Abstract: When a server receives a request for an information payload from a remote device, the server may determine the device's type and identify an optionally-installable application that can be used to access the information payload on devices of that type. When the optionally-installable application is not installed on the remote device, the server may store a identifier for the remote device and send the device a redirection message via which the device can obtain and install the application. Subsequently, when the server receives an installation indication from the application executing on a remote device, the server may identify the device as having recently been redirected to install the application and store or update a record indicating that an application-installation event occurred.

Abstract: A fact machine receives a comment string from a webpage and segments the comments into sub-conversations. The fact machine also identifies entities within comments or draft comments as well as a sentiment and/or attributes associated with the entity. The fact machine then queries a knowledge base for facts relating to the entity, the attributes, and/or the sentiment. The fact machine then provides the facts to a user prior to the user posting a draft comment.

Abstract: Methods, systems and computer readable media are provided for managing user generated content in relation to content. One example method includes receiving a request to access an article having descriptive content that includes one or more entities. Each entity in the article has an assigned prominence score, and the request is received from a website in response to user selection of the article. The method further includes identifying one or more media forums to relate to the article. Each media forum includes one or more discussion threads, and each media forum is associated with an interest graph that changes over time. Responsive to the request, the method selects a media forum from the one or more media forums to associate with the article based on examination of the interest graph of the media forum and the assigned prominence scores of entities in the article.

Abstract: Briefly, embodiments of methods and/or systems of detecting and image of a human face in a digital image are disclosed. For one embodiment, as an example, parameters of a neural network may be developed to generate object labels for digital images. The developed parameters may be refined by a neural network to generate signal sample value levels corresponding to probability that a human face may be depicted at a localized region of a digital image.

Abstract: An example system can include a server that includes or is associated with a keyword recommendation module. The keyword recommendation module can be configured to select keywords for a search engine for use in a search engine marketing campaign, wherein the search engine provides more traffic to Internet content of a publisher than other search engines, for the keywords. The module can also be configured to determine, per keyword, user engagement with the Internet content resulting from the traffic provided by the search engine for the keywords, according to one or more of time spent viewing the Internet content, page views of the Internet content, and dwell times. The module can also be configured to score, per keyword, the keywords according to the determined user engagement with the Internet content, and generate keyword recommendations according to the scoring of the keywords.

Abstract: Systems, methods, and apparatuses are disclosed for generating mapping data structures based on predicted relationships across tracking data obtained from tracking online browsing histories of users to a network of websites.

Abstract: A method comprises retrieving a profile of a given user, the given user having a given-user device; delivering a content item to the given-user device; receiving one or more user-specified tags associated with the content item; identifying one or more buddies of the user as indicated in the profile; and delivering the one or more tags to the one or more buddies.

Abstract: A computer implemented method includes: receiving an incomplete input from a user; presenting a plurality of suggestions to the user for completion of the input, wherein the suggestions are presented in a ranked order based on a characteristic associated with the user terminal; receiving a selection by the user of a suggestion from the suggestions; and completing the input with the suggestion.

Abstract: A method includes: generating profile data for users including a first user, the profile data related to contacts or persons used in messages to or from each user; generating, via a server platform, parameters corresponding to the profile data for ranking contacts or persons; and transmitting the parameters to client devices to allow each client device to determine ranks of contacts or persons in the profile data based on the parameters and a function that uses the parameters.

Abstract: Systems and methods consistent with the present innovations are directed to implementations involving creation, viewing, playing, sharing and/or utilization of information modules, such as mixed-media modules. Various embodiments relating to aspects of server processing, media searching, user interface and/or other features are disclosed.

Abstract: Methods and systems are provided for enabling presentation of supplemental application content to display devices while particular content is rendered on the display device. One example method includes receiving a request, at a server, to register a display device. The display device has hardware for communication over the Internet with the server. The display device further includes hardware for communication with a broadcast television provider that provides broadcast content to the display device. The method also includes registering the display device with the server. The registering includes receiving attributes of the display device. Also included is receiving information, at the server, regarding content rendered on the display device, and sending to the display device application data for at least one of the applications of the display device. The application data is correlated to the content rendered on the display device.

