Patents by Inventor Vinod Balakrishnan
Vinod Balakrishnan 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: 11893815Abstract: Disclosed are systems and methods for generating search result data based on machine-encoded text generated by computer vision optical character recognition machine learning techniques performed on digital media. The disclosed systems and methods provide a novel framework for performing machine learning visual search or machine learning text extraction techniques on digital media in order to extract and analyze the data therein and further conduct search queries based on the extracted and analyzed data. The disclosed framework may leverage the aforementioned computer vision machine learning techniques in order to provide a user with relevant search results regarding objects and text detect in digital media captured on a user device.Type: GrantFiled: December 23, 2022Date of Patent: February 6, 2024Assignee: Yahoo Assets LLCInventors: Vinod Balakrishnan, Xiaoyu Guo
-
Publication number: 20230126412Abstract: Disclosed are systems and methods for generating search result data based on machine-encoded text generated by computer vision optical character recognition machine learning techniques performed on digital media. The disclosed systems and methods provide a novel framework for performing machine learning visual search or machine learning text extraction techniques on digital media in order to extract and analyze the data therein and further conduct search queries based on the extracted and analyzed data. The disclosed framework may leverage the aforementioned computer vision machine learning techniques in order to provide a user with relevant search results regarding objects and text detect in digital media captured on a user device.Type: ApplicationFiled: December 23, 2022Publication date: April 27, 2023Inventors: Vinod BALAKRISHNAN, Xiaoyu GUO
-
Patent number: 11562586Abstract: Disclosed are systems and methods for generating search result data based on machine-encoded text generated by computer vision optical character recognition machine learning techniques performed on digital media. The disclosed systems and methods provide a novel framework for performing machine learning visual search or machine learning text extraction techniques on digital media in order to extract and analyze the data therein and further conduct search queries based on the extracted and analyzed data. The disclosed framework may leverage the aforementioned computer vision machine learning techniques in order to provide a user with relevant search results regarding objects and text detect in digital media captured on a user device.Type: GrantFiled: June 22, 2022Date of Patent: January 24, 2023Assignee: Yahoo Assets LLCInventors: Vinod Balakrishnan, Xiaoyu Guo
-
Publication number: 20220319212Abstract: Disclosed are systems and methods for generating search result data based on machine-encoded text generated by computer vision optical character recognition machine learning techniques performed on digital media. The disclosed systems and methods provide a novel framework for performing machine learning visual search or machine learning text extraction techniques on digital media in order to extract and analyze the data therein and further conduct search queries based on the extracted and analyzed data. The disclosed framework may leverage the aforementioned computer vision machine learning techniques in order to provide a user with relevant search results regarding objects and text detect in digital media captured on a user device.Type: ApplicationFiled: June 22, 2022Publication date: October 6, 2022Inventors: Vinod BALAKRISHNAN, Xiaoyu GUO
-
Patent number: 11398099Abstract: Disclosed are systems and methods for generating search result data based on machine-encoded text generated by computer vision optical character recognition machine learning techniques performed on digital media. The disclosed systems and methods provide a novel framework for performing machine learning visual search or machine learning text extraction techniques on digital media in order to extract and analyze the data therein and further conduct search queries based on the extracted and analyzed data. The disclosed framework may leverage the aforementioned computer vision machine learning techniques in order to provide a user with relevant search results regarding objects and text detect in digital media captured on a user device.Type: GrantFiled: October 18, 2019Date of Patent: July 26, 2022Assignee: Yahoo Assets LLCInventors: Vinod Balakrishnan, Xiaoyu Guo
-
Publication number: 20210085672Abstract: Described herein are solid, pharmaceutical compositions, dosage forms and methods of making and using the same, wherein the solid compositions comprise at least one high viscosity agent. The solid, high viscosity agent-comprising pharmaceutical compositions, when comprised of an opioid drug, can reduce the potential for abuse of such drug. The solid dosage forms are characterized by having a significantly reduced extractability of an opioid drug comprised therein upon contact of the dosage form with a solvent such as a typical household solvent. The solid dosage forms, following contact with a household solvent, such as an aqueous or alcoholic solvent, generate a high viscosity solution, thereby discouraging abuse of the resulting formulation via intravenous (IV) injection.Type: ApplicationFiled: July 25, 2018Publication date: March 25, 2021Inventors: Sindhuri Maddineni, Shailendra Mandge, Sourish Mukherjee, Vinod Balakrishnan Nair, Vijaya Srinivas Sekuboyina, Praveen Gaddam, Kevin J. Brodbeck, Ramakrishna Gadiraju, Xue Ge, Michael A. Eldon, Aleksandrs Odinecs, Satyanarayana Goda, Rajendra Tandale, Shiladitya Bhattacharya
