Method, device and computer equipment for automatically sorting express logistics items

Abstract

The present application relates to a method, device and computer equipment for automatically sorting logistics express. The method includes: when detecting that the sorting cart has arrived at each preset designated position, sending an image acquisition instruction carrying the address information of the sorting cart to the camera at each designated position; the image acquisition instruction is used to instruct the camera to collect the face sheet image of the logistics express on the sorting cart; the camera at each designated position is associated with a server with different functions; the face sheet image is sent to the server associated with the camera, and the recognition result of the face sheet image by the image recognition model in the server is obtained; the sorting address of the sorting cart is allocated according to the recognition result and the address information of the sorting cart; a sorting instruction carrying the sorting address is generated; the sorting instruction is used to control the sorting cart to deliver the logistics express to the delivery position corresponding to the sorting address. The use of this method can improve the efficiency of logistics express sorting.

Description

Technical Field

[0001] The present application relates to the technical field of logistics sorting, and in particular to a method, device, computer equipment and storage medium for automatically sorting logistics express items. Background Art

[0002] With the rapid development of the logistics and express delivery industry, the number of orders is increasing day by day. In order to achieve the rapid turnover of express parcels, automated sorting plays a vital role. The general process of automated sorting is that the express parcels are put on the conveyor line, introduced into the main sorting machine through the conveyor line, and the identification system reads the express parcel information and sorts it to the designated address according to the express parcel address information.

[0003] However, due to the relatively complete development of domestic information technology and the large volume of express delivery, express delivery bills are basically unified and have corresponding national standards. Therefore, barcode recognition technology is generally used in China to realize the information reading of express delivery. However, in other countries and regions, there are still handwritten bills and bills without barcodes. The problem of difficulty in realizing automatic reading and automatic sorting of information on handwritten bills and bills without barcodes leads to low sorting efficiency of logistics express delivery. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment and storage medium for automatically sorting logistics express parcels that can improve the efficiency of logistics express parcel sorting in response to the above-mentioned technical problems.

[0005] A method for automatically sorting logistics express items, the method comprising:

[0006] When it is detected that the sorting cart arrives at each preset designated position, an image acquisition instruction carrying the address information of the sorting cart is sent to the camera at each designated position; the image acquisition instruction is used to instruct the camera to capture the image of the logistics express on the sorting cart; the camera at each designated position is associated with a server with different functions;

[0007] Sending each of the face sheet images to a server associated with the camera, and obtaining recognition results of each of the face sheet images by an image recognition model in the server;

[0008] Allocating a sorting address of the sorting trolley according to the recognition result and the address information of the sorting trolley;

[0009] A sorting instruction carrying the sorting address is generated; the sorting instruction is used to control the sorting vehicle to deliver the logistics express to the delivery location corresponding to the sorting address.

[0010] In one embodiment, the designated positions include a first designated position and a second designated position; when the sorting trolley is detected to arrive at each preset designated position, an image acquisition instruction carrying the address information of the sorting trolley is sent to the camera at each designated position, including:

[0011] When it is detected that the sorting trolley arrives at the first designated position, a first image acquisition instruction carrying the address information of the sorting trolley is sent to the first camera at the first designated position; the first image acquisition instruction is used to instruct the first camera to acquire a first delivery bill image of the express item on the sorting trolley; the first camera is associated with a server for recognizing text information to recognize the delivery bill image of the text information;

[0012] When it is detected that the sorting cart arrives at the second designated position, a second image acquisition instruction carrying the address information of the sorting cart is sent to the second camera at the second designated position; the second image acquisition instruction is used to instruct the second camera to capture a second delivery order image of the express item on the sorting cart; the second camera is associated with a server that identifies barcode information to identify the delivery order image with barcode information.

[0013] In one embodiment, sending each of the face sheet images to a server associated with the camera to obtain a recognition result of each of the face sheet images by an image recognition model in the server includes:

[0014] Sending the first document image to a first server associated with the first camera, and obtaining a recognition result of the text information in the first document image by a first image recognition model in the first server; or

[0015] The second sheet image is sent to a second server associated with the second camera, and a recognition result of the barcode information in the second sheet image by a second image recognition model in the second server is obtained.

[0016] In one embodiment, sending the first face sheet image to a first server associated with the first camera, and obtaining a recognition result of the text information in the first face sheet image by a first image recognition model in the first server includes:

[0017] Sending the first sheet image to a first server, and detecting whether the first sheet image corresponds to a first region of interest by using a first image recognition model in the first server;

[0018] When there is a corresponding first region of interest, the text information of the first region of interest is recognized by the first image recognition model to obtain a recognition result of the text information.

[0019] In one embodiment, the sending of the second single image to a second server associated with the second camera to obtain a recognition result of the barcode information in the second single image by a second image recognition model in the second server includes:

[0020] Sending the second single image to a second server, and detecting whether the second single image has a corresponding second region of interest by a second image recognition model in the second server;

[0021] When there is a corresponding second region of interest, the barcode information of the second region of interest is recognized by the second image recognition model to obtain a recognition result of the barcode information.

