Automatic inventory checking method, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides an automatic inventory checking method, electronic equipment, a storage medium and a program product, and relates to the technical field of automatic control. Acquiring a current tray identification code identified by a scanning unit and a current inventory drawing acquired by an acquisition unit; searching a historical warehousing graph corresponding to the current tray identification code in the historical inventory data; and according to the current inventory drawing and the historical warehousing drawing, generating current inventory data. According to the method, manual intervention is not needed during inventory making, and the inventory making efficiency and the accuracy of inventory making data are improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of automation control technology, and in particular to automated inventory methods, electronic devices, storage media and program products. Background Technology

[0002] In cigarette manufacturing companies, inventory management plays a crucial role in ensuring the accuracy of production plan execution, controlling material batch timing, and guaranteeing product quality.

[0003] Traditional inventory methods primarily rely on two modes: person-to-goods and goods-to-person. The person-to-goods mode requires operators to stand on the stacker crane forks and move with the equipment to the target location to record data, posing serious safety hazards. Furthermore, operator errors due to visual bias or oversights can lead to low inventory accuracy, impacting supply chain stability. The goods-to-person mode, on the other hand, requires transporting all pallets to be inventoried from the high-bay warehouse to a designated station for manual counting, severely disrupting normal inbound and outbound operations and resulting in a long inventory cycle that significantly slows down production. Summary of the Invention

[0004] This invention provides an automated inventory check method, electronic device, storage medium, and program product that can improve inventory check efficiency and data accuracy without manual intervention.

[0005] In a first aspect, the warehouse management system provided by the embodiments of the present invention includes a management unit, a stacker crane, a data acquisition unit, and a scanning unit, wherein the data acquisition unit and the scanning unit are electrically connected to the management unit respectively; the automated inventory method provided by the embodiments of the present invention includes: after controlling the stacker crane to place a pallet carrying items to be inventoried at a first target position, acquiring the current pallet identification code identified by the scanning unit and the current inventory map acquired by the data acquisition unit; searching for the historical inbound map corresponding to the current pallet identification code in historical inventory data; and generating current inventory data based on the current inventory map and the historical inbound map.

[0006] Secondly, the warehouse management system provided in this embodiment of the invention includes a management unit, a stacker crane, a data acquisition unit, and a scanning unit, wherein the data acquisition unit and the scanning unit are electrically connected to the management unit. The automated inventory device provided in this embodiment of the invention includes: an image acquisition module, used to acquire the current pallet identification code identified by the scanning unit and the current inventory image acquired by the data acquisition unit after controlling the stacker crane to place a pallet carrying items to be inventoried at a first target position; an image search module, used to search for the historical inbound image corresponding to the current pallet identification code in historical inventory data; and a data generation module, used to generate current inventory data based on the current inventory image and the historical inbound image.

[0007] Thirdly, the electronic device provided in the embodiments of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the automated inventory method as described in any embodiment of the present invention.

[0008] Fourthly, the computer-readable storage medium provided in the embodiments of the present invention stores a computer program thereon, which, when executed by a processor, implements the automated inventory method as described in any embodiment of the present invention.

[0009] Fifthly, the computer program product provided in the embodiments of the present invention includes a computer program that, when executed by a processor, implements the automated inventory method as described in any embodiment of the present invention.

[0010] In this embodiment of the invention, after the stacker crane places the pallet carrying the items to be inventoried at the first target position, the current pallet identification code identified by the scanning unit and the current inventory map collected by the collection unit are obtained. This accurately identifies the status of the current pallet and its goods, providing a precise data foundation for subsequent inventory operations. Simultaneously, automated data collection is achieved without manual intervention, improving inventory efficiency and accuracy. Searching for the historical inbound map corresponding to the current pallet identification code in historical inventory data ensures that the retrieved historical inbound map and the pallet in the current inventory belong to the same pallet, guaranteeing data consistency. Based on the current inventory map and the historical inbound map, current inventory data is generated, enabling automatic recording of the current pallet's goods status, reducing manual statistical errors, and improving the accuracy and reliability of warehouse management. Attached Figure Description

[0011] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart illustrating an automated inventory management method provided in an embodiment of the present invention; Figure 2 This is another flowchart illustrating the automated inventory method provided in this embodiment of the invention; Figure 3 This is a schematic diagram of the structure of the automated inventory device provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0013] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0014] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover 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.

