Package image processing method, device, computer equipment and storage medium

Abstract

The present application relates to a package image processing method, device, computer equipment and storage medium. The method comprises: obtaining a package image; inputting the package image into an image segmentation model to obtain a pickup image containing a pickup code; inputting the pickup image into a text recognition model to obtain the pickup code in the pickup image; using the pickup code as the file name of the pickup image, and binding the pickup image with the corresponding user ID according to the file name. The use of this method can improve the efficiency of package information query.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a package image processing method, apparatus, computer equipment and storage medium. Background Art

[0002] With the development of computer technology, electronic commerce (Electronic Commerce) technology has emerged. Electronic commerce uses computer technology, network technology and telecommunication technology to realize the electronic, digital and networked nature of the entire business (buying and selling) process. In the process of e-commerce transactions, sellers often transfer goods to customers by express parcels. After the express parcels arrive at the express post station, customers need to go to the express post station to pick up the express parcels according to the pickup code. At present, the common delivery method of express post stations is to paste a delivery label on each parcel to be delivered, and then put the items in layers according to the shelf number on the delivery label, and then send the pickup code on the delivery label to the corresponding pickup customer. When the customer picks up the parcel, he finds the corresponding shelf according to the pickup code, and compares the pickup code of each parcel on the shelf in turn to take out his own express parcel.

[0003] However, with the current method of picking up express parcels, customers only have a pickup code and no more express parcel information. Customers need to compare numerous express parcels one by one, and it takes a long time to find the parcel. Summary of the invention

[0004] Based on this, it is necessary to provide a package image processing method, device, computer equipment and storage medium that can improve the efficiency of package information query in response to the above technical problems.

[0005] A package image processing method, the method comprising:

[0006] Get the package image;

[0007] Inputting the package image into an image segmentation model to obtain a pickup image including a pickup code;

[0008] Inputting the pickup image into a text recognition model to obtain a pickup code in the pickup image;

[0009] The pickup code is used as the file name of the pickup image, and the pickup image is bound to the corresponding user ID according to the file name.

[0010] In one embodiment, the method further comprises:

[0011] Receiving a target user identifier sent by a user terminal;

[0012] Searching for a target pickup image according to the target user identifier;

[0013] The found target pickup image is sent to the user terminal.

[0014] In one embodiment, the method further comprises:

[0015] Get sample package image;

[0016] Determine key points in the sample package image and perform feature annotation on the key points; the key points are points containing coding information;

[0017] The image segmentation model is trained by the sample package image after feature annotation.

[0018] In one embodiment, the method further comprises:

[0019] Obtain sample pickup images;

[0020] Determine the sample pickup code in the sample pickup image, and perform feature annotation on the sample pickup code;

[0021] The text recognition model is trained by the sample pickup images after feature annotation.

[0022] In one embodiment, the step of inputting the package image into an image segmentation model to obtain a pickup image containing a pickup code includes:

[0023] inputting the package image into an image segmentation model;

[0024] extracting image features of the package image by using the image segmentation model;

[0025] The package image is segmented according to the image features to obtain a pickup image containing a pickup code; wherein one pickup code corresponds to one pickup image.

[0026] In one embodiment, the step of inputting the pickup image into a text recognition model to obtain the pickup code in the pickup image includes:

[0027] Inputting the pickup image into a text recognition model;

[0028] Extracting text features of the pickup image by using the text recognition model;

[0029] The pickup image is subjected to text recognition according to the text features to obtain the pickup code in the pickup image.

[0030] In one embodiment, the step of binding the pickup image to the corresponding user ID according to the file name includes:

[0031] Obtaining a mapping relationship table between the pickup code and the user identifier;

[0032] Determine the corresponding relationship between the user identifier and the file name according to the mapping relationship table;

[0033] According to the corresponding relationship between the user identification and the file name, the pickup image is bound to the corresponding user identification.

