Patents by Inventor Sandeep Pandey
Sandeep Pandey 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: 11912604Abstract: The present disclosure provides a method for fabrication of a glass preform. The method includes production of soot particles in a combustion chamber using a precursor material. The heating of the precursor material produces the soot particles along with one or more impurities. In addition, the method includes agglomeration of the soot particles. Further, the method includes separation of the soot particles from the one or more impurities. Also, the separation of the soot particles is performed in a cyclone separator. Furthermore, the method includes collection of the soot particles. Also, the soot particles are compacted with facilitation of a preform compaction chamber. Also, the compacted preform is sintered with facilitation of a sintering furnace. The compaction of the soot particles followed by sintering results in formation of the glass preform.Type: GrantFiled: August 13, 2020Date of Patent: February 27, 2024Inventors: Sandeep Gaikwad, Badri Gomatam, Anand Pandey
-
Patent number: 11288702Abstract: A real-time messaging platform allows advertiser accounts to pay to insert candidate messages into the message streams requested by account holders. To accommodate multiple advertisers, the messaging platform controls an auction process that determines which candidate messages are selected for inclusion in a requested account holder's message stream. Selection is based on a bid for the candidate message, the message stream that is requested, and a variety of other factors that vary depending upon the implementation. The process for selection of candidate messages generally includes the following steps, though any given step may be omitted or combined into another step in a different implementation: targeting, filtering, prediction, ranking, and selection.Type: GrantFiled: June 19, 2020Date of Patent: March 29, 2022Assignee: Twitter, Inc.Inventors: Reid Andersen, James Neufeld, Ashish Goel, Michael Jahr, Utkarsh Srivastava, Sandeep Pandey
-
Patent number: 11270333Abstract: In some examples, a computing device includes at least one processor and at least one module, operable by the at least one processor to receive, from a client device of a user, a request for one or more advertisements to display at the client device with a set of messages. The set of messages is associated with the user in a social network messaging service. The at least one module may be further operable to determine a probability that the user will select a candidate advertisement using a machine learning model based on point-wise learning and pair-wise learning. The at least one module may be further operable to determine, based on the probability that the user will select the candidate advertisement, a candidate score for the candidate advertisement, determine that the candidate score satisfies a threshold, and send, for display at the client device, the candidate advertisement.Type: GrantFiled: May 18, 2020Date of Patent: March 8, 2022Assignee: Twitter, Inc.Inventors: Yue Lu, Parag Agrawal, Cheng Li, Sandeep Pandey, Michael Jahr, Jeremy Ginsberg
-
Patent number: 11132602Abstract: An example system includes prediction workers, training workers, and a parameter server. The prediction workers store a local copy of a machine-learned model and run the mode exclusively in serving mode. The training workers store a local copy of a machine-learned model and a local snapshot and run the local copy exclusively in training mode and compare the local model or state to the snapshot after training to send delta updates to the parameter server after training. The parameter server aggregates received delta updates into a master copy of the model, sends the aggregated updates back to training workers and provides two types of updates; a real-time update based on a comparison of the master model with a local snapshot, and a full update. The real-time update occurs at least an order of magnitude more frequently than the full update and includes a subset of the weights in the model.Type: GrantFiled: August 11, 2017Date of Patent: September 28, 2021Assignee: Twitter, Inc.Inventors: Zhiyong Xie, Yue Lu, Pengjun Pei, Gary Lam, Shuanghong Yang, Yong Wang, Ziqi Huang, Xiaojiang Guo, Van Lam, Lanbo Zhang, Bingjun Sun, Sridhar Iyer, Sandeep Pandey, Qi Li, Dong Wang
-
Publication number: 20210174398Abstract: A method for conversion attribution. The method includes obtaining a first identifier associated with a first device, obtaining a second identifier associated with a second device, bridging the first identifier and the second identifier based on a determination, made by a probabilistic classifier, that the first identifier and the second identifier are associated with a common user, and attributing, using the bridge, a conversion on a website accessed using the second device.Type: ApplicationFiled: December 7, 2020Publication date: June 10, 2021Inventors: Chinmoy Dutta, Santosh Kancha, Junjun Li, Wanchen Lu, Milind Mahajan, Sandeep Pandey, Xiaochuan Qin, Ameet Ranadive, Vibhor Rastogi, Shariq Rizvi, Abhishek Shrivastava, Yimin Wu, Lei Zhang, Ke Zhou