[0015] Figure 1 This is a flowchart illustrating an automated inventory counting method provided in an embodiment of the present invention. This automated inventory counting method is applicable to scenarios involving the automatic counting of palletized goods in warehouse management systems. The automated inventory counting method can be executed by an automated inventory counting device provided in this embodiment, which can be implemented using software and / or hardware. In one specific embodiment, the device can be integrated into an electronic device, such as a computer or server. The following embodiment illustrates the integration of the automated inventory counting device into an electronic device.

[0016] The warehouse management system in this embodiment includes a management unit, a stacker crane, a data acquisition unit, and a scanning unit. The data acquisition unit and the scanning unit are electrically connected to the management unit. (See reference...) Figure 1 The automated inventory management method of this embodiment may include the following steps: Step 101: After the stacker crane is controlled to place the pallet carrying the items to be inventoried at the first target position, the current pallet identification code identified by the scanning unit and the current inventory map collected by the acquisition unit are obtained.

[0017] A stacker crane is an automated material handling system installed in warehouse aisles. It moves pallets between racks and work positions, using its loading platform to carry the pallets for movement and retrieval operations. A pallet is a carrier that holds items to be inventoried and can be moved by the stacker crane. Items to be inventoried are boxed goods stored on pallets that require inventory verification. The first target location is a pre-set data collection location in the warehouse for inventory checks, such as the stacker crane's loading platform. A scanning unit is an identification device that reads pallet identification information, such as a barcode reader. The current pallet identification code is the unique code obtained by the scanning unit after identifying the current pallet, such as a pallet barcode or pallet QR code. A data acquisition unit is a data acquisition device used to acquire images of the items to be inventoried on the pallet, such as a smart camera. The current inventory image is the image data captured by the smart camera when the pallet is placed at the first target location during the inventory process, showing the pallet and the goods stacked on it.

[0018] Specifically, after the management unit controls the stacker crane to move the pallet carrying the items to be inventoried to the first target position, the scanning unit first identifies the pallet barcode of the current pallet to determine the identity of the pallet participating in the inventory, and locates the historical inbound information corresponding to the pallet in the system database. At the same time, the acquisition unit set at the first target position (stacker crane loading platform) acquires images of the pallet and the entire pallet of goods on it to obtain the current inventory image, thereby obtaining image data of the current status of the goods on the pallet, providing a data foundation for subsequent retrieval of historical inbound images based on the same pallet barcode and image feature comparison.

[0019] Step 102: Find the historical inbound image corresponding to the current pallet identifier in the historical inventory data.

[0020] Historical inventory data refers to the collection of inventory information recorded and stored during the goods receiving process. It reflects the historical status of goods on each pallet. Historical inventory data can be stored in the warehouse management system's database and associated with the corresponding pallet's goods information via pallet identification codes. The current pallet identification code is the coded information uniquely identifying the current pallet, obtained by the scanning unit. Historical receiving images are image data obtained by image acquisition devices located at the receiving end, capturing images of the pallet and the palletized goods. These images record the initial state of the palletized goods upon receiving the goods.

[0021] Specifically, after obtaining the current pallet identifier code, a query is performed in the historical inventory data based on the current pallet identifier code to retrieve the historical inbound image stored corresponding to the current pallet identifier code. This embodiment establishes a one-to-one correspondence between the current inventory image and the historical inbound image through the current pallet identifier code. This ensures that the retrieved historical inbound image and the pallet in the current inventory belong to the same pallet, avoiding cross-comparison of images from different pallets, guaranteeing data consistency, and thus providing a foundation for subsequent image feature comparison between the current inventory image and the corresponding historical inbound image.

[0022] Step 103: Generate current inventory data based on the current inventory map and historical inventory entry map.

[0023] Specifically, after obtaining the current inventory map and the corresponding historical inbound map, the current inventory map and the historical inbound map are analyzed and processed to determine whether the status of the goods on the current pallet is consistent with the status at the time of inbound. The current inventory data is generated by combining the item information to realize the automated inventory count of the goods in the warehouse.

[0024] For example, after obtaining the current inventory map and the corresponding historical inventory map, the item information of the items to be inventoried is determined based on the current inventory map, and the current inventory data is generated by combining the image similarity between the current inventory map and the historical inventory map.