[0034] A package image processing device, the device comprising:

[0035] An acquisition module, used to acquire a package image;

[0036] A segmentation module, used for inputting the package image into an image segmentation model to obtain a pickup image containing a pickup code;

[0037] A recognition module, used for inputting the pickup image into a text recognition model to obtain the pickup code in the pickup image;

[0038] The binding module is used to use the pickup code as the file name of the pickup image, and bind the pickup image to the corresponding user identification according to the file name.

[0039] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented:

[0040] Get the package image;

[0041] Inputting the package image into an image segmentation model to obtain a pickup image including a pickup code;

[0042] Inputting the pickup image into a text recognition model to obtain a pickup code in the pickup image;

[0043] The pickup code is used as the file name of the pickup image, and the pickup image is bound to the corresponding user ID according to the file name.

[0044] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0045] Get the package image;

[0046] Inputting the package image into an image segmentation model to obtain a pickup image including a pickup code;

[0047] Inputting the pickup image into a text recognition model to obtain a pickup code in the pickup image;

[0048] The pickup code is used as the file name of the pickup image, and the pickup image is bound to the corresponding user ID according to the file name.

[0049] The above-mentioned package image processing method, device, computer equipment and storage medium obtain a package image, input the package image into an image segmentation model, obtain a pickup image containing a pickup code, input the pickup image into a text recognition model, obtain the pickup code in the pickup image, use the pickup code as the file name of the pickup image, and bind the pickup image to the corresponding user ID according to the file name. In this way, since the binding relationship between the user ID and the corresponding pickup image is stored in the server, the server can provide a function of quickly querying package information. When looking for a package, the pickup image corresponding to the package can be obtained by only using the user ID, and then the user can quickly find the package according to the package information in the pickup image. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A diagram showing an application scenario of a package image processing method in an embodiment;

[0051] Figure 2 is a schematic flow chart of a package image processing method in one embodiment;

[0052] Figure 3 is a schematic diagram of wrapping an image in one embodiment;

[0053] Figure 4 A schematic diagram of a pickup image in one embodiment;

[0054] Figure 5 A flowchart of an application scenario of a package image processing method in an embodiment;

[0055] Figure 6 A schematic diagram of a flow chart of a code recognition system processing a package image in one embodiment;

[0056] Figure 7 is a structural block diagram of a package image processing device in one embodiment;

[0057] Figure 8 is a structural block diagram of a package image processing device in another embodiment;

[0058] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0059] 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.

[0060] The package image processing method provided in this application can be applied to Figure 1 In the application environment shown. The application environment includes a terminal 102 and a server 104. The terminal 102 communicates with the server 104 through a network. The terminal 102 may specifically include a desktop terminal or a mobile terminal. The mobile terminal may specifically include at least one of a mobile phone, a tablet computer, and a laptop computer. The server 104 may be implemented as an independent server or a server cluster composed of multiple servers. Those skilled in the art will understand that Figure 1 The application environment shown in is only a part of the scenarios related to the present application solution and does not constitute a limitation on the application environment of the present application solution.

[0061] The server 104 obtains the package image from the terminal 102, and inputs the package image into the image segmentation model to obtain the pickup image containing the pickup code. The server 104 inputs the pickup image into the text recognition model to obtain the pickup code in the pickup image. The server 104 uses the pickup code as the file name of the pickup image, and binds the pickup image to the corresponding user ID according to the file name.

[0062] In one embodiment, Figure 2 As shown, a package image processing method is provided, which is applied to Figure 1 Taking the server 104 in the example as an example, the following steps are included:

[0063] S202, obtaining a package image.

[0064] The package image is an image including at least one package.

[0065] Specifically, the courier can place the parcels with delivery labels on the pickup shelf in sequence, with the delivery labels facing outwards. The delivery labels contain corresponding pickup codes, which are unique codes for identifying the parcels. The courier can use a terminal, such as a mobile phone, iPad, or camera, to take a photo of the parcel on the pickup shelf to obtain a package image. The terminal can upload the package image to the server, and the server can obtain the package image.

