Venue based real time crowd modeling and forecasting

• US 9,449,121 B2
• Filed: 10/30/2012
• Issued: 09/20/2016
• Est. Priority Date: 10/30/2012
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Marti, Lukas M.
• Primary Examiner(s): Rivas, Omar Fernandez
• Assistant Examiner(s): Mapar, Bijan
• Application Number:
  US13/664,354
• Publication Number:
  US 20140122040A1
• Time in Patent Office: 1,421 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30

Abstract

Crowds of people within an environment can be modeled in real time. A multitude of mobile devices located within an environment can periodically transmit their geographical locations over networks to a remote server. The remote server can use these geographical locations to generate a current real-time model of a crowd of people who possess the mobile devices that transmitted the geographical locations. The remote server can transmit the model over networks back to the mobile devices. The mobile devices can use the received model to present useful information to the users of those mobile devices.

Claims

1. A method comprising:

sensing, using sensors of a particular mobile device, environmental data pertaining to an environment in which the particular mobile device is located;

sending the environmental data from the particular mobile device to a server that is separate from the particular mobile device;

obtaining, at the particular mobile device, an estimated wait time for the particular mobile device to traverse a line;

wherein the estimated wait time was determined by;

utilizing an estimate of a quantity of mobile devices of people currently ahead of the particular mobile device in the line, a history of model data that was generated over time, and the environmental data in order to predict a current wait time in the environment;

wherein the history provides;

amounts of time that one or more mobile devices other than the particular mobile device took to traverse the line; and

quantities of other mobile devices of people that were in the line when the one or more mobile devices entered the line; and

presenting the estimated wait time through a user interface of the particular mobile device.

2. The method of claim 1, wherein said sensing and said sending are performed no later than a first moment in time, wherein said model data is first model data, and further comprising:

sensing, at a second moment in time that is later than the first moment in time, using the sensors of the particular mobile device, second environmental data pertaining to the environment in which the particular mobile device is located, wherein the second environmental data includes at least one of a radio frequency (RF) fingerprint usable to estimate current geographical coordinates of the particular mobile device and the current geographical coordinates of the particular mobile device;

sending the second environmental data from the particular mobile device to the server;

receiving, at the mobile device, from the server, second model data indicating current characteristics of the environment, which second model data the server generated based at least in part upon (a) the second environmental data that the server received from the particular mobile device and (b) other environmental data that the server received from one or more other mobile devices after generating the first model data; and

presenting, through the user interface of the particular mobile device, information derived from the second model data.

3. The method of claim 1, wherein said sensing comprises the particular mobile device using a global positioning system of the mobile device to determine the current geographical coordinates of the mobile device automatically;

and wherein sending the environmental data comprises the particular mobile device sending the current geographical coordinates.

4. The method of claim 1, wherein the model data indicates one or more regions within the environment at which mobile device densities and movement speeds indicate the presence of movement bottlenecks within the environment.

5. The method of claim 1, wherein presenting information derived from the model data comprises presenting, for each particular line of two or more lines in the environment, an estimated amount of time that will be required to pass through that particular line.

18. The method of claim 1, wherein the history of model data is a history of wait times.

19. The method of claim 1, wherein the line is a security line at an airport, or a line to board a ski lift, or a queue at an amusement park ride.

20. The method of claim 1, wherein the particular mobile device generates the history of model data.

27. The method according to claim 1, wherein the environmental data includes current geographical coordinates of the particular mobile device, and

wherein the history further indicates geographical coordinates of the one or more mobile devices over time.

28. The method according to claim 1, wherein the estimate of the quantity of people currently ahead of the particular mobile device in the line is determined based on sensor data from mobile devices of the pedestrians currently ahead of the particular mobile device in the line.

6. A method comprising:

receiving, at a server, from two or more mobile devices, environmental data pertaining to an environment in which each of the two or more mobile devices is located, wherein each of the two or more mobile devices sensed the environmental data using sensors,

generating, based at least in part on the environmental data received from each of the two or more mobile devices, model data indicating current characteristics of the environment;

sending the model data to each of the two or more mobile devices, wherein the model data indicates characteristics of the environment in addition to characteristics indicated within environmental data received from any single one of the two or more mobile devices;

generating a history of the model data over time, wherein the history provides;

amounts of time that the two or more mobile devices took to traverse a line; and

quantities of mobile devices of people that were in the line when the two or more mobile devices entered the line;

utilizing the history, an estimate of a quantity of people currently ahead of a particular mobile device in the line, and the environmental data, to determine an estimated wait time for the particular mobile device to traverse the line in order to predict a current wait time in the environment; and

sending the estimated wait time to the particular mobile device.

7. The method of claim 6, wherein said environmental data is first environmental data, wherein said model data is first model data, wherein said receiving and said generating are performed no later than a first moment in time, and further comprising:

receiving, at the server, from the two or more mobile devices, second environmental data pertaining to the environment in which each of the two or more mobile devices is located, wherein each of the two or more mobile devices sensed the environmental data after the first moment in time, and wherein the second environmental data includes, for each of the two or more mobile devices, at least one of a radio frequency (RF) fingerprint usable to estimate current geographical coordinates and current geographical coordinates;

generating, based at least in part on the second environmental data received from each of the two or more mobile devices, second model data indicating current characteristics of the environment; and

sending the second model data to each of the two or more mobile devices.

