IDC data center automatic checking method and system based on image processing algorithm

Abstract

The invention provides an automatic checking method and system for an IDC (Internet Data Center) based on an image processing algorithm. The method comprises the following steps: step 1, deploying a plurality of inspection robots in an IDC data center, and enabling the inspection robots to autonomously move in a channel of the data center; the inspection robot is deployed to autonomously collect images, the tedious process of traditional manual checking is avoided, the checking efficiency is greatly improved, a large amount of time and labor cost are saved, meanwhile, a path planning algorithm, an automatic focusing algorithm and the like are utilized, it is ensured that the robot efficiently moves and collects clear images, and the overall working efficiency is further improved; feature extraction and asset information comparison are carried out based on an image processing algorithm, errors caused by human factors are reduced, the accuracy of asset identification is improved, meanwhile, the illegal moving-in and moving-out condition of equipment is detected by adopting an image difference algorithm, abnormity can be found timely and accurately, disorder of asset management is avoided, and intelligent management is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of data center management, and in particular to an IDC data center automatic inventory method and system based on an image processing algorithm. Background Art

[0002] With the rapid development of information technology, data centers play a vital role in today's society. Data centers are not only the core places for enterprises to store and process large amounts of data, but also the key infrastructure that supports the operation of various key business systems. In recent years, the scale of data centers has shown a trend of continuous expansion. On the one hand, with the accelerated advancement of enterprise digital transformation, more and more business data needs to be stored and processed, which has led to a sharp increase in the number of devices in data centers. On the other hand, in order to meet different business needs, the types of equipment used in data centers have become increasingly complex, covering a variety of types such as servers, storage devices, and network devices.

[0003] However, the traditional data center asset inventory method mainly relies on manual operation. In this method, staff need to check each cabinet one by one and record the model, serial number, location and other information of the equipment. This manual inventory method has many disadvantages.

[0004] First, the efficiency is extremely low. Due to the large number of devices in the data center, manual inventory takes a lot of time and manpower. When doing inventory, the staff needs to find and record the device information one by one. This process is not only cumbersome, but also prone to omissions and errors. Secondly, accuracy is difficult to guarantee. During the manual inventory process, due to human factors such as fatigue and negligence, it is easy to cause recording errors. For some complex equipment information, manual identification is also difficult. In addition, if the asset inventory is inaccurate, it may lead to chaotic equipment management and affect the stability of the business system. At the same time, inefficient inventory methods will also waste a lot of time and resources and reduce the operational efficiency of the data center; Therefore, an IDC data center automated inventory method and system based on image processing algorithm is proposed. Summary of the invention

[0005] In view of this, the embodiments of the present invention provide an IDC data center automated inventory method and system based on an image processing algorithm to solve or alleviate the technical problems existing in the prior art and at least provide a beneficial option.

[0006] In order to solve the above technical problems, a technical solution adopted by this application is: an IDC data center automatic inventory method based on image processing algorithm, comprising the following steps: Step 1: Deploy multiple inspection robots in the IDC data center; Step 2: The inspection robot collects device images of the devices in the IDC data center cabinet through the onboard camera; Step 3: preprocess the collected device images; Step 4: Extract features of the device image based on the image processing algorithm to extract key information of the device image; Step 5: Compare the key information of the extracted device image with the pre-established device asset database to automatically identify the asset information of the device; Step 6: Analyze the continuously collected device images to detect whether the device has been illegally moved in or out, and automatically generate detection results. If the device's position is found to have changed without authorization, an alarm will be issued, and the time and device information of the event will be recorded; Step 7: Automatically generate an asset inventory report for the data center based on the identified equipment asset information and illegal entry and removal detection results; Step 8. Visualize the data of the asset inventory report and present it in the form of intuitive charts.

[0007] As a further preferred embodiment of the present technical solution, in step one, the inspection robot moves autonomously in a passage of a data center, and the autonomous movement of the inspection robot is performed with a path planning algorithm for path planning.

[0008] As a further preferred embodiment of the present technical solution, in step 2, the camera continuously adjusts the focal length of the camera based on an autofocus algorithm and according to an image clarity evaluation function until the image reaches an optimal clarity.

