Granted Patent B2

US 11,774,257 · App. 17/354,820 · Granted Oct 3, 2023

Inventors: Matthew Klenk (San Francisco, CA); Victoria M. Bellotti (Oakland, CA); Shiwali Mohan (Palo Alto, CA)

Assignee: Xerox Corporation

G01C21/3484G01C21/3461G01C21/3605G01C21/3697G06F16/2379G06F16/24575G01C21/3676G06F16/29

Abstract

Claims (53)

1. A method comprising:

receiving a request for a transportation plan for a user, wherein the request comprises a starting point and an ending point for a route;

generating a set of potential transportation plans for the route;

determining an impact of a subset of plans in the set of potential transportation plans;

estimating, by a processing device of a transportation analysis system, a likelihood of acceptance of the subset of plans in the set of potential transportation plans based on personal preference of the user;

selecting, by the processing device, an influence strategy based on inference over user data of a user model;

generating, by the processing device, a message recommending a selected plan from the subset of plans for the user, wherein the message is generated based on the selected influence strategy and wherein the selected transportation plan is provided to and utilized by a navigation system of a user device associated with the user;

receiving, from the user device, an indication that the user did not accept the selected transportation plan; and

updating the user model based on the user not accepting the selected transportation plan, wherein after being updated, the user model is used to generate an updated selected transportation plan, wherein the updated selected transportation plan is provided to and utilized by the navigation system.

2. The method of claim 1 , wherein the influence strategy is determined by inference over user data using an influence model of the user model.

3. The method of claim 2 , wherein the influence model comprises a machine learning model.

4. The method of claim 1 , wherein determining the impact of the subset of plans comprises estimating a travel time and a fuel consumption comprises simulating the potential transportation plans across a transportation system.

5. The method of claim 1 , further comprising generating the user model based on explicit and inferred data regarding the user.

6. The method of claim 1 , wherein generating the message comprises:

identifying a messaging template based on the selected influence strategy; and

completing the messaging template based at least in part of a first impact measurement of the selected transportation plan.

7. The method of claim 1 , further comprising:

estimating a measurement of change to a transportation system for the subset of plans; and

selecting the selected plan based on the estimated measurement of change to the transportation system and the estimated likelihood of acceptance of the subset of plans.

8. The method of claim 1 , further comprising providing the generated message to the user device through a user interface.

9. A system comprising:

a memory device; and

a processing device operatively coupled to the memory device, wherein the processing device is to:

receive a request for a transportation plan for a user, wherein the request comprises a starting point and an ending point for a route;

generate a set of potential transportation plans for the route;

determine an impact of a subset of plans in the set of potential transportation plans;

estimate, by a transportation analysis system, a likelihood of acceptance of the subset of plans in the set of potential transportation plans based on personal preference of the user;

select an influence strategy of the user based on a user model associated with the user, wherein the influence strategy is determined by inference over user data;

generate a message recommending a selected transportation plan for the user, wherein the message is generated based on the selected influence strategy and wherein the selected transportation plan is provided to and utilized by a navigation system of a user device associated with the user;

receive, from the user device, an indication of that the user did not accept the selected transportation plan; and

update the user model based on the user not accepting the selected transportation plan, wherein after being updated, the user model is used to generate an updated selected transportation plan, wherein the updated selected transportation plan is provided to and utilized by the navigation system.

10. The system of claim 9 , wherein the influence strategy is determined by inference over user data using an influence model.

11. The system of claim 10 , wherein the influence model comprises a machine learning model.

12. The system of claim 9 , wherein the personal preference is based on at least one of publicly available sources, private data, surveys or user input.

13. The system of claim 9 , wherein to determine the impact of the subset of plans, the processing device is further to estimate a travel time and a fuel consumption comprises simulating the potential transportation plans across a transportation system.

14. The system of claim 9 , wherein the processing device is further to generate the user model based on explicit and inferred data regarding the user.

15. The system of claim 9 , wherein to generate the message the processing device is further to:

identify a messaging template based on the selected influence strategy; and

complete the messaging template based at least in part of a first impact measurement of the selected transportation plan.

16. The system of claim 9 , wherein the processing device is further to:

estimate a measurement of change to a transportation system for the subset of plans; and

select the selected plan based on the estimated measurement of change to the transportation system and the estimated likelihood of acceptance of the subset of plans.

17. A non-transitory computer-readable medium having instructions stored thereon that, when executed by a processing device, cause the processing device to:

receive a request for a transportation plan for a user, wherein the request comprises a starting point and an ending point for a route;

generate a set of potential transportation plans for the route;

determine an impact of a subset of plans in the set of potential transportation plans; and

estimate, by the processing device of a transportation analysis system, a likelihood of acceptance of the subset of plans in the set of potential transportation plans based on personal preference of the user;

select an influence strategy of the user based on a user model associated with the user; generate a message recommending a selected transportation plan for the user, wherein the influence strategy is determined by inference over user data, wherein the message is generated based on the selected influence strategy and wherein the selected transportation plan is provided to and utilized by a navigation system of a user device associated with the user;

receive an indication of that the user did not accept the selected transportation plan; and

update the user model based on the user not accepting the selected transportation plan, wherein after being updated, the user model is used to generate an updated selected transportation plan, wherein the updated selected transportation plan is provided to and utilized by the navigation system.

18. The non-transitory computer-readable medium of claim 17 , wherein the influence strategy is determined by inference over user data using an influence model.

19. The non-transitory computer-readable medium of claim 17 , wherein the influence model comprises a machine learning model.

20. The non-transitory computer-readable medium of claim 17 , wherein to determine the impact of the subset of plans, the processing device is further to estimate at least one of a travel time or a fuel consumption.

Assignments (8)

Continuity (2)