-
Patent number: 9619558Abstract: Methods, systems and programming for entity recognition in a query. In one example, an index that associates an alias with one or more entities is obtained. Each of the one or more entities is associated with one or more features. A query associated with one or more features is received from a user. The alias is then identified in the query. At least one of the one or more entities is determined based, at least in part, on the features associated with each of the one or more entities and the features associated with the query.Type: GrantFiled: April 29, 2014Date of Patent: April 11, 2017Assignee: EXCALIBUR IP, LLCInventors: Sudarshan Lamkhede, Peter Mika, Vinod Balakrishnan
-
Publication number: 20150310016Abstract: Methods, systems and programming for entity recognition in a query. In one example, an index that associates an alias with one or more entities is obtained. Each of the one or more entities is associated with one or more features. A query associated with one or more features is received from a user. The alias is then identified in the query. At least one of the one or more entities is determined based, at least in part, on the features associated with each of the one or more entities and the features associated with the query.Type: ApplicationFiled: April 29, 2014Publication date: October 29, 2015Applicant: Yahoo! Inc.Inventors: Sudarshan Lamkhede, Peter Mika, Vinod Balakrishnan
-
Publication number: 20140025493Abstract: A system and method for re-targeting users includes: logging user activity within a network of users; categorizing parameters of the user activity; storing the categorized parameters; receiving a request for re-targeting; reformulating the request using a custom language definition; and running the re-formulated request against the stored categorized parameters to generate a list of users matching the request.Type: ApplicationFiled: July 20, 2012Publication date: January 23, 2014Applicant: YAHOO! INC.Inventors: Vinod Balakrishnan, Prakash Chockalingam, Amlan Haldar, Dave Morro
-
Patent number: 7664529Abstract: According to one embodiment of the invention, a method for discovering the presence of at least one source and target mobile device, automatically displaying a graphical interface to show the dataset from the source mobile device, and initiating the transmission of data between the mobile devices, is provided. The method further includes automatically receiving the dataset from the source mobile device, where the dataset is at least a representation of the data on the source device. In one embodiment, the representation is a subset of the data on the device and/or a description of the data on the mobile device. In another embodiment, a method for a navigation system to discover the presence of at least one mobile device, to automatically receive data from the mobile device, and to process the data with navigation operations, is provided.Type: GrantFiled: September 15, 2008Date of Patent: February 16, 2010Assignee: Intel CorporationInventors: Muralidharan Sundararajan, Vinod Balakrishnan, John J. Light, Trevor A. Pering, Roy Want
-
Publication number: 20090012705Abstract: According to one embodiment of the invention, a method for discovering the presence of at least one source and target mobile device, automatically displaying a graphical interface to show the dataset from the source mobile device, and initiating the transmission of data between the mobile devices, is provided. The method further includes automatically receiving the dataset from the source mobile device, where the dataset is at least a representation of the data on the source device. In one embodiment, the representation is a subset of the data on the device and/or a description of the data on the mobile device. In another embodiment, a method for a navigation system to discover the presence of at least one mobile device, to automatically receive data from the mobile device, and to process the data with navigation operations, is provided.Type: ApplicationFiled: September 15, 2008Publication date: January 8, 2009Inventors: Muralidharan Sundararajan, Vinod Balakrishnan, John J. Light, Trevor A. Pering, Roy Want
-
Patent number: 7426403Abstract: According to one embodiment of the invention, a method for discovering the presence of at least one source and target mobile device, automatically displaying a graphical interface to show the dataset from the source mobile device, and initiating the transmission of data between the mobile devices, is provided. The method further includes automatically receiving the dataset from the source mobile device, where the dataset is at least a representation of the data on the source device. In one embodiment, the representation is a subset of the data on the device and/or a description of the data on the mobile device. In another embodiment, a method for a navigation system to discover the presence of at least one mobile device, to automatically receive data from the mobile device, and to process the data with navigation operations, is provided.Type: GrantFiled: January 28, 2005Date of Patent: September 16, 2008Assignee: Intel CorporationInventors: Muralidharan Sundararajan, Vinod Balakrishnan, John L. Light, Trevor A. Pering, Roy Want
-
Techniques for implementing a communication channel with suitable properties for run time adaptation