[0009] As a further preferred embodiment of the present technical solution, in step three, the image data preprocessing includes image enhancement processing, image denoising processing and image binarization processing; The image enhancement process uses a histogram equalization algorithm, and the calculation formula is as follows: Calculate the grayscale histogram of the original image ,in Indicates grayscale, ranging from 0 to 255; Compute the cumulative distribution function: ; Perform normalization to obtain the enhanced grayscale value: ; in, and are the number of rows and columns of the image, respectively. is the minimum value of the cumulative distribution function; The image denoising process uses the median filtering algorithm. For each pixel in the image, the median of the pixel values ​​in its neighborhood is taken as the new pixel value of the point; if the neighborhood size is set to , then for the pixel , the new pixel value calculation formula is: Take centered Pixel values ​​in the neighborhood ,in, ; Sort these pixel values ​​from small to large; Take the sorted middle value as the pixel point The new pixel value of The image binarization process uses a threshold segmentation algorithm, and the calculation formula is: Choose an appropriate threshold ; For each pixel in the image ,like , the pixel value of the point is set to 255; otherwise, it is set to 0.

[0010] As a further preferred embodiment of the present technical solution, in step 4, the method for extracting key information of the device image includes the following steps: Step 1: grayscale and smooth the device image; Step 2: Extract edge features of the device image based on the Canny edge detection algorithm; Step 3: Detect corner features in the device image based on the Harris corner detection algorithm; Step 4: Use feature descriptors to describe the detected edge points and corner points to generate unique feature vectors; Step 5: According to the characteristics and requirements of the equipment, select the appropriate feature vector combination as the key information.

[0011] As a further preferred embodiment of the present technical solution, in step 5, the asset information of the device includes the device name, model, serial number and location; The asset information of the identification device uses the Euclidean distance algorithm or the cosine similarity algorithm to calculate the similarity between the extracted feature vector and the feature vector already in the database. If the similarity exceeds a preset threshold, the match is successful. The Euclidean distance calculation formula is: ; in, and are two eigenvectors, is the dimension of the feature vector; The cosine similarity calculation formula is: ; in, and are two eigenvectors, · represents the vector dot product, and Represents vectors and Model.

[0012] As a further preferred embodiment of the present technical solution, in step six, the detection device is used to calculate the difference between two adjacent frames of images by using an image difference algorithm. If the difference exceeds a preset threshold, it is considered that the position of the device has changed and there is illegal movement in and out. If, the two frames of images are set to and , Then, the difference image .

[0013] As a further preferred embodiment of the present technical solution, in step seven, the asset inventory report includes basic information, equipment information, equipment status information, illegal entry and exit information, comparative analysis information, and summary and suggestion information.

[0014] As a further preferred embodiment of the present technical solution, in step eight, the data visualization processing is customized according to user needs, including different chart types, color schemes and layout settings.

[0015] To solve the above technical problems, another technical solution adopted by this application is: an IDC data center automated inventory system based on image processing algorithm, including: an inspection robot module, an image acquisition module, an image preprocessing module, a feature extraction module, an asset information comparison module, an illegal entry and exit detection module, a report generation module and a data visualization module; The inspection robot module is deployed inside the IDC data center, is used to move autonomously in the aisles of the data center, and is equipped with a camera to collect images of the equipment in the cabinet; The image acquisition module is connected to the inspection robot and is used to control the camera to acquire device images and adjust the camera focal length based on the auto-focus algorithm; The image preprocessing module is used to perform enhancement processing, denoising processing and binarization processing on the collected device image; The feature extraction module is used to extract features from the device image and extract key information of the device image; The asset information comparison module is used to compare the extracted key information with a pre-established equipment asset database to automatically identify the asset information of the equipment; The illegal entry and exit detection module is used to perform differential analysis on the continuously collected device images, detect illegal movement of the device, and issue an alarm and record relevant information when an unauthorized position change is found; The report generation module is used to automatically generate an asset inventory report of the data center based on the identified equipment asset information and the illegal entry and removal detection results; The data visualization module is used to perform customized data visualization processing on the asset inventory report and present it to the user in the form of intuitive charts, supporting different chart types, color schemes and layout settings.

