Warehouse management method and device, computer device and storage medium

Abstract

This application relates to a warehouse management method, apparatus, computer equipment, storage medium, and computer program product. The method includes: acquiring multiple images to be identified from a video queue, each image including at least one object to be identified; acquiring target information of the object to be identified; verifying the target information; and generating a verification result corresponding to the object to be identified; wherein the information verification verifies the object's access rights to the warehouse; when the verification result indicates successful verification, performing orientation detection on the object to be identified to determine its motion state; wherein the motion state includes: entry and exit; and generating a corresponding warehouse record based on the object's motion state. This method can improve the accuracy of identifying items entering and leaving the warehouse.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a warehouse management method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0002] With the rapid development of the logistics industry, the daily management of logistics involves a massive amount of warehouse management work.

[0003] Traditionally, RFID (Radio Frequency Identification) card readers are installed by drilling holes in the ground to sense entry and exit events.

[0004] However, in traditional technologies, the environment of each warehouse is different, and RFID is affected by interference from surrounding metal, resulting in low identification accuracy. Summary of the Invention

[0005] Therefore, it is necessary to provide a warehouse management method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the accuracy of identifying items entering and leaving the warehouse, in order to address the aforementioned technical problems.

[0006] Firstly, this application provides a warehouse management method. The method includes:

[0007] Acquire multiple images to be identified from the video queue, each image containing at least one object to be identified;

[0008] The system acquires target information of the object to be identified, performs information verification on the target information, and generates verification results for the corresponding object to be identified. Among these, information verification involves verifying the object's access permissions to and from the warehouse.

[0009] When the verification result indicates successful verification, orientation detection is performed on the object to be identified to determine its motion state; the motion state includes: entry and exit.

[0010] Based on the motion state of the object to be identified, a corresponding warehouse record is generated.

[0011] In one embodiment, before acquiring multiple images to be identified from the video queue, the method further includes:

[0012] Multiple image information at the same time are read using a thread-based approach; the image information includes: the image to be identified, and the viewpoint identifier;

[0013] Based on the preset viewpoint order and viewpoint identifier, the queue order corresponding to multiple images to be identified is obtained;

[0014] Multiple images to be identified are stored in a video queue according to the queue order; wherein, the acquisition time of multiple images to be identified in a video queue is consistent.

[0015] In one embodiment, orientation detection is performed on the object to be identified to determine its motion state, including:

[0016] Obtain the first and second crash lines; wherein the distance between the first crash line and the warehouse is greater than the distance between the second crash line and the warehouse;

[0017] Obtain the region information where the object to be identified is located from the target information, and determine the region where the object to be identified is located based on the region information;

[0018] When the area where the object to be identified is located overlaps with the first collision line, a corresponding first collision line record is generated; when the area where the object to be identified is located overlaps with the second collision line, a corresponding second collision line record is generated.

[0019] Based on the first and second collision records, the motion state of the object to be identified is determined.

[0020] In one embodiment, the motion state of the object to be identified is determined based on the first and second collision records, including:

[0021] When the area where the object to be identified is located overlaps with the first collision line, the historical collision line record corresponding to the object to be identified is obtained; wherein, the historical collision line record is the first or second collision line record of the object to be identified before the current moment;

[0022] When the historical collision record is the second collision record, the direction of movement of the object to be identified is from the second collision line to the first collision line, and the movement state of the object to be identified is leaving the warehouse.

[0023] In one embodiment, the motion state of the object to be identified is determined based on the first and second collision records, including:

[0024] When the area where the object to be identified is located overlaps with the second collision line, the historical collision line record corresponding to the object to be identified is obtained; wherein, the historical collision line record is the first or second collision line record of the object to be identified before the current moment;

[0025] When the historical collision record is the first collision record, the direction of movement of the object to be identified is from the first collision line to the second collision line, and the movement state of the object to be identified is "entered into the database".

[0026] In one embodiment, a corresponding warehouse record is generated based on the motion state of the object to be identified, including:

[0027] When the movement state is "entering the warehouse", a corresponding entry record is generated based on the target information of the object to be identified, the entry record is stored in the warehouse record, and the storage quantity in the warehouse is incremented by 1;

[0028] When the movement status is outbound, multiple warehouse records in the warehouse are queried based on the target information of the object to be identified, the inbound record corresponding to the target information is marked as outbound, and the storage quantity in the warehouse is decremented by 1.

[0029] In one embodiment, the method further includes:

[0030] An alarm message is issued when the verification result corresponds to a verification failure.

[0031] Secondly, this application also provides a warehouse management device. The device includes:

[0032] The image acquisition module is used to acquire multiple images to be identified from the video queue, and each image to be identified includes at least one object to be identified.

[0033] The information verification module is used to obtain the target information of the object to be identified, verify the target information, and generate the corresponding verification result for the object to be identified; among them, the information verification is to verify the permission of the object to be identified to enter and exit the warehouse.

[0034] The orientation detection module is used to perform orientation detection on the object to be identified when the verification result corresponds to successful verification, and to determine the motion state of the object to be identified; the motion state includes: entering the warehouse and leaving the warehouse;

[0035] The warehouse record generation module is used to generate corresponding warehouse records based on the movement state of the object to be identified.

