An archive inventory system, method, device and chip system

Abstract

This invention discloses a file inventory system, method, apparatus, and chip system. The method includes: acquiring a QR code image of the head cabinet of a file cabinet; determining the distance between the center points of two adjacent head cabinet QR code images; determining the open / closed state of the head cabinet based on the distance between the center points of the two adjacent head cabinet QR code images, thereby determining the open / closed state of the entire file cabinet row; and, based on the determination result, controlling a vision system to move to the position of the head cabinet of the file cabinet that is in the open state, and starting the corresponding inventory operation for the entire file cabinet row. This method achieves intelligent determination of the open / closed state of the file cabinet through QR code recognition and distance analysis, improving inventory efficiency and data reliability.

Description

Technical Field

[0001] This application relates to the field of records management, and in particular to a records inventory system, method, apparatus and chip system. Background Technology

[0002] With the continuous advancement of informatization and digital management, the intelligent and automated management of archives has become a research focus. Existing automated archive inventory technologies mainly fall into two categories: one based on RFID and the other on visual image recognition. The RFID method uses RFID tags attached to archive boxes, combined with readers deployed in the archive room, to quickly count whether archives are in storage and feed the information back to the management platform. To compensate for its shortcomings in archive location, existing technologies incorporate manual barcode scanning, robot or drone scanning, and the deployment of positioning readers in smart archive cabinets to assist in obtaining specific archive location information. The visual image recognition method uses cameras to capture images of archive cabinets and boxes, uses image segmentation algorithms to extract archive box areas, and combines OCR technology to identify file numbers, thereby determining the location and file number sequence of the archives. Both methods rely on specific equipment, have high requirements for environmental conditions and hardware performance, and suffer from slow processing speed, high error rates, and poor adaptability.

[0003] RFID methods rely on assisted positioning, resulting in low efficiency and high cost. Manual data entry and barcode scanning depend on a large workforce, leading to low efficiency. Robot or drone solutions face challenges in route planning and accuracy due to the frequent opening and closing of filing cabinets. Deploying readers in smart filing cabinets requires significant hardware upgrades. While visual recognition is feasible, it demands high precision in terms of file box spine width, font clarity, and OCR recognition capabilities, resulting in high computational load, slow processing speed, and potential data errors due to segmentation inaccuracies. Furthermore, most solutions rely on pre-set location information, making it difficult to adapt to the dynamic changes of mobile filing cabinets and lacking a rapid and accurate method for locating and inventorying non-fixed-location filing cabinets and aisles. Therefore, there is an urgent need for an efficient, low-cost, and adaptable filing location and inventory technology. Summary of the Invention

[0004] In order to overcome the above-mentioned problems of existing methods for locating and inventorying archives, this invention proposes an archive inventory system, method, apparatus, computer-readable storage medium, chip system, and computer program product.

[0005] In a first aspect, an archive inventory system is provided, comprising a main control unit, a vision system, and an archive management platform. The main control unit is configured to send a first control command to the vision system; the vision system, in response to the received first control command, acquires a QR code image of the head shelf of an archive cabinet and sends the QR code image to the main control unit; the main control unit determines the distance between the center points of two adjacent head shelf QR code images, and based on the distance between the center points of the two adjacent head shelf QR code images, determines the open / closed state of the head shelf of the archive cabinet, obtains a determination result, and sends the determination result to the archive management platform; the archive management platform, based on the received determination result, sends a second control command to the main control unit, the second control command controlling the vision system to move to the position of the head shelf of the archive cabinet in the open state.

[0006] Secondly, a method for inventorying archives is provided, characterized by comprising: acquiring a QR code image of the front shelf of an archive cabinet; determining the distance between the center points of two adjacent front shelf QR code images; determining the open / closed state of the front shelf of the archive cabinet based on the distance between the center points of the two adjacent front shelf QR code images, and obtaining a determination result; and controlling a vision system to move to the position of the front shelf of the archive cabinet that is in the open state based on the determination result.

[0007] In some possible implementations of the second aspect, determining the distance between the center points of two adjacent QR code images of the shelf includes: performing distortion correction and spot detection on the images, and calculating the distance between the center points of two adjacent QR code images of the shelf.

[0008] In some possible implementations of the second aspect, the determination of the opening / closing state of the filing cabinet's head cabinet based on the distance between the center points of the QR code images of two adjacent head cabinets, and the determination result includes: a passageway is provided between the adjacent head cabinets; the sum of the depth of the filing cabinet and the width of the passageway is obtained; and based on the relationship between the distance between the center points of the QR code images of two adjacent head cabinets and the sum of the depth of the filing cabinet and the width of the passageway, the determination is made whether the head cabinet of the filing cabinet is fully open, fully closed, or not fully open.

