Yahoo! Inc.

Oath Inc.

Yahoo Assets LLC

Verizon Media Inc.

Excalibur Ip, LLC

Suju Rajan

Scott J Gaffney

Nathan Liu

Kunal Punera

Liangjie Hong

Preetam Joshi

Amit Phadke

Vishesh Joshi

Victor Laguna

Christopher Chi Kai Lam

Adwait Ratnaparkhi

Dragomir Dimitrov Yankov

Rajesh Girish Parekh

Srinivas Vadrevu

Choon Hui Teo

Paul Yiu

Erheng Zhong

Naroo Krishnan

Yue Shi

Dun Liu

Wanlin Pang

One or more techniques and/or systems for sending push notifications of content items to client devices are provided herein. For example, an input received from a user can be expanded to obtain an expanded user interest. Content items from a content source can be filtered based upon the expanded user interest to obtain a set of filtered content items. A push notification can be constructed to comprise one or more of the filtered content items from the set of filtered content items. The push notification can be sent to a client device of the user for display as a device alert notification. In an example, the filtered content items, within the push notification, may be ranked based upon a ranking metric.

Personalized search filter and notification system

The present teaching, which includes methods, systems and computer-readable media, relates to providing content from multiple disparate sources including a person's personal data sources and non-personal data sources. The disclosed techniques may include receiving a request for content from a person; obtaining first content from a first source private to the person based on the request; obtaining second content from at least one second source based on the request; blending the first content from the first source and the second content from the at least one second source to generate a blended content; and providing the blended content to the person in response to the request.

Methods, systems and techniques for blending online content from multiple disparate content sources including a personal content source or a semi-personal content source

The present teaching, which includes methods, systems and computer-readable media, relates to ranking content from multiple disparate sources including a person's personal data sources and non-personal data sources. The disclosed techniques may include obtaining a plurality sets of content associated with a request from a person, each of which being from a separate data source, and applying a model for each set of content to obtain a set of features for each piece of content in the set of content, wherein the model is specific to a data source from where the set of content comes from. Each set of features for each piece of content of the set of content may be normalized with respect to a common space to generate a normalized feature set. Further, a score for each piece of content from a set of content may be estimated based on the normalized feature set for the piece of content, and based on the score of the piece of content, each piece of content of the plurality sets of content may be ranked.

Methods, systems and techniques for ranking blended content retrieved from multiple disparate content sources

Briefly, embodiments of methods and/or systems for performing content recommendation are disclosed. For one embodiment, as an example, estimating relevance may include computing an inner product of latent factors corresponding to a plurality of users and features of one or more content items.

Content recommendation

Techniques are described by which information needs are satisfied by taking into account a variety of contextual cues that constrain the information searched. Contextual data such as the location, speed, and direction of travel of a mobile device are used to generate or modify a search query in a way that constrains the geographic region being searched to improve the relevance of search results or recommendations provided.

Region of search based on context

Embodiments of the present teachings disclose method, system, and programs that monetize personalized user behavioral profiles by remapping the users to audience segments related to advertisement. In the method, the users can be targeted with advertisements that are personalized and hence are more likely to lead to conversions.

Method and system for efficient matching of user profiles with audience segments

A method and apparatus is described for assigning functional labels to segments of web pages in an application-independent way. In the approach described herein, one of a generic set functional labels are automatically assigned to each segment of a web page, where the generic functional labels may be topic-independent and application-independent. Applications with different needs can determine which segments of the web page to process based on which functional labels correspond to the types of information needed by each application. Thus, the work of classifying the function of each segment of a web page is separated from the work of selecting which segments satisfy the need of a particular application. The work of classification can be performed in an application-independent way, relieving the burden from every application developer from having to create their own classifiers.

Annotating HTML segments with functional labels

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.

System for incrementally clustering news stories

Methods, systems, and computer programs for categorizing the sensitivity of web pages are presented. In one method, a space of sensitive pages is identified based on the sensitivity categorization of a first plurality of web pages and a second plurality of web pages. The first plurality of web pages is obtained by performing search queries using known sensitive words, and the second plurality of web pages includes randomly selected web pages. Additionally, the method identifies a third plurality of web pages that includes web pages on or near the boundary between the space of sensitive pages and the space of non-sensitive pages. The space of sensitive pages is then redefined based on the sensitivity categorization of the first, second, and third pluralities of web pages. Once the space of sensitive pages is defined, the method is used to determine that a given web page is sensitive when the given web page is in the space of sensitive pages. Web pages are included in a marketing operation when the web pages are not sensitive.

Sensitivity categorization of web pages

Methods and apparatus are described for measuring the topical coherence of a keyword set while simultaneously partitioning the set into contextually related clusters.

Measuring topical coherence of keyword sets

A system for training classifiers in multiple categories through an active learning system, including a computer having a memory and a processor, the processor programmed to: train an initial set of m binary one-versus-all classifiers, one for each category in a taxonomy, on a labeled dataset of examples stored in a database coupled with the computer; uniformly sample up to a predetermined large number of examples from a second, larger dataset of unlabeled examples stored in a database coupled with the computer; order the sampled unlabeled examples in order of informativeness for each classifier; determine a minimum subset of the unlabeled examples that are most informative for a maximum number of the classifiers to form an active set for learning; and use editorially-labeled versions of the examples of the active set to re-train the classifiers, thereby improving the accuracy of at least some of the classifiers.

System for training classifiers in multiple categories through active learning

A method and apparatus are provided for utilizing social network information to show reviews written by others. In one example, the method includes uploading at least one review written by an entity other than a particular user; filtering the at least one review according to criteria specified by the particular user; and integrating into one central location reviews written by others, wherein the reviews include the at least one review.

Growing community of inventors

Sunnyvale, CA, United States of America

Suju Rajan