Abstract: Summary presentation of media consumption is described herein. An exemplary method for generating a personal highlight reel includes receiving personal consumption data indicating one or more media units consumed by a user computing device, and storing the personal consumption data in association with a user identifier. The method further includes identifying one or more relevant personal media units based on the personal consumption data. The method further includes generating a personal highlight reel including one or more personal media events representative of the one or more relevant personal media units, and outputting the personal highlight reel.

Abstract: Systems, apparatuses, and methods for analyzing information about a user are presented which include obtaining at least one search result based on at least one search terms describing the user; presenting the at least one search result to the user; receiving an indication from the user of the desirability of a search result; and performing an action based on the desirability of the search result. Systems, apparatuses, and methods are also presented for determining a reputation score representing the reputation of a user which include collecting search results from data source, determining an effect on the reputation of the user of the search results from the data source, and calculating a reputation score for the user based on the determined effect on the reputation of the user from the search results from the data source.

Abstract: A method and system for expanding attribute profiles are presented in which primary attributes from one or more attribute profiles are used to derive secondary attributes which are added to the respective attribute profiles to generate expanded attribute profiles. The expanded attribute profiles are generated to increase the strength of association of a query attribute with one or more attribute profiles associated with query-attribute-positive individuals.

Abstract: A search-enabled remote control device to facilitate viewers' ability to search through programming and/or content options and view results. In one embodiment, a viewer is able to use a traditional remote control interface to navigate through menus or selections and to display search results on screen. In another embodiment, a viewer's watching behavior and/or searching habits are tracked by the search-enabled remote control and used to develop a viewer profile, which may in turn be used to target advertisements, information and/or future programming options.

Abstract: The present invention relates to a method and system for detecting a keyword whose number of being inputted from a user terminal is rapidly increased, and more particularly, to a method and system which generate rapid increase standard quotient by using the average and standard deviation for each keyword and compare the rapid increase standard quotient with measured input number in order to detect a keyword whose input number is rapidly increased.

Abstract: Demographic information of an Internet user is predicted based on an analysis of accessed web pages. Web pages accessed by the Internet user are detected and mapped to a user path vector which is converted to a normalized weighted user path vector. A centroid vector identifies web page access patterns of users with a shared user profile attribute. The user profile attribute is assigned to the Internet user based on a comparison of the vectors. Bias values are also assigned to a set of web pages and a user profile attribute can be predicted for an Internet user based on the bias values of web pages accessed by the user. User attributes can also be predicted based on the results of an expectation maximization process. Demographic information can be predicted based on the combined results of a vector comparison, bias determination, or expectation maximization process.

Abstract: Information retrieval systems face challenging problems with delivering highly relevant and highly inclusive search results in response to a user's query. Contextual personalized information retrieval uses a set of integrated methodologies that can combine automatic concept extraction/matching from text, a powerful fuzzy search engine, and a collaborative user preference learning engine to provide accurate and personalized search results. The system can include constructing a search query to execute a search of a database, parsing an input query from a user into sub-strings, and matching the sub-strings to concepts in a semantic concept network of a knowledge base. The system can further map the matched concepts to criteria and criteria values that specify a set of constraints on and scoring parameters for the matched concepts. Furthermore, the system can learn user preferences to construct one or more profiles, including combined internal and profile weights, for producing personalized search results.

Abstract: Methods, systems, and apparatus, including computer program products, for providing ranking services. In one aspect, first signals are received from a first subscriber, and second signals are received from a second subscriber. The signals include information characterizing individual user actions relating to individual ones of first or second resources, respectively, values for one or more predefined parameters, and values for one or more first subscriber-specific parameters that are specific to the first or second subscriber, respectively. First ranking data is generated from the first signals, but not from values for any subscriber-specific parameter that is not a subscriber-specific parameter for the first subscriber. Second ranking data is generated from the second signals, but not from values for any subscriber-specific parameter that is not a subscriber-specific parameter for the second subscriber.

