Patents by Inventor Simon Tong

Simon Tong has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 10452718
    Abstract: A stopword detection component detects stopwords (also stop-phrases) in search queries input to keyword-based information retrieval systems. Potential stopwords are initially identified by comparing the terms in the search query to a list of known stopwords. Context data is then retrieved based on the search query and the identified stopwords. In one implementation, the context data includes documents retrieved from a document index. In another implementation, the context data includes categories relevant to the search query. Sets of retrieved context data are compared to one another to determine if they are substantially similar. If the sets of context data are substantially similar, this fact may be used to infer that the removal of the potential stopword(s) is not material to the search. If the sets of context data are not substantially similar, the potential stopword can be considered material to the search and should not be removed from the query.
    Type: Grant
    Filed: October 18, 2017
    Date of Patent: October 22, 2019
    Assignee: GOOGLE LLC
    Inventors: Simon Tong, Uri Lerner, Amit Singhal, Paul Haahr, Steven Baker
  • Patent number: 10229166
    Abstract: The present disclosure includes systems and techniques relating to ranking search results of a search query. In general, the subject matter described in this specification can be embodied in a computer-implemented method that includes determining a measure of relevance for a document result within a context of a search query for which the document result is returned, the determining being based on a first number in relation to a second number, the first number corresponding to longer views of the document result, and the second number corresponding to at least shorter views of the document result; and outputting the measure of relevance to a ranking engine for ranking of search results, including the document result, for a new search corresponding to the search query. The subject matter described in this specification can also be embodied in various corresponding computer program products, apparatus and systems.
    Type: Grant
    Filed: October 25, 2017
    Date of Patent: March 12, 2019
    Assignee: Google LLC
    Inventors: Hyung-Jin Kim, Simon Tong, Noam M. Shazeer, Michelangelo Diligenti
  • Publication number: 20190062261
    Abstract: The present invention provides a compound, and method of inhibiting the activity of a Fatty Acid Binding Protein (FABP) comprising contacting the FABP with a compound, said compound having the structure: Formula (I)
    Type: Application
    Filed: March 10, 2017
    Publication date: February 28, 2019
    Applicant: The Research Foundation for the State University of New York
    Inventors: Iwao Ojima, Dale Deutsch, Martin Kaczocha, Kongzhen Hu, Simon Tong, Matthew Elmes, Su Yan
  • Patent number: 10162895
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for correcting entity names. One method includes receiving texts and deriving a plurality of name-context pairs from the texts. The method further includes calculating a context consistency measure for each name-context pair and storing context-entity name data representing the name-context pairs. Another method includes identifying an entity name and one or more context terms from a query and generating candidate names for the entity name. The method further includes determining a score for each of the candidate names, selecting a number of top scoring candidate names, and using the selected candidate names to respond to the query.
    Type: Grant
    Filed: February 9, 2015
    Date of Patent: December 25, 2018
    Assignee: Google LLC
    Inventors: Lawrence J. Brunsman, Matthieu Devin, Uri N. Lerner, Simon Tong
  • Patent number: 10055461
    Abstract: A system ranks documents based, at least in part, on a ranking model. The ranking model may be generated to predict the likelihood that a document will be selected. The system may receive a search query and identify documents relating to the search query. The system may then rank the documents based, at least in part, on the ranking model and form search results for the search query from the ranked documents.
    Type: Grant
    Filed: July 31, 2015
    Date of Patent: August 21, 2018
    Assignee: Google LLC
    Inventors: Jeremy Bem, Georges R. Harik, Joshua L. Levenberg, Noam M. Shazeer, Simon Tong
  • Patent number: 10002201
    Abstract: Methods and systems allow users to enter natural language terms that describe a particular web site into an address field of a browser instead of a formal URL. The terms are evaluated to determine whether they correspond, with a high likelihood, to a particular web site. If so, this web site may be immediately accessed. If not, a list of search results based on the terms may be displayed by the browser.
    Type: Grant
    Filed: September 23, 2015
    Date of Patent: June 19, 2018
    Assignee: Google LLC
    Inventors: John Piscitello, Xuefu Wang, Simon Tong, Breen Hagan
  • Patent number: 9948699
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage medium, for identifying a set of items of digital content displayed to a user; processing the set of items to identify a set of boost items, items within the set of boost items to be prominently displayed, processing comprising: receiving a close-ties score associated with a respective item, the close-ties score representing a relationship between the user and other users associated with the respective item and an importance of a social circle associated with the item to the user, determining that the close-ties score associated with the respective item exceeds a threshold close-ties score, and in response to determining that the close-ties score exceeds the threshold close-ties score, adding the respective item to the set of boost items; providing instructions for boosting a display of items in the set of boost items in a page displayed to the user.
