Systems and methods for analyzing entity profiles

Inventors

Skarin, Bruce • Duchon, Andrew • DeJordy, Richard Alexis • Allopenna, Paul David

Interested in licensing this patent?

MTEC can help explore whether this patent might be available for licensing for your application.

Assignees

Aptima Inc

Member
Aptima, Inc.
Aptima, Inc.

Aptima, Inc. is a leader in optimizing and improving human performance in mission-critical, technology-intensive environments. Since 1995, Aptima has combined social science principles with advanced computational methods to deliver innovative, human-centered engineering solutions for defense, intelligence, aviation, law enforcement, and healthcare sectors. The company is recognized for its multidisciplinary approach, integrating expertise from engineering, data science, psychology, and cognitive science to address complex challenges. Aptima is committed to advancing research and development in artificial intelligence, machine learning, data analytics, and simulation, with a strong focus on enhancing human-machine teaming, learning, and readiness. Their mission is to ensure synergy between humans, technology, and organizations, accelerating learning and productivity in the age of AI. Aptima's culture is rooted in innovation, impact, and empathy, fostering an inclusive and supportive environment for its diverse team of experts.

Publication Number

US-9594825-B2

Patent

Publication Date

2017-03-14

Expiration Date


Abstract

Embodiments of the subject invention comprise a computer based system and methods to collect and compare the attributes of a group of entities using data representing topic data of the entity and interaction data between entities. Embodiments of the invention comprise using minimally invasive means to automatically collect and model both an entity's attributes such as their knowledge/work/interest as well as model the social interactions of the entity together with a means to identify opportunities to influence changes in the entity attributes. Minimally invasive means to collect and model attributes include semantic analysis and topic modeling techniques. Means to model social interactions include social network analysis techniques that can incorporate location data of the entity. Embodiments of the invention further provide a sharable index of the attributes of the entities and the group of entities.

Core Innovation

The disclosure describes computer-based entity profiling that combines topic models of entity attributes, including knowledge, work, and interests, with interaction models derived from communications and location or proximity information. It generates entity topic or interaction profiles from group-level models and compares profiles to determine topic or interaction similarity among entities in the group.

The available partial content does not include the background section, so the problem being solved is not explicitly described in patent. The disclosure also describes a client-server analysis system, optional wearable interaction sensors, shareable profile indexes, and a pilot evaluation illustrating network and interest-potential analyses.

Claims Coverage

The claims include five independent claims: four computer-based methods and one entity profiling system. They cover interaction-profile and topic-profile modeling and comparison, as well as a system implementing interaction-profile analysis.

Interaction profiles based on proximity information

The method receives interaction information for a group that includes location information indicating proximity in space and time between two entities, determines a global interaction model, derives an interaction profile for each entity, and compares the profiles to identify their degree of interaction similarity.

Interaction profiles based on a global interaction model

The method determines a global interaction model from interaction information for a group of entities, derives interaction profiles for two entities, and compares the profiles to identify their degree of interaction similarity.

Topic profiles based on interaction information

The method determines a global topic model for a group from interaction information, determines topic profiles for two entities from that model, and compares the profiles to identify their degree of topic similarity.

Topic profiles based on entity attributes

The method receives attributes of a group of entities, determines a global topic model representing at least one group attribute, determines topic profiles representing attributes of two entities, and compares the profiles to determine their degree of topic similarity.

Entity profiling system for interaction similarity

The system includes a system bus, a database containing interaction data, and computer-readable program code. The code receives interaction information that includes proximity in space and time between two entities, determines their interaction profiles from a global interaction model, and compares the profiles to identify their degree of interaction similarity.

The independent claims cover methods for comparing entity interaction profiles or topic profiles, including profiles derived from interaction information or entity attributes, and a system for comparing interaction profiles using proximity information.

Stated Advantages

Not explicitly described in patent.

Documented Applications

Identifying potential collaboration opportunities by comparing entity profiles for topic or interaction similarity.

A pilot evaluation illustrating network and interest-potential analyses.

JOIN OUR MAILING LIST

Stay Connected with MTEC

Keep up with active and upcoming solicitations, MTEC news and other valuable information.