[0009] In some possible implementations of the second aspect, after controlling the vision system to move to the target filing cabinet row position in a fully open state based on the judgment result, the method further includes: acquiring a grid layer QR code image in the target filing cabinet row, wherein the grid layer is set in the filing cabinet and the grid layer QR code image is set on the grid layer to identify the grid layer number; acquiring a file box QR code image, wherein the file box is set on the grid layer and the file box QR code image is set on the file box to identify the file box number; and associating and binding the file box QR code image with the grid layer QR code image of the grid layer where the file box is located.

[0010] In some possible implementations of the second aspect, the method further includes: associating and binding the file box number in the file box QR code image with the corresponding grid layer number in the grid layer QR code image.

[0011] In some possible implementations of the second aspect, the group range and the number of association bindings are determined based on the following two conditions: the distance between the center point of the file box QR code image and the center point of the grid QR code image; and the angle between the line connecting the center points of the file box QR code image and the grid QR code image and the horizontal line.

[0012] In some possible implementations of the second aspect, associating the file box number in the file box QR code image with the corresponding grid layer number in the grid layer QR code image includes: The image captured by the camera is obtained, and the binding relationship between the QR code images of the file boxes in the file box group in the image and the corresponding grid layer QR code images is established. The file box group includes all identifiable file boxes contained within the width range of the image.

[0013] Thirdly, an archive inventory device is provided, comprising: The acquisition module is used to acquire the QR code image of the head cabinet of the filing cabinet; The judgment module is used to determine the distance between the center points of two adjacent column cabinet QR code images; Based on the distance between the center points of the two adjacent column cabinet QR code images, the open / closed state of the column cabinet is determined, and the determination result is obtained. The control module is used to control the vision system to move to the position of the filing cabinet headboard that is in the open state, based on the judgment result.

[0014] Fourthly, a computer-readable storage medium is provided that stores a computer program or instructions that, when executed on a computer, cause the method of the second aspect described above to be performed.

[0015] Fifthly, a chip system is provided, comprising: a processor for calling and running a computer program from a memory to execute the method described in the second aspect above.

[0016] Sixthly, a computer program product is provided that, when run on a computer, causes the method described in the second aspect to be executed.

[0017] Based on the aforementioned document inventory system, method, apparatus, and chip system, the system includes a main control unit, a vision system, and a document management platform. The main control unit sends a first control command to the vision system. The vision system, in response to the received first control command, acquires a QR code image of the head shelf of a filing cabinet and sends the image to the main control unit. The main control unit determines the distance between the center points of two adjacent head shelf QR code images and, based on this distance, determines the open / closed state of the head shelf, obtaining a judgment result, which is then sent to the document management platform. The document management platform, based on the received judgment result, sends a second control command to the main control unit, which controls the vision system to move to the head shelf position of the filing cabinet in the open state. This effectively improves the automation and accuracy of document inventory, reducing the possibility of manual intervention and misjudgment. Simultaneously, controlling the vision system to move to a designated position based on the judgment result achieves an efficient and accurate document inventory process, improving overall work efficiency and data reliability. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of an archive inventory system applicable to embodiments of this application; Figure 2 This is a schematic diagram illustrating an application of an archive inventory system applicable to embodiments of this application; Figure 3 This is a schematic diagram of the architecture of an archive inventory system applicable to embodiments of this application; Figure 4 This is a partial front view of a visual system applicable to an embodiment of this application for an inventory system; Figure 5 This is a schematic diagram of a file inventory method applicable to an embodiment of this application; Figure 6 This is a top view of a filing cabinet passageway applicable to an embodiment of this application; Figure 7 This is a front view of a filing cabinet shelf applicable to an embodiment of this application; Figure 8This is a schematic diagram illustrating the requirements for a camera to capture QR codes on a grid layer and a file box, applicable to embodiments of this application. Figure 9 This is a schematic diagram of a file box positioning method applicable to embodiments of this application; Figure 10 This is a top view of a combined horizontal slide rail system applicable to embodiments of this application; Figure 11 This is a schematic diagram of an archive inventory device applicable to embodiments of this application; Figure 12 This is a system workflow diagram applicable to embodiments of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The specific operating methods in the method embodiments can also be applied to the device embodiments or system embodiments. In the description of this application, unless otherwise stated, "multiple" means two or more.

[0020] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0021] It is understood that the various numerical designations used in this application are merely for descriptive convenience and are not intended to limit the scope of this application. The order of the process numbers does not imply the order of execution; the execution order of each process should be determined by its function and internal logic.

