Microsoft Technology Licensing, LLC

Sasi Parthasarathy

Junaid Ahmed

Walter Sun

Xiao Lin Zhang

Peter Bailey

Nikhil Dandekar

Xin Chen

Yatharth Saraf

Yipeng Li

David Earl Heckerman

Jack W Stokes

Christian Seifert

Jingfeng Li

Paul Alexander Dow

Christina Colcernian

Yajie Siamwalla

Long Lu

Navaneethan Santhanam

Methods, systems, and computer-readable media are provided for updating a search index with new uniform resource locators (URLs) and spiking URLs with increased user interest. History data, provided from browser applications residing on users' computers that indicate URLs accessed by the users, is parsed to identify new/previously unknown URLs. The history data also indicates URLs in which there is increased interest based on a number of recent hits as compared to an average number of hits determined over time. Author postings of new URLs to social networking sites and a quality rating of the authors may also be used to identify and filter new URLs. Search indexes are updated with the new and spiking URL data. As such, lag time between posting of new URLs and spiking of URL interest and inclusion of this data in a search index is greatly decreased.

Updating a search index using reported browser history data

Methods, systems, and media are provided for delivering clustered search results for recent and non-recent events by maintaining the identification (ID) numbers of the respective clustered documents beyond the 'fresh' life span of the clustered documents. When clusters are formed according to similar content, an ID number and associated attributes are assigned to each of the clusters. This provides a mechanism to track and retrieve the respective clusters for subsequent delivery of search results. The respective ID numbers of the clusters are maintained, even after the documents are no longer considered 'fresh.' These similar-content clusters are further subdivided according to publication date. This provides individual subdivided clusters for similar content events that occurred at different time spans, which are delivered along with individual non-clustered search results in a SERP.

Clustering web pages on a search engine results page

Methods, systems, and computer-readable media are provided for updating a search index with new uniform resource locators (URLs) and with metadata for new and known URLs. Data associated with communications made by users using a social network is received. The communications include a URL therein that a user has shared, posted, or otherwise communicated to one or more other users using the social network. When the URL is not found in a search index it is identified as a new URL and is added to the search index. A measure of a trending interest, or virality, of the URL is determined from the data. The determined virality is associated with the URL in a search index as metadata. The virality is useable to inform a ranking of the URL against a plurality of other URLs for identification and presentation as a search result in a search engine results page.

Using social-network data for identification and ranking of URLs

A machine-implemented method for detecting scareware includes the steps of accessing one or more landing pages to be evaluated, extracting one or more features from the landing pages, and providing a classifier to compare the features extracted from the landing pages with features of known scareware and non-scareware pages. The classifier determines a likelihood that the landing page is scareware. If determined to be scareware, the landing page is removed from search results generated by a search engine. The features can be URLs, text, image interest points, image descriptors, a number of pop-ups generated, IP addresses, hostnames, domain names, text derived from images, images, metadata, identifiers of executables, and combinations thereof.

Scareware detection

Growing community of inventors

Seattle, WA, United States of America

Sasi Parthasarathy