[0066] In one embodiment, the package image may be pre-stored in a third-party storage device, and the server may be in communication with the third-party storage device to directly obtain the package image from the third-party storage device.

[0067] In one embodiment, Figure 3 The package image shown is an image of packages placed on the second layer of the pickup shelf 1. The package image includes 7 packages, each of which is affixed with a corresponding delivery label, each of which includes a pickup code, such as 1-2-2007, and a QR code of the corresponding package.

[0068] S204: Input the package image into an image segmentation model to obtain a pickup image including a pickup code.

[0069] The image segmentation model is a model for segmenting a package image into a pickup image. The pickup image is an image corresponding to each pickup package.

[0070] Specifically, the server may pre-train an image segmentation model, and after acquiring the package image, input the package image into the image segmentation model, and segment the package image through the image segmentation model to obtain a pickup image containing the pickup code.

[0071] For example, Figure 3 The package image including 7 packages shown in FIG. 1 is input into the image segmentation model, and 7 pickup images can be obtained, each of which contains its own pickup code. For example, Figure 4 As shown, this is a pickup image containing the pickup code 1-2-2002.

[0072] S206, inputting the pickup image into a text recognition model to obtain the pickup code in the pickup image.

[0073] The text recognition model is a model for recognizing text in the pickup image.

[0074] Specifically, the server may pre-train a text recognition model. After acquiring the pickup image, the server may input the pickup image into the text recognition model, and recognize the text in the pickup image through the text recognition model to obtain the pickup code in the pickup image.

[0075] In one embodiment, the text recognition model may specifically be an OCR (Optical Character Recognition) text recognition model.

[0076] S208, using the pickup code as the file name of the pickup image, and binding the pickup image with the corresponding user ID according to the file name.

[0077] The file name of the pickup image is a file name that uniquely identifies the pickup image. The user ID is a string used to uniquely identify the user, and the user ID may include at least one of numbers, letters, and special characters. The special characters may specifically be an underscore, an asterisk, a pound sign, or a percent sign.

[0078] Specifically, after the server identifies the corresponding pickup code from the pickup image, it can use the corresponding pickup code as the file name of the pickup image. The server can obtain a mapping relationship table between the pickup code and the user ID, and then bind the pickup image to the corresponding user ID according to the file name and the mapping relationship table.

[0079] In the above-mentioned package image processing method, by acquiring a package image, the package image is input into an image segmentation model to obtain a pickup image containing a pickup code, the pickup image is input into a text recognition model to obtain the pickup code in the pickup image, the pickup code is used as the file name of the pickup image, and the pickup image is bound to the corresponding user ID according to the file name. In this way, since the binding relationship between the user ID and the corresponding pickup image is stored in the server, the server can provide a function of quickly querying package information. When searching for a package, the pickup image corresponding to the package can be obtained by only using the user ID, and then the user can quickly find the package according to the package information in the pickup image.

[0080] In one embodiment, the package image processing method further includes: receiving a target user identifier sent by a user terminal; searching for a target pickup image according to the target user identifier; and sending the found target pickup image to the user terminal.

[0081] The target user ID is the user ID corresponding to the user who is searching for the package. The target pickup image is the pickup image of the package that the user who is searching for the package is searching for.

[0082] Specifically, the pickup user can send the target user identifier to the server through the client application or applet in the user terminal. The server can receive the target user identifier sent by the user terminal and search for the target pickup image according to the target user identifier. The server can send the found target pickup image to the user terminal.

[0083] It can be understood that after the user terminal receives the target pickup image, the pickup user can obtain more package information from the target pickup image, such as the shape of the package, the color of the package, and the relative position of the package. Then, based on the rich package information, the pickup user can quickly find his own package from the pickup shelf where many packages are placed. Compared with the traditional situation where there is only a pickup code but no more express package information, it can effectively shorten the time for the pickup user to find the package.

