IP Library Granted Patent US 12,307,408
Granted Patent B2
US 12,307,408 · App. 17/914,216 · Granted May 20, 2025

Method and apparatus for positioning express parcel

Inventors: Peng Zhou (Beijing, CN); Yuntao Wang (Beijing, CN); Mo Zhou (Beijing, CN)
Assignees: Beijing Wodong Tianjun Information Technology Co., Ltd.; Beijing Jingdong Century Trading Co., Ltd.
G06Q10/0833G06T7/75G06T2207/10004G06V30/424
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,307,408
App. No.
17/914,216
Granted
May 20, 2025
Kind
B2
Abstract

A method and apparatus for locating an express package. The method includes: receiving an express locating request, where the express locating request is used to locate an express waybill corresponding to a target express package from an express image presenting express packages, and the express locating request includes express information; searching for pre-stored location information of the express waybill corresponding to the express information; generating an express locating result image by means of the location information, where the express locating result image includes a locating identifier, and the locating identifier is used to indicate the express waybill corresponding to the target express package from the express image; and outputting the express locating result image.

Claims (84)

1. A method for locating an express package, comprising:

receiving an express locating request, wherein the express locating request is used to locate an express waybill corresponding to a target express package from an express image presenting express packages, and the express locating request comprises express information;

searching for pre-stored location information of the express waybill corresponding to the express information;

generating an express locating result image by means of the location information, wherein the express locating result image comprises a locating identifier, and the locating identifier is used to indicate the express waybill corresponding to the target express package from the express image; and

outputting the express locating result image.

2. The method according to claim 1 , wherein before receiving the express locating request, the method comprises:

acquiring the express image presenting express packages;

determining, based on the express image and a pre-trained express identification model, location information of each express waybill in at least one express waybill identified from the express image and express information on each express waybill; and

associatively storing the location information of each express waybill in the at least one express waybill with the corresponding express information.

3. The method according to claim 2 , wherein the express image comprises a regional express image, and the express identification model comprises an express detection model, an express location identification model, and an express information identification model; and

determining, based on the express image and the pre-trained express identification model, location information of each express waybill in at least one express waybill identified from the express image and express information on each express waybill comprises:

determining an express waybill region in the regional express image based on the regional express image and the express detection model;

inputting the express waybill region into the express location identification model, to obtain the location information of each express waybill in the at least one express waybill; and

inputting the express waybill region into the express information identification model, to obtain the express information on each express waybill in the at least one express waybill.

4. The method according to claim 3 , wherein the express detection model comprises an express waybill detection model and an express package detection model; and

determining the express waybill region in the regional express image based on the regional express image and the express detection model comprises:

inputting the regional express image into the express waybill detection model, to obtain at least one initial express waybill region detected from the regional express image and a predicted probability corresponding to each initial express waybill region in the at least one initial express waybill region;

inputting the regional express image into the express package detection model, to obtain at least one express package region detected from the regional express image and a predicted probability corresponding to each express package region in the at least one express package region; and

determining the express waybill region in the regional express image based on the at least one initial express waybill region, the predicted probability corresponding to each initial express waybill region in the at least one initial express waybill region, the at least one express package region, and the predicted probability corresponding to each express package region in the at least one express package region.

5. The method according to claim 4 , wherein the express image comprises a panoramic express image, and the express identification model further comprises a panoramic identification model; and

determining, based on the express image and the pre-trained express identification model, location information of each express waybill in at least one express waybill identified from the express image and express information on each express waybill comprises:

inputting the regional express image and the panoramic express image into the panoramic identification model, to obtain a corresponding relationship between the location information of the express waybill in the panoramic express image and the location information of the express waybill in the regional express image; and

storing the corresponding relationship between the location information of the express waybill in the panoramic express image and the location information of the express waybill in the regional express image.

6. The method according to claim 3 , wherein the express image comprises a panoramic express image, and the express identification model further comprises a panoramic identification model; and

determining, based on the express image and the pre-trained express identification model, location information of each express waybill in at least one express waybill identified from the express image and express information on each express waybill comprises:

inputting the regional express image and the panoramic express image into the panoramic identification model, to obtain a corresponding relationship between the location information of the express waybill in the panoramic express image and the location information of the express waybill in the regional express image; and

storing the corresponding relationship between the location information of the express waybill in the panoramic express image and the location information of the express waybill in the regional express image.

