North Carolina Patent of the Month – June 2023
Innovation in computer-based reasoning systems has revolutionized the way we predict outcomes and make decisions. These reasoning systems use available knowledge and logical techniques such as deduction and induction to draw conclusions. These systems heavily rely on training data to generate accurate models. However, acquiring and preparing sufficient training data can be a challenging task. Diveplane Corporation, a leading inventor in this field, has recently been granted a patent for their solution to this dilemma. Their invention involves the generation of synthetic data that meets a high dataset quality threshold, ensuring the reliability of computer-based reasoning systems.
Their process involves receiving a request for synthetic data generation based on a set of training data cases. The system then repeatedly determines new synthetic data cases by analyzing focal training data cases. This process generates a set of two or more synthetic data cases, each derived from the training data.
To assess the quality of the synthetic data, the system calculates a dataset quality metric. This metric considers statistical quality, model comparison, and dataset privacy. The dataset privacy metric specifically quantifies the likelihood of identifying private data in the training data from the synthetic data. If the dataset quality metric falls below the defined threshold, corrective actions are taken to improve the synthetic data.
The corrective actions can involve modifying, deleting, or replacing specific synthetic data cases. This iterative process ensures that the synthetic data meets the desired quality standards. Once the dataset quality metric meets the threshold, the synthetic data is used to control a controllable system, enabling accurate predictions and decision-making.
Diveplane Corporation’s method overcomes the limitation of acquiring training data by simply generating high-quality synthetic data. This eliminates the need for large-scale data collection efforts, reduces privacy concerns, and improves the efficiency of training processes. With Diveplane Corporation’s invention, computer-based reasoning systems can achieve enhanced performance and accuracy, leading to more reliable predictions and decision-making in various domains.
Are you developing new technology for an existing application? Did you know your development work could be eligible for the R&D Tax Credit and you can receive up to 14% back on your expenses? Even if your development isn’t successful your work may still qualify for R&D credits (i.e. you don’t need to have a patent to qualify). To find out more, please contact a Swanson Reed R&D Specialist today or check out our free online eligibility test.
Who We Are:
Swanson Reed is one of the U.S.’ largest Specialist R&D tax advisory firms. We manage all facets of the R&D tax credit program, from claim preparation and audit compliance to claim disputes.
Swanson Reed regularly hosts free webinars and provides free IRS CE and CPE credits for CPAs. For more information please visit us at www.swansonreed.com/webinars or contact your usual Swanson Reed representative.