Artificial intelligence system for optimizing network-accessible content

    公开(公告)号:US11126785B1

    公开(公告)日:2021-09-21

    申请号:US15436359

    申请日:2017-02-17

    Abstract: An optimal combination of content items may be determined and served to increase the likelihood of a predefined user interaction. A user can request content which may include an entity (such as a web page, document, advertisement, and the like) that has multiple components through which content items may be provided. For example, a web page may include multiple slots where content items may be displayed on the web page. Each component may be associated with multiple possible content items, resulting in many combinations of layouts for an entity. A content server may determine which layout to provide using a content selection model that is weighted based on a likelihood of groupings of content items resulting in a user interaction that satisfies a success condition (e.g., selecting a hyperlink, selecting a content item, initiating a transaction, etc.).

    Optimizing content engagement with imposed content constraints

    公开(公告)号:US10915336B1

    公开(公告)日:2021-02-09

    申请号:US16180932

    申请日:2018-11-05

    Abstract: Systems and methods are provided for selecting content components to include in portions of a content page under various constraints and according to various effectiveness considerations. Organizing the content components may include considering the expected user engagement with the content components, while simultaneously endeavoring to comply with certain content constraints imposed on the system. The content constraints may be complied with to the greatest extent possible before the expected user engagement with the page is adversely impacted to an unacceptable degree. The content constraints may be imposed across an entire set of content pages, such that only the content pages in the aggregate are expected to comply with a global constraint. This allows for maximizing the expected user engagement while assembling a content page without unduly constraining each content page, where those global constraints may be known to reduce expected user engagement in some instances.

Patent Agency Ranking