Computerized systems and methods for address correction

Patent metadata

Field	Value
Publication number	US-11328249-B2
Application number	US-202016805647-A
Country	US
Kind code	B2
Filing date	Feb 28, 2020
Priority date	Jul 15, 2019
Publication date	May 10, 2022
Grant date	May 10, 2022

Abstract

A computer-implemented system for correcting address information. The system may include a memory storing instructions and at least one processor configured to execute the instructions to perform operations. The operations may include requesting an address for normalization from at least one of a current address or a residential history of a user; receiving, from a user device, a user input including requested address information responsive to the request for normalization; searching, based on the user input, a cache to determine whether a refined version of the requested address is available; returning, based on a determination that a refined version of the requested address exists in the cache, a refined address as the normalized address to the user; and beginning to transport a package to the user at the normalized address, by providing instructions to a mobile device associated with a delivery worker, to transport the package to the normalized address.

First claim

What is claimed is:

1. A computer-implemented system for correcting address information, the system comprising:
a memory storing instructions; and
at least one processor configured to execute the instructions to:
receive, from a user device, an address for normalization, wherein the address is one of a current address or a historical residential address of a user;
normalize the address;
compare a location associated with the normalized address to a current location of a delivery worker;
based on a determination that the normalized address location does not match the current location of the delivery worker, transmit a warning to the user device;
correct the normalized address, based on a machine learning process;
store, based on the correction, the corrected normalized address in a database;
provide instructions to a mobile device of the delivery worker to deliver a package to the user at a delivery location based on the corrected normalized address;
generate, by the processor, a learning curve based on the corrected normalized address information;
develop, based on a determination of common differences, a corrective pattern; and
modify, based on the generation of a learning curve and the corrective pattern, a predetermined threshold for correcting inputted address information.

2. The computer-implemented system of claim 1 , wherein the determination that the normalized address location does not match the current location of the delivery worker comprises
determining that an amount of detected differences between the normalized address location and the current location of the delivery worker exceeds a predetermined threshold.

3. The computer-implemented system of claim 2 , wherein the predetermined threshold includes a predetermined number of differences between the normalized address location and the current location of the delivery worker, and wherein the differences include at least one of differences in numbers, street names, zip codes, city names, and district names.

4. The computer-implemented system of claim 1 , wherein the location of the delivery worker includes at least one of stored location data, stored map data, region, neighborhood divisions, or a residence title.

5. The computer-implemented system of claim 1 , wherein the at least one processor is further configured to execute the instructions to:
compare, while the package is in transit, the normalized address location to address information stored in a database, wherein the database includes a dictionary of address terms.

6. The computer-implemented system of claim 1 , wherein the at least one processor is further configured to execute the instructions to:
develop, based on a determination of multiple differences between the normalized address and the current location of the delivery worker, a corrective pattern to correct future user input that includes address information.

7. The computer-implemented system of claim 1 , wherein the at least one processor is further configured to execute the instructions to:
receive the user input including requested address information from the user from at least one of a web browser, a mobile device, or a user database.

8. A computer-implemented method for correcting address information, the method comprising:
receiving, from a user device, an address for normalization, wherein the address is one of a current address or a historical residential address of a user;
normalizing the address;
comparing a location associated with the normalized address to a current location of a delivery worker;
based on a determination that the normalized address location does not match the current location of the delivery worker, transmitting a warning to the user device;
correcting the normalized address, based on a machine learning process;
storing, based on the correction, the corrected normalized address in a database;
providing instructions to a mobile device of the delivery worker to deliver a package to the user at a delivery location based on the corrected normalized address;
generating, by the processor, a learning curve based on the corrected normalized address information;
developing, based on a determination of common differences, a corrective pattern; and
modifying, based on the generation of a learning curve and the corrective pattern, a predetermined threshold for correcting inputted address information.

9. The computer-implemented method of claim 8 , the method comprising:
communicating, if it is determined that an amount of detected differences between the normalized address location and the current location of the delivery worker exceeds a predetermined threshold, a notification to the user that the normalized address location does not match the current location of the delivery worker.

10. The computer-implemented method of claim 8 , the method comprising:
receiving the user input including requested address information from the user from at least one of a web browser, a mobile device, or a user database.

11. The computer-implemented method of claim 8 , wherein the location of the delivery worker includes at least one of stored location data, stored map data, region, neighborhood divisions, or a residence title.

12. The computer-implemented method of claim 8 , the method comprising:
comparing, while the package is in transit, the normalized address location to address information stored in a database, wherein the database includes a dictionary of address terms.

13. The computer-implemented method of claim 8 , wherein the at least one processor is further configured to execute the instructions to:
develop, based on a determination of multiple differences between the normalized address and the current location of the delivery worker, a corrective pattern to correct future user input that includes address information.

14. The computer-implemented method of claim 8 , wherein the predetermined threshold includes a predetermined number of differences between the normalized address location and the current location of the delivery worker, and wherein the differences include at least one of differences in numbers, street names, zip codes, city names, and district names.

15. A non-transitory computer readable medium comprising executable instructions that when executed by at least one processing device cause the at least one processing device to correct address information and perform operations comprising:
receiving, from a user device, an address for normalization, wherein the address is one of a current address or a historical residential address of a user;
normalizing the address;
comparing a location associated with the normalized address to a current location of a delivery worker;
based on a determination that the normalized address location does not match the current location of the delivery worker, transmitting a warning to the user device;
correcting the normalized address, based on a machine learning process;
storing, based on the correction, the corrected normalized address in a database;
providing instructions to a mobile device of the delivery worker to deliver a package to the user at a delivery location based on the corrected normalized address;
generating, by the processor, a learning curve based on the corrected normalized address information;
developing, based on a determination of common differences, a corrective pattern; and
modifying, based on the generation of a learning curve and the corrective pattern, a predetermined threshold for correcting inputted address information.

16. The non-transitory computer readable medium of cl

Assignees

• Coupang Corp

Inventors

• Lee Hanjun
• Lee Kyoungwook
• Jeon Hansham
• Lim Hyunsu
• Song Taeho

Classifications

• G06Q10/0838 Primary

  Historical data · CPC title

• G06Q10/08355 Primary

  Routing methods · CPC title

• G06F16/2379

  Updates performed during online database operations; commit processing · CPC title

• G06F16/2365

  Ensuring data consistency and integrity · CPC title

• G06F16/29

  Geographical information databases · CPC title