US 11,704,371 B1
User centric topics for topic suggestions
David Timothy Chan, Sammamish, WA (US); Dmitriy Meyerzon, Bellevue, WA (US); Sebastian Johannes Blohm, Munich (DE); Anita Rajan, Redmond, WA (US); and Ravi Kumar Bikkula, Sammamish, WA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Feb. 7, 2022, as Appl. No. 17/666,287.
Int. Cl. G06F 16/30 (2019.01); G06F 16/907 (2019.01); G06F 16/9038 (2019.01); G06F 16/9035 (2019.01); G06F 16/903 (2019.01); G06F 16/00 (2019.01)
CPC G06F 16/907 (2019.01) [G06F 16/9035 (2019.01); G06F 16/9038 (2019.01); G06F 16/90344 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A data processing system comprising:
a processor; and
a machine-readable medium storing executable instructions that, when executed, cause the processor to perform operations comprising:
receiving a request for user-centric topic recommendations from a computing device of a user in response to a user input in an application indicating that the user is attempting to assign a tag to a first content item in the application, the request indicating a requested number of topic recommendations, the tag representing a topic of the first content item;
obtaining a first set of user-centric topic recommendations from a first topic datastore based on a relevance ranking assigned to each of the topic recommendations, the relevance ranking indicating how relevant a respective topic recommendation is likely to be to the user, and the first topic datastore comprising user-centric topic information extracted from electronic content created by the user by analyzing the electronic content with one or more first machine learning models;
correlating the first set of user-centric topics with a set of organization-wide topics of an organization with which the user is associated;
discarding any topics from the first set of user-centric topic which are not present in the set of organization-wide topics;
providing the first set of user-centric topic recommendations to the computing device of the user;
causing the computing device of the user to display the first set of user-centric topic recommendations;
receiving one or more second requests for user-centric topic recommendations from the computing device of the user, each of the one or more second requests comprising a query string, the query string being incrementally updated in each of the one or more second requests;
obtaining one or more second sets of user-centric topic recommendations from the first topic datastore based on the query string and the relevance ranking, the one or more second sets of user-centric topic recommendations further refining the user-centric topic recommendations;
providing the one or more second sets of user-centric topic recommendations to the computing device of the user; and
causing the computing device of the user to dynamically display the one or more second sets of user-centric topic recommendations.