Complement image processing method, device and storage medium

Abstract

This application provides a code replacement image processing method, device, and storage medium. The solution includes: receiving a code replacement request from a sorting system for a target package and an image of the target package; performing text recognition processing on the package image to obtain a text recognition result; generating a code replacement task for the target package based on the package image and the text recognition result; and enabling code replacement personnel to edit or confirm the text recognition result based on the package image displayed on the code replacement client to obtain missing logistics information from the waybill of the target package. This allows code replacement personnel to complete the code replacement task by confirming or correcting only a small amount of information, simplifying the code replacement process, reducing the number of steps required, shortening the code replacement time, and improving code replacement efficiency. Furthermore, it also helps reduce errors that may occur during manual operation.

Description

Technical Field

[0001] This application relates to the field of logistics technology, specifically to a two's complement image processing method, device, and storage medium. Background Technology

[0002] The logistics sorting system utilizes machine vision technology to identify waybill images on packages, achieving efficient and accurate product classification and delivery. As packages move along the conveyor belt, high-definition cameras capture images of the waybills on the packages. The sorting system identifies the waybill number by scanning the barcode in the waybill image and then queries the company's database for the corresponding destination based on the identified waybill number. If destination information is available, the package can be automatically sorted successfully; otherwise, it is marked as an abnormal package.

[0003] However, during transportation, packages may experience compression, wear and tear, or contamination, resulting in blurred or missing waybill information, causing sorting system failures. In such cases, personnel are needed to add missing waybill information. These personnel obtain photos of the packages taken by the sorting system through a waybill client and input the missing information. Summary of the Invention

[0004] In view of this, this application aims to provide a two's complement image processing method, device and storage medium, which can improve the efficiency of two's complement personnel.

[0005] According to a first aspect of this application, a code-supplementing image processing method is provided, comprising: receiving a code-supplementing request from a sorting system for a target package, and a package image of the target package; the code-supplementing request instructing, based on the package image, to supplement missing logistics information in the waybill of the target package; performing text recognition processing on the package image to obtain a text recognition result of the package image; generating a code-supplementing task for the target package based on the package image of the target package and the text recognition result; the code-supplementing task instructing code-supplementing personnel at the code-supplementing client to supplement missing logistics information in the waybill of the target package based on the text recognition result.

[0006] According to a second aspect of this application, an electronic device is provided, comprising: a processor; a memory for storing processor-executable instructions; the processor being configured to perform the method described in any of the above embodiments.

[0007] According to a third aspect of this application, a computer-readable storage medium is provided, the storage medium storing a computer program for performing the methods described in any of the above embodiments.

[0008] This application provides a code replacement image processing method, device, and storage medium. The solution includes: receiving a code replacement request from a sorting system for a target package and an image of the target package; performing text recognition processing on the package image to obtain a text recognition result; generating a code replacement task for the target package based on the package image and the text recognition result; and enabling code replacement personnel to edit or confirm the text recognition result based on the package image displayed on the code replacement client to obtain missing logistics information from the waybill of the target package. This allows code replacement personnel to complete the code replacement task by confirming or correcting only a small amount of information, simplifying the code replacement process, reducing the number of steps required, shortening the code replacement time, and improving code replacement efficiency. Furthermore, it also helps reduce errors that may occur during manual operation. Attached Figure Description

[0009] Figure 1 The diagram shown is a schematic representation of an implementation environment provided in an embodiment of this application.

[0010] Figure 2 The diagram shown is a flowchart of a two's complement image processing method provided in one embodiment of this application.

[0011] Figure 3 The diagram shown is a block diagram of a two's complement image processing apparatus provided in one embodiment of this application.

[0012] Figure 4 The diagram shown is a structural block diagram of an electronic device provided in one embodiment of this application. Detailed Implementation

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

[0014] Application Overview

[0015] The existing sorting system first identifies the package's tracking number using a camera, then queries the company's database for the corresponding destination based on the identified tracking number. If destination information is available, automatic sorting is successful; otherwise, the package is marked as an abnormal package and removed from the abnormal sorting chute for manual processing. When sorting volume is large, many packages will be removed from the abnormal sorting chute, leading to low efficiency and potential inventory buildup. If the replacement code result is obtained before the abnormal package is removed from the abnormal sorting chute, the abnormal package can be sorted without manual processing.