[0025] In this embodiment, after the stacker crane places the pallet carrying the items to be inventoried at the first target position, the current pallet identification code identified by the scanning unit and the current inventory map collected by the collection unit are obtained. This accurately identifies the status of the current pallet and its goods, providing a precise data foundation for subsequent inventory operations. Simultaneously, automated data collection is achieved without manual intervention, improving inventory efficiency and accuracy. Searching for the historical inbound map corresponding to the current pallet identification code in historical inventory data ensures that the retrieved historical inbound map and the pallet in the current inventory belong to the same pallet, guaranteeing data consistency. Based on the current inventory map and the historical inbound map, current inventory data is generated, enabling automatic recording of the current pallet's goods status, reducing manual statistical errors, and improving the accuracy and reliability of warehouse management.

[0026] The warehouse management system in this embodiment includes a management unit, a stacker crane, a data acquisition unit, and a scanning unit. The data acquisition unit and the scanning unit are electrically connected to the management unit. Figure 2 This is another flowchart illustrating the automated inventory method provided in this embodiment of the invention, such as... Figure 2 As shown, the automated inventory management method of this embodiment may include: Step 201: After the stacker crane is controlled to place the pallet carrying the items to be inventoried at the first target position, the current pallet identification code identified by the scanning unit and the current inventory map collected by the acquisition unit are obtained.

[0027] Optionally, the warehouse management system also includes a monitoring unit for: monitoring the operating status of the stacker crane in real time, and sending a prompt message after determining that the stacker crane is faulty based on the operating status, wherein the prompt message is used to remind the user to replace or repair the stacker crane.

[0028] A monitoring unit refers to the equipment or module in a warehouse management system used to acquire, monitor, and analyze the real-time operating status of a stacker crane. Operating status refers to the real-time status information of various working parameters of the stacker crane during pallet handling, picking, and placing operations, including but not limited to position, speed, load, mechanical movements, and equipment health status. Fault refers to abnormal conditions that occur during the operation of the stacker crane, such as abnormal movements, mechanical jamming, sensor malfunctions, or other situations that prevent the stacker crane from performing its handling tasks normally. Warning messages refer to alerts or notifications generated by the monitoring unit and sent to the user, indicating that the stacker crane has a fault and needs replacement or repair.

[0029] Specifically, the warehouse management system includes a monitoring unit that can obtain real-time operating status information of the stacker crane and analyze and judge the operating status. Once the stacker crane malfunctions, it will automatically generate a prompt message and send it to the user to remind the user to replace or repair the faulty stacker crane, so as to avoid interruption of the inventory process caused by equipment failure, thereby ensuring the safe and efficient execution of the automatic inventory task in the warehouse.

[0030] Step 202: Find the historical inbound image corresponding to the current pallet identifier in the historical inventory data.

[0031] Step 203: Determine the item information of the items to be inventoried based on the current inventory diagram.

[0032] The item information includes at least one of the following: item specifications, item quantity, stacking shape, and entry time. Item information refers to a set of data describing the specific characteristics of the items to be inventoried, reflecting the attributes and status of the goods. Item specifications refer to attribute information such as the brand and specifications of the items to be inventoried, for example, the brand of cigarette cartons, packaging method, and item type (finished or semi-finished). Item quantity refers to the number of items currently to be inventoried on the pallet, such as the total number of cigarette cartons on the pallet. Stacking shape refers to the layout or arrangement of the goods on the pallet, such as a grid, quincunx, or crisscross pattern. Entry time refers to the time when the pallet and its goods were recorded by the warehousing system, reflecting the time point when the goods entered the warehouse.

[0033] Step 204: Determine the image similarity based on the current inventory map and the historical inventory map.

[0034] Image similarity is a numerical indicator obtained by comparing the current inventory image with historical inbound images. It is used to quantify the degree of consistency between the current palletized goods and the goods at the time of inbound.

[0035] Specifically, based on the current inventory map and historical data entry maps, image similarity is determined, including the following steps: Step A1: Preprocess the current inventory map and the historical inventory map respectively to generate the first grayscale image and the second grayscale image.

[0036] A grayscale image is image data that has been converted from a color image to a single-channel grayscale image through image preprocessing. This reduces computational load, eliminates color redundancy, and improves the stability of subsequent feature extraction. The first grayscale image refers to the grayscale image obtained after preprocessing operations such as grayscale conversion and denoising of the current database image. The second grayscale image refers to the grayscale image obtained after preprocessing operations such as grayscale conversion and denoising of historical database images.

