WO2021196836A1 - 用于定位快递包裹的方法和装置 - Google Patents

用于定位快递包裹的方法和装置 Download PDF

Info

Publication number
WO2021196836A1
WO2021196836A1 PCT/CN2021/073321 CN2021073321W WO2021196836A1 WO 2021196836 A1 WO2021196836 A1 WO 2021196836A1 CN 2021073321 W CN2021073321 W CN 2021073321W WO 2021196836 A1 WO2021196836 A1 WO 2021196836A1
Authority
WO
WIPO (PCT)
Prior art keywords
express
image
order
courier
area
Prior art date
Application number
PCT/CN2021/073321
Other languages
English (en)
French (fr)
Inventor
周鹏
王云涛
周默
Original Assignee
北京沃东天骏信息技术有限公司
北京京东世纪贸易有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京沃东天骏信息技术有限公司, 北京京东世纪贸易有限公司 filed Critical 北京沃东天骏信息技术有限公司
Priority to EP21778855.3A priority Critical patent/EP4131100A4/en
Priority to US17/914,216 priority patent/US20230123879A1/en
Publication of WO2021196836A1 publication Critical patent/WO2021196836A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping
    • G06Q10/0833—Tracking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/587—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G06T7/75—Determining position or orientation of objects or cameras using feature-based methods involving models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/40—Document-oriented image-based pattern recognition
    • G06V30/42—Document-oriented image-based pattern recognition based on the type of document
    • G06V30/424—Postal images, e.g. labels or addresses on parcels or postal envelopes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning

