Personalizing a shared ride in a mobility-on-demand service

1 . A method for providing a mobility-on-demand service, the method comprising:

receiving feedback from a first set of users that share a first shared ride, wherein the feedback describes their individual satisfaction with different ride attributes of the first shared ride;

scoring an effect of the different ride attributes on different individual users from the first set;

generating prediction data by identifying for the different individual users what their personal response is to different ride attributes to determine an optimum combination of ride attributes for all similar users that yields a most positive response possible relative to other combinations of attributes and wherein the prediction data describes the optimum combination;

updating, by a processor, a response matrix to include the prediction data so that the processor is able to identify the optimum combination on a user-by-users basis based on the prediction data describing the optimum combination, wherein the response matrix includes digital data describing historical user satisfaction with a plurality of shared rides over time and the prediction data;

matching, by the processor, a second set of users to a second shared ride based on service profile data for the users indicating the second set of users is similar to the first set of users and the response matrix wherein the mobility-on-demand service is operable to provide a personalized pairing orchestration among the second set of users and the second shared ride based on the digital data and the prediction data included in the response matrix; and

autonomously navigating an autonomous vehicle to provide the second shared ride based on the matching, wherein the autonomous vehicle uses the response matrix and the prediction data to determine a navigation route that optimizes the ride share attributes for the second set of users.

2 . The method of claim 1 , wherein the first set of users includes a control group of users and a non-control group of users.

3 . The method of claim 2 , wherein the scoring considers the feedback of the control group of users and the non-control group of users.

4 . The method of claim 1 , wherein the method is executed by a processor of a hardware server.

5 . The method of claim 1 , wherein the response matrix includes interpolated responses which are inferred by the processor.

6 . The method of claim 1 , wherein the response matrix includes interpolated responses which are inferred by the processor based on a set of digital twin simulations.

7 . The method of claim 1 , wherein the method is executed by an onboard vehicle computer of a vehicle.

8 . The method of claim 1 , wherein the method is executed by onboard vehicle computers of one or more vehicles that are members of a vehicular micro cloud.

9 . The method of claim 8 , wherein the vehicular micro cloud does not include a server as a member of the vehicular micro cloud.

10 . The method of claim 1 , wherein one or more vehicles which provide the rides is an autonomous vehicle.

11 . A system for providing a mobility-on-demand service comprising:

a non-transitory memory;

and a processor communicatively coupled to the non-transitory memory, wherein the non-transitory memory stores computer readable code that is operable, when executed by the processor, to cause the processor to execute steps including:

receiving feedback from a first set of users that share a first shared ride, wherein the feedback describes their individual satisfaction with different ride attributes of the first shared ride;

scoring an effect of the different ride attributes on different individual users from the first set;

generating prediction data by identifying for the different individual users what their personal response is to different ride attributes to determine an optimum combination of ride attributes for all similar users that yields a most positive response possible relative to other combinations of attributes and wherein the prediction data describes the optimum combination;

updating, by a processor, a response matrix to include the prediction data so that the processor is able to identify the optimum combination on a user-by-users basis based on the prediction data, wherein the response matrix includes digital data describing historical user satisfaction with a plurality of shared rides over time and the prediction data;

matching, by the processor, a second set of users to a second shared ride based on service profile data for the users indicating the second set of users is similar to the first set of users and the response matrix wherein the mobility-on-demand service is operable to provide a personalized pairing orchestration among the second set of users and the second shared ride based on the digital data and the prediction data included in the response matrix; and

autonomously navigating an autonomous vehicle to provide the second shared ride based on the matching, wherein the autonomous vehicle uses the response matrix and the prediction data to determine a navigation route that optimizes the ride share attributes for the second set of users.

12 . The system of claim 11 , wherein one or more of the first shared ride, the plurality of shared rides, and the second shared ride are a multiple-origin-multiple-destination trip.

13 . The system of claim 11 , wherein each of the first shared ride, the plurality of shared rides, and the second shared ride are multiple-origin-multiple-destination trips.

14 . The system of claim 11 , wherein the steps are executed by a processor of a hardware server.

15 . The system of claim 11 , wherein the response matrix includes interpolated responses which are inferred by the processor.

16 . The system of claim 11 , wherein the response matrix includes interpolated responses which are inferred by the processor based on a set of digital twin simulations.

17 . The system of claim 11 , wherein the steps are executed by an onboard vehicle computer of a vehicle which includes the processor.

18 . The system of claim 11 , wherein the steps are executed by onboard vehicle computers of one or more vehicles that are members of a vehicular micro cloud.

19 . The system of claim 18 , wherein the vehicular micro cloud does not include a server as a member of the vehicular micro cloud.

20 . A computer program product including computer code stored on a non-transitory memory that is operable, when executed by a processor, to cause the processor to execute operations for providing a mobility-on-demand service, the operations including:

receive feedback from a first set of users that share a first shared ride, wherein the feedback describes their individual satisfaction with different ride attributes of the first shared ride;

score an effect of the different ride attributes on different individual users from the first set;

generate prediction data by identifying for the different individual users what their personal response is to different ride attributes to determine an optimum combination of ride attributes for all similar users that yields a most positive response possible relative to other combinations of attributes and wherein the prediction data describes the optimum combination;

update, by the processor, a response matrix to include the prediction data so that the processor is able to identify the optimum combination on a user-by-users basis based on the prediction data, wherein the response matrix includes digital data describing historical user satisfaction with a plurality of shared rides over time and the prediction data;

match, by the processor, a second set of users to a second shared ride based on service profile data for the users indicating the second set of users is similar to the first set of users and the response matrix wherein the mobility-on-demand service is operable to provide a personalized pairing orchestration among the second set of users and the second shared ride based on the digital data and the prediction data included in the response matrix; and

autonomously navigate an autonomous vehicle to provide the second shared ride based on the matching, wherein the autonomous vehicle uses the response matrix and the prediction data to determine a navigation route that optimizes the ride share attributes for the second set of users.