[0037] Specifically, the current inventory image and the historical inventory image are preprocessed to generate a first grayscale image and a second grayscale image. By generating grayscale images, the complexity of image processing can be reduced, color interference can be eliminated, and clear and regular images can be provided for subsequent feature point extraction and image matching.

[0038] For example, both the current inventory chart and the historical inventory chart are RGB images. RGB images can be represented by formulas. Convert to a single-channel grayscale image (reducing computational load and eliminating color redundancy). Here, G is the output grayscale value, R, G, and B represent the brightness values ​​of the three channels of a pixel, and the corresponding coefficients a, b, and c represent the proportions of G. For example, the coefficients can be a=0.299, b=0.587, and c=0.114. In practice, the coefficients are adjusted according to the warehouse's lighting intensity. If the wrapped cigarette tray has a large area of ​​white reflection, c is appropriately decreased, and b is slightly increased. If the warehouse lighting is dim or yellowish, a is slightly increased. After obtaining the single-channel grayscale image, image filtering methods can be used to smooth high-frequency noise in the grayscale image while preserving edges. Assume the convolution kernel size is... ,Right now Standard deviation (Adjust according to ambient lighting; when lighting is complex) (Adjustable to 1.5). The formula for calculating image filtering is: , where e is the exponent, and x and y are the kernel sizes.

[0039] Step A2: Extract M first feature points from the first grayscale image and extract M second feature points from the second grayscale image, where M is a positive integer greater than or equal to 2.

[0040] Feature points refer to key locations in a grayscale image that stably reflect local image information. These key points typically correspond to identifiable local image features such as pallet corners, cargo box corners, or product specification markings. The first feature point refers to the M feature points extracted from the first grayscale image, used to describe key local information in the current inventory image. The second feature point refers to the M feature points extracted from the second grayscale image, used to describe key local information in historical inventory images.

[0041] Specifically, M feature points are extracted from the first grayscale image and the second grayscale image respectively to represent key local information of the current inventory image and the historical inventory image, providing basic data for subsequent image similarity calculation and ensuring that image comparison can accurately reflect the consistency of the palletized goods status.

[0042] Step A3: For each first feature point, calculate the Euclidean distance between the feature vector of the first feature point and the feature vector of each second feature point, and select the second feature point with the smallest Euclidean distance to form a candidate matching point pair with the first feature point.

[0043] A feature vector is a multi-dimensional numerical vector describing the local image information of each feature point. In this embodiment, the feature vector of each feature point can be 128-dimensional, used to represent local features such as pallet corners, cargo box corners, or product specification markings. Euclidean distance is a distance metric used in multi-dimensional space to quantify the difference between two feature vectors; the smaller the value, the more similar the local features of the two feature points. Candidate matching point pairs are point pairs formed by the first feature point and the second feature point with the smallest Euclidean distance, used for subsequent screening of true matching point pairs.

[0044] Specifically, for each feature point, a 16×16 pixel block is selected within its neighborhood as the description range for extracting local image features. This 16×16 pixel block is divided into 16 (4×4) smaller sub-blocks. Gradient histograms in 8 directions are calculated for each sub-block. The gradient information of all sub-blocks is concatenated to form the 128-dimensional feature vector corresponding to that feature point. Each The gradient direction and magnitude of the feature point's neighborhood are calculated. After obtaining the eigenvectors of the first and second feature points, for each first feature point, the Euclidean distance between its eigenvector and the eigenvectors of each second feature point is calculated. If the eigenvector of the first feature point is... The eigenvector of the second feature point is Then through the formula calculate and The Euclidean distance is calculated. Then, the second feature point with the smallest distance value is selected from the multiple calculated Euclidean distances, and this second feature point is paired with the first feature point to obtain candidate matching point pairs. In this way, a feature point that is closest to its feature in the historical data entry image can be determined for each first feature point, thereby forming a candidate matching relationship and providing a basis for subsequent screening of candidate matching point pairs.

[0045] Step A4: Filter out the true matching pairs from all candidate matching pairs.

[0046] True matching point pairs refer to the combination of feature points that, after further geometric consistency verification, are determined to correspond to the same object location or structural features in two images from among the candidate matching point pairs.

