Adaptive content deployment
Systems and methods presented herein provide for adaptive content delivery. In one embodiment, a system includes a repository operable to store a plurality of web components, and a database operable to store identifiers of a plurality of users. The system also includes a machine learning module operable to: generate a model of computing device interactions of the plurality of the users based on the stored identifiers of the plurality of users; monitor a computing device interaction of a first of the plurality of users; process the computing device interaction of the first user through the model; and predict a format of web component delivery desired by the user based on the model. A formatter may be operable to retrieve a portion of the web components from the repository, and to automatically format the retrieved web components for the first user based on the predicted format of web component delivery.
1. A server based system, comprising:
a repository operable to store a plurality of web components;
a database operable to store identifiers of a plurality of users;
a machine learning module operable to generate a model of computing device interactions of the plurality of the users based on the stored identifiers of the plurality of users, to monitor a computing device interaction of a first of the plurality of users, to process the computing device interaction of the first user through the model, and to predict a format of web component delivery desired by the user based on the model; and
a formatter operable to retrieve a portion of the web components from the repository, and to automatically format the retrieved web components for the first user based on the predicted format of web component delivery,
wherein the machine learning module is further operable to process the computing device interaction of the first user via a regression analysis, and wherein the machine learning module is further operable to enhance a prediction of the format of web component delivery desired by the user via said regression analysis of subsequent computing device interactions of the first user.
2. The system of claim 1 , wherein:
the web components comprise one or more of an image, text, video, audio, a mapping module, an icon, or a web based application.
3. The system of claim 1 , wherein:
the machine learning module is further operable to update the model based on subsequent computing device interactions of the plurality of users.
4. The system of claim 1 , wherein:
the formatter is further operable to change the format of the web component delivery based on the enhanced prediction.
5. The system of claim 1 , further comprising:
a media distributer operable to deliver the formatted web components to the first user via a web-based application,
wherein the formatter is further operable to manipulate individual pixels of the formatted web components in the web-based application.
6. A method operable with a web server, comprising:
storing a plurality of web components in a repository;
storing identifiers of a plurality of users in a database;
machine learning a model of computing device interactions of the plurality of the users based on the stored identifiers of the plurality of users;
monitoring a computing device interaction of a first of the plurality of users;
processing the computing device interaction of the first user through the model via a regression analysis;
predicting a format of web component delivery desired by the user based on the model;
retrieving a portion of the web components from the repository;
automatically formatting the retrieved web components for the first user based on the predicted format of web component delivery; and
enhancing a prediction of the format of web component delivery desired by the user via said regression analysis of subsequent computing device interactions of the first user.
7. The method of claim 6 , wherein:
the web components comprise one or more of an image, text, video, audio, a mapping module, an icon, or a web based application.
8. The method of claim 6 , further comprising:
updating the model based on subsequent computing device interactions of the plurality of users.
9. The method of claim 6 , further comprising:
changing the format of the web component delivery based on the enhanced prediction.
10. The method of claim 6 , further comprising:
manipulating individual pixels of the formatted web components in the web-based application.
11. A non-transitory computer readable medium comprising instructions that, when executed by a processor, direct the processor to:
store a plurality of web components in a repository;
store identifiers of a plurality of users in a database;
machine learn a model of computing device interactions of the plurality of the users based on the stored identifiers of the plurality of users;
monitor a computing device interaction of a first of the plurality of users;
process the computing device interaction of the first user through the model via a regression analysis;
predict a format of web component delivery desired by the user based on the model;
retrieve a portion of the web components from the repository;
automatically format the retrieved web components for the first user based on the predicted format of web component delivery; and
enhance a prediction of the format of web component delivery desired by the user via said regression analysis of subsequent computing device interactions of the first user.
12. The non-transitory computer readable medium of claim 11 , wherein:
the web components comprise one or more of an image, text, video, audio, a mapping module, an icon, or a web based application.
13. The non-transitory computer readable medium of claim 11 , further comprising instructions that direct the processor to:
update the model based on subsequent computing device interactions of the plurality of users.
14. The non-transitory computer readable medium of claim 11 , further comprising instructions that direct the processor to:
change the format of the web component delivery based on the enhanced prediction.