Server exception identification method and device, equipment, medium and program product

Abstract

The invention provides a server exception identification method which can be applied to the technical field of artificial intelligence. The server abnormity identification method comprises the steps that a rack image is collected, the rack image comprises a server arranged in a rack, and the server is provided with a status lamp; adjusting the image information of the rack image based on an adaptive adjustment strategy, and obtaining an adjusted first image; and identifying a status lamp of the server based on the first image, and determining an abnormal condition of the server according to an identification result of the status lamp of the server. The invention further provides a server exception recognition device and equipment, a storage medium and a program product.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and more specifically to a method, device, equipment, medium and program product for identifying server anomalies. Background Art

[0002] At present, some enterprises or institutions, including the financial industry, have built their own computer server rooms, in which a large number of rack servers are deployed. Through the bayonet and slide rails on both sides of the rack servers, the rack servers can be embedded in the standard racks, and multiple rack servers are installed in each rack. In a computer room of a certain size, due to the large number of racks, in order to facilitate the management of the racks, a prominent number will be posted on the top of the rack or on the front mesh door of the rack to identify the specific number or location of the rack.

[0003] In order to ensure the normal operation of the server hardware equipment in the computer room, the on-duty personnel in the computer room need to inspect and identify the status lights of all servers every day to determine whether there are any abnormalities in the status lights. The status lights of servers are usually indicator lights on the servers. Although the specific locations of the indicator lights may vary depending on the type of server, the same standard adopted by the industry is: the indicator lights are always green in normal situations, and yellow or red in abnormal situations. Abnormal situations may include: always yellow, flashing yellow, always red, flashing red, and the indicator lights are off. Inspection personnel usually determine whether there are any abnormalities by directly checking the color of the indicator lights.

[0004] However, manual inspections have the following problems: the number of rack-mounted servers in the computer rooms of banks and other institutions is huge, and computer room inspectors are usually required to conduct inspections multiple times a day, which consumes human resources; manual inspections may result in omissions or errors, for example, missing a rack or a server, or misreading the indicator light; status light abnormalities are difficult to detect, for example, under normal circumstances, the servers on the rack will have multiple green indicator lights. If the indicator light of a server is abnormal, one of the green lights that should be on is not on, which may be difficult to detect. Summary of the invention

[0005] In view of the above problems, the present disclosure provides a method, apparatus, device, medium and program product for identifying server anomalies.

[0006] According to a first aspect of the present disclosure, a method for identifying server abnormalities is provided, comprising: acquiring a rack image, the rack image comprising a server arranged in the rack, wherein the server is provided with a status light; adjusting image information of the rack image based on an adaptive adjustment strategy, and acquiring an adjusted first image; and identifying the status light of the server based on the first image, and determining an abnormality of the server according to the identification result of the status light of the server.

[0007] According to an embodiment of the present disclosure, collecting rack images includes: photographing the rack at different time intervals at the same position to obtain N rack images, where N≥5; identifying the status light of the server based on the first image includes: identifying the status light of the server by comparing the first images corresponding to the N rack images respectively.

[0008] According to an embodiment of the present disclosure, the adaptive adjustment strategy includes at least one of image brightness adaptive adjustment, image contrast adaptive adjustment and image color enhancement.

[0009] According to an embodiment of the present disclosure, it is characterized in that the image brightness adaptive adjustment includes: adaptively adjusting the brightness value of the rack image based on the pixel value level of the image information.

[0010] According to an embodiment of the present disclosure, the image contrast adaptive adjustment includes: adaptively adjusting the contrast of the rack image based on the contrast level of the image information.

[0011] According to an embodiment of the present disclosure, image color enhancement includes: enhancing three channels of the rack image respectively by a color enhancement factor; and synthesizing the enhanced three channels.

[0012] According to the method for identifying server abnormalities in an embodiment of the present disclosure, it also includes: obtaining location information of servers of the same type as the server based on the configuration management system, wherein the shape, position, and function of the status lights in the servers of the same type are the same as the shape, position, and function of the status lights in the server; extracting images of servers of the same type based on the location information; and determining the abnormal situation of the server based on the images of the servers of the same type.

[0013] According to an embodiment of the present disclosure, determining an abnormal situation of a server based on images of servers of the same type includes: intercepting a second image corresponding to the server from a rack image; converting the second image and the image of the server of the same type into binary images respectively through pixel transformation, wherein in the binary image, the color of the status light is different from the color of other areas; and comparing the status light of the server with the status lights of servers of the same type based on the converted binary image to determine the abnormal situation of the server.