Definitions

  • the embodiments of the present application relate to the field of computer technology, in particular to methods and devices for locating express packages.
  • the related express parcel positioning method is usually that the courier manually mark the express parcel, for example, write the last four digits of the mobile phone number on the express bill on the express bill; then, the express parcels are classified according to the mobile phone number and placed in different locations. Finally, when the customer comes to pick up the package, the customer’s express package will be searched in a specific area according to the mobile phone number provided by the customer.
  • This express parcel positioning method is more common in campus express delivery or township express delivery.
  • the embodiment of the present application proposes a method and device for locating express parcels.
  • an embodiment of the present application provides a method for locating a courier package, including: receiving a courier positioning request, where the courier positioning request is used to locate the courier corresponding to the target courier package from the courier image showing the courier package.
  • the courier location request includes the courier information; finds the location information of the pre-stored courier information corresponding to the courier information; uses the location information to generate the courier location result image, where the courier location result image includes the location identifier, and the location identifier is used to retrieve
  • the express image indicates the express note corresponding to the target express package; the express location result image is output.
  • the method before receiving the courier location request, includes: obtaining a courier image showing the courier package; based on the courier image and a pre-trained courier identification model, determining the at least one courier order identified from the courier image
  • the location information of each express order and the express information on each express order; the location information of each express order in at least one express order and the corresponding express information are stored in association.
  • the express image includes a regional express image
  • the express recognition model includes a express detection model, an express location recognition model, and an express information recognition model; and based on the express image and a pre-trained express recognition model, it is determined that the express image is identified
  • the location information of each express order in at least one express order and the express information on each express order including: based on the regional express image and express detection model, determine the express order area in the regional express image; enter the express order area into the express In the location identification model, the location information of each express order in at least one express order is obtained; the express order area is input into the express information identification model to obtain the express information on each express order in at least one express order.
  • the express delivery detection model includes a delivery order detection model and an express package inspection model; and based on the regional express image and the express delivery detection model, determining the express order area in the regional express image includes: inputting the regional express image into the express order detection In the model, obtain at least one initial express order area detected from the regional express image and the predicted probability corresponding to each initial express order area in at least one initial express order area; input the regional express image into the express package detection model to obtain The predicted probability corresponding to at least one express package area and each express package area in the at least one express package area detected in the regional express image; based on at least one initial express order area and each initial express order area in at least one initial express order area The corresponding predicted probability, at least one express package area and the predicted probability corresponding to each express package area in the at least one express package area, determine the express order area in the regional express image.
  • the express image includes a panoramic express image
  • the express recognition model further includes a panoramic recognition model; and based on the express image and the pre-trained express recognition model, it is determined that each express in at least one express order identified from the express image
  • the location information of the order and the express information on each express order including: input the regional express image and the panoramic express image into the panoramic recognition model to obtain the position information of the express order in the panoramic express image and the position information of the express order in the regional express image
  • an embodiment of the present application provides an apparatus for locating express parcels, including: a receiving unit configured to receive an express positioning request, wherein the express positioning request is used for locating from an express image showing the express package
  • the express delivery order corresponding to the target express package, the express delivery location request includes express delivery information
  • the search unit is configured to find the pre-stored location information of the express delivery order corresponding to the express delivery information
  • the generation unit is configured to use the location information to generate the express delivery location
  • the result image wherein the express location result image includes a location identifier, which is used to indicate the express order corresponding to the target express package from the express image
  • the output unit is configured to output the express location result image.
  • an embodiment of the present application provides an electronic device, the electronic device includes: one or more processors; a storage device, on which one or more programs are stored, when the above one or more programs are When executed by the or multiple processors, the above one or more processors implement the method described in any implementation manner in the first aspect.
  • an embodiment of the present application provides a computer-readable medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the method described in any implementation manner in the first aspect.
  • the method and device for locating express parcels provided by the above-mentioned embodiments of the present application receive the express locating request; then, search for the pre-stored position information of the express order corresponding to the express information included in the express locating request; and then Using the above-mentioned location information to generate an express delivery positioning result image that includes the express delivery note corresponding to the target express package from the above-mentioned express delivery image; finally, outputting the above-mentioned express delivery positioning result image.
  • the efficiency of express parcel positioning is improved, thereby improving the efficiency of express delivery.
  • Fig. 1 is an exemplary system architecture diagram to which various embodiments of the present application can be applied;
  • Figure 2 is a flowchart of an embodiment of the method for locating express parcels according to the present application
  • Fig. 3 is a schematic diagram of an application scenario of the method for locating express parcels according to the present application
  • Figure 4 is a flowchart of another embodiment of the method for locating express packages according to the present application.
  • FIG. 5 is a schematic diagram of another application scenario of the method for locating express parcels according to the present application.
  • Fig. 6 is a schematic structural diagram of an embodiment of a device for locating express parcels according to the present application.
  • Fig. 7 is a schematic structural diagram of a computer system suitable for implementing an electronic device according to an embodiment of the present application.
  • FIG. 1 shows an exemplary system architecture 100 to which an embodiment of the method for locating express parcels of the present application can be applied.
  • the system architecture 100 may include terminal devices 1011, 1012, and 1013, a network 102 and a server 103.
  • the network 102 is used to provide a medium for communication links between the terminal devices 1011, 1012, 1013 and the server 103.
  • the network 102 may include various connection types, such as wired, wireless communication links, or fiber optic cables, and so on.
  • the courier can use the terminal devices 1011, 1012, 1013 to interact with the server 103 through the network 102 to send or receive messages, etc. (for example, the server 103 can receive the courier location request sent by the terminal devices 1011, 1012, 1013, and the terminal devices 1011, 1012 , 1013 can also receive the express location result image sent by the server 103) and so on.
  • Various communication client applications such as image processing applications, express management applications, instant messaging software, etc., can be installed on the terminal devices 1011, 1012, and 1013.
  • the terminal devices 1011, 1012, and 1013 can first receive the express location request; after that, they can search for the pre-stored location information of the courier order corresponding to the courier information included in the aforementioned express location request; then, they can use the aforementioned location information to generate the express delivery.
  • the positioning result image wherein the express delivery positioning result image includes a positioning identifier for indicating the express order corresponding to the target express package from the express delivery image; finally, the express delivery positioning result image can be output.
  • the terminal devices 1011, 1012, and 1013 may be hardware or software.
  • the terminal devices 1011, 1012, and 1013 are hardware, they can be various electronic devices that support information interaction, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and so on.
  • the terminal devices 1011, 1012, and 1013 are software, they can be installed in the electronic devices listed above. It can be implemented as multiple software or software modules, or as a single software or software module. There is no specific limitation here.
  • the server 103 may be a server that provides various services. For example, it can be a back-end server that analyzes the express location request.
  • the server 103 can first receive the express location request from the terminal devices 1011, 1012, and 1013; after that, it can search for the location information of the courier order corresponding to the courier information included in the aforementioned express location request that is stored in advance; then, it can use the aforementioned location information , Generate an express positioning result image, wherein the express positioning result image includes a positioning identifier for indicating the express order corresponding to the target express package from the express image; finally, the express positioning result image can be output, for example, the above The express location result image is sent to the terminal devices 1011, 1012, and 1013.
  • the server 103 may be hardware or software.
  • the server 103 can be implemented as a distributed server cluster composed of multiple servers, or as a single server.
  • the server 103 is software, it can be implemented as multiple software or software modules (for example, to provide distributed services), or it can be implemented as a single software or software module. There is no specific limitation here.
  • the method for locating express parcels provided in the embodiments of the present application may be executed by the server 103, or may be executed by the terminal devices 1011, 1012, and 1013.
  • the terminal devices 1011, 1012, and 1013 can store the correspondence between the location information of the courier order and the corresponding courier information locally, and the terminal devices 1011, 1012, and 1013 can find the courier corresponding to the courier information locally. Single location information.
  • the server 103 and the network 102 may not exist in the exemplary system architecture 100 at this time.
  • terminal devices, networks, and servers in FIG. 1 are merely illustrative. There can be any number of terminal devices, networks, and servers according to implementation needs.
  • the method for locating express packages includes the following steps:
  • Step 201 Receive a courier location request.
  • the execution subject of the method for locating express parcels can receive the express locating request.
  • the aforementioned express delivery location request is usually used to locate the express order corresponding to the target express package from the express image on which the express package is presented.
  • the aforementioned target express package may be the express package to be found or to be located.
  • the courier usually needs to use a terminal device to take pictures of the area where the express package (which may be one express package or multiple express packages) is placed, so as to obtain the express image showing the express package.
  • Express delivery is usually delivered from the sender to the recipient in the form of a courier package.
  • the courier bill is usually a document that presents express-related information.
  • the express-related information can usually include the courier bill number, the sender's address information, the sender's contact information, the recipient's address information, and the recipient's contact information.
  • the express package usually corresponds to the express note, for example, the express note can be pasted on the express package.
  • couriers need to standardize the placement of express parcels. For example, it is necessary to ensure that the express bill on the express parcel is facing upwards, and it is better to leave a certain gap between each parcel.
  • the aforementioned express delivery location request usually includes express delivery information.
  • the aforementioned express delivery information may include, but is not limited to: part or all of the mobile phone number of the express recipient (for example, the last four digits of the mobile phone number), and the express order Part of the number or all of the number in the number (for example, the last four digits of the courier number).
  • Step 202 Search for pre-stored location information of the courier note corresponding to the courier information.
  • the execution subject may search for pre-stored location information of the courier note corresponding to the courier information.
  • the above-mentioned executive body usually pre-stores the correspondence between the express information and the location information of the express bill.
  • the location information of the above express order can be characterized in the form of ⁇ x, y, w, h ⁇ .
  • x and y can respectively be the abscissa and ordinate values of the preset position (for example, the upper left corner) of the express order (usually a rectangular area) in the preset coordinate system
  • w and h can respectively be the express order Width and height.
  • the above-mentioned preset coordinate system can be the world coordinate system or the preset express image coordinate system.
  • the lower left corner of the express image can be the coordinate origin, and the two adjacent sides of the express image These are the coordinate systems of the abscissa axis and the ordinate axis respectively.
  • Step 203 Use the location information to generate an express location result image.
  • the above-mentioned execution subject may use the location information found in step 202 to generate the express location result image.
  • the aforementioned express positioning result image may include a positioning mark, for example, it may be a positioning frame or a positioning arrow.
  • the above-mentioned positioning identifier is used to indicate the express note corresponding to the above-mentioned target express package from the above-mentioned express image.
  • the aforementioned express delivery positioning result image may be an image obtained by superimposing the aforementioned positioning mark on the aforementioned express delivery image.
  • Step 204 Output the express location result image.
  • the above-mentioned execution subject may output the express location result image generated in step 203. If the execution subject is a terminal device, the execution subject may present the express delivery positioning result image, so that the courier can find the target express package from a plurality of express parcels according to the positioning mark in the express positioning result image. If the execution subject is a server, the execution subject may send the courier positioning result image to the terminal device of the courier.
  • the aforementioned express delivery image may include a regional express delivery image.
  • the courier can upload the regional express image by clicking the upload icon used to upload the regional express image, so as to identify the express order corresponding to the target express package in the regional express image.
  • the execution subject can search for the pre-stored location information of the courier order in the regional express image corresponding to the courier information; afterwards, the location information can be used to generate the courier positioning result image, in the courier positioning result image
  • the location mark is used to indicate the courier note corresponding to the target courier package from the regional courier image.
  • the aforementioned express delivery image may include a panoramic express delivery image.
  • the courier can upload the panoramic express image by clicking the upload icon used to upload the panoramic express image to identify the courier list corresponding to the target express package in the panoramic express image.
  • the execution subject can search for the pre-stored location information of the courier order in the panoramic express image corresponding to the courier information; afterwards, the location information can be used to generate the courier positioning result image, in the courier positioning result image
  • the location mark is used to indicate the courier note corresponding to the target courier package from the panoramic courier image.
  • Fig. 3 is a schematic diagram of an application scenario of the method for locating express parcels according to this embodiment.
  • the courier can use the terminal device 301 to upload the courier image 302 showing the courier package.
  • the user informs the courier of the courier information (for example, the last four digits of the mobile phone number) during the process of picking up the courier.
  • the courier can enter the last four digits of the user’s mobile phone number 5118 into the query box 303 for querying the courier. Click the "query express" icon 304.
  • the terminal device 301 can receive an express location request for locating the express order (the express order corresponding to the last four digits 5118 of the mobile phone number) of the target express package from the express image 302. Then, the terminal device 301 can search for the location information of the courier note corresponding to the last four digits 5118 of the mobile phone number. Then, the terminal device 301 can generate and output the express location result image 305 by using the above-mentioned location information.
  • the express delivery positioning result image 305 usually includes a positioning mark, where the positioning mark is a positioning frame 306, and the positioning frame 306 is used to indicate from the express delivery image 302 the express order corresponding to the target express package.
  • the courier can find the target courier package from multiple courier packages according to the location identifier 306 in the courier location result image 305.