[0022] In one embodiment, sending each of the face sheet images to a server associated with the camera to obtain a recognition result of the face sheet image by an image recognition model in the server includes:

[0023] The image of the delivery note is sent to a server associated with the camera, and when the camera forms a closed loop, a sorting address request instruction of the sorting vehicle is generated;

[0024] According to the sorting address request instruction, the recognition result of the image recognition model in the server on the face sheet image is obtained; and the step of allocating the sorting address of the sorting cart according to the recognition result and the address information of the sorting cart is executed.

[0025] An automatic sorting logistics express device, the device comprising:

[0026] The detection module is used to detect that the sorting trolley has arrived at each preset designated position, and send an image acquisition instruction carrying the address information of the sorting trolley to the camera at each designated position; the image acquisition instruction is used to instruct the camera to capture the image of the logistics express on the sorting trolley; the camera at each designated position is associated with a server with different functions;

[0027] A sending module, used for sending each of the face sheet images to a server associated with the camera, and obtaining a recognition result of each of the face sheet images by an image recognition model in the server;

[0028] An allocation module, used for allocating a sorting address of the sorting trolley according to the recognition result and the address information of the sorting trolley;

[0029] The sorting module is used to generate a sorting instruction carrying the sorting address; the sorting instruction is used to control the sorting vehicle to deliver the logistics express to the delivery position corresponding to the sorting address.

[0030] An automatic sorting logistics express system, characterized in that the system comprises a sensing device, a camera, a sorting machine and a control host for controlling the camera and the sorting machine; the sorting machine is provided with a conveyor belt, and the camera is set at a designated position of the camera; the control host comprises a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0031] When it is detected that the sorting cart arrives at each preset designated position, an image acquisition instruction carrying the address information of the sorting cart is sent to the camera at each designated position; the image acquisition instruction is used to instruct the camera to capture the image of the logistics express on the sorting cart; the camera at each designated position is associated with a server with different functions;

[0032] Sending each of the face sheet images to a server associated with the camera, and obtaining recognition results of each of the face sheet images by an image recognition model in the server;

[0033] Allocating a sorting address of the sorting trolley according to the recognition result and the address information of the sorting trolley;

[0034] A sorting instruction carrying the sorting address is generated; the sorting instruction is used to control the sorting vehicle to deliver the logistics express to the delivery location corresponding to the sorting address.

[0035] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0036] When it is detected that the sorting cart arrives at each preset designated position, an image acquisition instruction carrying the address information of the sorting cart is sent to the camera at each designated position; the image acquisition instruction is used to instruct the camera to capture the image of the logistics express on the sorting cart; the camera at each designated position is associated with a server with different functions;

[0037] Sending each of the face sheet images to a server associated with the camera, and obtaining recognition results of each of the face sheet images by an image recognition model in the server;

[0038] Allocating a sorting address of the sorting trolley according to the recognition result and the address information of the sorting trolley;

[0039] A sorting instruction carrying the sorting address is generated; the sorting instruction is used to control the sorting vehicle to deliver the logistics express to the delivery location corresponding to the sorting address.

[0040] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0041] When it is detected that the sorting cart arrives at each preset designated position, an image acquisition instruction carrying the address information of the sorting cart is sent to the camera at each designated position; the image acquisition instruction is used to instruct the camera to capture the image of the logistics express on the sorting cart; the camera at each designated position is associated with a server with different functions;

[0042] Sending each of the face sheet images to a server associated with the camera, and obtaining recognition results of each of the face sheet images by an image recognition model in the server;

[0043] Allocating a sorting address of the sorting trolley according to the recognition result and the address information of the sorting trolley;

[0044] A sorting instruction carrying the sorting address is generated; the sorting instruction is used to control the sorting vehicle to deliver the logistics express to the delivery location corresponding to the sorting address.

[0045] The above-mentioned method, device, computer equipment and storage medium for automatically sorting logistics express parcels, by detecting that the sorting cart arrives at each designated location, triggering the camera at each designated location to collect the waybill image of the logistics express parcel of the sorting cart, and uploading the collected image waybill information to the server associated with the camera at each designated location; assigning the sorting address of the sorting cart according to the recognition result of the waybill image by the image recognition model in each server and the address information of the sorting cart; and generating a sorting instruction carrying the sorting address; controlling the sorting cart to deliver the logistics express parcel to the delivery position corresponding to the sorting address through the sorting instruction; that is, decoding different types of collected waybill images through different types of servers associated with cameras at different designated locations; obtaining the recognition results of different types of waybill express information, determining the sorting address of each sorting cart according to the recognition results, and implementing the sorting of logistics express parcels with different types of waybill images, thereby improving the sorting efficiency of logistics express parcels. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is an application environment diagram of a method for automatically sorting logistics express mails in an embodiment;

[0047] Figure 2 A schematic diagram of a process for automatically sorting logistics express items in one embodiment;

[0048] Figure 3 It is a structural schematic diagram of an automatic sorting machine in one embodiment;

