US 11,657,415 B2
Net promoter score uplift for specific verbatim topic derived from user feedback
Manoj Kumar Rawat, Bellevue, WA (US); Gregory Lawrence Brake, Sammamish, WA (US); Christopher Lawrence Laterza, Issaquah, WA (US); Erfan Najmi, Renton, WA (US); Andres Felipe Salcedo, Seattle, WA (US); and Jin Luo, Kirkland, WA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by MICROSOFT TECHNOLOGY LICENSING, LLC, Redmond, WA (US)
Filed on May 10, 2021, as Appl. No. 17/315,393.
Prior Publication US 2022/0358529 A1, Nov. 10, 2022
Int. Cl. G06Q 30/02 (2023.01); G06Q 30/0203 (2023.01); G06F 16/35 (2019.01); G06N 20/00 (2019.01); G06F 40/30 (2020.01); G06Q 30/0201 (2023.01); G06Q 30/0601 (2023.01)
CPC G06Q 30/0203 (2013.01) [G06F 16/353 (2019.01); G06F 40/30 (2020.01); G06N 20/00 (2019.01); G06Q 30/0201 (2013.01); G06Q 30/0631 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A system for managing online user feedbacks for a product, the system comprising:
a processor; and
a memory, coupled to the processor and configured to store executable instructions that, when executed by the processor, cause the processor to:
receive, via a communication network, the online user feedbacks for the product from a plurality of users, the online user feedbacks being received through an online feedback management platform managing the online user feedbacks provided by the plurality of users through the communication network;
provide each online user feedback for the product to a machine learning model for performing semantic analysis on the online user feedbacks, performing semantic analysis including at least one of implementing optical character recognition to convert verbatim in the online user feedbacks into machine-encoded text, and identifying based on text in the online user feedbacks a plurality of topics;
receive as an output from the machine learning model the plurality of topics for the product from the online user feedbacks;
for each topic, automatically categorize each of the received online user feedbacks into one of a plurality of groups based on a rating score provided for the product in each online user feedback and the semantic analysis of each online user feedback for the product;
for each topic, automatically identify a subset of the online user feedbacks to be moved among the plurality of groups based on an assumption that one or more issues related to the topic are resolved;
determine a net promoter score (NPS) uplift for each topic based on a movement of the subset of online user feedbacks, wherein the NPS uplift measures an improvement in a first NPS for the product if the one or more issues related to the topic are resolved;
identify, from the plurality of topics included in the user feedbacks for the product, a priority topic based on the NPS uplift for each of the plurality of topics; and
prioritize the identified topic when resolving an issue related to the plurality of topics included in the online user feedbacks.