BMC equipment monitoring method, device, equipment and readable storage medium

Abstract

The present application discloses a BMC device monitoring method, device, equipment and readable storage medium, the method comprising: obtaining a video captured by a shooting device installed inside the BMC device; calculating the average grayscale value of each frame image in the video, and calculating the average grayscale value difference between two adjacent frames of the image; if the average grayscale value difference is greater than a first threshold, obtaining the current image inside the BMC device; inputting the current image into a pre-trained BMC device unpacking detection model to obtain a first detection value; if the first detection value is greater than a second threshold, determining that the chassis shell of the BMC device is opened, and generating an alarm message based on the video and the current image. The above technical solution disclosed in the present application uses a combination of the video inside the BMC device and the image inside the BMC device to monitor the BMC device for theft, thereby improving the reliability and accuracy of the BMC device theft monitoring.

Description

Technical Field

[0001] The present application relates to the technical field of equipment monitoring, and more specifically, to a BMC equipment monitoring method, apparatus, device and readable storage medium. Background Art

[0002] Servers, computers, switches, industrial computers and other devices including BMC (Baseboard Management Controller, baseboard management controller) (referred to as BMC devices) provide applications for users, while their security and anti-theft have also become one of the key issues.

[0003] At present, the BMC device is often monitored for theft risks with the help of mechanical switches and the BMC contained in the BMC device. Specifically, the BMC is used to obtain the switch state of the mechanical switch installed on the chassis shell of the BMC device, and then, whether the chassis of the BMC device is opened is determined according to the switch state of the mechanical switch. If it is determined that the chassis of the BMC device is opened, it indicates that the BMC device is at risk of theft. At this time, an alarm message indicating that the BMC device is at risk of theft is generated and sent to the user. However, mechanical aging of the mechanical switch, external vibrations, etc. can also cause the state of the mechanical switch to change. Therefore, the existing method of monitoring the theft of BMC devices has the problem of low reliability and accuracy.

[0004] In summary, how to improve the reliability and accuracy of monitoring the theft of BMC devices is a technical problem that needs to be urgently solved by those skilled in the art. Summary of the invention

[0005] In view of this, the purpose of the present application is to provide a BMC device monitoring method, apparatus, device and readable storage medium, so as to improve the reliability and accuracy of monitoring the theft of BMC devices.

[0006] In order to achieve the above objectives, this application provides the following technical solutions:

[0007] A BMC device monitoring method, comprising:

[0008] Obtain the video captured by the camera installed inside the BMC device;

[0009] Calculate the average grayscale value of each frame image in the video, and calculate the average grayscale value difference between two adjacent frame images using the average grayscale values ​​of two adjacent frame images;

[0010] If the average gray value difference is greater than a first threshold, acquiring a current image inside the BMC device;

[0011] Inputting the current image into a pre-trained BMC device unpacking detection model to obtain a first detection value;

[0012] If the first detection value is greater than a second threshold, it is determined that the chassis shell of the BMC device is opened, and an alarm message is generated according to the video and the current image.

[0013] Preferably, when the first detection value is greater than a second threshold, the method further includes:

[0014] Detecting a switch state of a mechanical switch corresponding to a chassis shell of the BMC device;

[0015] If the mechanical switch is in an open state, it is determined that the chassis shell of the BMC device is opened.

[0016] Preferably, after generating the warning information according to the video and the current image, the method further includes:

[0017] Output the warning information.

[0018] Preferably, before outputting the warning information, the method further comprises:

[0019] Determine whether the communication module can communicate normally;

[0020] If not, the built-in SIM card is used to provide mobile network.

[0021] Preferably, after obtaining the video captured by the camera installed inside the BMC device, the method further includes:

[0022] Perform smoke detection inside the BMC device based on the video.

[0023] Preferably, performing smoke detection inside the BMC device according to the video includes:

[0024] Calculating the difference between two adjacent frames of the video using an inter-frame difference method;

[0025] If the difference value is greater than a third threshold, acquiring a current internal image of the BMC device;

[0026] Inputting the current internal image into a pre-trained smoke detection model to obtain a second detection value;

[0027] If the second detection value is greater than a fourth threshold, it is determined that smoke exists inside the BMC device, and smoke alarm information is generated according to the video and the current internal image.

[0028] Preferably, when the second detection value is greater than a fourth threshold, the method further includes:

[0029] Obtaining a smoke value collected by a gas sensor installed at an air outlet of a chassis of the BMC device;

[0030] It is determined whether the smoke value is greater than a fifth threshold value, and if so, it is determined that smoke exists inside the BMC device.

