US 12,216,657 B2
Contextual searches in software development environments
Jeffrey Bisti, New Paltz, NY (US); Justin Paul Largo, Raleigh, NC (US); and Colton Jarrett Cox, Wappingers Falls, NY (US)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed on Mar. 16, 2023, as Appl. No. 18/184,751.
Prior Publication US 2024/0311375 A1, Sep. 19, 2024
Int. Cl. G06F 16/2455 (2019.01); G06F 8/20 (2018.01); G06F 8/41 (2018.01)
CPC G06F 16/2455 (2019.01) [G06F 8/20 (2013.01); G06F 8/427 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A computer-implemented method for identifying content relevant to a task being performed within a software development environment (SDE), the computer-implemented method comprising:
receiving a search query from a user in the SDE;
obtaining activity data and prior interactions of the SDE from the SDE;
training one or more machine learning models using the activity data, the SDE's prior interactions, and tasks known to the one or more machine learning models through the SDE's prior interactions;
integrating the one or more trained machine learning models in the SDE;
determining a context for the received search query and whether the received search query has sequential context using the one or more trained machine learning models;
predicting one or more steps in a programming objective in the activity data and a subsequent step in the programming objective using the one or more trained machine learning models upon determining that the received search query has sequential context;
introducing the determined context, as well as the predicted one or more steps and the subsequent step in the programming objective, to the received search query using the one or more trained machine learning models to modify search parameters of the received search query;
performing a search using a search engine integrated with the SDE, using the modified search parameters of the received search query; and
displaying a list of search results in the SDE, wherein the search results are weighted using the one or more trained machine learning models based on the determined context, as well as the predicted one or more steps and the subsequent step in the programming objective.