[0014] According to an embodiment of the present disclosure, the abnormal situation of the server includes at least one of: abnormal color of the status light, blinking of the status light, long-on of the status light, and off of the status light.

[0015] A second aspect of the present disclosure provides a device for identifying server abnormalities, including: a collection module, used to collect a rack image, the rack image includes a server arranged in the rack, wherein the server is provided with a status light; an adjustment module, used to adjust image information of the rack image based on an adaptive adjustment strategy, and obtain an adjusted first image; and an identification module, used to identify the status light of the server based on the first image, and determine the abnormality of the server according to the identification result of the status light of the server.

[0016] According to the server abnormality identification device of the embodiment of the present disclosure, it also includes: an acquisition module, which is used to obtain the location information of the same type of server corresponding to the server based on the configuration management system, wherein the shape, position, and function of the status light in the same type of server are the same as the shape, position, and function of the status light in the server; an extraction module, which is used to extract the image of the same type of server based on the location information; and the identification module is also used to determine the abnormal situation of the server according to the image of the same type of server.

[0017] A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.

[0018] The fourth aspect of the present disclosure further provides a computer-readable storage medium having a computer program or instructions stored thereon, which implements the steps of the above method when the above computer program or instructions are executed by a processor.

[0019] The fifth aspect of the present disclosure further provides a computer program product, including a computer program or instructions, which implement the steps of the above method when the above computer program or instructions are executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above contents and other purposes, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0021] Figure 1 The application scenario diagram schematically shows the method, apparatus, device, medium and program product for identifying server anomalies according to an embodiment of the present disclosure;

[0022] Figure 2 A flowchart of a method for identifying server abnormality according to an embodiment of the present disclosure is schematically shown;

[0023] Figure 3 A flowchart of a method for identifying server abnormality according to another embodiment of the present disclosure is schematically shown;

[0024] Figure 4A flowchart for determining an abnormal situation of a server based on images of servers of the same type according to an embodiment of the present disclosure is schematically shown;

[0025] Figure 5 A schematic diagram schematically shows a binary image of a rack image according to an embodiment of the present disclosure;

[0026] Figure 6 A schematic diagram schematically shows a binary image after expansion according to an embodiment of the present disclosure;

[0027] Figure 7 A structural block diagram schematically shows a device for identifying server abnormality according to an embodiment of the present disclosure; and

[0028] Figure 8 A structural block diagram schematically shows a device for identifying server abnormality according to another embodiment of the present disclosure; and

[0029] Fig. 9 A block diagram of an electronic device suitable for implementing a method for identifying server anomalies according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0030] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0031] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0032] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0033] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0034] Some block diagrams and / or flow charts are shown in the accompanying drawings. It should be understood that some boxes or combinations thereof in the block diagrams and / or flow charts can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable server abnormality identification device, so that these instructions can be constructed to implement the functions / operations described in these block diagrams and / or flow charts when executed by the processor. The technology of the present disclosure can be implemented in the form of hardware and / or software (including firmware, microcode, etc.). In addition, the technology of the present disclosure can take the form of a computer program product on a computer-readable storage medium storing instructions, which can be used by an instruction execution system or used in combination with an instruction execution system.

[0035] The embodiment of the present disclosure provides a method for identifying server abnormalities, including: collecting a rack image, the rack image including servers arranged in the rack, wherein the servers are provided with status lights; adjusting the image information of the rack image based on an adaptive adjustment strategy, and obtaining an adjusted first image; and identifying the status lights of the servers based on the first image, and determining the abnormality of the server according to the identification result of the status lights of the servers. The method is applied to a server room, and the abnormality of the rack server is determined by automatically identifying the status of the status lights of the rack servers.

[0036] The server anomaly identification method provided by the disclosed embodiment can reduce human resource investment, improve work efficiency, and avoid the problems of missed or wrong observations in manual inspections. Specifically, for the collected rack image, the image information of the rack image is adjusted through an adaptive adjustment strategy, and image recognition is performed on the adjusted image. The display of the server's status light can be clearly observed, and then it can be determined whether the server has an abnormality. By automatically identifying the status light of the rack server, it is possible to avoid inspection personnel from inspecting the computer room every day; the adaptive adjustment strategy solves the problems of exposure and smoothness of the captured image, and can obtain a rack image with obvious color, brightness, and contrast, thereby improving the accuracy of server anomaly detection.