[0031] A BMC equipment monitoring device, comprising:

[0032] A first acquisition module is used to acquire a video captured by a camera installed inside the BMC device;

[0033] A calculation module, used to calculate the average grayscale value of each frame image in the video, and calculate the average grayscale value difference between two adjacent frames of images using the average grayscale values ​​of two adjacent frames of images;

[0034] A second acquisition module, configured to acquire a current image inside the BMC device if the average gray value difference is greater than a first threshold;

[0035] An input module, used for inputting the current image into a pre-trained BMC device unpacking detection model to obtain a first detection value;

[0036] The first determination module is configured to determine that a chassis shell of the BMC device is opened if the first detection value is greater than a second threshold value, and to generate an alarm message according to the video and the current image.

[0037] A BMC device monitoring device, comprising:

[0038] Memory for storing computer programs;

[0039] The processor is used to implement the steps of the BMC device monitoring method as described in any one of the above when executing the computer program.

[0040] A readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the BMC device monitoring method as described in any one of the above are implemented.

[0041] The present application provides a BMC device monitoring method, apparatus, device and readable storage medium, wherein the method comprises: obtaining a video captured by a shooting device installed inside a BMC device; calculating the average grayscale value of each frame image in the video, and calculating the average grayscale value difference between two adjacent frames of image using the average grayscale value of two adjacent frames of image; if the average grayscale value difference is greater than a first threshold, obtaining a current image inside the BMC device; inputting the current image into a pre-trained BMC device unpacking detection model to obtain a first detection value; if the first detection value is greater than a second threshold, determining that a chassis shell of the BMC device is opened, and generating an alarm message according to the video and the current image.

[0042] The above technical solution disclosed in the present application uses a shooting device installed inside the BMC device to collect a video inside the BMC device, and calculates the average grayscale value difference between two adjacent frames of images in the video. If the average grayscale value difference is greater than a first threshold, it may be due to the fact that the chassis shell of the BMC device is opened, resulting in an excessively large average grayscale value difference between the two adjacent frames of images. At this time, the current image inside the BMC device can be further obtained, and the BMC device unpacking detection module obtained by pre-training is used to detect the current image inside the BMC device to obtain a first detection value. If the first detection value is greater than a second threshold, it is determined that the BMC device chassis is opened, so as to realize the theft monitoring of the BMC device by combining the video inside the BMC device and the image inside the BMC device, thereby reducing the misjudgment of the theft monitoring of the BMC device and improving the reliability and accuracy of the theft monitoring of the BMC device. During the monitoring process, when it is determined that the BMC device chassis is opened, an alarm message is generated based on the video inside the BMC device and the current image inside the BMC device, so that relevant personnel can promptly and intuitively learn that the BMC device is at risk of being stolen and the current specific situation of the BMC device based on the alarm message. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0044] Figure 1 A flowchart of a BMC device monitoring method provided in an embodiment of the present application;

[0045] Figure 2 An internal structure diagram of a BMC device provided in an embodiment of the present application;

[0046] Figure 3 A flowchart of another BMC device monitoring method provided in an embodiment of the present application;

[0047] Figure 4 A smoke detection flow chart provided for an embodiment of the present application;

[0048] Figure 5 A schematic diagram of the structure of a BMC equipment monitoring device provided in an embodiment of the present application;

[0049] Figure 6 A schematic diagram of the structure of a BMC device monitoring device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0051] See also Figure 1 and Figure 2 ,in, Figure 1 A flow chart of a BMC device monitoring method provided in an embodiment of the present application is shown. Figure 2 The internal structure diagram of the BMC device provided by the embodiment of the present application is shown. A BMC device monitoring method provided by the embodiment of the present application may include:

[0052] S11: Acquire a video captured by a camera installed inside the BMC device.

[0053] It should be noted that the BMC device mentioned in this application specifically refers to a device containing a BMC, such as a server, a computer, a switch, an industrial computer, etc., and the BMC device provided in this application is internally installed with a camera, which can capture the video inside the BMC device. In addition, this application can use the BMC contained in the BMC device to realize the monitoring of the BMC, wherein the BMC can provide local and remote diagnosis, console support, configuration management, hardware management, fault analysis, alarm push and other management functions.

[0054] In order to improve the reliability of BMC monitoring, in addition to the power supply module provided inside the BMC device to supply power to the BMC and the communication module, the present application also additionally provides a rechargeable battery (specifically, a lithium battery). When the power supply module is supplying power normally, it can charge the rechargeable battery. When the power supply module is supplying power abnormally, the rechargeable battery can be used to supply power to the BMC and the communication module, so that the BMC can continue to monitor, thereby improving the reliability of the BMC device monitoring. When the rechargeable battery is discharged, the BMC can also collect the remaining power information of the rechargeable battery.