  • the method provided in the above-mentioned embodiment of the present application searches for the location information of the express order corresponding to the target express package requested to be located after receiving the express locating request for locating the express order corresponding to the target express package from the express image, Then, using the above-mentioned location information, an image of the express positioning result is generated.
  • the courier can quickly and accurately find the customer's courier package according to the positioning mark in the image of the above-mentioned express positioning result. This method improves the efficiency of express parcel positioning, thereby improving the efficiency of express delivery.
  • FIG. 4 shows a process 400 of another embodiment of a method for locating express parcels.
  • the process 400 of the method for locating express parcels includes the following steps:
  • Step 401 Obtain an express image showing the express package.
  • the execution subject of the method for locating the express package can obtain the express image showing the express package.
  • the execution subject is a terminal device of a courier
  • the courier can use the terminal device to take a picture of the area where the courier package is placed, so as to obtain the courier image showing the courier package.
  • the server can receive the express image showing the express package taken by the courier using the terminal device.
  • Step 402 based on the express image and the pre-trained express identification model, determine the location information of each express order and the express information on each express order in the at least one express order identified from the express image.
  • the above-mentioned execution subject may determine the location information and the location information of each express order in at least one express order identified from the above-mentioned express image based on the express image obtained in step 401 and the pre-trained express delivery recognition model.
  • Courier information on a courier list may be input the express delivery image into the express delivery identification model to obtain the location information of each express order and the express information on each express order in the at least one express order identified from the express delivery image.
  • the aforementioned express delivery identification model can be used to characterize the image and the location information of the express order identified from the image and the express information on the express order.
  • the location information of the express order may be characterized in the form of ⁇ x, y, w, h ⁇ .
  • x and y may respectively be the abscissa value and the ordinate value of the preset position of the express order (usually a rectangular area) in the preset coordinate system
  • w and h may be the width and height of the express order, respectively.
  • the above-mentioned preset coordinate system can be the world coordinate system or the preset express image coordinate system.
  • the lower left corner of the express image can be the coordinate origin, and the two adjacent sides of the express image These are the coordinate systems of the abscissa axis and the ordinate axis respectively.
  • the aforementioned express delivery information may include, but is not limited to: part or all of the number in the mobile phone number of the express recipient, and part or all of the number in the express order number.
  • Step 403 Associate and store the location information of each express order in the at least one express order and the corresponding express information.
  • the above-mentioned execution subject may store the location information of each express order in the at least one express order obtained in step 403 and the corresponding express information in association with each other.
  • Step 404 Receive the express location request.
  • Step 405 Search for pre-stored location information of the courier note corresponding to the courier information.
  • Step 406 Use the location information to generate an express location result image.
  • Step 407 Output the express location result image.
  • steps 404-407 can be performed in a manner similar to steps 201-204, and will not be repeated here.
  • the aforementioned express delivery image may include a regional express delivery image.
  • the above-mentioned regional express image usually refers to an image obtained by photographing a part of an area where a plurality of express parcels are placed. Therefore, the above-mentioned regional express image usually shows part of all express parcels. It should be noted that the image of the express delivery bill on the front side is usually displayed in the above regional express delivery image.
  • the aforementioned express delivery identification model may include an express delivery detection model, an express location identification model, and an express information identification model. The aforementioned express delivery detection model can be used to characterize the correspondence between the image and the express delivery order area in the image.
  • the aforementioned express order area may be an area containing an express order, for example, it may be the smallest area that includes an express order.
  • the aforementioned express location identification model can be used to characterize the correspondence between the express order area and the position information of the express order area in the express order area.
  • the aforementioned express information identification model can be used to characterize the correspondence between the express order area and the express information on the express order area in the express order area.
  • the above-mentioned executive body may determine the location information of each express order and the express information on each express order in at least one express order identified from the aforementioned express image based on the aforementioned express delivery image and the pre-trained express delivery identification model in the following manner:
  • the above-mentioned execution subject may first determine the express order area in the above-mentioned regional express image based on the above-mentioned regional express image and the above-mentioned express detection model. Specifically, the execution subject may input the regional express image into the express delivery detection model to obtain the express order area in the regional express image.
  • the execution subject may input the regional express image into the express delivery detection model to obtain the probability of whether each pixel in the regional express image is an express order area, thereby determining the express order area in the regional express image.
  • the express order area can be input into the express delivery location identification model to obtain the location information of each express delivery order in at least one express delivery order.
  • the express delivery order area can be input into the express delivery information identification model to obtain the express delivery information on each express delivery order in the at least one express delivery order.
  • the above-mentioned express delivery detection model may include an express order inspection model and an express package inspection model.
  • the aforementioned express order detection model may be used to characterize the correspondence between the image and the predicted probability corresponding to the initial express order area and the initial express order area detected from the image.
  • the aforementioned express package detection model can be used to characterize the correspondence between the image and the predicted probability corresponding to the express package area and the express package area detected from the image.
  • the aforementioned express parcel area may be an area containing express parcels, for example, it may be the smallest area containing express parcels.
  • the above-mentioned executive body may determine the express order area in the above-mentioned regional express image based on the above-mentioned regional express image and the above-mentioned express delivery detection model in the following manner: the above-mentioned executive body may first input the above-mentioned regional express image into the above-mentioned express order detection model, and obtain information from the above The at least one initial express order area detected in the regional express image and the predicted probability corresponding to each initial express order area in the at least one initial express order area.
  • the initial express order area can be characterized in the form of ⁇ x,y,w,h ⁇ .
  • x and y may respectively be the abscissa value and the ordinate value of the preset position of the initial express note in the preset coordinate system
  • w and h may be the width and height of the initial express note, respectively.
  • the regional express image can be input into the express package detection model to obtain the predicted probability corresponding to at least one express package area detected from the regional express image and each express package area in the at least one express package area.
  • the express parcel area can also be characterized in the form of ⁇ x,y,w,h ⁇ .
  • x and y can respectively be the abscissa value and the ordinate value of the preset position of the express package in the preset coordinate system
  • w and h can be the width and height of the express package, respectively.
  • an initial express order area corresponds to an express package area
  • the corresponding relationship between the initial express order area and the express package area is determined by the relationship between the area location of the initial express order area and the area location of the express package area . If there is at least a partial overlap between the initial express order area and the express package area, it can usually be explained that they have a corresponding relationship.
  • the express parcel area with the corresponding relationship contains the corresponding initial express order area.
  • the aforementioned express package detection model may include a convolutional layer, a pooling layer, and a fully connected layer.
  • the above regional express image can be input into the convolution layer of the above express package detection model to convolve the pixel features of the above regional express image with the convolution kernel to obtain the image features; then, the above image features can be input In the pooling layer of the aforementioned express package detection model, the pooled feature vector is obtained. Maximum pooling and average pooling can be used to extract features. Finally, the pooled feature vector can be input into the fully connected layer of the above-mentioned express package detection model, so as to classify the pooled feature vector to obtain the express package area and the corresponding predicted probability.
  • the execution subject may first determine multiple sets of correspondences including the initial express order area and the express package area based on the at least one initial express order area and the at least one express package area.
  • the initial express order area and express parcel area with overlapping areas may be determined as a set of correspondences.
  • the following formula (1) can be used to determine the final probability that the initial express order area included in the set of correspondences is the express order area in the regional express image:
  • P is the initial express order area included in the set of correspondences is the final probability of the express order area in the regional express image
  • P bill is the predicted probability corresponding to the initial express order area included in the set of correspondences
  • ⁇ bill is the weight of the predicted probability corresponding to the initial express order area included in the set of correspondences
  • P package is the predicted probability of the express package area included in the set of correspondences
  • ⁇ package is the predicted probability of the set of correspondences The weight of the predicted probability corresponding to the included express parcel area.
  • the final probability P that the initial express order area included in the set of correspondences is the express order area in the above regional express image it can be determined whether the initial express order area included in the set of correspondences is the above regional express The express order area in the image. Specifically, if the initial express order area included in the set of correspondences is the express order area in the regional express image, the final probability P is greater than the preset probability threshold (for example, 0.8), then the set of correspondences can be determined The initial express order area included in is the express order area in the above regional express image.
  • the preset probability threshold for example, 0.8
  • the predicted probability corresponding to the initial express order area included in the set of correspondences is 0, then the initial express order area included in the set of correspondence must not be the express delivery in the above regional express image Single area. If the predicted probability corresponding to the initial express order area contained in the set of correspondences is greater than 0, the final probability of the corresponding initial express order can be determined by the predicted probability corresponding to the express package area contained in the set of correspondences Make corrections.
  • the aforementioned express delivery image may include a panoramic express delivery image.
  • the aforementioned panoramic express image generally refers to an image obtained by photographing all areas in an area where a plurality of express parcels are placed. Therefore, the aforementioned panoramic express image usually presents all express parcels among all express parcels.
  • the aforementioned express delivery recognition model also includes a panoramic recognition model. The aforementioned panoramic recognition model can be used to map the location information of the express order in the regional express image to the panoramic express image, so as to determine the position information of a certain express order in the regional express image in the panoramic express image.
  • the above-mentioned executive body may determine the location information of each express order and the express information on each express order in at least one express order identified from the aforementioned express image based on the aforementioned express delivery image and the pre-trained express delivery identification model in the following manner:
  • the execution subject may input the regional express image and the panoramic express image into the panoramic recognition model to obtain the correspondence between the position information of the express order in the panoramic express image and the position information of the express order in the regional express image.
  • the execution subject may input the regional express image and the panoramic express image into the panoramic recognition model to obtain the feature vector of a certain express order in the regional express image and the characteristics of each express order in the panoramic express image.
  • the distance between the vectors (for example, cosine distance, Euclidean distance), the express order corresponding to the feature vector with the smallest distance can be selected as the express order most similar to the express order in the above regional express image, and the above regional express image can be determined Correspondence between the courier note in and the courier note in the above panoramic express image. It should be noted that in the process of determining the similarity between a certain express order in the above regional express image and each express order in the above panoramic express image, the detection box can be used to compare each express order in the above panoramic express image. Traverse. After that, the correspondence relationship between the location information of the express bill in the panoramic express image and the location information of the express bill in the regional express image may be stored.
  • the partial express image can be combined with the panoramic express image, and the clear partial image on the front can be identified, and then the target express package can be located in the panoramic image.
  • This method can increase the number of single-identified express parcels and further improve the efficiency of express parcel search.
  • the process 400 of the method for locating express parcels in this embodiment reflects the determination of the difference between the location information of the express order and the express information on the express order.
  • the corresponding relationship between, and the step of storing the determined corresponding relationship. Therefore, the solution described in this embodiment can accurately determine the correspondence between the location information of the courier order and the courier information on the courier order before locating the courier package, thereby improving the accuracy of searching for the courier package.
  • FIG. 5 is a schematic diagram of another application scenario of the method for locating express parcels according to this embodiment.
  • the courier can use the terminal device 501 to upload the courier image showing at least one courier package.
  • the courier can click the "upload image” icon 502, and then select the "partial” option.
  • the icon 503 As shown by the icon 503, to upload the partial express image, and the uploaded partial express image is as shown by the icon 504.
  • the courier can upload the partial express image 505 and the partial express image 506 in the same manner.
  • the courier can click the “upload image” icon 502, and then select the “panoramic” option, as shown by the icon 507, to upload the panoramic express image, and the uploaded panoramic express image is shown by the icon 508.
  • the user informs the courier of the courier information (for example, the last four digits of the mobile phone number) during the process of picking up the courier, and the courier can input the last four digits of the user’s mobile phone number 1234 into the query box 509 for inquiring about courier delivery.
  • the terminal device 501 can receive the courier form used to locate the target courier package from the partial courier images 504, 505, 506 and the panoramic courier image 508 (the last four digits of the mobile phone number correspond to 1234). Courier tracking request). Then, the terminal device 501 can search for the pre-stored location information of the courier note corresponding to the last four digits 1234 of the mobile phone number.
  • the above-mentioned location information may include the location information of the express order corresponding to the target express package on the partial express image and the position information of the express order corresponding to the target express package on the panoramic express image.
  • the terminal device 501 can use the location information of the courier note corresponding to the target courier package on the partial courier image to generate and output the courier positioning result image 511. If the courier selects the “panoramic” option, as shown by the icon 507, the terminal device 501 can present the courier positioning result image 511.
  • the express delivery positioning result image 511 includes a positioning identifier 512, and the positioning identifier 512 is used to indicate from the panoramic express image 508 the express order corresponding to the aforementioned target express package.
  • the terminal device 501 can generate and output the express location result image 513 by using the location information of the express order corresponding to the target express package on the panoramic express image.
  • the terminal device 501 can present the courier positioning result image 513.
  • the express delivery positioning result image 513 includes a positioning identifier 514, and the positioning identifier 514 is used to indicate from the partial express image 506 the express order corresponding to the aforementioned target express package.