[0037] It should be noted that the server anomaly identification method and device of the embodiment of the present disclosure can be used in the field of artificial intelligence, and can also be used in any field other than the field of artificial intelligence. The present disclosure does not limit the application field of the server anomaly identification method and device.

[0038] Figure 1 The following schematically shows an application scenario diagram of a method and device for identifying server anomalies according to an embodiment of the present disclosure. It should be noted that: Figure 1 The examples shown are merely scenarios in which the embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0039] like Figure 1 As shown, the application scenario 100 according to this embodiment may include a terminal device, a network 104 and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0040] The user can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0041] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0042] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0043] It should be noted that the server anomaly identification method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the server anomaly identification device provided in the embodiment of the present disclosure can generally be set in the server 105. The server anomaly identification method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the server anomaly identification device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0044] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0045] The following will be based on Figure 1 The scene described by Figure 2~Figure 6 The method for identifying server anomalies in an embodiment of the present disclosure is described in detail.

[0046] Figure 2 The flowchart of the method for identifying server abnormality according to an embodiment of the present disclosure is schematically shown.

[0047] like Figure 2 As shown, the server abnormality identification method 200 includes operations S210 to S230.

[0048] In operation S210, a rack image is acquired, where the rack image includes servers arranged in the rack, wherein the servers are provided with status lights.

[0049] In the embodiments of the present disclosure, each rack needs to be photographed from the front of the rack to obtain a rack image. In the same rack image, the following information is included: rack (also called cabinet) number sticker, complete rack outer frame, each server in the rack, server status light details, etc. For example, the rack image includes a rack number sticker above, and the rack image includes a server status light on the left or right side. The above-listed positions of the rack number sticker and server status light are only examples. For different computer rooms and different rack-mounted servers, the positions of the rack number sticker and server status light are different.

[0050] Acquiring rack images includes: photographing the rack at different time intervals at the same position to obtain N rack images, where N≥5. Specifically, photographing at least 5 times at different intervals at the same position, for example, the intermediate time intervals may be 1 second, 1.1 seconds, 1.2 seconds, and 1.3 seconds, to ensure that the status light abnormality can be captured even when the status light is flashing. The listed intermediate time intervals are only examples, and the specific time intervals can be set according to actual conditions, which will not be elaborated in detail here.

[0051] In some embodiments, rack images can be collected manually or by a currently more mature automatic inspection robot, which is an automated machine that takes pictures at a fixed position and can automatically collect images of all racks in the computer room. Specifically, rack images in the computer room can be collected regularly or irregularly, and the collected rack images can be used to determine server abnormalities.

[0052] After the gantry image is acquired, in operation S220, image information of the gantry image is adjusted based on an adaptive adjustment strategy to obtain an adjusted first image.

[0053] Since the captured rack image may have problems such as exposure and smoothness, it may be difficult to identify relevant information in the rack image. For example, it is difficult to identify the server in the image due to low exposure, and it is difficult to tell whether the server has a fault.

[0054] In the embodiments of the present disclosure, the adaptive adjustment strategy can adjust the image information of the captured image, reduce or avoid the problem of difficult-to-distinguish image caused by exposure, smoothness, etc., and obtain a clear rack image. For example, in the case where the specific location of a faulty server is difficult to distinguish due to lack of focus, the unfocused rack image is adjusted through the adaptive adjustment strategy, and the specific location of the faulty server is identified based on the adjusted rack image.

[0055] Through a series of adaptive image adjustment strategies, a more obvious and intuitive rack image can be obtained, and the current status of each server can be clearly seen.

[0056] In operation S230, the status light of the server is identified based on the first image, and an abnormal situation of the server is determined according to the identification result of the status light of the server.

[0057] In some embodiments, the abnormality of the server can be determined by identifying the first image enhanced by the adaptive image adjustment strategy. Specifically, the abnormality of the server can be determined by identifying the display of the status light of the server in the first image. For example, if the status light of a server in the first image is red, then the server has an abnormality indicated by the red status light.

[0058] Further, after collecting N rack images, identifying the status light of the server based on the first image includes: identifying the status light of the server by comparing the first images corresponding to the N rack images. For example, if the number of lit status lights in the first images corresponding to the N rack images is inconsistent, there is a situation where the status light is flashing, and one or more servers have a fault indicated by the flashing status light. By searching for a server whose status light is not lit in the multiple first images, the server is a faulty server, and the server has a fault corresponding to the flashing status light.

