PERSONALIZED RIDE EXPERIENCE BASED ON REAL-TIME SIGNALS

• US 20190197430A1
• Filed: 12/21/2017
• Published: 06/27/2019
• Est. Priority Date: 12/21/2017
• Status: Active Application

• Current Assignee: LYFT Incorporated
• Original Assignee: LYFT Incorporated
• Inventors: Arditi, Gil
• Application Number:
  US15/851,078
• Publication Number:
  US 20190197430A1
• Time in Patent Office: Days
• CPC Class Codes: G01C 21/3438 Rendez-vous, i.e. searching a destination where several users can meet, and the routes to this destination for these users; Ride sharing, i.e. searching a route such that at least two users can share a vehicle for at least part of the route
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 5/01 Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

In particular embodiments, a computing system may, in response to a ride request, match a ride requestor with a vehicle. The system may receive data associated with sensory output from sensors associated with the vehicle. The sensory output may be associated with at least the ride requestor while the requestor is at least partially within a passenger compartment of the vehicle. The system may extract features from the received data according to a machine-learning model, which may be trained using a set of training data, each of which may be associated with sensory output relating to one or more predetermined event types. The system may generate, using the machine-learning model and the extracted features, a score representing a likelihood that the received data is indicative of one of the predetermined event types. An alert may be generated based a determination that the score satisfies a predetermined criterion.

Claims

1. A method comprising, by a computing system:

receiving data associated with sensory output from one or more sensors associated with a vehicle, the sensory output being associated with at least a ride requestor while the ride requestor is at least partially within a passenger compartment of the vehicle, wherein the vehicle is matched with the ride requestor for transporting the ride requestor to a request location;

extracting features from the received data according to a machine-learning model, wherein the machine-learning model is trained using a set of training data, wherein each training data in the set of training data is associated with sensory output relating to one or more predetermined event types;

generating, using the machine-learning model and the features extracted from the received data, a score representing a likelihood that the received data is indicative of a first event type selected from the one or more predetermined event types; and

generating an alert based a determination that the score satisfies a predetermined criterion.

2. The method of claim 1, further comprising:

determining that the ride requestor consents to the one or more sensors in the vehicle being activated while the ride requestor is in the vehicle;

transmitting an instruction configured to cause the one or more sensors in the vehicle to be activated.

3. The method of claim 2, further comprising:

determining that a ride provider associated with the vehicle consents to the one or more sensors in the vehicle being activated while the ride requestor is in the vehicle.

4. The method of claim 1, wherein the sensory output associated with a first training data in the set of training data is from one or more first sensors in a first vehicle different from the vehicle associated with the received data.

5. The method of claim 1, wherein the one or more sensors in the vehicle comprises a first sensor that is (1) integrated with a device placed on a dashboard of the vehicle and (2) configured to capture at least one of audio or video.

6. The method of claim 5, wherein the device is configured to enable or disable the first sensor from recording audio or video based on a preference indicator associated with the ride requestor.

7. The method of claim 1, further comprising:

determining that the first event type is associated with at least one of a confrontation event or a health event;

identifying, based on the first event type, a third-party computing system associated with the first event type; and

sending the alert to the third-party computing system.

8. The method of claim 1, further comprising:

determining that the first event type is associated with at least one of a confrontation event or a health event;

determining, based on the first event type, an alternate destination different from a destination specified by the ride request; and

instructing the vehicle to travel to the alternate destination.

9. The method of claim 1,

wherein the machine-learning model is further trained using a set of user profile information associated with the set of training data;

wherein the score is further generated using profile information associated with the ride requestor, a ride provider associated with the vehicle, or both the ride requestor and the ride provider.

10. The method of claim 1, further comprising:

receiving a first location associated with the device associated with the ride requestor;

receiving a second location associated with the vehicle;

determining that a proximity between the first location and the second location is within a predetermined threshold; and

transmitting an instruction configured to cause the one or more sensors in the vehicle to be activated.

11. The method of claim 1, wherein the computing system is associated with a transportation management system, the method further comprising:

receiving a ride request from a device associated with the ride requestor; and

matching, in response to the ride request, the ride requestor with the vehicle for transporting the ride requestor.

12. The method of claim 1, wherein the computing system is integrated with the vehicle, the method further comprising:

receiving the machine-learning model from a remote system.

13. A computing system comprising:

one or more processors and one or more computer-readable non-transitory storage media coupled to one or more of the processors, the one or more computer-readable non-transitory storage media comprising instructions operable when executed by one or more of the processors to cause the computing system to perform operations comprising;

receiving data associated with sensory output from one or more sensors associated with a vehicle, the sensory output being associated with at least a ride requestor while the ride requestor is at least partially within a passenger compartment of the vehicle, wherein the vehicle is matched with the ride requestor for transporting the ride requestor to a request location;

extracting features from the received data according to a machine-learning model, wherein the machine-learning model is trained using a set of training data, wherein each training data in the set of training data is associated with sensory output relating to one or more predetermined event types;

generating, using the machine-learning model and the features extracted from the received data, a score representing a likelihood that the received data is indicative of a first event type selected from the one or more predetermined event types; and

generating an alert based a determination that the score satisfies a predetermined criterion.

14. The computing system of claim 13, wherein the processors are further operable when executing the instructions to perform operations comprising:

determining that the ride requestor consents to the one or more sensors in the vehicle being activated while the ride requestor is in the vehicle;

transmitting an instruction configured to cause the one or more sensors in the vehicle to be activated.

15. The computing system of claim 13, wherein the processors are further operable when executing the instructions to perform operations comprising:

determining that the first event type is associated with at least one of a confrontation event or a health event;

identifying, based on the first event type, a third-party computing system associated with the first event type; and

sending the alert to the third-party computing system.

16. The computing system of claim 13, wherein the processors are further operable when executing the instructions to perform operations comprising:

determining that the first event type is associated with at least one of a confrontation event or a health event;

determining, based on the first event type, an alternate destination different from a destination specified by the ride request; and

instructing the vehicle to travel to the alternate destination.

17. One or more computer-readable non-transitory storage media embodying software that is operable when executed to cause one or more processors to perform operations comprising:

receiving data associated with sensory output from one or more sensors associated with a vehicle, the sensory output being associated with at least a ride requestor while the ride requestor is at least partially within a passenger compartment of the vehicle, wherein the vehicle is matched with the ride requestor for transporting the ride requestor to a request location;

extracting features from the received data according to a machine-learning model, wherein the machine-learning model is trained using a set of training data, wherein each training data in the set of training data is associated with sensory output relating to one or more predetermined event types;

generating, using the machine-learning model and the features extracted from the received data, a score representing a likelihood that the received data is indicative of a first event type selected from the one or more predetermined event types; and

generating an alert based a determination that the score satisfies a predetermined criterion.

18. The media of claim 17, wherein the software is further operable when executed to cause the one or more processors to perform operations comprising:

determining that the ride requestor consents to the one or more sensors in the vehicle being activated while the ride requestor is in the vehicle;

transmitting an instruction configured to cause the one or more sensors in the vehicle to be activated.

19. The media of claim 17, wherein the software is further operable when executed to cause the one or more processors to perform operations comprising:

determining that the first event type is associated with at least one of a confrontation event or a health event;

identifying, based on the first event type, a third-party computing system associated with the first event type; and

sending the alert to the third-party computing system.

20. The media of claim 17, wherein the software is further operable when executed to cause the one or more processors to perform operations comprising:

determining that the first event type is associated with at least one of a confrontation event or a health event;

determining, based on the first event type, an alternate destination different from a destination specified by the ride request; and

instructing the vehicle to travel to the alternate destination.