US 12,277,050 B2
Source knowledge graph building in context of artificial intelligence based generation of data connectors
Levon Korganyan, Tarzana, CA (US); Meel Velliste, San Ramon, CA (US); Emrah Diril, Myrtle Beach, SC (US); Sergey Numerov, Walnut Creek, CA (US); Ashutosh Chaurasia, Rajasthan (IN); Shreyans Shrimal, Telangana (IN); Varun Dhall, Uttar Pradesh (IN); and Ravi Sharda, Karnataka (IN)
Assigned to Fivetran Inc., Oakland, CA (US)
Filed by Fivetran Inc., Oakland, CA (US)
Filed on Oct. 18, 2023, as Appl. No. 18/489,769.
Claims priority of application No. 202341033100 (IN), filed on May 10, 2023.
Prior Publication US 2024/0378248 A1, Nov. 14, 2024
Int. Cl. G06F 16/00 (2019.01); G06F 8/60 (2018.01); G06F 11/30 (2006.01); G06F 11/3604 (2025.01); G06F 16/334 (2025.01); G06F 16/93 (2019.01); G06F 16/951 (2019.01); G06F 40/35 (2020.01)
CPC G06F 11/3616 (2013.01) [G06F 8/60 (2013.01); G06F 11/3006 (2013.01); G06F 16/3344 (2019.01); G06F 16/93 (2019.01); G06F 16/951 (2019.01); G06F 40/35 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for source knowledge generation, the method comprising:
identifying one or more external systems storing API (Application Programming Interface) documentation for accessing one or more data source systems;
crawling the one or more external systems to extract a plurality of documents, each document representing information describing APIs for accessing the one or more data source systems;
generating a plurality of vector representations by, for each document of the plurality of documents, providing the document to a neural network to generate a vector representation of the document;
generating an index that maps each vector representation to its respective document;
extracting information describing one or more aspects for a data connector by querying the index, receiving an indication of a set of matching documents, and extracting the information describing the data connector from the set of matching documents, the query corresponding to a particular type of data source; and
generating a connector representation based on the extracted information, wherein the connector representation is used for generating and deploying a new data connector for accessing data from a data source system of the particular type of data source.