-
Publication number: 20210110428Abstract: In some examples, a computing device includes at least one processor and at least one module, operable by the at least one processor to receive, from a client device of a user, a request for one or more advertisements to display at the client device with a set of messages. The set of messages is associated with the user in a social network messaging service. The at least one module may be further operable to determine a probability that the user will select a candidate advertisement using a machine learning model based on point-wise learning and pair-wise learning. The at least one module may be further operable to determine, based on the probability that the user will select the candidate advertisement, a candidate score for the candidate advertisement, determine that the candidate score satisfies a threshold, and send, for display at the client device, the candidate advertisement.Type: ApplicationFiled: December 22, 2020Publication date: April 15, 2021Inventors: Yue Lu, Parag Agrawal, Cheng Li, Sandeep Pandey, Michael Jahr, Jeremy Ginsberg
-
Patent number: 10861055Abstract: A method for conversion attribution. The method includes obtaining a first identifier associated with a first device, obtaining a second identifier associated with a second device, bridging the first identifier and the second identifier based on a determination, made by a probabilistic classifier, that the first identifier and the second identifier are associated with a common user, and attributing, using the bridge, a conversion on a website accessed using the second device.Type: GrantFiled: September 23, 2019Date of Patent: December 8, 2020Assignee: Twitter, Inc.Inventors: Chinmoy Dutta, Santosh Kancha, Junjun Li, Wanchen Lu, Milind Mahajan, Sandeep Pandey, Xiaochuan Qin, Ameet Ranadive, Vibhor Rastogi, Shariq Rizvi, Abhishek Shrivastava, Yimin Wu, Lei Zhang, Ke Zhou
-
Patent number: 10692114Abstract: A real-time messaging platform allows advertiser accounts to pay to insert candidate messages into the message streams requested by account holders. To accommodate multiple advertisers, the messaging platform controls an auction process that determines which candidate messages are selected for inclusion in a requested account holder's message stream. Selection is based on a bid for the candidate message, the message stream that is requested, and a variety of other factors that vary depending upon the implementation. The process for selection of candidate messages generally includes the following steps, though any given step may be omitted or combined into another step in a different implementation: targeting, filtering, prediction, ranking, and selection.Type: GrantFiled: November 26, 2018Date of Patent: June 23, 2020Assignee: Twitter, Inc.Inventors: Reid Andersen, James Neufeld, Ashish Goel, Michael Jahr, Utkarsh Srivastava, Sandeep Pandey
-
Patent number: 10657556Abstract: In some examples, a computing device includes at least one processor and at least one module, operable by the at least one processor to receive, from a client device of a user, a request for one or more advertisements to display at the client device with a set of messages. The set of messages is associated with the user in a social network messaging service. The at least one module may be further operable to determine a probability that the user will select a candidate advertisement using a machine learning model based on point-wise learning and pair-wise learning. The at least one module may be further operable to determine, based on the probability that the user will select the candidate advertisement, a candidate score for the candidate advertisement, determine that the candidate score satisfies a threshold, and send, for display at the client device, the candidate advertisement.Type: GrantFiled: June 9, 2016Date of Patent: May 19, 2020Assignee: Twitter, Inc.Inventors: Yue Lu, Parag Agrawal, Cheng Li, Sandeep Pandey, Michael Jahr, Jeremy Ginsberg
-
Patent number: 10423985Abstract: A method for conversion attribution. The method includes obtaining a first identifier associated with a first device, obtaining a second identifier associated with a second device, bridging the first identifier and the second identifier based on a determination, made by a probabilistic classifier, that the first identifier and the second identifier are associated with a common user, and attributing, using the bridge, a conversion on a website accessed using the second device.Type: GrantFiled: February 9, 2016Date of Patent: September 24, 2019Assignee: Twitter, Inc.Inventors: Chinmoy Dutta, Santosh Kancha, Junjun Li, Wanchen Lu, Milind Mahajan, Sandeep Pandey, Xiaochuan Qin, Ameet Ranadive, Vibhor Rastogi, Shariq Rizvi, Abhishek Shrivastava, Yimin Wu, Lei Zhang, Ke Zhou