[0022] The terms "first," "second," "third," "fourth," and other various terminology (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0023] Figure 1 This is a schematic diagram of the structure of an archive inventory system provided in an embodiment of this application. For example... Figure 1As shown, the archive inventory system includes a main control unit 101, a vision system 102, and an archive management platform 103. The main control unit 101 sends a first control command to the vision system 102. In response to the received first control command, the vision system 102 acquires the QR code image of the head cabinet of the filing cabinet and sends it to the main control unit 101. The main control unit 101 determines the distance between the center points of two adjacent head cabinet QR code images and, based on this distance, determines the open / closed state of the head cabinet, obtaining a judgment result, which is then sent to the filing management platform 103. The filing management platform 103, based on the received judgment result, sends a second control command to the main control unit 101, which controls the vision system 102 to move to the head cabinet position of the filing cabinet in the open state.

[0024] In some embodiments, when the vision system 102 is controlled to move based on the second control command, it needs to move to the head cabinet position of the fully open file cabinet column. In addition, the head cabinet position refers to the open / closed state of the entire file cabinet column.

[0025] In some embodiments, the naming of a row of filing cabinets may vary depending on the application scenario. It may also be called a row of filing cabinets, a line of filing cabinets, etc. The specific implementation of this disclosure does not limit this.

[0026] Figure 5 This is a schematic diagram of an archive inventory method included in an embodiment of this application. Figure 5 As shown, the method includes steps S201, S202, S203, and S204. S201, Obtain the QR code image of the head cabinet of the filing cabinet. S202, determine the distance between the center points of two adjacent column cabinet QR code images. S203. Based on the distance between the center points of the QR code images of two adjacent cabinets, determine the open / closed status of the cabinet's cabinet and obtain the judgment result. S204, Based on the judgment result, control the vision system to move to the position of the filing cabinet headboard that is in the open state.

[0027] In some embodiments, when the vision system 102 is moved based on a second control command, it needs to move to the head cabinet position of the fully open row of filing cabinets to begin the corresponding inventory operation for the entire row of filing cabinets. Furthermore, the head cabinet position refers to the open / closed state of the entire row of filing cabinets.

[0028] The file inventory method includes: acquiring the QR code image of the head cabinet of a filing cabinet; determining the distance between the center points of two adjacent head cabinet QR code images; determining the open / closed state of the head cabinet based on the distance between the center points of the two adjacent head cabinet QR code images, thereby determining the open / closed state of the entire row of filing cabinets; and, based on the determination result, controlling the vision system to move to the position of the head cabinet of the filing cabinet that is in the open state, and starting the corresponding inventory operation for the entire row of filing cabinets. This method achieves intelligent determination of the open / closed state of filing cabinets through QR code recognition and distance analysis, improving inventory efficiency and data reliability.

[0029] In some implementations, determining the distance between the center points of two adjacent QR code images of the kiosks includes: performing distortion correction and spot detection on the images, and then calculating the distance between the center points of the two adjacent QR code images. Thus, through image preprocessing and precise distortion correction, the accuracy of QR code center point positioning and the reliability of distance measurement are improved. In some implementations, the opening / closing status of a filing cabinet's head cabinet is determined based on the distance between the center points of the QR code images of two adjacent head cabinets. The determination results include: a passageway exists between adjacent head cabinets; the sum of the filing cabinet's depth and the passageway width is obtained; and based on the relationship between the distance between the center points of the QR code images of two adjacent head cabinets and the sum of the filing cabinet's depth and the passageway width, it is determined whether the head cabinet is fully open, fully closed, or not fully open. Thus, by comparing theoretical values ​​with actual measurements, accurate determination of the head cabinet's opening / closing status is achieved, facilitating subsequent positioning and inventory operations. The positional status of the adjacent head cabinets can then determine the positional status of the entire filing cabinet row containing that head cabinet. In some implementations, after controlling the vision system to move to the target filing cabinet column position that is in the open state according to the judgment result, the method further includes: acquiring the grid layer QR code image in the target filing cabinet column, wherein the grid layer is set in the filing cabinet and the grid layer QR code image is set on the grid layer to identify the grid layer number; acquiring the file box QR code image, wherein the file box is set on the grid layer and the file box QR code image is set on the file box to identify the file box number. In some implementations, the method further includes associating the file box number in the file box's QR code image with the corresponding grid layer number in the grid layer's QR code image. This establishes a correspondence between file boxes and grid layers, enabling structured management and rapid retrieval of archival information. In some implementations, the association binding is determined based on the following two factors: the distance between the center point of the file box QR code image and the center point of the grid layer QR code image; and the angle between the line connecting the center points of the file box QR code image and the grid layer QR code image and the horizontal line. In some implementations, the QR codes for cabinets, grids, and file boxes differ in at least one of the following: QR code system version; error correction level; size; color; center pattern; and valid code elements. Therefore, by differentiating the design of QR codes at different levels, software systems can quickly identify and classify them, improving recognition efficiency and management accuracy. Figure 11 This is a schematic diagram of the structure of an archive inventory device provided in an embodiment of this application. Figure 3 As shown, the file inventory device includes an acquisition module 1101, a judgment module 1102, and a control module 1103. The acquisition module 1101 is used to acquire the QR code images of the top shelves of the filing cabinets. Specifically, the acquisition module 1101 can be a camera in the vision system. When the camera is shooting vertically downwards, it moves horizontally along the longitudinal slide rail at a predetermined step length to take pictures of the top of each top shelf, including the QR code images of all the top shelves. The judgment module 1102 is used to determine the distance between the center points of two adjacent QR code images of the filing cabinet. Specifically, the judgment module 1102 can be a calculation module based on image processing algorithms and calibration parameters. By performing operations such as distortion correction, spot detection, and contour extraction on the images, it identifies the center point of each QR code image and calculates the pixel distance between the center points of two adjacent QR code images. Based on the correspondence between the calibrated pixel distance and the actual physical distance, it determines the width of the filing cabinet aisle. The control module 1103 is used to control the vision system to move to the position of the head cabinet of the filing cabinet that is in the open state, based on the judgment result. The control module 1103 can be specifically the control program in the main control unit, which determines whether the filing cabinet has an open passage based on the distance data output by the judgment module 1102, and controls the sliders on the horizontal and vertical slide rails to move so that the camera is positioned at the head cabinet of the filing cabinet that needs to be queried or inventoried. This application provides a chip system. The chip system includes a processor for calling and running a computer program from memory, causing the various method embodiments of the present invention to be executed. This application also provides a computer-readable storage medium storing a computer program or instructions that, when executed on a computer, cause the various method embodiments of the present invention to be performed.

