresponding to each feature image, and the motion trajectory information of the server in each initial target action image of the changing image information in the three-dimensional structure image information of the server in the computer room is identified.

[0154] Based on the three-dimensional server structural feature information and the feature identification information of each server, the initial target server corresponding to the three-dimensional server structural feature information is identified, and based on the motion trajectory information of the initial target server, the type information of the initial target server is identified.

[0155] Based on the type information of the initial target server and the initial target server, the target server corresponding to the changed image information is determined.

[0156] Optionally, the identification module 320 is specifically used for:

[0157] Each of the initial target motion images is projected onto the three-dimensional structure image information, and the three-dimensional position information of the server in each of the initial target motion images in the data center server is identified;

[0158] The three-dimensional position information is connected according to the time sequence of the acquisition time points corresponding to each initial target motion image to obtain the motion trajectory information of the server in the computer room.

[0159] Optionally, the determining module 330 is specifically used for:

[0160] Based on the movement trajectory information of each target server in the data center server and the operation information of the personnel corresponding to each target server, the change operation information of each target server is identified, and based on the current status information of each target server and the change operation information of each target server, the change information of each target server is determined.

[0161] Each module in the aforementioned device for determining server change information can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can invoke and execute the operations corresponding to each module.

[0162] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in Figure 4. The computer device includes a processor, memory, communication interface, display screen, and input device connected via a system bus. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for wired or wireless communication with external terminals. Wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for determining server change information. The display screen of the computer device may be an LCD screen or an e-ink display screen. The input device of the computer device may be a touch layer covering the display screen, or buttons, a trackball, or a touchpad located on the casing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0163] Those skilled in the art will understand that the structure shown in Figure 4 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or may combine certain components, or may have different component arrangements.

[0164] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in any one of the first aspects.

[0165] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0166] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0167] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0168] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0169] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0170] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining server change information, characterized in that, The method includes: acquiring three-dimensional structural image information of the data center server, feature identification information of all servers included in the data center server, and current status information of each server, and real-time acquisition of various changing image information of the data center server; the changing image information is image information corresponding to the change operation of the server; extracting the feature image of the server contained in each of the changing image information, and identifying the target server corresponding to each of the changing image information based on the three-dimensional structural image information of the data center server, the feature identification information of each server, and the feature image of each of the changing image information; determining the change information of each target server based on the current status information of each target server; wherein, the real-time acquisition of various changing image information of the data center server includes: acquiring the first status information of each server when personnel are detected entering the data center server, and re-acquiring the second status information of each server when personnel leave the data center server; in the case where the first status information of a server differs from the second status information of the server, acquiring the change information of the personnel entering the data center server. The system collects image information of each action of the personnel during the time period from when the personnel leave the server in the data center. Based on each image information, it identifies the personnel's operation information, and if the operation information meets the server change operation conditions, it filters the target image information corresponding to the operation features of the operation information from each image information as the server change image information. The identification of the personnel's operation information based on each image information includes: extracting personnel feature images and server feature images from each image information through an image feature recognition network; sorting the personnel feature images and server feature images according to the time sequence of the acquisition time of each image information to obtain a personnel action sequence and a server change sequence; identifying the personnel's action content information based on the personnel action sequence, and identifying the server change content information based on the server change sequence; and identifying the personnel's operation information based on the action content information and the change content information.

2. The method according to claim 1, characterized in that, The step of filtering target motion image information corresponding to the operation features of the operation information from each of the motion image information includes: identifying personnel motion images and server images in each of the motion image information, and filtering a preset number of motion image information as a first motion image information set according to the order of the area proportion of the server image in the motion image information from large to small; extracting motion feature information of each of the personnel motion images, and performing clustering processing on each of the motion feature information according to the similarity of the motion feature information to obtain multiple motion feature groups; filtering the motion feature information with the highest average similarity with other motion feature information in each motion feature group as target motion feature information, and using the motion image information corresponding to the target motion feature information as a second motion image information set; filtering the same motion image information in each of the first motion image information sets and each of the second motion image information sets as initial target motion images, and using all initial target motion images as target motion image information.

3. The method according to claim 2, characterized in that, The step of extracting the server feature image contained in each of the changed image information includes: for each changed image information, using an image feature extraction algorithm, extracting the server features of the server image in each initial target action image of the changed image information as an initial feature image; dividing each initial feature image according to the server region corresponding to each initial feature image to obtain each feature image group, and in each feature image group, selecting the initial feature image with the largest server area as the feature image.

4. The method according to claim 2, characterized in that, The step of identifying the target server corresponding to each of the changing image information based on the three-dimensional structural image information of the data center server, the feature identification information of each of the servers, and the feature images of each of the changing image information includes: for each feature image corresponding to the changing image information, establishing three-dimensional server structural feature information according to the server area corresponding to each feature image, and identifying the motion trajectory information of the server in each initial target motion image of the changing image information in the three-dimensional structural image information of the data center server; based on the three-dimensional server structural feature information and the feature identification information of each of the servers, identifying the initial target server corresponding to the three-dimensional server structural feature information, and identifying the type information of the initial target server based on the motion trajectory information of the initial target server; and determining the target server corresponding to the changing image information based on the type information of the initial target server and the initial target server.

5. The method according to claim 4, characterized in that, The process of identifying the motion trajectory information of the server in each initial target motion image of the changing image information within the three-dimensional structural image information of the server in the data center includes: projecting each initial target motion image into the three-dimensional structural image information and identifying the three-dimensional position information of the server in each initial target motion image within the data center server; and connecting the three-dimensional position information according to the time sequence of the acquisition time points corresponding to each initial target motion image to obtain the motion trajectory information of the server within the data center server.

6. The method according to claim 1, characterized in that, The step of determining the change information of each target server based on the current status information of each target server includes: identifying the change operation information of each target server based on the movement trajectory information of each target server on the server in the data center and the operation information of the personnel corresponding to each target server, and determining the change information of each target server based on the current status information of each target server and the change operation information of each target server.

7. A device for determining server change information, characterized in that, The device includes: an acquisition module, used to acquire three-dimensional structural image information of a data center server, feature identification information of all servers included in the data center server, and current status information of each server, and to collect real-time changes in image information of the data center server; the changes in image information are image information corresponding to changes performed on the server; an identification module, used to extract feature images of servers contained in each of the changes in image information, and to identify the target server corresponding to each of the changes in image information based on the three-dimensional structural image information of the data center server, the feature identification information of each server, and the feature images of each of the changes in image information; and a determination module, used to determine the change information of each target server based on the current status information of each target server; wherein, the real-time collection of changes in image information of the data center server includes: acquiring first status information of each server when personnel are detected entering the data center server, and re-acquiring second status information of each server when personnel leave the data center server; in the case where the first status information and the second status information of a server are different... The process involves collecting image information of the personnel's actions during the time period from when they enter the server room to when they leave the server room; identifying the personnel's operation information based on each image information; and, if the operation information meets the server change operation conditions, filtering the target image information corresponding to the operation features of the operation information from each image information as the server change image information; identifying the personnel's operation information based on each image information includes: extracting personnel feature images and server feature images from each image information using an image feature recognition network; sorting the personnel feature images and server feature images according to the time sequence of the collection time of each image information to obtain a personnel action sequence and a server change sequence; identifying the personnel's action content information based on the personnel action sequence and identifying the server change content information based on the server change sequence; and identifying the personnel's operation information based on the action content information and the change content information.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images