[0016] The embodiment of the present invention has the following advantages due to the adoption of the above technical solution: 1. The present invention deploys inspection robots to autonomously collect images, avoiding the tedious process of traditional manual inventory counting, greatly improving the efficiency of inventory counting, saving a lot of time and labor costs. At the same time, the path planning algorithm and autofocus algorithm are used to ensure that the robot moves efficiently and collects clear images, further improving the overall work efficiency; 2. The present invention reduces errors caused by human factors and improves the accuracy of asset identification by performing feature extraction and asset information comparison based on image processing algorithms. At the same time, it uses image difference algorithms to detect illegal movement of equipment in and out, which can detect anomalies in a timely and accurate manner and avoid confusion in asset management.

[0017] 3. The present invention automatically generates asset inventory reports and performs data visualization processing to provide managers with intuitive chart displays, which facilitates quick understanding of the overall status and potential risks of the data center and realizes intelligent management. The asset inventory report is rich in content and fully reflects the asset status of the data center. The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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 technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 It is a flow chart of an IDC data center automated inventory method based on an image processing algorithm of the present invention; Figure 2 A schematic diagram of the process of extracting key information of device images according to the present invention; Figure 3 This is a schematic diagram of the functional modules of the IDC data center automated inventory system based on the image processing algorithm of the present invention. DETAILED DESCRIPTION

[0020] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0021] It should be clear that the following embodiments of the present disclosure are described by specific specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other in the absence of conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.

[0022] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0023] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present disclosure. The drawings only show components related to the present disclosure rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0024] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects described may be practiced without these specific details.

[0025] Figure 11 is a flow chart of an IDC data center automated inventory method based on an image processing algorithm according to an embodiment of the present invention. It should be noted that if there are substantially the same results, the method of the present application is not used in the same manner. Figure 1 The process sequence shown is limited. Figure 1-Figure 2 As shown: The IDC data center automatic inventory method based on image processing algorithm includes the following steps: Step 1: Deploy multiple inspection robots in the IDC data center. Specifically: First, select inspection robots with autonomous navigation and obstacle avoidance functions, and equip them with hardware devices such as high-definition cameras and infrared sensors. Then, use path planning algorithms (such as A* algorithm, Dijkstra algorithm or its variants) to plan the movement path of the inspection robots in the IDC data center channels to ensure full coverage and high efficiency. Ensure a stable network connection between the inspection robots and the data center management system (DCMS) to transmit data in real time. Step 2: The inspection robot uses the camera it carries to collect images of the equipment in the IDC data center cabinet. Specifically: The camera on the inspection robot starts the autofocus algorithm and continuously adjusts the focal length through the image clarity evaluation function (such as the Laplace operator) until the image reaches the optimal clarity. During the inspection process, the camera collects images of the equipment in the cabinet at a fixed time or according to a preset path to ensure that the image is clear and comprehensive. Step 3: Preprocess the collected device images; device image preprocessing includes image enhancement, image denoising and image binarization. Image enhancement uses a histogram equalization algorithm to enhance the image, improve the image contrast and brightness, and make the details clearer; image denoising uses a median filter algorithm to remove noise in the image and protect the edge information from being blurred; image binarization converts the image into a binary image through a threshold segmentation algorithm to facilitate subsequent edge detection and feature extraction; Step 4: Extract features of the device image based on the image processing algorithm to extract key information of the device image; wherein the key information includes the shape, size, color, texture, identifier, etc. of the device; Step 5: Compare the key information of the extracted device image with the pre-established device asset database to automatically identify the device asset information; specifically: pre-establish a device asset database containing information such as device name, model, serial number, location and corresponding feature vector; use the Euclidean distance algorithm or cosine similarity algorithm to calculate the similarity between the extracted feature vector and the feature vector already in the database. If the similarity exceeds the preset threshold, it is considered a successful match and the device asset information is automatically identified; Step 6: Analyze the continuously collected device images to detect whether the device has been illegally moved in or out, and automatically generate detection results. If the device position is found to have changed without authorization, an alarm is issued, and the time of the event and the device information are recorded. Specifically: calculate the difference between two adjacent frames of images. If the difference exceeds a preset threshold, it is considered that the device position has changed, and there may be illegal movement in or out. If illegal movement in or out is found, an alarm is immediately issued, and the time of the event, device information, and location change details are recorded. Step 7: Automatically generate an asset inventory report for the data center based on the identified equipment asset information and the illegal entry and removal detection results; specifically: count the total number of equipment, the number of each type of equipment, the distribution of equipment and other basic information; analyze the frequency, occurrence time, and equipment types involved in illegal entry and removal events, and assess potential security risks; compare historical data to analyze the changing trends and patterns of equipment assets; and automatically generate an asset inventory report for the data center based on the analysis results; Step 8. Visualize the data of the asset inventory report and display it in the form of intuitive charts. Specifically: customize the data visualization according to user needs, including selecting different chart types (such as bar charts, pie charts, heat maps, etc.), color schemes, and layout settings. Display the asset inventory results and illegal entries and exits in the form of intuitive charts, so that managers can quickly understand the overall status and potential risks of the data center.