[0030] This application also provides a computer program product that, when run on a computer, enables the execution of various method embodiments of the present invention.

[0031] In some implementations, the algorithm for determining whether a filing cabinet is open or closed includes the following steps: First, Figure 2 and Figure 4In the initial state, the vision system, robotic arm, and 2D gimbal are positioned with the camera pointing vertically downwards. The longitudinal slide rail moves horizontally in predetermined steps according to the depth of the filing cabinet, and the camera takes photos of the top of each cabinet, including all cabinet tops containing QR codes. The photos require preprocessing, including image stitching, grayscale conversion, Gaussian filtering, edge detection, and contour line finding.

[0032] During this stage of work, known calibration parameters such as the size of the QR code on the front shelf of the filing cabinet and the depth (width) of the filing cabinet must be calibrated in advance (based on the actual dimensions on site). At the same time, the focal length and distortion parameters (such as radial distortion coefficients k1 / k2) of the camera are measured and calibrated using a checkerboard pattern to eliminate lens distortion, as shown in formulas (1) and (2).

[0033] (1) Where fx and fy are the camera's focal lengths (in pixels), representing the scaling ratios of the image in the x and y directions, respectively. Cx and Cy are the principal point coordinates (in pixels), i.e., the optical center of the image (usually close to the image center). k is the radial distortion coefficient. This formula converts normalized coordinates (ideal coordinates without physical units) into actual image pixel coordinates.

[0034] (2) Where x, y: normalized coordinates (uncorrected) of the distorted point. r: distance from the point to the image center. r2 = x² + y². k1, k2: Radial distortion coefficients, describing the degree of distortion caused by manufacturing defects in the lens (such as barrel distortion or pincushion distortion). r4 is used for more complex distortion correction. xcorrected, ycorrected: Corrected coordinates, closer to a true distortion-free image.

[0036] Image distortion correction and spot detection are fundamental to subsequent length calculations. Distortion correction, through parameter calibration, effectively eliminates barrel / pincushion distortion by distorting the image. Spot detection uses thresholding, such as OpenCV's cv2.threshold, to extract the laser spot and calculate its pixel coordinates in the image.

[0037] Because images typically contain complex background information beyond just the cabinet's shape, QR codes, and channels, it's impossible to directly extract feature points of the target object. Therefore, when acquiring the contour information of the object to be tested in an image, the Segment Anything model or the cv2.findcontours function can be used to extract the contour of the target object from the corrected image.

[0038] The image is traversed by the Census algorithm. The comparison result between the center point of the window and other pixels is the Census transform bit string of the center point pixel. The similarity of the bit string is calculated using Hamming distance, which is the pixel similarity. The smaller the Hamming distance, the higher the bit string similarity, as shown in formula (3): (3) Where I(p) is the gray value of the reference pixel; I(q) is the gray value of the non-center pixel within the transformation window. ξ[ ] is a binarization function that outputs 0 or 1 based on the condition, used to compare the gray values ​​of two pixels.

[0040] Alternatively, you can use OpenCV's cv2.boundingRect function to calculate the minimum bounding rectangle for each contour and perform general image traversal.

