Abstract: Methods and systems for providing a user with content relevant to a location of interest to the user, when the user is determined to be at or near the location, are presented. The user's interest in the location may be determined based on queries about the location received from the user prior to the user arriving at the location. The queries received from the user about the location are used to build a location recommendation model, which generates personalized content relevant to the location and to one or more interest verticals identified for the user. The location recommendation model is built using a location recommendation engine that collects data about the user, the queried location, one or more associations between the user, the queried location, and/or one or more other users, as well as various other information related to the user's interests and the queried location.

Abstract: In a computerized search system, a document corpus is searched according to a query and results of the search are presentable as an ordered search result set comprising one or more search hits, a search hit being a document of the document corpus or reference thereto. Based on content of the search result set, a number of suggested queries and/or parameter options are presented to a querier, thereby allowing the querier to select a suggested query and/or provide values for the parameters and those selections can be used to reorder the hits of the search result set. The particular suggested queries and/or parameters presented depend on the page elements of the search result set's documents and their categorization. The categorization might be done using concept networks.

Abstract: Methods and systems for providing a user with content relevant to a location of interest to the user, when the user is determined to be at or near the location, are presented. The user's interest in the location may be determined based on queries about the location received from the user prior to the user arriving at the location. The queries received from the user about the location are used to build a location recommendation model, which generates personalized content relevant to the location and to one or more interest verticals identified for the user. The location recommendation model is built using a location recommendation engine that collects data about the user, the queried location, one or more associations between the user, the queried location, and/or one or more other users, as well as various other information related to the user's interests and the queried location.

Abstract: Methods and systems for providing a user with content relevant to a location of interest to the user, when the user is determined to be at or near the location, are presented. The user's interest in the location may be determined based on queries about the location received from the user prior to the user arriving at the location. The queries received from the user about the location are used to build a location recommendation model, which generates personalized content relevant to the location and to one or more interest verticals identified for the user. The location recommendation model is built using a location recommendation engine that collects data about the user, the queried location, one or more associations between the user, the queried location, and/or one or more other users, as well as various other information related to the user's interests and the queried location.

Abstract: In a computerized search system, a document corpus is searched according to a query and results of the search are presentable as an ordered search result set comprising one or more search hits, a search hit being a document of the document corpus or reference thereto. Based on content of the search result set, a number of suggested queries and/or parameter options are presented to a querier, thereby allowing the querier to select a suggested query and/or provide values for the parameters and those selections can be used to reorder the hits of the search result set. The particular suggested queries and/or parameters presented depend on the page elements of the search result set's documents and their categorization. The categorization might be done using concept networks.

Abstract: In a computerized search system, a document corpus is searched according to a query and results of the search are presentable as an ordered search result set comprising one or more search hits, a search hit being a document of the document corpus or reference thereto. Based on content of the search result set, a number of suggested queries and/or parameter options are presented to a querier, thereby allowing the querier to select a suggested query and/or provide values for the parameters and those selections can be used to reorder the hits of the search result set. The particular suggested queries and/or parameters presented depend on the page elements of the search result set's documents and their categorization. The categorization might be done using concept networks.

Abstract: Methods and systems for providing a user with content relevant to a location of interest to the user, when the user is determined to be at or near the location, are presented. The user's interest in the location may be determined based on queries about the location received from the user prior to the user arriving at the location. The queries received from the user about the location are used to build a location recommendation model, which generates personalized content relevant to the location and to one or more interest verticals identified for the user. The location recommendation model is built using a location recommendation engine that collects data about the user, the queried location, one or more associations between the user, the queried location, and/or one or more other users, as well as various other information related to the user's interests and the queried location.

Abstract: Methods and apparatus are disclosed for identifying a photo that lacks location metadata indicating where the photo was captured and determining a photo location to associate with the photo. In some implementations, a photo associated with a user is identified that includes metadata indicating a date and/or time it was captured, but lacks location data indicating where the photo was captured. In some versions of those implementations, a relationship of the metadata of the photo to at least one of a location date and a location time associated with a visit location of the user is determined. A photo location may be determined based on the visit location and associated with the photo. In some implementations, the visit location of the user may be determined independent of any location sensor.

Abstract: A tokenization platform and method is described for accurately tokenizing character strings, including but not limited to non-delimited character strings of the type commonly used in Internet domain names and computer filenames, to accurately identify words and phrases occurring therein. In one embodiment, a phased tokenization approach is used in which the final phase is a lexical analysis-based tokenization using a dictionary. The dictionary may be advantageously created and updated based upon one or more query logs associated with respective information retrieval systems, thereby ensuring that the dictionary accurately reflects currently-used terminology and captures alternative spellings and presentations of words and phrases submitted by users.