[0016] The general process for code replacement is as follows: When the code replacement personnel begin processing the code replacement task from the sorting system, the package images captured by the sorting system are displayed on the code replacement client. The code replacement personnel then read the missing logistics information from the package images and input it into the code replacement client as the code replacement result. It is evident that the code replacement operation is quite cumbersome and time-consuming due to the numerous steps involved in manipulating the package images.

[0017] To address the aforementioned issues, this embodiment of the application, upon receiving a code replenishment request from the sorting system for a target package, performs text recognition processing on the package image to obtain the text recognition result; and sends a code replenishment task carrying the text recognition result to the code replenishment client. This enables the code replenishment personnel at the client to supplement missing logistics information in the target package's waybill based on the text recognition result, helping to reduce the time required for code replenishment and improve replenishment efficiency.

[0018] After introducing the basic principles of this application, various non-limiting embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0019] Exemplary System

[0020] Figure 1 The diagram illustrates an implementation environment provided in this application embodiment. This implementation environment includes a sorting system 110, a code replacement server 120, and a code replacement client 130. Generally, there are multiple sorting systems 110, code replacement servers 120, and code replacement clients 130 in this implementation environment; no specific limitation is made here. The sorting system 110 and the code replacement server 120 are connected via a communication network. The code replacement server 120 and the code replacement client 130 are connected via a communication network. Optionally, the communication network can be a wired network or a wireless network.

[0021] The sorting system 110 can capture images of packages and identify the barcodes in the waybill images using barcode recognition technology to obtain the waybill number, thereby achieving efficient and accurate product classification and delivery. When an unidentifiable abnormal package is encountered, a supplementary barcode request is generated for the abnormal package.

[0022] The code replacement server 120 can receive code replacement requests sent by the sorting system 110 and obtain the corresponding package images, thereby generating code replacement tasks and distributing them to each code replacement client 130. Before distributing the code replacement tasks, the code replacement server 120 can also perform at least one preprocessing operation on the package images, such as waybill cutting, straightening, and text recognition.

[0023] The supplementary coding client 130 is used to receive the supplementary coding task and its corresponding package image, display the package image and obtain the supplementary coding result of the supplementary coding personnel for the supplementary coding task, and feed the supplementary coding result back to the sorting system 110 through the supplementary coding server 120.

[0024] The complement code client 130 can be a general-purpose computer or a computer device composed of dedicated integrated circuits, etc., and this application embodiment does not limit this. For example, the complement code client 130 can be a mobile terminal device such as a tablet computer, or it can be a personal computer (PC), such as a laptop computer and a desktop computer, etc. Those skilled in the art will know that the number of the above-mentioned complement code clients 130 can be one or more, and their types can be the same or different. For example, there can be one complement code client 130, or there can be dozens or hundreds of complement code clients 130, or more. This application embodiment does not limit the number and device type of the complement code clients 130.

[0025] The complement server 120 may be a single server, or a combination of several servers, or a virtualization platform, or a cloud computing service center; this application embodiment does not limit this.

[0026] Exemplary methods

[0027] Figure 2 This is a schematic diagram of the process of two's complement image processing provided in one embodiment of this application. Figure 2 The method described can be executed by a computing device (e.g., a two's complement server 120 or a two's complement client 130), and this application embodiment does not limit this. Figure 2 As shown, the method includes the following:

[0028] Step S210: Receive a code supplementation request from the sorting system for the target package, and an image of the target package; the code supplementation request is used to instruct the missing logistics information in the waybill of the target package to be supplemented based on the package image.

[0029] In this embodiment of the application, the code supplementation request is used to instruct the supplementation of missing logistics information in the waybill of the target package based on the package image.

[0030] In this embodiment of the application, the missing logistics information may be a waybill number, destination address, etc. that the sorting system failed to identify, and is not specifically limited here.

[0031] In this embodiment of the application, the waybill may include an image code (such as a barcode or QR code) recording the waybill number, as well as information such as the waybill number, shipper information, consignee information, carrier information, origin, and destination.

[0032] In this embodiment of the application, the package image may include the original image acquired for the target package, and may also include an image obtained by preprocessing the original image such as cutting and straightening.

[0033] Step S220: Perform text recognition processing on the package image to obtain the text recognition result of the package image.

[0034] In this embodiment, the text recognition processing refers to the process of extracting and converting text information in a package image using Optical Character Recognition (OCR) technology. This process may include preprocessing, character segmentation, feature extraction, and pattern matching steps to convert the text content in the image into machine-coded text.

