Browse Prior Art Database

Cognitive navigation system

IP.com Disclosure Number: IPCOM000248008D
Publication Date: 2016-Oct-17
Document File: 3 page(s) / 145K

Publishing Venue

The IP.com Prior Art Database

Abstract

This article describes how, by using machine learning and cognitive computing, a navigation system could anticipate and improve the route selection in function of the user's point of interest. Objective of this invention is to improve the quality of service for navigation systems. As a source of information this invention will use information "manually" selected by the user, information coming from social network selected in function of their location and information related to maps and route quality.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 54% of the total text.

Page 01 of 3

Cognitive navigation system

Today, navigation systems respond to one and only one objective which is clear. Providing the fastest way to connect two points.

    Most of the GPS take into account the method of travel (walking, riding a bicycle, driving a car…) in order to display this best route.

    Some GPS offers alternatives between multiple routes but within a lot of information about the differences between these routes.


- Differences are the cost, the distance, and the speed limit in general.

Problem, these options are not « personalized » and don't take into account the «

objectives » of the traveler.

    When traveling for holidays for instance. Route that have to be chosen could be drastically different from the one you would choose if you are already familiar with an area.

    On a one hour drive, loosing 10 minutes for seeing a important center of interest or a good point of view could worth the « detour » especially if the « objective » of the travel is to visit.

    Objectives of this patent is to provide a way to enhance experience and increase the level of satisfaction of users when traveling.

    With the raise of autonomous car, the importance of the speed and duration of a navigation will decrease and, the "quality" of the ride will become more important since we'll be able to do different thing in the car (resting, reading, taking picture of the environment, etc...)

    Point of interests could quickly evolve in function of a lot of points, user profile, weather, day of the week, special events, etc…

    To calculate an up to date and accurate list of the point of interest in an area or along a route, our solution will scan social network such as tweeter or instagram to collect and look for locations that have generated a lot of interest from a community.

Our solution will combine:


Analyze of the post related to locations along the route in real time.

- Are the post positives or negatives?

- Does they sound enthusiast, surprising, or disappointing?

    All these sentiments could lead to a lot of posts but should not be interpreted in the same way.

    - Our solution will also use hashtag or image analysis to understand what can be seeing in a specific location.

    - Our solution would then try to correlate this location with our personal center of interest.

    Based on the information listed above, our cognitive navigation system will be able to adapt the offer to what the user like. The interest of this solution is also to offer road that were not expected by the user but that could interest him. In a way, this mechanism will be pro-active and will not be just based on pre-filled information given by th...