7. An electronic device, comprising:

one or more processors; and

a storage apparatus, storing one or more programs,

wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform operations, comprising:

receiving an express locating request, wherein the express locating request is used to locate an express waybill corresponding to a target express package from an express image presenting express packages, and the express locating request comprises express information:

searching for pre-stored location information of the express waybill corresponding to the express information;

generating an express locating result image by means of the location information, wherein the express locating result image comprises a locating identifier, and the locating identifier is used to indicate the express waybill corresponding to the target express package from the express image; and

outputting the express locating result image.

8. The electronic device according to claim 7 , wherein before receiving the express locating request, the method comprises:

acquiring the express image presenting express packages;

determining, based on the express image and a pre-trained express identification model, location information of each express waybill in at least one express waybill identified from the express image and express information on each express waybill; and

associatively storing the location information of each express waybill in the at least one express way bill with the corresponding express information.

9. The electronic device according to claim 8 , wherein the express image comprises a regional express image, and the express identification model comprises an express detection model, an express location identification model, and an express information identification model; and

determining, based on the express image and the pre-trained express identification model, location information of each express waybill in at least one express waybill identified from the express image and express information on each express waybill comprises:

determining an express waybill region in the regional express image based on the regional express image and the express detection model;

inputting the express waybill region into the express location identification model, to obtain the location information of each express waybill in the at least one express waybill; and

inputting the express waybill region into the express information identification model, to obtain the express information on each express waybill in the at least one express waybill.

10. The electronic device according to claim 9 , wherein the express detection model comprises an express waybill detection model and an express package detection model; and

determining the express waybill region in the regional express image based on the regional express image and the express detection model comprises:

inputting the regional express image into the express waybill detection model, to obtain at least one initial express waybill region detected from the regional express image and a predicted probability corresponding to each initial express waybill region in the at least one initial express way bill region;

inputting the regional express image into the express package detection model, to obtain at least one express package region detected from the regional express image and a predicted probability corresponding to each express package region in the at least one express package region; and

determining the express waybill region in the regional express image based on the at least one initial express waybill region, the predicted probability corresponding to each initial express waybill region in the at least one initial express waybill region, the at least one express package region, and the predicted probability corresponding to each express package region in the at least one express package region.

11. The electronic device according to claim 10 , wherein the express image comprises a panoramic express image, and the express identification model further comprises a panoramic identification model; and

determining, based on the express image and the pre-trained express identification model, location information of each express waybill in at least one express waybill identified from the express image and express information on each express way bill comprises:

inputting the regional express image and the panoramic express image into the panoramic identification model, to obtain a corresponding relationship between the location information of the express waybill in the panoramic express image and the location information of the express waybill in the regional express image; and

storing the corresponding relationship between the location information of the express waybill in the panoramic express image and the location information of the express waybill in the regional express image.

12. The electronic device according to claim 9 , wherein the express image comprises a panoramic express image, and the express identification model further comprises a panoramic identification model; and

determining, based on the express image and the pre-trained express identification model, location information of each express waybill in at least one express waybill identified from the express image and express information on each express waybill comprises:

inputting the regional express image and the panoramic express image into the panoramic identification model, to obtain a corresponding relationship between the location information of the express waybill in the panoramic express image and the location information of the express waybill in the regional express image; and

storing the corresponding relationship between the location information of the express waybill in the panoramic express image and the location information of the express waybill in the regional express image.

13. A non-transitory computer-readable medium storing a computer program, wherein the program when executed by a processor, causes the processor to perform operations, comprising:

receiving an express locating request, wherein the express locating request is used to locate an express waybill corresponding to a target express package from an express image presenting express packages, and the express locating request comprises express information:

searching for pre-stored location information of the express waybill corresponding to the express information;

generating an express locating result image by means of the location information, wherein the express locating result image comprises a locating identifier, and the locating identifier is used to indicate the express waybill corresponding to the target express package from the express image; and

outputting the express locating result image.

14. The non-transitory computer-readable medium according to claim 13 , wherein before receiving the express locating request, the method comprises:

acquiring the express image presenting express packages;

determining, based on the express image and a pre-trained express identification model, location information of each express waybill in at least one express waybill identified from the express image and express information on each express waybill; and

associatively storing the location information of each express waybill in the at least one express waybill with the corresponding express information.

15. The non-transitory computer-readable medium according to claim 14 , wherein the express image comprises a regional express image, and the express identification model comprises an express detection model, an express location identification model, and an express information identification model; and

determining, based on the express image and the pre-trained express identification model, location information of each express waybill in at least one express waybill identified from the express image and express information on each express way bill comprises:

determining an express waybill region in the regional express image based on the regional express image and the express detection model;

inputting the express waybill region into the express location identification model, to obtain the location information of each express waybill in the at least one express waybill; and

inputting the express waybill region into the express information identification model, to obtain the express information on each express waybill in the at least one express waybill.

