公开(公告)号：US20250077538A1

公开(公告)日：2025-03-06

申请号：US18241028

申请日：2023-08-31

Applicant: Microsoft Technology Licensing, LLC

Inventor： Shaily Jignesh FOZDAR ,  David Joseph DONAHUE ,  Fang LIU ,  Noelle Yanhui LI ,  Abhishek NARAIN ,  Irene Rogan SHAFFER ,  Wee Hyong TOK ,  Ehimwenma NOSAKHARE ,  Vivek GUPTA ,  Gust VERBRUGGEN ,  Vu Minh LE ,  Jordan Joseph HENKEL ,  Avrilia FLORATOU ,  Joyce Yu CAHOON ,  Richard ANARFI ,  Jason Wang ,  Daniel MUÑOZ HUERTA ,  Yan Qiu

IPC: G06F16/25 ,  G06F16/242

Abstract: A computer-implemented method for performing natural language-based data integration includes causing execution of a data integration application on a remote device via a network and causing surfacing of a GUI corresponding to the data integration application on a display of the remote device. The method includes receiving, via the GUI, a natural language input representing a data integration task, generating, via an LLM, a set of ordered activities corresponding to the data integration task represented by the natural language input, and selecting, via the LLM, one or more APIs for performing each activity within the set of ordered activities. The method also includes generating a data pipeline based on the set of ordered activities and the API(s) for performing each activity, as well as back-translating the data pipeline to a desired data format for execution by the data integration application.

公开(公告)号：US20250124022A1

公开(公告)日：2025-04-17

申请号：US18487009

申请日：2023-10-13

Applicant: Microsoft Technology Licensing, LLC

Inventor： Reshmi GHOSH ,  Shaily Jignesh FOZDAR ,  Tianyi YAO ,  Huitian JIAO ,  H M Sajjad HOSSAIN ,  Jiangning CHEN ,  Dario Kikuchi BERNAL ,  Tianwei CHEN ,  Irene Rogan SHAFFER ,  Zhongzhong LI ,  Junlin WU ,  Dongxiao YANG ,  Weiwei SHI ,  Yuanquan HU ,  Genglin HUANG ,  Sheikh Sadid Al HASAN

IPC: G06F16/242 ,  G06F16/21

Abstract: A system classifies an intent based on a received prompt and identifies system-provided prompts based on the intent. The system inputs the system-provided prompts and the received prompt to a generative artificial intelligence model, wherein the generative artificial intelligence model outputs form items corresponding to the received prompt and the system-provided prompts, the form items including form prompt items and form response items. The system converts the form items into the renderable form presentable in a user interface, wherein the renderable form includes the form prompt items and the form response items.

公开(公告)号：US20250086202A1

公开(公告)日：2025-03-13

申请号：US18466524

申请日：2023-09-13

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yiwen ZHU ,  Subramaniam Venkatraman KRISHNAN ,  Weihan TANG ,  Tengfei HUANG ,  Rui FANG ,  Rahul Kumar CHALLAPALLI ,  Mo LIU ,  Long TIAN ,  Karuna Sagar KRISHNA ,  Estera Zaneta KOT ,  Xin HE ,  Ashit R. GOSALIA ,  Dario Kikuchi BERNAL ,  Aditya LAKRA ,  Arshdeep SEKHON ,  Sule KAHRAMAN ,  Carlo Aldo CURINO ,  Brian Paul KROTH ,  Rathijit SEN ,  Andreas Christian MUELLER ,  Shaily Jignesh FOZDAR ,  Dhruv Harendra RELWANI ,  Xiang LI ,  Sergiy MATUSEVYCH

IPC: G06F16/28 ,  G06F11/34 ,  G06F16/2455

Abstract: Systems, methods and computer-readable memory devices are provided for greater efficiency in the configuration of a database cluster for performing a query workload. A database cluster configuration system is provided that includes a database cluster comprising one or more compute resources configured to perform database queries. A query workload comprising a plurality of queries is received. An initial workload-level configuration is applied. For each query of the query workload, a query-level configuration is generated using a query configuration model corresponding to each query in a contextual Bayesian optimization with centroid learning while also leveraging the query plan for each executing query for query characterization and including application of virtual operators. Query events are collected and used to update the corresponding query configuration model. The workload-level configuration is updated based on the query events and cached for use during a subsequent execution of the workload.