[0055] When monitoring the BMC device, the BMC contained in the BMC device can obtain the video inside the BMC device collected by the shooting device installed in the BMC device in a scheduled or real-time manner. The shooting device installed in the BMC device can start to collect the video inside the BMC device after the BMC device is installed and the chassis shell of the BMC device is closed, that is, the BMC can start to obtain the video after the BMC device is installed and the chassis shell of the BMC device is closed, so as to monitor the BMC device, thereby improving the reliability and accuracy of monitoring.

[0056] After acquiring the video inside the BMC device captured by the shooting device, the BMC can capture multiple frames of the video within a preset time length in real time, and use the multiple frames of the video within the preset time length for subsequent analysis and calculation each time to reduce the amount of data processing each time. It should be noted that the preset time length can be set according to actual conditions, such as 3 seconds or other time, etc. Taking the preset time length of 3 seconds as an example, if the video is 15 frames per second, 45 frames of images are captured in 3 seconds.

[0057] S12: Calculate the average grayscale value of each frame image in the video, and calculate the average grayscale value difference between two adjacent frame images using the average grayscale values ​​of two adjacent frame images.

[0058] On the basis of step S11, BMC calculates the average grayscale value of each frame image in the video. Specifically, all the pixels of each frame image are traversed, and the grayscale values ​​of all the pixels of each frame image are accumulated to obtain the sum of the grayscale values ​​of each frame image, and then the sum of the grayscale values ​​of each frame image is divided by the number of pixels in the corresponding frame image to obtain the average grayscale value of each frame image. Among them, when calculating the average grayscale value, the average grayscale value of each frame image can be calculated in turn, that is, the average grayscale value of the first frame image can be calculated first, and then the average grayscale value of the second frame image can be calculated... until the average grayscale value of the last frame image in the video is calculated.

[0059] After calculating and obtaining the average grayscale value of two adjacent frames of images, the average grayscale values ​​of the two adjacent frames of images may be subtracted to obtain the average grayscale value difference of the two adjacent frames of images. The average grayscale value difference of the two adjacent frames of images located in the latter frame may be subtracted from the average grayscale value difference of the two adjacent frames of images located in the former frame of images to obtain the average grayscale value difference (under normal circumstances, the average grayscale value difference should be close to 0. When the server is turned on, the average grayscale value difference of the latter frame of images will increase, thereby causing the average grayscale value difference to increase). Alternatively, the method of subtracting the average grayscale values ​​of the two adjacent frames of images may not be limited. Instead, after the average grayscale values ​​of the two adjacent frames of images are subtracted to obtain the difference, the absolute value of the difference is taken to obtain the average grayscale value difference of the two adjacent frames of images.

[0060] S13: If the average gray value difference is greater than the first threshold, the current image inside the BMC device is acquired.

[0061] After obtaining the average grayscale value difference between two adjacent frames of images, the average grayscale value difference is compared with a first threshold value, wherein the first threshold value can be set according to the average grayscale value of the image in two situations in which the BMC device is turned on and the BMC device is not turned on in the actual scene.

[0062] If the calculated average gray value difference is not greater than the first threshold, it indicates that the average gray value of two adjacent frames of images does not change much, that is, the color and brightness of the two adjacent frames of images do not change much, and at this time, it indicates that the chassis of the BMC device is not opened. In this case, the BMC can continue to monitor the BMC device.

[0063] If the calculated average gray value difference is greater than the first threshold, it indicates that the average gray value of two adjacent frames of images changes greatly, that is, the color and brightness of the two adjacent frames of images change greatly, and this may be because the chassis shell of the BMC device is opened, resulting in a large change in the average gray value difference of the two adjacent frames of images. To this end, the BMC device can obtain the current image inside the BMC device, specifically, the current image captured by the shooting device installed inside the BMC device can be obtained, so as to combine the current image inside the BMC for further analysis.

[0064] S14: Input the current image into a pre-trained BMC device unpacking detection model to obtain a first detection value.

[0065] On the basis of step S13 , the BMC inputs the acquired current image inside the BMC device into a pre-trained BMC device unpacking detection model to obtain a first detection value.

[0066] Among them, the BMC device unpacking detection model is obtained by pre-training the first deep learning model using the first training sample set. The first training sample set mentioned here specifically includes images of BMC devices in different scenarios when the chassis shell is opened and the corresponding detection values, and images when the chassis shell is not opened and the corresponding detection values. It should be noted that the size of the detection values ​​corresponding to different images in the first training sample set can be set by relevant personnel, and the detection value corresponding to the image when the chassis shell is opened is greater than the detection value corresponding to the image when the chassis shell is not opened.