16. The non-transitory computer-readable medium according to claim 15 , wherein the express detection model comprises an express waybill detection model and an express package detection model; and

determining the express waybill region in the regional express image based on the regional express image and the express detection model comprises:

inputting the regional express image into the express waybill detection model, to obtain at least one initial express waybill region detected from the regional express image and a predicted probability corresponding to each initial express waybill region in the at least one initial express waybill region;

inputting the regional express image into the express package detection model, to obtain at least one express package region detected from the regional express image and a predicted probability corresponding to each express package region in the at least one express package region; and

determining the express waybill region in the regional express image based on the at least one initial express waybill region, the predicted probability corresponding to each initial express waybill region in the at least one initial express waybill region, the at least one express package region, and the predicted probability corresponding to each express package region in the at least one express package region.

17. The non-transitory computer-readable medium according to claim 16 , wherein the express image comprises a panoramic express image, and the express identification model further comprises a panoramic identification model; and

determining, based on the express image and the pre-trained express identification model, location information of each express waybill in at least one express way bill identified from the express image and express information on each express waybill comprises:

inputting the regional express image and the panoramic express image into the panoramic identification model, to obtain a corresponding relationship between the location information of the express waybill in the panoramic express image and the location information of the express waybill in the regional express image; and

storing the corresponding relationship between the location information of the express waybill in the panoramic express image and the location information of the express waybill in the regional express image.

18. The non-transitory computer-readable medium according to claim 15 , wherein the express image comprises a panoramic express image, and the express identification model further comprises a panoramic identification model; and

determining, based on the express image and the pre-trained express identification model, location information of each express waybill in at least one express waybill identified from the express image and express information on each express waybill comprises:

inputting the regional express image and the panoramic express image into the panoramic identification model, to obtain a corresponding relationship between the location information of the express waybill in the panoramic express image and the location information of the express waybill in the regional express image; and

storing the corresponding relationship between the location information of the express waybill in the panoramic express image and the location information of the express waybill in the regional express image.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 23, 2022
From: ZHOU, PENG; WANG, YUNTAO; ZHOU, MO
To: BEIJING WODONG TIANJUN INFORMATION TECHNOLOGY CO., LTD.; BEIJING JINGDONG CENTURY TRADING CO., LTD.
Reel/Frame 061198/0817 →
Priority Claims (1)
CN 202010239330.1 · Mar 30, 2020 · national
Continuity (1)
Related Publication 20230123879A1 · Apr 20, 2023
References Cited (28)
US 10854055B1 · Cornell · 2020 [cited by examiner]
US 11163968B1 · Boguszewski · 2021 [cited by examiner]
US 20070138285A1 · Auslander et al. · 2007 [cited by applicant]
US 20190043004A1 · Lesieur · 2019 [cited by examiner]
US 20200018603A1 · Deng et al. · 2020 [cited by applicant]
CN 104951915A · 2015 [cited by applicant]
CN 106355174A · 2017 [cited by applicant]
CN 107341523A · 2017 [cited by applicant]
CN 107368983A · 2017 [cited by applicant]
CN 107622247A · 2018 [cited by applicant]
CN 207622247A · 2018 [cited by applicant]
CN 108696594A · 2018 [cited by applicant]
CN 109271935A · 2019 [cited by applicant]
CN 110102490A · 2019 [cited by applicant]
CN 110210488A · 2019 [cited by applicant]
CN 110263047A · 2019 [cited by applicant]
CN 110309796A · 2019 [cited by applicant]
CN 110443551A · 2019 [cited by applicant]
CN 110446082A · 2019 [cited by applicant]
CN 110705486A · 2020 [cited by applicant]
CN 10844508A · 2020 [cited by applicant]
CN 111866085A · 2020 [cited by applicant]
KR 1020180009330A · 2018 [cited by applicant]
KR 1020190101929A · 2019 [cited by applicant]
WO 2013137789A1 · 2013 [cited by applicant]
WO WO2014177751A1 · 2014 [cited by examiner]
International Search Report and Written Opinion for PCT/CN2021/092931, dated Jul. 30, 2021, 4 pgs. [cited by applicant]
Liu et al., Location and Processing the Handwriting Information Region of Scanned Express Form Images, Computer Knowledge and Technology, vol. 8, No. 32, Nov. 2012, 3 pages. [cited by applicant]