Patent application number | Description | Published |
20090067395 | Routing Network Requests Based on a Mobile Network Signature - Disclosed are systems and methods for responding to a web page request from a mobile device by providing the network address of a server hosting content formatted for the mobile device. The systems and methods include means and ways for redirecting a request for URL resolution from a DNS server to an enhanced DNS server with facilities to determine the kind of the requesting device, e.g., whether the requesting device is fixed or mobile. | 03-12-2009 |
20090070413 | Displaying Content on a Mobile Device - A method for facilitating the rendering of a web page on a mobile device includes providing an enhanced DOM tree for the web page that includes web page components and their display coordinates. A rule set is applied to the DOM tree, thereby selecting components for display on the mobile device. A mobile-device-specific version of the source code is generated based on the selected components. | 03-12-2009 |
20100228625 | WIRELESS NETWORK USER TRACKING - Requests for WAP-enabled content from mobile subscribers may be assigned to a particular subscriber based on a degree of match between hashed request attribute groupings. Targeted contend and/or advertising may be directed at the subscribers based on identifying common requests assigned to the same subscriber. | 09-09-2010 |
20110295628 | AUDIENCE TARGETING BASED ON PERFORMANCE HISTORY OF INVITATIONAL CONTENT - Systems and methods are provided for audience targeting based on a performance history of invitational content from secondary content providers, such as advertisements. In operation, responsive to request from a user for content package, a queue of available invitational content is retrieved. Thereafter, based at least on a performance history of the available invitational content in the queue, a context of the primary content, and a performance history of invitational content previously presented to other users, the queue can be at least partially reordered to provide an adjusted queue. The invitational content for the content package can then be selected based on the adjusted queue. | 12-01-2011 |
20110295679 | PRESENTING CONTENT PACKAGES BASED ON AUDIENCE EXCLUSION - The present technology maintains a profile for each user known to a content delivery system and selectively excludes delivery of certain content to some users based on past performance. The user profile includes a listing of all completed conversion actions associated with the invitational content presented to the user. When presented with a request for invitational content, the system identifies the set of all possible invitational content for the given context. Based on the user profile, the system removes from the set all invitational content for which the user has completed the associated conversion action to create a user-specific set of invitational content. The system selects an invitational content from the user-specific set of invitational content to include in the content package presented to the user. | 12-01-2011 |
20110295997 | PRESENTING CONTENT PACKAGES BASED ON AUDIENCE RETARGETING - A present technology intelligently retargets invitational content to a user by maintaining a user profile that includes data descriptive of the user's interaction with invitational content previously presented to the user and making decisions regarding retargeting based on an analysis of the user profile. The information in the user profile is not limited to whether or not the user completed a conversion action associated with invitational content presented. Rather, the profile is expanded to include such information as where on the conversion continuum the user abandoned the process and details of how the invitational content was presented to the user, e.g. colors used, situation, and message. When presented with a request for invitational content, the system uses the profile information to influence which content is selected and how it is presented to the user. This enables the system to re-present invitational content in a form and/or situation where the user is more likely to complete the conversion action. | 12-01-2011 |
20120041792 | CUSTOMIZABLE POPULATION SEGMENT ASSEMBLY - The presently described technology provides a mechanism for allowing custom targeted segments to be defined by parties outside of a content delivery system. Segments include collections of users grouped together based on common characteristics wherein targeted content is provided to a user based on her assignment to a segment. The present technology allows a content provider, as an example, to define a custom segment, thereby creating a grouping of users suited to receive the content provider's content. In some embodiments, a user interface is provided to the content provider, which includes all available characteristics, and value ranges corresponding to the characteristics. The content provider selects from among the characteristics and values corresponding to the characteristics to create a definition of a custom segment. | 02-16-2012 |
20120041817 | PRIORITIZING POPULATION SEGMENT ASSIGNMENTS TO OPTIMIZE CAMPAIGN GOALS - The present technology prioritizes or ranks segments based on the content provider's or content delivery system's goals or priorities. The content delivery system can monitor its performance in meeting any known goals, and should the content delivery system recognize that its progress towards meeting a goal is not satisfactory, the content delivery system can prioritize some segments over others to meet one or more goals. Since prioritizing a selection of segments can impact other system and content provider goals, the system can also be provided with a performance predictor that can run a series of prediction models to predict the optimum prioritization of segments to result in the best performance of the system. | 02-16-2012 |
20120041969 | DERIVING USER CHARACTERISTICS - The present technology derives unknown user characteristics from known user characteristics. Unknown characteristics can be inferred from products purchased by a user; by comparing two similar users and inputing characteristics known about one user to another user with unknown characteristics; by inferring characteristics using classifying algorithms to infer additional user characteristics from a collection of other known data about a user. The inferred characteristics can further be associated with a confidence score which is an indication of the likelihood that the inferred value is the correct value for a user. | 02-16-2012 |