[0026] In one embodiment, specifically, in step 1, the inspection robot moves autonomously in a passage of the data center, and the autonomous movement of the inspection robot is performed on a path planning algorithm; Specifically: The inspection robot first starts and performs self-inspection to ensure that all sensors (such as cameras, lidar, infrared sensors, etc.), motors, batteries and other key components are working properly; through the integrated sensor system (such as lidar SLAM, cameras, etc.), the inspection robot perceives the environment of the data center channel in real time, including obstacle locations, channel width, lighting conditions, etc.; If there is no ready-made map in the data center, the inspection robot can use SLAM (Simultaneous Localization and Mapping) technology to build a two-dimensional or three-dimensional map of the data center while moving. If a map already exists, it can be directly loaded and used; based on the constructed map or the loaded map, the inspection robot uses a path planning algorithm (such as A algorithm, Dijkstra algorithm, RRT algorithm, etc.) to calculate the optimal or feasible path from the current position to the target position. The path planning algorithm will consider a variety of factors, such as path length, obstacle location, channel width limit, robot steering ability, etc.; during the movement process, if the inspection robot encounters unforeseen obstacles or environmental changes (such as temporarily placed equipment, personnel movement, etc.), it will dynamically adjust the path planning based on the real-time perception information to ensure safe and efficient arrival at the destination; According to the path planning results, the inspection robot generates specific control instructions, including forward, backward, turning, speed adjustment, etc. The inspection robot executes the control instructions and moves autonomously in the channels of the data center. During the movement, the robot will continuously monitor the surrounding environment through the sensor system to ensure safety. During the movement, the inspection robot will feed back its position, status, path execution and other information to the control center or management system in real time; if the inspection robot encounters an abnormal situation during the movement (such as insufficient power, sensor failure, path obstruction, etc.), it will handle it accordingly according to the preset emergency processing mechanism and report to the control center; According to the optimal or feasible path calculated by the path planning algorithm, the inspection robot eventually reaches the target location; at the target location, the inspection robot performs predetermined inspection tasks, such as equipment status inspection, temperature and humidity monitoring, abnormality alarm, etc.

[0027] In one embodiment, specifically, in step two, the camera continuously adjusts the focal length of the camera based on an autofocus algorithm and according to an image clarity evaluation function until the image reaches optimal clarity; the camera automatically adjusts the focal length based on the autofocus algorithm to ensure that the images collected during the inspection process have optimal clarity, thereby improving the accuracy and efficiency of the inspection.