[0035] In this embodiment, the text recognition result is text information on the parcel waybill obtained after text recognition processing. The text recognition result may include, but is not limited to, the recipient's and sender's names, addresses, contact numbers, postal codes, and any other information on labels or tags. The text recognition result can be further used for automated processing, such as automatically filling in logistics information, verifying address accuracy, or providing a basis for parcel classification and routing selection.

[0036] In this embodiment of the application, the text recognition result may be obtained by recognizing the text in the area where the missing logistics information is located in the package image, or it may be obtained by recognizing the text in the entire package image or the waybill area in the package image.

[0037] Step S230: Based on the package image of the target package and the text recognition result, generate a code supplementation task for the target package; the code supplementation task is used to instruct the code supplementation personnel at the code supplementation client to supplement the missing logistics information in the waybill of the target package based on the text recognition result.

[0038] In this embodiment of the application, the complementation task may carry the package image of the target package, the text recognition result, and the information in the complementation request.

[0039] In this embodiment of the application, the complement code client is used to obtain the complement code task assigned to it, as well as the package image and its text recognition result corresponding to the complement code task.

[0040] In this embodiment, after receiving a replenishment request for a target package and an image of the package from the sorting system, text recognition processing is performed on the package image to obtain the text recognition result. Based on the package image and the text recognition result, a replenishment task for the target package is generated. This allows replenishment personnel to edit or confirm the text recognition result based on the package image displayed on the replenishment client, thereby obtaining the missing logistics information in the waybill of the target package. This allows replenishment personnel to complete the replenishment task by confirming or correcting only a small amount of information, simplifying the replenishment process, reducing the number of steps required, shortening the replenishment time, and improving replenishment efficiency. Furthermore, it helps reduce errors that may occur due to manual operation.

[0041] based on Figure 2 In addition to the method described in the embodiments of this specification, some specific implementation schemes of the method are also provided, which will be described below.

[0042] In practical applications, package images often include not only waybills but also a large amount of unnecessary background information or interfering elements, resulting in slow text recognition speed and a high risk of misrecognition. Therefore, this specification provides some specific implementation schemes to improve text recognition efficiency by performing text recognition processing only on the waybill area of ​​the package image. The specific implementation is as follows:

[0043] Optionally, before performing text recognition processing on the package image, the method further includes: segmenting the package image into a waybill based on a target detection algorithm to obtain a waybill image of the target package; the target detection algorithm is used to detect the waybill of the target package in the region of the package image; the text recognition processing on the package image to obtain the text recognition result of the package image includes: performing text recognition processing on the waybill image to obtain the text recognition result.

[0044] In this embodiment of the application, the target detection algorithm is used to automatically locate and select the specific location of the waybill in the package image, thereby accurately extracting the waybill image and reducing the impact of non-text areas on text recognition.

[0045] Specifically, the object detection algorithm may include, but is not limited to, R-CNN, YOLO (You Only Look Once), SSD (Single Shot MultiBox Detector), RetinaNet, CenterNet, FCOS, etc., without any specific limitation here.

[0046] In this embodiment, the waybill cutting is used to separate the area containing the waybill in the package image to form an independent waybill image. The waybill image is a portion of the image precisely cut out from the original package image, containing only the waybill information.

[0047] In this embodiment of the application, the text recognition result refers to the text information obtained by performing text recognition processing on the entire waybill image. This information usually includes missing logistics information.

[0048] In practical applications, waybills typically use a formatted text design, where the location of logistics information is pre-defined. Therefore, text recognition results can specifically refer to the text information obtained by recognizing and processing the missing logistics information portions in a waybill image.

[0049] In this embodiment, based on an object detection algorithm, the package image is segmented into a waybill image to obtain the waybill image of the target package. The waybill image is then subjected to text recognition processing to obtain the text recognition result. Thus, by employing an object detection algorithm to accurately segment the waybill portion of the package image, and performing text recognition only on the waybill image, the amount of data processed is reduced, the text recognition processing speed is improved, computational resource consumption is effectively reduced, and the recognition accuracy is increased. This approach is particularly suitable for large-scale automated logistics information processing scenarios.

