Approaches to crowdsourced-based wait time estimates

Patent metadata

Field	Value
Publication number	US-2016363450-A1
Application number	US-201514737399-A
Country	US
Kind code	A1
Filing date	Jun 11, 2015
Priority date	Jun 11, 2015
Publication date	Dec 15, 2016
Grant date	—

Abstract

In one embodiment of the present invention, a wait time client enables prediction of wait times (e.g., time required to checkout at a grocery store) based on crowdsourced wait data. In operation, the wait time application downloads predicted wait data from a server. The predicted wait data reflects measured wait times for one or more location, such as the ticket line at a movie theater. The wait time client then selects a wait time data point that corresponds to a location of a point-of-interest. Based on the selected wait time data point, the wait time client determines a predicted wait time at the point-of-interest. Advantageously, by leveraging crowdsourced, deterministically measured wait times, the wait time clients enables the incorporation of realistic and up-to-date predicted wait times into the trip planning process.

First claim

1 . A computer-implemented method for predicting wait times at points-of-interest, the method comprising:
receiving a plurality of data points from a server machine, wherein each data point reflects at least one crowdsourced measured wait time and is associated with any one of several different points-of interest, and wherein at least one of the data points is determined based on a duration of time for which a path of a mobile device satisfies one or more queue pattern constraints; receiving a request to predict a wait time at a first point-of-interest that is included in the several different points-of-interest; selecting a first data point included in the plurality of data points based on the first point-of-interest; and determining a predicted wait time based on the first data point.

2 . The method of claim 1 , wherein selecting the first data point comprises:
identifying a subset of data points that are included in the plurality of data points and are associated with the first point-of-interest; and selecting a data point included in the subset of data points that is associated with a start time that lies within a specified range of times.

3 . The method of claim 1 , further comprising, prior to receiving the plurality of data points from the server machine:
determining that a location of the mobile device is associated with the first point-of-interest; calculating a first wait time based on a start time and an end time, wherein both the start time and the end time are associated with the mobile device; and causing the server machine to generate the first data point based on the start time, the first wait time, and the location of the mobile device.

4 . The method of claim 3 , wherein determining at least one of the start time and the end time comprises receiving a message, and analyzing the message to determine a transaction time associated with the first point-of-interest.

5 . The method of claim 4 , wherein the message is received from a proximity beacon.

6 . The method of claim 4 , wherein determining the end time comprises receiving a message that corresponds to a financial transaction, and analyzing the message to determine a timestamp associated with the message.

7 . The method of claim 4 , wherein determining the start time comprises:
storing sensor data indicating that the mobile device has moved; performing one or more backtracking operations on the sensor data to determine the path from the transaction time to a previous time specified in the sensor data, wherein the mobile device moving between the transaction time and the previous time satisfies the one or more queue pattern constraints; and setting the start time to the previous time.

8 . The method of claim 1 , further comprising performing one or more search operations based on a location of a mobile device to identify the first point-of-interest.

9 . The method of claim 1 , wherein determining the predicted wait time comprises:
performing one or more read operations on the first data point to determine a first predicted wait time, a first measurement time, a second predicted wait time, and a second measurement time; determining a start time based on the request; computing a first difference between the start time and the first measurement time, and a second difference between the start time and the second measurement time; and if the first difference is less than the second difference, then setting the predicted wait time to the first predicted wait time; and if the first difference is not less than the second difference, then setting the predicted wait time to the second predicted wait time.

10 . A non-transitory computer-readable storage medium including instructions that, when executed by a processor, cause the processor to predict wait times at points-of-interest, the method comprising:
downloading a plurality of data points from a server machine, wherein each data point reflects at least one crowdsourced measured wait time and is associated with any one of several different points-of interest, and wherein at least one of the data points is determined based on a duration of time for which a path of a mobile device satisfies one or more queue pattern constraints; receiving a request to predict a wait time at a first point-of-interest that is included in the several different points-of-interest; selecting a first data point included in the plurality of data points based on the first point-of-interest; and determining a predicted wait time based on the first data point.

11 . The non-transitory computer-readable storage medium of claim 10 , wherein determining the predicted wait time comprises identifying a first predicted wait time included in the first data point based on an end time that is specified in the request.

12 . The non-transitory computer-readable storage medium of claim 10 , further comprising, prior to downloading the plurality of data points from the server machine:
determining that a location of the mobile device is associated with the first point-of-interest; calculating a first wait time based on a start time and an end time, wherein both the start time and the end time are associated with the mobile device; and causing the server machine to generate the first data point based on the start time, the first wait time, and the location of the mobile device.

13 . The non-transitory computer-readable storage medium of claim 12 , wherein determining the start time comprises;
storing sensor data indicating that the mobile device has moved; receiving a message, and analyzing the message to determine a transaction time associated with the first point-of-interest; performing one or more backtracking operations on the sensor data to determine the path from the transaction time to a previous time specified in the sensor data, wherein the mobile device moving between the transaction time and the previous time satisfies one or more queue pattern constraints; and setting the start time to the previous time.

14 . The non-transitory computer-readable storage medium of claim 13 , wherein the one or more queue pattern constraints include at least one of a maximum change in direction and a maximum change in velocity.

15 . The non-transitory computer-readable storage medium of claim 13 , wherein at least one of the one or more backtracking operations comprises a step-detection operation.

16 . The non-transitory computer-readable storage medium of claim 13 , wherein at least one of the one or more backtracking operations comprises a turn-detection operation.

17 . The non-transitory computer-readable storage medium of claim 10 , further comprising estimating a travel time to the first point-of-interest and calculating a total time based on the predicted wait time and the travel time.

18 . The non-transitory computer-readable storage medium of claim 10 , wherein determining the predicted wait time comprises:
performing one or more read operations on the first data point to determine a first predicted wait time, a first measurement time, a second predicted wait time, and a second measurement time; determining an end time based on the request; computing a first difference between the end time and the first measurement time, and a second difference between the end time and the second measurement time; and if the first difference is less than the second difference, then setting the predicted wait time to the first predicted wait time; and if the first difference is not less than the second difference, then setting the predicted wait

Assignees

• Harman Int Ind

Inventors

• Sahay Pratyush
• Biswal Rajesh

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06Q10/04 Primary

  Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202) · CPC title

• G01C21/1654

  with electromagnetic compass · CPC title

• G01C22/006

  Pedometers · CPC title

• G01C21/26

  specially adapted for navigation in a road network · CPC title