  • the courier can find the target courier package from multiple courier packages according to the location identifier 512 in the courier location result image 511 and the location identifier 514 in the courier location result image 513.
  • this application provides an embodiment of a device for locating express parcels, and the device embodiment corresponds to the method embodiment shown in FIG. 2.
  • the device can be specifically applied to various electronic devices.
  • the apparatus 600 for locating express parcels in this embodiment includes: a receiving unit 601, a searching unit 602, a generating unit 603, and an output unit 604.
  • the receiving unit 601 is configured to receive a courier location request, where the courier location request is used to locate the courier order corresponding to the target courier package from the courier image showing the courier package, and the courier location request includes courier information;
  • the search unit 602 is configured
  • the generation unit 603 is configured to use the location information to generate an express location result image, wherein the express location result image includes a location identifier, and the location identifier is used to retrieve the location information from the express image.
  • the courier note corresponding to the target courier package is indicated in, and the output unit 604 is configured to output the courier positioning result image.
  • the specific processing of the receiving unit 601, the searching unit 602, the generating unit 603, and the output unit 604 of the device 600 for locating express parcels can refer to step 201, step 202, and step 203 in the embodiment corresponding to FIG. 2. And step 204.
  • the above-mentioned device 600 for locating express parcels may further include an acquiring unit (not shown in the figure), a determining unit (not shown in the figure), and a storage unit (not shown in the figure). Not shown).
  • the above-mentioned acquiring unit can acquire the express image showing the express package.
  • the aforementioned determining unit may determine the location information of each courier order and the courier information on each courier order in at least one courier order identified from the aforementioned courier image based on the obtained express image and a pre-trained express delivery identification model.
  • the determination unit may input the express delivery image into the express delivery identification model to obtain the location information of each express order and the express information on each express order in at least one express order identified from the express delivery image.
  • the aforementioned express delivery identification model can be used to characterize the image and the location information of the express order identified from the image and the express information on the express order.
  • the location information of the aforementioned express order can be characterized in the form of ⁇ x, y, w, h ⁇ .
  • x and y may respectively be the abscissa value and the ordinate value of the preset position of the express order (usually a rectangular area) in the preset coordinate system
  • w and h may be the width and height of the express order, respectively.
  • the aforementioned express delivery information may include, but is not limited to: part or all of the number in the mobile phone number of the express recipient, and part or all of the number in the express order number.
  • the above-mentioned storage unit may store the location information of each express order in the obtained at least one express order in association with the corresponding express information.
  • the aforementioned express delivery image may include a regional express delivery image.
  • the above-mentioned regional express image usually refers to an image obtained by photographing a part of an area where a plurality of express parcels are placed. Therefore, the above-mentioned regional express image usually shows part of all express parcels. It should be noted that the image of the express delivery bill on the front side is usually displayed in the above regional express delivery image.
  • the aforementioned express delivery identification model may include an express delivery detection model, an express location identification model, and an express information identification model. The aforementioned express delivery detection model can be used to characterize the correspondence between the image and the express delivery order area in the image.
  • the aforementioned express order area may be an area containing an express order, for example, it may be the smallest area that includes an express order.
  • the aforementioned express location identification model can be used to characterize the correspondence between the express order area and the position information of the express order area in the express order area.
  • the aforementioned express information identification model can be used to characterize the correspondence between the express order area and the express information on the express order area in the express order area.
  • the aforementioned determining unit may determine the location information of each courier order and the courier information on each courier order in at least one courier order identified from the aforementioned courier image based on the aforementioned courier image and a pre-trained courier identification model in the following manner:
  • the determination unit may first determine the express order area in the regional express image based on the regional express image and the express detection model. Specifically, the determination unit may input the regional express image into the express delivery detection model to obtain the express order area in the regional express image.
  • the determination unit may input the regional express image into the express delivery detection model to obtain the probability of whether each pixel in the regional express image is an express order area, so as to determine the express order area in the regional express image.
  • the express order area can be input into the express delivery location identification model to obtain the location information of each express delivery order in at least one express delivery order. Then, the express delivery order area can be input into the express delivery information identification model to obtain the express delivery information on each express delivery order in the at least one express delivery order.
  • the above-mentioned express delivery detection model may include an express order inspection model and an express package inspection model.
  • the aforementioned express order detection model may be used to characterize the correspondence between the image and the predicted probability corresponding to the initial express order area and the initial express order area detected from the image.
  • the aforementioned express package detection model can be used to characterize the correspondence between the image and the predicted probability corresponding to the express package area and the express package area detected from the image.
  • the aforementioned express parcel area may be an area containing express parcels, for example, it may be the smallest area containing express parcels.
  • the determination unit may determine the express order area in the regional express image based on the regional express image and the express delivery detection model in the following manner: the determination unit may first input the regional express image into the express order detection model, and obtain information from the above The at least one initial express order area detected in the regional express image and the predicted probability corresponding to each initial express order area in the at least one initial express order area.
  • the initial express order area can be characterized in the form of ⁇ x,y,w,h ⁇ .
  • x and y may respectively be the abscissa value and the ordinate value of the preset position of the initial express note in the preset coordinate system
  • w and h may be the width and height of the initial express note, respectively.
  • the regional express image can be input into the express package detection model to obtain the predicted probability corresponding to at least one express package area detected from the regional express image and each express package area in the at least one express package area.
  • the express parcel area can also be characterized in the form of ⁇ x,y,w,h ⁇ .
  • x and y can respectively be the abscissa value and the ordinate value of the preset position of the express package in the preset coordinate system
  • w and h can be the width and height of the express package, respectively.
  • an initial express order area corresponds to an express package area
  • the corresponding relationship between the initial express order area and the express package area is determined by the relationship between the area location of the initial express order area and the area location of the express package area . If there is at least a partial overlap between the initial express order area and the express package area, it can usually be explained that they have a corresponding relationship.
  • the express parcel area with the corresponding relationship contains the corresponding initial express order area.
  • the aforementioned express package detection model may include a convolutional layer, a pooling layer, and a fully connected layer.
  • the above regional express image can be input into the convolution layer of the above express package detection model to convolve the pixel features of the above regional express image with the convolution kernel to obtain the image features; then, the above image features can be input In the pooling layer of the aforementioned express package detection model, the pooled feature vector is obtained. Maximum pooling and average pooling can be used to extract features. Finally, the pooled feature vector can be input into the fully connected layer of the above-mentioned express package detection model, so as to classify the pooled feature vector to obtain the express package area and the corresponding predicted probability.
  • the determining unit may first determine multiple sets of correspondences including the initial express order area and the express package area through the at least one initial express order area and the at least one express package area.
  • the initial express order area and express parcel area with overlapping areas may be determined as a set of correspondences.
  • the following formula (1) can be used to determine the final probability that the initial express order area included in the set of correspondences is the express order area in the regional express image:
  • P is the initial express order area included in the set of correspondences is the final probability of the express order area in the regional express image
  • P bill is the predicted probability corresponding to the initial express order area included in the set of correspondences
  • ⁇ bill is the weight of the predicted probability corresponding to the initial express order area contained in the set of correspondences
  • p package is the predicted probability of the express package area contained in the set of correspondences
  • ⁇ package is the predicted probability of the set of correspondences. The weight of the predicted probability corresponding to the included express parcel area.
  • the initial express order area included in the set of correspondences is the express order area in the above regional express image. Specifically, if the initial express order area included in the set of correspondences is that the final probability P of the express order area in the regional express image is greater than the preset probability threshold, then the initial set of correspondences included in the set of correspondences can be determined The express order area is the express order area in the above regional express image.
  • the predicted probability corresponding to the initial express order area included in the set of correspondences is 0, then the initial express order area included in the set of correspondence must not be the express delivery in the above regional express image Single area. If the predicted probability corresponding to the initial express order area contained in the set of correspondences is greater than 0, the final probability of the corresponding initial express order can be determined by the predicted probability corresponding to the express package area contained in the set of correspondences Make corrections.
  • the aforementioned express delivery image may include a panoramic express delivery image.
  • the aforementioned panoramic express image usually refers to an image obtained by shooting all areas in an area where a plurality of express parcels are placed. Therefore, the aforementioned panoramic express image usually presents all express packages among all express parcels.
  • the aforementioned express delivery recognition model also includes a panoramic recognition model. The aforementioned panoramic recognition model can be used to map the location information of the express order in the regional express image to the panoramic express image, so as to determine the position information of a certain express order in the regional express image in the panoramic express image.
  • the aforementioned determining unit may determine the location information of each courier order and the courier information on each courier order in at least one courier order identified from the aforementioned courier image based on the aforementioned courier image and a pre-trained courier identification model in the following manner:
  • the determination unit may input the regional express image and the panoramic express image into the panoramic recognition model to obtain the correspondence between the position information of the express order in the panoramic express image and the position information of the express order in the regional express image.
  • the determination unit may input the regional express image and the panoramic express image into the panoramic recognition model to obtain the feature vector of a certain express order in the regional express image and the characteristics of each express order in the panoramic express image.
  • the distance between the vectors, the express order corresponding to the feature vector with the smallest distance can be selected as the express order most similar to the express order in the above regional express image, and the express order in the above regional express image and the above panoramic express image can be determined Correspondence between the express orders in the. It should be noted that in the process of determining the similarity between a certain express order in the above regional express image and each express order in the above panoramic express image, the detection box can be used to compare each express order in the above panoramic express image. Traverse. After that, the correspondence relationship between the location information of the express bill in the panoramic express image and the location information of the express bill in the regional express image may be stored.
  • the partial express image can be combined with the panoramic express image, and the clear partial image on the front can be identified, and then the target express package can be located in the panoramic image.
  • This method can increase the number of single-identified express parcels and further improve the efficiency of express parcel search.
  • FIG. 7 shows a schematic structural diagram of an electronic device (for example, the server or terminal device in FIG. 1) 700 suitable for implementing the embodiments of the present disclosure.
  • the electronic device shown in FIG. 7 is only an example, and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.
  • the electronic device 700 may include a processing device (such as a central processing unit, a graphics processor, etc.) 701, which may be loaded into a random access device according to a program stored in a read-only memory (ROM) 702 or from a storage device 708.
  • the program in the memory (RAM) 703 executes various appropriate actions and processing.
  • various programs and data required for the operation of the electronic device 700 are also stored.
  • the processing device 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704.
  • An input/output (I/O) interface 705 is also connected to the bus 704.
  • the following devices can be connected to the I/O interface 705: including input devices 706 such as touch screens, touch pads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; including, for example, liquid crystal displays (LCD), speakers, vibrations Output device 707 such as a device; and a communication device 709.
  • the communication device 709 may allow the electronic device 700 to perform wireless or wired communication with other devices to exchange data.
  • FIG. 7 shows an electronic device 700 having various devices, it should be understood that it is not required to implement or have all of the illustrated devices. It may be implemented alternatively or provided with more or fewer devices.
  • Each block shown in Figure 7 can represent one device, or can represent multiple devices as needed.
  • an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from the network through the communication device 709, or installed from the storage device 708, or installed from the ROM 702.
  • the processing device 701 the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.
  • the computer-readable medium described in the embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination of any of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable removable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in a baseband or as a part of a carrier wave, and a computer-readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium.
  • the computer-readable signal medium may send, propagate, or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .
  • the program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist alone without being assembled into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs.
  • the electronic device In the express image, locate the express order corresponding to the target express package.
  • the express positioning request includes express information; find the pre-stored position information of the express order corresponding to the express information; use the position information to generate an express positioning result image, where the express positioning result
  • the image includes a positioning mark, which is used to indicate the express order corresponding to the target express package from the express image; and output the express positioning result image.
  • the computer program code for performing the operations of the embodiments of the present disclosure may be written in one or more programming languages or a combination thereof, the programming languages including object-oriented programming languages-such as Java, Smalltalk, C++, Also includes conventional procedural programming languages-such as "C" language or similar programming languages.
  • the program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server.
  • the remote computer can be connected to the user’s computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to Connect via the Internet).
  • LAN local area network
  • WAN wide area network
  • each block in the flowchart or block diagram can represent a module, program segment, or part of code, and the module, program segment, or part of code contains one or more for realizing the specified logic function.
  • Executable instructions can also occur in a different order from the order marked in the drawings. For example, two blocks shown one after another can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or operations Or it can be realized by a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments described in the present disclosure can be implemented in software or hardware.
  • the described unit can also be provided in a processor, for example, it can be described as: a processor includes a receiving unit, a searching unit, a generating unit, and an output unit. Among them, the names of these units do not constitute a limitation on the unit itself under certain circumstances.
  • the output unit can also be described as "a unit that outputs an image of express positioning results.”