[0050] In practical applications, sorting systems collect package images from multiple angles, including top, bottom, front, back, left, and right. Waybills may appear in multiple images. Typically, the waybill is located at the top of the package; besides the bottom scan image, it appears in the top scan image and images from the front, back, left, and right. The re-coding personnel need to select the clearest image of the waybill from multiple package images (usually the top or bottom scan image), and then zoom in and rotate that image to clearly see the logistics information in the waybill area, thus reading and inputting any missing logistics information. It's clear that the re-coding process is cumbersome and time-consuming due to the numerous steps involved in manipulating the package images. Therefore, this specification provides specific implementation schemes to reduce the steps of selecting the clearest image of the waybill and zooming / rotating that image, thereby improving the efficiency of the re-coding operation. The specific implementations are as follows:

[0051] Optionally, the code completion task carries the waybill image or the storage path of the waybill image; the waybill image is used to be displayed preferentially on the code completion client when the code completion personnel process the code completion task.

[0052] In this embodiment of the application, when using a storage server to store the package image of the target package, after cutting the package image into a waybill image to obtain the waybill image of the target package, the waybill image can be stored on the storage server. The code completion task can simply carry the waybill image to the storage server.

[0053] In this embodiment, after the code completion personnel begin processing the code completion task based on the code completion client, if the image of the target package includes the waybill image, the waybill image is displayed first in full-image mode. Other waybill images are displayed in full-image mode only if they do not include the waybill image.

[0054] In this embodiment, the code replacement task carries the waybill image or its storage path. When the code replacement personnel process the code replacement task, the waybill image is displayed first on the code replacement client. This reduces the steps required for code replacement personnel to select the clearest image of the waybill and to zoom in and rotate that image, improving the efficiency of the code replacement operation. It also helps to obtain timely feedback on the code replacement results before abnormal packages are taken offline at the abnormal point, avoiding package backlog.

[0055] Based on this, the embodiments in this specification also provide some specific implementation schemes to further reduce the operation steps of the code completion personnel when processing code completion tasks and improve code completion efficiency. The specific implementation is as follows:

[0056] Optionally, before performing text recognition processing on the package image, the method further includes: performing image preprocessing on the waybill image; the image preprocessing includes performing text orientation correction processing on the waybill image.

[0057] In the embodiments of this application, the image preprocessing may include not only text direction correction processing, but also contrast enhancement, image denoising, perspective transformation, grayscale processing, etc., without specific limitations.

[0058] In this embodiment of the application, the text orientation correction process is used to rotate the waybill image so that the text orientation in the waybill image is aligned with the reading direction (horizontal direction).

[0059] In this embodiment, before performing text recognition processing on the package image, the waybill image undergoes image preprocessing, including text orientation correction. This reduces the number of steps required for code completion personnel to rotate the code image, further improving code completion efficiency. Furthermore, it also improves the accuracy and efficiency of text recognition.

[0060] In practical applications, a complement code server is typically used to receive complement code requests from the sorting system and to distribute complement code tasks to various complement code clients. Based on this, the embodiments in this specification also provide some specific implementation schemes that improve the flexibility and scalability of the complement code server by employing a storage-compute separation architecture. The specific implementation is as follows:

[0061] Optionally, the method is applied to a code replacement server; receiving the code replacement request from the sorting system for the target package, and the package image of the target package, includes: receiving the code replacement request from the sorting system for the target package; the code replacement request carries device identification information of the device that captured the package image, and package identification information of the target package at the sorting system; based on the device identification information and the package identification information, obtaining the package image of the target package from a storage server; the storage server is used to store the package images collected by the sorting system for the target package.

[0062] In this embodiment of the application, the storage server can be used to store package images collected by the sorting system for the target package; the storage server can also be used to store the waybill image.

[0063] In this embodiment, the filename and / or storage path of the package image stored on the storage server are determined based on the device identification information and the package identification information. Based on the device identification information and the package identification information, the package image of the target package can be queried from the storage server using a wildcard algorithm or regular expressions.

[0064] In this embodiment, the device identification information may be the identification information of the camera at the sorting system. The package identification information may be the serial number of the target package at the supplementary coding system, used to identify the target package.

[0065] In this embodiment of the application, the storage server may be an FTP (File Transfer Protocol) server or an object storage server.

