Amazon Technologies, Inc.

Matthew J Round

Graeme N Smith

Jason A Kilar

Andrew J Bradley

David Neil Turner

Andrew Douglas Birkett

Oliver Masting

Robert Philip Japp

Gregory Huczynski

Jason King

Haakon Sorensen

Elinor Trotter

Michael Davidson

Jonathan G G Tams

Aniruddha Gadre

Dominic E H K Seymour

A method and system are disclosed for allowing a user to suggest information about content that can be utilized in processing subsequent searches. The suggested information may be different from a fixed set of information about an item, such as keywords, attributes or characteristics of an item, generally provided by a manufacturer or seller of the item. Users can submit to a service the information that they feel is relevant to the item, such as a brief explanation of relevance and a detailed explanation that would help other users to make a decision about the item. The submitted information may be associated with the item information and stored in a data store and utilized as additional attributes of the item for a search. In addition, when a user requests detail information about an item, the user-submitted information may be displayed to the user.

Enhanced search with user suggested search information

A system regulates server load by dynamically selecting variables that directly or indirectly control the type and/or quantity of processing performed in responding to content requests, such as requests for dynamically generated web pages. For example, the system may use current load level data to vary the sizes of input data sets used to generate personalized recommendations or other content for users.

Regulating server load by varying sizes of data sets used to generate content

A method and system are disclosed for allowing a user to suggest information about content that can be utilized in processing subsequent searches. The suggested information may be different from a fixed set of information about an item, such as keywords, attributes, or characteristics of an item, generally provided by a manufacturer or seller of the item. Users can submit to a service the information that they feel is relevant to the item, such as a brief explanation of relevance and a detailed explanation that would help other users to make a decision about the item. The submitted information may be associated with the item information and stored in a data store and utilized as additional attributes of the item for a search. In addition, when a user requests detail information about an item, the user-submitted information may be displayed to the user.

Embodiments of the present invention provide a system and method for providing reviewer feedback identifying a correlation between a reviewer's past voting record and successful results. Based on a reviewer's past record, the reviewer may be assigned a power rating identifying the statistical accuracy of the reviewer's voting history. That power rating may be used to weight future votes, thereby increasing the likelihood that accurate decisions will be made.

Closed loop voting feedback

A web server system regulates its own load level by dynamically varying its responses to requests for like web pages. The responses are preferably varied at least in-part using variables that directly or indirectly specify the type and/or quantity of processing to be performed in responding to requests for dynamically-generated web pages. The type of response generated by the web server system is preferably selected based upon one or more of the following: (a) the current load level of the server system as a whole, (b) the current load levels of specific computing devices or components invoked by the request, and (c) a profile of the user who requests the page.

Managing server load by varying responses to page requests

This disclosure describes systems and associated methods that can selectively filter seed behavior, e.g., user activity used to generate item recommendations. In some embodiments, seed behaviors and catalog items are associated with categories in an electronic catalog, and a particular seed behavior is used to generate user recommendations if it is more recent than a user's last purchase in the category of the seed behavior. For example, a user's activity in the TV category, e.g., viewing various TV models, may not be used to generate recommendations if the activity occurred prior to the user's purchase of a TV. As a result, in certain embodiments, additional TVs may not appear in the user's recommendations following her purchase, reflecting that the user has fulfilled her desire to purchase a TV.

Behavioral filter for personalized recommendations

Systems and methods of determining genre information are provided. A particular method includes receiving a first data set including a plurality of genre descriptors and associated strength values related to particular content. Each strength value indicates a degree to which the associated genre descriptor describes the particular content. The method also includes storing a data record associating the first data set with the particular content.

Growing community of inventors

West Lothian, United Kingdom

Matthew J Round