Systems, apparatus, and methods for generating prediction sets based on a known set of features

Inventors: Thomas Mathew (Vienna, VA); John William Seaman (Reston, VA); Ali Reza Manouchehri (Reston, VA); Jorge Luis Vasquez (Fairfax, VA); Lee Evan Kohn (Arlington, VA)

Assignee: Zoomph, Inc.

G06N7/005 G06N5/02

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 9,996,800
App. No.: 15/347,777
Granted: Jun 12, 2018
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

An individual having a plurality of first features and a second characteristic is identified. A plurality of second features associated with a second characteristic is determined. For each first feature among the plurality of first features, a respective probability distribution indicating, for each respective second feature, a probability that a person having the respective second feature has the first feature, is determined, thereby generating a plurality of probability distributions. A probabilistic classifier is used to combine the plurality of probability distributions, thereby generating a merged probability distribution. A Monte Carlo method is used to generate a prediction set based on the merged probability distribution, the prediction set including a plurality of prediction values for the second characteristic of the individual, each respective prediction value being associated with one of the plurality of second features. The prediction set is stored in a memory. The probabilistic classifier may include a Naïve-Bayes method. Prediction sets may be generated for each of a plurality of individuals, and used to predict a feature associated with a group. For example, an advertisement may be selected and displayed based on the predicted feature.

Claims (83)

1. A method of configuring a plurality of display devices communicatively coupled to a distributed local area communication network, the method comprising:

obtaining images of a plurality of individuals at an event location, wherein the local area communication network is at the event location:

identifying a plurality of individual data objects in a data store, each of the plurality of individual data objects defining features of a respective set of the plurality of individuals using facial recognition of images obtained of the plurality of individuals;

identifying a data object of the plurality of individual data objects, the data object identifying a first set of individuals having a first feature;

selecting a plurality of content tags based on the first feature;

tagging a plurality of content items with one or more of the plurality of content tags;

identifying a first content item of the plurality of content items, the first content item being associated with a first content tag, the first content tag being associated with the first set of individuals;

selecting a second content item based on the first content tag;

generating a display layout for the first and second content items;

selecting a display device among the plurality of the display devices communicatively coupled to the distributed local area communication network, wherein a location of the display device is associated with the respective set of the plurality of individuals;

transmitting, to the selected display device, the first and second content item, the display layout, and a display time;

configuring, over the distributed communication network, a first FPGA chip in the selected display device to display the first and second content items having a look and feel of the generated display layout;

configuring a second FPGA chip in the selected display device to display the second content item for the display time,

wherein the selecting of the plurality of content tags comprises:

for the first feature, determining a respective probability distribution indicating, for each of a respective content tag among the plurality of content tags, a probability that a set of individuals associated with a content tag has the first feature, thereby generating a plurality of probability distributions;

using a probabilistic classifier to generate a merged probability distribution based on the plurality of probability distributions; and

using a plurality of prediction sets to select the plurality of content tags, the plurality of content tags being associated with the first set of individuals, and

wherein the method further comprises, using a Monte Carlo method to generate the plurality of prediction sets based on the merged probability distribution, the prediction sets including a plurality of prediction values for the first set of individuals, each respective prediction value being associated with one of the plurality of content tags.

2. The method of claim 1 , further comprising:

determining that a plurality of new content items have been added to the plurality of content items;

selecting an additional content item from the plurality of new content items based on the first content tag;

modifying the display layout to include the additional content item; and

transmitting, to the display device, the additional content item, the modified display layout, and a second display time,

wherein, the display device is further configured to display the additional content item using the modified display layout, the additional content item being displayed for the second display time.

3. The method of claim 1 , wherein the first feature comprises a hashtag.

4. The method of claim 1 , wherein the tagging of the plurality of content items with the one or more of the plurality of content tags comprises tagging of the plurality of content items based on text included in one of the content items.

5. The method of claim 1 , wherein the tagging of the plurality of content items with the one or more of the plurality of content tags comprises tagging of the plurality of content items based on an image included in one of the content items.

6. A system of a plurality of display devices communicatively coupled to a distributed local area communication network, the system comprising:

a display device of the plurality of display devices adapted to display text and images;

a memory adapted to store instructions; and

one or more devices adapted to execute the instructions, which, when executed by the one or more devices, cause the one or more devices to perform operations comprising:

obtaining images of a plurality of individuals at an event location, wherein the local area communication network is at the event location;