[0067] S15: If the first detection value is greater than the second threshold, it is determined that the chassis shell of the BMC device is opened, and an alarm message is generated according to the video and the current image.

[0068] Based on step S14, the first detection value can be compared with a second threshold value, wherein the second threshold value is set by relevant personnel. If the first detection value is not greater than the second threshold value, it can be determined that the BMC chassis shell is not opened, and the BMC can continue to monitor the BMC device.

[0069] If the second detection value obtained by the BMC device unpacking detection model is greater than the second threshold, it can be determined that the BMC device chassis shell is opened. At this time, an alarm message can be generated based on the video and current image inside the BMC device obtained by the BMC, that is, the alarm message can include the obtained video and current image inside the BMC device, so that relevant personnel can intuitively and timely determine through the alarm message that the BMC device chassis shell is opened and there is a risk of theft. In addition, the alarm message can also include the BMC device logo, so that relevant personnel can quickly and accurately locate the corresponding BMC device according to the logo in the alarm message.

[0070] Through the above process, it can be seen that compared with the existing method of installing a mechanical switch on the chassis of the BMC device and monitoring whether the BMC device is stolen by using the status of the mechanical switch, the present application combines the internal video calculation of the BMC device with the internal image recognition of the BMC device to monitor the theft of the BMC device, thereby reducing the impact of factors such as time and external vibration on the BMC theft monitoring, thereby reducing the misjudgment of the BMC device theft monitoring and improving the reliability and accuracy of the BMC device theft monitoring.

[0071] The above technical solution disclosed in the present application uses a shooting device installed inside the BMC device to collect a video inside the BMC device, and calculates the average grayscale value difference between two adjacent frames of images in the video. If the average grayscale value difference is greater than a first threshold, it may be due to the fact that the chassis shell of the BMC device is opened, resulting in an excessively large average grayscale value difference between the two adjacent frames of images. At this time, the current image inside the BMC device can be further obtained, and the BMC device unpacking detection module obtained by pre-training is used to detect the current image inside the BMC device to obtain a first detection value. If the first detection value is greater than a second threshold, it is determined that the BMC device chassis is opened, so as to realize the theft monitoring of the BMC device by combining the video inside the BMC device and the image inside the BMC device, thereby reducing the misjudgment of the theft monitoring of the BMC device and improving the reliability and accuracy of the theft monitoring of the BMC device. During the monitoring process, when it is determined that the BMC device chassis is opened, an alarm message is generated based on the video inside the BMC device and the current image inside the BMC device, so that relevant personnel can promptly and intuitively learn that the BMC device is at risk of being stolen and the current specific situation of the BMC device based on the alarm message.

[0072] See also Figure 3 , which shows a flow chart of another BMC device monitoring method provided by an embodiment of the present application. A BMC device monitoring method provided by an embodiment of the present application, when the first detection value is greater than the second threshold, may also include:

[0073] Detecting the switch state of a mechanical switch corresponding to a chassis shell of a BMC device;

[0074] If the mechanical switch is in the open state, it is determined that the chassis case of the BMC device is opened.

[0075] In the present application, after determining that the first detection value is greater than the second detection value, in order to further improve the accuracy and reliability of monitoring the theft of the BMC, the BMC can detect the switch state of the mechanical switch corresponding to the chassis shell of the BMC device, wherein the mechanical switch is installed on the chassis wall of the chassis shell of the BMC device, connected to the BMC to the GPIO (General Purpose Input Output, general input / output port), when the chassis shell is opened, the mechanical switch is in the open state, and when the chassis shell is closed, the mechanical switch is in the closed state. If the BMC determines that the mechanical switch is in the closed state by detecting the switch state of the mechanical switch, it indicates that the chassis shell of the BMC device has not been opened, and at this time, the BMC can continue to monitor the BMC device. If the mechanical switch is in the on state, it can be determined that the chassis shell of the BMC device is opened, that is, if the average grayscale value difference between two adjacent frames of the acquired video is greater than the first threshold, the first detection value obtained by using the BMC device unpacking detection model to detect the current image is greater than the second threshold, and the chassis switch is in the on state, it is determined that the chassis shell of the BMC device is opened. Monitoring the BMC device by combining the three methods can further improve the reliability and accuracy of BMC device theft monitoring.

[0076] A BMC device monitoring method provided in an embodiment of the present application may further include, after generating alarm information according to a video and a current image:

[0077] Output warning information.