[0028] In one embodiment, specifically, in step three, the image data preprocessing includes image enhancement processing, image denoising processing and image binarization processing; Image enhancement processing uses the histogram equalization algorithm, and the calculation formula is as follows: Calculate the grayscale histogram of the original image ,in Indicates grayscale, ranging from 0 to 255; Compute the cumulative distribution function: ; Perform normalization to obtain the enhanced grayscale value: ; in, and are the number of rows and columns of the image, respectively. is the minimum value of the cumulative distribution function; Image denoising uses the median filter algorithm. For each pixel in the image, the median of the pixel values ​​in its neighborhood is taken as the new pixel value of the point. If the neighborhood size is set to , then for the pixel , the new pixel value calculation formula is: Take centered Pixel values ​​in the neighborhood ,in, ; Sort these pixel values ​​from small to large; Take the sorted middle value as the pixel point The new pixel value of The image binarization process uses the threshold segmentation algorithm, and the calculation formula is: Choose an appropriate threshold ; For each pixel in the image ,like , the pixel value of the point is set to 255; otherwise, it is set to 0.

[0029] In one embodiment, specifically, in step 4, the method for extracting key information of the device image includes the following steps: Step 1: grayscale and smooth the device image; Among them, grayscale processing: converting the device image from color (usually RGB) to grayscale image. This step reduces the complexity of image processing because grayscale image only contains brightness information but not color information. Grayscale is usually achieved by weighted average method, maximum method or minimum method; Smoothing: Smoothing the grayscale image to remove noise and unnecessary details in preparation for subsequent edge detection and corner detection. Smoothing can be achieved through various filters, such as Gaussian filter, median filter, etc. Step 2: Extract edge features of the device image based on the Canny edge detection algorithm; Among them, Canny edge detection is a widely used edge detection algorithm, which combines multiple steps such as Gaussian filtering, gradient calculation, non-maximum suppression and dual threshold detection. The Canny algorithm can effectively detect the edges in the image while suppressing the interference of noise. The edge part of the image processed by the Canny algorithm is clearly marked. These edge features are important structural information in the device image and are of great significance for subsequent image analysis and recognition. Step 3: Detect corner features in the device image based on the Harris corner detection algorithm; Harris corner detection is a corner detection algorithm based on the second-order derivative matrix of image grayscale (i.e., structure tensor). It determines whether a point is a corner by calculating the Harris response value of each pixel in the image. Corner points are important local features in the image, usually located at the intersection of edges, and have a certain invariance to image rotation, scaling and other transformations. Corner points detected by the Harris algorithm represent important geometric structure points in the device image. These corner point features can be used for subsequent image matching, positioning and other tasks. Step 4: Use feature descriptors to describe the detected edge points and corner points to generate unique feature vectors; Among them, feature descriptors are vectors used to describe image feature points. Common feature descriptors include SIFT (Scale Invariant Feature Transform), SURF (Speeded Robust Features), ORB (Oriented FAST and RotatedBRIEF), etc. These descriptors can capture the local texture information around the feature points and generate unique feature vectors. For edge points detected by the Canny algorithm and corner points detected by the Harris algorithm, feature descriptors can be used to describe them. Each feature point is assigned a unique feature vector for subsequent matching and recognition. Step 5: Select appropriate feature vector combinations as key information based on the characteristics and requirements of the device; Specifically, according to the characteristics and requirements of the device, appropriate feature vectors can be selected from the detected edge features and corner features for combination. This combination should be able to comprehensively and accurately reflect the appearance and structural characteristics of the device. By selecting appropriate feature vector combinations, unique and representative key information is generated, which will be used in subsequent image recognition, device classification, anomaly detection and other tasks.

[0030] In one embodiment, specifically, in step five, the asset information of the device includes the device name, model, serial number, and location; The device name is a unique or universal identifier of the device, which is used to quickly identify the device in documents, databases or management systems. It usually reflects the type or function of the device, such as "server", "switch", "air conditioning unit", etc. The model is a specific specification of the device, used to distinguish devices of the same type with different configurations or performance. The model information usually includes the manufacturer's name, product series, and a specific model code, such as "Dell PowerEdge R740xd" or "Cisco Catalyst 9300"; The serial number is a unique identifier assigned by the manufacturer to each device. It is used to track the entire life cycle information of the device, including production, sales, maintenance, and scrapping. The serial number is usually a combination of letters and numbers, which is highly unique and traceable. The location refers to the specific installation location of the equipment in the data center or other facilities. This can be a room number, rack number, U-position number, or a more detailed physical location description. The location information is crucial for quickly locating equipment, conducting on-site inspections, and maintenance. The asset information of the identification device uses the Euclidean distance algorithm or the cosine similarity algorithm to calculate the similarity between the extracted feature vector and the existing feature vector in the database. If the similarity exceeds the preset threshold, the match is successful; The Euclidean distance calculation formula is: ; in, and are two eigenvectors, is the dimension of the feature vector; The formula for calculating cosine similarity is: ; in, and are two eigenvectors, · represents the vector dot product, and Represents vectors and Model.

