US 10,891,348 B1
Identifying relevant messages in a conversation graph
Ross Cohen, San Francisco, CA (US); Kyle Maxwell, San Francisco, CA (US); Stuart Hood, San Francisco, CA (US); Cara Meverden, San Francisco, CA (US); Coleen Baik, San Francisco, CA (US); and Marcel Molina, San Francisco, CA (US)
Assigned to Twitter, Inc., San Francisco, CA (US)
Filed by Twitter, Inc., San Francisco, CA (US)
Filed on Mar. 11, 2019, as Appl. No. 16/298,799.
Application 16/298,799 is a continuation of application No. 14/824,015, filed on Aug. 11, 2015, granted, now 10,229,218.
Application 14/824,015 is a continuation of application No. 13/736,634, filed on Jan. 8, 2013, granted, now 9,143,468, issued on Sep. 22, 2015.
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 15/16 (2006.01); G06F 17/50 (2006.01); H04L 12/58 (2006.01); G06F 16/955 (2019.01); G06F 3/0484 (2013.01)
CPC G06F 16/9558 (2019.01) [G06F 3/04842 (2013.01); H04L 51/16 (2013.01); H04L 51/32 (2013.01)] 26 Claims
OG exemplary drawing
 
1. A method for identifying relevant messages in a conversation graph, the method comprising:
transmitting, over a network, messages between a plurality of users on a messaging platform;
generating a conversation graph based on relationships between the messages, the conversation graph including a plurality of messages related to a conversation, the plurality of messages including a root message and one or more reply messages connected to the root message;
marking a subset of the plurality of messages of the conversation graph as relevant to the conversation, including:
identifying a topic based on a semantic analysis of at least one of the plurality of messages of the conversation graph;
determining that a user account of a message in the conversation graph is relevant to the topic; and
marking the message as relevant;
transmitting, over the network, digital information to render the subset of the plurality of messages on a user interface of a computing device.