首页|Patent Issued for Model ML registry and model serving (USPTO 12117983)
Patent Issued for Model ML registry and model serving (USPTO 12117983)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News-From Alexandria, Virginia, NewsRx jour nalists report that a patent by the inventorsDavidson, Aaron Daniel (Berkeley, CA, US), Mewald, Clemens (Lafayette, CA, US), Nykodym, Tomas(San Francisco, CA, US), filed on November 17, 2023, was published online on October 15, 2024.The patent's assignee for patent number 12117983 is Databricks Inc. (San Francis co, California,United States).News editors obtained the following quote from the background information suppli ed by the inventors:"A business utilizing machine learning models for decision making typically stores multiple versions ofmultiple models. As models are upda ted with new data or new techniques, the new versions are stored.One or more of the versions are utilized at any given time. Typically the model is accessed us ing a universalresource locator (e.g., URL) application programming interface ( e.g., API) endpoint including a modelserver, model name, and version number. Ad ding a new version requires manually creating a new modelservice with a new end point URL and configuring requesting services to access the new model service atthe new endpoint. This creates a problem wherein a substantial amount of manual maintenance is requiredfor model updating, increasing the chances of introduci ng errors in the process."
BusinessCyborgsDatabricks Inc.Emer ging TechnologiesMachine Learning
NETL
NSTL