    Type: Grant
    Filed: June 26, 2015
    Date of Patent: April 17, 2018
    Assignee: Google LLC
    Inventors: Benjamin Tauber, Sachin Jain, Boris Mazniker, Shimrit Ben-Yair, Simon Tong
  • Patent number: 9858590
    Abstract: Different ad selection techniques may be evaluated and compared by (i) combining ads generated using at least two different techniques and (ii) determining performance statistics of these combined (e.g., interleaved) advertising serves over time. The relative performance of the different techniques can then be determined. These principles can also be used to gauge different ad scoring techniques. These principles can also be used to gauge different ad rendering techniques.
    Type: Grant
    Filed: December 30, 2003
    Date of Patent: January 2, 2018
    Assignee: Google Inc.
    Inventors: Jeffrey A. Dean, Georges R. Harik, Noam Shazeer, Simon Tong
  • Patent number: 9817920
    Abstract: A stopword detection component detects stopwords (also stop-phrases) in search queries input to keyword-based information retrieval systems. Potential stopwords are initially identified by comparing the terms in the search query to a list of known stopwords. Context data is then retrieved based on the search query and the identified stopwords. In one implementation, the context data includes documents retrieved from a document index. In another implementation, the context data includes categories relevant to the search query. Sets of retrieved context data are compared to one another to determine if they are substantially similar. If the sets of context data are substantially similar, this fact may be used to infer that the removal of the potential stopword(s) is not material to the search. If the sets of context data are not substantially similar, the potential stopword can be considered material to the search and should not be removed from the query.
    Type: Grant
    Filed: February 23, 2015
    Date of Patent: November 14, 2017
    Assignee: Google LLC
    Inventors: Simon Tong, Uri Lerner, Amit Singhal, Paul Haahr, Steven Baker
  • Patent number: 9811566
    Abstract: The present disclosure includes systems and techniques relating to ranking search results of a search query. In general, the subject matter described in this specification can be embodied in a computer-implemented method that includes determining a measure of relevance for a document result within a context of a search query for which the document result is returned, the determining being based on a first number in relation to a second number, the first number corresponding to longer views of the document result, and the second number corresponding to at least shorter views of the document result; and outputting the measure of relevance to a ranking engine for ranking of search results, including the document result, for a new search corresponding to the search query. The subject matter described in this specification can also be embodied in various corresponding computer program products, apparatus and systems.
    Type: Grant
    Filed: January 11, 2016
    Date of Patent: November 7, 2017
    Assignee: Google Inc.
    Inventors: Hyung-Jin Kim, Simon Tong, Noam M. Shazeer, Michelangelo Diligenti
  • Patent number: 9703837
    Abstract: The subject matter of this specification can be implemented in, among other things, a computer-implemented method including determining an affinity score representing an affinity of a user with respect to a contact of the user, wherein the affinity score is an indication of a strength of a relationship between the user and the contact, determining an engagement score of the user with respect to the contact, wherein the engagement score in an indication of a probability of the user engaging with a content item associated with the contact, determining an interest score of the user with respect to the contact based on the affinity score and the engagement score and providing a plurality of content items posted by the contact display in an activity stream, the content items being ordered based on the interest score. Other aspects can include corresponding systems, apparatus and computer program products.
    Type: Grant
    Filed: September 27, 2013
    Date of Patent: July 11, 2017
    Assignee: GOOGLE INC.
    Inventors: Junbin Teng, Simon Tong, Boris Mazniker
  • Patent number: 9639579
    Abstract: A system receives a search query from a user and searches a group of repositories, based on the search query, to identify, for each of the repositories, a set of search results. The system also identifies one of the repositories based on a likelihood that the user desires information from the identified repository and presents the set of search results associated with the identified repository.
    Type: Grant
    Filed: July 27, 2015
    Date of Patent: May 2, 2017
    Assignee: GOOGLE INC.
    Inventors: Michael Angelo, David Braginsky, Jeremy Ginsberg, Simon Tong
  • Patent number: 9477758
    Abstract: In one aspect, the present disclosure can be embodied in a method that includes identifying a collection of entities from one or more data sources, calculating a score for subsets of entities from the collection based on one or more seed entities associated with the collection, identifying one or more entities from each of the subsets based on the calculated score, assigning the calculated score to the identified one or more entities from the respective subset, and ranking the one or more entities based on the assigned score, so as to identify entities in the collection that are related to the one or more seed entities.