[0036] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in any of the above embodiments.

[0037] Fourthly, this application also provides a computer device readable storage medium. The computer device readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the method described in any of the above embodiments.

[0038] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in any of the above embodiments.

[0039] The aforementioned warehouse management method, apparatus, computer equipment, storage medium, and computer program products first acquire multiple images to be identified from a video queue, each image including at least one object to be identified. Then, target information of the object to be identified is acquired, and this target information is verified to generate a verification result for the corresponding object; this verification verifies the object's access rights to the warehouse. Further, when the verification result indicates successful verification, orientation detection is performed on the object to be identified to determine its motion state; this motion state includes entry and exit. Finally, based on the object's motion state, a corresponding warehouse record is generated. By performing information verification and orientation detection on the images to be identified in the video queue, interference from metal can be avoided in the identification of items entering and leaving the warehouse, thus improving the accuracy of item entry and exit identification. Attached Figure Description

[0040] Figure 1 This is a diagram illustrating the application environment of a warehouse management method in one embodiment;

[0041] Figure 2 This is a flowchart illustrating a warehouse management method in one embodiment;

[0042] Figure 3 This is a schematic diagram of the process of obtaining the video queue in one embodiment;

[0043] Figure 4 This is a flowchart illustrating a method for orientation detection of an object to be identified in another embodiment;

[0044] Figure 5 This is a schematic diagram of the warehouse management architecture in another embodiment;

[0045] Figure 6 This is a structural block diagram of a warehouse management device in one embodiment;

[0046] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0048] The warehouse management method provided in this application embodiment can be applied to, for example, Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on a cloud or other network server. Server 104 provides a warehouse management environment for terminal 102, and the server 104 communicates and interacts with terminal 102 to enter the warehouse management environment. First, server 104 acquires multiple images to be identified from a video queue through terminal 102, each image including at least one object to be identified. Then, server 104 acquires the target information of the object to be identified, performs information verification on the target information, and generates a verification result for the corresponding object; the information verification verifies the object's access rights to the warehouse. Further, when the verification result indicates successful verification, server 104 performs orientation detection on the object to be identified to determine its motion state; the motion state includes: entry and exit. Finally, server 104 can generate a corresponding warehouse record based on the motion state of the object to be identified. Terminal 102 can be multiple cameras, multiple robots carrying cameras, or other electronic devices with recording capabilities. Server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0049] The warehouse management method provided in this application can be implemented on a single side of a server or terminal, or it can be implemented in a system including both a terminal and a server, through the interaction between the terminal and the server.

[0050] In one embodiment, such as Figure 2 As shown, a warehouse management method is provided. Taking the application of this method to a single server implementation as an example, it includes the following steps 202 to 208.

[0051] Step 202: Obtain multiple images to be identified from the video queue, each image including at least one object to be identified.

[0052] In this embodiment, the acquisition times of multiple images to be identified in the video queue are consistent.

[0053] In this embodiment, the multiple images to be identified in the video queue are images captured or recorded by multiple terminals in the warehouse.

[0054] Step 204: Obtain the target information of the object to be identified, perform information verification on the target information, and generate the corresponding verification result for the object to be identified; wherein, the information verification is to verify the permission of the object to be identified to enter and exit the warehouse.

[0055] In this embodiment, each object to be identified carries target information, which may include, but is not limited to, an information identifier. Each object to be identified has a unique information identifier.

[0056] In another embodiment, the server can query multiple images to be identified based on information identifiers to obtain the motion trajectory of the object to be identified corresponding to the information identifier.

[0057] In this embodiment, the target information may further include permission information. The server can perform information verification on the object to be identified based on the permission information to determine whether the object to be identified has the permission to enter or exit the database. When the object to be identified has the permission to enter or exit the database, the generated verification result corresponds to verification success; when the object to be identified does not have the permission to enter or exit the database, the generated verification result corresponds to verification failure.

[0058] In another embodiment, the target information may include, but is not limited to, storage location information. The server can match the storage location information with the current warehouse, and when a match is successful, the object to be identified has the authority to enter and exit the warehouse.

[0059] In this embodiment, the target information may also include Maker information, and the server can use the Maker detection algorithm to verify the information of the object to be identified.

[0060] In this embodiment, the target information of the item (the target to be identified) can be a pre-printed label, which is pasted on top of the top box so that the server can detect the target object using the Maker detection algorithm.

[0061] In this embodiment, the warehouse clerk can enter the available storage location numbers to be shelved in the property management system. The server can then use the Aruco algorithm to overlay information based on the item information and the aforementioned available storage location numbers to generate a tag for the corresponding item (the target to be identified), i.e., the target information.

[0062] Step 206: When the verification result corresponds to successful verification, the orientation detection of the object to be identified is performed to determine the motion state of the object to be identified; wherein, the motion state includes: entering the warehouse and leaving the warehouse.

[0063] In this embodiment, when the verification result corresponds to successful verification, the object to be identified has the permission to enter and exit the database, and the server can perform orientation detection on the object to be identified.

[0064] In this embodiment, the server can obtain the motion trajectory of the object to be identified in the video queue, perform direction detection based on the motion trajectory of the object to be identified, and determine the motion state of the object to be identified.

