Abstract: Devices and techniques are generally described for search using a micro-partitioned catalog. In some examples, a search system can determine a plurality of items in an online catalog. The search system can generate a similarity graph based on vector representations of the plurality of items and determine an item as a representative item for a cluster of items. The search system can receive a query and determine the cluster of items as a candidate cluster based on a comparison between the query and the representative item. The search system can determine a candidate item of the cluster of items based on a comparison between the query and the cluster of items.

Abstract: Real-time consumer feedback collection includes: receiving a unique product code from a device associated with a consumer of a product, the unique product code, when decoded, revealing an address of an on-line survey site; providing an interface within the on-line survey site for providing feedback about the product; receiving the feedback; storing the feedback; and supplying the feedback to the producer of the product.

Abstract: Method, system, and programs for mapping data. Information related to users and their interests is obtained by a first application from a second application. An interest space is determined based on one or more sources of information, each of which provides a plurality of concepts. A data structure is created with respect to the interest space, where the data structure has a plurality of attributes each of the attributes corresponds to a concept in the interest space. One or more interests for each of the users based on information obtained from the second application. Each user interest corresponds to an attribute in the structure. A user profile is generated for each user by mapping the interests of the user to the corresponding attributes in the structure.

Abstract: The present teaching relates to discovery of user unknown interests. In one example, information related to a user is retrieved from a user profile. The information indicates one or more known interests of the user. At least one known interest of the user is identified based on the information. One or more supplemental interests with respect to each identified at least one known interest of the user are identified. The one or more supplemental interests do not overlap with the one or more known interests of the user. Supplemental content associated with the one or more supplemental interests are identified. Each piece of content in the supplemental content is ranked. At least one piece of content in the supplemental content is selected based on the ranking. The selected at least one piece of supplemental content is used to discover unknown interest of the user.

Abstract: Method, system, and programs for mapping data. Information related to users and their interests is obtained by a first application from a second application. An interest space is determined based on one or more sources of information, each of which provides a plurality of concepts. A data structure is created with respect to the interest space, where the data structure has a plurality of attributes each of the attributes corresponds to a concept in the interest space. One or more interests for each of the users based on information obtained from the second application. Each user interest corresponds to an attribute in the structure. A user profile is generated for each user by mapping the interests of the user to the corresponding attributes in the structure.

Abstract: A method and system for exploring a list of user interests beyond the currently known user interests by defining a distance metrics in the interest space is disclosed. The new method and system target for exploration, items of interests which are close in proximity to the current set of user interests, thereby greatly improving the chance that one of the exploration items will be liked by the user.

Abstract: Disclosed are methods and apparatus for clustering news stories, which are to be presented over a computer network. In general, an incremental clustering system is configured to update a current set of news clusters with newly arrived news articles without having to recompute the clusters for the entire corpus, as well as form new clusters for recently generated news topics. In one embodiment, a plurality of news articles are initially obtained via the computer network, and the news articles are clustered into a plurality of initial clusters. For only news articles, including any unclustered news articles, that are less than a predetermined age limit, it is determined in an incremental clustering process whether to form one or more new clusters or assign to the initial clusters.

Abstract: Real-time consumer feedback collection includes: receiving a unique product code from a device associated with a consumer of a product, the unique product code, when decoded, revealing an address of an on-line survey site; providing an interface within the on-line survey site for providing feedback about the product; receiving the feedback; storing the feedback; and supplying the feedback to the producer of the product.

Abstract: Disclosed are methods and apparatus for clustering news stories, which are to be presented over a computer network. In general, an incremental clustering system is configured to update a current set of news clusters with newly arrived news articles without having to recompute the clusters for the entire corpus, as well as form new clusters for recently generated news topics. In one embodiment, a plurality of news articles are initially obtained via the computer network, and the news articles are clustered into a plurality of initial clusters. For only news articles, including any unclustered news articles, that are less than a predetermined age limit, it is determined in an incremental clustering process whether to form one or more new clusters or assign to the initial clusters.

Abstract: Techniques for clustering of search results are described. In an example embodiment, a plurality of first clusters is determined, in a corpus of articles, independently of user queries issued against the corpus of articles, where each first cluster represents a group of articles that relate to a news story. One or more cluster identifiers are assigned to each article in the corpus, where the one or more cluster identifiers respectively identify one or more of the plurality of first clusters to which the article belongs. A query that specifies search criteria against the corpus of articles is received. In response to receiving the query, a result for the query is generated by at least selecting, from the corpus of articles, a set of articles based on the search criteria. The selected set of articles is grouped into one or more second clusters based at least on the one or more cluster identifiers that are assigned to each article in the set of articles.

Abstract: Disclosed is a method and system for providing intuitive and efficient representations of positions of interest to a user within encoded media. Various embodiments of the present disclosure provide a heatmap representation that indicates the interestingness of content at different locations within the media. These locations of interest are presented to a user to allow quick jumps to the interesting parts of the content.