[0049] Figure 4 A schematic diagram of a flow chart of a method for automatically sorting logistics express items in another embodiment;

[0050] Figure 5This is a schematic diagram of an application scenario of automatically sorting logistics express in an embodiment;

[0051] Figure 6 A schematic diagram of an automatic sorting logistics express system in one embodiment;

[0052] Figure 7 It is a structural block diagram of an automatic sorting logistics express device in one embodiment;

[0053] Figure 8 It is a structural block diagram of an automatic sorting logistics express device in another embodiment;

[0054] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] The automatic sorting logistics express delivery method provided in this application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102, the camera 104 and the server 106 communicate through the network. When the terminal 102 detects that the sorting cart arrives at each preset designated position in turn, it sends an image acquisition instruction carrying the address information of the sorting cart to the camera 104 at the designated position; the image acquisition instruction is used to instruct the camera to collect the face order image of the logistics express on the sorting cart; the camera at each designated position is associated with a server with different functions; the face order image is sent to the server 106 associated with the camera 102, and the recognition result of the face order image by the image recognition model in the server 106 is obtained; the sorting address of the sorting cart is assigned according to the recognition result and the address information of the sorting cart; the sorting instruction carrying the sorting address is generated; the sorting instruction is used to control the sorting cart to deliver the logistics express to the delivery position corresponding to the sorting address. Among them, the terminal 102 can be but not limited to various personal computers, laptops, smart phones, and tablet computers, and the server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0057] In one embodiment, Figure 2 As shown, a method for automatically sorting logistics express parcels is provided, and the method is applied to Figure 1 The terminal in is used as an example to illustrate, including the following steps:

[0058] Step 202, when it is detected that the sorting cart has arrived at each preset designated position, an image acquisition instruction carrying the address information of the sorting cart is sent to the camera at each designated position; the image acquisition instruction is used to instruct the camera to capture the image of the logistics express on the sorting cart; the camera at each designated position is associated with a server with different functions.

[0059] Among them, the address information of the sorting trolley is a physical address, which can be the location information of the sorting trolley arriving at the designated location of the automated sorting machine. The address information of the sorting trolley arriving at different designated locations is different. The automatic sorting machine is provided with at least two designated locations, and each designated location is equipped with a camera for collecting the image of the waybill of the logistics express on the sorting trolley. The function of the camera at each designated location can be different or the same, but the camera at each designated location is associated with a server with different functions; for example, the preset designated location includes a first designated location and a second designated location, the camera at the first designated location is associated with a server for identifying the image of the waybill of text information, and the camera at the second designated location is associated with a server for identifying the image of the waybill of barcode information; the camera may include a top scanning camera and a five-sided scanning camera. The top scanning camera only collects images of the top of the logistics express, and the five-sided scanning camera collects images of the top and four sides of the logistics express at one time. In this application, the designated location includes the first designated location and the second designated location, and the camera at the first designated location is a top scanning camera, and the camera at the second designated location is a five-sided scanning camera for explanation by way of example.

[0060] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe preset designated positions, but these designated positions are not limited by these terms. These terms are only used to distinguish a first designated position from another designated position. For example, without departing from the scope of this application, a first designated position may be referred to as a second designated position, and similarly, a second designated position may be referred to as a first designated position. Both the first designated position and the second designated position are designated positions, but they are not the same designated position.

[0061] Specifically, the conveyor belt of the automated import station enables the sorting trolley to carry the logistics express to be transported on the automatic sorting machine. When the sensor at the first designated position senses the sorting trolley, that is, the terminal detects that the sorting trolley has arrived at the first designated position, the sorting machine PLC control unit in the terminal generates an image acquisition instruction, triggers the top surface scanning camera at the first designated position to collect the image of the logistics express on the sorting trolley, and the address information of the sorting trolley is the first designated position; the sorting trolley is continuously transported by the conveyor belt. When the sorting trolley is transferred from the first designated position to the second designated position, the sensor at the second designated position senses the sorting trolley, that is, the terminal detects that the sorting trolley has arrived at the second designated position, and the sorting machine PLC control unit in the terminal generates an image acquisition instruction, triggers the five-surface scanning camera at the second designated position to collect the image of the logistics express on the sorting trolley, and the address information of the sorting trolley is the second designated position. Among them, the camera at the first designated position is an OCR camera (top surface scanning camera), and the camera at the second designated position is an OBR camera (five-surface scanning camera).

[0062] Step 204: Send each face sheet image to a server associated with the camera to obtain a recognition result of each face sheet image by an image recognition model in the server.

[0063] The server may be an optical character recognition (OCR) server or an optical barcode recognition (OBR) server. The OCR server is used to recognize text information, and the OBR server is used to recognize barcode information. Cameras at different designated positions are associated with servers with different functions. The camera at the first designated position is associated with the OCR server, and the camera at the second designated position is associated with the OBR server. The waybill image may include, but is not limited to, the order number, item attributes, customer information, and delivery address information of the logistics express. The waybill image may be any one of a waybill image with text information and a waybill image with barcode information.

