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

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;
• 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 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.

A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon said execution, cause the one or more computers to perform operations of configuring a plurality of display devices communicatively coupled to a distributed local area communication network, the operation 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 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,
• wherein the operations further comprise, 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.