[0065] In another embodiment, the server can also determine the motion state of the object to be identified by dividing the collision zone and the area where the object to be identified is located in the video queue.

[0066] Step 208: Generate the corresponding warehouse record based on the motion state of the object to be identified.

[0067] In this embodiment, when the movement state of the object to be identified is "entering the warehouse", a corresponding entry record is generated and the storage quantity in the warehouse is incremented by 1; when the movement state is "leaving the warehouse", a corresponding exit record is generated and the storage quantity in the warehouse is decremented by 1.

[0068] In the aforementioned warehouse management method, firstly, multiple images to be identified are acquired from a video queue, each image containing at least one object to be identified. Then, target information of the object to be identified is acquired, and this information is verified to generate a corresponding verification result for the object. This verification verifies the object's access rights to the warehouse. Further, when the verification result indicates successful verification, orientation detection is performed on the object to determine its motion state, which includes both entry and exit. Finally, based on the object's motion state, a corresponding warehouse record is generated. By performing information verification and orientation detection on the images to be identified in the video queue, interference from metal can be avoided, improving the accuracy of item entry and exit identification.

[0069] In some embodiments, such as Figure 3 As shown, before acquiring multiple images to be recognized from the video queue, the above method may further include: reading multiple image information at the same time using a thread; wherein the image information includes: the image to be recognized, and a viewpoint identifier; obtaining the queue order corresponding to the multiple images to be recognized based on a preset viewpoint order and viewpoint identifier; storing the multiple images to be recognized into the video queue according to the queue order; wherein the acquisition time corresponding to the multiple images to be recognized in a video queue is consistent.

[0070] In this embodiment, the server can use a thread-based approach to read multiple image information captured simultaneously by the terminal. The terminal can be an electronic device with recording capabilities, such as multiple cameras or multiple robots equipped with cameras. For example, when the terminal consists of multiple cameras, the server can use a thread-based approach to read multiple image information captured simultaneously by all cameras. This application supports determining the motion state of objects using video streams pushed by multiple cameras. By using a queue algorithm, multiple video streams can be extracted, maximizing resource utilization.

[0071] In this embodiment, as Figure 3 As shown, the number of images to be recognized in a video queue is consistent with the number of cameras.

[0072] In this embodiment, the terminal has a viewpoint identifier. For example, when the terminal has multiple cameras, each camera has a unique viewpoint identifier.

[0073] In this embodiment, the server can determine a preset viewpoint order based on the terminal's viewpoint identifier and a preset viewpoint identifier order, and then obtain the queue order corresponding to multiple images to be recognized based on the preset viewpoint order. For example, when the terminal has 5 cameras (camera 1, camera 2, camera 3, camera 4, and camera 5), ​​the viewpoint identifier corresponding to camera 1 is a, the viewpoint identifier corresponding to camera 2 is c, the viewpoint identifier corresponding to camera 3 is b, the viewpoint identifier corresponding to camera 4 is e, the viewpoint identifier corresponding to camera 1 is d, and the preset viewpoint identifier order is abcde, based on the viewpoint identifier of each camera and the preset viewpoint identifier order, the preset viewpoint order of the 5 cameras can be obtained as camera 1-camera 3-camera 2-camera 5-camera 4. Furthermore, when the images captured by the above 5 cameras at time A are: image 11 (captured by camera 1), image 12 (captured by camera 2), image 13 (captured by camera 3), image 14 (captured by camera 4), and image 15 (captured by camera 5), ​​the queue order corresponding to the multiple images to be identified at time A is: image 11-image 13-image 12-image 15-image 14.

[0074] In this embodiment, the queue order corresponding to the multiple images to be identified is consistent with the order of the video queue corresponding to the multiple images to be identified.

[0075] In some embodiments, performing orientation detection on the object to be identified to determine its motion state may include: acquiring a first collision line and a second collision line; wherein the distance between the first collision line and the warehouse is greater than the distance between the second collision line and the warehouse; acquiring the area information of the object to be identified in the target information, and obtaining the area where the object to be identified is located based on the area information; generating a corresponding first collision line record when the area where the object to be identified is located overlaps with the first collision line; generating a corresponding second collision line record when the area where the object to be identified is located overlaps with the second collision line; and determining the motion state of the object to be identified based on the first collision line record and the second collision line record.

[0076] In this embodiment, the server can preset the areas of the first and second collision lines, wherein the distance between the first collision line and the warehouse is greater than the distance between the second collision line and the warehouse.

[0077] In this embodiment, the server can determine the location of the object to be identified based on the queue order of multiple images to be identified in the video queue.

[0078] In this embodiment, the server can identify the positional relationship between the area where the object to be identified is located and the area where the first line of collision is located, as well as the positional relationship between the area where the object to be identified is located and the area where the second line of collision is located, based on the preset area where the first line of collision is located, the preset area where the second line of collision is located, and the area where the object to be identified is located.

[0079] When the area where the object to be identified is located overlaps with the area of ​​the first collision line, or when the area where the object to be identified is located overlaps with the area of ​​the second collision line, the server can determine the motion state of the object to be identified based on the first collision line record and the second collision line record corresponding to the object to be identified.