[0041] Using the Euclidean distance method, referencing the size of the calibrated object and its pixel value, and combining it with the pixel value of the target object, the actual size of the target object in the photo is calculated, as shown in formula (4): (4) in, These are the coordinates of the measured object in the image. It is the coordinate point of the reference object in the image.

[0043] After traversing all QR codes, the distance between the center points of two adjacent QR codes is calculated. This embodiment determines whether the filing cabinet is fully open, or whether it is fully closed or not, by judging whether the distance between the center points of two adjacent QR codes is greater than or equal to the depth of the filing cabinet plus the width of the passageway.

[0044] Judgment Result 1: Any two adjacent rows of filing cabinets are completely closed. Condition: The distance L1 between the two QR codes at the top equals the depth of the filing cabinet.

[0045] Judgment Result 2: Any two adjacent rows of filing cabinets are fully open. Condition: The distance L1 between the two QR codes at the top is greater than or equal to the depth of the filing cabinet plus the width of the passageway.

[0046] Judgment Result 3: No two adjacent rows of filing cabinets are fully opened. Condition: The distance L1 between the two QR codes at the top satisfies: Filing cabinet depth + aisle width > L1 > filing cabinet depth.

[0047] The measured distance between the center points of any two QR code images in a camera photograph can be calibrated with the actual depth of the filing cabinet and the width of the aisle when it is opened and closed, with a certain tolerance margin. Figure 6 As shown.

[0048] In some implementations, each filing cabinet, shelf, and file box has a unique identification number, which is a QR code for accurate and rapid identification and decoding. The top of the head cabinet of each filing cabinet row needs to be marked with a QR code corresponding to the head cabinet of that row, ensuring that the camera can identify the filing cabinet row to be located and thus determine the position of the longitudinal slide rail.

[0049] Each compartment and each file box also needs to be identified with a QR code indicating the compartment number and file box number, respectively. This ensures that the camera can establish a connection between the file box number and the compartment number during data collection, thereby accurately locating the file box. Figure 7 As shown.

[0050] Depending on the camera's field of view, multiple QR codes may need to be marked on a wider grid panel.

[0051] In the archive management platform database, the archive cabinet number, shelf number, and file box number correspond to different data groups. In other words, the QR code corresponds to different three-level data groups (archive cabinet group, shelf group, and file box group). When using QR code identification, the QR code format corresponding to the three-level data groups is also different, which facilitates software judgment and action control.

[0052] The three-level data groups correspond to the three-level data management system of the archives, as follows: Front cabinet group (highest level); Grid group (intermediate level); File box group (most basic level).

[0053] In some implementations, the effective data capacity, anti-defacement error correction capability, and ease of posting requirements of QR codes corresponding to different levels are differentiated in terms of QR code system version, error correction level, size, color, center pattern, and effective code element content as shown in Table 1 below: Table 1. Coding Design Table for the Three-Level QR Code Identification System

[0054] The QR codes designed according to Table 1 above can not only improve the efficiency and accuracy of initial labeling, but also, due to the associated design of the QR code center patterns in the file cabinet and the grid, can promptly detect subsequent decoding errors caused by QR code soiling or damage.

[0055] In the visual recognition module of the file management platform, a verification procedure is added between the column cabinet and the QR code. When the QR code is damaged due to various reasons in subsequent applications, resulting in inconsistencies between the file cabinet information presented by the column cabinet and the cell layer decoding, the information of the column cabinet and the multiple cell layers contained therein can be compared to determine whether the QR code of the column cabinet or a certain cell layer has been damaged. The system alarm is then output so that the QR code can be maintained and replaced in a timely manner.

[0056] In some implementations, unlike traditional library management, archives do not have fixed classifications and index numbers. Archive management is evolving from "physical order" to "logical order," achieving "disordered placement, orderly management." Its essence is replacing physical order with information tools, achieving efficient management through dynamic mapping. This model is particularly suitable for highly digitized environments. The storage location of archives does not depend on a fixed order (such as traditional classifications like time or numbering), but is dynamically adjusted based on actual space utilization and usage frequency. For example, archives are randomly stored in mobile shelving or intelligent storage systems, without being forced into a specific order. Similar to the "dense storage" model of libraries, the appearance is irregular, but the system accurately records the location. This patent replaces high-cost deployment methods such as visual OCR recognition or RFID, using a QR code positioning algorithm to determine the shelving unit where the archive box is located and uploads the associated management information to the platform. The platform establishes a three-level management strategy, realizing the association between QR code data and complete archive information in the database.

[0057] The principle of the QR code positioning algorithm is to use the QR codes affixed to the file boxes and grids, and by calculating the distance and angle between the file boxes and the grids, to bind the position of the file boxes on a grid to that grid. For example... Figure 8 As shown, 2N-1 QR code labels are evenly affixed to each compartment of the mobile shelving unit. The value of N is related to the camera's shooting width and the compartment width. If the camera can capture the entire width of a compartment at once, then N=1, and each compartment needs to be affixed with 2N-1=1 QR code labels. If it cannot capture the entire compartment, then N is a number greater than 1, ensuring that each captured image contains at least one compartment QR code and one or more file box QR codes.