-
Patent number: 9361322Abstract: A real-time messaging platform allows advertiser accounts to pay to insert candidate messages into the message streams requested by account holders. To accommodate multiple advertisers, the messaging platform controls an auction process that determines which candidate messages are selected for inclusion in a requested account holder's message stream. Selection is based on a bid for the candidate message, the message stream that is requested, and a variety of other factors that vary depending upon the implementation. The process for selection of candidate messages generally includes the following steps, though any given step may be omitted or combined into another step in a different implementation: targeting, filtering, prediction, ranking, and selection.Type: GrantFiled: March 14, 2014Date of Patent: June 7, 2016Assignee: Twitter, Inc.Inventors: Chinmoy Dutta, Junjun Li, Vibhor Rastogi, Wanchen Lu, Sandeep Pandey, Utkarsh Srivastava
-
Patent number: 8312011Abstract: The present invention relates to methods, systems, and computer readable media comprising instructions for identifying needy queries for which additional responsive content is needed. The method of the present invention comprises receiving a query comprising one or more terms and retrieving one or more content items identified as responsive to the query, the one or more content items ranked according to one or more ranking techniques. A score is generated for the one or more ranked content items identified as responsive to the query. A determination is thereafter made as to whether the query is needy based upon a comparison of the one or more scores associated with the one or more content items identified as responsive to the query and a needy query score threshold.Type: GrantFiled: May 16, 2011Date of Patent: November 13, 2012Assignee: Yahoo! Inc.Inventors: Christopher Olston, Sandeep Pandey
-
Publication number: 20110258054Abstract: Automatic generation of bid phrases for online advertising comprising storing a computer code representation of a landing page for use with a language model and a translation model (with a parallel corpus) to produce a set of candidate bid phrases that probabilistically correspond to the landing page, and/or to web search phrases. Operations include extracting a set of raw candidate bid phrases from a landing page, generating a set of translated candidate bid phrases using a parallel corpus in conjunction with the raw candidate bid phrases. In order to score and/or reduce the number of candidate bid phrases, a translation table is used to capture the probability that a bid phrase from the raw bid phrases is generated from a bid phrase from the set of translated candidate bid phrases. Scoring and ranking operations reduce the translated candidate bid phrases to just those most relevant to the landing page inputs.Type: ApplicationFiled: April 19, 2010Publication date: October 20, 2011Inventors: Sandeep Pandey, Vanja Josifovski, Bo Pang, Andrei Zary Broder, Evgeniy Gabrilovich, Sujith Ravi
-
Publication number: 20110218991Abstract: The present invention relates to methods, systems, and computer readable media comprising instructions for identifying needy queries for which additional responsive content is needed. The method of the present invention comprises receiving a query comprising one or more terms and retrieving one or more content items identified as responsive to the query, the one or more content items ranked according to one or more ranking techniques. A score is generated for the one or more ranked content items identified as responsive to the query. A determination is thereafter made as to whether the query is needy based upon a comparison of the one or more scores associated with the one or more content items identified as responsive to the query and a needy query score threshold.Type: ApplicationFiled: May 16, 2011Publication date: September 8, 2011Applicant: YAHOO! INC.Inventors: Christopher Olston, Sandeep Pandey
-
Patent number: 7970760Abstract: Methods, systems, and computer readable media comprising instructions for identifying needy queries for which additional responsive content is needed. A method comprises receiving a query comprising one or more terms and retrieving one or more content items identified as responsive to the query, the one or more content items ranked according to one or more ranking techniques. A score is generated for the one or more ranked content items identified as responsive to the query. A determination is thereafter made as to whether the query is needy based upon a comparison of the one or more scores associated with the one or more content items identified as responsive to the query and a needy query score threshold.Type: GrantFiled: March 11, 2008Date of Patent: June 28, 2011Assignee: Yahoo! Inc.Inventors: Christopher Olston, Sandeep Pandey