[0059] In some embodiments, the abnormal condition of the server includes at least one of: abnormal color of the status light, blinking of the status light, long-on status light, and off status light.

[0060] Specifically, under normal circumstances, the indicator light is displayed as green and always on, and under abnormal circumstances, the indicator light is displayed as yellow or red. Abnormal situations may include: yellow and always on, yellow flashing, red and always on, red flashing, the status light is off, etc., and the color of the indicator light can be checked to determine whether the corresponding server has an abnormality. The normal and abnormal conditions of the indicator light can be set according to actual needs and configured by the server manufacturer, and the present disclosure does not limit this. The server abnormality identification method according to the embodiment of the present disclosure can identify the state of the server status light, and determine the abnormality of the server based on the corresponding relationship between the state and the server failure.

[0061] In an embodiment of the present disclosure, the method for identifying server abnormalities may collect rack images regularly or irregularly, and identify server status lights in the rack images to determine abnormal conditions of the servers.

[0062] In some embodiments, the adaptive adjustment strategy includes at least one of image brightness adaptive adjustment, image contrast adaptive adjustment, and image color enhancement.

[0063] For example, for the acquired rack image, the image brightness can be adjusted by adaptively adjusting the image brightness to obtain the adjusted first image, the image contrast can be adjusted by adaptively adjusting the image contrast to obtain the adjusted first image, or the image color can be adjusted by enhancing the image color to obtain the adjusted first image. Which adaptive adjustment method to use can be determined based on the problems existing in the rack image.

[0064] For example, for the acquired rack image, the image brightness and contrast can be adjusted by adaptively adjusting the image brightness and the image contrast to obtain the adjusted first image, the image contrast and color can be adjusted by adaptively adjusting the image contrast and the image color enhancement to obtain the adjusted first image, or the image color and brightness can be adjusted by adaptively adjusting the image color and the image brightness to obtain the adjusted first image. For situations where the image problem is more complicated, the image information of the rack image can be adjusted by two adaptive adjustment strategies. The order of adjusting the image by the two adaptive adjustment methods is not specifically limited and needs to be selected according to the specific situation of the rack image.

[0065] Exemplarily, for the collected rack image, the image brightness, contrast and color can be adjusted by adaptive adjustment of image brightness, adaptive adjustment of image contrast and image color enhancement to obtain the adjusted first image. For situations where the image problem is complex and there are multiple problems, the image information of the rack image can be adjusted by three adaptive adjustment strategies. There is no specific limitation on the order in which the three adaptive adjustment methods adjust the image, and it is necessary to analyze and select according to the specific situation of the rack image. For example, the image brightness of the rack image can be adjusted by adaptive adjustment of image brightness first, and the image contrast of the rack image after the brightness adjustment can be adjusted by adaptive adjustment of image contrast. After adjusting the image contrast, the color of the rack image can be adjusted by image color enhancement, so as to obtain an observation image with obvious brightness, contrast and color, and clearly see the current status of each server.

[0066] In some embodiments, adaptively adjusting the image brightness includes: adaptively adjusting the brightness value of the rack image based on the pixel value level of the image information.

[0067] The image brightness adaptive adjustment formula is as follows:

[0068] (1)

[0069] in, It is the pixel value of the corresponding position of the two-dimensional image, and its value range is [0, 255], where 0 represents black and 255 represents white; is the current pixel value level. When the pixel value is too bright, is a value less than 1. When the pixel value is too dark, is a value greater than 1; is the pixel value at the position after brightness adjustment. Formula (1) can realize the pixel adjustment function.

[0070] In some embodiments, image brightness is adaptively adjusted for each channel of the gantry image, that is, the brightness value of each channel is adaptively adjusted based on the pixel value level of the image information of the channel, and the adjusted gantry image is obtained by synthesizing each adjusted channel.

[0071] The pixel value level of the image information reflects the overall brightness of the image. By adaptively adjusting the brightness value of the image based on the pixel value level of the image information, the brightness of the entire image can be made more uniform, solving the problem of abnormal recognition caused by the status light in the image being too dark or too bright due to shooting problems, and the status light turning black during subsequent processing.

[0072] In some embodiments, adaptively adjusting the image contrast includes: adaptively adjusting the contrast of the gantry image based on a contrast level of the image information.