[0080] In some embodiments, determining the motion state of the object to be identified based on the first and second collision records may include: when the area where the object to be identified is located overlaps with the first collision line, obtaining the historical collision record corresponding to the object to be identified; wherein, the historical collision record is the first or second collision record of the object to be identified before the current moment; when the historical collision record is the second collision record, the motion direction of the object to be identified is from the second collision line to the first collision line, and the motion state of the object to be identified is out of the warehouse.

[0081] In this embodiment, when the area where the object to be identified is located overlaps with the first collision line, the historical collision line record corresponding to the object to be identified is obtained. The historical collision line record is obtained by querying the previous collision line record corresponding to the object to be identified, starting from the time the image to be identified was acquired, in the opposite direction of time flow; the previous collision line record can be either the first collision line record or the second collision line record.

[0082] In this embodiment, when the area where the object to be identified is located overlaps with the first collision line and the historical collision line record is the second collision line record, the movement direction of the object to be identified is from the second collision line to the first collision line (i.e., moving from a position close to the warehouse to a position far away from the warehouse), and the movement state of the object to be identified is out of the warehouse.

[0083] In another embodiment, after the server generates the warehouse record corresponding to the object to be identified, it can delete the historical collision records of the object to be identified. When the area where the object to be identified is located overlaps with the first collision line, the server can query whether the area where the object to be identified is located overlapped with the area of ​​the second collision line before overlapping with the area of ​​the first collision line. If the area where the object to be identified is located overlapped with the area of ​​the second collision line before overlapping with the area of ​​the first collision line, then the movement direction of the object to be identified is from the second collision line to the first collision line (i.e., moving from a position closer to the warehouse to a position farther away from the warehouse), and the movement state of the object to be identified is out of the warehouse.

[0084] In some embodiments, the server can divide the collision zone in different scenarios to adapt to applications requiring direction recognition in different scenarios. For example... Figure 4 As shown, the server can set the area corresponding to the first collision line as a red area and the area corresponding to the second collision line as a yellow area. When the server detects an object to be identified in the red area (collision with the red area) through marker detection, it generates the corresponding first collision line record, that is, writes the marker information to the red queue; when the server detects an object to be identified in the yellow area (collision with the yellow area) through marker detection, it generates the corresponding second collision line record, that is, writes the marker information to the yellow queue.

[0085] In this embodiment, when the server detects that the object to be identified is in the red area through marker detection, the server can first query the yellow queue to check whether there is a second collision record of the object to be identified (whether it is in the yellow area queue). If it exists, the movement direction of the object to be identified is outbound; if it does not exist, the marker information is written to the red queue.

[0086] In some embodiments, determining the motion state of the object to be identified based on the first and second collision records may include: when the area where the object to be identified is located overlaps with the second collision line, obtaining the historical collision record corresponding to the object to be identified; wherein, the historical collision record is the first or second collision record of the object to be identified before the current moment; when the historical collision record is the first collision record, the motion direction of the object to be identified is from the first collision line to the second collision line, and the motion state of the object to be identified is "entered into the database".

[0087] In this embodiment, when the area where the object to be identified is located overlaps with the second collision line, the historical collision line record corresponding to the object to be identified is obtained. The historical collision line record is obtained by querying the previous collision line record corresponding to the object to be identified, starting from the time the image to be identified was acquired, in the opposite direction of time flow; the previous collision line record can be either the first collision line record or the second collision line record.

[0088] In this embodiment, when the area where the object to be identified is located overlaps with the second collision line and the historical collision line record is the first collision line record, the movement direction of the object to be identified is from the first collision line to the second collision line (i.e., moving from a position close to the warehouse to a position far away from the warehouse), and the movement state of the object to be identified is entering the warehouse.

[0089] In another embodiment, after the server generates the warehouse record corresponding to the object to be identified, it can delete the historical collision records of the object to be identified. When the area where the object to be identified is located overlaps with the second collision line, the server can query whether the area where the object to be identified is located overlapped with the area of ​​the first collision line before overlapping with the area of ​​the second collision line. If the area where the object to be identified is located overlapped with the area of ​​the first collision line before overlapping with the area of ​​the second collision line, then the movement direction of the object to be identified is from the first collision line to the second collision line (i.e., moving from a position far from the warehouse to a position close to the warehouse), and the movement state of the object to be identified is "entering the warehouse".

[0090] In some embodiments, the server can divide the collision zone in different scenarios to adapt to applications requiring direction recognition in different scenarios. For example... Figure 4 As shown, the server can set the area corresponding to the first collision line as a red area and the area corresponding to the second collision line as a yellow area. When the server detects an object to be identified in the red area (collision with the red area) through marker detection, it generates the corresponding first collision line record, that is, writes the marker information to the red queue; when the server detects an object to be identified in the yellow area (collision with the yellow area) through marker detection, it generates the corresponding second collision line record, that is, writes the marker information to the yellow queue.

[0091] In this embodiment, when the server detects that the object to be identified is in the yellow area through marker detection, the server can first query the red queue to check if there is a first collision record of the object to be identified (whether it is in the red area queue). If it exists, the movement direction of the object to be identified is to be entered into the database; if it does not exist, the marker information is written to the yellow queue.

