US 12,086,543 B2
Rule-based machine learning classifier creation and tracking platform for feedback text analysis
Sathia Prabhu Thirumal, Bothell, WA (US); Christopher Lawrence Laterza, Issaquah, WA (US); Manoj Kumar Rawat, Bellevue, WA (US); Karan Singh Rekhi, Sammamish, WA (US); Natarajan Arumugam, Bothell, WA (US); and Pranav Jayant Farswani, Seattle, WA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Jun. 23, 2021, as Appl. No. 17/356,122.
Application 17/356,122 is a continuation of application No. 17/322,720, filed on May 17, 2021.
Prior Publication US 2022/0366139 A1, Nov. 17, 2022
Int. Cl. G06F 40/279 (2020.01); G06F 16/33 (2019.01); G06F 16/338 (2019.01); G06F 16/35 (2019.01); G06N 20/00 (2019.01)
CPC G06F 40/279 (2020.01) [G06F 16/3331 (2019.01); G06F 16/338 (2019.01); G06F 16/35 (2019.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system for viewing search results in a database, comprising:
a processor; and
machine-readable media including instructions which, when executed by the processor, cause the processor to:
display in a user interface a plurality of topics relevant to the database, the plurality of topics including:
a keyword-based topic manually selected with a list of keywords by one first user to generate a keyword topic classifier that classifies an entry in the database as pertinent to the keyword-based topic by checking whether the entry contains a word in the list of keywords, wherein the first user is a subject matter expert regarding the keyword-based topic; and
a machine-learning-based topic associated with a machine-learning classifier, the machine-learning classifier generated based on a training data set that was automatically labelled by running the keyword topic classifier on a subset of entries in the database; and
for at least one displayed topic:
if the displayed topic is a keyword-based topic, perform a search of the database for the list of keywords and display the results of the search to a second user together with at least one of (1) an identifier of the first user, (2) a time that the keyword-based topic was manually selected, or (3) one or more database entry verbatim metrics along a timeline for the keyword topic classifier; and
if the displayed topic is a machine-learning-based topic, retrieve stored results of the machine-learning classifier and display the stored results to the second user together with at least one of (1) the identifier of the first user, (2) a time when the machine-learning-based topic was created, or (3) one or more database entry verbatim metrics along a timeline for the machine-learning classifier.