Inferring accurate locations

Patent metadata

Field	Value
Publication number	US-12535326-B2
Application number	US-202217807293-A
Country	US
Kind code	B2
Filing date	Jun 16, 2022
Priority date	Jun 16, 2022
Publication date	Jan 27, 2026
Grant date	Jan 27, 2026

Abstract

Systems and methods herein describe a network system for generating inferred accurate locations. The systems and methods receive a transportation trip request from a first computing device that includes a target address, access a first plurality of historical location data and a second plurality of historical data, generate clustered location data using the first plurality of historical location data and the second plurality of historical location data, select a subset of cluster locations from the clustered location data, determine an inferred accurate location address, and modify the transportation trip request by associating the inferred accurate location address with the target address.

First claim

What is claimed is:

1 . A method comprising:
receiving, by a processor, a transportation trip request from a user of a first computing device via a first graphical user interface displayed on the first computing device, the transportation trip request comprising a target address; retrieving, by the processor, service provider location estimates that are based on location data received from a plurality of service provider devices, and requester location estimates that are based on location data received from a plurality of requester devices; generating clustered location data using the service provider location estimates and the requester location estimates, wherein the clustered location data is generated using a density-based clustering algorithm; selecting, from the clustered location data, multiple clusters above a threshold cluster size that are located within a threshold distance of the target address, the threshold distance based on urban density data associated with the target address, wherein the urban density data is determined using a machine learning model that is trained to analyze location data associated with the target address and generates the threshold distance based on the analysis; determining an inferred accurate location address based on a centroid of locations represented by the selected multiple clusters; modifying the transportation trip request, in real-time as the transportation trip request is received to associate the inferred accurate location address with the target address, the modification comprising updating the first graphical user interface displayed on the first computing device with a selectable user interface element corresponding to the inferred accurate location; detecting selection, by the user of the first computing device, of the selectable user interface element corresponding to the inferred accurate location; and causing navigation instructions to the inferred accurate location to be displayed in a second graphical user interface displayed on a second computing device upon detecting the selection by the user, in the first graphical user interface displayed on the first computing device, of the selectable user interface element corresponding to the inferred accurate location.

2 . The method of claim 1 , wherein the plurality of service provider devices and the plurality of requester devices are computing devices.

3 . The method of claim 1 , further comprising:
causing display on the second graphical user interface of the second computing device of navigation instructions from the inferred accurate location to the target address.

4 . The method of claim 1 , wherein the inferred accurate location is an entrance location associated with the target address.

5 . The method of claim 4 , further comprising:
causing display of a map interface on the second computing device, the map interface comprising a first icon representing the target address and a second icon representing the inferred accurate location.

6 . The method of claim 1 , wherein the inferred accurate location is a parking location associated with the target address.

7 . The method of claim 1 , further comprising:
based on the transportation trip request, accessing historical location data corresponding to parking locations associated with the target address; and generating clustered location data using the service provider location estimates, the requester location estimates, and the historical location data.

8 . The method of claim 7 , wherein the historical location data is received from the plurality of service provider devices.

9 . The method of claim 1 , wherein the clustered location data is generated using a density-based clustering algorithm.

10 . The method of claim 1 , wherein the inferred accurate location address is a first inferred accurate location address, the method further comprising:
determining a second inferred accurate location address based on the selected multiple clusters; and modifying the transportation trip request, the modification comprising associating the first inferred accurate location address and the second inferred accurate location address with the target address.

11 . The method of claim 1 , wherein the service provider location estimates are for a range up to and including a time each trip begins for historical transportation services provided by each respective service provider of a plurality of service providers.

12 . The method of claim 1 , wherein the requester location estimates comprise a location of a requester device at a time a transportation trip was requested.

13 . The method of claim 1 , wherein the selectable user interface element is displayed in a drop-down list or carousel from which a user can select the selectable user interface element.

14 . A computing system comprising:
a processor; and a memory storing instructions that, when executed by the processor, configure the computing system to perform operations comprising: receiving, by the processor, a transportation trip request from a user of a first computing device via a first graphical user interface displayed on the first computing device, the transportation trip request comprising a target address; retrieving, by the processor, service provider location estimates that are based on location data received from a plurality of service provider devices, and requester location estimates that are based on location data received from a plurality of requester devices; generating clustered location data using the service provider location estimates and the requester location estimates, wherein the clustered location data is generated using a density-based clustering algorithm; selecting, from the clustered location data, multiple clusters above a threshold cluster size that are located within a threshold distance of the target address, the threshold distance based on urban density data associated with the target address, wherein the urban density data is determined using a machine learning model that is trained to analyze location data associated with the target address and generates the threshold distance based on the analysis; determining an inferred accurate location address based on a centroid of locations represented by the selected multiple clusters; modifying the transportation trip request, in real-time as the transportation trip request is received to associate the inferred accurate location address with the target address, the modification comprising updating the first graphical user interface displayed on the first computing device with a selectable user interface element corresponding to the inferred accurate location; detecting selection, by the user of the first computing device, of the selectable user interface element corresponding to the inferred accurate location; and causing navigation instructions to the inferred accurate location to be displayed in a second graphical user interface displayed on a second computing device upon detecting the selection by the user, in the first graphical user interface displayed on the first computing device, of the selectable user interface element corresponding to the inferred accurate location.

15 . The computing system of claim 14 , wherein the plurality of service provider devices and the plurality of requester devices are computing devices.

16 . The computing system of claim 14 , wherein the navigation instructions include instructions from a current location of the second computing device to the inferred accurate location.

17 . The computing system of claim 16 ,

Assignees

• Uber Technologies Inc

Inventors

• Takyar Mir Shahrouz
• Wang Andrew Yuh-Hsien
• Pakhomova Nina
• Li Xiaowei
• Parikh Akash
• Bidyuk Bozhena

Classifications

• G01C21/3617 Primary

  using user history, behaviour, conditions or preferences, e.g. predicted or inferred from previous use or current movement · CPC title

• G01C21/3476

  using point of interest [POI] information, e.g. a route passing visible POIs · CPC title

• G01C21/343

  Calculating itineraries (travelling salesman problem G06Q10/04; optimisation of routes G06Q10/047) · CPC title

• G01C21/3415 Primary

  Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents · CPC title

• G01C21/3685

  the POI's being parking facilities · CPC title