Google Inc.

Yahoo! Inc.

Excalibur Ip, LLC

Sundeep Tirumalareddy

Eric Lehman

Trystan G Upstill

Henele Iitaka Adams

Neesha Subramaniam

Wensi Xi

Paul Haahr

Michael E Flaster

Daniel Glasner

Wei Fan

Thomas Richard Strohmann

Sushrut Suresh Karanjkar

Hayrettin Kolukisaoglu

Manas Ashok Pathak

Shubhang Verma

Suddha Kalyan Basu

Wenyuan Yin

Yonghui Wu

Jason W Blythe

Zhaoyang Xu

Mahsan Rofouei

Shamik Sharma

Jamie Leach

Pinank Gogri

Michael Mulvihill

Danielle Fisher

Hayrettin Kolukisiaoglu

According to an aspect, a method includes, in response to a search query for web content, obtaining, by a search engine, search results relevant to the search query, where the search results include a set of responsive documents, and generating a plurality of themes from content included in the set of responsive documents, where each of the plurality of themes includes a respective phrase that describes a respective theme. The method includes providing thematic data to a browser application on a client device, where the thematic data includes the plurality of themes and thematic search results, which may be a portion of the search results arranged by the plurality of themes. The thematic data is configured to cause the browser application to display the plurality of themes in a search results page.

Thematic search

Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for retrieving image search results using embedding neural network models. In one aspect, an image search query is received. A respective pair numeric embedding for each of a plurality of image-landing page pairs is determined. Each pair numeric embedding is a numeric representation in an embedding space. An image search query embedding neural network processes features of the image search query and generates a query numeric embedding. The query numeric embedding is a numeric representation of the image search query in the same embedding space. A subset of the image-landing page pairs having pair numeric embeddings that are closest to the query numeric embedding of the image search query in the embedding space are identified as first candidate image search results.

Embedding based retrieval for image search

Methods, systems, and apparatus, including computer program products, for identifying navigational resources for queries. In an aspect, a candidate query in a query sequence is selected, and a revised query subsequent to the candidate query in the query sequence is selected. If a quality score for the revised query is greater than a quality score threshold and a navigation score for the revised query is greater than a navigation score threshold, then a navigational resource for the revised query is identified and associated with the candidate query. The association specifies the navigational resource as being relevant to the candidate query in a search operation.

Navigational resources for queries

A system and method may add to a web page a similar-content module which may contain information related to the context of the web page, may look like a portion of the web page, and may lead to a jump page which presents information in the similar-content module in more detail and contains an advertiser's advertisement or a link to an advertiser's web page. If a user is interested in the information in the similar-content module, he may click on the module and be sent to the jump page. Displaying the similar-content module will not cost any advertiser anything. A pay per impression advertiser will not be charged until its advertisement is displayed on the jump page, and a pay per click advertiser will not be charged until its link in the jump page is clicked on.

Method and system for presenting targeted advertisements

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for ranking search results. One method includes ranking web objects in response to a search query to generate a global ranking based on a relevance of each web object to the search query and a relative authority of each web object compared to other web objects in the plurality of web objects, each web object including a web page in a corresponding website that includes a plurality of web pages; ranking the plurality of web pages corresponding to each website based on onsite ranking criteria to generate an onsite ranking; generating a combined ranking for each web page based on a combination of the global ranking of the web object that includes the web page and the onsite ranking of the web page; and presenting web pages responsive to the search query based on the combined rankings.

Ranking search results

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating synthetic descriptive text. One of the methods includes identifying a group of linking resources, wherein each of the linking resources includes a link to a respective target resource; determining, from a search engine index, that at least some of the target resources are associated with seed queries; generating term location information that identifies, for each seed query, locations of terms from the seed query in the linking resource that links to the target resource associated with the seed query; generating synthetic descriptive text for the target resources based on the term location information; and associating the synthetic descriptive text with the target resources in the search engine index.

Generating synthetic descriptive text

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using synthetic descriptive text to rank search results. One of the methods includes receiving a search query from a user device; receiving data identifying a plurality of search result resources and respective initial scores for each of the search result resources; determining, from a search engine index, that a particular search result resource of the plurality of search result resources is associated with one or more pieces of synthetic descriptive text, wherein each piece of synthetic descriptive text is generated by applying a respective template to a respective linking resource that links to the particular search result resource; computing a synthetic descriptive text score for the particular search result resource; and adjusting the initial score for the particular search result resource based at least in part on the synthetic descriptive text score.

Using synthetic descriptive text to rank search results

Onsite and offsite search ranking results

A system and method of facilitating search by color processes an image of an item to obtain its color space parameter values and/or color names based on the color space parameter values, and adds the color space parameter values and/or color names as color attribute of the item. When a user inputs a color as a search criterion, the method searches the color attributes of items, and returns a list of items matching the color selected by the user.

Method and system of facilitating search by color

A method for facilitating online shopping stores shopping cart information of users who shopped before and makes recommendations for matching products according to aggregated shopping cart information. The method finds out what products go well with a product in a user's shopping cart by collecting data about combinations of products in different categories from the shopping carts of users who shopped before. Based on the collected shopping cart data, the method recommends popular matches to the user.

Method and system of providing recommendations during online shopping

Growing community of inventors

Mountain View, CA, United States of America

Sundeep Tirumalareddy