US 12,462,109 B2
Contextual search in collaborative communications applications
Venkata Madhu Sravanth Kurumaddali, Redmond, WA (US); and Rashi Anand, Hyderabad (IN)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Appl. No. 17/759,169
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
PCT Filed Dec. 8, 2020, PCT No. PCT/US2020/063721
§ 371(c)(1), (2) Date Jul. 20, 2022,
PCT Pub. No. WO2021/154395, PCT Pub. Date Aug. 5, 2021.
Claims priority of application No. 2024793 (NL), filed on Jan. 30, 2020.
Prior Publication US 2022/0414129 A1, Dec. 29, 2022
Int. Cl. G06F 40/40 (2020.01); G06F 40/205 (2020.01)
CPC G06F 40/40 (2020.01) [G06F 40/205 (2020.01)] 17 Claims
OG exemplary drawing
 
1. On a computing device, a method comprising:
iteratively,
receiving user data comprising communications of a user from one or more collaborative communications applications,
analyzing the received user data to extract contextual information regarding the user, and
providing the contextual information regarding the user to a contextual information data store for the user,
wherein the contextual information regarding the user comprises an identified entity type/entity name pair, and wherein analyzing the received user data to extract the contextual information regarding the user further comprises
determining a confidence score regarding a confidence in a correctness of a relationship between an identified entity type of the identified entity type/entity name pair and an identified entity name of the identified entity type/entity name pair,
wherein the confidence score comprises a cumulative confidence score obtained from combining separate confidence scores associated with separate ones of a plurality of identifications of the identified entity type/entity name pair, and wherein the cumulative confidence score is compared to a threshold confidence score for providing the identified entity type/entity name pair to the contextual information data store, and
wherein providing the contextual information regarding the user to the contextual information data store for the user comprises providing the contextual information regarding the user to the contextual information data store for the user for storage based at least upon the cumulative confidence score meeting the threshold confidence score; and,
separately,
receiving a user input of a search query originating from within an originating collaborative communications application,
parsing the search query to identify a referential search term,
performing the search query with the previously stored contextual information regarding the user augmenting the referential search term by querying the contextual information data store for the user with the referential search term to identify previously stored contextual information regarding the user associated with the referential search term; and
sending the identified previously stored contextual information regarding the user to the originating collaborative communications application.