[0047] Specifically, after obtaining candidate matching point pairs, to avoid mismatches caused by similar features but different locations, these candidate matching point pairs need to be further filtered. In this embodiment, the perspective transformation relationship between the current inventory map and the historical inventory map can be used to filter the candidate matching point pairs.

[0048] Optionally, select true matching point pairs from all candidate matching point pairs, including: calculating the pixel error of each candidate matching point pair; and selecting candidate matching point pairs whose pixel error is less than or equal to the pixel threshold as true matching point pairs.

[0049] Pixel error refers to the deviation of pixel coordinates between the predicted positions of feature points in the current image and the actual corresponding positions in the current image after establishing the perspective transformation relationship between two images and mapping the feature points in the historical image to their predicted positions in the current image. It is typically calculated using the Euclidean distance between the two points. Pixel threshold refers to a preset error range for determining whether a candidate matching point pair meets the matching conditions. When the pixel error does not exceed this threshold, the matching point pair is considered to meet the geometric consistency requirements.

[0050] For example, based on multiple candidate matching point pairs between the current inventory image and the historical inventory image, the perspective transformation matrix between the two images is calculated. , among which, element The parameter is fixed at 1 for normalization. The remaining parameters are calculated using candidate matching point pairs. The perspective transformation matrix describes the spatial mapping relationship between feature points in the historical inventory entry image and feature points in the current inventory entry image. When calculating the perspective transformation matrix, four sets of candidate matching point pairs for the same inventory pallet in the historical inventory entry image and the current inventory entry image can be selected. Assume the feature point coordinates in the historical inventory entry image are... The coordinates of the corresponding feature point in the current inventory chart are: Then the following relation can be established: By establishing a system of equations using multiple sets of matching point pairs, the perspective transformation matrix H can be obtained. After obtaining the perspective transformation matrix H, for any candidate matching point pair, the predicted position of the feature point in the historical data entry image in the current data entry image can be calculated based on this matrix. Let the coordinates of the feature point in the historical data entry image be... The predicted coordinates in the current inventory chart are used Indicate, then Then, predict the location. The actual detected feature point locations in the current inventory chart Compare and calculate the pixel error between the two. Let the preset pixel threshold be... Then when If a candidate matching point pair is deemed to meet the geometric consistency requirement, it is identified as a true matching point pair. If it does not meet the above conditions, it is considered a false matching point pair and is removed. This process allows for the selection of true matching point pairs from all candidate matching point pairs, improving the accuracy of feature matching and providing a reliable basis for subsequent image similarity calculations.

[0051] Step A5: Calculate image similarity based on the actual matching point pairs.

[0052] Specifically, the similarity between two images is calculated by comprehensively considering the proportion of real matching point pairs among all candidate matching points and the similarity of feature vectors between each real matching point pair.

[0053] Optionally, calculating the image similarity based on real matching point pairs includes: determining a first similarity index based on the number of real matching point pairs and the number of candidate matching point pairs; calculating the cosine similarity of each pair of real matching point pairs, and calculating a second similarity index based on the cosine similarity; and calculating the image similarity based on the first similarity index and the second similarity index.

[0054] The number of true matching point pairs refers to the number of feature point pairs that, after pixel error filtering, are determined to meet the matching conditions among all candidate matching point pairs. The number of candidate matching point pairs refers to the total number of initial matching point pairs obtained by calculating the Euclidean distance between feature vectors during feature matching. The first similarity index is used to reflect the proportion of true matching point pairs among candidate matching point pairs, and it is used to characterize the consistency of the structural feature matching degree between two images. Cosine similarity is used to measure the similarity of the directions of two feature vectors. It is represented by the cosine value of the angle between the two feature vectors. The closer the cosine value is to 1, the more similar the two feature vectors are. The second similarity index is the average cosine similarity calculated based on the cosine similarity of the feature vectors of each true matching point pair, and it is used to characterize the overall similarity of the two images in feature description. Image similarity refers to the comprehensive similarity result obtained by fusing the first and second similarity indices, and it is used to represent the overall consistency between the current database image and the historical database images.

[0055] For example, the first similarity index is obtained based on the number of true matching point pairs and the number of candidate matching point pairs. The cosine similarity of each pair of true matching points is The second similarity index is Where k represents the number of true matching points, the image similarity is obtained by weighted fusion of the first similarity index and the second similarity index. The weight of each item can be adjusted according to the actual situation.

[0056] Step 205: Generate the current inventory data based on item information and image similarity.

