US 11,921,763 B2
Methods and systems to parse a software component search query to enable multi entity search
Ashok Balasubramanian, Chennai (IN); Karthikeyan Krishnaswamy Raja, Chennai (IN); and Arul Reagan S, Chengalpattu District (IN)
Assigned to Open Weaver Inc., Miami, FL (US)
Filed by Open Weaver Inc., Miami, FL (US)
Filed on Feb. 23, 2022, as Appl. No. 17/678,920.
Claims priority of provisional application 63/153,220, filed on Feb. 24, 2021.
Prior Publication US 2022/0269706 A1, Aug. 25, 2022
Int. Cl. G06F 16/00 (2019.01); G06F 16/33 (2019.01); G06F 16/335 (2019.01)
CPC G06F 16/3335 (2019.01) [G06F 16/3334 (2019.01); G06F 16/335 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system for parsing a software component search query to enable multi entity searches, the system comprising:
one or more processors and memory storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
filtering a search query for a plurality of unwanted characters;
applying a software dictionary of terms to correct a spelling of the search query;
training a plurality of machine learning models using respective sets of data;
applying a first machine learning model of the plurality of machine learning models to remove one or more filter terms from the search query;
parsing the search query to extract a plurality of entities;
categorizing a first entity of the plurality of entities as natural language, categorizing a second entity of the plurality of entities as programming language, and categorizing a third entity of the plurality of entities as keyword text;
applying a second machine learning model of the plurality of machine learning models to the first entity categorized as natural language to enhance one or more search characteristics of the first entity categorized as natural language;
applying a third machine learning model of the plurality of machine learning models to the second entity categorized as programming language to enhance one or more search characteristics of the second entity categorized as programming language;
applying a fourth machine learning model of the plurality of machine learning models to the third entity categorized as keyword text to enhance one or more search characteristics of the third entity categorized as keyword text;
consolidating the plurality of entities into an enhanced search query comprising the one or more search characteristics of the first entity, the one or more search characteristics of the second entity, and the one or more search characteristics of the third entity;
applying a fifth machine learning model of the plurality of machine learning models to determine one or more intended sources for the enhanced search query; and
searching the one or more intended sources using the enhanced search query to generate and present a plurality of results pertaining to the enhanced search query.