IP Library Granted Patent US 11,210,499
Granted Patent B2
US 11,210,499 · App. 16/029,072 · Granted Dec 28, 2021

Determining a social group to which customers belong from appearance and using artificial intelligence, machine learning, and computer vision, for estimating customer preferences and intent, and for improving customer services

Inventors: Henricus Meinardus Gerardus Stokman (Amsterdam, NL); Marc Jean Baptist van Oldenborgh (Amsterdam, NL)
Assignee: Kepler Vision Technologies BV
G06K9/00288G06F16/9536G06K9/00362
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,210,499
App. No.
16/029,072
Granted
Dec 28, 2021
Kind
B2
Abstract

An artificial intelligence (AI) system for determining to which social group a person belongs. The AI system includes a computer system and a computer program product which, when running on the computer system, is to: retrieve at least one image of the person belonging to a social group; labels the person, resulting in a labeled person; retrieve at least one image part showing appearance of the labeled person; subject said at least one image part to at least one trained machine learning model defined in the computer program product, the machine learning model including at least a part that is trained on a test set of annotated images which are annotated with respect to categories that correlate to social group, and determine from the at least one trained machine learning model a social group category to which the labeled person belongs.

Claims (45)

1. An artificial intelligence (AI) system for determining to which social group a person belongs, said AI system comprising:

a computer system; and

a computer program product which, when running on said computer system:

retrieves at least one image of said person belonging to a social group;

labels said person in said at least one image, resulting in a labeled person;

retrieves at least one image part showing appearance of said labeled person;

subjects said at least one image part to at least one trained machine learning model defined in said computer program product, said at least one trained machine learning model comprising:

at least a part that is trained to detect key points on the body of said labeled person;

a part that is trained to segment said body into relevant body parts;

a part that is trained to detect clothing on the segmented said relevant body parts, and

at least a part that is trained on a test set of annotated images which are annotated with respect to said detected clothing that correlate to a social group, and

determines from said at least one trained machine learning model a social group category to which the labeled person belongs.

2. The AI system of claim 1 , wherein said clothing comprises accessories, at least one of said accessories selected from clothes, shoes, glasses, jewelry, and watches.

3. The AI system of claim 1 , wherein said at least one trained machine learning model also comprises a part that is trained to determine a head in said relevant body parts, and detects at least one selected from makeup, glasses, jewelry, dental brace, and hairstyle of a person.

4. The AI system according to claim 1 , wherein said AI system retrieves at least one image comprising a series of persons, and for said series of persons determines said social group category.

5. The AI system of claim 4 , further comprising a statistical analyzer for applying a statistical analysis on said social group categories of said series of persons for determining demographics of said series of persons.

6. The AI system of claim 1 , wherein said AI system determines said social group categories real-time.

7. A robot system comprising:

a humanoid robot for interacting with human beings;

an artificial intelligence (AI) system operatively connected to the humanoid robot, and which is for determining to which social group a person belongs, said AI system including:

a computer system; and

a computer program product which, when running on said computer system:

retrieves at least one image of said person belonging to a social group;

labels said person in said at least one image, resulting in a labeled person;

retrieves at least one image part showing appearance of said labeled person;

subjects said at least one image part to at least one trained machine learning model defined in said computer program product, said at least one trained machine learning model comprising:

at least a part that is trained to detect key points on the body of said labeled person;

a part that is trained to segment said body into relevant body parts;

a part that is trained to detect clothing on the segmented said relevant body parts, and

at least a part that is trained on a test set of annotated images which are annotated with respect to said detected clothing that correlate to a social group, and

determines from said at least one trained machine learning model a social group category to which the labeled person belongs.

8. A camera, comprising:

an artificial intelligence (AI) system for determining to which social group a person belongs, said AI system including:

a computer system; and

a computer program product which, when running on said computer system:

retrieves at least one image of said person belonging to a social group;

labels said person in said at least one image, resulting in a labeled person;

retrieves at least one image part showing appearance of said labeled person;

subjects said at least one image part to at least one trained machine learning model defined in said computer program product, said at least one trained machine learning model comprising:

at least a part that is trained to detect key points on the body of said labeled person;

a part that is trained to segment said body into relevant body parts;

a part that is trained to detect clothing on the segmented said relevant body parts, and

at least a part that is trained on a test set of annotated images which are annotated with respect to said detected clothing that correlate to a social group, and

determines from said at least one trained machine learning model a social group category to which the labeled person belongs.

9. The camera of claim 8 , further comprising a housing to house said AI system.

Continuity (1)
Related Publication 20200387692A1 · Dec 10, 2020