Abstract: A search query for searching electronic messages, such as email, may be used to search for different types of items, such as and without limitation electronic messages, contacts, photos, documents, such as and without limitation papers, presentations, etc., business entities, personal information extracted from messages, such as and without limitation purchase orders, shipments, reservations, travel itineraries, etc. Several sources of data, which may be indexed for searching, such as and without limitation a personal mail search index, contacts, or business entity, index, attachments index, extracted data index, etc. may be searched using the search query. A number of top search result items, which may include different types of items, may be presented apart from other search result items.

Abstract: Methods and system for providing a list of recommended items in response to a query includes obtaining user navigation information relevant to the query from a plurality of user access logs associated with the plurality of users. The user access logs define the navigation sequence followed by a plurality of users for a plurality of queries. The navigation sequence represents the users browsing behavior and identifies answers to the queries. A set of temporal parameters for analyzing the user navigation information is identified. The temporal parameters define time frame for analyzing the user navigation information. A list of recommended items to navigate is dynamically generated by analyzing user navigation information obtained from user access logs using temporal parameters. The generated list includes items that are most relevant to the query. The generated list of items is returned in response to the query and represents an optimal result.

Abstract: Systems and methods for generation of a relationship history or text for a new message. In one embodiment, a method includes: scanning, by a computing device, a set of messages to or from a user to generate a plurality of profiles for persons associated with the messages, each person being a sender or a recipient of at least one of the set of messages, and the persons including a first person; generating, via the computer, a relationship history using the plurality of profiles, wherein the relationship history is for a relationship between the user and the first person; and presenting the relationship history to the user.

Abstract: In a client-server system where a client system presents a browser for user interaction, a browser user interface includes functionality for handling dynamic interface elements received by the browser in connection with received pages, presented as part of the browser user interface and modified in response to selected user input without requiring farther interaction with a server. In addition to, or in place of, dynamic interface elements such as slide sheets, the browser user interface might also include a rotation display area, tool displays that can overlay a page, opaquely or semi-transparently, menu structures, and an ability for the user to modify a page layout without requiring server interaction.

Abstract: Users receive content recommendations from a personalized, generalized recommendation service that aggregates and selects content of high personal relevance to each individual user from a large pool of both personal and public content. The received content is filtered and the content determined to be relevant is cached. When a user request for content is received, the cached content is rescored and the content determined to be most relevant based on satisfaction of a relevance threshold is selected and forwarded to the user. Feedback methodologies are also implemented so that a user's actions are taken into consideration in real time and can affect subsequent recommendations to the user.

Abstract: A content item categorizer system retrieves content items from Internet sources. If a retrieved content item includes sufficient information for traditional categorization methods, then the system assigns one or more categories to the content item using such traditional methods. The system creates a metadata model, based on information about traditionally-categorized content items, that maps at least hashtags from the content items to one or more content categories. When the system retrieves a sparse-info item that does not include sufficient information for traditional categorization, the system applies the metadata model to categorize the content item using at least hashtags in the sparse-info item. The metadata model may also include information indicating mappings between categories and coincidence of hashtags and additional content item attributes. Also, the metadata model may provide information for categorizing sparse-info items based on multiple hashtags in the sparse-info item metadata.

Abstract: Systems and methods of natural language processing in an environment with no existing corpus are disclosed. The method includes defining an input grammar specific to a chosen domain, the input grammar having a domain specific knowledge and general grammatical knowledge. Groups of tokens are identified within the input grammar having syntactic and semantic equivalence. The identified groups are assembled into hypernyms, wherein the hypernyms include a semantic output for each token in the hypernyms. A list of fields is then combined with the hypernyms for combination with the hypernyms. A corpus of possible combinations of hypernyms and fields is created. A data structure mapping each possible combination to a partial semantic output is generated and the data structure is saved for use in later processing.

Abstract: A signature matrix is used to test each online event for inclusion of a user in a pre-generated lookalike audience. Locality Sensitive Hashing is used to compile the signature matrix to dramatically reduce memory storage requirements and processing time for each received online event. A technique of producing incremental signature matrices between generation of the full signature matrix helps to enable near-real time performance in processing each received event to see if a user associated with that event should be added to one of the lookalike audiences pre-generated by advertiser.

Abstract: Systems and methods to provide assistance for completion during user input. In one embodiment, a method includes automatically generating profiles for persons identified in messages, such as incoming and outgoing emails. When a user is typing an input, the profiles are used to identify suggestions for the completion of the user input.