Facebook, Inc. (Menlo Park, CA)

A system online stores online documents, and each online document is organized according to a layout. The system produces augmented online documents by combining the online documents with at least one content item. The system records client interactions with content items and allows clients to present the augmented online documents via their devices. The system receives a brand new online document. The system creates online documents that are augmented by adding one or more content elements to the online document. Each time a new online document is augmented document, the system calculates scores by analyzing the features that describe the design of the augmented online document. The system selects a new online document that is augmented using the generated scores and sends the selected new enhanced online document for presentation using a device for clients.

This disclosure relates to the transfer of electronic media items to client devices, and more specifically, the automatic placement electronic media items in online documents, which are displayed via client devices.

Online systems usually offer documents to users. The online system could show an article from the news or a science paper to clients, as well as documents provided by another client. The documents that are online can be read by clients on client devices, for example, either a laptop or mobile device. Clients typically scroll through the online document using the device of their choice.

Online documents may contain text as along with media objects like images and videos. Online systems typically include content items in the online document that is presented to a client, for example, images or videos. Online documents with embedded content can have a negative effects on user experience. This is often due to the placement of the embedded content in the online document. For instance, certain positions of content items could divert the user from the content of the online document, or from other items contained in the online document.

Content-rich documents online that include items are usually presented in standard manners. This could result in poor client experiences. Poor client experience leads to fewer client interactions withcontent items, or with the document online. Client participation in the online system might be less if there are few interactions between clients. For instance, if the online system is a social media system, customers are less likely interact with their social networks when the content offered by the social networking system is not well presented or is difficult to follow.

A system online stores online documents that contain blocks of text and media items. Online systems can produce enhanced online documents by combining documents from online with content items. The online system is able to extract features that describe the layout of each online document and calculates a score. The online system selects an online document with augmented features in accordance with the score generated and sends the selected supplemented online document to a client device. Examples ofonline documents include news articles, science papers, documents supplied by other clients, corporate websites, etc. Examples of content comprise text, images, and video clips, as well as hyperlinks, audio clips and online forms, for example.

In one instance, the online system uses the machine-learning model to assist in determining the layout of the online document. The online system offers an online document that is augmented and records their interactions with the items of content. The online system trains the machine learning model using the data from client interactions. Machine learning models could be used to predict whether the user will interact with one or more items. The online system employs the trained machine learning model to evaluate the layouts of online documents generated by online documents received later.

Certain methods generate the score of an augmented document online as a weighted aggregate value that is based upon the attributes of the augmented documents.

Click here to view the patent on USPTO website.

Get Patents with PatentPC

What is a patent?

How to Search for Patents

  • Add keywords to your search. Keyword searches may turn up documents that are not well-categorized or have missed classifications during Step 2. For example, US patent examiners often supplement their classification searches with keyword searches. Think about the use of technical engineering terminology rather than everyday words.
  • Search for foreign patents using the CPC classification. Then, re-run the search using international patent office search engines such as Espacenet, the European Patent Office’s worldwide patent publication database of over 130 million patent publications. Other national databases include:
  • Search non-patent literature. Inventions can be made public in many non-patent publications. It is recommended that you search journals, books, websites, technical catalogs, conference proceedings, and other print and electronic publications.

To review your search, you can hire a registered patent attorney to assist. A preliminary search will help one better prepare to talk about their invention and other related inventions with a professional patent attorney. In addition, the attorney will not spend too much time or money on patenting basics.