[0084] In the above embodiment, the target pickup image is searched through the target user identification, and the found target pickup image is sent to the user terminal, which improves the efficiency of package information query and allows the user to obtain more package information from the target pickup image, thereby quickly finding his or her own package from the pickup shelf where many packages are placed, saving time in searching for the package.

[0085] In one embodiment, the package image processing method further includes: obtaining a sample package image; determining key points in the sample package image and performing feature annotation on the key points; the key points are points containing coding information; and training an image segmentation model using the feature-annotated sample package image.

[0086] The sample package image is sample data used to train the image segmentation model.

[0087] Specifically, the server may obtain a sample package image, determine key points in the sample package image, and perform feature annotation on the key points. The key points are points containing coded information. The server may input the feature-annotated sample package image into the image segmentation model to obtain an output sample pickup image. Then, the server may adjust the model parameters of the image segmentation model according to the key points in the sample pickup image and the package image to complete the training of the image segmentation model.

[0088] In one embodiment, the key points in the sample package image may specifically include a QR code on a delivery label of the package, edge points of the package, and the like.

[0089] In the above embodiment, the image segmentation model is trained by using the sample package images after feature annotation, so that the image segmentation model has the ability to accurately segment the package images, further improving the efficiency of package information query.

[0090] In one embodiment, the package image processing method further includes: acquiring a sample pickup image; determining a sample pickup code in the sample pickup image, and feature-labeling the sample pickup code; and training a text recognition model using the feature-labeled sample pickup image.

[0091] Among them, the sample pickup image is the sample data used to train the text recognition model.

[0092] Specifically, the server can obtain the sample pickup image, determine the sample pickup code in the sample pickup image, and perform feature annotation on the sample pickup code. The server can input the feature-annotated sample pickup image into the text recognition model to obtain the output sample pickup code. Then, the server can adjust the model parameters of the text recognition model according to the sample pickup code and the sample pickup code in the sample pickup image to complete the training of the text recognition model.

[0093] In the above embodiment, the text recognition model is trained by using the sample pickup images after feature annotation, so that the text recognition model has the ability to accurately identify the pickup code, further improving the efficiency of package information query.

[0094] In one embodiment, step S202, that is, inputting the package image into the image segmentation model to obtain the pickup image including the pickup code, specifically includes: inputting the package image into the image segmentation model; extracting image features of the package image through the image segmentation model; performing image segmentation on the package image according to the image features to obtain the pickup image including the pickup code; wherein one pickup code corresponds to one pickup image.

[0095] Specifically, the server may input the package image into the image segmentation model. For each package image, the package image contains corresponding image features, and the server may extract the image features of the package image through the image segmentation model. Then, the server may perform image segmentation on the package image according to the image features to obtain a pickup image containing a pickup code. One pickup code corresponds to one pickup image.

[0096] In the above embodiment, the image features of the package image are extracted by the image segmentation model, and the package image is segmented according to the image features, thereby further improving the segmentation accuracy of the image segmentation model.

[0097] In one embodiment, step S206, that is, inputting the pickup image into the text recognition model to obtain the pickup code in the pickup image, specifically includes: inputting the pickup image into the text recognition model; extracting the text features of the pickup image through the text recognition model; performing text recognition on the pickup image according to the text features to obtain the pickup code in the pickup image.

[0098] Specifically, the server may input the pickup image into the text recognition model. For each pickup image, the pickup image contains corresponding text features, and the server may extract the text features of the pickup image through the text recognition model. Furthermore, the server may perform text recognition on the pickup image according to the text features of the pickup image to obtain the pickup code in the pickup image.

[0099] In the above embodiment, the text features of the pickup image are extracted by the text recognition model, and the text recognition is performed on the pickup image according to the text features, thereby further improving the recognition accuracy of the text recognition model.

[0100] In one embodiment, the step of binding the pickup image with the corresponding user ID according to the file name in step S20 specifically includes: obtaining a mapping relationship table between the pickup code and the user ID; determining the correspondence between the user ID and the file name according to the mapping relationship table; and binding the pickup image with the corresponding user ID according to the correspondence between the user ID and the file name.

