SYSTEM AND METHOD FOR MULTI-FACTORED-BASED RANKING OF TRIPS

• US 20170053209A1
• Filed: 08/20/2015
• Published: 02/23/2017
• Est. Priority Date: 08/20/2015
• Status: Abandoned Application

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Cret, Eric, Lehoux, Vassilissa, Castellani, Stefania
• Application Number:
  US14/831,326
• Publication Number:
  US 20170053209A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G01C 21/20 Instruments for performing navigational calculations G01C21/24, G01C21/26 take precedence
• CPC Class Codes: G01C 21/3423 Multimodal routing, i.e. combining two or more modes of transportation, where the modes can be any of, e.g. driving, walking, cycling, public transport
• CPC Class Codes: G01C 21/343 Calculating itineraries, i.e. routes leading from a starting point to a series of categorical destinations using a global route restraint, round trips, touristic trips travelling salesman problem G06Q10/04; optimisation of routes G06Q10/047
• CPC Class Codes: G01C 21/3484 Personalized, e.g. from learned user behaviour or user-defined profiles
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: G06Q 10/02 Reservations, e.g. for tickets, services or events

Abstract

A trip-planning method and system employ a user profile for each user which includes the user'"'"'s preferences for each of a plurality of transportation modes, user goals, and optionally user constraints on trips. Inferred user preference (resp. goal) values and stated user preference (resp. goal) values are aggregated using a coefficient which places more emphasis on stated goals/preferences that have been recently set. Candidate itineraries for a requested user trip that meet the user'"'"'s constraints are ranked based on the aggregated goal and preference values and the costs/contributions of each itinerary to the respective goal/preference. A subset of the ranked itineraries may be output to the user for the user to select one for making the trip.

Claims

1. A method for assisting a user in planning a trip comprising:

receiving a request for a trip from a user;

accessing a user profile for the user, the user profile including user preferences for each of a plurality of transportation modes, user goals, and optionally user constraints on trips, the user preferences each including an inferred user preference value and, where stated, a stated user preference value; and

the user goals each including an inferred user goal value and, where stated, a stated user goal value;

building a set of candidate itineraries for the trip which meet the user'"'"'s constraints, the candidate itineraries each specifying a respective set of the plurality of transportation modes;

for each of the user preferences, aggregating the stated preference value, where stated, and the inferred preference value to generate a weight for the preference;

for each of the user goals, aggregating the stated goal value, where stated, and the inferred goal value to generate a weight for the goal;

for each of the candidate itineraries, computing a cost for each of the goals;

with a processor, for each of the candidate itineraries, ranking the itinerary based on the preference weights, goal weights, and the computed cost for each of the goals; and

outputting information on at least a subset of the ranked itineraries for enabling the user to select an itinerary for the trip.

2. The method of claim 1, wherein the ranking includes computing a utility function as an aggregation of a plurality of objective functions, the plurality of objective functions including:

a first objective function that is a function of, for each of the goals, the goal weight and the respective computed cost of the candidate itinerary, for that goal; and

a second objective function that is a function of, for each of the user preferences, the preference weight and the computed contribution of the respective mode of transportation to the candidate itinerary.

3. The method of claim 1, wherein contribution of the respective mode of transportation is computed as a function of at least one of duration and distance in the itinerary of that transportation mode.

4. The method of claim 1, wherein in the aggregating of the stated preference value and the inferred preference value to generate a weight for the preference, includes computing a coefficient for at least one of the stated preference value and the inferred preference value, the coefficient being a function of a duration since the preference was last stated.

5. The method of claim 1, wherein in the aggregating of the stated goal value and the inferred goal value to generate a weight for the goal, includes computing a coefficient for at least one of the stated goal value and the inferred goal value, the coefficient being a function of a duration since the goal was last stated.

6. The method of claim 1, wherein the computing a cost for each of the goals includes projecting a computed cost related to the goal onto a common range of values.

7. The method of claim 1, wherein the goals include goals selected from a fitness goal, a cost saving goal, a time saving goal, and an environmental impact goal.