[0073] The image contrast adaptive adjustment formula is as follows:

[0074] (2)

[0075] in, is the image brightness; yes The contrast between two points; yes Distance function between two points; is the average pixel value of the image; is the contrast level of the image; is the adjusted image brightness.

[0076] Exemplarily, based on the adaptive adjustment of image contrast, when the average contrast is greater than 1, the image contrast is adaptively reduced, and when the average contrast is less than 1, the contrast is adaptively increased. The lower the average brightness of the image, the lower the visual contrast will be, and the closer the brightness is, the closer the contrast level is to 0. The more the brightness increases, the more obvious the contrast is, and the key features of the image are more prominent.

[0077] In some embodiments, image contrast is adaptively adjusted for each channel of the gantry image, that is, the contrast of each channel is adaptively adjusted based on the contrast level of image information of the channel, and the adjusted gantry image is acquired by synthesizing each adjusted channel.

[0078] The rack image adjusted through adaptive image contrast adjustment has a more obvious outline, and the specific position of each server can be seen more clearly.

[0079] Exemplarily, the image color enhancement includes: enhancing three channels of the rack image respectively by using a color enhancement factor; and synthesizing the enhanced three channels.

[0080] The rack image is an RGB three-color image. It is necessary to perform color enhancement on each channel of the rack image. Specifically, the color enhancement factor is used to enhance the color of the rack image. aisle, aisle, The image color enhancement formula is as follows: Formulas (3), (4) and (5) are respectively aisle, Channel and The formula for color enhancement of the channel, formula (6) is the formula for synthesizing the three enhanced channels.

[0081] (3)

[0082] (4)

[0083] (5)

[0084] (6)

[0085] In the above formula, is the color enhancement factor; , and The enhanced Channel image, Channel images and Channel image; This is a color-enhanced rack image.

[0086] Image color enhancement can form a rack image with obvious colors, further enhancing the color information of the status light.

[0087] During the server status light recognition process, the image information of the collected rack image is adjusted through an adaptive adjustment strategy, and the status light recognition is performed based on the adjusted image information. This can solve problems such as inaccurate focus and inconsistent exposure in the captured image, and help to automatically identify the status of the status light of the rack server and help to automatically identify abnormalities of the rack server.

[0088] In fact, during the inspection of the server in the computer room, in addition to abnormal situations such as the server status light showing red or yellow, there are other problems such as the server status light is off. For example, for the same model of server, the lighting situation of a server is different from that of other servers of the same model, with one less green light or one more green light on, which is difficult to detect. In this regard, the embodiment of the present disclosure judges the abnormal situation of the server based on the display of the status lights of the same type of servers. Figure 3 A method for identifying server abnormalities according to another embodiment of the present disclosure is described.

[0089] Figure 3 The flowchart of a method for identifying server abnormality according to another embodiment of the present disclosure is schematically shown.

[0090] like Figure 3 As shown, the server abnormality identification method 300 according to the embodiment of the present disclosure may include operations S310 to S330, and operations S310 to S330 may be operations performed on the basis of operations S210 to S230.

[0091] In operation S310, location information of a server of the same type as the server is acquired based on the configuration management system.

[0092] Among them, the shape, position, and function of the status light in the same type of server are the same as the shape, position, and function of the status light in the server.

[0093] It should be noted that the same type of server includes the same model server. In a broad sense, the same type of server can be a server of the same model before or after the update, and the status lights of the same type of server are exactly the same. Specifically, the shape of the status light and the relative position in the same type of server are exactly the same, and the corresponding relationship between the display state of the status light and the abnormal situation of the server is exactly the same. For example, in the same type of server, the status light showing red and always on means the same thing. The same type of server can also be understood as a server with exactly the same appearance and the same function of the status light.

[0094] In addition, a configuration management system is used in the information technology architecture. The resource code, server model, hardware configuration, rack location, etc. of each server are recorded in the configuration management system. For example, the following Table 1 shows the relevant information of a server recorded by the configuration management system. The resource code of the server is 310000768, the model is ××4008, and the hardware configuration is 4C8G. In the rack location column, "48" refers to the rack number, and "3" refers to the server position of the server from the bottom to the top of the rack. Specifically, the server is the third server in the 48th rack. It should be clear that the relevant information of the server recorded by the configuration management system shown in Table 1 is only an example. In fact, the configuration management system can record more relevant information of each server, such as the purchase time, size, function, brand, etc., for searching and managing the server.