[0064] Specifically, the face order image is sent to the server associated with the camera, and the sorting cart address information is uploaded to the sorting machine PLC control unit in the terminal again, so that when the camera is in a closed-loop state, a sorting address request instruction for the sorting cart is generated; according to the sorting address request instruction, the recognition result of the face order image by the image recognition model in the server is obtained. The camera being in a closed-loop state means that the camera has completed the current acquisition, the camera is in a reset state, and can be triggered to take pictures again.

[0065] Optionally, if the waybill image is a waybill image with text information, the top surface scanning camera at the first designated position collects the waybill image of the logistics express on the sorting cart, and the collected waybill image is a waybill image with text information. The waybill image is bound to the address information of the sorting cart, and the collected waybill image, image collection time and camera number are sent to the OCR server associated with the top surface scanning camera; when the top surface scanning camera forms a closed loop and generates a sorting address request instruction for the sorting cart, when the image recognition model in the OCR server detects the text information of the waybill image, the text information is identified by the image recognition model. The five-sided scanning camera at the second designated position collects the waybill image of the logistics express on the sorting trolley, and the waybill image is bound to the address information of the sorting trolley. The collected waybill image, image collection time and camera number are sent to the OBR server associated with the top-surface scanning camera. When the five-sided scanning camera forms a closed loop and generates a sorting address request instruction for the sorting trolley, the OBR server cannot recognize the waybill image of the text information, and the recognition result corresponding to the text information obtained by the OCR server is used as the recognition result of the waybill image.

[0066] If the waybill image is a waybill image with barcode information, the top surface scanning camera at the first designated position collects the waybill image of the logistics express on the sorting trolley, and the collected waybill image is a waybill image with text information. The waybill image is bound to the address information of the sorting trolley, and the collected waybill image, image collection time and camera number are sent to the OCR server associated with the top surface scanning camera; the OCR server cannot recognize the waybill image with barcode information; the five-sided scanning camera at the second designated position collects the waybill image of the logistics express on the sorting trolley, and the waybill image is bound to the address information of the sorting trolley, and the collected waybill image, image collection time and camera number are sent to the OBR server associated with the top surface scanning camera. When the five-sided scanning camera forms a closed loop and generates a sorting address request instruction for the sorting trolley, when the image recognition model in the OBR server detects the text information of the waybill image, the barcode information is recognized by the image recognition model to obtain the recognition result corresponding to the barcode information, and the recognition result is the sending destination of the logistics express.

[0067] Step 206, assigning a sorting address of the sorting trolley according to the recognition result and the address information of the sorting trolley.

[0068] Among them, the recognition result is the destination of the logistics express, and a corresponding relationship is pre-established between the destination, the address information of the sorting cart and the sorting address; the sorting address of the sorting cart is matched according to the recognition result, the address information of the sorting cart and the pre-established corresponding relationship.

[0069] Specifically, when the waybill image is a waybill image with text information, the sorting address of the sorting cart is assigned according to the results obtained by the image recognition model in the OCR server and the address information of the sorting cart; when the waybill image is a waybill image with barcode information, the sorting address of the sorting cart is assigned according to the results obtained by the image recognition model in the OBR server and the address information of the sorting cart.

[0070] Step 208, generating a sorting instruction carrying a sorting address; the sorting instruction is used to control the sorting vehicle to deliver the logistics express to the delivery location corresponding to the sorting address.

[0071] Specifically, when the terminal obtains the recognition result of the logistics express delivery image from the server, the sorting machine PLC control unit in the terminal sends a sorting request to the upper system, assigns the sorting address of the sorting trolley according to the obtained recognition result and the address information of the sorting trolley, and generates a sorting instruction carrying the sorting address; the sorting instruction is sent to the sorting machine PLC control unit, and the sorting trolley is controlled by the sorting machine PLC control unit to deliver the logistics express to the delivery position corresponding to the sorting address. For example, in a sorting scenario, there are 100 sorting grids, each of which represents a destination. When the logistics express passes through the import platform, the address of the sorting trolley is bound to the logistics express. When the logistics express passes through the OCR system, the OCR identifies the destination of the logistics express, and the upper system control unit assigns the sorting grid according to the destination of the logistics express. When the trolley arrives at the designated sorting grid, the PLC triggers the sorting command, and the logistics express is accurately delivered to the designated sorting grid; when the logistics express passes through the OBR system, the OBR identifies the destination of the logistics express, and the upper system control unit allocates the sorting grid according to the destination of the logistics express. When the trolley arrives at the designated sorting grid, the PLC triggers the sorting command, and the logistics express is accurately delivered to the designated sorting grid.

[0072] The following is a schematic diagram of the structure of an automatic sorting machine in one embodiment. Figure 3 As shown, "1" represents the automatic induction platform of the automatic sorting machine, which is composed of seven sections of belt conveyors; "2" is the OCR camera, "3" is the OBR camera, and "4" is the sorting grid. The logistics express is put into the automatic sorting machine through the automatic induction platform. The sorting cart carries the logistics express through the OCR camera and the OBR camera in turn, and the images of the logistics express on the sorting cart are collected respectively. The images of the logistics express collected by the OCR camera and the OBR camera are sent to their respective associated servers. The sorting address of the sorting cart is allocated according to the recognition result of the image recognition model on the image of the sorting cart and the address information of the sorting cart in the server, and the sorting instruction carrying the sorting address is sent to the sorting machine PLC control unit, which controls the sorting cart to put the logistics express at the delivery position corresponding to the sorting address.

