Patents Assigned to Distributed Analytics Solutions, Ltd.
  • Real-time drift detection in time-series data for automated AI model re-training
    Patent number: 12646003
    Abstract: Aspects disclosed provide system and method for monitoring a trained artificial intelligence (AI) model to determine when the AI model needs to be re-trained. The system and method provides a framework for detecting when the model's ability to provide accurate predictions for real-time time-series data have trended/drifted away from data used to train the AI model. Based on detecting the trend/drift, the system and method will generate an alert indicating at the AI model may need to be re-trained.
    Type: Grant
    Filed: August 4, 2025
    Date of Patent: June 2, 2026
    Assignee: DISTRIBUTED ANALYTICS SOLUTIONS, LTD.
    Inventors: Stylianos Kapetanakis, Khuong An Nguyen, Zhiyuan Luo
  • Reliable outputs from large language models for multi-label classification tasks
    Patent number: 12499134
    Abstract: Aspects disclosed provide system and methods for providing reliability measures to outputs of large language models (LLMs). The system and methods do this by integrating Large Language Models (LLMs) in a multi-label classification setting, utilizing the Conformal Prediction (CP) framework. This approach ensures that the predictions made by the LLM are accompanied by mathematically guaranteed error bounds, enhancing the LLMs reliability and trustworthiness.
    Type: Grant
    Filed: June 20, 2025
    Date of Patent: December 16, 2025
    Assignee: Distributed Analytics Solutions, Ltd.
    Inventors: Stylianos Kapetanakis, Khuong An Nguyen, Nery Riquelme-Granada, Zhiyuan Luo
  • Calibrated large language models for multi-label classifications
    Patent number: 12367223
    Abstract: Aspects disclosed provide system and methods for providing reliability measures to outputs of large language models (LLMs). The system and methods do this by integrating Large Language Models (LLMs) in a multi-label classification setting, utilizing the Conformal Prediction (CP) framework. This approach ensures that the predictions made by the LLM are accompanied by mathematically guaranteed error bounds, enhancing the LLMs reliability and trustworthiness.
    Type: Grant
    Filed: November 18, 2024
    Date of Patent: July 22, 2025
    Assignee: Distributed Analytics Solutions, Ltd.
    Inventors: Nery Riquelme-Granada, Khuong An Nguyen, Stylianos Kapetanakis, Zhiyuan Luo