发明名称 |
Identifying relevant messages in a conversation graph |
摘要 |
A method, system, and non-transitory computer readable medium for identifying a relevant conversation. The method can include: identifying a conversation graph including identifiers of messages posted by a set of authoring accounts; identifying a relevance score for each authoring account; applying, by a computer processor, a first relevance filter to the conversation graph in order to modify the set of relevance scores; applying, by the computer processor and after applying the first relevance filter, a second relevance filter to the conversation graph in order to further modify the set of relevance scores; selecting, based on the set of relevance scores and after applying the second relevance filter, a subset of messages of the conversation graph for inclusion in the relevant conversation; and providing at least a portion of the relevant conversation to a client device. |
申请公布号 |
US9449050(B1) |
申请公布日期 |
2016.09.20 |
申请号 |
US201313770955 |
申请日期 |
2013.02.19 |
申请人 |
Twitter, Inc. |
发明人 |
Molina Marcel;Cohen Ross;Maxwell Kyle;Hood Stuart;Meverden Cara;Baik Coleen |
分类号 |
G06F15/16;G06F17/30 |
主分类号 |
G06F15/16 |
代理机构 |
Brakes Hughes Bellermann LLP |
代理人 |
Brakes Hughes Bellermann LLP |
主权项 |
1. A method for identifying a relevant conversation, comprising:
identifying a conversation graph comprising identifiers of a plurality of messages posted by a plurality of authoring accounts; identifying a plurality of relevance scores, wherein each of the plurality of relevance scores corresponds to an authoring account of the plurality of authoring accounts; applying, by a computer processor, a first relevance filter to the conversation graph in order to modify the plurality of relevance scores; applying, by the computer processor and after applying the first relevance filter, a second relevance filter to the conversation graph in order to further modify the plurality of relevance scores; selecting, based on the plurality of relevance scores and after applying the second relevance filter, a subset of messages of the conversation graph for inclusion in the relevant conversation; and providing at least a portion of the relevant conversation to a client device. |
地址 |
San Francisco CA US |