US 12,411,663 B2
Notebook for navigating code using machine learning and flow analysis
Brian Paul Kroth, Madison, WI (US); and Jordan Joseph Henkel, Madison, WI (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Oct. 5, 2023, as Appl. No. 18/481,916.
Application 18/481,916 is a continuation of application No. 17/099,720, filed on Nov. 16, 2020, granted, now 11,816,456.
Prior Publication US 2024/0028307 A1, Jan. 25, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 8/33 (2018.01); G06F 8/30 (2018.01); G06F 8/41 (2018.01); G06F 8/75 (2018.01); G06F 9/445 (2018.01); G06F 9/451 (2018.01); G06F 9/54 (2006.01); G06F 16/23 (2019.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01)
CPC G06F 8/33 (2013.01) [G06F 8/30 (2013.01); G06F 8/44 (2013.01); G06F 8/75 (2013.01); G06F 9/44526 (2013.01); G06F 9/451 (2018.02); G06F 9/541 (2013.01); G06F 16/2379 (2019.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
presenting a user interface (UI) of a code notebook, the UI comprising a query window with a representation of a program source code;
receiving a code query from a user in the query window, the code query including a code variable;
converting the code variable into a first vector, wherein the first vector is used to identify a latent space of vectors;
comparing a proximity of the first vector of the code variable to a second vector indicative of text different from the code variable;
receiving a query result that is semantically equivalent to the code query based on the comparison and also the latent space of vectors, wherein the latent space of vectors is indicative of a threshold proximity of the code query to the query result in the program source code; and
showing the query result in the representation of the program source code in the UI of the code notebook.