Optimizing and predicting availability of resources in a shared vehicle environment

Patent metadata

Field	Value
Publication number	US-12236359-B2
Application number	US-201816980923-A
Country	US
Kind code	B2
Filing date	Mar 16, 2018
Priority date	Mar 16, 2018
Publication date	Feb 25, 2025
Grant date	Feb 25, 2025

Abstract

An intelligent bicycle sharing system, or other vehicle sharing system, is able to provide helpful bicycle availability predictions based on historical data, including various utilization statistics. Historical data can be collected over time as users use the bicycle sharing system. For example, the historical data may include the number of available bicycles at various locations and times, as well as contextual data associated with the locations and times. Contextual data may include data regarding the weather, local events, season, day of the week or year, news events, among other environmental factors that may or may not influence bicycle utilization. In some embodiments, a model, such as a machine learning model (e.g., neural network) may be trained using the historical data as training data such that the model can predict bicycle availability for a certain future time and location.

First claim

What is claimed is:

1. A system, comprising:
at least one computing device processor; and
a memory device including instructions that, when executed by the at least one computing device processor, cause the system to:
obtain historical data collected from a vehicle sharing system, the vehicle sharing system comprising a plurality of vehicles comprising a first vehicle and a second vehicle, and the historical data including information for vehicle availability at respective times and locations;
receive, from a user device, a query for vehicle availability information, the query including a time and a first location associated with vehicle pickup;
determine, using the time and first location, vehicle availability information at the first location;
provide the the vehicle availability information to the user device;
determine that a user of the user device has retrieved the first vehicle from the first location based on the vehicle availability information; and
as the first user is enroute to the first location to return the first vehicle;
determine that there are no docking spots available at the first location;
determine that a second user is scheduled to pick up the second vehicle from a second location,
generate an updated docking spot availability information based at least in part on the second user picking up the second vehicle, the updated docking spot availability information indicating an availability of a docking spot at the second location; and
provide the updated docking spot availability information to the user device.

2. The system of claim 1 , wherein the instructions when executed further cause the system to:
obtain contextual data associated with the time and first location, the contextual data including one or more of weather information, event information, seasonal information, day of the week information, day of the year information, holiday information, and news information, wherein the historical data includes contextual data associated with the respective times and locations; and
determine the vehicle availability information based at least in part on the contextual data associated with the time and the first location.

3. The system of claim 1 , wherein the vehicle sharing system includes a a plurality of docking stations comprising the docking spot, wherein the first location is associated with at least one of the plurality of docking stations other than the docking spot.

4. The system of claim 1 , wherein the first and second vehicles are located and movable through a plurality of geographic regions, wherein the first location is associated with at least one of the plurality of geographic regions.

5. A computer-implemented method, comprising:
receiving a query for vehicle availability prediction associated with a vehicle sharing system, the vehicle sharing system comprising a first vehicle and a second vehicle, the query including a time value and a first location;
determining the vehicle availability information based at least in part on the time value and the first location;
providing the vehicle availability information to a user device of the first user;
determining that the first user has picked up the first vehicle form the first location; and
as the first user is enroute to the first location to return the first vehicle;
determining that there are no docking spots available at the first location to dock the first vehicle;
determining that a second user is schedule to pick up the second vehicle from a second dock at a second location different from the first location;
determining an updated docking spot availability information based at least in part on the second user picking up the second vehicle;
providing the updated docking spot availability information to the user device causing the first user to go to the second location to park the first vehicle.

6. The computer-implemented method of claim 5 , wherein the historical data includes contextual data associated with the respective times and locations, the method further comprising:
obtaining contextual data associated with the time value and the first location; and
determining the vehicle availability based at least in part on the contextual data associated with the time value and the first location.

7. The computer-implemented method of claim 6 , wherein the contextual data includes at least one of weather information, event information, seasonal information, day of the week information, day of the year information, holiday information, and news information.

8. The computer-implemented method of claim 5 , wherein the first and second vehicles each have either an available state at a given time, and wherein the vehicle availability information includes a prediction of vehicle availability at the time value and the first location.

9. The computer-implemented method of claim 5 , wherein the vehicle availability information includes an estimated number of vehicles available at a time indicated by the time value and the location.

10. The computer-implemented method of claim 5 , further comprising:
determining a recommendation for the user based on the vehicle availability information, the recommendation including one of an alternate location or an alternate time that is associated with a higher vehicle availability.

11. The computer-implemented method of claim 5 , further comprising:
receiving a plurality of queries from a plurality of devices for vehicle availability predictions for a same time as a time indicated by the time value and the first location;
determining a measure of present demand based at least in part on the plurality of queries; and
determining the vehicle availability information based at least in part on the measure of present demand.

12. The computer-implemented method of claim 5 , further comprising:
determining a location of the user device;
determining a travel time from the location to the first location; and
determining the vehicle availability information based at least in part on the travel time.

Assignees

• Ford Motor Co
• Ford Global Tech Llc

Inventors

• Seagraves Jamel
• Tang Chih-Wei
• Aich Sudipto
• Kock Beaudry

Classifications

• G06Q50/40 Primary

  Business processes related to the transportation industry (shipping G06Q10/083) · CPC title

• G06Q2240/00

  Transportation facility access, e.g. fares, tolls or parking · CPC title

• G06Q30/0645

  Rental transactions; Leasing transactions · CPC title

• G06Q10/06315

  Needs-based resource requirements planning or analysis · CPC title

• G01S19/01

  Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO · CPC title