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Library & Information Science (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Human Resources & Organizations (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Image Analysis (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Character Discrimination (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本申请实施例公开了用于定位快递包裹的方法和装置。该方法的一具体实施方式包括：接收快递定位请求，其中，快递定位请求用于从呈现有快递包裹的快递图像中定位目标快递包裹对应的快递单，快递定位请求包括快递信息；查找预先存储的、与快递信息对应的快递单的位置信息；利用位置信息，生成快递定位结果图像，其中，快递定位结果图像包括定位标识，定位标识用于从快递图像中指示出目标快递包裹对应的快递单；输出快递定位结果图像。该实施方式提高了快递包裹定位效率，从而提高了快递配送效率。

Description

用于定位快递包裹的方法和装置
本专利申请要求于2020年3月30日提交的、申请号为202010239330.1、申请人为北京沃东天骏信息技术有限公司及北京京东世纪贸易有限公司、发明名称为“用于定位快递包裹的方法和装置”的中国专利申请的优先权，该申请的全文以引用的方式并入本申请中。
技术领域
本申请实施例涉及计算机技术领域，具体涉及用于定位快递包裹的方法和装置。
背景技术
随着社会的不断发展，快递包裹的应用越来越广泛，消费者网上购物，公司之间文件或货物的交付，个人与个人寄送物品都是通过物流公司以快递包裹的形式进行的。相关的快递包裹定位方法通常是快递员将快递包裹进行手工标记，例如，将快递单上的手机号码后四位写在快递单上；之后，按照手机号码对快递包裹进行分类，并放置在不同的区域；最后，当客户来取件时，根据客户提供的手机号码在特定区域查找客户的快递包裹。这种快递包裹定位方法在校园快件配送或乡镇快递配送的过程中较为普遍。
发明内容
本申请实施例提出了用于定位快递包裹的方法和装置。
第一方面，本申请实施例提供了一种用于定位快递包裹的方法，包括：接收快递定位请求，其中，快递定位请求用于从呈现有快递包裹的快递图像中定位目标快递包裹对应的快递单，快递定位请求包括快递信息；查找预先存储的、与快递信息对应的快递单的位置信息；利用位置信息，生成快递定位结果图像，其中，快递定位结果图像包括定位标识，定位标识用于从快递图像中指示出目标快递包裹对应的 快递单；输出快递定位结果图像。
在一些实施例中，在接收快递定位请求之前，该方法包括：获取呈现有快递包裹的快递图像；基于快递图像和预先训练的快递识别模型，确定从快递图像中识别出的至少一个快递单中每个快递单的位置信息和每个快递单上的快递信息；将至少一个快递单中每个快递单的位置信息与对应的快递信息进行关联存储。
在一些实施例中，快递图像包括区域快递图像，快递识别模型包括快递检测模型、快递位置识别模型和快递信息识别模型；以及基于快递图像和预先训练的快递识别模型，确定从快递图像中识别出的至少一个快递单中每个快递单的位置信息和每个快递单上的快递信息，包括：基于区域快递图像和快递检测模型，确定区域快递图像中的快递单区域；将快递单区域输入快递位置识别模型中，得到至少一个快递单中每个快递单的位置信息；将快递单区域输入快递信息识别模型中，得到至少一个快递单中每个快递单上的快递信息。
在一些实施例中，快递检测模型包括快递单检测模型和快递包裹检测模型；以及基于区域快递图像和快递检测模型，确定区域快递图像中的快递单区域，包括：将区域快递图像输入快递单检测模型中，得到从区域快递图像中检测出的至少一个初始快递单区域和至少一个初始快递单区域中每个初始快递单区域对应的预测概率；将区域快递图像输入快递包裹检测模型中，得到从区域快递图像中检测出的至少一个快递包裹区域和至少一个快递包裹区域中每个快递包裹区域对应的预测概率；基于至少一个初始快递单区域、至少一个初始快递单区域中每个初始快递单区域对应的预测概率、至少一个快递包裹区域和至少一个快递包裹区域中每个快递包裹区域对应的预测概率，确定区域快递图像中的快递单区域。
在一些实施例中，快递图像包括全景快递图像，快递识别模型还包括全景识别模型；以及基于快递图像和预先训练的快递识别模型，确定从快递图像中识别出的至少一个快递单中每个快递单的位置信息和每个快递单上的快递信息，包括：将区域快递图像和全景快递图像输入全景识别模型中，得到全景快递图像中快递单的位置信息与区域 快递图像中快递单的位置信息之间的对应关系；存储全景快递图像中快递单的位置信息与区域快递图像中快递单的位置信息之间的对应关系。
第二方面，本申请实施例提供了一种用于定位快递包裹的装置，包括：接收单元，被配置成接收快递定位请求，其中，快递定位请求用于从呈现有快递包裹的快递图像中定位目标快递包裹对应的快递单，快递定位请求包括快递信息；查找单元，被配置成查找预先存储的、与快递信息对应的快递单的位置信息；生成单元，被配置成利用位置信息，生成快递定位结果图像，其中，快递定位结果图像包括定位标识，定位标识用于从快递图像中指示出目标快递包裹对应的快递单；输出单元，被配置成输出快递定位结果图像。
第三方面，本申请实施例提供了一种电子设备，该电子设备包括：一个或多个处理器；存储装置，其上存储有一个或多个程序，当上述一个或多个程序被上述一个或多个处理器执行时，使得上述一个或多个处理器实现如第一方面中任一实现方式描述的方法。
第四方面，本申请实施例提供了一种计算机可读介质，其上存储有计算机程序，其中，该计算机程序被处理器执行时实现如第一方面中任一实现方式描述的方法。
本申请的上述实施例提供的用于定位快递包裹的方法和装置，通过接收快递定位请求；之后，查找预先存储的、与上述快递定位请求中包括的快递信息对应的快递单的位置信息；而后，利用所述上述位置信息，生成包含用于从上述快递图像中指示出上述目标快递包裹对应的快递单的快递定位结果图像；最后，输出上述快递定位结果图像。通过这种方式提高了快递包裹定位效率，从而提高了快递配送效率。
附图说明
通过阅读参照以下附图所作的对非限制性实施例所作的详细描述，本申请的其它特征、目的和优点将会变得更明显：
图1是本申请的各个实施例可以应用于其中的示例性系统架构图；
图2是根据本申请的用于定位快递包裹的方法的一个实施例的流 程图；
图3是根据本申请的用于定位快递包裹的方法的一个应用场景的示意图；
图4是根据本申请的用于定位快递包裹的方法的又一个实施例的流程图；
图5是根据本申请的用于定位快递包裹的方法的又一个应用场景的示意图；
图6是根据本申请的用于定位快递包裹的装置的一个实施例的结构示意图；
图7是适于用来实现本申请实施例的电子设备的计算机系统的结构示意图。
具体实施方式
下面结合附图和实施例对本申请作进一步的详细说明。可以理解的是，此处所描述的具体实施例仅仅用于解释相关发明，而非对该发明的限定。另外还需要说明的是，为了便于描述，附图中仅示出了与有关发明相关的部分。
需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本申请。
图1示出了可以应用本申请的用于定位快递包裹的方法的实施例的示例性系统架构100。
如图1所示，系统架构100可以包括终端设备1011、1012、1013，网络102和服务器103。网络102用以在终端设备1011、1012、1013和服务器103之间提供通信链路的介质。网络102可以包括各种连接类型，例如有线、无线通信链路或者光纤电缆等等。
快递员可以使用终端设备1011、1012、1013通过网络102与服务器103交互，以发送或接收消息等(例如，服务器103可以接收终端设备1011、1012、1013发送的快递定位请求，终端设备1011、1012、1013也可以接收服务器103发送的快递定位结果图像)等。终端设备 1011、1012、1013上可以安装有各种通讯客户端应用，例如图像处理类应用、快递管理类应用、即时通讯软件等。
终端设备1011、1012、1013可以首先接收快递定位请求；之后，可以查找预先存储的、与上述快递定位请求中包括的快递信息对应的快递单的位置信息；而后，可以利用上述位置信息，生成快递定位结果图像，其中，上述快递定位结果图像包括用于从上述快递图像中指示出上述目标快递包裹对应的快递单的定位标识；最后，可以输出上述快递定位结果图像。
终端设备1011、1012、1013可以是硬件，也可以是软件。当终端设备1011、1012、1013为硬件时，可以是支持信息交互的各种电子设备，包括但不限于智能手机、平板电脑、膝上型便携计算机和台式计算机等等。当终端设备1011、1012、1013为软件时，可以安装在上述所列举的电子设备中。其可以实现成多个软件或软件模块，也可以实现成单个软件或软件模块。在此不做具体限定。
服务器103可以是提供各种服务的服务器。例如，可以是对快递定位请求进行分析的后台服务器。服务器103可以首先从终端设备1011、1012、1013接收快递定位请求；之后，可以查找预先存储的、与上述快递定位请求中包括的快递信息对应的快递单的位置信息；而后，可以利用上述位置信息，生成快递定位结果图像，其中，上述快递定位结果图像包括用于从上述快递图像中指示出上述目标快递包裹对应的快递单的定位标识；最后，可以输出上述快递定位结果图像，例如，将上述快递定位结果图像发送到终端设备1011、1012、1013。
需要说明的是，服务器103可以是硬件，也可以是软件。当服务器103为硬件时，可以实现成多个服务器组成的分布式服务器集群，也可以实现成单个服务器。当服务器103为软件时，可以实现成多个软件或软件模块(例如用来提供分布式服务)，也可以实现成单个软件或软件模块。在此不做具体限定。
需要说明的是，本申请实施例所提供的用于定位快递包裹的方法可以由服务器103执行，也可以由终端设备1011、1012、1013执行。
需要说明的是，终端设备1011、1012、1013的本地可以存储有快 递单的位置信息与对应的快递信息之间的对应关系，终端设备1011、1012、1013可以从本地查找与快递信息对应的快递单的位置信息。此时示例性系统架构100可以不存在服务器103和网络102。
应该理解，图1中的终端设备、网络和服务器的数目仅仅是示意性的。根据实现需要，可以具有任意数目的终端设备、网络和服务器。
继续参考图2，示出了根据本申请的用于定位快递包裹的方法的一个实施例的流程200。该用于定位快递包裹的方法，包括以下步骤：
步骤201，接收快递定位请求。
在本实施例中，用于定位快递包裹的方法的执行主体(例如图1所示的服务器或终端设备)可以接收快递定位请求。上述快递定位请求通常用于从呈现有快递包裹的快递图像中定位目标快递包裹对应的快递单。上述目标快递包裹可以是待查找或待定位的快递包裹。
在这里，快递员通常需要利用终端设备对放置有快递包裹(可以是一个快递包裹，也可以是多个快递包裹)的区域进行拍照，从而获取到呈现有快递包裹的快递图像。快递通常以快递包裹的形式从寄件方送达到收件方手中。快递单通常是呈现有快递相关信息的单据，快递相关信息通常可以包括快递单编号、寄件方地址信息、寄件方联系方式、收件方地址信息和收件方联系方式。快递包裹通常与快递单相对应，例如，快递单可以粘贴在快递包裹上。通常情况下，快递员需要对快递包裹进行规范化放置，例如，需要保证快递包裹上快递单朝上，且各个包裹之间最好能留有一定的缝隙。
在本实施例中，上述快递定位请求通常包括快递信息，上述快递信息可以包括但不限于：快递收件方的手机号码中的部分号码或全部号码(例如，手机号码后四位)，快递订单编号中的部分编号或全部编号(例如，快递编号的后四位)。
步骤202，查找预先存储的、与快递信息对应的快递单的位置信息。
在本实施例中，上述执行主体可以查找预先存储的、与上述快递信息对应的快递单的位置信息。上述执行主体中通常预先存储有快递信息与快递单的位置信息之间的对应关系。上述快递单的位置信息可 以以{x,y,w,h}的形式表征。在这里，x和y可以分别为快递单(通常为矩形区域)的预设位置(例如，左上角)在预设坐标系下的横坐标值和纵坐标值，w和h可以分别为快递单的宽和高。需要说明的是，上述预设坐标系可以为世界坐标系，也可以为预设的快递图像坐标系，例如，可以是以快递图像的左下角为坐标原点，以快递图像的相邻两个边分别为横坐标轴和纵坐标轴的坐标系。
步骤203，利用位置信息，生成快递定位结果图像。
在本实施例中，上述执行主体可以利用在步骤202中查找到的位置信息，生成快递定位结果图像。上述快递定位结果图像可以包括定位标识，例如，可以是定位框，也可以是定位箭头。上述定位标识用于从上述快递图像中指示出上述目标快递包裹对应的快递单。上述快递定位结果图像可以是将上述定位标识叠加到上述快递图像上所得到的图像。
步骤204，输出快递定位结果图像。
在本实施例中，上述执行主体可以输出在步骤203中所生成的快递定位结果图像。若上述执行主体为终端设备，上述执行主体可以对上述快递定位结果图像进行呈现，以供快递员按照快递定位结果图像中的定位标识，从多个快递包裹中找出上述目标快递包裹。若上述执行主体为服务器，上述执行主体可以将上述快递定位结果图像发送到快递员的终端设备上。
在本实施例的一些可选的实现方式中，上述快递图像可以包括区域快递图像。快递员可以通过点击用于上传区域快递图像的上传图标将上述区域快递图像进行上传，以识别上述区域快递图像中的目标快递包裹对应的快递单。此时，上述执行主体可以查找预先存储的、与上述快递信息对应的上述区域快递图像中的快递单的位置信息；之后，可以利用上述位置信息，生成快递定位结果图像，上述快递定位结果图像中的定位标识用于从上述区域快递图像中指示出上述目标快递包裹对应的快递单。
在本实施例的一些可选的实现方式中，上述快递图像可以包括全景快递图像。快递员可以通过点击用于上传全景快递图像的上传图标 将上述全景快递图像进行上传，以识别上述全景快递图像中的目标快递包裹对应的快递单。此时，上述执行主体可以查找预先存储的、与上述快递信息对应的上述全景快递图像中的快递单的位置信息；之后，可以利用上述位置信息，生成快递定位结果图像，上述快递定位结果图像中的定位标识用于从上述全景快递图像中指示出上述目标快递包裹对应的快递单。