[0092] In some embodiments, generating a corresponding warehouse record based on the motion state of the object to be identified may include: when the motion state is inbound, generating a corresponding inbound record based on the target information of the object to be identified, storing the inbound record in the warehouse record, and incrementing the storage quantity in the warehouse by 1; when the motion state is outbound, querying multiple warehouse records in the warehouse based on the target information of the object to be identified, marking the inbound record corresponding to the target information as outbound, and decrementing the storage quantity in the warehouse by 1.

[0093] In another embodiment, after the server generates the warehouse record corresponding to the object to be identified, it can delete the historical collision records of the object to be identified.

[0094] In this embodiment, when the movement state of the object to be identified is out of the warehouse, the server can also delete the inbound information corresponding to the outbound information of the object to be identified, which can avoid the problem of overlapping inbound information when the object to be identified enters the warehouse next time.

[0095] In another embodiment, the target information may further include: item information. The server can generate corresponding warehouse records based on the item information and the movement state of the object to be identified.

[0096] In some embodiments, the above method may further include: issuing an alarm message when the verification result corresponds to a verification failure.

[0097] In this embodiment, as Figure 5 As shown, the server can issue alarm messages via lights, voice, or text. For example, indicator lights can be pre-installed at preset locations on the warehouse door. When the verification result indicates a failure, an error or alarm can be issued via light (such as flashing red light); when the verification result indicates a success, feedback can also be provided via light (such as green light).

[0098] In this embodiment, as Figure 5 As shown, when the verification result is successful, the server can control the roller shutter door to open automatically based on the I / O (Input / Output) controller connected to the roller shutter door (warehouse door).

[0099] In another embodiment, the server can perform image enhancement processing on the image to be identified before verifying the information of the object to be identified, which can reduce the interference of environmental factors on information verification and improve the accuracy of information verification.

[0100] In another embodiment, the server processes the image information in the video queue. After processing all the images to be identified from all perspectives in a video queue, it can acquire another video queue through multiple cameras. In each video queue, the acquisition time of the multiple images to be identified is consistent.

[0101] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0102] Based on the same inventive concept, this application also provides a warehouse management device for implementing the warehouse management method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more warehouse management device embodiments provided below can be found in the limitations of the warehouse management method described above, and will not be repeated here.

[0103] In one embodiment, such as Figure 6 As shown, a warehouse management device is provided, including: an image acquisition module 602, an information verification module 604, a direction detection module 606, and a warehouse record generation module 608, wherein:

[0104] The image acquisition module 602 is used to acquire multiple images to be identified in the video queue, and each image to be identified includes at least one object to be identified.

[0105] The information verification module 604 is used to obtain the target information of the object to be identified, perform information verification on the target information, and generate the corresponding verification result of the object to be identified; among them, the information verification is to verify the permission of the object to be identified to enter and exit the warehouse.

[0106] The orientation detection module 606 is used to perform orientation detection on the object to be identified when the verification result corresponds to successful verification, and to determine the motion state of the object to be identified; wherein, the motion state includes: entering the warehouse and leaving the warehouse.

[0107] The warehouse record generation module 608 is used to generate corresponding warehouse records based on the motion state of the object to be identified.

[0108] In one embodiment, before the image acquisition module 602, the above-mentioned apparatus may further include:

[0109] The image information reading module is used to read multiple image information at the same time using a thread; the image information includes: the image to be identified, and the viewpoint identifier.

[0110] The queue order determination module is used to obtain the queue order corresponding to multiple images to be identified based on a preset view order and view identifier.

[0111] The queue storage module is used to store multiple images to be recognized into a video queue in the order of the queue; wherein, the acquisition time of multiple images to be recognized in a video queue is consistent.

[0112] In one embodiment, the orientation detection module 606 may include:

[0113] The "Cross-Line Acquisition Submodule" is used to acquire the first and second cross-lines; wherein the distance between the first cross-line and the warehouse is greater than the distance between the second cross-line and the warehouse.

[0114] The region determination submodule is used to obtain the region information of the object to be identified in the target information, and to obtain the region where the object to be identified is located based on the region information.

[0115] The collision record generation submodule is used to generate a corresponding first collision record when the area where the object to be identified is located overlaps with the first collision line; and to generate a corresponding second collision record when the area where the object to be identified is located overlaps with the second collision line.

[0116] The motion state determination submodule is used to determine the motion state of the object to be identified based on the first and second collision records.

[0117] In one embodiment, the motion state determination submodule may include:

[0118] The first historical collision record acquisition unit is used to acquire the historical collision record corresponding to the object to be identified when the area where the object to be identified is located overlaps with the first collision line; wherein, the historical collision record is the first collision record or the second collision record of the object to be identified before the current moment.

[0119] The first judgment unit is used to determine that when the historical collision record is the second collision record, the movement direction of the object to be identified is from the second collision line to the first collision line, and the movement state of the object to be identified is leaving the warehouse.

[0120] In one embodiment, the motion state determination submodule may further include:

[0121] The second historical collision record acquisition unit is used to acquire the historical collision record corresponding to the object to be identified when the area where the object to be identified is located overlaps with the second collision line; wherein, the historical collision record is the first or second collision record of the object to be identified before the current moment.

[0122] The second judgment unit is used when the historical collision record is the first collision record, the movement direction of the object to be identified is from the first collision record to the second collision record, and the movement state of the object to be identified is "entered into the database".

