US 12,333,499 B2
Rules-based generation of transmissions to connect members of an organization
Siu Wan Surlina Yin, London (GB); and Ryan Patrick, Seaton (GB)
Assigned to Oracle International Corporation, Redwood Shores, CA (US)
Filed by Oracle International Corporation, Redwood Shores, CA (US)
Filed on May 19, 2023, as Appl. No. 18/320,802.
Application 18/320,802 is a continuation of application No. 17/038,872, filed on Sep. 30, 2020, granted, now 11,694,163.
Prior Publication US 2023/0289732 A1, Sep. 14, 2023
Int. Cl. G06Q 10/105 (2023.01); G06N 3/04 (2023.01); G06N 20/00 (2019.01); G06Q 10/0639 (2023.01)
CPC G06Q 10/105 (2013.01) [G06N 3/04 (2013.01); G06N 20/00 (2019.01); G06Q 10/06393 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A non-transitory computer readable medium comprising instructions which, when executed by one or more hardware processors, causes performance of operations comprising:
obtaining sets of training data, the sets of training data including a particular set of training data comprising:
a particular set of one or more interactions; and
a label comprising at least one of:
an interaction type corresponding to the particular set of one or more interactions;
a topic corresponding to the particular set of one or more interactions; or
an identification of one or more members of an organization that are involved in the particular set of one or more interactions;
training a machine learning model based on the sets of training data to yield a trained machine learning model; and
applying the trained machine learning model to observed data comprising a target set of one or more interactions, to determine a prediction comprising at least one of: (a) a first interaction type corresponding to the target set of one or more interactions, (b) a first topic corresponding to the target set of one or more interactions, or (c) a first member, of an organization, involved in the target set of one or more interactions;
computing a connection score between the first member and the first topic based on a set of different types of interactions by the first member involving the first topic, wherein computing the connection score includes applying a set of weights to the set of different types of interactions;
obtaining feedback regarding the first member, the feedback indicating whether the first member is knowledgeable, helpful, or otherwise useful to one or more other members on matters related to the first topic; and
adjusting the set of weights assigned to the set of different types of interactions based on the feedback, wherein adjusting the set of weights includes increasing one or more weights, of the set of weights, associated with one or more interaction types, of the set of different types of interactions, that correlate with positive feedback.