8. The method of claim 6, wherein the environmental data includes first geographical coordinates that a first mobile device of the two or more mobile devices automatically determined using a global positioning system of the first mobile device;

wherein the environmental data includes second geographical coordinates that a second mobile device of the two or more mobile devices automatically determined using a global positioning system of the second mobile device; and

wherein the first geographical coordinates differ from the second geographical coordinates.

9. The method of claim 6, wherein generating the model data further comprises:

determining one or more potential bottleneck regions within the environment at which at least a specified quantity of mobile devices occur with at least a specified density; and

determining one or more bottleneck regions within the environment at which an average rate of movement of mobile devices through the potential bottleneck regions is less than a specified speed.

10. The method of claim 6, wherein the model data indicates, for each particular line of two or more lines in the environment, an estimated amount of time that will be required to pass through that particular line.

21. The method of claim 6, wherein sending the model data to each of the two or more mobile devices comprises sending, to each of the two or more mobile devices, information indicating locations at which mobile device users are clustered.

22. The method of claim 6, wherein sending the model data to each of the two or more mobile devices comprises sending, to each of the two or more mobile devices, information indicating locations of bottlenecks within the environment.

23. The method of claim 6, wherein sending the model data to each of the two or more mobile devices comprises sending one or more estimated wait times to each of the two or more mobile devices.

24. The method of claim 6, wherein generating the history of the model data over time comprises generating the history of the model data at a first moment in time and generating the history of the model data at a second moment in time subsequent to the first moment in time.

25. The method of claim 6, wherein determining the estimated wait time for the particular mobile device to traverse the line comprises determining rates of movement and directions of movement of mobile device users within a cluster of mobile device users.

26. The method of claim 6, wherein determining the estimated wait time for the particular mobile device to traverse the line comprises determining an average speed of mobile device users within a region and a density of the mobile device users within the region.

11. A computer-readable memory storing instructions which, when executed by one or more processors, cause the one or more processors to perform, at a server:

generating a history of a model over time of a particular environment based on data received over a network from a plurality of mobile devices located within the particular environment over time;

determining, based on the model, a plurality of queues that currently exist within the particular environment;

wherein the history provides;

amounts of time that mobile devices in the plurality of mobile devices took to traverse queues of the plurality of queues; and

quantities of other mobile devices of people that were in queues of the plurality of queues when each mobile device entered the queues of the plurality of queues;

determining, by utilizing the history, an estimate of a quantity of people currently in each queue of the plurality of queues, and the environmental data a wait time for each queue of the plurality of queues in order to predict a current wait time in the environment; and

sending, over the network, to one or more mobile devices of the plurality of mobile devices, information indicating a wait time for a particular queue of the plurality of queues.

12. The computer-readable memory of claim 11, wherein the instructions, when executed by the one or more processors, cause the one or more processors to perform:

determining that movements of the plurality of mobile devices within the environment are correlated with each other to an extent that exceeds a specified threshold; and

based at least in part on a determination that the movements of the plurality of mobile devices within the environment are correlated with each other to an extent that exceeds the specified threshold, determining that a queue exists at a location in which the correlated movements of the plurality of mobile devices occurred.

13. The computer-readable memory of claim 11, wherein the instructions, when executed by the one or more processors, cause the one or more processors to perform:

determining an amount of time taken for a particular mobile device to move from a first location to a second location;

based at least in part on the amount of time taken for the particular mobile device to move from the first location to the second location, estimating a predicted amount of time that will be required for a person to move through a particular queue that includes the first location and the second location; and

reporting the predicted amount of time to one or more mobile devices.

14. The computer-readable memory of claim 11, wherein the instructions, when executed by the one or more processors, cause the one or more processors to perform:

based at least in part on the wait times determined for each queue of the plurality of queues, determining a location at which an advertisement will be presented.

15. The computer-readable memory of claim 11, wherein the instructions, when executed by the one or more processors, cause the one or more processors to perform:

based at least in part on wait times determined for each queue of the plurality of queues over an interval of time, estimating a future wait time for each queue of the plurality of queues at a specified future time.

16. A computer-readable memory storing instructions which, when executed by one or more processors, cause the one or more processors to perform:

receiving, at a server, from each particular mobile device of a plurality of mobile devices, information that indicates a current location, a current direction, and a current speed of that particular mobile device;

aggregating, at the server, over time, the information received from each particular mobile device in order to generate a history of crowd movement behaviors;

receiving, at the server, from a particular mobile device, a planned route that a user of the particular mobile device plans to travel;

determining, by utilizing the history, for each particular area of a plurality of areas through which the planned route passes, a quantity of time historically taken by other mobile device users to traverse that particular area while that particular area contained a specified quantity of other people;

utilizing the quantity of time determined for each area and a quantity of other people currently on the planned route to calculate a total amount of time estimated to be required for the user of the particular mobile device to travel the planned route; and

transmitting, from the server to the particular mobile device, data including the total amount of time.

17. The computer-readable memory of claim 16, wherein aggregating the information received from the mobile devices includes decreasing an influence of particular information received from mobile devices upon aggregated information based at least in part on an age of that particular information.