继续参见图3，图3是根据本实施例的用于定位快递包裹的方法的一个应用场景的示意图。在图3的应用场景中，快递员可以利用终端设备301将呈现有快递包裹的快递图像302进行上传。之后，用户在取快递的过程中，将快递信息(例如，手机号码后四位)告知快递员，快递员可以将用户的手机号码后四位5118输入到用于查询快递的查询框303中并点击“查询快递”图标304，此时，终端设备301可以接收用于从快递图像302中定位目标快递包裹对应的快递单(手机号码后四位5118所对应的快递单)的快递定位请求。而后，终端设备301可以查找与手机号码后四位5118对应的快递单的位置信息。然后，终端设备301可以利用上述位置信息，生成并输出快递定位结果图像305。快递定位结果图像305通常包括定位标识，这里的定位标识为定位框306，定位框306用于从快递图像302中指示出上述目标快递包裹对应的快递单。快递员可以按照快递定位结果图像305中的定位标识306，从多个快递包裹中查找到目标快递包裹。
本申请的上述实施例提供的方法通过在接收到用于从快递图像中定位目标快递包裹对应的快递单的快递定位请求之后，查找与所请求定位的目标快递包裹对应的快递单的位置信息，而后，利用上述位置信息，生成快递定位结果图像。快递员可以按照上述快递定位结果图像中的定位标识，快速且准确地找到客户的快递包裹。这种方式提高了快递包裹定位效率，从而提高了快递配送效率。
进一步参考图4，其示出了用于定位快递包裹的方法的又一个实施例的流程400。该用于定位快递包裹的方法的流程400，包括以下步骤：
步骤401，获取呈现有快递包裹的快递图像。
在本实施例中，用于定位快递包裹的方法的执行主体(例如图1所示的服务器或终端设备)可以获取呈现有快递包裹的快递图像。若上述执行主体为快递员的终端设备，则快递员可以利用上述终端设备对放置有快递包裹的区域进行拍照，从而获取到呈现有快递包裹的快递图像。若上述执行主体为服务器，则服务器可以接收快递员利用终端设备所拍摄的呈现有快递包裹的快递图像。
步骤402，基于快递图像和预先训练的快递识别模型，确定从快递图像中识别出的至少一个快递单中每个快递单的位置信息和每个快递单上的快递信息。
在本实施例中，上述执行主体可以基于在步骤401中获取的快递图像和预先训练的快递识别模型，确定从上述快递图像中识别出的至少一个快递单中每个快递单的位置信息和每个快递单上的快递信息。具体地，上述执行主体可以将上述快递图像输入到上述快递识别模型中，得到从上述快递图像中识别出的至少一个快递单中每个快递单的位置信息和每个快递单上的快递信息。此时，上述快递识别模型可以用于表征图像与从图像中识别出的快递单的位置信息和快递单上的快递信息。
在本实施例中，快递单的位置信息可以以{x,y,w,h}的形式表征。在这里，x和y可以分别为快递单(通常为矩形区域)的预设位置在预设坐标系下的横坐标值和纵坐标值，w和h可以分别为快递单的宽和高。需要说明的是，上述预设坐标系可以为世界坐标系，也可以为预设的快递图像坐标系，例如，可以是以快递图像的左下角为坐标原点，以快递图像的相邻两个边分别为横坐标轴和纵坐标轴的坐标系。上述快递信息可以包括但不限于：快递收件方的手机号码中的部分号码或全部号码，快递订单编号中的部分编号或全部编号。
步骤403，将至少一个快递单中每个快递单的位置信息与对应的快递信息进行关联存储。
在本实施例中，上述执行主体可以将在步骤403中得到的至少一个快递单中每个快递单的位置信息与对应的快递信息进行关联存储。
步骤404，接收快递定位请求。
步骤405，查找预先存储的、与快递信息对应的快递单的位置信息。
步骤406，利用位置信息，生成快递定位结果图像。
步骤407，输出快递定位结果图像。
在本实施例中，步骤404-407可以按照与步骤201-204类似的方式执行，在此不再赘述。
在本实施例的一些可选的实现方式中，上述快递图像可以包括区域快递图像。上述区域快递图像通常指的是对放置有多个快递包裹的区域中的部分区域进行拍摄所得到的图像，因此，上述区域快递图像中通常呈现有所有快递包裹中的部分快递包裹。需要说明的是，上述区域快递图像中呈现出的通常是正面清晰的快递单图像。上述快递识别模型可以包括快递检测模型、快递位置识别模型和快递信息识别模型。上述快递检测模型可以用于表征图像与图像中的快递单区域之间的对应关系。上述快递单区域可以是包含快递单的区域，例如，可以是包含快递单的最小区域。上述快递位置识别模型可以用于表征快递单区域与快递单区域中的快递单的位置信息之间的对应关系。上述快递信息识别模型可以用于表征快递单区域与快递单区域中的快递单上的快递信息之间的对应关系。上述执行主体可以通过如下方式基于上述快递图像和预先训练的快递识别模型，确定从上述快递图像中识别出的至少一个快递单中每个快递单的位置信息和每个快递单上的快递信息：上述执行主体可以首先基于上述区域快递图像和上述快递检测模型，确定上述区域快递图像中的快递单区域。具体地，上述执行主体可以将上述区域快递图像输入上述快递检测模型中，得到上述区域快递图像中的快递单区域。上述执行主体可以将上述区域快递图像输入上述快递检测模型中，得到上述区域快递图像中的每个像素点是否为快递单区域的概率，从而确定上述区域快递图像中的快递单区域。之后，可以将上述快递单区域输入上述快递位置识别模型中，得到至少一个快递单中每个快递单的位置信息。而后，可以将上述快递单区域输入上述快递信息识别模型中，得到上述至少一个快递单中每个快递单上的快递信息。
在本实施例的一些可选的实现方式中，上述快递检测模型可以包括快递单检测模型和快递包裹检测模型。在这里，上述快递单检测模型可以用于表征图像与从图像中检测出初始快递单区域和初始快递单区域对应的预测概率之间的对应关系。上述快递包裹检测模型可以用于表征图像与从图像中检测出的快递包裹区域和快递包裹区域对应的预测概率之间的对应关系。上述快递包裹区域可以是包含快递包裹的区域，例如，可以是包含快递包裹的最小区域。
上述执行主体可以通过如下方式基于上述区域快递图像和上述快递检测模型，确定上述区域快递图像中的快递单区域：上述执行主体可以首先将上述区域快递图像输入上述快递单检测模型中，得到从上述区域快递图像中检测出的至少一个初始快递单区域和上述至少一个初始快递单区域中每个初始快递单区域对应的预测概率。需要说明的是，初始快递单区域可以以{x,y,w,h}的形式表征。在这里，x和y可以分别为初始快递单的预设位置在预设坐标系下的横坐标值和纵坐标值，w和h可以分别为初始快递单的宽和高。
之后，可以将上述区域快递图像输入上述快递包裹检测模型中，得到从上述区域快递图像中检测出的至少一个快递包裹区域和上述至少一个快递包裹区域中每个快递包裹区域对应的预测概率。需要说明的是，快递包裹区域也可以以{x,y,w,h}的形式表征。在这里，x和y可以分别为快递包裹的预设位置在预设坐标系下的横坐标值和纵坐标值，w和h可以分别为快递包裹的宽和高。通常来说，一个初始快递单区域与一个快递包裹区域相对应，通过初始快递单区域的区域位置与快递包裹区域的区域位置之间的关系确定初始快递单区域与快递包裹区域之间的对应关系。若初始快递单区域与快递包裹区域存在至少部分区域相重叠，则通常可以说明其具有对应关系。通常情况下，具有对应关系的快递包裹区域中包含与其对应的初始快递单区域。在这里，上述快递包裹检测模型可以包括卷积层、池化层和全连接层。可以将上述区域快递图像输入上述快递包裹检测模型的卷积层，以将上述区域快递图像的像素点的像素特征与卷积核进行卷积操作，得到图像特征；之后，可以将上述图像特征输入上述快递包裹检测模型的池 化层中，得到池化后的特征向量。可以采用最大池化和平均池化来提取特征。最后，可以将池化后的特征向量输入上述快递包裹检测模型的全连接层中，从而对池化后的特征向量进行分类，以得到快递包裹区域和对应的预测概率。
而后，可以基于上述至少一个初始快递单区域、上述至少一个初始快递单区域中每个初始快递单区域对应的预测概率、上述至少一个快递包裹区域和上述至少一个快递包裹区域中每个快递包裹区域对应的预测概率，确定上述区域快递图像中的快递单区域。具体地，上述执行主体可以首先基于上述至少一个初始快递单区域和上述至少一个快递包裹区域，确定包含初始快递单区域和快递包裹区域的多组对应关系。作为示例，可以将存在有重叠区域的初始快递单区域和快递包裹区域确定为一组对应关系。之后，针对上述多组对应关系中的每组对应关系，可以通过如下公式(1)确定该组对应关系中所包含的初始快递单区域为上述区域快递图像中的快递单区域的最终概率：
Figure PCTCN2021073321-appb-000001
其中，P为该组对应关系中所包含的初始快递单区域是上述区域快递图像中的快递单区域的最终概率，P bill为该组对应关系中所包含的初始快递单区域对应的预测概率，λ bill为该组对应关系中所包含的初始快递单区域对应的预测概率的权重，P package为该组对应关系中所包含的快递包裹区域对应的预测概率，λ package为该组对应关系中所包含的快递包裹区域对应的预测概率的权重。
最后，可以基于该组对应关系中所包含的初始快递单区域是上述区域快递图像中的快递单区域的最终概率P，确定上述该组对应关系中所包含的初始快递单区域是否为上述区域快递图像中的快递单区域。具体地，若该组对应关系中所包含的初始快递单区域是上述区域快递图像中的快递单区域的最终概率P大于预设的概率阈值(例如，0.8)，则可以确定上述该组对应关系中所包含的初始快递单区域为上述区域快递图像中的快递单区域。
通过上述公式(1)可知，若该组对应关系中所包含的初始快递单区域对应的预测概率为0，则该组对应关系中所包含的初始快递单区 域一定不是上述区域快递图像中的快递单区域。若该组对应关系中所包含的初始快递单区域对应的预测概率大于0，可以通过该组对应关系中所包含的快递包裹区域对应的预测概率来对其对应的初始快递单所对应的最终概率进行修正。
由于快递包裹之间颜色相近，区分快递包裹的边界具有一定的困难性，而快递单之间有与之颜色差异较大的快递包裹，因此，快递单相比于快递包裹较容易被识别出。通过上述这种从上述区域快递图像中确定快递单区域的方式可以以快递单的识别结果为主导，提高了快递包裹的检测效果。
在本实施例的一些可选的实现方式中，上述快递图像可以包括全景快递图像。上述全景快递图像通常指的是对放置有多个快递包裹的区域中的全部区域进行拍摄所得到的图像，因此，上述全景快递图像中通常呈现有所有快递包裹中的全部快递包裹。上述快递识别模型还包括全景识别模型。上述全景识别模型可以用于将区域快递图像中的快递单的位置信息映射到全景快递图像中，从而确定出区域快递图像中的某一快递单在全景快递图像中的位置信息。上述执行主体可以通过如下方式基于上述快递图像和预先训练的快递识别模型，确定从上述快递图像中识别出的至少一个快递单中每个快递单的位置信息和每个快递单上的快递信息：上述执行主体可以将上述区域快递图像和上述全景快递图像输入上述全景识别模型中，得到上述全景快递图像中快递单的位置信息与上述区域快递图像中快递单的位置信息之间的对应关系。具体地，上述执行主体可以将上述区域快递图像和上述全景快递图像输入上述全景识别模型中，得到上述区域快递图像中的某一快递单的特征向量与上述全景快递图像中的各个快递单的特征向量之间的距离(例如，余弦距离、欧式距离)，可以选取距离最小的特征向量对应的快递单作为与上述区域快递图像中的这一快递单最为相似的快递单，并确定上述区域快递图像中的快递单与上述全景快递图像中的快递单之间的对应关系。需要说明的是，在确定上述区域快递图像中的某一快递单与上述全景快递图像中的各个快递单之间的相似度的过程中，可以利用检测框对上述全景快递图像中的各个快递单进行遍 历。之后，可以存储上述全景快递图像中快递单的位置信息与上述区域快递图像中快递单的位置信息之间的对应关系。通过这种方式，可以将局部快递图像与全景快递图像相结合，通过对正面清晰的局部图像进行识别，而后在全景图像中定位出目标快递包裹。这种方式可以增加了单次识别快递包裹的数量，进一步提高了快递包裹查找效率。
从图4中可以看出，与图2对应的实施例相比，本实施例中的用于定位快递包裹的方法的流程400体现了确定快递单的位置信息和快递单上的快递信息之间的对应关系，并将确定出的对应关系进行存储的步骤。由此，本实施例描述的方案可以在对快递包裹进行定位之前，准确地确定出快递单的位置信息与快递单上的快递信息之间的对应关系，从而可以提高快递包裹查找的准确性。
继续参见图5，图5是根据本实施例的用于定位快递包裹的方法的又一个应用场景的示意图。在图5的应用场景中，快递员可以利用终端设备501将呈现有至少一个快递包裹的快递图像进行上传，在这里，快递员可以点击“上传图像”图标502，之后，可以选择“局部”选项，如图标503所示，以将局部快递图像上传，所上传的局部快递图像如图标504所示。而后，快递员可以利用相同的方式将局部快递图像505和局部快递图像506进行上传。然后，快递员可以点击“上传图像”图标502，之后，选择“全景”选项，如图标507所示，以将全景快递图像上传，所上传的全景快递图像如图标508所示。之后，用户在取快递的过程中，将快递信息(例如，手机号码后四位)告知快递员，快递员可以将用户的手机号码后四位1234输入到用于查询快递的查询框509中并点击“查询快递”图标510，此时，终端设备501可以接收用于从局部快递图像504、505、506和全景快递图像508中定位目标快递包裹对应的快递单(手机号码后四位1234所对应的快递单)的快递定位请求。而后，终端设备501可以查找预先存储的、与手机号码后四位1234对应的快递单的位置信息。在这里，上述位置信息可以包括局部快递图像上的目标快递包裹对应的快递单的位置信息和全景快递图像上的目标快递包裹对应的快递单的位置信息。然后，终端设备501可以利用局部快递图像上的目标快递包裹对应的快递单 的位置信息，生成并输出快递定位结果图像511。若快递员选择“全景”选项时，如图标507所示，终端设备501可以呈现快递定位结果图像511。在这里，快递定位结果图像511包括定位标识512，定位标识512用于从全景快递图像508中指示出上述目标快递包裹对应的快递单。终端设备501可以利用全景快递图像上的目标快递包裹对应的快递单的位置信息，生成并输出快递定位结果图像513。若快递员选择“局部”选项时，如图标503所示，终端设备501可以呈现快递定位结果图像513。在这里，快递定位结果图像513包括定位标识514，定位标识514用于从局部快递图像506中指示出上述目标快递包裹对应的快递单。快递员可以按照快递定位结果图像511中的定位标识512以及按照快递定位结果图像513中的定位标识514，从多个快递包裹中查找到目标快递包裹。