[0058] When both the QR code on the file box and the QR code on the cell shelf meet the following conditions, the file box will be assigned to the corresponding cell shelf, ensuring that all file boxes on that cell shelf are associated and bound to that cell shelf: Condition 1: The distance between the center point of the QR code on the file box and the center point of the QR code in the grid is less than the distance threshold S; Condition 2: The angle between the line connecting the center point of the QR code on the file box and the center point of the QR code in the grid and the horizontal line is greater than the critical angle θ.

[0059] in: The calculation method for S is: S = distance between inner diameters of the grid layer / N The calculation method for θ: θ = arccosine (A / S) Among them, such as Figure 9 As shown, a horizontal line is formed by connecting the center points of the QR codes on the file boxes. A perpendicular line is drawn from the center point of the QR codes in the grid layers to this line, and the foot of the perpendicular is connected to the center point of the target file box to form line segment A. The angle between line segment A and line segment S is θ.

[0060] As another possible approach, when acquiring images from a camera, an association and binding relationship is established between the QR code images of the file boxes within the file box group in the image and the corresponding grid layer QR code images. The file box group includes all identifiable file boxes within the width of the image; that is, it comprises all identifiable file box groups within the width of the image that meet the above two conditions (condition 1 and condition 2). For easier understanding, please refer to [link to relevant documentation]. Figure 8 , Figure 8 The process involves three image acquisitions, corresponding to the blue-framed image, red-framed image, and green-framed image, respectively. Three identical grid layer QR code images are applied within the same grid layer. Taking the blue-framed image as an example, it contains seven file box QR codes, forming a file box group. The association and binding relationship between the seven file box QR code images within this file box group and their corresponding grid layer QR code images is established. Figure 8 The process involved establishing the association between the QR code image of each file box and the corresponding QR code image of the corresponding grid layer three times. This method can quickly associate and bind all file boxes on the grid layer without requiring each file box to be associated and bound to the grid layer individually.

[0061] In some implementations, such as Figure 2 , Figure 4 and Figure 10 As shown, the vision system consists of five parts: a combined horizontal sliding rail system, a camera (with a light source), a 2D pan-tilt unit, a robotic arm, and a main control unit. A single vision system can be used throughout the entire archive storage room, reducing investment and simplifying maintenance; if the storage room is large, the number of vision systems can be increased to improve efficiency.

[0062] Combined horizontal slide rail system The combined horizontal slide rail system consists of three parts: a horizontal slide rail, a vertical slide rail, and a slider.

[0063] Horizontal slide rails: One is installed on each side of the outer perimeter of the filing cabinet row, which facilitates the horizontal movement of the vertical slide rails above the filing cabinet row.

[0064] Slider: Mounted on the slide rail, with a built-in high-precision servo motor, it can slide on the slide rail according to instructions.

[0065] Vertical slide rail: Located above the rows of filing cabinets, parallel to the direction of the rows. Sliding blocks are connected to both ends of the vertical slide rail, allowing it to slide laterally on the horizontal slide rail.

[0066] 2D gimbal The gimbal has a horizontal rotation capability of 360° and a vertical rotation capability of ≥180°, connected to the vertical slide rail by the slider.

[0067] robotic arm For taller filing cabinets, an electric robotic arm can be added between the pan-tilt head and the slider, and its extension and retraction can be adjusted through a control program according to the actual height of the shelves above the ground.

[0068] Camera It uses a high-definition, ranging, wide-angle camera.

[0069] High-definition shooting: Ensures clear capture of QR codes or barcodes on the spine of file boxes and QR codes on each compartment. When used with a 2D pan-tilt head, horizontal adjustment of the pan-tilt head allows the camera to capture QR codes on file boxes within the same compartment, as well as the compartment QR codes; vertical adjustment of the pan-tilt head in conjunction with the robotic arm allows the camera to capture file boxes on different compartments of the same shelf, as well as the compartment QR codes; and movement of the slider on the vertical slide rail allows the camera to capture images of different file cabinets.

[0070] Distance measurement: The longitudinal slide rail and the slider on the slide rail return to the starting position, which is the position of the first column of filing cabinets. In the initial state of the pan-tilt unit, the camera is vertically downward and the longitudinal slide rail moves horizontally. The camera determines which two columns of filing cabinets have open channels by judging the position of the QR code on the first column of filing cabinets, which facilitates the subsequent data collection actions of the camera.

[0071] Light source: Located next to the camera, it is turned on when the camera is working to ensure brightness when the camera is shooting.

