Automatic detection of point of interest change using cohort analysis

Patent metadata

Field	Value
Publication number	US-2019370349-A1
Application number	US-201815993328-A
Country	US
Kind code	A1
Filing date	May 30, 2018
Priority date	May 30, 2018
Publication date	Dec 5, 2019
Grant date	—

Abstract

Systems and methods for maintaining a current database of point of interest (POI) by automatically detecting a change associated with a POI based on cohort analysis are provided. A networked system accesses trip data associated with the POI. Using the analyzed trip data, the networked system generates a cohort associated with the POI. The networked system monitors for, and detects a change in, trip behavior in the cohort associated with the POI. In response to detecting the change in trip behavior, the networked system updates a database in a data store to indicate a status update.

First claim

What is claimed is:

1 . A system comprising:
one or more hardware processors; and a memory storing instructions that, when executed by the one or more hardware processors, causes the one or more hardware processors to perform operations comprising:
accessing and analyzing trip data associated with a point of interest (POI);
using the analyzed trip data, generating a cohort associated with the POI;
detecting a change in trip behavior in the cohort associated with the POI; and
in response to detecting the change in trip behavior, updating a database in a data store to indicate a status update.

2 . The system of claim 1 , wherein the analyzing the trip data comprises:
identifying the POI and a user traveling to the POI for each trip of the trip data; determining that the user traveled to the POI at a frequency that exceeds a frequency threshold; and in response to the determining, tying the user to the POI in a database.

3 . The system of claim 2 , wherein the generating the cohort comprises grouping together users tied to the POI.

4 . The system of claim 1 , wherein the detecting the change comprises detecting that a threshold number of users in the cohort stopped going to a location corresponding to the POI.

5 . The system of claim 4 , wherein:
the detecting the change comprises determining whether a threshold percentage of the threshold number of users is traveling to a second location; and the updating the database comprises updating a data structure to indicate that the POI is closed based on the determining that the threshold percentage of the threshold number of users is not traveling to the second location,

6 . The system of claim 4 , wherein the detecting the change comprises:
determining that a threshold percentage of the threshold number of users is traveling to a second location; and determining whether the second location is a new location for the POI or whether the second location associated with a new POI, the determining whether the second location is associated with the new POI comprising detecting that a portion of the cohort is still traveling to the location corresponding to the POI.

7 . The system of claim 6 , wherein the updating the database comprises including the new POI in the database based on the determining that the second location is associated with the new POI.

8 . The system of claim 1 , wherein the updating the database comprises flagging the POI with an indication of a status change, the flagging comprising indicating that the POI has moved, indicating that the POI has closed, or indicating that a new POI in a same category as the POI has opened.

9 . The system of claim 1 , wherein the updating the database comprises changing location data for the POI in the database based on detecting that the POI has moved.

10 . The system of claim 1 , wherein the operations further comprise, in response to the detecting the change, triggering a verification process to verify the status update.

11 . A method comprising:
accessing and analyzing trip data associated with a point of interest (POI); using the analyzed trip data, generating, by one or more hardware processors, a cohort associated with the POI; detecting a change in trip behavior in the cohort associated with the POI; and in response to detecting the change in trip behavior, updating a database in a data store to indicate a status update.

12 . The method of claim 11 , wherein the analyzing the trip data comprises:
identifying the POI and a user traveling to the POI for each trip of the trip data; determining that the user traveled to the POI at a frequency that exceeds a frequency threshold; and in response to the determining, tying the user to the POI in a database.

13 . The method of claim 12 , wherein the generating the cohort comprises grouping together users tied to the POI.

14 . The method of claim 11 , wherein the detecting the change comprises detecting that a threshold number of users in the cohort stopped going to a location corresponding to the POI.

15 . The method of claim 14 , wherein:
the detecting the change comprises determining whether a threshold percentage of the threshold number of users is traveling to a second location; and the updating the database comprises updating a data structure to indicate that the POI is closed based on the determining that the threshold percentage of the threshold number of users is not traveling to the second location,

16 . The method of claim 14 , wherein the detecting the change comprises:
determining that a threshold percentage of the threshold number of users is traveling to a second location; and determining whether the second location is a new location for the POI or whether the second location is associated with a new POI, the determining whether the second location is associated with the new POI comprising detecting that a portion of the cohort is still traveling to the location corresponding to the POI.

17 . The method of claim 11 , wherein the updating the database comprises flagging the POI with an indication of a status change, the flagging comprising indicating that the POI has moved, indicating that the POI has closed, or indicating that a new POI in a same category as the POI has opened.

18 . The method of claim 11 , further comprising, in response to the detecting the change, triggering a verification process to verify the status update.

19 . A machine-storage medium storing instructions that, when executed by one or more processors of a machine, cause the one or more processors to perform operations comprising:
accessing and analyzing trip data associated with a point of interest (POI); using the analyzed trip data, generating a cohort associated with the POI; detecting a change in trip behavior in the cohort associated with the POI; and in response to detecting the change in trip behavior, updating a database in a data store to indicate a status update.

20 . The machine-storage medium of claim 19 , wherein the operations further comprise, in response to the detecting the change, triggering a verification process to verify the status update.

Assignees

• Uber Technologies Inc

Inventors

• Saxena Vikram

Classifications

• G06F16/285

  Clustering or classification · CPC title

• G06F16/215

  Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors · CPC title

• G06F16/29 Primary

  Geographical information databases · CPC title

• G06F16/9535

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/2379

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