进一步参考图6，作为对上述各图所示方法的实现，本申请提供了一种用于定位快递包裹的装置的一个实施例，该装置实施例与图2所示的方法实施例相对应，该装置具体可以应用于各种电子设备中。
如图6所示，本实施例的用于定位快递包裹的装置600包括：接收单元601、查找单元602、生成单元603和输出单元604。其中，接收单元601被配置成接收快递定位请求，其中，快递定位请求用于从呈现有快递包裹的快递图像中定位目标快递包裹对应的快递单，快递定位请求包括快递信息；查找单元602被配置成查找预先存储的、与快递信息对应的快递单的位置信息；生成单元603被配置成利用位置信息，生成快递定位结果图像，其中，快递定位结果图像包括定位标识，定位标识用于从快递图像中指示出目标快递包裹对应的快递单；输出单元604被配置成输出快递定位结果图像。
在本实施例中，用于定位快递包裹的装置600的接收单元601、查找单元602、生成单元603和输出单元604的具体处理可以参考图2对应实施例中的步骤201、步骤202、步骤203和步骤204。
在本实施例的一些可选的实现方式中，上述用于定位快递包裹的装置600还可以包括获取单元(图中未示出)、确定单元(图中未示出)和存储单元(图中未示出)。上述获取单元可以获取呈现有快递包裹的 快递图像。上述确定单元可以基于获取的快递图像和预先训练的快递识别模型，确定从上述快递图像中识别出的至少一个快递单中每个快递单的位置信息和每个快递单上的快递信息。具体地，上述确定单元可以将上述快递图像输入到上述快递识别模型中，得到从上述快递图像中识别出的至少一个快递单中每个快递单的位置信息和每个快递单上的快递信息。此时，上述快递识别模型可以用于表征图像与从图像中识别出的快递单的位置信息和快递单上的快递信息。上述快递单的位置信息可以以{x,y,w,h}的形式表征。在这里，x和y可以分别为快递单(通常为矩形区域)的预设位置在预设坐标系下的横坐标值和纵坐标值，w和h可以分别为快递单的宽和高。上述快递信息可以包括但不限于：快递收件方的手机号码中的部分号码或全部号码，快递订单编号中的部分编号或全部编号。上述存储单元可以将得到的至少一个快递单中每个快递单的位置信息与对应的快递信息进行关联存储。
在本实施例的一些可选的实现方式中，上述快递图像可以包括区域快递图像。上述区域快递图像通常指的是对放置有多个快递包裹的区域中的部分区域进行拍摄所得到的图像，因此，上述区域快递图像中通常呈现有所有快递包裹中的部分快递包裹。需要说明的是，上述区域快递图像中呈现出的通常是正面清晰的快递单图像。上述快递识别模型可以包括快递检测模型、快递位置识别模型和快递信息识别模型。上述快递检测模型可以用于表征图像与图像中的快递单区域之间的对应关系。上述快递单区域可以是包含快递单的区域，例如，可以是包含快递单的最小区域。上述快递位置识别模型可以用于表征快递单区域与快递单区域中的快递单的位置信息之间的对应关系。上述快递信息识别模型可以用于表征快递单区域与快递单区域中的快递单上的快递信息之间的对应关系。上述确定单元可以通过如下方式基于上述快递图像和预先训练的快递识别模型，确定从上述快递图像中识别出的至少一个快递单中每个快递单的位置信息和每个快递单上的快递信息：上述确定单元可以首先基于上述区域快递图像和上述快递检测模型，确定上述区域快递图像中的快递单区域。具体地，上述确定单元可以将上述区域快递图像输入上述快递检测模型中，得到上述区域 快递图像中的快递单区域。上述确定单元可以将上述区域快递图像输入上述快递检测模型中，得到上述区域快递图像中的每个像素点是否为快递单区域的概率，从而确定上述区域快递图像中的快递单区域。之后，可以将上述快递单区域输入上述快递位置识别模型中，得到至少一个快递单中每个快递单的位置信息。而后，可以将上述快递单区域输入上述快递信息识别模型中，得到上述至少一个快递单中每个快递单上的快递信息。
在本实施例的一些可选的实现方式中，上述快递检测模型可以包括快递单检测模型和快递包裹检测模型。在这里，上述快递单检测模型可以用于表征图像与从图像中检测出初始快递单区域和初始快递单区域对应的预测概率之间的对应关系。上述快递包裹检测模型可以用于表征图像与从图像中检测出的快递包裹区域和快递包裹区域对应的预测概率之间的对应关系。上述快递包裹区域可以是包含快递包裹的区域，例如，可以是包含快递包裹的最小区域。
上述确定单元可以通过如下方式基于上述区域快递图像和上述快递检测模型，确定上述区域快递图像中的快递单区域：上述确定单元可以首先将上述区域快递图像输入上述快递单检测模型中，得到从上述区域快递图像中检测出的至少一个初始快递单区域和上述至少一个初始快递单区域中每个初始快递单区域对应的预测概率。需要说明的是，初始快递单区域可以以{x,y,w,h}的形式表征。在这里，x和y可以分别为初始快递单的预设位置在预设坐标系下的横坐标值和纵坐标值，w和h可以分别为初始快递单的宽和高。
之后，可以将上述区域快递图像输入上述快递包裹检测模型中，得到从上述区域快递图像中检测出的至少一个快递包裹区域和上述至少一个快递包裹区域中每个快递包裹区域对应的预测概率。需要说明的是，快递包裹区域也可以以{x,y,w,h}的形式表征。在这里，x和y可以分别为快递包裹的预设位置在预设坐标系下的横坐标值和纵坐标值，w和h可以分别为快递包裹的宽和高。通常来说，一个初始快递单区域与一个快递包裹区域相对应，通过初始快递单区域的区域位置与快递包裹区域的区域位置之间的关系确定初始快递单区域与快递包 裹区域之间的对应关系。若初始快递单区域与快递包裹区域存在至少部分区域相重叠，则通常可以说明其具有对应关系。通常情况下，具有对应关系的快递包裹区域中包含与其对应的初始快递单区域。在这里，上述快递包裹检测模型可以包括卷积层、池化层和全连接层。可以将上述区域快递图像输入上述快递包裹检测模型的卷积层，以将上述区域快递图像的像素点的像素特征与卷积核进行卷积操作，得到图像特征；之后，可以将上述图像特征输入上述快递包裹检测模型的池化层中，得到池化后的特征向量。可以采用最大池化和平均池化来提取特征。最后，可以将池化后的特征向量输入上述快递包裹检测模型的全连接层中，从而对池化后的特征向量进行分类，以得到快递包裹区域和对应的预测概率。
而后，可以基于上述至少一个初始快递单区域、上述至少一个初始快递单区域中每个初始快递单区域对应的预测概率、上述至少一个快递包裹区域和上述至少一个快递包裹区域中每个快递包裹区域对应的预测概率，确定上述区域快递图像中的快递单区域。具体地，上述确定单元可以首先通过上述至少一个初始快递单区域和上述至少一个快递包裹区域，确定包含初始快递单区域和快递包裹区域的多组对应关系。作为示例，可以将存在有重叠区域的初始快递单区域和快递包裹区域确定为一组对应关系。之后，针对上述多组对应关系中的每组对应关系，可以通过如下公式(1)确定该组对应关系中所包含的初始快递单区域为上述区域快递图像中的快递单区域的最终概率：
Figure PCTCN2021073321-appb-000002
其中，P为该组对应关系中所包含的初始快递单区域是上述区域快递图像中的快递单区域的最终概率，P bill为该组对应关系中所包含的初始快递单区域对应的预测概率，λ bill为该组对应关系中所包含的初始快递单区域对应的预测概率的权重，p package为该组对应关系中所包含的快递包裹区域对应的预测概率，λ package为该组对应关系中所包含的快递包裹区域对应的预测概率的权重。
最后，可以基于该组对应关系中所包含的初始快递单区域是上述区域快递图像中的快递单区域的最终概率P，确定上述该组对应关系 中所包含的初始快递单区域是否为上述区域快递图像中的快递单区域。具体地，若该组对应关系中所包含的初始快递单区域是上述区域快递图像中的快递单区域的最终概率P大于预设的概率阈值，则可以确定上述该组对应关系中所包含的初始快递单区域为上述区域快递图像中的快递单区域。
通过上述公式(1)可知，若该组对应关系中所包含的初始快递单区域对应的预测概率为0，则该组对应关系中所包含的初始快递单区域一定不是上述区域快递图像中的快递单区域。若该组对应关系中所包含的初始快递单区域对应的预测概率大于0，可以通过该组对应关系中所包含的快递包裹区域对应的预测概率来对其对应的初始快递单所对应的最终概率进行修正。
由于快递包裹之间颜色相近，区分快递包裹的边界具有一定的困难性，而快递单之间有与之颜色差异较大的快递包裹，因此，快递单相比于快递包裹较容易被识别出。通过上述这种从上述区域快递图像中确定快递单区域的方式可以以快递单的识别结果为主导，提高了快递包裹的检测效果。
在本实施例的一些可选的实现方式中，上述快递图像可以包括全景快递图像。上述全景快递图像通常指的是对放置有多个快递包裹的区域中的全部区域进行拍摄所得到的图像，因此，上述全景快递图像中通常呈现有所有快递包裹中的全部快递包裹。上述快递识别模型还包括全景识别模型。上述全景识别模型可以用于将区域快递图像中的快递单的位置信息映射到全景快递图像中，从而确定出区域快递图像中的某一快递单在全景快递图像中的位置信息。上述确定单元可以通过如下方式基于上述快递图像和预先训练的快递识别模型，确定从上述快递图像中识别出的至少一个快递单中每个快递单的位置信息和每个快递单上的快递信息：上述确定单元可以将上述区域快递图像和上述全景快递图像输入上述全景识别模型中，得到上述全景快递图像中快递单的位置信息与上述区域快递图像中快递单的位置信息之间的对应关系。具体地，上述确定单元可以将上述区域快递图像和上述全景快递图像输入上述全景识别模型中，得到上述区域快递图像中的某一 快递单的特征向量与上述全景快递图像中的各个快递单的特征向量之间的距离，可以选取距离最小的特征向量对应的快递单作为与上述区域快递图像中的这一快递单最为相似的快递单，并确定上述区域快递图像中的快递单与上述全景快递图像中的快递单之间的对应关系。需要说明的是，在确定上述区域快递图像中的某一快递单与上述全景快递图像中的各个快递单之间的相似度的过程中，可以利用检测框对上述全景快递图像中的各个快递单进行遍历。之后，可以存储上述全景快递图像中快递单的位置信息与上述区域快递图像中快递单的位置信息之间的对应关系。通过这种方式，可以将局部快递图像与全景快递图像相结合，通过对正面清晰的局部图像进行识别，而后在全景图像中定位出目标快递包裹。这种方式可以增加了单次识别快递包裹的数量，进一步提高了快递包裹查找效率。
下面参考图7，其示出了适于用来实现本公开的实施例的电子设备(例如图1中的服务器或终端设备)700的结构示意图。图7示出的电子设备仅仅是一个示例，不应对本公开的实施例的功能和使用范围带来任何限制。
如图7所示，电子设备700可以包括处理装置(例如中央处理器、图形处理器等)701，其可以根据存储在只读存储器(ROM)702中的程序或者从存储装置708加载到随机访问存储器(RAM)703中的程序而执行各种适当的动作和处理。在RAM 703中，还存储有电子设备700操作所需的各种程序和数据。处理装置701、ROM 702以及RAM 703通过总线704彼此相连。输入/输出(I/O)接口705也连接至总线704。
通常，以下装置可以连接至I/O接口705：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置706；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置707；以及通信装置709。通信装置709可以允许电子设备700与其他设备进行无线或有线通信以交换数据。虽然图7示出了具有各种装置的电子设备700，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。图7中示出的每个方框可 以代表一个装置，也可以根据需要代表多个装置。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置709从网络上被下载和安装，或者从存储装置708被安装，或者从ROM 702被安装。在该计算机程序被处理装置701执行时，执行本公开的实施例的方法中限定的上述功能。需要说明的是，本公开的实施例所述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开的实施例中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开的实施例中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。上述计算机可读介质承载有一 个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：接收快递定位请求，其中，快递定位请求用于从呈现有快递包裹的快递图像中定位目标快递包裹对应的快递单，快递定位请求包括快递信息；查找预先存储的、与快递信息对应的快递单的位置信息；利用位置信息，生成快递定位结果图像，其中，快递定位结果图像包括定位标识，定位标识用于从快递图像中指示出目标快递包裹对应的快递单；输出快递定位结果图像。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的实施例的操作的计算机程序代码，所述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)——连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开的实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。所描述的单元也可以设置在处理 器中，例如，可以描述为：一种处理器包括接收单元、查找单元、生成单元和输出单元。其中，这些单元的名称在某种情况下并不构成对该单元本身的限定，例如，输出单元还可以被描述为“输出快递定位结果图像的单元”。
以上描述仅为本公开的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开的实施例中所涉及的发明范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述发明构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开的实施例中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。