[0078] After the BMC generates alarm information based on the video and the current image, it can output the alarm information so that the relevant personnel can obtain the relevant information in a timely and intuitive manner. Specifically, the BMC can output the alarm information by means of e-mail, multimedia message, etc., wherein the e-mail and multimedia message can specifically include a link to the alarm information, and the relevant personnel can quickly learn about the alarm information of the BMC device by clicking on the link to the alarm information, and the e-mail and multimedia message can also include specific alarm information (including video information and current image information), so that the relevant personnel can intuitively obtain the alarm information of the BMC device without clicking on the link.

[0079] A BMC device monitoring method provided in an embodiment of the present application may further include, before outputting alarm information:

[0080] Determine whether the communication module can communicate normally;

[0081] If not, the built-in SIM card is used to provide mobile network.

[0082] In this application, before outputting the alarm information, the BMC can determine whether the internal communication module can communicate normally. If the communication module can communicate normally, the BMC outputs the alarm information through the communication module, wherein the communication module can provide network communication functions of 3G, 4G, and 5G network standards, and the communication module communicates with the BMC through a serial port. In addition, an antenna module can also be set inside the BMC device to use the antenna module to enhance the network signal strength of the communication module.

[0083] If the communication module cannot communicate normally, the BMC can use the built-in SIM (Subscriber Identification Module) card to provide a mobile network, and then the BMC outputs an alarm message through the mobile network. The SIM card mainly refers to a SIM card that supports 3G, 4G, and 5G network standards.

[0084] A BMC device monitoring method provided in an embodiment of the present application may further include, after acquiring a video captured by a camera installed inside the BMC device:

[0085] Perform smoke detection inside the BMC device based on the video.

[0086] In the present application, after obtaining the video captured by the camera installed inside the BMC device, the BMC can also perform smoke detection inside the BMC device based on the acquired video inside the BMC device, so that smoke can be discovered in time when there is smoke, and the accuracy and reliability of smoke detection can be improved through video.

[0087] For details, please refer to Figure 4 , which shows a smoke detection flow chart provided in an embodiment of the present application. A BMC device monitoring method provided in an embodiment of the present application performs smoke detection inside a BMC device based on a video, which may include:

[0088] The difference value between two adjacent frames of the video is calculated using the inter-frame difference method;

[0089] If the difference value is greater than the third threshold, obtaining the current internal image of the BMC device;

[0090] Inputting the current internal image into a pre-trained smoke detection model to obtain a second detection value;

[0091] If the second detection value is greater than the fourth threshold, it is determined that smoke exists inside the BMC device, and smoke alarm information is generated according to the video and the current internal image.

[0092] In the present application, when performing smoke detection inside a BMC device based on a video, the inter-frame difference method can be used to calculate the difference between two adjacent frames in the video, wherein the inter-frame difference method is a method for obtaining the contour of a moving target by performing a difference operation on two adjacent frames in a video image sequence, which can determine whether there is object movement in the image sequence. After calculating the difference between two adjacent frames in the video, the difference between the two adjacent frames can be compared with a third threshold, wherein the size of the third threshold can be specifically set by relevant personnel. If the difference between two adjacent frames of images is not greater than the third threshold, it indicates that there is no smoke inside the BMC device. At this time, the difference value calculation and smoke detection can be continued. If the difference between two adjacent frames of images is greater than the third threshold, it indicates that there may be smoke. At this time, the current internal image of the BMC device can be further obtained (specifically, it can be collected using a camera installed inside the BMC device), and the obtained current internal image can be input into a pre-trained smoke detection model to obtain a second detection value, wherein the smoke detection model is pre-trained using a second training sample set to train a second deep learning model, and the second training sample set mentioned here specifically includes images of the inside of the BMC device at different smoke values ​​and corresponding detection values ​​(the detection value can specifically be a smoke value). After obtaining the second detection value, the second detection value can be compared with the fourth threshold, wherein the size of the fourth threshold can be set by relevant personnel. If the second detection value is not greater than the fourth threshold, it indicates that there is no smoke inside the BMC device. At this time, the BMC can continue to perform smoke detection on the inside of the BMC device. If the second detection value is greater than the fourth threshold, it can be determined that there is smoke inside the BMC device. At this time, smoke alarm information can be generated according to the video and the current internal image, that is, the smoke alarm information can include the acquired video of the inside of the BMC device and the current internal image (wherein the smoke alarm information can also include the second detection value), so that relevant personnel can intuitively and timely determine the smoke situation inside the BMC device through the smoke alarm information.

[0093] Through the above process, it can be seen that the present application realizes smoke detection inside the BMC device by combining the internal video and internal image of the BMC device. Compared with the existing smoke detection using only the gas sensor set at the air outlet of the chassis, the present application is not limited by factors such as gas sensors, and can improve the accuracy of smoke detection inside the BMC device.