[0101] Specifically, for each parcel, the parcel corresponds to a unique express waybill number. The server can generate a pickup code according to the express waybill number and the corresponding user ID, and generate a mapping relationship table between the pickup code and the user ID. The server can obtain the mapping relationship table between the pickup code and the user ID, and determine the corresponding relationship between the user ID and the file name according to the mapping relationship table. The server can bind the pickup image to the corresponding user ID according to the corresponding relationship between the user ID and the file name.

[0102] In the above embodiment, the corresponding relationship between the user ID and the file name is accurately determined through the mapping relationship table between the pickup code and the user ID, thereby improving the accuracy of binding the pickup image with the corresponding user ID.

[0103] In one embodiment, Figure 5 As shown, the courier can print out the corresponding delivery label according to the express waybill number of each package, and paste the delivery label on the corresponding package. The courier can place the packages on the corresponding pickup shelves in sequence according to the delivery labels, and place the delivery labels outward. The courier can take a photo of the package on the pickup shelf through a terminal, such as a mobile phone, to obtain the package image, and upload the package image to the server. The server processes the package image through a coding recognition system. Figure 6 As shown in the figure, the specific process of the server processing the package image through the code recognition system is as follows: the server can pre-process the package image, input the pre-processed package image into the image segmentation model, and obtain the pickup image containing the pickup code. Then, the server can input the pickup image into the OCR text recognition model, extract the pickup code in the pickup image, and use the pickup code as the file name of the pickup image. The server can bind the user ID with the corresponding pickup image. Since the binding relationship between the user ID and the corresponding pickup image has been stored in the service, the server provides a function of quickly querying the package information. When the pickup user goes to pick up the package, the user ID can be entered in the user terminal, and the user terminal can send the user ID to the server. The server can locally query the pickup image corresponding to the user ID and send the pickup image to the user terminal. Since the pickup image contains rich package information, such as the shape of the package, the color of the package, and the relative position of the package, the user can quickly find his package from the pickup shelf, saving time in finding the package.

[0104] It should be understood that although Figure 2 The steps are shown in order, but they are not necessarily executed in order. 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. Figure 2 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0105] In one embodiment, Figure 7 As shown, a package image processing device 700 is provided, comprising: an acquisition module 701, a segmentation module 702, a recognition module 703 and a binding module 704, wherein:

[0106] The acquisition module 701 is used to acquire the package image.

[0107] The segmentation module 702 is used to input the package image into the image segmentation model to obtain the pickup image containing the pickup code.

[0108] The recognition module 703 is used to input the pickup image into the text recognition model to obtain the pickup code in the pickup image.

[0109] The binding module 704 is used to use the pickup code as the file name of the pickup image, and bind the pickup image to the corresponding user identification according to the file name.

[0110] In one embodiment, the segmentation module 702 is further used to input the package image into an image segmentation model; extract image features of the package image through the image segmentation model; perform image segmentation on the package image according to the image features to obtain a pickup image containing a pickup code; wherein one pickup code corresponds to one pickup image.

[0111] In one embodiment, the recognition module 703 is also used to input the pickup image into a text recognition model; extract text features of the pickup image through the text recognition model; perform text recognition on the pickup image according to the text features to obtain the pickup code in the pickup image.

[0112] In one embodiment, the binding module 704 is also used to obtain a mapping relationship table between the pickup code and the user identifier; determine the correspondence between the user identifier and the file name based on the mapping relationship table; and bind the pickup image to the corresponding user identifier based on the correspondence between the user identifier and the file name.

[0113] refer to Figure 8In one embodiment, the package image processing device 700 further includes: a search module 705 and a training module 706, wherein:

[0114] The search module 705 is used to receive the target user identification sent by the user terminal; search for the target pickup image according to the target user identification; and send the found target pickup image to the user terminal.