[0057] Specifically, the current inventory data includes item information and image similarity. Additionally, the current inventory data may include pallet information, such as the current pallet identification code, whether the pallet is recyclable, and whether there are goods on the pallet. For example, if the pallet is empty, this field is marked "None"; if the pallet contains cigarettes, it is marked "Yes". In other words, the current inventory data can include item specifications, quantity, stacking shape, entry time, image similarity, current pallet identification code, whether the current pallet is recyclable, and whether the current pallet contains goods.

[0058] Step 206: When the image similarity value is less than the preset similarity threshold, control the stacker crane to transfer the pallet carrying the items to be inventoried to the second target location for manual verification.

[0059] The preset similarity threshold refers to a pre-defined standard for judging whether images are consistent. When the image similarity value is lower than this value, it indicates a significant difference between the current inventory image and historical inventory images. The second target location refers to a pre-defined work location for manual inspection or anomaly handling, such as a manual verification station or anomaly handling area. Manual verification refers to the process by which staff re-check and confirm the generated current inventory data to ensure its accuracy.

[0060] For example, assuming a preset similarity threshold of 90%, then when the image similarity value... If the system detects a significant discrepancy or anomaly between the current status of the goods on the pallet and the historical inventory records, it will control the stacker crane to move the pallet containing the items to be inventoried from the current storage location or work location to a second target location. Staff will then re-verify the actual status of the goods on the pallet to confirm the accuracy of the current inventory data generated by the system. If the current inventory data is inaccurate, it will be updated. This ensures timely manual intervention in case of anomalies or inconsistencies during image recognition or automatic inventory checks, thereby improving the accuracy and reliability of the inventory data.

[0061] In this embodiment, after the stacker crane places the pallet carrying the items to be inventoried at the first target position, the current pallet identification code identified by the scanning unit and the current inventory map collected by the acquisition unit are obtained. This accurately identifies the status of the current pallet and its goods, providing a precise data foundation for subsequent inventory operations. Simultaneously, automated data collection is achieved, eliminating the need for manual intervention and improving inventory efficiency and accuracy. Searching for the historical entry map corresponding to the current pallet identification code in historical inventory data ensures that the retrieved historical entry map and the pallet being inventoried belong to the same pallet, guaranteeing data consistency. Based on the current inventory map, the item information of the items to be inventoried is determined, automatically identifying key information about the goods on the pallet. This provides a foundation for generating accurate inventory data, reducing manual recording and improving the efficiency of inventory operations. The system improves efficiency and accuracy. Based on the current inventory map and historical inbound maps, image similarity is determined. Image similarity provides objective evidence for identifying anomalies or discrepancies in palletized goods, improving the reliability and traceability of inventory data. Based on item information and image similarity, current inventory data is generated. This integrates item information and image similarity to create complete inventory data, enabling automatic recording of palletized goods status, reducing manual intervention, and improving the accuracy and reliability of warehouse management. When the image similarity value is less than a preset similarity threshold, the stacker crane is controlled to transfer the pallet carrying the items to be inventoried to a second target location for manual verification. This ensures timely manual intervention in case of anomalies or inconsistencies during image recognition or automatic inventory, thereby improving the accuracy and reliability of inventory data.

[0062] The warehouse management system in this embodiment includes a management unit, a stacker crane, a data acquisition unit, and a scanning unit. The data acquisition unit and the scanning unit are electrically connected to the management unit. Figure 3 This is a schematic diagram of the structure of the automated inventory management device provided in an embodiment of the present invention, as shown below. Figure 3 As shown, the device includes: The image acquisition module 301 is used to acquire the current pallet identification code recognized by the scanning unit and the current inventory image acquired by the acquisition unit after the stacker crane places the pallet carrying the items to be inventoried at the first target position. Image search module 302 is used to search for the historical inbound image corresponding to the current pallet identification code in historical inventory data; The data generation module 303 is used to generate the current inventory data based on the current inventory map and the historical inventory map.

[0063] In one embodiment, the data generation module 303 is specifically used for: Based on the current inventory diagram, determine the item information of the items to be inventoried, which includes at least one of the following: item specifications, item quantity, stacking shape, and entry time; Determine image similarity based on the current inventory map and historical inbound maps; Generate the current inventory data based on item information and image similarity.