[0123] In one embodiment, the warehouse record generation module 608 may include:

[0124] The inbound record submodule is used to generate a corresponding inbound record based on the target information of the object to be identified when the movement state is inbound, store the inbound record in the warehouse record, and increment the storage quantity in the warehouse by 1.

[0125] The outbound record submodule is used to query multiple warehouse records based on the target information of the object to be identified when the movement status is outbound, mark the inbound record corresponding to the target information as outbound, and decrement the storage quantity in the warehouse by 1.

[0126] In one embodiment, the above-described apparatus may further include:

[0127] The alarm module is used to issue an alarm message when the verification result corresponds to a verification failure.

[0128] Each module in the aforementioned warehouse management device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0129] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores data such as first and second collision records. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When executed by the processor, the computer program implements a warehouse management method.

[0130] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0131] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: acquiring multiple images to be identified from a video queue, each image including at least one object to be identified; acquiring target information of the object to be identified, performing information verification on the target information, and generating a verification result corresponding to the object to be identified; wherein, the information verification is to verify the permission of the object to be identified to enter and exit a warehouse; when the verification result corresponds to successful verification, performing orientation detection on the object to be identified to determine the motion state of the object to be identified; wherein, the motion state includes: entering the warehouse and leaving the warehouse; and generating a corresponding warehouse record based on the motion state of the object to be identified.

[0132] In one embodiment, before the processor executes the computer program to acquire multiple images to be identified from the video queue, the following steps may also be performed: reading multiple image information at the same time using a thread; wherein, the image information includes: images to be identified, and viewpoint identifiers; obtaining the queue order corresponding to the multiple images to be identified based on a preset viewpoint order and viewpoint identifiers; storing the multiple images to be identified into the video queue according to the queue order; wherein, the acquisition time corresponding to the multiple images to be identified in a video queue is consistent.

[0133] In one embodiment, when the processor executes a computer program to perform orientation detection on the object to be identified and determine the motion state of the object, it may include: acquiring a first collision line and a second collision line; wherein the distance between the first collision line and the warehouse is greater than the distance between the second collision line and the warehouse; acquiring the area information where the object to be identified is located from the target information, and obtaining the area where the object to be identified is located based on the area information; generating a corresponding first collision line record when the area where the object to be identified is located overlaps with the first collision line; generating a corresponding second collision line record when the area where the object to be identified is located overlaps with the second collision line; and determining the motion state of the object to be identified based on the first collision line record and the second collision line record.

[0134] In one embodiment, when the processor executes a computer program, it determines the motion state of the object to be identified based on the first and second collision records. This may include: when the area where the object to be identified is located overlaps with the first collision record, obtaining the historical collision record corresponding to the object to be identified; wherein, the historical collision record is either the first or second collision record of the object to be identified before the current moment; when the historical collision record is the second collision record, the motion direction of the object to be identified is from the second collision record to the first collision record, and the motion state of the object to be identified is out of the warehouse.

[0135] In one embodiment, when the processor executes a computer program, it determines the motion state of the object to be identified based on the first and second collision records. This may include: when the area where the object to be identified is located overlaps with the second collision line, obtaining the historical collision record corresponding to the object to be identified; wherein, the historical collision record is the first or second collision record of the object to be identified before the current moment; when the historical collision record is the first collision record, the motion direction of the object to be identified is from the first collision line to the second collision line, and the motion state of the object to be identified is "entering the database".

[0136] In one embodiment, when the processor executes a computer program, it generates a corresponding warehouse record based on the motion state of the object to be identified. This may include: when the motion state is "inbound", generating a corresponding inbound record based on the target information of the object to be identified, storing the inbound record in the warehouse's warehouse record, and incrementing the storage quantity in the warehouse by 1; when the motion state is "outbound", querying multiple warehouse records in the warehouse based on the target information of the object to be identified, marking the inbound record corresponding to the target information as outbound, and decrementing the storage quantity in the warehouse by 1.

[0137] In one embodiment, when the processor executes the computer program, it may also perform the following steps: when the verification result corresponds to a verification failure, an alarm message is issued.

[0138] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it performs the following steps: acquiring multiple images to be identified from a video queue, each image including at least one object to be identified; acquiring target information of the object to be identified, performing information verification on the target information, and generating a verification result corresponding to the object to be identified; wherein, the information verification is a verification of the object's access rights to enter and exit the warehouse; when the verification result corresponds to successful verification, performing orientation detection on the object to be identified to determine its motion state; wherein, the motion state includes: entering and exiting the warehouse; and generating a corresponding warehouse record based on the motion state of the object to be identified.

[0139] In one embodiment, before the computer program is executed by the processor to acquire multiple images to be identified in the video queue, the following steps may be performed: reading multiple image information at the same time using a thread; wherein the image information includes: images to be identified, and viewpoint identifiers; obtaining the queue order corresponding to the multiple images to be identified based on a preset viewpoint order and viewpoint identifiers; storing the multiple images to be identified into the video queue according to the queue order; wherein the acquisition time corresponding to the multiple images to be identified in a video queue is consistent.

