Cognitive-based passenger selection

Patent metadata

Field	Value
Publication number	US-11410079-B2
Application number	US-201916398360-A
Country	US
Kind code	B2
Filing date	Apr 30, 2019
Priority date	Oct 24, 2017
Publication date	Aug 9, 2022
Grant date	Aug 9, 2022

Abstract

Aspects of the invention perform an operation comprising receiving a plurality of rules associated with a first seat in a mass-transit vehicle, determining a plurality of physical attributes for a first passenger, of a plurality of passengers, based on data describing the first passenger received from a plurality of data sources, determining a plurality of non-physical attributes for the first passenger based on the received data describing the first passenger, determining that at least one of the plurality of physical attributes and the plurality of non-physical attributes of the first passenger satisfy each rule in the set of rules associated with the first seat, computing, based on a machine learning (ML) model a score for the first passenger, determining that the score exceeds a threshold score associated with the first seat, and allocating the first passenger to the first seat in the mass-transit vehicle.

First claim

What is claimed is:

1. A method, comprising:
receiving, by an application executing on a processor, a plurality of rules associated with a first seat of a plurality of seats in a mass-transit vehicle;
determining a plurality of physical attributes for a first passenger, of a plurality of passengers, based on data describing the first passenger received from a plurality of data sources;
determining a plurality of non-physical attributes for the first passenger based on the data describing the first passenger;
determining that at least one of the plurality of physical attributes and the plurality of non-physical attributes of the first passenger satisfy each rule in the plurality of rules associated with the first seat;
computing, at a first time, a first score reflecting a degree of suitability for the first passenger, with respect to the first seat, by processing the plurality of physical attributes and the plurality of non-physical attributes with a trained machine learning (ML) model;
determining that the first score exceeds a threshold score associated with the first seat;
allocating, by the application, the first passenger to the first seat in the mass-transit vehicle; and
computing, at a second time, a second score for the first passenger by processing at least one new attribute of the first passenger using the trained ML model; and
reallocating the first seat to a second passenger based on the second score.

2. The method of claim 1 , wherein the mass-transit vehicle comprises one of: (i) an airplane, (ii) a bus, and (iii) a train, wherein a first physical attribute of the plurality of physical attributes is received from a physical attribute service via a network, wherein the physical attribute service determines the first physical attribute based on an analysis of an image of the first passenger received from at least one of the plurality of data sources.

3. The method of claim 1 , wherein the non-physical attributes comprise: (i) emotions expressed by the first passenger, (ii) sentiment expressed by the first passenger, (iii) a preference of the first passenger, and (iv) a personality trait of the first passenger, wherein a first non-physical attribute of the plurality of non-physical attributes is received from a non-physical attribute service via a network, wherein the non-physical attribute service determines the first non-physical attribute based on an analysis of: (i) blog posts generated by the first passenger, (ii) social media publications generated by the first passenger, and (iii) a profile of the first passenger received from the plurality of data sources.

4. The method of claim 1 , further comprising:
training the application to generate the ML model based on training data, wherein the ML model specifies weights for the plurality of physical attributes and the plurality of non-physical attributes, wherein the application computes the first score based on the weights specified in the ML model.

5. The method of claim 4 , wherein the first score comprises a composite score, wherein the composite score is computed based on: (i) a physical attribute score computed based on the weights specified in the ML model and the plurality of physical attributes of the first passenger, (ii) a non-physical attribute score computed based on the weights specified in the ML model and the plurality of non-physical attributes of the first passenger.

6. The method of claim 1 , further comprising:
computing a respective score for each respective passenger of the plurality of passengers based on the ML model and a respective plurality of physical and non-physical attributes of each respective passenger;
generating an ordered list of the plurality of passengers ranked based on the respective score for each respective passenger of the plurality of passengers; and
allocating each respective passenger of the plurality of passengers to a respective seat in the mass-transit vehicle based on the ordered list of the plurality of passengers.

7. The method of claim 1 , further comprising:
determining a second plurality of physical attributes for a third passenger, of the plurality of passengers, based on data describing the third passenger received from the plurality of data sources;
determining a second plurality of non-physical attributes for the third passenger based on the data describing the first passenger;
determining that at least one of the second plurality of physical attributes and the second plurality of non-physical attributes of the third passenger violates at least one rule associated with a second seat in the mass-transit vehicle;
denoting, in a record stored in a memory, that the second seat in the mass-transit vehicle is unavailable to the third passenger based on the violation of the at least one rule associated with the second seat; and
allocating the third passenger to a third seat in the mass-transit vehicle.

Assignees

• IBM

Inventors

• Ayyagari Phani Kumar V U
• Bhide Manish A
• Chukka Madan K
• Jasti Purna Chandra

Classifications

• G06N20/00 Primary

  Machine learning · CPC title

• G06Q10/02

  Reservations, e.g. for tickets, services or events · CPC title

• G06Q10/0283

  for travel seating · CPC title