[0094] It should be noted that after generating the smoke alarm information, the BMC can also output the smoke alarm information so that relevant personnel can obtain relevant information in a timely and intuitive manner. In addition, before outputting the smoke alarm information, it can also be determined whether the communication module can communicate normally. If not, the built-in SIM card is used to provide a mobile network. That is, the process of outputting the smoke alarm information is similar to the process of outputting the alarm information generated above, which will not be repeated here.

[0095] A BMC device monitoring method provided in an embodiment of the present application may further include, when the second detection value is greater than a fourth threshold, the following steps:

[0096] Obtain the smoke value collected by the gas sensor installed at the chassis air outlet of the BMC device;

[0097] It is determined whether the smoke value is greater than a fifth threshold value. If so, it is determined that smoke exists inside the BMC device.

[0098] In the present application, after determining that the second detection value is greater than the fourth threshold, the BMC can further obtain the smoke value collected by the gas sensor installed at the air outlet of the BMC device chassis, and then determine whether the smoke value collected by the gas sensor is greater than the fifth threshold, wherein the size of the fifth threshold is specifically set by relevant personnel. If the smoke value collected by the gas sensor is greater than the fifth threshold, it is determined that there is smoke inside the BMC device, that is, the present application determines that there is smoke inside the BMC device only when the difference value of two adjacent frames of images in the acquired video is greater than the third threshold, the second detection value obtained by detecting the current internal image using the smoke detection model is greater than the fourth threshold, and the smoke value collected by the gas sensor installed at the air outlet of the BMC device chassis is greater than the fifth threshold, so as to improve the accuracy of smoke detection inside the BMC device; if the smoke value collected by the gas sensor is not greater than the fifth threshold, then the above three methods cannot accurately determine whether there is smoke inside the BMC device at this time, so the BMC can continue to perform smoke detection inside the BMC device, so as to determine whether there is smoke inside the BMC device based on subsequent smoke detection.

[0099] It should be noted that Figure 2 The memory card shown in the figure may mainly refer to an SD card (Secure Digital Memory Card) and a TF (Trans Flash) card, which are used to store relevant information of the BMC (such as alarm information, log information, etc.).

[0100] In addition to using the above-mentioned method to realize the theft monitoring and smoke monitoring of BMC equipment, BMC can also monitor the internal components of BMC equipment, generate corresponding alarm information and image information when abnormal, and push the alarm information and image information out. Specifically, BMC can also include equipment status acquisition module, configuration module, alarm information generation module, alarm push module, communication function module and equipment control module.

[0101] Among them, the device status acquisition module is mainly used to collect the status data of the internal components of the BMC device and to collect the image data of the internal components of the BMC device using the camera installed at the key component position inside the BMC device (when using the camera to collect the image data of the internal components, the flash can be turned on to capture clear image data). Taking the BMC device as a server as an example, the temperature, voltage, current, power, wind speed and other status data of the server's CPU, memory, hard disk, power supply, fan and other components can be used.

[0102] The configuration module mainly provides configuration information for alarm information generation, alarm push configuration information, and communication function configuration information. The configuration information for alarm information generation mainly refers to the configuration of the alarm threshold and alarm level for BMC device status data. For example, the temperature alarm threshold and alarm level of the CPU can be set as normal when the temperature is less than 86°C, general alarm when the temperature is greater than or equal to 86°C and less than 88°C, and severe alarm when the temperature is greater than 88°C. The configuration information for alarm push refers to the device type, alarm level, and push method for the user to push the alarm. The alarm levels include normal, general alarm, and severe alarm; the push methods include email, SMS, MMS, and voice call. For example, users can configure SMS alarm push for general alarms of the CPU and severe alarms of the hard disk. The configuration information for the communication function mainly includes the selection of the network standard, the serial port configuration information of the communication module, the user's email address and mobile phone number information, etc.

[0103] The alarm information generation module mainly includes generating a serious alarm of BMC device power supply abnormality and image information of the BMC device power supply module when the BMC device power supply is abnormal; and real-time analysis of device status data and image data. When the device status data exceeds the alarm threshold configured by the user, the corresponding alarm information and image information are generated according to the alarm level configured by the user, and then the alarm information is recorded in the BMC log and pushed to the Web end. Users can access the BMC through a browser to view the corresponding alarm information and image information.