[0140] In one embodiment, when a computer program is executed by a processor, it performs orientation detection on the object to be identified and determines the motion state of the object. This may include: acquiring a first collision line and a second collision line; wherein the distance between the first collision line and the warehouse is greater than the distance between the second collision line and the warehouse; acquiring the area information of the object to be identified from the target information, and obtaining the area where the object to be identified is located based on the area information; generating a corresponding first collision line record when the area where the object to be identified is located overlaps with the first collision line; generating a corresponding second collision line record when the area where the object to be identified is located overlaps with the second collision line; and determining the motion state of the object to be identified based on the first collision line record and the second collision line record.

[0141] In one embodiment, when the computer program is executed by the processor, determining the motion state of the object to be identified based on the first and second collision records may include: when the area where the object to be identified is located overlaps with the first collision line, obtaining the historical collision record corresponding to the object to be identified; wherein, the historical collision record is the first or second collision record of the object to be identified before the current moment; when the historical collision record is the second collision record, the motion direction of the object to be identified is from the second collision line to the first collision line, and the motion state of the object to be identified is out of the warehouse.

[0142] In one embodiment, when the computer program is executed by the processor, determining the motion state of the object to be identified based on the first and second collision records may include: when the area where the object to be identified is located overlaps with the second collision line, obtaining the historical collision record corresponding to the object to be identified; wherein, the historical collision record is the first or second collision record of the object to be identified before the current moment; when the historical collision record is the first collision record, the motion direction of the object to be identified is from the first collision line to the second collision line, and the motion state of the object to be identified is "entering the database".

[0143] In one embodiment, when the computer program is executed by the processor, it generates a corresponding warehouse record based on the motion state of the object to be identified. This may include: when the motion state is "inbound", generating a corresponding inbound record based on the target information of the object to be identified, storing the inbound record in the warehouse's warehouse record, and incrementing the storage quantity in the warehouse by 1; when the motion state is "outbound", querying multiple warehouse records in the warehouse based on the target information of the object to be identified, marking the inbound record corresponding to the target information as outbound, and decrementing the storage quantity in the warehouse by 1.

[0144] In one embodiment, when the computer program is executed by the processor, it may also perform the following steps: when the verification result corresponds to a verification failure, an alarm message is issued.

[0145] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps: acquiring multiple images to be identified from a video queue, each image including at least one object to be identified; acquiring target information of the object to be identified, performing information verification on the target information, and generating a verification result corresponding to the object to be identified; wherein, the information verification is a verification of the object's access rights to enter and exit a warehouse; when the verification result corresponds to successful verification, performing orientation detection on the object to be identified to determine its motion state; wherein, the motion state includes: entry and exit; and generating a corresponding warehouse record based on the motion state of the object to be identified.

[0146] In one embodiment, before the computer program is executed by the processor to acquire multiple images to be identified in the video queue, the following steps may be performed: reading multiple image information at the same time using a thread; wherein the image information includes: images to be identified, and viewpoint identifiers; obtaining the queue order corresponding to the multiple images to be identified based on a preset viewpoint order and viewpoint identifiers; storing the multiple images to be identified into the video queue according to the queue order; wherein the acquisition time corresponding to the multiple images to be identified in a video queue is consistent.

[0147] In one embodiment, when a computer program is executed by a processor, it performs orientation detection on the object to be identified and determines the motion state of the object. This may include: acquiring a first collision line and a second collision line; wherein the distance between the first collision line and the warehouse is greater than the distance between the second collision line and the warehouse; acquiring the area information of the object to be identified from the target information, and obtaining the area where the object to be identified is located based on the area information; generating a corresponding first collision line record when the area where the object to be identified is located overlaps with the first collision line; generating a corresponding second collision line record when the area where the object to be identified is located overlaps with the second collision line; and determining the motion state of the object to be identified based on the first collision line record and the second collision line record.

[0148] In one embodiment, when the computer program is executed by the processor, determining the motion state of the object to be identified based on the first and second collision records may include: when the area where the object to be identified is located overlaps with the first collision line, obtaining the historical collision record corresponding to the object to be identified; wherein, the historical collision record is the first or second collision record of the object to be identified before the current moment; when the historical collision record is the second collision record, the motion direction of the object to be identified is from the second collision line to the first collision line, and the motion state of the object to be identified is out of the warehouse.

[0149] In one embodiment, when the computer program is executed by the processor, determining the motion state of the object to be identified based on the first and second collision records may include: when the area where the object to be identified is located overlaps with the second collision line, obtaining the historical collision record corresponding to the object to be identified; wherein, the historical collision record is the first or second collision record of the object to be identified before the current moment; when the historical collision record is the first collision record, the motion direction of the object to be identified is from the first collision line to the second collision line, and the motion state of the object to be identified is "entering the database".

[0150] In one embodiment, when the computer program is executed by the processor, it generates a corresponding warehouse record based on the motion state of the object to be identified. This may include: when the motion state is "inbound", generating a corresponding inbound record based on the target information of the object to be identified, storing the inbound record in the warehouse's warehouse record, and incrementing the storage quantity in the warehouse by 1; when the motion state is "outbound", querying multiple warehouse records in the warehouse based on the target information of the object to be identified, marking the inbound record corresponding to the target information as outbound, and decrementing the storage quantity in the warehouse by 1.

[0151] In one embodiment, when the computer program is executed by the processor, it may also perform the following steps: when the verification result corresponds to a verification failure, an alarm message is issued.