[0066] In this embodiment, the sorting system stores the collected images on a storage server. Upon receiving a code replacement request, the code replacement server retrieves the package image of the target package from the storage server based on the device identification information of the capturing device and the package identification information in the code replacement request. This separates the code replacement task processing from the code replacement image storage, achieving storage-computing separation. The code replacement server can be independently expanded to adapt to different scales of data processing needs, ensuring the system can flexibly respond to business growth and improving the flexibility and scalability of the code replacement server.

[0067] This specification also provides some specific implementation schemes to further reduce the operational steps for code completion personnel and improve code completion efficiency. The specific implementations are as follows:

[0068] Optionally, the code completion request is used to instruct the completion of the waybill number of the target package based on the package image; the text recognition result includes the waybill number recognition result obtained by performing text recognition processing on the waybill number area in the package image; the code completion client is used to generate the code completion result of the code completion task based on the editing result or confirmation operation of the waybill number recognition result by the code completion personnel.

[0069] In this embodiment, when the code replacement personnel begin processing the code replacement task based on the code replacement client, the waybill number recognition result is displayed in the display area of ​​the code replacement client. Specifically, the waybill number recognition result is displayed in the input area of ​​the waybill number, so that the code replacement personnel can view and edit the waybill number recognition result.

[0070] In this embodiment of the application, the supplementary code result may include the waybill number, which may be the waybill number identification result confirmed by the supplementary code personnel, or the editing result of the waybill number identification result by the supplementary code personnel.

[0071] In this embodiment, when the code replacement personnel begin processing the code replacement task using the code replacement client, the waybill number identification result is displayed to facilitate feedback of the correct waybill number. This further simplifies the operation steps for code replacement personnel and helps improve code replacement efficiency.

[0072] This specification also provides some specific implementation schemes for automatically generating the two's complement result corresponding to the two's complement request, and the specific implementation is as follows:

[0073] Optionally, after performing text recognition processing on the package image to obtain the text recognition result of the package image, the process includes: determining whether the waybill number recognition result is the correct waybill number for the target package; if the waybill number recognition result is the correct waybill number for the target package, then generating a complement code result for the complement code request based on the waybill number recognition result.

[0074] In this embodiment of the application, determining whether the waybill number recognition result is the correct waybill number for the target package includes: determining whether the waybill number recognition result conforms to a preset format for waybill numbers; if the waybill number recognition result conforms to the preset format for waybill numbers, comparing the second waybill information determined based on the text recognition result with the third waybill information queried based on the waybill number recognition result; and determining whether the waybill number recognition result is the correct waybill number for the target package based on whether the first waybill information and the third waybill information determined from the text recognition result are consistent.

[0075] In this embodiment of the application, the complement code result includes the waybill number identification result.

[0076] In this embodiment, for a request to supplement the waybill number, if it is determined that the waybill number identification result is the correct waybill number for the target package, then a supplementary code result for the supplementary code request is generated based on the waybill number identification result. This achieves automatic completion of the entire process from image recognition to information verification to supplementary code result generation, significantly improving the efficiency and accuracy of supplementary code processing tasks.

[0077] This specification also provides some specific implementation schemes for automatically generating the two's complement result corresponding to the two's complement request, and the specific implementation is as follows:

[0078] Optionally, after performing text recognition processing on the package image to obtain the text recognition result of the package image, the process includes: if the waybill number recognition result includes an incomplete waybill number, then performing a fuzzy query based on the waybill number recognition result to obtain a candidate waybill number and the first waybill information corresponding to the candidate waybill number; determining the candidate waybill number corresponding to the first waybill information that is consistent with the second waybill information in the text recognition result as the target waybill number of the target package; the target waybill number is used to generate the complement code result for the complement code request.

[0079] In this embodiment of the application, whether the waybill number identification result is an incomplete waybill number can be determined based on whether the waybill number identification result conforms to the preset format of the waybill number.

[0080] In this embodiment of the application, the candidate waybill number and its corresponding first waybill information can be a fuzzy query result obtained by performing a fuzzy query based on the waybill number identification result.

[0081] In this embodiment of the application, the target waybill number can be used directly or after confirmation by the code supplementation personnel as the waybill number of the target package. In other words, the target waybill number can be used to generate a code supplementation task for the target package, or to generate a code supplementation result for the target package.

[0082] In this embodiment of the application, if the target waybill number is unique, then the target waybill number can be directly used as the waybill number of the target package, and a supplementary code result for the supplementary code request can be generated accordingly. In this case, the target waybill number can also be used as the waybill number of the target package after confirmation by the supplementary code personnel.