[0072] Main control unit It is responsible for controlling the movement of the slider, gimbal, and camera, and wirelessly uploading camera data.

[0073] Slider movement: Based on the data collection requirements specified by the file management platform, control the two sliders on the horizontal slide rail to move horizontally; control the one slider on the vertical slide rail to move vertically; so that the pan-tilt unit and camera stop at the file cabinet shelf where data needs to be collected.

[0074] Pan-Tilt Control: By controlling the pan-tilt unit to move horizontally or vertically according to the acquisition requirements specified by the archive management platform, the camera stays at an angle above and outside the archive box where data needs to be acquired, forming a good viewing angle.

[0075] Camera control: Controls the camera to capture QR codes on the spine of filing cabinets and file boxes, as well as QR codes on each compartment. Because it uses a wide-angle camera, it can capture multiple QR codes simultaneously (hereinafter referred to as QR code clusters).

[0076] Main control unit: Contains a wireless communication module (4 / 5G, WiFi), which uploads the data collected by the camera to the archive management platform through the wireless signal network built in the warehouse; the archive management platform transmits control signals to the main control unit through the wireless network to implement the actions of the slider, gimbal, robotic arm and camera.

[0077] In some implementations, the system principle includes: (1) Combined horizontal slide rail system The combined horizontal slide rail system consists of three parts: a horizontal slide rail, a vertical slide rail, and a slider. The horizontal slide rail primarily provides a fixed guide and load-bearing structure for the horizontal movement of the vertical slide rail; the vertical slide rail primarily provides a fixed guide and load-bearing structure for the vertical movement of the pan-tilt unit; the slider connects the vertical and horizontal slide rails, and the pan-tilt unit is connected to the vertical slide rail. The slider consists of a servo motor and rollers. The operation of the combined horizontal slide rail system is controlled by an algorithm for determining the opening and closing of the filing cabinet and a positioning and inventory program.

[0078] (2) File box and compartment binding system Using a QR code positioning algorithm, the camera uploads the QR codes on the spine of the file and the corresponding compartment to the file management platform for data binding. This one-to-many relationship means that one compartment can be bound to multiple file boxes, thus locating each file box to a unique compartment. When the entire warehouse undergoes periodic inventory checks or searches, the location of the file boxes can be verified again.

[0079] (3) Visual system Camera QR code group recognition function: The camera may collect a single QR code or a group of QR codes. The back-end software can identify which of the different QR code formats are the cabinet head number, compartment number, and file box number.

[0080] Camera distance measurement function: When the camera collects the QR code of the head cabinet of the filing cabinet, the camera has a distance measurement function. In conjunction with the filing cabinet opening and closing judgment algorithm, it determines whether the filing cabinet is open and provides distance information to the main control unit. It controls the longitudinal slide rail to move to the middle of the two open filing cabinets. The slider on the longitudinal slide rail reaches the designated filing cabinet shelf position, so that the vision system can perform the next action.

[0081] Pan-tilt function: When the slider on the longitudinal slide rail is positioned diagonally above and outside the filing cabinet where data needs to be collected, the robotic arm and pan-tilt unit operate according to the control program. Data collection for the entire filing cabinet is completed using a QR code positioning algorithm.

[0082] (4) Software control system The entire system requires a dedicated set of control software to handle the corresponding actions of the slider and gimbal, including horizontal slider positioning program, vertical slider positioning program, gimbal control program, robotic arm control program, fixed-point search program, and inventory program.

[0083] 1) Horizontal slider positioning program: The camera initially positions itself at the head cabinet in the first column. It then moves horizontally to the last column, collecting the identification codes of all head cabinets and measuring distances. An algorithm for determining whether the filing cabinet is open or closed is used to ascertain whether data collection or inventory is required.

[0084] 2) Vertical slider positioning program: Based on the fixed-point search program, inventory program, and the width of the filing cabinet, move the filing cabinets in the open aisle one by one to ensure that the camera can capture all the filing cabinets in the column.

[0085] 3) Pan-tilt control program (robotic arm control program): Based on the fixed-point search program, inventory program, as well as the width of the filing cabinet, the height of each compartment above the ground, and the distance between each compartment, the QR code positioning algorithm is used to collect the QR code of the filing box and the QR code of the compartment label in each layer.

[0086] 4) Fixed-point search procedure: According to the operator's requirements, go to the designated location and collect the QR codes of all file boxes and the QR code of the grid layer.

[0087] 5) Inventory procedure: According to the operator's requirements, collect data of each file box in each column and each compartment from the first column to the last column, and collect the compartment identification code. The background system will then perform data association or verification.