[0115] The training module 706 is used to obtain a sample package image; determine key points in the sample package image and perform feature annotation on the key points; the key points are points containing coding information; and train the image segmentation model using the feature-annotated sample package image.

[0116] In one embodiment, the training module 706 is also used to obtain a sample pickup image; determine a sample pickup code in the sample pickup image, and perform feature annotation on the sample pickup code; and train a text recognition model using the feature-annotated sample pickup image.

[0117] The above-mentioned package image processing device obtains a package image, inputs the package image into an image segmentation model, obtains a pickup image containing a pickup code, inputs the pickup image into a text recognition model, obtains the pickup code in the pickup image, uses the pickup code as the file name of the pickup image, and binds the pickup image to the corresponding user ID according to the file name. In this way, since the binding relationship between the user ID and the corresponding pickup image is stored in the server, the server can provide a function of quickly querying package information. When searching for a package, the pickup image corresponding to the package can be obtained by only using the user ID, and then the user can quickly find the package according to the package information in the pickup image.

[0118] The specific definition of the package image processing device can be found in the definition of the package image processing method above, and will not be repeated here. Each module in the above package image processing device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0119] In one embodiment, a computer device is provided, which may be the above-mentioned Figure 1 The internal structure diagram of the server 104 in FIG. 1 may be as follows: Fig. 9As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. 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, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store package image processing data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a package image processing method is implemented.

[0120] Those skilled in the art will understand that Fig. 9 The 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.

[0121] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0122] Get the package image;

[0123] Input the package image into the image segmentation model to obtain a pickup image containing the pickup code;

[0124] Input the pickup image into the text recognition model to obtain the pickup code in the pickup image;

[0125] The pickup code is used as the file name of the pickup image, and the pickup image is bound to the corresponding user ID according to the file name.

[0126] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0127] Receiving a target user identifier sent by a user terminal;

[0128] Searching for a target pickup image according to a target user ID;

[0129] The found target pickup image is sent to the user terminal.

[0130] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0131] Get sample package image;

[0132] Determine the key points in the sample package image and perform feature annotation on the key points; the key points are points that contain coded information;

[0133] The image segmentation model is trained by using the sample parcel images after feature annotation.

[0134] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0135] Obtain sample pickup images;

[0136] Determine the sample collection code in the sample collection image, and perform feature annotation on the sample collection code;

[0137] The text recognition model is trained through sample pickup images after feature annotation.

[0138] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0139] Input the parcel image to the image segmentation model;

[0140] Extracting image features of the package image through an image segmentation model;

[0141] The package image is segmented according to the image features to obtain a pickup image containing a pickup code; wherein one pickup code corresponds to one pickup image.

[0142] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0143] Input the pickup image into the text recognition model;

[0144] Extract text features of the pickup image through a text recognition model;

[0145] The pickup image is subjected to text recognition according to text features to obtain the pickup code in the pickup image.

[0146] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0147] Obtain a mapping table between pickup codes and user IDs;

[0148] According to the mapping relationship table, determine the corresponding relationship between the user ID and the file name;

[0149] According to the correspondence between the user ID and the file name, the pickup image is bound to the corresponding user ID.

[0150] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0151] Get the package image;

[0152] Input the package image into the image segmentation model to obtain a pickup image containing the pickup code;

[0153] Input the pickup image into the text recognition model to obtain the pickup code in the pickup image;

[0154] The pickup code is used as the file name of the pickup image, and the pickup image is bound to the corresponding user ID according to the file name.

[0155] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0156] Receiving a target user identifier sent by a user terminal;

[0157] Searching for a target pickup image according to a target user ID;

[0158] The found target pickup image is sent to the user terminal.

[0159] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0160] Get sample package image;

[0161] Determine the key points in the sample package image and perform feature annotation on the key points; the key points are points that contain coded information;

[0162] The image segmentation model is trained by using the sample parcel images after feature annotation.

