Back to results
US 2026/0179162 A1Published application
Systems and Methods for Entity, Relationship, and Timeline Generation from Complex Object Sets
AssigneeTranquility AI Inc.
InventorsJames T. Penrose, David M. Harvilicz
Life of this patent
Estimating the term…
Abstract
Disclosed are methods, systems, and non-transitory computer readable memory for processing, analyzing, and visualizing complex digital object sets using large language models. For instance, a method may include receiving a set of digital objects; indexing the received set of digital objects to generate indexed data; generating a timeline prompt based on the indexed data; processing the timeline prompt to generate a timeline response; and outputting the timeline response as an interactive timeline of based on the set of digital objects.
Claims20
A system for processing and analyzing digital content, comprising:
- a storage device configured to store digital objects and instructions;
- at least one processor configured to execute the instructions to:
- generate a set of vector embeddings for content of the digital objects, the set of vector embeddings capturing semantic relationships within the content;
- identify a set of identified entities within the content, wherein the set of identified entities include one or combinations of events, people, locations, objects, and identifiers;
- retrieve, using a semantic search of the set of vector embeddings, a set of confidence scores for the set of identified entities;
- resolve the set of identified entities based on the set of confidence scores to produce a set of resolved entities;
- generate a graph of a set of relationships associated with the set of resolved entities, wherein a node of the graph is associated with an entity of the set of resolved entities, and wherein an edge between the node and a second node of the graph represents a relationship between the entity and a second entity of the set of resolved entities;
- generate at least one timeline based on the graph of the set of relationships and the set of resolved entities;
- in response to identifying a new entity or a new relationship in the graph, provide a real-time update to the at least one timeline;
- and
- a user interface configured to:
- display the at least one timeline;
- receive user feedback and corrections related to displayed entities and relationships;
- and
- in response to the user feedback and corrections, update the set of resolved entities and the graph of the set of relationships.
12 more elements
A method for processing and analyzing digital content, comprising:
- storing digital objects;
- generating a set of vector embeddings for content of the digital objects, the set of vector embeddings capturing semantic relationships within the content;
- identifying a set of identified entities within the content, wherein the set of identified entities include one or combinations of events, people, locations, objects, and identifiers;
- retrieving, using a semantic search of the set of vector embeddings, a set of confidence scores for the set of identified entities;
- resolving the set of identified entities based on the set of confidence scores to produce a set of resolved entities;
- generating a graph of a set of relationships associated with the set of resolved entities, wherein a node of the graph is associated with an entity of the set of resolved entities, and wherein an edge between the node and a second node of the graph represents a relationship between the entity and a second entity of the set of resolved entities;
- generating at least one timeline based on the graph of the set of relationships and the set of resolved entities;
- in response to identifying a new entity or a new relationship in the graph, providing a real-time update to the at least one timeline;
- displaying the at least one timeline;
- receiving user feedback and corrections related to displayed entities and relationships;
- and
- in response to the user feedback and corrections, updating the set of resolved entities and the graph of the set of relationships.
9 more elements
A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations for processing and analyzing digital content, the operations comprising:
- storing digital objects;
- generating a set of vector embeddings for content of the digital objects, the set of vector embeddings capturing semantic relationships within the content;
- identifying a set of identified entities within the content, wherein the set of identified entities include one or combinations of events, people, locations, objects, and identifiers;
- retrieving, using a semantic search of the set of vector embeddings, a set of confidence scores for the set of identified entities;
- resolving the set of identified entities based on the set of confidence scores to produce a set of resolved entities;
- generating a graph of a set of relationships associated with the set of resolved entities, wherein a node of the graph is associated with an entity of the set of resolved entities, and wherein an edge between the node and a second node of the graph represents a relationship between the entity and a second entity of the set of resolved entities;
- generating at least one timeline based on the graph of the set of relationships and the set of resolved entities;
- in response to identifying a new entity or a new relationship in the graph, providing a real-time update to the at least one timeline;
- displaying the at least one timeline;
- receiving user feedback and corrections related to displayed entities and relationships;
- and
- in response to the user feedback and corrections, updating the set of resolved entities and the graph of the set of relationships.
9 more elements
Dependencies are inferred from the claim text.