Method and system for single-action personalized recommendation and display of internet content
AssigneeStumbleupon, Inc.
InventorsEric Boyd, Justin LaFrance, Geoff Smith, Garrett Camp
Life of this patent
Estimating the term…
Loading patent…
AssigneeStumbleupon, Inc.
InventorsEric Boyd, Justin LaFrance, Geoff Smith, Garrett Camp
Estimating the term…
A method and system for single-action personalized recommendation and display of content via the Internet. The recommendation is given by a server system and received by a client system. The content itself has been previously recommended to the server system by the users of the client system. Client system recommendations to the server system are also invoked with a single-action. Recommended content is referred to by a URL. Users can rate content to the server system using a single-action. The server system performs recommendation calculations using user-specific information such as user preferences, demographic data, content rating history, and content-specific information. The content rating history of other users may also influence these calculations. Client systems display recommended content directly to the user in response to only a single-action.
A method for retrieving content from a distributed network which is personalized to one or more network users comprising:
A system for displaying content which is recommended to a network user comprising:
A system for displaying content which is recommended to a network user comprising:
Dependencies are inferred from the claim text.
Drawings are temporarily unavailable. Open the PDF at USPTO
From the US filing history. Foreign family members aren’t listed.
Backward citations are indexed for grants only.
Querying, e.g. by the use of web search engines: search customisation based on user profiles and personalisation
Querying, e.g. by the use of web search engines: search customisation based on social or collaborative filtering
Querying, e.g. by the use of web search engines: presentation of query results
Computing and data processing
Term end not estimated
The present invention relates to a computer method and system for recommending content over the Internet.
The Internet comprises a vast number of computers and computer networks that are interconnected through communications links. Many different services and protocols operate over the Internet, including email, the world-wide-web (WWW), file transfer, and chat services.
The WWW service consists of server systems and client systems exchanging documents via the Hyper-Text Transport Protocol (HTTP). Server systems are generally permanently dedicated computers with high bandwidth connections to the Internet. They host the Internet content, run the server software, and perform many types of calculations. Client systems are generally personal computers being controlled by an individual. They display a Graphical User Interface (GUI) to the user, and run applications, such as browsers, which allow users to send requests for Internet content to the server systems, and then view the content.
FIG. 1a is a block diagram illustrating single-action server-recommendation in one embodiment of the present invention;
FIG. 1b is a block diagram illustrating single-action user-recommendation in one embodiment of the present invention;
FIG. 2 is a block diagram illustrating an embodiment of the present invention;
The present invention provides a method and system for single-action personalized recommendation of Internet content in a client/server environment, as well as the immediate display of this content to the user. The single-action recommendation system of the present invention minimizes the number of user interactions needed to obtain and view content recommended by the server system.
In order to enable the system, the client must register for the recommendation service. In one embodiment of the present invention, the client system is installed by a user simply by directing a web browser to a specified hyperlink. On initial use, the client is provided with a unique identifier, such as a cookie. Additionally, the client system directs the web browser to a form where users are asked to select from a broad range of interests and, optionally, to supply demographic data. Upon completion of this form, the registration process is complete. See FIG. 8, and further description, below. After the sign up process, the single-action recommendation process can be affected at any time.
When a user wants to view recommended content, the user uses a client system to submit the request for recommendations along with a client identifier to the server system. The user need only perform a single action (e.g., click a mouse button) to obtain the recommendation, and view the content recommended by the server system. When the user performs that single action, the client system sends a request for recommendation to the server system. This request may be sent directly from client to server or via the browser. The server system then uses real-time Web personalization software, such as Macromedia Likeminds, to generate personalized recommendations. In general, these systems incorporate into their recommendation calculations user-specific information such as user preferences, demographic data, content rating history, and content-specific information such as subject matter, content quality, complexity of language, and general aesthetics. See FIG. 5, and further description, below. The database of content from which recommendations are chosen is itself built from content recommended to the system by users (see below for detailed description). Once the content to recommend has been chosen, the server system determines the URL(s) which refer to that Recommended Content. If the original request was submitted directly by the client, this URL(s) is then sent back to the client, along with associated information. The client system then interfaces with a browser application, instructing it to retrieve and display the content recommended by the server system, referenced by the URL. Otherwise, the server instructs the browser to retrieve and display the content recommended by the server system, referenced by the URL. Thus, after completion of the registration process, the user has only to perform a single action in order to view content recommended by the server system.