Abstract: A recommendation engine and a user profile stored on a user device are employed by the user device to select from a content store, content that is relevant to a current display of the user device. The selected content is combined with the current display to generate the contextually relevant display. The user profile on the user device is updated based on user interaction with the displayed content and the updated profile may be uploaded to the server in accordance with privacy settings associated with the user profile.

Abstract: A recommendation engine and a user profile stored on a user device are employed by the user device to select from a content store, content that is relevant to a current display of the user device. The selected content is combined with the current display to generate the contextually relevant display. The user profile on the user device is updated based on user interaction with the displayed content and the updated profile may be uploaded to the server in accordance with privacy settings associated with the user profile.

Abstract: A system is described for discovering query intent based on search queries and concept networks. The system may construct frequency vectors from log data corresponding to a submitted query and at least one related query submitted to one or more search engines. The system may also construct a query intent vector based on the frequency vectors. The query intent vector may include frequency scores that represent the intent of the query.

Abstract: A system is described for discovering query intent based on search queries and concept networks. The system may construct frequency vectors from log data corresponding to a submitted query and at least one related query submitted to one or more search engines. The system may also construct a query intent vector based on the frequency vectors. The query intent vector may include frequency scores that represent the intent of the query.

Abstract: A system is described for discovering query intent based on search queries and concept networks. The system may construct frequency vectors from log data corresponding to a submitted query and at least one related query submitted to one or more search engines. The system may also construct a query intent vector based on the frequency vectors. The query intent vector may include frequency scores that represent the intent of the query.

Abstract: A method and apparatus using feedback obtained by user clicks and the position of the clicked images in the search result to determine user preferences for data that best satisfies particular queries. User click information is tracked to determine which images users click on for particular queries. This information is used to update and improve future query results. The described embodiment determines a user preference score for each image that is clicked for a given query. The placement of a clicked image in the search results is considered when computing the image/query score.

Abstract: A system is described for bidding in an online information system on tiers for a search term or group of terms in a search request based on the integrity of the network interaction which generated the search request. The system may include a processor, an interface and a memory. The memory may be operatively connected to the processor, and the interface, and may store a plurality of integrity tiers, a term, and a plurality of bid amounts. The interface may be operatively connected to the memory and the processor and may communicate with the advertisers. The processor may identify the plurality of integrity tiers. The processor may receive a plurality of bid amounts, from an advertiser via the interface, associated with the term and the plurality of integrity tiers. The processor may store the plurality of bid amounts in the memory.

Abstract: A system is described for discovering query intent based on search queries and concept networks. The system may construct frequency vectors from log data corresponding to a submitted query and at least one related query submitted to one or more search engines. The system may also construct a query intent vector based on the frequency vectors. The query intent vector may include frequency scores that represent the intent of the query.

Abstract: A style identifier is associated with each of a plurality of media clips stored in a database, based on a subjective evaluation of various characteristics of each media clip by an expert. The style represented by the style identifier corresponds to an impression on the expert regarding various qualities of the media clip and is not constrained by the subject of the media clip. Media clips with which style identifiers are associated can be any form of digital media, such as clip art files, sound files, photographs, animation files, fonts, etc. Also associated with each media clip in the database is an absolute ranking value for each of a plurality of different attributes based on a subjective evaluation of each media clip by an expert. A user can search the database for media clips associated with a specific style identifier and can sort the media clips that were identified by a search, based upon the absolute ranking value for a selected attribute.