[0073] In the above-mentioned automatic sorting method for logistics express, when it is detected that the sorting cart has arrived at each designated position, the camera at each designated position is triggered to collect the waybill image of the logistics express of the sorting cart, and the image waybill information collected at each designated position is uploaded to the associated server; the sorting address of the sorting cart is allocated according to the recognition result of the waybill image by the image recognition model in the server and the address information of the sorting cart; and a sorting instruction carrying the sorting address is generated; the sorting cart is controlled by the sorting instruction to deliver the logistics express to the delivery position corresponding to the sorting address; that is, different types of collected waybill images are decoded through different types of servers associated with cameras at different designated positions; the recognition results of different types of waybill express information are obtained, and the sorting addresses of each sorting cart are determined according to the recognition results, so as to realize the sorting of logistics express with different types of waybill images, thereby improving the sorting efficiency of logistics express.

[0074] In another embodiment, Figure 4 As shown, a method for automatically sorting logistics express parcels is provided, and the method is applied to Figure 1 The terminal in is used as an example to illustrate, including the following steps:

[0075] Step 402, obtaining the image category of the express delivery bill image on the sorting vehicle.

[0076] Among them, the image categories of the waybill image include waybill images with text information and waybill images with barcode information, etc. The waybill image with text information can be but not limited to handwritten waybill images, and the waybill image with barcode information can be but not limited to barcode or QR code waybill images.

[0077] Specifically, when a logistics express is put into a sorting machine, the logistics express is bound to the physical address of the sorting cart, the image category of the logistics express on the sorting cart is obtained, and the category of the face order image is judged.

[0078] Step 404, when the image category is a waybill image with text information, when it is detected that the sorting cart arrives at the first designated position, a first image acquisition instruction carrying the address information of the sorting cart is sent to the first camera at the first designated position; the first image acquisition instruction is used to instruct the first camera to capture the waybill image of the express item on the sorting cart.

[0079] Specifically, when the image category is a waybill image with text information, when it is detected that the sorting cart has arrived at the first designated position, the sorting machine PLC control unit in the terminal sends a first image acquisition instruction carrying the sorting cart address information, and the first camera at the first designated position starts to acquire the image; at this time, the sorting machine PLC control unit sends the sorting cart address information to the first camera. When the first camera completes image acquisition, it associates the acquired image waybill with the sorting cart address information, and obtains the camera number and image acquisition time of the first camera.

[0080] Step 406: Send the first sheet image to a first server associated with the first camera, and obtain a recognition result of the text information in the first sheet image by a first image recognition model in the first server.

[0081] Specifically, the first single-sided image captured by the camera at the first designated position, the sorting trolley address information associated with the first single-sided image, the camera number of the first camera and the image acquisition time are sent to the first server, which may be an OCR server; the first camera sends the sorting trolley address information to the sorting machine PLC control unit, so that the first camera is in a closed loop and generates a sorting address request instruction, and according to the sorting address request instruction, the first image recognition model in the first server is used to detect whether there is a corresponding first region of interest in the single-sided image; when there is a corresponding first region of interest, the text information of the first region of interest is recognized by the first image recognition model to obtain a recognition result of the text information. The first image recognition model is a pre-trained model.

[0082] Optionally, the training process of the first image recognition model is to obtain a sample face sheet image, mark the position of the information to be read in the sample face sheet image, and obtain a sample detection data set; obtain a sample recognition data set, train the text detection sub-model in the first image recognition model through the sample detection data set, and train the text recognition sub-model in the first image recognition model through the sample recognition data, until the text detection sub-model and the text recognition sub-model converge within a set convergence value range, thereby obtaining a trained first image recognition model.

[0083] Step 408, when the image category is a waybill image with barcode information, when it is detected that the sorting cart arrives at the second designated position, a second image acquisition instruction carrying the address information of the sorting cart is sent to the second camera at the second designated position; the second image acquisition instruction is used to instruct the second camera to capture the waybill image of the express item on the sorting cart.

[0084] Specifically, when the image category is a bill image with barcode information, when it is detected that the sorting cart has arrived at the second designated position, the sorting machine PLC control unit in the terminal sends a second image acquisition instruction carrying the sorting cart address information, and the second camera at the second designated position starts image acquisition; at this time, the sorting machine PLC control unit sends the sorting cart address information to the second camera. When the second camera completes image acquisition, it associates the acquired image bill with the sorting cart address information, and obtains the camera number and image acquisition time of the second camera.

[0085] Step 410: Send the second sheet image to a second server associated with the second camera, and obtain a recognition result of the barcode information in the second sheet image by a second image recognition model in the second server.