Abstract: A computer-implemented system provides a browse tree in which items represented within a database are arranged within a hierarchy of item categories. Each time a user selects an item, an amount of credit is cumulatively assigned to the ancestor nodes (categories) of the selected item. The amount of credit assigned to a particular category of the browse tree over time for a given user represents the user's predicted affinity for that category. The user's relative preferences for some or all of the categories are predicted by calculating differences between the user's predicted affinities for such categories and the predicted affinities of a population of users for such categories. Scores reflective of these relative category preferences are used to provide personalized recommendations or other personalized content to the user.

Abstract: A user profile and/or the suggestions computed based thereon are obtained taking a special set of user features into account. The user features are defined to represent a typical general behaviour of an individual user in respect to the application where the user profile is used. In other words, for each application where a user profile is used a special set of user features are defined which are able to represent a typical general behaviour of an individual user. Based on these user features the weights in the list of word-weight pairs or weighted keywords which represents the user profile are computed or influenced during the creation of the user profile, and/or a mufti-user profile is split during the creation of an individual user profile from a mufti-user profile, and/or during specification of a suggestion a user history which is used to create the user profile, and/or the user profile, and/or the suggestion results are filtered.

Abstract: A method and apparatus for optimizing content on a topic page includes receiving a query for a topic at a topic page on a client and transmitting the query from the topic page on the client to a web application on a server. The web application includes algorithm to analyze the query to identify a plurality of content modules that match the query. The content modules are identified from anyone of a branded source or an un-branded source. One or more module performance indicators are computed for each of the identified content modules. An aggregate module performance indicator for each of the plurality of content modules is generated from the one or more computed module performance indicators. One or more content modules from the identified plurality of content modules are automatically selected for rendering on the topic page based on the aggregate module performance indicator associated with each of the identified content modules.

Abstract: A method and system for improving targeted data delivery. One method accesses a user profile based on information about a user from at least one electronic device from a set of electronic devices that is associated with the user. A targeted data offer is received, wherein the targeted data offer defines selection criteria for targeted user profiles. A determination is made as to whether the user profile satisfies the selection criteria. A non-user selected relevancy criteria based on the user profile is then utilized to characterize the targeted data offer.

Abstract: Workflows are used to automate processes. When a first workflow is performed, it may invoke a set of one or more nested workflows, workflows in other applications or services in other applications. The first workflow can be configured to pause and wait for the invoked set of one or more nested workflows, workflows in other applications, or services in other applications. Alternatively, the first workflow can be configured to proceed without waiting. Various means are disclosed for re-staring the first workflow and providing data back for the first workflow.

Abstract: A method for mood detection, comprising receiving audio data, determining a mood for the audio data based on at least one mood model, receiving user feedback of a user for the determined mood, the user feedback being on a gradual scale and indicative as to whether the determined mood corresponds to a perceived mood of the user for the audio data, and adapting the mood model based on the user feedback.

Abstract: Apparatus for syndicated data stream content provisioning, the apparatus comprising: an interaction tracker, configured to track at least one interaction of a user with at least one content object of a respective one of a group consisting of at least one syndicated data stream received on a computer device, the interaction being implicitly indicative of a preference of the user, a ranking function calculator, in communication with the interaction tracker, configured to calculate a ranking function based on the tracked interaction, and a content ranker, in communication with the ranking function calculator, configured to rank a plurality of content objects of the syndicated data streams of the group, in an order based on the calculated ranking function.

Abstract: Disclosed is a projector and data processing method and system for recommending digital media content to a user. The method and system gather statistics about the preferences of the user and/or compare the user to population data to create recommendations in accord with the preferences of the population. The population data may be qualified by demographics or other factors classifying the user. Sources of the digital media content include radio broadcast television broadcast, global computer network content, email, and personal organizing software/programs.