Abstract: The present invention is directed towards systems and methods for indexing one or more items of content. The method of the present invention comprises extracting one or more items of text from a given item of content. The one or more items of extracted text are tokenized into one or more concepts. One or more related concepts associated with the one or more concepts are identified. A support score is generated for the one or more concepts, and the item of content is index with the one or more concepts and the one or more associated support scores.

Abstract: The present invention is directed towards systems and methods for indexing one or more items of content. The method of the present invention comprises extracting one or more items of text from a given item of content. The one or more items of extracted text are tokenized into one or more concepts. One or more related concepts associated with the one or more concepts are identified. A support score is generated for the one or more concepts, and the item of content is index with the one or more concepts and the one or more associated support scores.

Abstract: Methods, systems, and apparatus, including computer program products, for query ranking based on query clustering and categorization, are disclosed. In one aspect, search queries are selected and grouped into one or more clusters. A representative query is selected for each cluster. Each cluster is associated with a respective representative category. A rank is assigned to each cluster based on a cluster popularity score of the cluster and a category popularity score of the cluster's representative category. The selected representative queries are presented in order according to the ranks of their respective clusters.

Abstract: Embodiments are directed towards providing a list of potential friends to a user based on an analysis of friends' contact lists. The user may provide a subset of friends within a contact list for analysis, along with a degree of separation over which to perform the analysis, and/or a minimum threshold number of occurrences for identifying a candidate friend. The subset of friends' contact lists may then be recursively traversed and merged, where common friends may be identified as members of a candidate set for suggesting friends to the user. In one embodiment, the candidate members may be retained within the candidate set if there is a commonality between the friends and the candidate that exceeds the minimum threshold. The candidate list may also be rank order using various approaches, including a weighted energy diffusion model based in part on a number of communications between the candidates.

Abstract: An advertisement distribution system can generate advertisement creatives having annotations and advertisement microsites using content extracted from landing web page documents. An advertisement module of the advertisement distribution system can analyze landing pages and other documents to identify relevant information, such as a phone number for a click-to-call annotation, an address for a merchant, and additional product information. The advertisement module can automatically generate the advertisement creatives and/or microsites using the extracted content. The microsite can include less data intensive content than the landing page and be linked to the advertisement creative. In this way, the less data intensive microsite can be downloaded and displayed in response to a user selecting the advertisement creative rather than downloading the landing page. This supports quicker advertisement browsing and is especially useful for serving advertisements on wireless devices having slower download speeds.

Abstract: Methods and apparatus are described by which “superphrases” of “seed phrases” representing basic concepts may be identified without having to compare all possible pairs of seed and candidate phrases. According to one class of embodiments, a data structure similar to an inverted index is used for indexing phrases. The elimination of seed and candidate phrase pairs is enabled by building and traversing the index in a particular manner.

Abstract: An apparatus and method for inferring a geographic locus for a publisher document in order to obtain advertisements that are relevant to the inferred geographic locus. Landing pages are analyzed by determining whether the page encodes a street address and extract the street address or for information that is indicative of a geographic locus and thereby determine the geographic locus of the page. The ad server can infer a geographic locus for the publisher document based on information indicating a geographic location encoded in the publisher document, and select ads based on corresponding landing pages having inferred geographic locus that match the inferred geographic locus for the publisher document.

Abstract: A tokenization platform and method is described for accurately tokenizing character strings, including but not limited to non-delimited character strings of the type commonly used in Internet domain names and computer filenames, to accurately identify words and phrases occurring therein. In one embodiment, a phased tokenization approach is used in which the final phase is a lexical analysis-based tokenization using a dictionary. The dictionary may be advantageously created and updated based upon one or more query logs associated with respective information retrieval systems, thereby ensuring that the dictionary accurately reflects currently-used terminology and captures alternative spellings and presentations of words and phrases submitted by users.

Abstract: A tokenization platform and method is described for accurately tokenizing character strings, including but not limited to non-delimited character strings of the type commonly used in Internet domain names and computer filenames, to accurately identify words and phrases occurring therein. In one embodiment, a phased tokenization approach is used in which the final phase is a lexical analysis-based tokenization using a dictionary. The dictionary may be advantageously created and updated based upon one or more query logs associated with respective information retrieval systems, thereby ensuring that the dictionary accurately reflects currently-used terminology and captures alternative spellings and presentations of words and phrases submitted by users.

Abstract: Techniques are provided for designating an item as being of a particular type when the item has been selected after being returned in response to a search and by identifying which mode, of a plurality of modes, in which the search engine was operating when the item was selected.

Abstract: Methods and apparatus are described by which “superphrases” of “seed phrases” representing basic concepts may be identified without having to compare all possible pairs of seed and candidate phrases. According to one class of embodiments, a data structure similar to an inverted index is used for indexing phrases. The elimination of seed and candidate phrase pairs is enabled by building and traversing the index in a particular manner.