[0031] In one embodiment, specifically, in step six, it is detected whether the device has been illegally moved in or out by using an image difference algorithm to calculate the difference between two adjacent frames of images. If the difference exceeds a preset threshold, it is considered that the position of the device has changed and there has been illegal movement in or out. If, the two frames of images are set to and , Then, the difference image .

[0032] In one embodiment, specifically, in step seven, the asset inventory report includes basic information, equipment information, equipment status information, illegal entry and exit information, comparative analysis information, and summary and suggestion information; Among them, basic information includes report date, data center name and inventory scope; Report date: the specific time when the report was generated; Data center name: the name of the IDC data center being inventoried; Inventory scope: clearly define the specific scope of the area, cabinets, etc. covered by the inventory; Equipment information includes equipment quantity, equipment type distribution, equipment brand and model, equipment serial number and equipment location distribution; Number of devices: The total number of various devices in the data center, which can be listed separately by device type; Device type distribution: the number and proportion of different types of devices such as servers, switches, and storage devices; Equipment brand and model: List the brand and specific model information of various equipment; Device serial number: facilitates accurate identification and tracking of individual devices; Equipment location distribution: indicate the specific location of each device in the data center, such as cabinet number, machine position number, etc. Equipment status information includes operating status, maintenance records, and equipment life assessment; Operation status: divided into normal operation, fault, standby and other states, and the number of devices in different states is counted; Maintenance records: If any equipment has been maintained during the inventory, record the time, content and maintenance personnel of the maintenance; Equipment life assessment: Evaluate the remaining life of the equipment based on factors such as equipment usage time and operating status; Illegal entry and exit information includes detection results, information about the equipment involved, and changes in time and location; Detection results: Determine whether any equipment has been illegally moved in or out; Involved equipment information: If there is illegal entry or removal, list the specific information of the equipment involved, including equipment type, brand, model, serial number, etc.; Time and location changes: record the time and location changes of illegal device movement; Comparative analysis information includes comparison with the previous inventory results and analysis of the reasons for changes; Compare with the last inventory result: compare the changes in the number, location, status, etc. of equipment between this and the last inventory; Analysis of causes of changes: Analyze the causes of changes, such as equipment addition, replacement, and repair; Summary and recommendations information includes summary inventory results and recommended measures; Summarize the inventory results: Summarize the entire asset inventory work, emphasizing key findings and problems; Recommended measures: Make targeted suggestions based on the inventory results, such as strengthening equipment management, optimizing layout, and improving safety.

[0033] In one embodiment, specifically, in step eight, data visualization is performed to customize the display according to user needs, including different chart types, color schemes, and layout settings; Among them, the chart type is selected according to the nature of the data and the user's analysis needs. Common chart types include line charts, bar charts, pie charts, scatter charts, heat maps, radar charts, etc. Each chart type has its unique advantages and applicable scenarios. For example, line charts are suitable for showing trend changes, and bar charts are suitable for comparing different categories of data; Color scheme plays a vital role in data visualization. It not only enhances the aesthetics of the chart, but also helps users identify and understand data more quickly. According to user preferences, data characteristics, and analysis goals, a suitable color scheme can be customized. For example, contrasting colors can be used to highlight important data points, or gradient colors can be used to indicate continuous changes in data. Layout settings can improve the readability and usability of charts. You can optimize the layout of charts based on the size and resolution of the display device and the user's browsing habits. For example, you can adjust the size, position, margins and other properties of the chart to ensure that the chart appears both beautiful and practical on the page.