Abstract: One embodiment is a method that builds a website profile from keywords appearing at the website and builds a user profile from a subset of the keywords that appear in documents accessed by the user. A web page is personalized based on the user profile.

Abstract: A method of selecting and presenting content on a first system based on user preferences learned on a second system is provided. The method includes receiving a user's input for identifying items of the second content system and, in response thereto, presenting a subset of items of the second content system and receiving the user's selection actions thereof. The method includes analyzing the selected items to learn the user's content preferences for the content of the second content system and determining a relationship between the content of the first and second content systems to determine preferences relevant to items of the first content system. The method includes, in response subsequent user input for items of the first content system, selecting and ordering a collection of items of the first content system based on the user's learned content preferences determined to be relevant to the items of the first content system.

Abstract: To estimate, or predict, the relevance of items, or documents, in a set of search results, relevance information is extracted from user click data, and relational information among the documents as manifested by an aggregation of user clicks is determined from the click data. A supervised approach uses judgment information, such as human judgment information, as part of the training data used to generate a relevance predictor model, which minimizes the inherent noisiness of the click data collected from a commercial search engine.

Abstract: A web site usage pattern insight platform may be provided. User behaviors associated with web page requests, including search queries, may be captured and analyzed to provide usage pattern insights. The pattern insights may be aggregated across a plurality of users and may be used to provide recommendations for improving a system that hosts the web pages.

Abstract: Systems and methods for generating and using performance metadata associated with a media piece (e.g., music or video) are provided. An electronic device can monitor a user's workout performance while playing a particular media piece. Workout performance may include the user's rate of motion and/or one or more physiological metrics of the user. Based on the user's workout performance, the electronic device can create new or modify existing performance metadata associated with the media piece. In some embodiments, the performance metadata based on a particular user's workout performance in response to a media piece may be combined with collective performance metadata based on the workout performances of multiple users in response to the media piece. The combined performance metadata may then be stored as new collective metadata. Accordingly, the collective performance metadata can represent the average response to a media piece over multiple users.

Abstract: A method and apparatus for activity-based users' interests modeling for determining relevance of the content distributed to the users is provided. Modeling of the user's interests starts by collecting information about the actions that the user performed and about the contents that were associated with the actions. That information may be used to determine how much interest the user has had in the individual subjects up to date, and to determine which subjects became more or less important to the user over time. Further processing of the information about the interests of each of the individual users in a group of users may produce characteristics indicating the interests of the group as a whole. Additional processing may generate the information reflecting relative importance of the interests of an individual user in the group to the interests of other users in the same group.

Abstract: Methods of inferring user preferences using ontologies use ontology structure based similarity and an inference mechanism in defining ontology filtering (OF). Items are recommended to users by identifying items that the users may prefer, but may not have been aware of. This is performed by computing personalized scores for concepts and selecting an instance having a highest score.

Abstract: A content searching and presentation method in a terminal of an original user having a playlist includes the steps of accessing a playlist of a different user from the terminal and obtaining the playlist of the different user; computing a similarity between the obtained playlist of the different user and the playlist of the original user, which is a playlist owned by the terminal, in accordance with a predetermined computation equation; and presenting, as a searched result, content that is contained in the playlist of the different user and that is not contained in the playlist owned by the terminal when the computed similarity exceeds a predetermined threshold value.

Abstract: A method of selecting and presenting content based on learned user preferences is provided. The method includes receiving search input from the user for identifying desired content items and receiving content selection actions from the user. The method further includes analyzing the date, day, and time of content selection actions by the user and analyzing descriptive terms associated with the selected content items to learn a periodicity of user selections of similar content items. In response to subsequent searches by the user, the method calls for selecting and ordering a collection of content items for presentation to the user based on comparing the user's search input to descriptive terms associated with content items and based on the learned periodicities of the user.