[0095] Table 1 Server information recorded by the configuration management system

[0096] Resource Encoding 310000768 Server Model ××4008 Hardware Configuration 4C8G Rack location 48-3

[0097] Since the configuration management system accurately records the model of each server, the configuration management system can be used to obtain relevant information about servers of the same type as the server, such as location, hardware configuration, resource code, etc. In fact, other factors such as the purchase time, size, function, brand, etc. of each server recorded in the configuration management system can also be considered to obtain servers of the same type as the server and the locations of these servers of the same type.

[0098] Exemplarily, location information of servers of the same type as the server may be acquired based on the configuration management system, and in operation S320, images of servers of the same type may be extracted based on the location information.

[0099] The image of each server can be captured by image recognition technology or by an automated program. Specifically, images of servers of the same type can be acquired from rack images based on their positions obtained from the configuration management system. For example, images of servers of the same type at corresponding positions can be captured from the collected rack images by an automated capture program.

[0100] After acquiring the images of the same type of servers, in operation S330, the abnormality of the server is determined according to the images of the same type of servers. Figure 4 A method for determining an abnormal situation of a server based on images of servers of the same type is described.

[0101] Figure 4 A flowchart for determining an abnormal situation of a server based on images of servers of the same type according to an embodiment of the present disclosure is schematically shown.

[0102] like Figure 4 As shown, the server abnormality identification method 400 according to the embodiment of the present disclosure includes operations S410 to S430.

[0103] In operation S410, a second image corresponding to a server is intercepted from a rack image.

[0104] The image of the server can be captured from the rack image through image recognition technology and automated programs. Specifically, based on the position of the server in the rack image, a second image corresponding to the server can be obtained from the rack image. For example, for rack position 48-3, an image corresponding to the third server in rack No. 48 can be captured from the rack image through an automated program.

[0105] In some embodiments, the rack image corresponding to the second image and the rack image corresponding to the image of the same type of server may be images taken in the same time period.

[0106] In operation S420, the second image and the image of the same type of server are respectively converted into binary images through pixel transformation, wherein in the binary image, the color of the status light is different from the color of other areas.

[0107] In the embodiment of the present disclosure, the status light is identified and located using a binary image, and any method that can convert the second image and the image of the same type of server into a binary image can be applied. For example, pixel transformation can be performed by the inRange(img, lower_img, upper_img) function in the computer vision library, where img represents the input image; inRange changes the pixel values ​​of the input image whose pixel values ​​are lower than lower_img to 0 (black); changes the pixel values ​​of the input image whose pixel values ​​are higher than upper_img to 0; changes the pixel values ​​of the input image whose pixel values ​​are between lower_img and upper_img to 255 (white). Changing the image color corresponding to the pixel values ​​between lower_img and upper_img to white actually means changing the image at the position of the indicator light in the rack image to white, and changing other areas in the rack image to black. For example, the positions corresponding to the green indicator light, the yellow indicator light, etc. in the rack image are changed to white through pixel transformation.

[0108] Figure 5 A schematic diagram of a binary image of a rack image according to an embodiment of the present disclosure is schematically shown.

[0109] like Figure 5 As shown, in the binary image, the position corresponding to the light-emitting status light in the rack image is displayed in white, and the background area in the image is displayed in black. The binary image of the second image is a part of the binary image of the corresponding rack image. Similarly, the binary image of the image of the same type of server is also a part of the binary image of the corresponding rack image. In order to more clearly show the distribution of the status light in the binary image, only the binary image of the rack image is shown.

[0110] In some embodiments, contour detection may be performed directly on the binary image after pixel transformation, or a dilation operation may be performed on the binary image obtained after pixel transformation, and contour detection may be performed on the dilated binary image.

[0111] Figure 6 A schematic diagram of a binary image after expansion according to an embodiment of the present disclosure is schematically shown.

[0112] Figure 6 is Figure 5Based on the binary image of the rack image, the binary image is expanded. In the expanded binary image, the position of the light-emitting status light is displayed in white, and the outline of the status light is very obvious. Exemplarily, any method that can expand the binary image can be applied, which will not be elaborated in detail here.

[0113] In some embodiments, contour detection can be performed using the findContours function in the computer vision library. Specifically, contour detection can be performed on the binary image of the rack image or the dilated binary image to obtain , , , Four values, among which, , is the coordinate of the upper left corner of the target contour, , are the width and height of the outline respectively. , , , The position and relative size of the status light can be determined, and the physical coordinates of the status light, i.e. the center point, can be obtained. , you can also get the distance between the status light and the corresponding rack number Furthermore, the height of each server in the rack is fixed, and the distance between the status light and the corresponding rack number is within the position range of the corresponding server.

