公开(公告)号：US20210303602A1

公开(公告)日：2021-09-30

申请号：US17301797

申请日：2021-04-14

Applicant: Snap Inc.

Inventor： Fangqiu Han ,  Xinran He ,  Jie Luo ,  Yu Shi

IPC: G06F16/28 ,  H04L12/58 ,  G06F16/901

Abstract: Embodiments of the present disclosure relate generally to determining node embedding using multi-view graphs for analyzing electronic content.

公开(公告)号：US10664512B1

公开(公告)日：2020-05-26

申请号：US15895821

申请日：2018-02-13

Applicant: Snap Inc.

Inventor： Xinran He ,  Jie Luo ,  Sushobhan Nayak ,  Zhou Ren ,  Christophe Jacky Henri Van Gysel

IPC: G06F16/435 ,  G06Q50/00 ,  G06N20/00 ,  G06F16/951 ,  G06F16/2457

Abstract: Systems and methods are provided for generating training data from queries and user interactions associated with media collections related to the queries, and training a machine learning model using the generated training data to generate a trained machine learning model. The systems and methods further provide for receiving a prediction request comprising a query for relevant media collections, analyzing the query to determine query features, determining a plurality of media collections for the query, analyzing the plurality of media collections to determine media collection features for each media collection of the plurality of media collections, and generating, using the trained machine learning model, a semantic matching score for each media collection of the plurality of media collections based on matching the query features to the media collection features for each media collection of the plurality of media collections.

公开(公告)号：US11328008B2

公开(公告)日：2022-05-10

申请号：US16844300

申请日：2020-04-09

Applicant: Snap Inc.

Inventor： Xinran He ,  Jie Luo ,  Sushobhan Nayak ,  Zhou Ren ,  Christophe Jacky Henri Van Gysel

IPC: G06F16/435 ,  G06Q50/00 ,  G06N20/00 ,  G06F16/951 ,  G06F16/2457

Abstract: Systems and methods are provided for generating training data from queries and user interactions associated with media collections related to the queries, and training a machine learning model using the generated training data to generate a trained machine learning model. The systems and methods further provide for receiving a prediction request comprising a query for relevant media collections, analyzing the query to determine query features, determining a plurality of media collections for the query, analyzing the plurality of media collections to determine media collection features for each media collection of the plurality of media collections, and generating, using the trained machine learning model, a semantic matching score for each media collection of the plurality of media collections based on matching the query features to the media collection features for each media collection of the plurality of media collections.

公开(公告)号：US10997219B1

公开(公告)日：2021-05-04

申请号：US16024015

申请日：2018-06-29

Applicant: Snap Inc.

Inventor： Fangqiu Han ,  Xinran He ,  Jie Luo ,  Yu Shi

IPC: G06F16/28 ,  G06F16/901 ,  H04L12/58 ,  G06F3/0484

Abstract: Embodiments of the present disclosure relate generally to determining node embedding using multi-view graphs for analyzing electronic content.

公开(公告)号：US11636137B2

公开(公告)日：2023-04-25

申请号：US17301797

申请日：2021-04-14

Applicant: Snap Inc.

Inventor： Fangqiu Han ,  Xinran He ,  Jie Luo ,  Yu Shi

IPC: G06F16/28 ,  G06F16/901 ,  H04L51/52 ,  G06F3/0484

Abstract: Embodiments of the present disclosure relate generally to determining node embedding using multi-view graphs for analyzing electronic content.

公开(公告)号：US20200233893A1

公开(公告)日：2020-07-23

申请号：US16844300

申请日：2020-04-09

Applicant: Snap Inc.

Inventor： Xinran He ,  Jie Luo ,  Sushobhan Nayak ,  Zhou Ren ,  Christophe Jacky Henri Van Gyse

IPC: G06F16/435 ,  G06N20/00 ,  G06F16/951 ,  G06F16/2457 ,  G06Q50/00

Abstract: Systems and methods are provided for generating training data from queries and user interactions associated with media collections related to the queries, and training a machine learning model using the generated training data to generate a trained machine learning model. The systems and methods further provide for receiving a prediction request comprising a query for relevant media collections, analyzing the query to determine query features, determining a plurality of media collections for the query, analyzing the plurality of media collections to determine media collection features for each media collection of the plurality of media collections, and generating, using the trained machine learning model, a semantic matching score for each media collection of the plurality of media collections based on matching the query features to the media collection features for each media collection of the plurality of media collections.