Abstract: A computer-implemented system provides a browse tree in which items represented within a database are arranged within a hierarchy of item categories. Each time a user selects an item, an amount of credit is cumulatively assigned to the ancestor nodes (categories) of the selected item. The amount of credit assigned to a particular category of the browse tree over time for a given user represents the user's predicted affinity for that category. The user's relative preferences for some or all of the categories are predicted by calculating differences between the user's predicted affinities for such categories and the predicted affinities of a population of users for such categories. Scores reflective of these relative category preferences are in-turn used to provide personalized recommendations or other personalized content to the user.

Abstract: A method of selecting and presenting content on a first system based on user preferences learned on a second system is provided. The method includes receiving a user's input for identifying items of the second content system and, in response thereto, presenting a subset of items of the second content system and receiving the user's selection actions thereof. The method includes analyzing the selected items to learn the user's content preferences for the content of the second content system and determining a relationship between the content of the first and second content systems to determine preferences relevant to items of the first content system. The method includes, in response subsequent user input for items of the first content system, selecting and ordering a collection of items of the first content system based on the user's learned content preferences determined to be relevant to the items of the first content system.

Abstract: Information retrieval systems face challenging problems with delivering highly relevant and highly inclusive search results in response to a user's query. Contextual personalized information retrieval uses a set of integrated methodologies that can combine automatic concept extraction/matching from text, a powerful fuzzy search engine, and a collaborative user preference learning engine to provide accurate and personalized search results. The system can include constructing a search query to execute a search of a database parsing an input query from a user conducting the search of the database into sub-strings, and matching the sub-strings to concepts in a semantic concept network of a knowledge base. The system can further map the matched concepts to criteria and criteria values that specify a set of constraints on and scoring parameters for the matched concepts. Furthermore, the system can learn user preferences to construct one or more profiles for producing personalized search results.

Abstract: A method of selecting and presenting content based on inferred user preferences is provided. The method includes providing a set of content items having associated descriptive terms and receiving search inputs from an input device and presenting a corresponding subset of content items. The method includes receiving selection actions of content items and analyzing the descriptive terms associated with the selected content items to learn a composite set of preferred descriptive terms of the plurality of users of the input device. The method includes inferring preferences of individual users from the composite set of preferred descriptive terms by decomposing the composite set of preferred descriptive terms into individual sets of preferred descriptive terms. The decomposition act utilizes prespecified statistical models of preferences.

Abstract: A method for collecting user data includes: collecting content of a user action event; modifying a user interest data model which stores user interest data according to the content of the user action event collected. In this way, the interest and concerns of the user are effectively tracked. Furthermore, the method and system provided by embodiments of the invention features little disturbance to user and accurate collection of user information, thus effectively shows the interest of user. Through method and system provided by embodiments of the invention, the user data can be collected effectively and the interest of the user is well represented.

Abstract: Methods and systems for searching comprise presenting a first information set to a user, receiving feedback, applying an evolutionary algorithm based on the feedback to generate a search query, causing the search query to be executed to generate a second information set, and presenting the second information set to the user. Then, in response to user input, the first information set is again presented to the user; feedback is again received, an evolutionary algorithm is again applied based on the feedback to generate a search query, and the new search query is caused to be executed to generate a third information set which is presented to the user.

Abstract: A system and method for adaptive marketing using insight driven customer interaction. The invention uses a closed-loop process for developing insight that may be used to refine further customer interactions. Results of a first customer interaction such as a marketing campaign are stored in a database. The results may be used to retrain predictive models and gain new insights regarding how customers are responding to marketing campaigns. The insights may be used to refine the offers delivered to customers or to extend additional offers in an effort to increase the likelihood that customers will redeem the offers. After each marketing campaign, the results are stored in the database. New and/or modified offers are created based on insights provided by the results of past campaigns. This process may be repeated such that subsequent campaigns are based on insights generated by the predictive models. The insight enables businesses to better target customers with better offers.