[0086] Specifically, the second single image captured by the camera at the second designated position, the sorting trolley address information associated with the second single image, the camera number of the second camera and the image acquisition time are sent to the second server, which may be an OBR server; the second camera sends the sorting trolley address information to the sorting machine PLC control unit, so that the second camera is in a closed loop and generates a sorting address request instruction, and according to the sorting address request instruction, the second image recognition model in the second server is used to detect whether there is a corresponding second region of interest in the single image; when there is a corresponding second region of interest, the barcode information of the second region of interest is recognized by the second image recognition model to obtain a recognition result of the barcode information. The second image recognition model is a pre-trained model.

[0087] Optionally, the training process of the second image recognition model is to obtain a sample face sheet image, mark the position of the information to be read in the sample face sheet image, and obtain a sample detection data set; obtain a sample recognition data set, train the barcode detection sub-model in the second image recognition model through the sample detection data set, and train the barcode recognition sub-model in the second image recognition model through the sample recognition data, until the barcode detection sub-model and the barcode recognition sub-model converge within a set convergence value range, thereby obtaining a trained second image recognition model.

[0088] Step 412, assigning a sorting address of the sorting cart according to the recognition result and the sorting cart address information.

[0089] Specifically, if the waybill image is a waybill image with text information, the image recognition model in the OBR server cannot recognize the waybill image with text information, and the sorting address of the sorting cart is assigned according to the recognition result obtained by the image recognition model in the OCR server and the address information of the sorting cart; when the waybill image is a waybill image with barcode information, the image recognition model in the OCR server cannot recognize the waybill image with barcode information, and the sorting address of the sorting cart is assigned according to the recognition result obtained by the image recognition model in the OBR server and the address information of the sorting cart.

[0090] Step 414, generating a sorting instruction carrying a sorting address; the sorting instruction is used to control the sorting vehicle to deliver the logistics express to the delivery location corresponding to the sorting address.

[0091] The following is an application scenario diagram of automatic sorting of logistics express in one embodiment. Figure 5 As shown, the terminal includes a sorting machine PLC control unit and a host system unit. Specifically, the image category of the logistics express delivery bill image on the sorting trolley is obtained. If the image category is a bill image with text information, when the terminal detects that the sorting trolley has arrived at the first designated position, the sorting machine PLC control unit in the terminal sends a first image acquisition instruction carrying the sorting trolley address information, and the OCR camera at the first designated position starts to acquire the image; at this time, the sorting machine PLC control unit sends the sorting trolley address information to the OCR camera. When the OCR camera completes image acquisition, it associates the acquired image bill with the sorting trolley address information, and obtains the camera number and image acquisition time of the first camera; the first designated position The waybill image captured by the OCR camera, the sorting trolley address information associated with the waybill image, the camera number of the first camera and the image acquisition time are sent to the OCR server; the first camera sends the sorting trolley address information to the sorting machine PLC control unit, so that the OCR camera is in a closed loop and generates a sorting address request instruction, and according to the sorting address request instruction, the first image recognition model in the OCR server is used to detect whether there is a corresponding first area of ​​interest in the waybill image; when the corresponding first area of ​​interest exists, the text information of the first area of ​​interest is recognized by the first image recognition model to obtain a recognition result of the text information.

[0092] If the image category is a waybill image with barcode information, when the terminal detects that the sorting trolley has arrived at the second designated position, the sorting machine PLC control unit in the terminal sends a second image acquisition instruction carrying the sorting trolley address information, and the OBR camera at the second designated position starts to acquire images; at this time, the sorting machine PLC control unit sends the sorting trolley address information to the OBR camera. When the OBR camera completes image acquisition, it associates the acquired image waybill with the sorting trolley address information, and obtains the camera number and image acquisition time of the second camera; the waybill image acquired by the OBR camera at the second designated position, the sorting trolley address information associated with the waybill image, the camera number and image acquisition time of the second camera are sent to the OBR server; the second camera sends the sorting trolley address information to the sorting machine PLC control unit, so that the OBR camera is in a closed loop and generates a sorting address request instruction. According to the sorting address request instruction, the second image recognition model in the OBR server is used to detect whether there is a corresponding second area of ​​interest in the waybill image; when there is a corresponding second area of ​​interest, the barcode information of the second area of ​​interest is recognized by the second image recognition model to obtain the recognition result of the text information.

[0093] The upper system module assigns the sorting address of the sorting trolley according to the recognition result and the address information of the sorting trolley, and sends the generated sorting instruction carrying the sorting address to the sorting machine PLC control module. The sorting machine PLC control module controls the sorting trolley to deliver the logistics express to the delivery position corresponding to the sorting address, thereby realizing the sorting of logistics express with different types of delivery list images and improving the sorting efficiency of logistics express.

