Optimize and generate a personalized content item for display during web page load time
Provided are techniques for optimizing and generating a personalized content item for display during web page load time. The web page load time is predicted, and a list of personalized content items with corresponding ranks is received. In response to determining that a top ranked personalized content item of the list of personalized content items does not run within the web page load time, the web page load time is split into a split generation time and a split run time. In response to determining that the split generation time is less than a threshold, a new personalized content item is generated that runs within the split run time and displayed. In response to determining that the split generation time is equal to or greater than the threshold, an existing personalized content item is summarized to run within the split run time and displayed.
1 . A computer-implemented method, comprising operations for:
predicting a web page load time of a web page selected by a user based on one or more real time load factors that are selected from a group consisting of a user's traffic, a server load time, resource sizes, and web content availability;
receiving a list of personalized content items with corresponding ranks; and
in response to determining that a top ranked personalized content item of the list of personalized content items does not run within the web page load time,
splitting the web page load time into a split generation time and a split run time;
in response to determining that the split generation time is less than a threshold,
generating a new personalized content item based on user preferences of the user that runs within the split run time; and
displaying the new personalized content item during the split run time while the web page is loading; and
in response to determining that the split generation time is equal to or greater than the threshold,
summarizing an existing personalized content item to run within the split run time; and
displaying the summarized personalized content item during the split run time while the web page is loading.
2 . The computer-implemented method of claim 1 , wherein the web page and historical web page load time for that web page are input to a Deep Neural Network (DNN), which outputs the predicted web page load time.
3 . The computer-implemented method of claim 1 , wherein the operations further comprise:
sending user data and the predicted web page load time to an edge server that stores a plurality of personalized content items, wherein the list of personalized content items are selected from the plurality of personalized content items and returned by the edge server.
4 . The computer-implemented method of claim 1 , wherein the list of personalized content items are input into a Deep Neural Network (DNN), which outputs the list of personalized content items with the corresponding ranks.
5 . The computer-implemented method of claim 1 , wherein user interests are input into a Conditional Generative Adversarial Network, which outputs the new personalized content item.
6 . The computer-implemented method of claim 1 , wherein the existing personalized content item is input into a Conditional Generative Adversarial Network, which outputs the summarized personalized content item.
7 . The computer-implemented method of claim 1 , wherein the operations further comprise:
in response to determining that a top ranked personalized content item of the list of personalized content items runs within the web page load time, displaying the top ranked personalized content item.
8 . A computer program product, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform operations for:
predicting a web page load time of a web page selected by a user based on one or more real time load factors that are selected from a group consisting of a user's traffic, a server load time, resource sizes, and web content availability;
receiving a list of personalized content items with corresponding ranks; and
in response to determining that a top ranked personalized content item of the list of personalized content items does not run within the web page load time,
splitting the web page load time into a split generation time and a split run time;
in response to determining that the split generation time is less than a threshold,
generating a new personalized content item based on user preferences of the user that runs within the split run time; and
displaying the new personalized content item during the split run time while the web page is loading; and
in response to determining that the split generation time is equal to or greater than the threshold,
summarizing an existing personalized content item to run within the split run time; and
displaying the summarized personalized content item during the split run time while the web page is loading.
9 . The computer program product of claim 8 , wherein the web page and historical web page load time for that web page are input to a Deep Neural Network (DNN), which outputs the predicted web page load time.
10 . The computer program product of claim 8 , wherein the program instructions are executable by the processor to cause the processor to perform operations for:
sending user data and the predicted web page load time to an edge server that stores a plurality of personalized content items, wherein the list of personalized content items are selected from the plurality of personalized content items and returned by the edge server.
11 . The computer program product of claim 8 , wherein the list of personalized content items are input into a Deep Neural Network (DNN), which outputs the list of personalized content items with the corresponding ranks.
12 . The computer program product of claim 8 , wherein user interests are input into a Conditional Generative Adversarial Network, which outputs the new personalized content item.
13 . The computer program product of claim 8 , wherein the existing personalized content item is input into a Conditional Generative Adversarial Network, which outputs the summarized personalized content item.
14 . The computer program product of claim 8 , wherein the program instructions are executable by the processor to cause the processor to perform operations for:
in response to determining that a top ranked personalized content item of the list of personalized content items runs within the web page load time, displaying the top ranked personalized content item.
15 . A computer system, comprising:
one or more processors, one or more computer-readable memories and one or more computer-readable, tangible storage devices; and
program instructions, stored on at least one of the one or more computer-readable, tangible storage devices for execution by at least one of the one or more processors via at least one of the one or more computer-readable memories, to perform operations comprising:
predicting a web page load time of a web page selected by a user based on one or more real time load factors that are selected from a group consisting of a user's traffic, a server load time, resource sizes, and web content availability;
receiving a list of personalized content items with corresponding ranks; and
in response to determining that a top ranked personalized content item of the list of personalized content items does not run within the web page load time,
splitting the web page load time into a split generation time and a split run time;
in response to determining that the split generation time is less than a threshold,
generating a new personalized content item based on user preferences of the user that runs within the split run time; and
displaying the new personalized content item during the split run time while the web page is loading; and
in response to determining that the split generation time is equal to or greater than the threshold,
summarizing an existing personalized content item to run within the split run time; and
displaying the summarized personalized content item during the split run time while the web page is loading.
16 . The computer system of claim 15 , wherein the web page and historical web page load time for that web page are input to a Deep Neural Network (DNN), which outputs the predicted web page load time.
17 . The computer system of claim 15 , wherein the program instructions further perform operations comprising:
sending user data and the predicted web page load time to an edge server that stores a plurality of personalized content items, wherein the list of personalized content items are selected from the plurality of personalized content items and returned by the edge server.
18 . The computer system of claim 15 , wherein the list of personalized content items are input into a Deep Neural Network (DNN), which outputs the list of personalized content items with the corresponding ranks.
19 . The computer system of claim 15 , wherein user interests are input into a Conditional Generative Adversarial Network, which outputs the new personalized content item.
20 . The computer system of claim 15 , wherein the existing personalized content item is input into a Conditional Generative Adversarial Network, which outputs the summarized personalized content item.