[0104] The alarm push module mainly analyzes alarm information in real time. When the alarm device and alarm level corresponding to the alarm information are consistent with the information configured by the user, the alarm is pushed out by calling the interface of the communication function module according to the alarm push method configured by the user. The information pushed by the alarm mainly includes the location information of the server, the alarm device, the alarm level, the alarm details, etc. Among them, the alarm push information in the form of email, SMS, and MMS will contain the alarm information link. The user can click on the alarm information link to quickly understand the detailed information of the server alarm; the alarm push information in the form of email and MMS will contain the internal image information of the server corresponding to the alarm.

[0105] The main functions of the communication function module include controlling the switch of the communication module, modifying the configuration of the communication module according to the communication function configuration configured by the user, and sending the alarm push information to the user when receiving the interface call of the alarm push module. The communication function module is responsible for network switching and switches to mobile communication when the server network is abnormal.

[0106] The main functions of the device control module include controlling the server device after receiving the user control command, for example: controlling the server power module to restart; and providing users with real-time video preview function inside the server.

[0107] That is, through the above modules, BMC can collect status data and images of internal components of BMC devices, trigger alarms according to user configurations, generate alarm information and image information, and then push the alarm information and image information to users. It can also control BMC devices according to control instructions sent by users and provide users with real-time preview of internal videos of BMC devices.

[0108] The present application also provides a BMC device monitoring device. Figure 5 , which shows a schematic diagram of the structure of a BMC device monitoring device provided in an embodiment of the present application, which may include:

[0109] A first acquisition module 51 is used to acquire a video captured by a camera installed inside the BMC device;

[0110] A calculation module 52 is used to calculate the average grayscale value of each frame image in the video, and calculate the average grayscale value difference between two adjacent frames of images using the average grayscale values ​​of two adjacent frames of images;

[0111] A second acquisition module 53 is used to acquire a current image inside the BMC device if the average gray value difference is greater than a first threshold;

[0112] An input module 54, configured to input the current image into a pre-trained BMC device unpacking detection model to obtain a first detection value;

[0113] The first determination module 55 is configured to determine that the chassis shell of the BMC device is opened if the first detection value is greater than the second threshold value, and generate an alarm message according to the video and the current image.

[0114] A BMC device monitoring device provided in an embodiment of the present application may further include:

[0115] A detection module, configured to detect a switch state of a mechanical switch corresponding to a chassis shell of the BMC device when the first detection value is greater than a second threshold value;

[0116] The second determining module is used to determine that the chassis shell of the BMC device is opened if the mechanical switch is in an open state.

[0117] A BMC device monitoring device provided in an embodiment of the present application may further include:

[0118] The output module is used to output the alarm information after generating the alarm information according to the video and the current image.

[0119] A BMC device monitoring device provided in an embodiment of the present application may further include:

[0120] A judgment module, used to judge whether the communication module can communicate normally before outputting the alarm information;

[0121] The utilization module is used to provide a mobile network by utilizing a built-in SIM card if the communication module fails to communicate normally.

[0122] A BMC device monitoring device provided in an embodiment of the present application may further include:

[0123] The smoke detection module is used to perform smoke detection inside the BMC device according to the video after acquiring the video shot by the shooting device installed inside the BMC device.

[0124] In a BMC equipment monitoring device provided in an embodiment of the present application, a smoke detection module may include:

[0125] a calculation unit, configured to obtain a current internal image of the BMC device if the difference value is greater than a third threshold;

[0126] An obtaining unit, used for inputting the current internal image into a pre-trained smoke detection model to obtain a second detection value;

[0127] The determination unit is configured to determine that smoke exists inside the BMC device if the second detection value is greater than a fourth threshold value, and to generate smoke alarm information according to the video and the current internal image.

[0128] In the BMC equipment monitoring device provided in the embodiment of the present application, the smoke detection module may further include:

[0129] an acquisition unit, configured to acquire, when the second detection value is greater than a fourth threshold, a smoke value collected by a gas sensor installed at an air outlet of a chassis of the BMC device;

[0130] The judging unit is used to judge whether the smoke value is greater than a fifth threshold value, and if so, determine that smoke exists inside the BMC device.

[0131] The present application also provides a BMC device monitoring device. Figure 6 , which shows a schematic diagram of the structure of a BMC device monitoring device provided in an embodiment of the present application, which may include:

[0132] A memory 61, used for storing computer programs;

[0133] The processor 62, when used to execute the computer program stored in the memory 61, can implement the following steps:

[0134] A video captured by a shooting device installed inside a BMC device is obtained; an average grayscale value of each frame image in the video is calculated, and an average grayscale value difference between two adjacent frames of image is calculated using the average grayscale value of the two adjacent frames of image; if the average grayscale value difference is greater than a first threshold, a current image inside the BMC device is obtained; the current image is input into a pre-trained BMC device unpacking detection model to obtain a first detection value; if the first detection value is greater than a second threshold, it is determined that a chassis shell of the BMC device is opened, and an alarm message is generated according to the video and the current image.

