WEB APPLICATION ACCELERATION WITH PERSONALIZED CACHE OR PRERENDERING
Systems and methods are provided for predicting user browsing behavior and developing a personalized pre-fetching strategy. In some embodiments, a user equipment entity identifies web pages that are linked from a page being visited by a user, and, based on a user model, determines pre-fetch weights for the linked pages. The user equipment then pre-fetches the web pages with weights above a pre-fetch threshold. In some embodiments, the pre-fetch strategy is generated by or with the assistance of a separate network entity, which may be a distributed logical entity. Policies may also be enforced, such as avoiding pre-fetching while a user is on the telephone, or avoiding pre-fetching of pages containing video.
1 . A method carried out by a user equipment entity, the method comprising:
retrieving a selected web page in response to a user selection of the web page, wherein the selected web page includes links to a plurality of linked web pages;
identifying at least one current user activity based at least in part on a sensor in the user equipment;
determining respective pre-fetch weights for a plurality of the linked web pages, wherein the pre-fetch weight of a linked web page is based at least in part on a size of the linked web page;
determining a threshold weight based at least in part on the identified user activity; and
pre-fetching the linked web pages having a pre-fetch weight above the threshold weight.
2 . The method of claim 1 , wherein the sensor is an accelerometer, and wherein identifying at least one user activity includes determining that the user is engaged in physical activity.
3 . The method of claim 1 , wherein the UE entity includes telephone functionality, and wherein identifying at least one user activity includes determining that the user is speaking on the telephone.
4 . (canceled)
5 . The method of claim 1 , wherein the pre-fetch weights are based at least in part on the identified user activity.
6 . The method of claim 1 , wherein the pre-fetch weight of a linked web page is based at least in part on a probability of the user navigating to the linked web page.
7 . (canceled)
8 . The method of claim 1 , wherein the pre-fetch weight of a linked web page is based at least in part on both a size of the linked web page and a probability of the user navigating to the linked web page.
9 . The method of claim 1 , wherein the threshold weight is based at least in part on a level of network traffic.
10 . The method of claim 1 , wherein identifying at least one user activity includes determining whether the user is participating in a telephone call, wherein the pre-fetching is performed only after determining that the user is not participating in a telephone call.
11 . The method of claim 1 , wherein identifying at least one user activity includes determining whether the user is engaged in physical activity, wherein the pre-fetching is performed only after determining that the user is not engaged in physical activity.
12 . The method of claim 1 , further comprising rendering at least one of the pre-fetched web pages.
13 . A method carried out by at least one network entity, the method comprising:
receiving, from a user equipment entity, information identifying a web page visited by a user, wherein the visited web page includes links to a plurality of linked web pages;
retrieving a plurality of the linked web pages to determine the content of the respective linked web pages;
compiling from among the linked web pages a list of web pages to be pre-fetched, wherein the list of pages to be pre-fetched is based at least in part on the content of the respective linked web pages, wherein determining the content of the respective linked web pages includes determining a size of the respective linked web pages, wherein the list of pages to be pre-fetched is based at least in part on the sizes of the respective linked web pages; and
sending the list to the user equipment entity.
14 . (canceled)
15 . The method of claim 13 , wherein determining the content of the respective linked web pages includes determining whether the respective linked web pages include video, wherein the list of pages to be pre-fetched includes only web pages that do not include video.
16 . The method of claim 13 , further comprising:
for a plurality of the linked web pages, determining a probability of the user visiting the linked web page;
wherein the list of web pages to be pre-fetched is based at least in part on the probabilities that the user will visit the respective linked web pages.
17 . The method of claim 13 , wherein the list of web pages to be pre-fetched includes a plurality of pre-fetch weights associated with respective linked web pages on the list.
18 . A user equipment entity comprising a processor, a network interface, at least one sensor, and a non-transitory computer-readable medium, the medium storing instructions that, when executed by the processor, are operative:
to retrieve a selected web page over the network interface in response to a user selection of the web page, wherein the selected web page includes links to a plurality of linked web pages;
to identify at least one current user activity based at least in part on a sensor in the user equipment;
to determine respective pre-fetch weights for a plurality of the linked web pages, wherein the pre-fetch weight of a linked web page is based at least in part on a size of the linked web page;
to determine a threshold weight based at least in part on the identified user activity; and
to pre-fetch the linked web pages having a pre-fetch weight above the threshold weight.
19 . (canceled)
20 . (canceled)