[0088] like Figure 12 As shown, the document inventory workflow is as follows: The slider on the longitudinal slide rail returns to its original position in the first row of cabinet configuration; The longitudinal slide rail moves horizontally from the first column to the last column; During the horizontal movement, the camera measures the distance to the QR code on each row of cabinets; The algorithm for determining whether a filing cabinet column is open is used. If the judgment result is open, the slider on the longitudinal slide rail will move to the position above the outer side of the cabinet that needs to be positioned / inventoryed; The gimbal is moved vertically to the angle required for positioning / inventory of the grid layer; Using a QR code positioning algorithm, the camera reads the QR codes on the file boxes and the cell layers one by one. Data correlation / verification; If no file boxes need to be read, the process ends; if there are still file boxes to be read, proceed to step 10. The pan-tilt unit moves horizontally to read the file box in the next field of view of this grid layer; The camera reads the QR codes on the file boxes and the cell shelves; Data association / verification.

[0089] The sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0090] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0091] Those skilled in the art will recognize that, based on the units and algorithm steps described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is implemented in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0092] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0093] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0094] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of apparatus or units may be electrical, mechanical, or other forms.

[0095] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0096] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0097] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0098] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An archive inventory system, characterized in that, Includes the main control unit, vision system, and document management platform. The main control unit is used to send a first control command to the vision system; The vision system, in response to the received first control command, acquires the QR code image of the head cabinet of the filing cabinet and sends the QR code image of the head cabinet to the main control unit; The main control unit determines the distance between the center points of two adjacent column cabinet QR code images, and determines the open / closed state of the column cabinet based on the distance between the center points of the two adjacent column cabinet QR code images, obtains the determination result, and sends the determination result to the file management platform. The file management platform is used to send a second control command to the main control unit based on the received judgment result. The second control command controls the vision system to move to the position of the file cabinet head cabinet that is in the open state.

2. A method for inventorying archives, characterized in that, include: Obtain the QR code image of the head cabinet of the filing cabinet; Determine the distance between the center points of two adjacent column cabinet QR code images; Based on the distance between the center points of the two adjacent column cabinet QR code images, the open / closed state of the column cabinet is determined, and the determination result is obtained. Based on the judgment result, the vision system is controlled to move to the position of the head cabinet of the filing cabinet that is in the open state.

3. The method according to claim 1, characterized in that, The determination of the distance between the center points of two adjacent QR code images of the cabinet includes: The image is subjected to distortion correction and spot detection, and the distance between the center points of two adjacent column cabinet QR code images is calculated.

4. The method according to claim 1, characterized in that, The step of determining the open / closed state of the filing cabinet based on the distance between the center points of the QR code images of two adjacent cabinets, and obtaining the determination result includes: A passageway is provided between the adjacent cabinets; Obtain the sum of the depth of the filing cabinet and the width of the passageway; Based on the relationship between the distance between the center points of the QR code images of two adjacent file cabinets and the sum of the depth of the file cabinet and the width of the passage, it is determined whether the file cabinet at the head of the row is fully open, fully closed, or not fully open. The opening and closing state of the file cabinet at the head of the row is used to characterize the opening and closing state of the entire row of file cabinets.

5. The method according to claim 1, characterized in that, After controlling the vision system to move to the target filing cabinet row that is in the open state based on the judgment result, the method further includes: Obtain the QR code image of the grid in the target filing cabinet column. The grid is set in the filing cabinet, and the QR code image of the grid is set in the grid to identify the grid number. Obtain the QR code image of the file box, which is set on the grid layer and is used to identify the file box number.

6. The method according to claim 5, characterized in that, The method further includes: Associate and bind the file box number in the file box QR code image with the corresponding grid layer number in the grid layer QR code image.

7. The method according to claim 6, characterized in that, The group scope and the number of associations are determined based on the following two conditions: The distance between the center point of the file box QR code image and the center point of the grid layer QR code image; The angle between the line connecting the center point of the file box QR code image and the grid layer QR code image and the horizontal line.

8. The method according to claim 5, characterized in that, The step of associating and binding the file box number in the file box QR code image with the corresponding grid layer number in the grid layer QR code image includes: The image captured by the camera is obtained, and the association and binding relationship between the QR code images of all file boxes in the file box group in the image and the corresponding grid layer QR code images is established. The file box group includes all file boxes contained within the width range of the image.

9. An archive inventory device, characterized in that, include: The acquisition module is used to acquire the QR code image of the head cabinet of the filing cabinet; The judgment module is used to determine the distance between the center points of two adjacent column cabinet QR code images; Based on the distance between the center points of the two adjacent column cabinet QR code images, the open / closed state of the column cabinet is determined, and the determination result is obtained. The control module is used to control the vision system to move to the position of the filing cabinet headboard that is in the open state, based on the judgment result.

10. A chip system, characterized in that, Includes: a processor for retrieving and running a computer program from memory, such that the method as described in any one of claims 2 to 8 is performed.

Images