[0163] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0164] Obtain sample pickup images;

[0165] Determine the sample collection code in the sample collection image, and perform feature annotation on the sample collection code;

[0166] The text recognition model is trained through sample pickup images after feature annotation.

[0167] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0168] Input the parcel image to the image segmentation model;

[0169] Extracting image features of the package image through an image segmentation model;

[0170] The package image is segmented according to the image features to obtain a pickup image containing a pickup code; wherein one pickup code corresponds to one pickup image.

[0171] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0172] Input the pickup image into the text recognition model;

[0173] Extract text features of the pickup image through a text recognition model;

[0174] The pickup image is subjected to text recognition according to text features to obtain the pickup code in the pickup image.

[0175] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0176] Obtain a mapping table between pickup codes and user IDs;

[0177] According to the mapping relationship table, determine the corresponding relationship between the user ID and the file name;

[0178] According to the correspondence between the user ID and the file name, the pickup image is bound to the corresponding user ID.

[0179] Those skilled 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 non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0180] 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.

[0181] 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 package image processing method, characterized in that: The method comprises: Get the package image; Inputting the package image into an image segmentation model to obtain a pickup image containing a pickup code; the pickup code is generated according to the express waybill number corresponding to the package and the corresponding user identifier; Inputting the pickup image into a text recognition model to obtain a pickup code in the pickup image; The pickup code is used as the file name of the pickup image, and a mapping relationship table between the pickup code and the user identifier is obtained; the file name of the pickup image is a file name that uniquely identifies the pickup image; Determine the corresponding relationship between the user identifier and the file name according to the mapping relationship table; According to the corresponding relationship between the user identification and the file name, the pickup image is bound to the corresponding user identification.

2. The method according to claim 1, characterized in that The method further comprises: Receiving a target user identifier sent by a user terminal; Searching for a target pickup image according to the target user identifier; The found target pickup image is sent to the user terminal.

3. The method according to claim 1, characterized in that The method further comprises: Get sample package image; Determine key points in the sample package image and perform feature annotation on the key points; the key points are points containing coding information; The image segmentation model is trained by the sample package image after feature annotation.

4. The method according to claim 1, characterized in that: The method further comprises: Obtain sample pickup images; Determine the sample pickup code in the sample pickup image, and perform feature annotation on the sample pickup code; The text recognition model is trained by the sample pickup images after feature annotation.

5. The method according to claim 1, characterized in that The step of inputting the package image into an image segmentation model to obtain a pickup image including a pickup code comprises: inputting the package image into an image segmentation model; extracting image features of the package image by using the image segmentation model; The package image is segmented according to the image features to obtain a pickup image containing a pickup code; wherein one pickup code corresponds to one pickup image.

6. The method according to claim 1, characterized in that The step of inputting the pickup image into a text recognition model to obtain the pickup code in the pickup image includes: Inputting the pickup image into a text recognition model; Extracting text features of the pickup image by using the text recognition model; The pickup image is subjected to text recognition according to the text features to obtain the pickup code in the pickup image.

7. A package image processing device, characterized in that: The device comprises: An acquisition module, used to acquire a package image; A segmentation module, used to input the package image into an image segmentation model to obtain a pickup image containing a pickup code; the pickup code is generated according to the express waybill number corresponding to the package and the corresponding user identifier; A recognition module, used for inputting the pickup image into a text recognition model to obtain the pickup code in the pickup image; A binding module is used to use the pickup code as the file name of the pickup image, and obtain a mapping relationship table between the pickup code and the user identifier; the file name of the pickup image is a file name that uniquely identifies the pickup image; according to the mapping relationship table, the correspondence between the user identifier and the file name is determined; according to the correspondence between the user identifier and the file name, the pickup image is bound to the corresponding user identifier.

8. The device according to claim 7, characterized in that The device also includes: The training module is used to obtain a sample package image; determine key points in the sample package image and perform feature annotation on the key points; the key points are points containing coding information; and train the image segmentation model through the sample package image after feature annotation.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. 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 6 are implemented.

Images