[0064] In one embodiment, the data generation module 303 determines image similarity based on the current inventory map and historical inventory maps, including: The current inventory map and the historical inventory map are preprocessed to generate a first grayscale image and a second grayscale image; Extract M first feature points from the first grayscale image and extract M second feature points from the second grayscale image, where M is a positive integer greater than or equal to 2; For each first feature point, calculate the Euclidean distance between the feature vector of the first feature point and the feature vector of each second feature point, and select the second feature point with the smallest Euclidean distance to form a candidate matching point pair with the first feature point; Filter out the true matching pairs from all candidate matching pairs; The image similarity is calculated based on the actual matching point pairs.

[0065] In one embodiment, selecting true matching point pairs from all candidate matching point pairs includes: Calculate the pixel error for each pair of candidate matching points; Candidate matching point pairs with pixel errors less than or equal to the pixel threshold are taken as true matching point pairs.

[0066] In one embodiment, calculating image similarity based on true matching point pairs includes: The first similarity index is determined based on the number of true matching point pairs and the number of candidate matching point pairs; Calculate the cosine similarity of each pair of real matching points, and calculate the second similarity index based on the cosine similarity. Image similarity is calculated based on the first similarity index and the second similarity index.

[0067] In one embodiment, after generating the current disk inventory data, the method further includes: When the image similarity value is less than the preset similarity threshold, the stacker crane is controlled to transfer the pallet carrying the items to be inventoried to the second target location for manual verification.

[0068] In one embodiment, the warehouse management system further includes a monitoring unit; the automated inventory device is also used for: The system monitors the stacker crane's operating status in real time and sends a notification message after determining a fault in the stacker crane based on its operating status. The notification message is used to remind the user to replace or repair the stacker crane.

[0069] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is merely an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the functional modules described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0070] The apparatus of this invention, after controlling the stacker crane to place a pallet carrying items to be inventoried at a first target position, acquires the current pallet identification code identified by the scanning unit and the current inventory map collected by the acquisition unit. This accurately identifies the status of the current pallet and its goods, providing a precise data foundation for subsequent inventory operations. Simultaneously, it achieves automated data collection without manual intervention, improving inventory efficiency and accuracy. Searching for the historical inbound map corresponding to the current pallet identification code in historical inventory data ensures that the retrieved historical inbound map and the pallet in the current inventory belong to the same pallet, guaranteeing data consistency. Generating current inventory data based on the current inventory map and the historical inbound map enables automatic recording of the current pallet's goods status, reducing manual statistical errors and improving the accuracy and reliability of warehouse management.

[0071] The following is for reference. Figure 4 It shows a schematic diagram of the structure of a computer system 400 suitable for implementing an electronic device according to embodiments of the present invention. Figure 4 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0072] like Figure 4 As shown, the computer system 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 402 or programs loaded from storage section 408 into random access memory (RAM) 403. The RAM 403 also stores various programs and data required for the operation of the computer system 400. The CPU 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0073] The following components are connected to I / O interface 405: input section 406 including keyboard, mouse, etc.; output section 407 including cathode ray tube, liquid crystal display, etc., and speakers, etc.; storage section 408 including hard disk, etc.; and communication section 409 including network interface card, such as modem, etc. Communication section 409 performs communication processing via a network such as the Internet. Drive 410 is also connected to I / O interface 405 as needed. Removable media 411, such as disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 410 as needed so that computer programs read from them can be installed into storage section 408 as needed.

[0074] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 409, and / or installed from removable medium 411. When the computer program is executed by central processing unit (CPU) 401, it performs the functions defined above in the system of this invention.

[0075] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical fiber, a portable compact disk read-only memory, an optical storage device, a magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, etc., or any suitable combination thereof.

[0076] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0077] The modules and / or units described in the embodiments of the present invention can be implemented in software or hardware. The described modules and / or units can also be housed in a processor; for example, a processor can be described as including an image acquisition module, an image search module, and a data generation module. The names of these modules do not necessarily limit the functionality of the module itself.

[0078] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, cause the device to include: After the stacker crane is controlled to place the pallet carrying the items to be inventoried at the first target position, the current pallet identification code identified by the scanning unit and the current inventory map collected by the acquisition unit are obtained; the historical inbound map corresponding to the current pallet identification code is searched in the historical inventory data; and the current inventory data is generated based on the current inventory map and the historical inbound map.

