Geohash-related location predictions

Patent metadata

Field	Value
Publication number	US-10820148-B2
Application number	US-202016859797-A
Country	US
Kind code	B2
Filing date	Apr 27, 2020
Priority date	Apr 4, 2017
Publication date	Oct 27, 2020
Grant date	Oct 27, 2020

Abstract

Embodiments provide techniques, including systems and methods, for determining an estimated target pickup location for a corresponding transport request at a particular location, such as associated with a particular geohash. A requestor may send a request that is associated with a location that does not reflect the requestor's intent regarding where they would like to be met by the provider (i.e., “picked up”). GPS inaccuracies may cause the request location to inaccurately indicate where the requestor will be; for example, the request location may be inside a building while the requestor is waiting on a curb around a far side of the building. The target pickup location allows for a requestor and a provider to meet more efficiently, reducing delay for the provider and improving the efficiency of the system by preventing provider system resources from being taken from other service areas and decreasing provider downtime upon matching.

First claim

What is claimed is:

1. A method of managing transportation services comprising:
receiving, by a dynamic transportation matching system from a requestor device, a transportation request indicating a pickup location;
determining a pickup action to be performed for the transportation request;
identifying, within a geographical area corresponding to the pickup location, a plurality of instances of prior transport data comprising a threshold number of instances of a prior pickup data and one or more instances of prior drop-off data, wherein the prior pickup data corresponds to the pickup action;
generating a boundary for a sub-cluster comprising the plurality of instances of prior transport data;
utilizing the sub-cluster of the prior transport data to identify a suggested location for the pickup action to be performed for the transportation request, wherein the suggested location is within the boundary; and
providing the suggested location to the requestor device.

2. The method of claim 1 , wherein utilizing the sub-cluster of the prior transport data to identify the suggested location comprises determining a weighted average location of the plurality of instances of prior transport data.

3. The method of claim 1 , further comprising:
determining a drop-off action to be performed for a second transportation request at a drop-off location;
identifying a second plurality of instances of prior transport data within a geographical area corresponding to the drop-off location, wherein the second plurality of instances of prior transport data does not include at least a threshold number of instances of prior drop-off data corresponding to the drop-off action; and
disregarding the second plurality of instances of prior transport data based on the second plurality of instances of prior transport data not including at least the threshold number of instances of prior drop-off data corresponding to the drop-off action.

4. The method of claim 1 , further comprising:
determining that the prior pickup data corresponds to the pickup action; and
wherein utilizing the sub-cluster of the prior transport data to identify a suggested location for the pickup action comprises weighting the threshold number of instances of the prior pickup data more heavily than the one or more instances of the prior drop-off data.

5. The method of claim 1 , further comprising:
determining that the pickup location indicated by the transportation request is at a location where the pickup action cannot be performed; and
determining, by analyzing the sub-cluster of the prior transport data, a requestor intent based on the pickup location being at a location where the pickup action cannot be performed.

6. The method of claim 5 , wherein utilizing the sub-cluster of the prior transport data to identify a suggested location for the pickup action comprises identifying a location where the pickup action can be performed for the transportation request based on the requestor intent.

7. The method of claim 1 , wherein utilizing the sub-cluster of the prior transport data to identify a suggested location for the pickup action comprises:
identifying, for the plurality of instances of prior transport data, prior actual pickup locations of pickup actions;
determining relationships between the prior actual pickup locations and corresponding request locations of the plurality of instances of prior transport data; and
determining a suggested location for the pickup action to be performed for the transportation request based on the determined relationships.

8. A non-transitory computer readable medium comprising instructions that, when executed by at least one processor, cause a computing device to:
receive, by a dynamic transportation matching system from a requestor device, a transportation request indicating a pickup location;
determine a pickup action to be performed for the transportation request;
identify, within a geographical area corresponding to the pickup location, a plurality of instances of prior transport data comprising a threshold number of instances of a prior pickup data and one or more instances of prior drop-off data, wherein the prior pickup data corresponds to the pickup action;
generate a boundary for a sub-cluster comprising the plurality of instances of prior transport data;
utilize the sub-cluster of the prior transport data to identify a suggested location for the pickup action to be performed for the transportation request, wherein the suggested location is within the boundary; and
provide the suggested location to the requestor device.

9. The non-transitory computer readable medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computing device to utilize the sub-cluster of the prior transport data to identify the suggested location by determining a weighted average location of the plurality of instances of prior transport data.

10. The non-transitory computer readable medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computing device to:
determine a drop-off action to be performed for a second transportation request at a drop-off location;
identify a second plurality of instances of prior transport data within a geographical area corresponding to the drop-off location, wherein the second plurality of instances of prior transport data does not include at least a threshold number of instances of prior drop-off data corresponding to the drop-off action; and
disregard the second plurality of instances of prior transport data based on the second plurality of instances of prior transport data not including at least the threshold number of instances of prior drop-off data corresponding to the drop-off action.

11. The non-transitory computer readable medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computing device to:
determine that the prior pickup data corresponds to the pickup action; and
utilize the sub-cluster of the prior transport data to identify a suggested location for the pickup action by weighting the threshold number of instances of the prior pickup data more heavily than the one or more instances of the prior drop-off data.

12. The non-transitory computer readable medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computing device to:
determine that the pickup location indicated by the transportation request is at a location where the pickup action cannot be performed; and
determine, by analyzing the sub-cluster of the prior transport data, a requestor intent based on the pickup location being at a location where the pickup action cannot be performed.

13. The non-transitory computer readable medium of claim 12 , further comprising instructions that, when executed by the at least one processor, cause the computing device to utilize the sub-cluster of the prior transport data to identify a suggested location for the pickup action by identifying a location where the pickup action can be performed for the transportation request based on the requestor intent.

14. The non-transitory computer readable medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computing device to utilize the sub-cluster of the prior transport data to identify a suggested location for the pickup action by:
identifying, for the plurality of instances of prior transport data, prior actual pickup locations of pickup actions;
determining relationships between

Assignees

• Lyft Inc

Inventors

• Pao Yuanyuan
• Kodesh Snir
• Chopra Jatin
• Fan Kevin
• Lin Charlie
• Shen Limin
• Levi Dor
• Haque Asif
• Baz Zeynep Erkin

Classifications

• H04W4/44

  for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H] · CPC title

• H04W4/023 Primary

  using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds · CPC title

• H04W4/021

  Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences · CPC title

• H04W4/029

  Location-based management or tracking services · CPC title

• H04W4/024

  Guidance services · CPC title