[0034] In addition, data visualization is not just a static chart display, but also includes interaction with users. By adding interactive elements such as filters, sliders, and drop-down menus, users can dynamically adjust the content and presentation of charts according to their needs. This interactive design can enhance users' sense of participation and desire to explore, and improve the efficiency and quality of data analysis.

[0035] Figure 3 Schematic diagram of the functional modules of the IDC data center automatic inventory system based on the image processing algorithm according to the embodiment of the present application. Figure 3 As shown, the IDC data center automated inventory system based on image processing algorithm includes: inspection robot module, image acquisition module, image preprocessing module, feature extraction module, asset information comparison module, illegal entry and exit detection module, report generation module and data visualization module; The inspection robot module is deployed inside the IDC data center. It is used to move autonomously in the aisles of the data center and is equipped with a camera to collect images of the equipment in the cabinet. The inspection robot uses the built-in SLAM (simultaneous localization and mapping) algorithm to achieve autonomous navigation and obstacle avoidance functions to ensure stable operation in complex environments. The image acquisition module is connected to the inspection robot and is used to control the camera to acquire device images and adjust the camera focal length based on the auto-focus algorithm. By using the auto-focus algorithm, the camera focal length is dynamically adjusted according to the quality of the acquired image, thereby ensuring that the acquired image is clear and discernible; The image preprocessing module is used to perform enhancement, denoising and binarization on the collected device images; the image clarity and brightness are improved through enhancement; the noise and interference in the image are removed through denoising to ensure the image quality; the image information is simplified through binarization to facilitate subsequent feature extraction and processing; The feature extraction module is used to extract features from the device image, extract key information from the device image, and output the extracted key information to the asset information comparison module for comparison; The asset information comparison module is used to compare the extracted key information with the pre-established equipment asset database, automatically identify the asset information of the equipment, and output the comparison results to the report generation module as part of the asset inventory report; The illegal entry and exit detection module is used to perform differential analysis on continuously collected device images to detect illegal movement of the device, and to issue an alarm and record relevant information when unauthorized location changes are found, where the relevant information includes movement time, movement trajectory, etc.; A report generation module is used to automatically generate an asset inventory report for the data center based on the identified equipment asset information and illegal entry and removal detection results; The data visualization module is used to perform customized data visualization processing on the asset inventory report and present it to users in the form of intuitive charts, supporting different chart types, color schemes and layout settings.

[0036] This embodiment describes in detail the various modules of the IDC data center automated inventory system based on image processing algorithms and their function implementation methods. Through the collaborative work of inspection robots, image acquisition, preprocessing, feature extraction, asset information comparison, illegal entry and exit detection, report generation and data visualization modules, the automated inventory and security management of equipment in the IDC data center are realized. The system has the characteristics of high efficiency, accuracy and flexibility, and can be widely used in the management and operation and maintenance of various data centers.

[0037] For other details about the technical solutions for implementing each module in the system of the above embodiment, please refer to the description of the IDC data center automated inventory method and system based on image processing algorithm in the above embodiment, which will not be repeated here.

[0038] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0039] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.

[0040] In the present disclosure, 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. The block diagrams of the devices, devices, equipment, and systems involved in the present disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0041] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0042] It should also be noted that in the system and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0043] Various changes, substitutions, and modifications of the techniques described herein may be made without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of the present disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of events, means, methods, and actions described above. Currently existing or later to be developed processes, machines, manufactures, compositions of events, means, methods, or actions that perform substantially the same functions or achieve substantially the same results as the corresponding aspects described herein may be utilized. Thus, the appended claims include such processes, machines, manufactures, compositions of events, means, methods, or actions within their scope.