Publication number: 20060212872Abstract: Apparatus, system, and method including a local resource to transfer information between a first processing unit and a second processing unit; and a global resource to transfer information between said first processing unit and said second processing unit, and to transfer information between said first processing unit and a third processing unit if said local resource is full are described.Type: ApplicationFiled: March 21, 2005Publication date: September 21, 2006Inventors: Arun Raghunath, Vinod Balakrishnan -
Publication number: 20060212654Abstract: A method and apparatus for intelligent instruction caching using application characteristics. In conjunction with building an application or application module, a function address map is generated identifying the location of functions to be cached in the application or module code. In conjunction with loading the application/module into system memory, a function memory map is generated in view of the function address map and the location at which the application/module was loaded, so as to define the location in system memory of the functions to be cached. In response to a cache miss for an instruction, the function memory map is searched to determine if the instruction corresponds to the first instruction of a function to be cached. If it does, the instructions corresponding to the function are loaded into the cache. In one embodiment, a first portion of the instructions are immediately loaded into the cache, while a second portion of the instructions are asynchronously loaded using a background task.Type: ApplicationFiled: March 18, 2005Publication date: September 21, 2006Inventor: Vinod Balakrishnan
-
Publication number: 20060172778Abstract: According to one embodiment of the invention, a method for discovering the presence of at least one source and target mobile device, automatically displaying a graphical interface to show the dataset from the source mobile device, and initiating the transmission of data between the mobile devices, is provided. The method further includes automatically receiving the dataset from the source mobile device, where the dataset is at least a representation of the data on the source device. In one embodiment, the representation is a subset of the data on the device and/or a description of the data on the mobile device. In another embodiment, a method for a navigation system to discover the presence of at least one mobile device, to automatically receive data from the mobile device, and to process the data with navigation operations, is provided.Type: ApplicationFiled: January 28, 2005Publication date: August 3, 2006Inventors: Muralidharan Sundararajan, Vinod Balakrishnan, John Light, Trevor Pering, Roy Want
-
Publication number: 20060136878Abstract: A method for managing code includes profiling the code to determine statistics corresponding to a first and second actor in the code, wherein the first actor transmits data to the second actor on a passive channel. The code is mapped to one or more processors during compilation in response to the statistics. Other embodiments are described and claimed.Type: ApplicationFiled: December 17, 2004Publication date: June 22, 2006Inventors: Arun Raghunath, Vinod Balakrishnan, Stephen Goglin
-
Publication number: 20060070046Abstract: Provided are a method, system, and program for allocating call stack frame entries at different memory levels to functions in a program. Functions in a program accessing state information stored in call stack frame entries are processed. Call stack frame entries are allocated to the state information for each function, wherein the call stack frame entries span multiple memory levels, and wherein one function is capable of being allocated stack entries in multiple memory levels.Type: ApplicationFiled: September 30, 2004Publication date: March 30, 2006Inventors: Vinod Balakrishnan, Ruiqi Lian, Junchao Zhang, Dz-ching Ju
-
Publication number: 20050125514Abstract: Systems and methods are disclosed for facilitating dynamic resource allocation in a limited memory environment. In one embodiment, a master code image is created that includes one or more alternative implementations of an interface. When it is determined that a particular implementation of the interface is desired, the alternative implementations are removed from the master code image, and the resulting code image is compiled. The program is then used to process network traffic. If a condition is subsequently detected that could be handled more efficiently by one of the alternative interface implementations, the process can be repeated, and the resulting program used to process further network traffic.Type: ApplicationFiled: November 21, 2003Publication date: June 9, 2005Applicant: Intel Corporation, A DELAWARE CORPORATIONInventor: Vinod Balakrishnan
-
Patent number: 6085164Abstract: The present invention relates to an inventory control method and architecture that maximizes revenues derived from the sale of a given inventory resource to a customer. More particularly, the present invention uses a continuous nested execution environment that allows a determination of a minimum acceptable price by continuously computing an optimal sale price based on current demand and supply and expected cancellations. The method described accesses a centrally located information repository and retrieves an inventory resource type and value allowing requests below the minimum acceptable price to be rejected, while requests above the minimum acceptable price can be accepted thus allowing the resource provider to maximize incoming revenues from the sale of its inventory of reservations.Type: GrantFiled: March 4, 1997Date of Patent: July 4, 2000Assignee: Sabre Inc.Inventors: Barry Craig Smith, Vinod Balakrishnan, Richard Wenman Pennefather Green