8. The method of claim 1, wherein the cost for each goal is computed as a function of a different respective variable.

9. The method of claim 1, wherein the cost for a fitness goal is computed as a function of computed calories consumed, the cost for a money saving goal is computed as a function of a computed monetary cost of the itinerary, the cost for a time saving goal is computed as a function of a computed duration of the itinerary, and the cost for an environmental impact goal is computed as a function of a computed CO₂ output.

10. The method of claim 1 wherein the transportation modes include modes selected from the group consisting of walk, bicycle, tram, bus, train, and personal vehicle.

11. The method of claim 1, wherein the transportation modes include at least one public transportation mode and at least one personal transportation mode.

12. The method of claim 1, wherein at least one of the constraints places a limit on use of one of the transportation modes from the plurality of transportation modes for building the set of candidate itineraries.

13. The method of claim 1, further comprising updating at least one of the user'"'"'s inferred preferences and inferred goals based on information received from at least one of a mobility tracker and an activity tracker associated with the user.

14. The method of claim 1, further comprising updating at least one of the user'"'"'s inferred preferences and inferred goals based on the user'"'"'s selected itinerary.

15. The method of claim 1, further comprising providing a set of stereotypical profiles and wherein when a user selects one of the stereotypical profiles, modifying at least one of the user'"'"'s goals and the user'"'"'s preferences for the trip.

16. The method of claim 1, further comprising providing for the user to state preferences and goals and updating the user profile based on the stated preferences and goals.

17. A computer program product comprising a non-transitory recording medium storing instructions, which when executed on a computer, causes the computer to perform the method of claim 1.

18. A system for planning a trip comprising memory which stores instructions for performing the method of claim 1 and a processor in communication with the memory for executing the instructions.

19. A system for planning a trip comprising:

a profile manager which manages, for each of a plurality of users, a respective user profile, the user profile including the user'"'"'s preferences for each of a plurality of transportation modes, user goals, and optionally user constraints on trips, the user preferences each including an inferred user preference value and, where stated, a stated user preference value, and the user goals each including an inferred user goal value and, where stated, a stated user goal value;

a trip planner which builds a set of candidate itineraries for a trip requested by one of the users, which meet the user'"'"'s constraints on trips, the candidate itineraries each specifying a respective set of the plurality of transportation modes;

an aggregation component which, for each of the user preferences, aggregates the stated preference value, where stated, and the inferred preference value to generate a weight for the preference and for each of the user goals, aggregates the stated goal value, where stated, and the inferred goal value to generate a weight for the goal;

a ranking component which ranks the candidate itineraries for each of the candidate itineraries based on the preference weights, goal weights, and a computed cost for each of the preferences and of the goals;

a representation generator which outputs information on at least a subset of the ranked itineraries for enabling the user to select an itinerary for the trip; and

a processor which implements the profile manager, trip planner, aggregation component, ranking component, and representation generator.

20. The system of claim 19, further comprising an update component which updates the user'"'"'s inferred preferences and inferred goals based on at least one of:

information received from at least one of a mobility tracker and an activity tracker associated with the user; and

the user'"'"'s selected itinerary.

21. A method comprising:

providing for a user to state preference values for each of a plurality of transportation modes;

providing for the user to state goal values for each of a plurality of goals to which the transportation modes employed in a trip itinerary contribute differently;

optionally, providing for the user to state a constraint for at least one of the transportation modes;

generating a user profile for the user, the user profile including user preferences for each of a plurality of transportation modes, user goals, and optionally user constraints on trips, the user preferences each including an inferred user preference value and, where stated, the stated user preference value, and the user goals each including an inferred user goal value and, where stated, the stated user goal value, the inferred user goal values and inferred user preference values being based on prior user behavior;

for each of a set of candidate itineraries for a trip, ranking the candidate itinerary, the ranking comprising computing a utility function which takes into account the stated and inferred preferences and stated and inferred goals and coefficients which place a weight on the inferred goals and inferred preferences as a function of a duration since the respective goal or preference was last stated; and

outputting information based on the ranking; and

wherein the generating a user profile and ranking the candidate itineraries is performed with a processor.