[0094] In the above-mentioned automated sorting method for logistics express, by determining the image category of the waybill image of the logistics express, by detecting that the sorting cart arrives at each designated position, triggering the camera at each designated position to collect the waybill image of the logistics express on the sorting cart, uploading the collected image waybill information to the OBR server and the OCR server, recognizing the waybill image through the trained image recognition model in the OBR server or the OCR server, obtaining the destination of the logistics express of the waybill image with text information and the waybill image with barcode information, allocating the sorting address of the sorting cart according to the destination of the logistics express and the address information of the sorting cart, and controlling the sorting cart to deliver the logistics express to the delivery position corresponding to the sorting address according to the sorting instruction carrying the sorting address, thereby realizing the sorting of logistics express with different types of waybill images, and improving the sorting efficiency of logistics express.

[0095] It should be understood that although Figure 2 , Figure 4The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2 , Figure 4 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0096] In one embodiment, Figure 6 As shown, an automatic sorting logistics express system is provided, which includes a sensing device, a camera, a sorting machine and a control host for controlling the camera and the sorting machine, the sorting machine is provided with a conveyor belt, and the camera is set at a designated position of the camera; wherein the sensing device is used to sense whether the sorting trolley has arrived at each preset designated position; the camera is used to collect the image of the logistics express on the sorting trolley; the sorting machine is used to deliver the logistics express to the delivery position corresponding to the sorting address; the control host includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program: sensing the sorting trolley through the sensing device When arriving at each preset designated position, an image acquisition instruction carrying the address information of the sorting cart is sent to the camera at each designated position; the image acquisition instruction is used to instruct the camera to collect the image of the logistics express on the sorting cart; the camera at each designated position is associated with a server with different functions; each image of the logistics express is sent to the server associated with the camera, and the recognition result of the image recognition model in the server for each image of the logistics express is obtained; the sorting address of the sorting cart is allocated according to the recognition result and the address information of the sorting cart; a sorting instruction carrying the sorting address is generated, and the sorting instruction is used to control the sorting cart to deliver the logistics express to the delivery position corresponding to the sorting address.

[0097] For the specific limitations of the automatic sorting logistics express system, please refer to the limitations of the automatic sorting logistics express method above, which will not be repeated here.

[0098] In one embodiment, Figure 7 As shown, an automatic sorting logistics express device is provided, including: a detection module 702, a sending module 704, a distribution module 706 and a sorting module 708, wherein:

[0099] The detection module 702 is used to detect that the sorting cart has arrived at each preset designated position, and send an image acquisition instruction carrying the address information of the sorting cart to the camera at each designated position; the image acquisition instruction is used to instruct the camera to capture the image of the logistics express on the sorting cart; the camera at each designated position is associated with a server with different functions.

[0100] The sending module 704 is used to send each face sheet image to a server associated with the camera, and obtain the recognition result of each face sheet image by the image recognition model in the server.

[0101] The allocation module 706 is used to allocate the sorting address of the sorting trolley according to the recognition result and the address information of the sorting trolley.

[0102] The sorting module 708 is used to generate a sorting instruction carrying a sorting address; the sorting instruction is used to control the sorting vehicle to deliver the logistics express to the delivery location corresponding to the sorting address.

[0103] In the above-mentioned automatic sorting logistics express device, when it is detected that the sorting cart arrives at each designated position, the camera at each designated position is triggered to collect the waybill image of the logistics express of the sorting cart, and the image waybill information collected at each designated position is uploaded to the associated server; the sorting address of the sorting cart is allocated according to the recognition result of the waybill image by the image recognition model in the server and the address information of the sorting cart; and a sorting instruction carrying the sorting address is generated; the sorting cart is controlled by the sorting instruction to deliver the logistics express to the delivery position corresponding to the sorting address; that is, different types of collected waybill images are decoded through different types of servers associated with cameras at different designated positions; the recognition results of different types of waybill express information are obtained, and the sorting addresses of each sorting cart are determined according to the recognition results, so as to realize the sorting of logistics express with different types of waybill images, thereby improving the sorting efficiency of logistics express.

[0104] In another embodiment, Figure 8 As shown, an automatic sorting logistics express device is provided, which includes, in addition to a detection module 702, a sending module 704, a distribution module 706 and a sorting module 708, an identification module 710 and a generation module 712, wherein:

[0105] The image processing module 710 is used to send the first single image to the first server, and detect whether there is a corresponding first region of interest in the first single image through the first image recognition model in the first server; when there is a corresponding first region of interest, the text information of the first region of interest is recognized through the first image recognition model to obtain a recognition result of the text information.

[0106] The image processing module 710 is also used to send the second single image to the second server, and detect whether there is a corresponding second region of interest in the second single image through a second image recognition model in the second server; when there is a corresponding second region of interest, the barcode information of the second region of interest is identified through the second image recognition model to obtain a recognition result of the barcode information.

[0107] The generation module 712 is used to send the waybill image to the server associated with the camera, and when the camera forms a closed loop, generate a sorting address request instruction for the sorting cart.

[0108] In one embodiment, the detection module 702 is also used to send a first image acquisition instruction carrying the address information of the sorting cart to the first camera at the first designated position when it is detected that the sorting cart has arrived at the first designated position; the first image acquisition instruction is used to instruct the first camera to capture the first delivery bill image of the express item on the sorting cart, and the first camera is associated with a server that recognizes text information to identify the delivery bill image of the text information.