    Type: Grant
    Filed: July 19, 2012
    Date of Patent: October 25, 2016
    Assignee: GOOGLE INC.
    Inventors: Simon Tong, Jeffrey Adgate Dean, Sanjay Ghemawat
  • Patent number: 9298852
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reranking query completions based on activity session data. One of the methods includes receiving a query prefix from a user. Query completions are obtained for the query prefix. One or more likely queries that are likely to co-occur with a reference query in user activity sessions are obtained. If one of the likely queries matches one of the query completions, a modified ranking of the query completions is determined, including boosting a ranking of matching query completions. The modified ranking of the query completions is provided in response to receiving the query prefix.
    Type: Grant
    Filed: June 27, 2013
    Date of Patent: March 29, 2016
    Assignee: Google Inc.
    Inventors: Emanuel Taropa, Jeffrey A. Dean, Simon Tong, Nitin Gupta, Noam M. Shazeer, Anwis Das, Murtaza A. Basrai
  • Patent number: 9256694
    Abstract: Methods and systems allow users to enter natural language terms that describe a particular web site into an address field of a browser instead of a formal URL. The terms are evaluated to determine whether they correspond, with a high likelihood, to a particular web site. If so, this web site may be immediately accessed. If not, a list of search results based on the terms may be displayed by the browser.
    Type: Grant
    Filed: June 27, 2008
    Date of Patent: February 9, 2016
    Assignee: Google Inc.
    Inventors: John Piscitello, Xuefu Wang, Simon Tong, Breen Hagan
  • Publication number: 20160012112
    Abstract: Methods and systems allow users to enter natural language terms that describe a particular web site into an address field of a browser instead of a formal URL. The terms are evaluated to determine whether they correspond, with a high likelihood, to a particular web site. If so, this web site may be immediately accessed. If not, a list of search results based on the terms may be displayed by the browser.
    Type: Application
    Filed: September 23, 2015
    Publication date: January 14, 2016
    Inventors: John Piscitello, Xuefu Wang, Simon Tong, Breen Hagan
  • Patent number: 9235627
    Abstract: The present disclosure includes systems and techniques relating to ranking search results of a search query. In general, the subject matter described in this specification can be embodied in a computer-implemented method that includes determining a measure of relevance for a document result within a context of a search query for which the document result is returned, the determining being based on a first number in relation to a second number, the first number corresponding to longer views of the document result, and the second number corresponding to at least shorter views of the document result; and outputting the measure of relevance to a ranking engine for ranking of search results, including the document result, for a new search corresponding to the search query. The subject matter described in this specification can also be embodied in various corresponding computer program products, apparatus and systems.
    Type: Grant
    Filed: December 30, 2013
    Date of Patent: January 12, 2016
    Assignee: Google Inc.
    Inventors: Hyung-Jin Kim, Simon Tong, Noam M. Shazeer, Michelangelo Diligenti
  • Patent number: 9218369
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for ranking images using hover data. In one aspect, a method includes determining a click count and a hover count for an image and a search query pair. The click count specifies a number of times that an image search result that includes a representation of the image has been selected when provided in response to the search query. The hover count specifies a number of times that the representation of the image has been hovered over when the image search result has been provided in response to the search query. A quality measure for the image with respect to the search query is determined. The quality measure is based on the click count and the hover count. A ranking of the image is adjusted for the search query based on the quality measure for the image.
    Type: Grant
    Filed: July 29, 2014
    Date of Patent: December 22, 2015
    Assignee: Google Inc.
    Inventors: Alexandre Petcherski, Michihiro Kuramochi, Simon Tong
  • Patent number: 9218397
    Abstract: Methods and systems for improved searching are described. In one of the described methods, a user enters a search query, and in response, a search engine receives a substantially complete initial search result set having a plurality of ranked article identifiers. The search engine automatically selects at least one of the article identifiers and provides a final result set in which the selected article identifier is ranked higher than in the initial search result set.
    Type: Grant
    Filed: November 26, 2014
    Date of Patent: December 22, 2015
    Assignee: GOOGLE INC.
    Inventors: Mark Pearson, Simon Tong
  • Publication number: 20150331868
    Abstract: A system receives a search query from a user and searches a group of repositories, based on the search query, to identify, for each of the repositories, a set of search results. The system also identifies one of the repositories based on a likelihood that the user desires information from the identified repository and presents the set of search results associated with the identified repository.
    Type: Application
    Filed: July 27, 2015
    Publication date: November 19, 2015
    Inventors: Michael ANGELO, David BRAGINSKY, Jeremy GINSBERG, Simon TONG