20120042253 | POPULATION SEGMENTATION - Segments used to select content to be targeted to a user are recursively refined based on continuously derived user characteristics. Based on information gathered from new requests for targeted content and/or user interaction with previously delivered content the user is assigned to one or additional candidate segments. The candidate segments can be used to select content to be delivered to the user based on the user's assignment to the targeted segments. Accordingly, each user is grouped into one or more targeted segments and based on the user's inclusion in those segments, requests for targeted content can be served to the user. | 02-16-2012 |
20120042262 | POPULATION SEGMENTATION BASED ON BEHAVIORAL PATTERNS - The present technology analyzes a user's behavior to assign a user to targeted segments. The segments to which the user is assigned can be a reflection of a user's context with respect to potential targeted content. While a user can be assigned to many different segments, the user is likely to be most interested in content that she is presently interested in. Accordingly, the system can also prioritize or rank or order segments based on the user's present context. Content is then provided to the user on the basis of the segments to which the user belongs and the priority of segments. | 02-16-2012 |
20140337716 | DISPLAYING CONTENT ON A MOBILE DEVICE - A method for facilitating the rendering of a web page on a mobile device includes providing an enhanced DOM tree for the web page that includes web page components and their display coordinates. A rule set is applied to the DOM tree, thereby selecting components for display on the mobile device. A mobile-device-specific version of the source code is generated based on the selected components. | 11-13-2014 |
Patent application number | Description | Published |
20130304748 | SELECTION AND DELIVERY OF INVITATIONAL CONTENT BASED ON PREDICTION OF USER INTEREST - Systems and methods are provided for selecting invitational content for users based on their short-term and their long-term features. In operation, responsive to a request from a user terminal for a content package a journal of events associated with a user. Thereafter, short-term and long-term features in the journal are identified and tagged with pre-defined tags indicating a type of content associated with the patterns. The tags are then used to select invitational content by selecting content based on tags for the identified short-term features associated with a threshold level of activity or tags for the identified long-term features. | 11-14-2013 |
20140074959 | CLIENT SIDE MEDIA STATION GENERATION - To generate a media station, a client device can receive a candidate media item playlist and media playback rules corresponding to the media station. When a new media item is needed for the media station, the client device can apply the media playback rules to a next media item in the list of candidate media items. The playback rules can be used to determine whether the next media item is currently eligible for playback. Additionally, the client device can receive a candidate invitational content item playlist and invitational content playback rules corresponding to the media station. In response to detecting an invitational content triggering action, the client device can apply the invitational content item rules to the candidate invitational content item playlist to select at least one invitational content item to present in the media stream. | 03-13-2014 |
20140101548 | CONCURRENTLY PRESENTING INTERACTIVE INVITATIONAL CONTENT AND MEDIA ITEMS WITHIN A MEDIA STATION THROUGH THE USE OF BUMPER CONTENT - A media channel can include a mix of media items and invitational content packages. At some point during the playback of the media channel, an invitational content package can be presented. In response to detecting the occurrence of an interactive segment triggering event during the presentation of the invitational content package, an invitational content interactive segment and a next media item can be simultaneously presented. This can be accomplished by splitting the media channel into multiple streams, such as an audio stream and a visual stream, and presenting an element of the interactive segment within a first stream and an element of the media item within a second stream. To decrease the likelihood that a user may equate the invitational content with the media item, a bumper content item, such as audio that says, “now back to the music,” can be presented just prior to playback of the media item. | 04-10-2014 |
20140172539 | MEDIA STATION WITH CUSTOM BUMPER - Disclosed herein are systems, methods, and non-transitory computer-readable storage media for providing a custom bumper within a media station. A custom bumper can be created using gathered bumper creation data and a bumper template. Bumper creation data can be any data regarding the media station and can be used to populate an appropriate bumper template. The populated template is a completed custom bumper customized based on the bumper creation data. Further, rewards can be awarded to encourage desired user interactions. Upon a determination that a desired user interaction has occurred a predetermined number of times, a reward can be awarded. The reward can be making available a previously unavailable media item. Bumper creation data indicating the remaining number of times the user interaction has to be performed to achieve the reward to be awarded can be used to create a custom bumper. | 06-19-2014 |
Patent application number | Description | Published |
20100293175 | FEATURE NORMALIZATION AND ADAPTATION TO BUILD A UNIVERSAL RANKING FUNCTION - To increase the amount of training data available to train a machine learning ranking function, data from multiple markets are normalized in such a manner as to optimize a measurement of quality of the ranking function trained on the various sets of normalized training data. Furthermore, the feature scores of training data from individual markets are adapted to conform to the distributions of feature scores from a base market. Such adapted training data from the various markets may be used to train a single, robust ranking function. Adaptation of feature scores in a particular training data set involves mapping feature scores of the particular training data set to feature scores of a base training data set to conform the distributions of the feature scores in the particular training data set to the distributions of the feature scores in the base training data set. | 11-18-2010 |