[0135] The present application also provides a readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the following steps can be implemented:

[0136] A video captured by a shooting device installed inside a BMC device is obtained; an average grayscale value of each frame image in the video is calculated, and an average grayscale value difference between two adjacent frames of image is calculated using the average grayscale value of the two adjacent frames of image; if the average grayscale value difference is greater than a first threshold, a current image inside the BMC device is obtained; the current image is input into a pre-trained BMC device unpacking detection model to obtain a first detection value; if the first detection value is greater than a second threshold, it is determined that a chassis shell of the BMC device is opened, and an alarm message is generated according to the video and the current image.

[0137] The readable storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0138] The description of the relevant parts of a BMC device monitoring apparatus, device and readable storage medium provided in the present application can refer to the detailed description of the corresponding parts of a BMC device monitoring method provided in an embodiment of the present application, which will not be repeated here.

[0139] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the term "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or equipment that includes a series of elements are inherent to the elements. In the absence of more restrictions, the elements limited by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or equipment that includes the elements. In addition, the above-mentioned technical solution provided in the embodiment of the present application is consistent with the corresponding technical solution in the prior art in principle, and the part is not described in detail, so as not to repeat too much.

[0140] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A BMC device monitoring method, characterized in that: include: Obtain the video captured by the camera installed inside the BMC device; Calculate the average grayscale value of each frame image in the video, and calculate the average grayscale value difference between two adjacent frame images using the average grayscale values ​​of two adjacent frame images; If the average gray value difference is greater than a first threshold, acquiring a current image inside the BMC device; Inputting the current image into a pre-trained BMC device unpacking detection model to obtain a first detection value; If the first detection value is greater than a second threshold, it is determined that the chassis shell of the BMC device is opened, and an alarm message is generated according to the video and the current image; When the first detection value is greater than a second threshold, the method further includes: detecting a switch state of a mechanical switch corresponding to a chassis shell of the BMC device; If the mechanical switch is in an open state, it is determined that the chassis shell of the BMC device is opened.

2. The BMC device monitoring method according to claim 1, characterized in that: After generating the warning information according to the video and the current image, the method further includes: Output the warning information.

3. The BMC device monitoring method according to claim 2, characterized in that: Before outputting the alarm information, the method further includes: Determine whether the communication module can communicate normally; If not, the built-in SIM card is used to provide mobile network.

4. The BMC device monitoring method according to any one of claims 1 to 3, characterized in that: After obtaining the video captured by the camera installed inside the BMC device, the following steps are also included: Perform smoke detection inside the BMC device based on the video.

5. The BMC device monitoring method according to claim 4, characterized in that: Performing smoke detection inside the BMC device according to the video includes: Calculating the difference between two adjacent frames of the video using an inter-frame difference method; If the difference value is greater than a third threshold, acquiring a current internal image of the BMC device; Inputting the current internal image into a pre-trained smoke detection model to obtain a second detection value; If the second detection value is greater than a fourth threshold, it is determined that smoke exists inside the BMC device, and smoke alarm information is generated according to the video and the current internal image.

6. The BMC device monitoring method according to claim 5, characterized in that: When the second detection value is greater than a fourth threshold, the method further includes: Obtaining a smoke value collected by a gas sensor installed at an air outlet of a chassis of the BMC device; It is determined whether the smoke value is greater than a fifth threshold value, and if so, it is determined that smoke exists inside the BMC device.

7. A BMC equipment monitoring device, characterized in that: include: A first acquisition module is used to acquire a video captured by a camera installed inside the BMC device; A calculation module, used to calculate the average grayscale value of each frame image in the video, and calculate the average grayscale value difference between two adjacent frames of images using the average grayscale values ​​of two adjacent frames of images; A second acquisition module, configured to acquire a current image inside the BMC device if the average gray value difference is greater than a first threshold; An input module, used for inputting the current image into a pre-trained BMC device unpacking detection model to obtain a first detection value; a first determination module, configured to determine that a chassis shell of the BMC device is opened if the first detection value is greater than a second threshold value, and to generate an alarm message according to the video and the current image; When the first detection value is greater than a second threshold, the device is further used to detect a switch state of a mechanical switch corresponding to a chassis shell of the BMC device; If the mechanical switch is in an open state, it is determined that the chassis shell of the BMC device is opened.

8. A BMC equipment monitoring device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the BMC device monitoring method according to any one of claims 1 to 6 when executing the computer program.

9. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the BMC device monitoring method according to any one of claims 1 to 6 are implemented.

Images