Claims (8)

  1. 一种用于定位快递包裹的方法，包括：
    接收快递定位请求，其中，所述快递定位请求用于从呈现有快递包裹的快递图像中定位目标快递包裹对应的快递单，所述快递定位请求包括快递信息；
    查找预先存储的、与所述快递信息对应的快递单的位置信息；
    利用所述位置信息，生成快递定位结果图像，其中，所述快递定位结果图像包括定位标识，所述定位标识用于从所述快递图像中指示出所述目标快递包裹对应的快递单；
    输出所述快递定位结果图像。
  2. 根据权利要求1所述的方法，其中，在所述接收快递定位请求之前，所述方法包括：
    获取所述呈现有快递包裹的快递图像；
    基于所述快递图像和预先训练的快递识别模型，确定从所述快递图像中识别出的至少一个快递单中每个快递单的位置信息和每个快递单上的快递信息；
    将所述至少一个快递单中每个快递单的位置信息与对应的快递信息进行关联存储。
  3. 根据权利要求2所述的方法，其中，所述快递图像包括区域快递图像，所述快递识别模型包括快递检测模型、快递位置识别模型和快递信息识别模型；以及
    所述基于所述快递图像和预先训练的快递识别模型，确定从所述快递图像中识别出的至少一个快递单中每个快递单的位置信息和每个快递单上的快递信息，包括：
    基于所述区域快递图像和所述快递检测模型，确定所述区域快递图像中的快递单区域；
    将所述快递单区域输入所述快递位置识别模型中，得到至少一个 快递单中每个快递单的位置信息；
    将所述快递单区域输入所述快递信息识别模型中，得到至少一个快递单中每个快递单上的快递信息。
  4. 根据权利要求3所述的方法，其中，所述快递检测模型包括快递单检测模型和快递包裹检测模型；以及
    所述基于所述区域快递图像和所述快递检测模型，确定所述区域快递图像中的快递单区域，包括：
    将所述区域快递图像输入所述快递单检测模型中，得到从所述区域快递图像中检测出的至少一个初始快递单区域和所述至少一个初始快递单区域中每个初始快递单区域对应的预测概率；
    将所述区域快递图像输入所述快递包裹检测模型中，得到从所述区域快递图像中检测出的至少一个快递包裹区域和所述至少一个快递包裹区域中每个快递包裹区域对应的预测概率；
    基于所述至少一个初始快递单区域、所述至少一个初始快递单区域中每个初始快递单区域对应的预测概率、所述至少一个快递包裹区域和所述至少一个快递包裹区域中每个快递包裹区域对应的预测概率，确定所述区域快递图像中的快递单区域。
  5. 根据权利要求3或4所述的方法，其中，所述快递图像包括全景快递图像，所述快递识别模型还包括全景识别模型；以及
    所述基于所述快递图像和预先训练的快递识别模型，确定从所述快递图像中识别出的至少一个快递单中每个快递单的位置信息和每个快递单上的快递信息，包括：
    将所述区域快递图像和所述全景快递图像输入所述全景识别模型中，得到所述全景快递图像中快递单的位置信息与所述区域快递图像中快递单的位置信息之间的对应关系；
    存储所述全景快递图像中快递单的位置信息与所述区域快递图像中快递单的位置信息之间的对应关系。
  6. 一种用于定位快递包裹的装置，包括：
    接收单元，被配置成接收快递定位请求，其中，所述快递定位请求用于从呈现有快递包裹的快递图像中定位目标快递包裹对应的快递单，所述快递定位请求包括快递信息；
    查找单元，被配置成查找预先存储的、与所述快递信息对应的快递单的位置信息；
    生成单元，被配置成利用所述位置信息，生成快递定位结果图像，其中，所述快递定位结果图像包括定位标识，所述定位标识用于从所述快递图像中指示出所述目标快递包裹对应的快递单；
    输出单元，被配置成输出所述快递定位结果图像。
  7. 一种电子设备，包括：
    一个或多个处理器；
    存储装置，其上存储有一个或多个程序，
    当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1-5中任一所述的方法。
  8. 一种计算机可读介质，其上存储有计算机程序，其中，该程序被处理器执行时实现如权利要求1-5中任一所述的方法。
PCT/CN2021/073321 2020-03-30 2021-01-22 用于定位快递包裹的方法和装置 WO2021196836A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP21778855.3A EP4131100A4 (en) 2020-03-30 2021-01-22 METHOD AND DEVICE FOR POSITIONING EXPRESS PARCEL PACKAGES
US17/914,216 US20230123879A1 (en) 2020-03-30 2021-01-22 Method and apparatus for positioning express parcel

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010239330.1 2020-03-30
CN202010239330.1A CN112308915A (zh) 2020-03-30 2020-03-30 用于定位快递包裹的方法和装置

Publications (1)

Publication Number Publication Date
WO2021196836A1 true WO2021196836A1 (zh) 2021-10-07

Family

ID=74336765

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/073321 WO2021196836A1 (zh) 2020-03-30 2021-01-22 用于定位快递包裹的方法和装置

Country Status (4)

Country Link
US (1) US20230123879A1 (zh)
EP (1) EP4131100A4 (zh)
CN (1) CN112308915A (zh)
WO (1) WO2021196836A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115965900A (zh) * 2023-03-09 2023-04-14 杭州也得智能有限公司 一种快件识别搜寻系统及方法

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113706613A (zh) * 2021-08-06 2021-11-26 百度在线网络技术（北京）有限公司 快递定位方法及其装置
US12020690B1 (en) * 2021-09-29 2024-06-25 Amazon Technologies, Inc. Adaptive targeting for proactive voice notifications

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070138285A1 (en) * 2005-12-19 2007-06-21 Pitney Bowes Inc. Black fluorescent optical codes and process for printing and reading
CN109271935A (zh) * 2018-09-17 2019-01-25 北京旷视科技有限公司 物品与电子标签的配对方法、装置及系统
CN110443551A (zh) * 2019-08-08 2019-11-12 上海中通吉网络技术有限公司 快递跟踪方法、电子设备及快递管理系统

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
RU2597492C2 (ru) * 2012-03-15 2016-09-10 Ска Хайджин Продактс Аб Способ содействия обнаружению предмета в месте хранения
WO2014177751A1 (en) * 2013-04-29 2014-11-06 Nokia Corporation Method and apparatus for finding a location
CN104951915A (zh) * 2015-05-19 2015-09-30 桂林 一种利用虚拟联络员完成实时快递的信息系统与设备
CN106355174B (zh) * 2016-09-23 2023-06-20 华南理工大学 一种快递单关键信息动态提取方法及系统
CN107368983A (zh) * 2017-06-09 2017-11-21 张敏 一种系统提高快递效率的系统
CN107341523A (zh) * 2017-07-13 2017-11-10 浙江捷尚视觉科技股份有限公司 基于深度学习的快递单信息识别方法和系统
CN107622247B (zh) * 2017-09-26 2020-08-25 华东师范大学 一种快递运单的定位与提取方法
KR20180009330A (ko) * 2017-12-28 2018-01-26 에스지생활안전 주식회사 상품 추적 시스템 및 상품 추적 방법
CN109141451B (zh) * 2018-07-13 2023-02-10 京东方科技集团股份有限公司 购物定位系统及方法、智能购物车、电子设备
CN110102490B (zh) * 2019-05-23 2021-06-01 北京阿丘机器人科技有限公司 基于视觉技术的流水线包裹分拣装置和电子设备
CN110210488A (zh) * 2019-06-14 2019-09-06 上海中通吉网络技术有限公司 一种快递运单上条形码和手机号的识别方法和装置
CN110309796A (zh) * 2019-07-05 2019-10-08 上海中通吉网络技术有限公司 面单识别方法、装置和设备
KR20190101929A (ko) * 2019-08-16 2019-09-02 주식회사 알지비솔루션 바코드인식과 영상촬영기능을 갖는 웨어러블 무선단말기 및 이를 이용한 화물영상추적 시스템
CN110446082B (zh) * 2019-08-23 2021-11-30 北京市商汤科技开发有限公司 广告推送方法、信息处理方法及相关产品
CN110705486B (zh) * 2019-10-08 2021-06-25 济南东朔微电子有限公司 一种基于视频图像识别快递面单上倾斜数字的方法
CN110844508B (zh) * 2019-11-18 2021-03-02 中科微至智能制造科技江苏股份有限公司 一种包裹运输控制方法和系统

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070138285A1 (en) * 2005-12-19 2007-06-21 Pitney Bowes Inc. Black fluorescent optical codes and process for printing and reading
CN109271935A (zh) * 2018-09-17 2019-01-25 北京旷视科技有限公司 物品与电子标签的配对方法、装置及系统
CN110443551A (zh) * 2019-08-08 2019-11-12 上海中通吉网络技术有限公司 快递跟踪方法、电子设备及快递管理系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4131100A4

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115965900A (zh) * 2023-03-09 2023-04-14 杭州也得智能有限公司 一种快件识别搜寻系统及方法

Also Published As

Publication number Publication date
CN112308915A (zh) 2021-02-02
US20230123879A1 (en) 2023-04-20
EP4131100A1 (en) 2023-02-08
EP4131100A4 (en) 2024-04-17

Similar Documents

Publication Publication Date Title
WO2021196836A1 (zh) 用于定位快递包裹的方法和装置
US9336541B2 (en) Augmented reality product instructions, tutorials and visualizations
CN108307240B (zh) 视频推荐方法和装置
US9165206B2 (en) Updating point of interest data based on an image
US8737737B1 (en) Representing image patches for matching
CN108830329B (zh) 图片处理方法和装置
US10528808B2 (en) Automated document processing system
US20140365307A1 (en) Transmitting listings based on detected location
CN113420757B (zh) 文本审核方法、装置、电子设备和计算机可读介质
CN111767750A (zh) 图像处理方法和装置
CN112766284A (zh) 图像识别方法和装置、存储介质和电子设备
CN110198473A (zh) 视频处理方法、装置、电子设备及计算机可读存储介质
WO2024131630A1 (zh) 车牌识别方法、装置、电子设备及存储介质
CN111598128B (zh) 用户界面的控件状态识别、控制方法、装置、设备及介质
CN111260445A (zh) 房源信息展示方法、装置、终端及存储介质
US11798210B2 (en) Neural network based detection of image space suitable for overlaying media content
US20140231523A1 (en) Electronic device capable of recognizing object
CN115422123A (zh) 数据处理方法、装置、电子设备及存储介质
CN110991270B (zh) 文本识别的方法、装置、电子设备和存储介质
CN109634827A (zh) 用于生成信息的方法和装置
CN109508519A (zh) 用于处理请求的方法和装置
CN110020906A (zh) 订单信息的检测方法和装置
US20230161989A1 (en) Method and system for setting dynamic image threshold for two-dimensional identification code detection
US11625929B2 (en) Selection of object recognition models for computer vision
US20230260309A1 (en) Table extraction from image-based documents

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21778855

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2021778855

Country of ref document: EP

Effective date: 20221031