[0083] In this embodiment of the application, when multiple target waybill numbers are obtained (e.g., the waybill is severely damaged), the target waybill number can be confirmed by the code replacement personnel at the code replacement client and used as the waybill number of the target package.

[0084] In this embodiment of the application, if the number of candidate waybill numbers or target waybill numbers is greater than a preset number, the task of generating supplementary codes for the target package is directly abandoned. By abandoning the time-consuming and low-success-rate supplementary code task, resources and time are allocated to other supplementary code tasks that are more likely to succeed, thereby improving the overall supplementary code efficiency. This helps to reduce the number of abnormal packages that are taken offline at the abnormal port and avoids package backlog.

[0085] In this embodiment, when the waybill number recognition result includes an incomplete waybill number, a fuzzy query is performed based on the waybill number recognition result, and the target waybill number of the target package is filtered from the fuzzy query result based on the second waybill information in the text recognition result. This improves the code completion efficiency when the waybill number recognition result includes an incomplete waybill number.

[0086] Exemplary device

[0087] The apparatus embodiments of this application can be used to execute the method embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the method embodiments of this application.

[0088] Figure 3 The diagram shown is a block diagram of a two's complement image processing apparatus provided in one embodiment of this application. Figure 3As shown, the device 300 includes: a receiving module 310, used to receive a code replenishment request from the sorting system for a target package, and a package image of the target package; the code replenishment request is used to instruct the missing logistics information in the waybill of the target package to be replenished based on the package image; a recognition module 320, used to perform text recognition processing on the package image to obtain the text recognition result of the package image; and a generation module 330, used to generate a code replenishment task for the target package based on the package image of the target package and the text recognition result; the code replenishment task is used to instruct the code replenishment personnel at the code replenishment client to replenish the missing logistics information in the waybill of the target package based on the text recognition result.

[0089] Optionally, the device 300 further includes: a cutting module, used to cut the package image into waybill images based on a target detection algorithm to obtain a waybill image of the target package; the target detection algorithm is used to detect the waybill of the target package in the region of the package image; and the recognition module 320 is used to perform text recognition processing on the waybill image to obtain the text recognition result.

[0090] Optionally, the code completion task carries the waybill image or the storage path of the waybill image; the waybill image is used to be displayed preferentially on the code completion client when the code completion personnel process the code completion task.

[0091] Optionally, the recognition module 320 is further configured to perform image preprocessing on the waybill image; the image preprocessing includes text orientation correction processing on the waybill image.

[0092] Optionally, the device 300 is a code supplementation server; the receiving module 310 is used to receive a code supplementation request from the sorting system for a target package; the code supplementation request carries device identification information of the device that captured the package image, and package identification information of the target package at the sorting system; based on the device identification information and the package identification information, the package image of the target package is obtained from the storage server; the storage server is used to store the package images collected by the sorting system for the target package.

[0093] Optionally, the code completion request is used to instruct the completion of the waybill number of the target package based on the package image; the text recognition result includes the waybill number recognition result obtained by performing text recognition processing on the waybill number area in the package image; the code completion client is used to generate the code completion result of the code completion task based on the editing result or confirmation operation of the waybill number recognition result by the code completion personnel.

[0094] Optionally, the device 300 further includes: a judgment module, used to judge whether the waybill number identification result is the correct waybill number for the target package; and a result generation module, used to generate a complement code result for the complement code request based on the waybill number identification result if the waybill number identification result is the correct waybill number for the target package.

[0095] Optionally, the device 300 further includes: a fuzzy query module, used to perform a fuzzy query based on the waybill number recognition result if the waybill number recognition result includes an incomplete waybill number, to obtain a candidate waybill number and the first waybill information corresponding to the candidate waybill number; and a waybill number determination module, used to determine the candidate waybill number corresponding to the first waybill information that is consistent with the second waybill information in the text recognition result as the target waybill number of the target package; the target waybill number is used to generate a complement code result for the complement code request.

[0096] Exemplary electronic devices

[0097] Below, for reference Figure 4 This describes an electronic device according to embodiments of the present application. Figure 4 A block diagram of an electronic device according to an embodiment of this application is illustrated.

[0098] like Figure 4 As shown, the electronic device 400 includes one or more processors 410 and memory 420.

[0099] The processor 410 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 400 to perform desired functions.

