Patents Assigned to Chooch Intelligence Technologies Co.
  • Publication number: 20240386578
    Abstract: Embodiments of the present invention train multiple Perception models to predict contextual metadata (tags) with respect to target content items. By extracting context from content items, and generating associations among the Perception models, individual Perceptions trigger one another based on the extracted context to generate a more robust set of contextual metadata. A Perception Identifier predicts core tags that make coarse distinctions among content items at relatively higher levels of abstraction, while also triggering other Perception models to predict additional perception tags at lower levels of abstraction. A Dense Classifier identifies sub-content items at various levels of abstraction, and facilitates the iterative generation of additional dense tags across integrated Perceptions.
    Type: Application
    Filed: July 29, 2024
    Publication date: November 21, 2024
    Applicant: Chooch Intelligence Technologies Co.
    Inventors: Hakan Robert Gultekin, Emrah Gultekin
  • Publication number: 20240354578
    Abstract: Embodiments of the present invention train multiple Perception models to predict contextual metadata (tags) with respect to target content items. By extracting context from content items, and generating associations among the Perception models, individual Perceptions trigger one another based on the extracted context to generate a more robust set of contextual metadata. A Perception Identifier predicts core tags that make coarse distinctions among content items at relatively higher levels of abstraction, while also triggering other Perception models to predict additional perception tags at lower levels of abstraction. A Dense Classifier identifies sub-content items at various levels of abstraction, and facilitates the iterative generation of additional dense tags across integrated Perceptions.
    Type: Application
    Filed: July 1, 2024
    Publication date: October 24, 2024
    Applicant: Chooch Intelligence Technologies Co.
    Inventors: Hakan Robert Gultekin, Emrah Gultekin
  • Patent number: 12051209
    Abstract: Embodiments of the present invention train multiple Perception models to predict contextual metadata (tags) with respect to target content items. By extracting context from content items, and generating associations among the Perception models, individual Perceptions trigger one another based on the extracted context to generate a more robust set of contextual metadata. A Perception Identifier predicts core tags that make coarse distinctions among content items at relatively higher levels of abstraction, while also triggering other Perception models to predict additional perception tags at lower levels of abstraction. A Dense Classifier identifies sub-content items at various levels of abstraction, and facilitates the iterative generation of additional dense tags across integrated Perceptions.
    Type: Grant
    Filed: April 19, 2021
    Date of Patent: July 30, 2024
    Assignee: CHOOCH INTELLIGENCE TECHNOLOGIES CO.
    Inventors: Hakan Robert Gultekin, Emrah Gultekin
  • Patent number: 12026622
    Abstract: Embodiments of the present invention train multiple Perception models to predict contextual metadata (tags) with respect to target content items. By extracting context from content items, and generating associations among the Perception models, individual Perceptions trigger one another based on the extracted context to generate a more robust set of contextual metadata. A Perception Identifier predicts core tags that make coarse distinctions among content items at relatively higher levels of abstraction, while also triggering other Perception models to predict additional perception tags at lower levels of abstraction. A Dense Classifier identifies sub-content items at various levels of abstraction, and facilitates the iterative generation of additional dense tags across integrated Perceptions.
    Type: Grant
    Filed: June 6, 2022
    Date of Patent: July 2, 2024
    Assignee: CHOOCH INTELLIGENCE TECHNOLOGIES CO.
    Inventors: Hakan Robert Gultekin, Emrah Gultekin
  • Patent number: 11354351
    Abstract: Embodiments of the present invention train multiple Perception models to predict contextual metadata (tags) with respect to target content items. By extracting context from content items, and generating associations among the Perception models, individual Perceptions trigger one another based on the extracted context to generate a more robust set of contextual metadata. A Perception Identifier predicts core tags that make coarse distinctions among content items at relatively higher levels of abstraction, while also triggering other Perception models to predict additional perception tags at lower levels of abstraction. A Dense Classifier identifies sub-content items at various levels of abstraction, and facilitates the iterative generation of additional dense tags across integrated Perceptions.
    Type: Grant
    Filed: January 31, 2019
    Date of Patent: June 7, 2022
    Assignee: CHOOCH INTELLIGENCE TECHNOLOGIES CO.
    Inventors: Hakan Robert Gultekin, Emrah Gultekin
  • Publication number: 20210326646
    Abstract: Embodiments of the present invention train multiple Perception models to predict contextual metadata (tags) with respect to target content items. By extracting context from content items, and generating associations among the Perception models, individual Perceptions trigger one another based on the extracted context to generate a more robust set of contextual metadata. A Perception Identifier predicts core tags that make coarse distinctions among content items at relatively higher levels of abstraction, while also triggering other Perception models to predict additional perception tags at lower levels of abstraction. A Dense Classifier identifies sub-content items at various levels of abstraction, and facilitates the iterative generation of additional dense tags across integrated Perceptions.
    Type: Application
    Filed: April 19, 2021
    Publication date: October 21, 2021
    Applicant: Chooch Intelligence Technologies Co.
    Inventors: Hakan Robert Gultekin, Emrah Gultekin