-
Patent number: 7921103Abstract: Techniques described herein adaptively select materialized view fragments for persistent maintenance. During an interval of time, the selected fragments are persistently maintained in the database system, while the other non-selected fragments are not persistently maintained as materialized view fragments. Over time, the composition of the set of selected fragments may change. As queries are executed in the database system over an interval of time, statistics including the frequency of access of each currently selected fragment during that interval are generated. At the start of the next interval of time, based on these statistics, some currently selected fragments may be unselected. Some currently non-selected fragments of one or more candidate materialized views may be selected based on the statistics.Type: GrantFiled: June 20, 2008Date of Patent: April 5, 2011Assignee: Yahoo! Inc.Inventors: Chris Olston, Jayavel Shanmugasundaram, Sandeep Pandey
-
Publication number: 20110054999Abstract: An improved system and method for predicting user navigation within sponsored search advertisements is provided. A list of sponsored advertisements for display on a web page of search results may be received. A click prediction classifier may be applied to predict a click probability of each sponsored advertisement and a dwell time prediction classifier may be applied to predict a dwell time probability on web pages of a website of each sponsored advertisement. A probability of user navigation may be predicted for each sponsored advertisement using a probability of a click on each sponsored advertisement and a probability of a dwell time on web pages of a website of each sponsored advertisement. The list of the sponsored advertisements may be ranked in part by the probability of user navigation and served to a web browser executing on a client device for display on a web page of search results.Type: ApplicationFiled: August 25, 2009Publication date: March 3, 2011Applicant: Yahoo! Inc.Inventors: Joshua Attenberg, Sandeep Pandey, Torsten Suel
-
Patent number: 7899807Abstract: An improved system and method for crawl ordering of a web crawler by impact upon search results of a search engine is provided. Content-independent features of uncrawled web pages may be obtained, and the impact of uncrawled web pages may be estimated for queries of a workload using the content-independent features. The impact of uncrawled web pages may be estimated for queries by computing an expected impact score for uncrawled web pages that match needy queries. Query sketches may be created for a subset of the queries by computing an expected impact score for crawled web pages and uncrawled web pages matching the queries. Web pages may then be selected to fetch using a combined query-based estimate and query-independent estimate of the impact of fetching the web pages on search query results.Type: GrantFiled: December 20, 2007Date of Patent: March 1, 2011Assignee: Yahoo! Inc.Inventors: Christopher Olston, Sandeep Pandey
-
Publication number: 20100205213Abstract: The subject matter disclosed herein relates to returning cached object results based at least in part on a non-exact comparison with a query key.Type: ApplicationFiled: February 12, 2009Publication date: August 12, 2010Applicant: Yahoo! Inc.Inventors: Andrei Broder, Vanja Josifovski, Shanmugasundaram Ravikumar, Sandeep Pandey, Serguei Vassilvitskii, Flavio Chierichetti
-
Publication number: 20090319476Abstract: Techniques described herein adaptively select materialized view fragments for persistent maintenance. During an interval of time, the selected fragments are persistently maintained in the database system, while the other non-selected fragments are not persistently maintained as materialized view fragments. Over time, the composition of the set of selected fragments may change. As queries are executed in the database system over an interval of time, statistics including the frequency of access of each currently selected fragment during that interval are generated. At the start of the next interval of time, based on these statistics, some currently selected fragments may be unselected. Some currently non-selected fragments of one or more candidate materialized views may be selected based on the statistics.Type: ApplicationFiled: June 20, 2008Publication date: December 24, 2009Inventors: CHRIS OLSTON, JAYAVEL SHANMUGASUNDARAM, SANDEEP PANDEY