[0109] The sending module 704 is further configured to send the first single face image to a first server associated with the first camera, and obtain a recognition result of the text information in the single face image by a first image recognition model in the first server.

[0110] In one embodiment, the detection module 702 is also used to send a second image acquisition instruction carrying the address information of the sorting cart to the second camera at the second designated position when it is detected that the sorting cart has arrived at the second designated position; the second image acquisition instruction is used to instruct the second camera to capture the waybill image of the express item on the sorting cart, and the second camera is associated with a server that identifies barcode information to identify the waybill image of the barcode information.

[0111] The sending module 704 is further configured to send the second single face image to a second server associated with the second camera, and obtain a recognition result of the barcode information in the single face image by a second image recognition model in the second server.

[0112] In one embodiment, by determining the image category of the logistics express delivery bill image, by detecting that the sorting cart arrives at each designated location, triggering the camera at each designated location to collect the logistics express delivery bill image of the sorting cart, and uploading the collected image bill information to the OBR server and the OCR server, the bill image is recognized by the trained image recognition model in the OBR server or the OCR server, and the destination of the logistics express delivery of the bill image with text information and the bill image with barcode information is obtained. The sorting address of the sorting cart is allocated according to the destination of the logistics express delivery and the address information of the sorting cart, and the sorting cart is controlled according to the sorting instruction carrying the sorting address to deliver the logistics express delivery to the delivery position corresponding to the sorting address, so as to realize the sorting of logistics express delivery with different types of bill images, thereby improving the sorting efficiency of logistics express delivery.

[0113] For the specific limitations of the automatic sorting logistics express device, please refer to the limitations of the automatic sorting logistics express method above, which will not be repeated here. Each module in the above-mentioned automatic sorting logistics express device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0114] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for automatically sorting logistics express parcels is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0115] Those skilled in the art will understand that Fig. 9The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0116] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0117] 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, the steps in the above-mentioned method embodiments are implemented.

[0118] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database 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 or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0119] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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.

[0120] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for automatically sorting express logistics, characterized in that: The method comprises: Get the image category of the express delivery bill image on the sorting cart; When the image category is a waybill image with text information, when it is detected that the sorting cart has arrived at the first designated position, a first image acquisition instruction carrying the address information of the sorting cart is sent to the first camera at the first designated position; the first image acquisition instruction is used to instruct the first camera to acquire a first waybill image of the express item on the sorting cart; the first waybill image is sent to a first server associated with the first camera, and a recognition result of the text information in the first waybill image by a first image recognition model in the first server is obtained; When the image category is a waybill image with barcode information, when it is detected that the sorting cart has arrived at the second designated position, a second image acquisition instruction carrying the address information of the sorting cart is sent to the second camera at the second designated position; the second image acquisition instruction is used to instruct the second camera to acquire a second waybill image of the express item on the sorting cart; the second waybill image is sent to a second server associated with the second camera, and a recognition result of the barcode information in the second waybill image by a second image recognition model in the second server is obtained; Allocating a sorting address of the sorting trolley according to the recognition result and the address information of the sorting trolley; A sorting instruction carrying the sorting address is generated; the sorting instruction is used to control the sorting vehicle to deliver the logistics express to the delivery location corresponding to the sorting address.

2. The method according to claim 1, characterized in that The step of sending the first face sheet image to a first server associated with the first camera, and obtaining a recognition result of the text information in the first face sheet image by a first image recognition model in the first server includes: Sending the first sheet image to a first server, and detecting, by a first image recognition model in the first server, whether the first sheet image corresponds to a first region of interest; When there is a corresponding first region of interest, the text information of the first region of interest is recognized by the first image recognition model to obtain a recognition result of the text information.

3. The method according to claim 1, characterized in that The step of sending the second sheet image to a second server associated with the second camera, and obtaining a recognition result of the barcode information in the second sheet image by a second image recognition model in the second server, includes: Sending the second single image to a second server, and detecting whether the second single image has a corresponding second region of interest by a second image recognition model in the second server; When there is a corresponding second region of interest, the barcode information of the second region of interest is recognized by the second image recognition model to obtain a recognition result of the barcode information.

4. The method according to claim 1, characterized in that: The method further comprises: When the cameras form a closed loop, a sorting address request instruction for the sorting vehicle is generated; According to the sorting address request instruction, the recognition result of the text information or the recognition result of the barcode information is obtained; and the step of allocating the sorting address of the sorting cart according to the recognition result and the sorting cart address information is executed.

5. An automatic sorting logistics express system, characterized in that: The system includes a sensing device, a camera, a sorting machine and a control host for controlling the camera and the sorting machine; the sorting machine is provided with a conveyor belt, and the camera is set at a designated position of the camera; the control host includes a memory and a processor, the memory stores a computer program, and is characterized in that the processor implements the steps of any one of claims 1 to 4 when executing the computer program.

6. An automatic sorting logistics express device, characterized in that: The automatic sorting logistics express device is used to execute the steps of any one of the methods described in claims 1 to 4.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images