Patents Assigned to Lighty AI, Inc.
  • Patent number: 12724826
    Abstract: In a computer-implemented method for generating a knowledge graph of interaction information, a data item including an interaction between at least two entities is received. A knowledge tuple for the data item is generated, the knowledge tuple including entities of the data item and a topic of the interaction of the data item. At least one thread to which the data item corresponds is identified, wherein a thread includes connected data items. An interaction tuple for the data item is generated, the interaction tuple including the entities of the data item, the thread corresponding to the data item, and a type of interaction of the data item. The knowledge graph is populated with the knowledge tuple and the interaction tuple, the knowledge graph including nodes associated with the entities, the topics, and the interactions, wherein the nodes associated with interactions include the type of interaction and thread of the data item.
    Type: Grant
    Filed: January 30, 2025
    Date of Patent: September 1, 2026
    Assignee: Lighty AI, Inc.
    Inventors: Anthony Morris Johnson, Michaela Kindler, Richard R. Rabbat
  • Publication number: 20260220201
    Abstract: In a computer-implemented method for generating a knowledge graph of interaction information, a data item including an interaction between at least two entities is received. A knowledge tuple for the data item is generated, the knowledge tuple including entities of the data item and a topic of the interaction of the data item. At least one thread to which the data item corresponds is identified, wherein a thread includes connected data items. An interaction tuple for the data item is generated, the interaction tuple including the entities of the data item, the thread corresponding to the data item, and a type of interaction of the data item. The knowledge graph is populated with the knowledge tuple and the interaction tuple, the knowledge graph including nodes associated with the entities, the topics, and the interactions, wherein the nodes associated with interactions include the type of interaction and thread of the data item.
    Type: Application
    Filed: January 30, 2025
    Publication date: July 30, 2026
    Applicant: Lighty AI, Inc.
    Inventors: Anthony Morris JOHNSON, Michaela KINDLER, Richard R. RABBAT
  • Publication number: 20260220613
    Abstract: In a computer-implemented method for automatically effectuating an action based on a data item, a data item is received at a first agent, wherein the data item includes an interaction between at least two entities, wherein the first agent is configured to determine whether to automatically effectuate an action based on the data item. The data item is evaluated at the first agent to determine whether to automatically effectuate an action. Provided the first agent determines to automatically effectuate an action based on the data item, a query of a knowledge graph is generated at the first agent to retrieve information from the knowledge graph. The information from the knowledge graph is forwarded to a second agent for effectuating the action. At least the information related to effectuating the action is evaluated at the second agent to determine the action. The action is effectuated at the second agent.
    Type: Application
    Filed: January 30, 2025
    Publication date: July 30, 2026
    Applicant: Lighty AI, Inc.
    Inventors: Anthony Morris JOHNSON, Michaela KINDLER, Richard R. RABBAT