[0044] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0045] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. An IDC data center automated inventory method based on image processing algorithm, characterized in that: The following steps are involved: Step 1: Obtain device image data and deploy multiple inspection robots in the IDC data center; Step 2: The inspection robot collects device images of the devices in the IDC data center cabinet through the onboard camera; Step 3: preprocess the collected device images; Step 4: Extract features of the device image based on the image processing algorithm to extract key information of the device image; Step 5: Compare the key information of the extracted device image with the pre-established device asset database to automatically identify the asset information of the device; Step 6: Analyze the continuously collected device images to detect whether the device has been illegally moved in or out, and automatically generate detection results. If the device's position is found to have changed without authorization, an alarm will be issued, and the time and device information of the event will be recorded; Step 7: Automatically generate an asset inventory report for the data center based on the identified equipment asset information and illegal entry and removal detection results; Step 8. Visualize the data of the asset inventory report and present it in the form of intuitive charts.

2. The IDC data center automated inventory method based on image processing algorithm according to claim 1 is characterized by: In step one, the inspection robot moves autonomously in a passage of a data center, and the autonomous movement of the inspection robot is performed using a path planning algorithm for path planning.

3. The IDC data center automated inventory method based on image processing algorithm according to claim 1, characterized in that: In step 2, the camera continuously adjusts the focal length of the camera based on an auto-focus algorithm and according to an image clarity evaluation function.

4. The IDC data center automated inventory method based on image processing algorithm according to claim 1, characterized in that: In step three, the image data preprocessing includes image enhancement processing, image denoising processing and image binarization processing.

5. The IDC data center automated inventory method based on image processing algorithm according to claim 1, characterized in that: In step 4, the method for extracting key information of device images includes the following steps: Step 1: grayscale and smooth the device image; Step 2: Extract edge features of the device image based on the Canny edge detection algorithm; Step 3: Detect corner features in the device image based on the Harris corner detection algorithm; Step 4: Use feature descriptors to describe the detected edge points and corner points to generate unique feature vectors; Step 5: According to the characteristics and requirements of the equipment, select the appropriate feature vector combination as the key information.

6. The IDC data center automated inventory method based on image processing algorithm according to claim 1, characterized in that: In step 5, the asset information of the device includes the device name, model, serial number and location; The asset information of the identification device uses the Euclidean distance algorithm or the cosine similarity algorithm to calculate the similarity between the extracted feature vector and the feature vector already in the database. If the similarity exceeds a preset threshold, the match is successful.

7. The IDC data center automated inventory method based on image processing algorithm according to claim 1, characterized in that: In step six, the detection device is used to detect whether there is illegal movement in and out by using an image difference algorithm to calculate the difference between two adjacent frames of images. If the difference exceeds a preset threshold, it is considered that the device position has changed and there is illegal movement in and out.

8. The IDC data center automated inventory method based on image processing algorithm according to claim 1, characterized in that: In step seven, the asset inventory report includes basic information, equipment information, equipment status information, illegal entry and exit information, comparative analysis information, and summary and suggestion information.

9. The IDC data center automated inventory method based on image processing algorithm according to claim 1, characterized in that: In step eight, the data visualization processing is customized according to user needs, including different chart types, color schemes and layout settings.

10. The IDC data center automated inventory system based on image processing algorithm is characterized by: Also includes: Inspection robot module, image acquisition module, image preprocessing module, feature extraction module, asset information comparison module, illegal entry and exit detection module, report generation module and data visualization module; The inspection robot module is deployed inside the IDC data center, is used to move autonomously in the aisles of the data center, and is equipped with a camera to collect images of the equipment in the cabinet; The image acquisition module is connected to the inspection robot and is used to control the camera to acquire device images and adjust the camera focal length based on the auto-focus algorithm; The image preprocessing module is used to perform enhancement processing, denoising processing and binarization processing on the collected device image; The feature extraction module is used to extract features from the device image and extract key information of the device image; The asset information comparison module is used to compare the extracted key information with a pre-established equipment asset database to automatically identify the asset information of the equipment; The illegal entry and exit detection module is used to perform differential analysis on the continuously collected device images, detect illegal movement of the device, and issue an alarm and record relevant information when an unauthorized position change is found; The report generation module is used to automatically generate an asset inventory report of the data center based on the identified equipment asset information and the illegal entry and removal detection results; The data visualization module is used to perform customized data visualization processing on the asset inventory report and present it to the user in the form of intuitive charts, supporting different chart types, color schemes and layout settings.

Images