Abstract: Methods, systems, and products are disclosed for characterizing a target system. A query is sent. The query includes an ontology of interest, a predicate, and a scoring algorithm. The predicate describes a membership qualification for a node in the ontology of interest. A response is received comprising a score. The score represents an evaluation of the predicate to metadata associated with the target system. The score represents how well the metadata matches the ontology of interest.

Abstract: Computer-readable media, computerized methods, and graphical user interfaces (GUI's) for interactively presenting features within the panes of a display area rendered in a GUI workspace are provided. Initially, a computing device memory is inspected to discover a profile that accommodates a user-visual pattern. When the profile is not discovered, a default page layout is retrieved and communicated to the display device for presentation within the display area. If the profile is discovered, commonly viewed screen locations, based upon a frequency of eye fixation upon each of the screen locations, are ordered. Contextually relevant features are selected for presentation within the display area. The selected features are ranked based on predetermined criteria and each associated with the commonly viewed screen locations by comparing the ranking with the ordering.

Abstract: The present invention provides systems and methods that rank search results. Such ranking typically includes determining a relevance of individual search results via one or more feature-based relevance functions. These functions can be tailored to users and/or applications, and typically are based on scoped information (e.g., lexical), digital artifact author related attributes, digital artifact source repository attributes, and/or relationships between features, for example. In addition, relevance functions can be generated via training sets (e.g., machine learning) or initial guesses that are iteratively refined over time. Upon determining relevance, search results can be ordered with respect to one another, based on respective relevances. Additionally, thresholding can be utilized to mitigate returning results likely to be non-relevant to the query, user and/or application.

Abstract: A system and method of generating a playlist of affinity related media files using affinity relationship data. In one aspect the relationship affinity data is based upon a user rating score obtained from a population of user's ratings associated with media file attributes. In one aspect, a media file attribute which can include an artist, album, title, and genre information associated with a media file is received from a user, indicating the user's desire to create an affinity playlist of media files having an affinity relationship based upon the selected media file attribute.

Abstract: Xml pages are obtained from knowledge bases that contain step by step instructions. The xml pages are presented as “active content,” by which we mean a series of prompted questions and answers. A user's interactions with the active content is recorded so that the results may be copied to the user's clipboard for automatic transfer to a problem management/ticketing system. Active content that contains embedded questions asked of the user may be used to infer answers to some of the questions from a search query, and, thus, alleviate the need for the user to answer them.

Abstract: A method of selecting and presenting content based on inferred user preferences is provided. The method includes providing a set of content items having associated descriptive terms and receiving search inputs from an input device and presenting a corresponding subset of content items. The method includes receiving selection actions of content items and analyzing the descriptive terms associated with the selected content items to learn a composite set of preferred descriptive terms of the plurality of users of the input device. The method includes inferring preferences of individual users from the composite set of preferred descriptive terms by decomposing the composite set of preferred descriptive terms into individual sets of preferred descriptive terms. The decomposition act utilizes prespecified statistical models of preferences.

Abstract: A method and a system for maintaining the freshness of a search engine server's database. A popularity parameter is defined, and a popularity value is assigned to each link in the search engine's database. The most popular links are selected for updating the contents stored, or associated with, the site to which the links refer. In one embodiment, popularity is based at least in part on the search results generated by the search engine in response to user queries.

Abstract: A multidimensional method and apparatus for adaptively characterizing and aggregating data through a secure automated means of database modification, a prioritization and weighting system, a third party enhanced metadata entry and classification mechanism, adaptive and time varying individual personality and preference characterization, and an aggregation and delivery capability which allows for multiple data formats and mediums. Individual characterization incorporates an inference engine which formulates client composite images which vary with time. Asynchronous data interchanges enabled through the use of XML allow for more efficient and effective resource utilization and time. The knowledge system of this invention A) effectively integrates information from diverse sources, B) verifies, adds to or enhances source metadata (product data sheet; article title), and C) searches, queries, retrieves, and aggregates information.