[0079] The technical solution of this invention, by controlling the stacker crane to place the pallet carrying the items to be inventoried at the first target position, obtains the current pallet identification code identified by the scanning unit and the current inventory map collected by the collection unit, which can accurately identify the status of the current pallet and its goods, providing an accurate data foundation for subsequent inventory operations. Simultaneously, it achieves automated data collection without manual intervention, improving inventory efficiency and accuracy. Searching for the historical inbound map corresponding to the current pallet identification code in historical inventory data ensures that the retrieved historical inbound map and the pallet in the current inventory belong to the same pallet, guaranteeing data consistency. Based on the current inventory map and the historical inbound map, current inventory data is generated, enabling automatic recording of the current pallet's goods status, reducing manual statistical errors, and improving the accuracy and reliability of warehouse management.

[0080] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the automated inventory method provided in any embodiment of this invention.

[0081] In the implementation of a computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​as well as conventional procedural programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including local area networks (LANs) or wide area networks (WANs), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0082] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and no limitation is imposed herein.

[0083] It should be noted that the collection, use, storage, sharing, and transfer of user personal information involved in the technical solution of this invention all comply with the provisions of relevant laws and regulations, and require notification to the user and obtaining the user's consent or authorization. Where applicable, user personal information has undergone de-identification and / or anonymization and / or encryption technical processing. In addition, a corresponding operation entry is provided for the user to choose to agree to or reject the automated decision result; if the user chooses to reject, the process proceeds to the expert decision-making process.

[0084] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An automated inventory counting method, characterized in that, The warehouse management system includes a management unit, a stacker crane, a data acquisition unit, and a scanning unit. The data acquisition unit and the scanning unit are electrically connected to the management unit. The method is applied to the management unit and includes: After the stacker crane is controlled to place the pallet carrying the items to be inventoried at the first target position, the current pallet identification code identified by the scanning unit and the current inventory map collected by the acquisition unit are obtained. Find the historical inbound image corresponding to the current pallet identifier code in the historical inventory data; Based on the current inventory map and the historical inventory map, generate the current inventory data.

2. The method according to claim 1, characterized in that, The step of generating current inventory data based on the current inventory map and the historical inventory map includes: Based on the current inventory diagram, determine the item information of the items to be inventoried, wherein the item information includes at least one of the following: item specifications, item quantity, stacking shape, and entry time; Based on the current inventory map and the historical inventory map, determine the image similarity; Based on the item information and the image similarity, the current inventory data is generated.

3. The method according to claim 2, characterized in that, The step of determining image similarity based on the current inventory map and the historical inventory map includes: The current inventory map and the historical inventory map are preprocessed respectively to generate a first grayscale image and a second grayscale image; M first feature points are extracted from the first grayscale image, and M second feature points are extracted from the second grayscale image, where M is a positive integer greater than or equal to 2; For each first feature point, calculate the Euclidean distance between the feature vector of the first feature point and the feature vector of each second feature point, and select the second feature point with the smallest Euclidean distance to form a candidate matching point pair with the first feature point; Filter out the true matching pairs from all candidate matching pairs; The image similarity is calculated based on the actual matching point pairs.

4. The method according to claim 3, characterized in that, The step of filtering out true matching point pairs from all candidate matching point pairs includes: Calculate the pixel error for each pair of candidate matching points; Candidate matching point pairs with pixel errors less than or equal to the pixel threshold are taken as the true matching point pairs.

5. The method according to claim 3, characterized in that, The step of calculating the image similarity based on the true matching point pairs includes: The first similarity index is determined based on the number of actual matching point pairs and the number of candidate matching point pairs; Calculate the cosine similarity of each pair of real matching points, and calculate the second similarity index based on the cosine similarity. The image similarity is calculated based on the first similarity index and the second similarity index.

6. The method according to claim 2, characterized in that, After generating the current disk inventory data, the method further includes: When the image similarity value is less than a preset similarity threshold, the stacker crane is controlled to transfer the pallet carrying the items to be inventoried to the second target location for manual verification.

7. The method according to claim 1, characterized in that, The warehouse management system further includes a monitoring unit; the method further includes: The system monitors the operating status of the stacker crane in real time, and sends a prompt message after determining that the stacker crane is faulty based on the operating status. The prompt message is used to remind the user to replace or repair the stacker crane.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the automated inventory method as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the automated inventory method as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the automated inventory method as described in any one of claims 1 to 7.

Images