Travel mobility as a service (MaaS)

Patent metadata

Field	Value
Publication number	US-10839467-B2
Application number	US-201715413591-A
Country	US
Kind code	B2
Filing date	Jan 24, 2017
Priority date	Jan 24, 2017
Publication date	Nov 17, 2020
Grant date	Nov 17, 2020

Abstract

Embodiments for improving travel mobility as a service (MaaS) by one or more processors. A selected mode of transportation may be matched with a selected route to generate a travel package according to a multi-objective model based on a route profile for a plurality of routes, a user profile of the one or more users, an environmental profile, and a collaboration of monitored data relating to preferences of a mode of transportation and routes of the one or more users, wherein the travel package includes at least the matching selected mode of transportation, the selected route, and one or more travel suggestions.

First claim

The invention claimed is:

1. A method, by a processor, for improving travel mobility as a service (MaaS), comprising:
determining, by the processor, a current geographical position of a mobile device according to global positioning satellite (GPS) data received by a GPS system integrated into the mobile device;
matching, by the processor, one or more users with a selected mode of transportation and a selected route to generate a travel package displayed to the one or more users using a display of the mobile device according to a multi-objective model based on a route profile for a plurality of routes, a user profile of the one or more users, an environmental profile, and a collaboration of monitored data relating to preferences of a mode of transportation and routes of the one or more users, wherein the travel package includes at least the matching selected mode of transportation, the selected route, and one or more travel suggestions based, at least in part, on the current geographical position of the mobile device as determined by the GPS system;
selecting, by the processor, the selected mode of transportation and the selected route from one of a plurality of route options by the one or more users, wherein the route profile includes a maximum or minimum speed, a type of travel route, a length of a travel route, an elevation, mapping information, and one or more points of interest, wherein the user profile includes driving habits, calendar information, preferences and interests of the user, key performance indicators, a physical or emotional condition of the user, travel experience of the user, preferred transportation means, common travel destinations, wherein the environmental profile includes at least weather, traffic conditions, construction, legal restrictions or requirements, and transportation services, and wherein a selected mode of transportation is a vehicle, a train, or plane;
monitoring, by the processor, each interaction by the one or more users relating to the selected mode of transportation and the selected route and correlating the selected mode of transportation and the selected route to the collaboration of monitored data related to the preferences;
training, by the processor, an artificial neural network (ANN) classifier of the multi-objective model using each monitored interaction to increase an accuracy of the matching such that interactions between the user and the mobile device are used as a feedback loop to iteratively train the ANN classifier according to an amalgamation of the route profile, the user profile of the one or more users, the environmental profile, and the collaboration of monitored data, wherein a virtual computing system filters and stores training data relating to the training of the ANN classifier commensurate with each of the iterations; and
automatically generating, by the processor, the travel package on the display of the mobile device for presentation to the one or more users according to an output of the multi-objective model having the trained ANN classifier to match the one or more users with the selected mode of transportation and the selected route; wherein generating the travel package further includes displaying, in natural language, identified advantages of the generated travel package relative to the user profile of characteristics learned from the one or more users based on a history of the monitored interactions.

2. The method of claim 1 , wherein the matching further includes:
generating a plurality of route options from the plurality of routes to perform the matching according to integrated data based on the route profile, the user profile, and the environmental profile; or
matching one of a plurality of modes of transportation with one of the generated route options according to the integrated data upon generating the plurality of routes.

3. The method of claim 1 , further including ranking each one of a plurality of route options available for the matching according to a route score, wherein the route score is based upon the collaboration of data and one or more user profiles for the one or more users.

4. The method of claim 1 , further including providing in the travel package one or more travel related commercial offers and services, travel pricing alternatives, estimated travel costs, and parking options.

5. The method of claim 1 , further including providing the selected mode of transportation with the selected route for the one or more users to share with one or more drivers similar to the one or more users.

6. A system for improving travel mobility as a service (MaaS), comprising:
one or more processors coupled to one or more memory devices storing executable instructions that:
determine, by the one or more processors, a current geographical position of a mobile device according to global positioning satellite (GPS) data received by a GPS system integrated into the mobile device;
match, by the one or more processors, one or more users with a selected mode of transportation and a selected route to generate a travel package displayed to the one or more users using a display of the mobile device according to a multi-objective model based on a route profile for a plurality of routes, a user profile of the one or more users, an environmental profile, and a collaboration of monitored data relating to preferences of a mode of transportation and routes of the one or more users, wherein the travel package includes at least the matching selected mode of transportation, the selected route, and one or more travel suggestions based, at least in part, on the current geographical position of the mobile device as determined by the GPS system;
select, by the one or more processors, the selected mode of transportation and the selected route from one of a plurality of route options by the one or more users, wherein the route profile includes a maximum or minimum speed, a type of travel route, a length of a travel route, an elevation, mapping information, and one or more points of interest, wherein the user profile includes driving habits, calendar information, preferences and interests of the user, key performance indicators, a physical or emotional condition of the user, travel experience of the user, preferred transportation means, common travel destinations, wherein the environmental profile includes at least weather, traffic conditions, construction, legal restrictions or requirements, and transportation services, and wherein a selected mode of transportation is a vehicle, a train, or plane;
monitor, by the one or more processors, each interaction by the one or more users relating to the selected mode of transportation and the selected route and correlating the selected mode of transportation and the selected route to the collaboration of monitored data related to the preferences;
train, by the one or more processors, an artificial neural network (ANN) classifier of the multi-objective model using each monitored interaction to increase an accuracy of the matching such that interactions between the user and the mobile device are used as a feedback loop to iteratively train the ANN classifier according to an amalgamation of the route profile, the user profile of the one or more users, the environmental profile, and the collaboration of monitored data, wherein a virtual computing system filters and stores training data relating to the training of the ANN classifier commensurate with each of the iterations; and
automatically generate, by the one or more processors, the travel package on the display of the mobile device for presentation to the one or more users according to an output of the multi-objective model having the trained ANN classifier to match the one or more users with the selected mode of transportation and the selected route; wherein generat

Assignees

• IBM

Inventors

• Ghaddar Bissan
• Russo Giovanni
• Shorten Robert
• Verago Rudi

Classifications

• G06N20/00

  Machine learning · CPC title

• G01C21/3438

  Rendezvous; Ride sharing · CPC title

• G01C21/3484

  Personalized, e.g. from learned user behaviour or user-defined profiles · CPC title

• G01C21/3492

  employing speed data or traffic data, e.g. real-time or historical (traffic control systems for road vehicles involving transmission of navigation instructions to the vehicle G08G1/0968) · CPC title

• G01C21/3476

  using point of interest [POI] information, e.g. a route passing visible POIs · CPC title