[0152] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0153] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0154] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0155] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A warehouse management method characterized by, The method includes: Acquire multiple images to be identified from a video queue, wherein each image to be identified includes at least one object to be identified; Obtain the target information of the object to be identified, perform information verification on the target information, and generate a verification result corresponding to the object to be identified; wherein, the information verification is to verify the permission of the object to be identified to enter and exit the warehouse; When the verification result corresponds to a successful verification, orientation detection is performed on the object to be identified to determine the motion state of the object to be identified; wherein, the motion state includes: entering the warehouse and leaving the warehouse; Based on the motion state of the object to be identified, a corresponding warehouse record is generated; The step of performing orientation detection on the object to be identified to determine the motion state of the object to be identified includes: Obtain the first and second collision lines; wherein the distance between the first collision line and the warehouse is greater than the distance between the second collision line and the warehouse; Obtain the region information where the object to be identified is located in the target information, and obtain the region where the object to be identified is located based on the region information; When the area where the object to be identified is located overlaps with the first collision line, a corresponding first collision line record is generated and stored in the first queue; when the area where the object to be identified is located overlaps with the second collision line, a corresponding second collision line record is generated and stored in the second queue. Based on the first and second boundary crossing records, the motion state of the object to be identified is determined, including: when the area where the object to be identified is located overlaps with the first boundary crossing record, querying the second queue to determine the motion state of the object to be identified; when the area where the object to be identified is located overlaps with the second boundary crossing record, querying the first queue to determine the motion state of the object to be identified.

2. The method of claim 1, wherein, Before acquiring multiple images to be identified from the video queue, the method further includes: Multiple image information at the same time are read using a thread-based approach; wherein, the image information includes: the image to be identified, and the viewpoint identifier; Based on the preset viewpoint order and the viewpoint identifier, the queue order corresponding to the multiple images to be identified is obtained; Multiple images to be identified are stored in a video queue according to the queue order; wherein the acquisition times of multiple images to be identified in a video queue are consistent.

3. The method of claim 1, wherein, The step of determining the motion state of the object to be identified based on the first and second collision records includes: When the area where the object to be identified is located overlaps with the first collision line, the historical collision line record corresponding to the object to be identified is obtained; wherein, the historical collision line record is the first collision line record or the second collision line record of the object to be identified before the current moment; When the historical collision record is the second collision record, the movement direction of the object to be identified is from the second collision line to the first collision line, and the movement state of the object to be identified is out of the warehouse.

4. The method of claim 1, wherein, The step of determining the motion state of the object to be identified based on the first and second collision records includes: When the area where the object to be identified is located overlaps with the second collision line, the historical collision line record corresponding to the object to be identified is obtained; wherein, the historical collision line record is the first collision line record or the second collision line record of the object to be identified before the current moment; When the historical collision record is the first collision record, the movement direction of the object to be identified is from the first collision record to the second collision record, and the movement state of the object to be identified is "entering the database".

5. The method of claim 1, wherein, The step of generating corresponding warehouse records based on the motion state of the object to be identified includes: When the movement state is "entering the warehouse", a corresponding entry record is generated based on the target information of the object to be identified, the entry record is stored in the warehouse record of the warehouse, and the storage quantity in the warehouse is incremented by 1; When the movement state is outbound, multiple warehouse records of the warehouse are queried based on the target information of the object to be identified, the inbound records corresponding to the target information are marked as outbound, and the storage quantity in the warehouse is reduced by 1.

6. The method of claim 1, wherein, The method further includes: When the verification result corresponds to a verification failure, an alarm message is issued.

7. A warehouse management apparatus characterized by comprising: The device includes: An image acquisition module is used to acquire multiple images to be identified from a video queue, wherein each image to be identified includes at least one object to be identified. The information verification module is used to obtain the target information of the object to be identified, perform information verification on the target information, and generate a verification result corresponding to the object to be identified; wherein, the information verification is to verify the permission of the object to be identified to enter and exit the warehouse. The orientation detection module is used to perform orientation detection on the object to be identified when the verification result corresponds to a successful verification, and to determine the motion state of the object to be identified; wherein, the motion state includes: entering the warehouse and leaving the warehouse; The warehouse record generation module is used to generate corresponding warehouse records based on the movement state of the object to be identified. The orientation detection module includes: The finish line acquisition submodule is used to acquire the first finish line and the second finish line; wherein the distance between the first finish line and the warehouse is greater than the distance between the second finish line and the warehouse; The region determination submodule is used to obtain the region information where the object to be identified is located in the target information, and to obtain the region where the object to be identified is located based on the region information; The collision record generation submodule is used to generate a corresponding first collision record when the area where the object to be identified is located overlaps with the first collision line, and store the first collision record in a first queue; and to generate a corresponding second collision record when the area where the object to be identified is located overlaps with the second collision line, and store the second collision record in a second queue. The motion state determination submodule is used to determine the motion state of the object to be identified based on the first and second collision records, including: when the area where the object to be identified is located overlaps with the first collision record, querying the second queue to determine the motion state of the object to be identified; and when the area where the object to be identified is located overlaps with the second collision record, querying the first queue to determine the motion state of the object to be identified.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

Images