Brian Thomas Morrison

US Patent:

20230114158, Apr 13, 2023

Filed:

Oct 8, 2021

Appl. No.:

17/497224

Inventors:

- Santa Monica CA, US
Darshana Umakanth - Culver City CA, US
Yuchong Luo - Beijing, CN
Brian T. Morrison - Burien WA, US
Lena Bareket - Culver City CA, US
Huimin Chen - Los Angeles CA, US
Carlos Sandoval - Los Angeles CA, US
Brian Burkhart - Seattle WA, US
David Jung - Seattle WA, US
Brandon Lonac - Edmonds WA, US
Bo Liu - Beijing, CN

International Classification:

H04N 21/482
H04N 21/437

Abstract:

In some embodiments, a method receives a request for an interface. A configuration for the interface includes a plurality of slots that are associated with a plurality of collection pools, wherein each collection pool is configurable with a ranking strategy. The method determines a collection pool for a slot in the interface where the collection pool is associated with a plurality of collections. A collection is received for the slot. The collection is determined by ranking the plurality of collections using a ranking strategy for the collection pool to generate a ranking of the plurality of collections. The method outputs the collection for the collection pool for display in the slot of the interface.

US Patent:

20210374178, Dec 2, 2021

Filed:

Oct 6, 2020

Appl. No.:

17/064286

Inventors:

- Santa Monica CA, US
Yunsheng Jiang - Beijing, CN
Xiaohui Xie - Beijing, CN
Brian Morrison - Seattle WA, US
Jiarui Yang - Beijing, CN
Christopher Russell Kehler - Seattle WA, US

International Classification:

G06F 16/735
G06F 16/2457
G06N 3/04
G06N 3/08

Abstract:

In some embodiments, a method selects a sequence of programs watched by a user account. The method calculates a first set of weights based on comparing content of the sequence of programs to content of a target program and calculates a second set of weights based on an order of the sequence of the programs and the first of weights. The first set of weights and the second set of weights are applied to the sequence of programs to generate a prediction of a similarity of the sequence of programs to the target program. Then, the method outputs the prediction of the similarity for use in determining a recommendation for the user account.