Back to results
US 11,689,756 B2Granted
Systems and methods for time-shifted prefetching of predicted content for wireless users
AssigneeGeorgia Tech Research Corporation
InventorsRaghupathy Sivakumar, Shruti Lall
Life of this patent
Estimating the term…
Abstract
Systems and methods for time-shifted prefetching of predicted content for wireless users. Prefetching video data can include retrieving video data and feature data and generating a video candidate set including selected videos of the related video data. The method can further include determining predicted videos using a machine learning algorithm. The predicted videos can be videos of the video candidate set that are likely to be viewed by a user at a future time. The method can further include prefetching the predicted videos by downloading the predicted videos.
Claims19
A method of prefetching a video comprising:
- retrieving user data comprising video watch history data;
- retrieving related video data based, at least in part, on the video watch history data;
- retrieving feature data comprising data indicative of features of one or more videos of the video watch history data and the related video data;
- generating a video candidate set comprising one or more selected videos of the related video data based, at least in part, on the user data and the feature data;
- generating video candidate feature data comprising data indicative of features of one or more videos in the video candidate set;
- determining one or more predicted videos based, at least in part, on the video candidate feature data and a machine learning algorithm, wherein the machine learning algorithm comprises at least one of a k-nearest neighbor (KNN) classifier, a Gaussian Naive Bayes (GNB) classifier, a linear support vector machine (SVM) classifier, or a random forests (RF) classifier;
- and
- prefetching one or more of the predicted videos.
5 more elements
A method of prefetching a video from a content provider server comprising:
- retrieving user data comprising video watch history data;
- retrieving, from the content provider server, related video data based, at least in part, on the video watch history data;
- retrieving, from the user data and the video watch history data, feature data comprising data indicative of features of one or more videos of the video watch history data and the related video data;
- generating a video candidate set comprising one or more selected videos of the related video data based, at least in part, on the user data and the feature data;
- generating video candidate feature data comprising data indicative of features of one or more videos in the video candidate set;
- determining one or more predicted videos based, at least in part, on the video candidate feature data and a machine learning algorithm, wherein the machine learning algorithm comprises at least one of a k-nearest neighbor (KNN) classifier, a Gaussian Naive Bayes (GNB) classifier, a linear support vector machine (SVM) classifier, or a random forests (RF) classifier;
- and
- prefetching one or more of the predicted videos by downloading the one or more of the predicted videos from the content provider server;
- wherein the one or more predicted videos are a subset of videos of the video candidate set.
6 more elements
A system for prefetching a video comprising:
- one or more processors;
- and
- a memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, cause the system to:
- retrieve user data comprising video watch history data;
- retrieve related video data based, at least in part, on the video watch history data;
- retrieve feature data comprising data indicative of features of one or more videos of the video watch history data and the related video data;
- generate a video candidate set comprising one or more selected videos of the related video data based, at least in part, on the user data and the feature data;
- generate video candidate feature data comprising data indicative of features of one or more videos in the video candidate set:
- determine one or more predicted videos based, at least in part, on the video candidate feature data and a machine learning algorithm, wherein the machine learning algorithm comprises at least one of a k-nearest neighbor (KNN) classifier, a Gaussian Naive Bayes (GNB) classifier, a linear support vector machine (SVM) classifier, or a random forests (RF) classifier;
- and
- output instructions to prefetch one or more of the predicted videos.
8 more elements
Dependencies are inferred from the claim text.