Systems and methods for personalized ground transportation processing and user intent predictions
The present disclosure provides methods and systems for predicting a trip intent or destination while a user is traveling along a route. The method may comprise: (a) receiving a starting geographic location of the route and data about an identity of the user; (b) retrieving a trained classifier based at least in part on the data about the identity of the user; (c) using the trained classifier to predict the trip intent or destination based on the starting geographic location; and (d) while the user is traveling in a terrestrial vehicle along at least a portion of said route, presenting one or more transactional options to the user on an electronic device, wherein the one or more transactional options are identified based on the trip intent or destination predicted in (c).
1. A method for predicting a trip intent of a user trip taken by a user to determine information to provide to the user during the user trip, comprising:
(a) receiving a starting geographic location of a travel route and data about an identity of the user;
(b) training a trip abstractor by:
(1) obtaining a training plurality of prior trip records, wherein a prior trip record of the training plurality of prior trip records comprises a trip intent and trip characteristics of a prior trip for which an intent was determined;
(2) generating a plurality of models, wherein for at least two models of the plurality of models, each of the at least two models has an associated trip intent different from the trip intent associated with the other of the at least two models and each of the at least two models comprises a trip classifier that is trained on a subset of the training plurality of prior trip records that are prior trip records having a trip intent that matches the associated trip intent; and
(3) storing the plurality of models into a trip classifier database;
(c) identifying, using a trip identification engine, a trip dataset from location data collected from the user trip, wherein the location data provides geospatial points visited by the user during the user trip, with at least some visited points provided to the trip identification engine in real-time;
(d) applying the trip dataset and the trip classifier database to an intent predictor, to determine a determined trip intent of the user trip, wherein the intent predictor uses at least the at least two models of the plurality of models for determining the determined trip intent of the user trip; and
(e) presenting, to the user, on an electronic device, while the user is traveling in a vehicle along at least a portion of the travel route, one or more transactional options identified based, at least in part, on the determined trip intent of the user trip.
2. The method of claim 1 , wherein said starting geographic location is received in a form of Global Positioning System (GPS) data.
3. The method of claim 1 , wherein said starting geographic location is entered by said user via a graphical user interface (GUI) on said electronic device, or is determined using in part a geographic location of said electronic device, which geographic location is determined by a global position system or signal triangulation.
4. The method of claim 1 , wherein the training plurality of prior trip records comprises uncorrelated GPS data.
5. The method of claim 4 , wherein the training plurality of prior trip records comprises labeled data obtained using clustering analysis of a plurality of trip data records, wherein the clustering analysis automatically identifies subsets of trips with common characteristics.
6. The method of claim 5 , further comprising generating said plurality of trip data records by associating the uncorrelated GPS data with one or more person identities.
7. The method of claim 5 , wherein said plurality of trip data records are augmented by a social graph, transportation data, or purchase data of the corresponding person identity.
8. The method of claim 1 , wherein training the trip abstractor comprises creating labels for a segment of trip based on one or more labeling rules.
9. The method of claim 1 , further comprising predicting a transportation mode for one or more portions of said travel route.
10. The method of claim 9 , wherein said transportation mode comprises autonomous vehicle, ride-hailing service, rail transportation, and/or terrestrial mass transit vehicle.
11. The method of claim 1 , further comprising updating said trip intent or destination upon receiving new location data during the user trip.
12. A system for predicting a trip intent of a user trip taken by a user to determine information to provide to the user during the user trip, comprising:
a trip abstractor, trained by (1) obtaining a training plurality of prior trip records, wherein a trip record of the training plurality of prior trip records comprises a trip intent and trip characteristics of a prior trip for which an intent was determined, and (2) generating a plurality of models, wherein for at least two models of the plurality of models, each of the at least two models has an associated trip intent different from the trip intent associated with the other of the at least two models and each of the at least two models comprises a trip classifier that is trained on a subset of the training plurality of prior trip records that are prior trip records having a trip intent that matches the associated trip intent;
a trip classifier database for storing the plurality of models generated by the trip abstractor;
a trip identification engine for identifying a trip dataset from location data collected from the user trip, wherein the location data includes a travel route represented by geospatial points visited by the user during the user trip, with at least some visited points provided to the trip identification engine in real-time;
an intent predictor coupled to the trip identification engine and the trip classifier database, for determining a determined trip intent of the user trip, while the user is traveling in a vehicle along at least a portion of the travel route, based at least on (1) a matching model of the plurality of models that is matching in that it has a trip intent that matches the determined trip intent of the user trip, (2) a starting geographic location of the travel route, and (3) data about an identity of the user; and
a user interface of an electronic device adapted to present one or more transactional options identified based at least in part on the determined trip intent of the user trip, to be presented while the user is traveling in along the travel route.
13. The system of claim 12 , wherein said starting geographic location is received in a form of Global Positioning System (GPS) data.
14. The system of claim 12 , wherein said starting geographic location is entered by said user via a graphical user interface (GUI) on said electronic device, or is determined using in part a geographic location of said electronic device, which geographic location is determined by a global position system or signal triangulation.
15. The system of claim 12 , wherein the training plurality of prior trip records comprises uncorrelated GPS data.
16. The system of claim 15 , wherein the training plurality of prior trip records comprises labeled data obtained using clustering analysis of a plurality of trip data records.
17. The system of claim 16 , wherein the plurality of trip data records associate the uncorrelated GPS data with one or more person identities.
18. The system of claim 16 , wherein said plurality of trip data records are augmented by a social graph, transportation data, or purchase data of the corresponding person identity.
19. The system of claim 12 , wherein the intent predictor is further configured to predict a transportation mode for one or more portions of the travel route.
20. The system of claim 19 , wherein said transportation mode comprises autonomous vehicle, ride-hailing service, rail transportation, and/or terrestrial mass transit vehicle.