[0100] The memory 420 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 410 may execute the program instructions to implement the two's complement image processing and / or other desired functions described in the various embodiments of this application above. Various contents, such as category correspondences, may also be stored in the computer-readable storage medium.

[0101] In one example, the electronic device 400 may also include an input device 430 and an output device 440, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0102] In addition, the input device 430 may also include, for example, a keyboard, a mouse, etc. The output device 440 can output various information to the outside. The output device 440 may include, for example, a monitor, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0103] Of course, for the sake of simplicity, Figure 4 Only some of the components of the electronic device 400 relevant to this application are shown in this illustration; components such as buses, input / output interfaces, etc., are omitted. In addition, the electronic device 400 may include any other suitable components depending on the specific application.

[0104] Exemplary computer program products and computer-readable storage media

[0105] In addition to the methods and apparatus described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in complement image processing according to various embodiments of this application as described in the "Exemplary Methods" section of this specification.

[0106] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0107] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in complement image processing according to various embodiments of this application as described in the "Exemplary Methods" section above.

[0108] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0109] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0110] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0111] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0112] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0113] It should be understood that the qualifiers “first,” “second,” “third,” “fourth,” “fifth,” and “sixth” used in the description of the embodiments of this application are only used to more clearly illustrate the technical solutions and are not intended to limit the scope of protection of this application.

[0114] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method of processing a complement image, characterized by, include: The system receives a code supplementation request for a target package from the sorting system, along with an image of the target package. The code supplementation request is used to instruct the system to supplement the missing logistics information in the waybill of the target package based on the package image. The package image is subjected to text recognition processing to obtain the text recognition result of the package image; Based on the package image of the target package and the text recognition result, a code supplementation task is generated for the target package; the code supplementation task is used to instruct the code supplementation personnel at the code supplementation client to supplement the missing logistics information in the waybill of the target package based on the text recognition result.

2. The method according to claim 1, characterized in that, Before performing text recognition processing on the package image, the method further includes: Based on the target detection algorithm, the package image is segmented into waybill images to obtain the waybill images of the target package; the target detection algorithm is used to detect the waybill of the target package in the region of the package image. The step of performing text recognition processing on the package image to obtain the text recognition result of the package image includes: The waybill image is subjected to text recognition processing to obtain the text recognition result.

3. The method of claim 2, wherein, The code completion task carries the waybill image or the storage path of the waybill image; the waybill image is used to be displayed preferentially on the code completion client when the code completion personnel process the code completion task.

4. The method of claim 3, wherein, The process of obtaining the text recognition result also includes: The waybill image is preprocessed; the image preprocessing includes text orientation correction processing of the waybill image.

5. The method according to claim 1, characterized in that, The method is applied to a code replacement server; the receiving of the code replacement request from the sorting system for a target package, and the package image of the target package, includes: The sorting system receives a code replacement request for a target package; the code replacement request carries the device identification information of the device that captured the image of the package, and the package identification information of the target package at the sorting system. Based on the device identification information and the package identification information, the package image of the target package is obtained from the storage server; the storage server is used to store the package images collected by the sorting system for the target package.

6. The method according to claim 1, characterized in that, The code completion request is used to instruct the addition of the waybill number of the target package based on the package image; the text recognition result includes the waybill number recognition result obtained by performing text recognition processing on the waybill number area in the package image; the code completion client is used to generate the code completion result of the code completion task based on the editing result or confirmation operation of the waybill number recognition result by the code completion personnel.

7. The method according to claim 6, characterized in that, After performing text recognition processing on the package image to obtain the text recognition result of the package image, the process includes: Determine whether the waybill number identification result is the correct waybill number for the target package; If the waybill number identification result is the correct waybill number for the target package, then a complement code result for the complement code request is generated based on the waybill number identification result.

8. The method according to claim 6, characterized in that, After performing text recognition processing on the package image to obtain the text recognition result of the package image, the process includes: If the waybill number identification result includes an incomplete waybill number, then a fuzzy query is performed based on the waybill number identification result to obtain a candidate waybill number and the first waybill information corresponding to the candidate waybill number; The candidate waybill number corresponding to the first waybill information that is consistent with the second waybill information in the text recognition result is determined as the target waybill number of the target package; the target waybill number is used to generate the complement code result for the complement code request.

9. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is used to perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, cause the processor to perform the method as described in any one of claims 1 to 7.

Images