Systems and methods for reducing digital video latency
Examples of the systems and methods described herein relate to reducing latency issues associated with playing online digital video on client devices. An example method includes: determining a likelihood that a user will trigger presentment of video content within a portion of digital content, and when the likelihood is determined to exceed a threshold, obtaining a video tag that identifies the video content or caching a portion of the video content prior to presentment of the video content.
1 . A method comprising:
obtaining activity data indicative of an interaction with a first digital content being displayed at a client device, wherein the client device displays a plurality of digital content;
providing the activity data as input into a machine learning model, wherein the machine learning model is trained upon historical activity data;
determining, based upon the output of the machine learning model, a first likelihood of interaction with a second digital content, and a second likelihood of interaction with a third digital content;
responsive to determining that the first likelihood of interaction or second likelihood of interaction exceeds a threshold, performing acts comprising at least one of:
causing the client device to cache at least a portion of the second digital content prior to presentation of the second digital content at the client device;
causing the client device to cache at least a portion of the third digital content prior to presentation of the third digital content at the client device; or
causing the client device to cache at least a portion of the second digital content and a portion of the third digital content prior to presentation of the second digital content and the third digital content at the client device.
2 . The method of claim 1 , wherein the output of the machine learning model is indicative of a likelihood of interaction with digital content that is not included in the first portion of digital content.
3 . The method of claim 1 , wherein the first digital content, the second digital content, and the third digital content comprise a web page or digital content displayed within an interface of a mobile application executing on the client device.
4 . The method of claim 1 , wherein the activity data comprises at least one of: a distance between the first digital content and the second digital content as displayed at the client device, a distance between the first digital content and the third digital content as displayed at the client device, a velocity at which the user scrolls between digital content, a viewing history of the user, a view history of other users, a duration of the user's Internet session, and an Internet browser history.
5 . The method of claim 1 , wherein the historical activity data comprises: a distance between the first digital content and the second digital content when a web page comprising the first digital content and second digital content is rendered, a distance between the first digital content and the third digital content when a web page comprising the first digital content and third digital content is rendered, a historical velocity at which the user scrolls between digital content, a viewing history of the user, a view history of other users, an average duration of the user's Internet session, and an Internet browser history.
6 . The method of claim 1 , wherein at least one of the first digital content, the second visual content, and the third digital content comprise video content.
7 . The method of claim 1 , wherein at the first digital content is a web page and at least one of the second digital content and the third digital content comprises video content.
8 . The method of claim 1 , accessing at least one of the cached portion of the second digital content prior to the client device displaying the second digital content or the cached portion of the third digital content prior to the client device displaying the third digital content.
9 . The method of claim 8 , wherein the cached portion of the second digital content or the cached portion of the third digital content is at least a portion of a video advertisement.
10 . The method of claim 1 , further comprising:
causing the client device to display the second content and not display the third content at the client device based upon the output of the machine learning model.
11 . The method of claim 1 , further comprising:
causing the client device to obtain a video tag that identifies video content based upon the first digital content;
causing the client device to provide the video tag to a video server, wherein responsive to receiving the video tag, the video server provides the video content to the client device, wherein responsive to receipt of the video content, the client device caches at least the portion of the video content prior to presentation of the video content within the second digital content or the third digital content.
12 . A server computing device comprising:
at least one processor; and
memory that stores instructions that, when executed by the processor, cause the processor to perform acts comprising:
obtaining activity data indicative of an interaction with a first digital content being displayed at a client device, wherein the client device displays a plurality of digital content;
providing the activity data as input into a machine learning model, wherein the machine learning model is trained upon historical activity data;
determining, based upon the output of the machine learning model, a first likelihood of interaction with a second digital content, and a second likelihood of interaction with a third digital content;
responsive to determining that the first likelihood of interaction or second likelihood of interaction exceeds a threshold, performing acts comprising at least one of:
causing the client device to cache at least a portion of the second digital content prior to presentation of the second digital content at the client device;
causing the client device to cache at least a portion of the third digital content prior to presentation of the third digital content at the client device; or
causing the client device to cache at least a portion of the second digital content and a portion of the third digital content prior to presentation of the second digital content and the third digital content at the client device.
13 . The server computing device of claim 12 , wherein the first digital content, the second digital content, and the third digital content comprise a web page or digital content displayed within an interface of a mobile application executing on the client device.
14 . The server computing device of claim 12 , wherein the activity data comprises at least one of: a distance between the first digital content and the second digital content as displayed at the client device, a distance between the first digital content and the third digital content as displayed at the client device, a velocity at which the user scrolls between digital content, a viewing history of the user, a view history of other users, a duration of the user's Internet session, and an Internet browser history.
15 . The server computing device of claim 12 , wherein at least one of the first digital content, the second visual content, and the third digital content comprise video content.
16 . The server device of claim 12 , wherein at least one of the first visual content and the second visual content comprise video content.
17 . The server device of claim 12 , accessing at least one of the cached portion of the second digital content prior to the client device displaying the second digital content or the cached portion of the third digital content prior to the client device displaying the third digital content.
18 . The server device of claim 12 , further comprising:
causing the client device to display the second content and not display the third content at the client device based upon the output of the machine learning model.
19 . The server device of claim 12 , further comprising:
causing the client device to obtain a video tag that identifies video content based upon the first digital content;
causing the client device to provide the video tag to a video server, wherein responsive to receiving the video tag, the video server provides the video content to the client device, wherein responsive to receipt of the video content, the client device caches at least the portion of the video content prior to presentation of the video content within the second digital content or the third digital content.
20 . A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processing system of a client device and including a processor, facilitate performance of operations, the operations comprising:
obtaining activity data indicative of an interaction with a first digital content being displayed at a client device, wherein the client device displays a plurality of digital content;
providing the activity data as input into a machine learning model, wherein the machine learning model is trained upon historical activity data;
determining, based upon the output of the machine learning model, a first likelihood of interaction with a second digital content, and a second likelihood of interaction with a third digital content;
responsive to determining that the first likelihood of interaction or second likelihood of interaction exceeds a threshold, performing acts comprising at least one of:
causing the client device to cache at least a portion of the second digital content prior to presentation of the second digital content at the client device;
causing the client device to cache at least a portion of the third digital content prior to presentation of the third digital content at the client device; or
causing the client device to cache at least a portion of the second digital content and a portion of the third digital content prior to presentation of the second digital content and the third digital content at the client device.