[0114] In operation S430, the status light of the server is compared with status lights of servers of the same type based on the converted binary image to determine an abnormality of the server.

[0115] Specifically, the contour information of the converted binary image can be applied to the actual server image, and based on the contour information in the binary image, the status light on the actual server image can be circled, and the image that circles the status light on the actual server image can be called a "light map". Based on the coordinates of each light in the acquired server "light map", it can be determined which status lights in the "light map" of the same type of server belong to the same status light, and the lighting conditions of the status lights of the same type of servers are automatically compared through algorithms to determine abnormal power-off servers and servers with abnormal status lights. For example, by performing algorithmic comparison on the lighting conditions of the status lights of the same type of servers, servers with off status lights and servers with abnormal status lights can be determined.

[0116] In the embodiment of the present disclosure, the image information of the image is adjusted through an adaptive adjustment strategy, and the status light of the rack-mounted server is automatically identified based on the adjusted image, so that the abnormal situation of the server can be automatically determined. By combining image recognition and artificial intelligence and applying them to the field of computer room fault inspection, work efficiency can be improved, human resource consumption can be avoided, and the accuracy of server abnormality detection can be improved.

[0117] Based on the above-mentioned server abnormality identification method, the present disclosure also provides a server abnormality identification device. Figure 7 The device is described in detail.

[0118] Figure 7 The structural block diagram of the apparatus for identifying server abnormality according to an embodiment of the present disclosure is schematically shown.

[0119] like Figure 7 As shown, the server abnormality identification device 700 of the embodiment includes a collection module 710 , an adjustment module 720 and an identification module 730 .

[0120] The acquisition module 710 is used to acquire a rack image, which includes servers arranged in the rack, wherein the servers are provided with status lights. In one embodiment, the acquisition module 710 can be used to perform the operation S210 described above, which will not be described in detail here.

[0121] The adjustment module 720 is used to adjust the image information of the rack image based on the adaptive adjustment strategy to obtain the adjusted first image. In one embodiment, the adjustment module 720 can be used to perform the operation S220 described above, which will not be repeated here.

[0122] The recognition module 730 is used to recognize the status light of the server based on the first image, and determine the abnormality of the server according to the recognition result of the status light of the server. In one embodiment, the recognition module 730 can be used to perform the operation S230 described above, which will not be repeated here.

[0123] Figure 8 The structural block diagram of a device for identifying server abnormality according to another embodiment of the present disclosure is schematically shown.

[0124] like Figure 8 As shown, the server abnormality identification device 700 also includes an acquisition model 740 and an extraction module 750.

[0125] The acquisition module 740 is used to acquire the location information of the same type of server corresponding to the server based on the configuration management system, wherein the shape, position, and function of the status light in the same type of server are the same as the shape, position, and function of the status light in the server. In one embodiment, the acquisition module 740 can be used to perform the operation S310 described above, which will not be repeated here.

[0126] The extraction module 750 is used to extract images of servers of the same type based on the location information. In one embodiment, the extraction module 750 can be used to perform the operation S320 described above, which will not be described in detail here.

[0127] The identification module 730 is also used to determine the abnormal situation of the server according to the images of the servers of the same type. In one embodiment, the identification module 730 can be used to perform the operation S330 described above, which will not be described in detail here.

[0128] According to an embodiment of the present disclosure, any multiple modules among the acquisition module 710, the adjustment module 720, the identification module 730 acquisition model 740 and the extraction module 750 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the acquisition module 710, the adjustment module 720, the identification module 730 acquisition model 740 and the extraction module 750 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in a suitable combination of any of them. Alternatively, at least one of the acquisition module 710 , the adjustment module 720 , the identification module 730 , the acquisition model 740 , and the extraction module 750 may be at least partially implemented as a computer program module, and when the computer program module is executed, a corresponding function may be performed.

[0129] Fig. 9 A block diagram of an electronic device suitable for implementing a method for identifying server anomalies according to an embodiment of the present disclosure is schematically shown.