20100325129 | DETERMINING THE GEOGRAPHIC SCOPE OF WEB RESOURCES USING USER CLICK DATA - A geographic region is automatically determined for an Internet resource based on information that has been gathered over time through the automatic monitoring of certain “click” activities of Internet search engine-using users. Over time, the search engine collects information for each click. Using this click-related data, the search engine estimates the geographic region with which the resource ought to be associated. The fact that a significant proportion of clicks on a resource's hyperlink are clicks that “came through” a search engine portal that is associated with a geographic region tends to suggest that the resource ought to be associated with that geographic region. Similarly, the fact that a significant proportion of clicks on a resource's hyperlink are clicks that were made by users whose computers have IP addresses that are associated with a geographic region tends to suggest that the resource ought to be associated with that geographic region. | 12-23-2010 |
20110035345 | AUTOMATIC CLASSIFICATION OF SEGMENTED PORTIONS OF WEB PAGES - Exemplary methods and apparatuses are provided which may be used for classifying and indexing segmented portions of web pages and providing related information for use in information extraction and/or information retrieval systems. | 02-10-2011 |
20110035374 | SEGMENT SENSITIVE QUERY MATCHING OF DOCUMENTS - Exemplary methods and apparatuses are provided which may be used to provide or otherwise support segment sensitive query matching based on segmented portions of web pages and/or providing related information for use in information extraction and/or information retrieval systems. | 02-10-2011 |
20110071965 | SYSTEM AND METHOD FOR CROSS DOMAIN LEARNING FOR DATA AUGMENTATION - According to an example embodiment, a method comprises executing instructions by a special purpose computing apparatus to, for labeled source domain data having a plurality of original labels, generate a plurality of first predicted labels for the labeled source domain data using a target function, the target function determined by using a plurality of labels from labeled target domain data. The method further comprises executing instructions by the special purpose computing apparatus to apply a label relation function to the first predicted labels for the source domain data and the original labels for the source domain data to determine a plurality of weighting factors for the labeled source domain data. The method further comprises executing instructions by the special purpose computing apparatus to generate a new target function using the labeled target domain data, the labeled source domain data, and the weighting factors for the labeled source domain data, and evaluate a performance of the new target function to determine if there is a convergence. | 03-24-2011 |
20120016877 | CLUSTERING OF SEARCH RESULTS - One particular embodiment clusters a plurality of documents using one or more clustering algorithms to obtain one or more first sets of clusters, wherein: each first set of clusters results from clustering the documents using one of the clustering algorithms; and with respect to each first set of clusters, each of the documents belongs to one of the clusters from the first set of clusters; accesses a search query; identifies a search result in response to the search query, wherein the search result comprises two or more of the documents; and clusters the search result to obtain a second set of clusters, wherein each document of the search result belongs to one of the clusters from the second set of clusters. | 01-19-2012 |
20120284275 | UTILIZING OFFLINE CLUSTERS FOR REALTIME CLUSTERING OF SEARCH RESULTS - 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. In the result for the query, the set of articles is organized according to the one or more second clusters. | 11-08-2012 |
20120303623 | SYSTEM FOR INCREMENTALLY CLUSTERING NEWS STORIES - 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. Indications of the initial clusters and the one or more new clusters, if any, are then stored so as to be accessible for sending a portion of the news articles to users in a clustered format based on the initial clusters and the one or more new clusters, if any. | 11-29-2012 |
20130246452 | PERSONALIZATION OF NEWS ARTICLES BASED ON NEWS SOURCES - News search and browse experience is personalized based on user preferences. User attributes like a geographic location are obtained and news sources preferred by other users with attributes similar to those of a requesting user are identified. News sources that are popular across different user groups are eliminated and relevant news items from the remaining news sources are retrieved and presented to the requesting user. | 09-19-2013 |
20140207763 | RANKING RELEVANT ATTRIBUTES OF ENTITY IN STRUCTURED KNOWLEDGE BASE - Architecture that addresses at least the problem of ranking the relevant attributes for a given entity within the context of a structured knowledge base (SKB). The architecture utilizes the attribute, entity type statistics, and the taxonomy of the attributes to consistently and efficiently rank attributes for each and every type of entity in the SKB. Using the SKB, intermediate features are computed, including the importance or popularity each entity type for every entity, inverse document frequency (IDF) computation for each attribute on a global basis, IDF computation for entity types, and the popularity of attributes for each entity type. The intermediate features are aggregated to obtain a final feature set, which can be used in combination with human judgments to train a machine learned classifier model to produce and predict a relevance score for a given entity and each of its attributes. The attributes are ranked for each entity using this score. | 07-24-2014 |
20140222800 | PERSONALIZATION OF NEWS ARTICLES BASED ON NEWS SOURCES - News search and browse experience is personalized based on user preferences. User attributes like a geographic location are obtained and news sources preferred by other users with attributes similar to those of a requesting user are identified. News sources that are popular across different user groups are eliminated and relevant news items from the remaining news sources are retrieved and presented to the requesting user. | 08-07-2014 |
20150066934 | AUTOMATIC CLASSIFICATION OF SEGMENTED PORTIONS OF WEB PAGES - Exemplary methods and apparatuses are provided which may be used for classifying and indexing segmented portions of web pages and providing related information for use in information extraction and/or information retrieval systems. | 03-05-2015 |