[0130] like Fig. 9As shown, the electronic device 900 according to an embodiment of the present disclosure includes a processor 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage part 908 to a random access memory (RAM) 903. The processor 901 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 901 may also include an onboard memory for caching purposes. The processor 901 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0131] In RAM 903, various programs and data required for the operation of electronic device 900 are stored. Processor 901, ROM 902 and RAM 903 are connected to each other via bus 904. Processor 901 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 902 and / or RAM 903. It should be noted that the program can also be stored in one or more memories other than ROM 902 and RAM 903. Processor 901 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0132] According to an embodiment of the present disclosure, the electronic device 900 may further include an input / output (I / O) interface 905, which is also connected to the bus 904. The electronic device 900 may further include one or more of the following components connected to the input / output (I / O) interface 905: an input portion 906 including a keyboard, a mouse, etc.; an output portion 907 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 908 including a hard disk, etc.; and a communication portion 909 including a network interface card such as a LAN card, a modem, etc. The communication portion 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the input / output (I / O) interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed, so that a computer program read therefrom is installed into the storage portion 908 as needed.

[0133] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0134] According to an embodiment of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 902 and / or RAM 903 described above and / or one or more memories other than ROM 902 and RAM 903.

[0135] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the server abnormality identification method provided by the embodiment of the present disclosure.

[0136] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 901. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0137] In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of a signal on a network medium, and downloaded and installed through the communication part 909, and / or installed from a removable medium 911. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0138] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 909, and / or installed from the removable medium 911. When the computer program is executed by the processor 901, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0139] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0140] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0141] It will be appreciated by those skilled in the art that the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations or combinations are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0142] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for identifying server anomalies, characterized in that: The method comprises: Acquiring a rack image, wherein the rack image includes a server arranged in the rack, wherein the server is provided with a status light; Adjusting the image information of the rack image based on an adaptive adjustment strategy to obtain an adjusted first image; and The status light of the server is identified based on the first image, and the abnormal situation of the server is determined according to the identification result of the status light of the server.

2. The method according to claim 1, characterized in that The collecting of rack images comprises: photographing the rack at different time intervals at the same position to obtain N rack images, wherein N≥5; The identifying the status light of the server based on the first image includes: identifying the status light of the server by comparing the first images respectively corresponding to the N rack images.

3. The method according to claim 1, characterized in that The adaptive adjustment strategy includes at least one of image brightness adaptive adjustment, image contrast adaptive adjustment and image color enhancement.

4. The method according to claim 3, characterized in that The image brightness adaptive adjustment comprises: The brightness value of the rack image is adaptively adjusted based on the pixel value level of the image information.

5. The method according to claim 3, characterized in that: The image contrast adaptive adjustment comprises: The contrast of the gantry image is adaptively adjusted based on the contrast level of the image information.

6. The method according to claim 3, characterized in that The image color enhancement includes: enhancing the three channels of the rack image respectively by a color enhancement factor; and The three channels after synthesis enhancement.

7. The method according to claim 1, characterized in that The method further comprises Acquire location information of a server of the same type as the server based on the configuration management system, wherein the shape, position, and function of the status light in the server of the same type are the same as the shape, position, and function of the status light in the server; Extracting images of the same type of servers based on the location information; and An abnormal situation of the server is determined according to the images of the servers of the same type.

8. The method according to claim 7, characterized in that Determining the abnormal situation of the server according to the image of the server of the same type includes: capturing a second image corresponding to the server from the rack image; Converting the second image and the image of the same type of server into binary images respectively by pixel transformation, wherein in the binary image, the color of the status light is different from the color of other areas; as well as The status light of the server is compared with the status lights of the servers of the same type based on the converted binary image to determine the abnormal situation of the server.

9. The method according to claim 1, characterized in that: The abnormal situation of the server includes at least one of: abnormal status light color, blinking status light, long-on status light, and off status light.

10. A device for identifying server anomalies, characterized in that: The device comprises: A collection module, used for collecting a rack image, wherein the rack image includes a server arranged in the rack, wherein the server is provided with a status light; an adjustment module, configured to adjust the image information of the rack image based on an adaptive adjustment strategy, and obtain an adjusted first image; and The recognition module is used to recognize the status light of the server based on the first image, and determine the abnormal situation of the server according to the recognition result of the status light of the server.

11. The device according to claim 10, characterized in that The device also includes: an acquisition module, configured to acquire location information of a server of the same type as the server based on a configuration management system, wherein the shape, position, and function of the status light in the server of the same type are the same as the shape, position, and function of the status light in the server; an extraction module, configured to extract images of the same type of servers based on the location information; and The identification module is further used to determine the abnormal situation of the server according to the image of the server of the same type.

12. An electronic device comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 9.

13. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

14. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images