Patents by Inventor Srinath Ravindran
Srinath Ravindran 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: 11880401Abstract: Technologies for template generation using directed acyclic word graphs (DAWGs). The technologies can include receiving a first plurality of titles from a first plurality of title feeds, and sorting the first plurality of titles into a plurality of category sets. And, for each category set of the plurality of category sets, the technologies can include transforming the respective titles belonging to the category set into a trie data structure by separating words in the respective titles into nodes of the trie data structure. For each category set, the technologies can also include transforming the trie data structure into a directed acyclic word graph (DAWG) data structure. Also, for each category set, the technologies can also include generating one or more unique templates based on the DAWG data structure.Type: GrantFiled: April 15, 2022Date of Patent: January 23, 2024Assignee: YAHOO ASSETS LLCInventors: Srinath Ravindran, Mahmoudreza Abasi, Narayan Bhamidipati
-
Patent number: 11868886Abstract: One or more computing devices, systems, and/or methods for generating time-preserving embeddings are provided. User trails of user activities performed by users are generated. Frequencies at which the activities were performed are identified. Indices are assigned to a set of activities identified from the activities as having frequencies above a threshold. Activity descriptions of the set of activities are mapped to the indices to generate a vocabulary. A model is trained using the user trails, timestamps of the activities, and the vocabulary to learn a set of time-preserving embeddings.Type: GrantFiled: January 25, 2021Date of Patent: January 9, 2024Assignee: Yahoo Assets LLCInventors: Jelena Gligorijevic, Ivan Stojkovic, Martin Pavlovski, Shubham Agrawal, Djordje Gligorijevic, Srinath Ravindran, Richard Hin-Fai Tang, Shabhareesh Komirishetty, Chander Jayaraman Iyer, Lakshmi Narayan Bhamidipati
-
Publication number: 20230418829Abstract: One or more computing devices, systems, and/or methods are provided. In an example, an internet resource identification item associated with one or more internet resources may be identified. User activity information associated with a plurality of events may be analyzed to determine a plurality of sets of text associated with the internet resource identification item, wherein each set of text of the plurality of sets of text is associated with an event, of the plurality of events, associated with an internet resource of the one or more internet resources. A plurality of term representations may be determined based upon the plurality of sets of text. A user intention-based representation associated with the internet resource identification item may be generated based upon the plurality of term representations. A content item may be selected for presentation via a client device based upon the user intention-based representation.Type: ApplicationFiled: September 11, 2023Publication date: December 28, 2023Inventors: Chander Jayaraman Iyer, Ivan Stojkovic, Eric Ye, Lakshmi Narayan Bhamidipati, Srinath Ravindran, Shubham Agrawal
-
Publication number: 20230316328Abstract: This teaching relates to predictive targeting. Training data are obtained with pairs of data. Each pair includes an ad opportunity context corresponding to an ad served to a plurality of audiences and a label vector having a plurality of labels, each of which indicates a reaction, with respect to the ad served, of a corresponding one of the audiences in the ad opportunity context. Based on the training data, model parameters of a joint predictive model are learned via machine learning based on an initialized model with initial model parameters by minimizing a loss in an iterative process. The learned joint predictive model is to be used to map an input context of an ad opportunity to an output label vector having a plurality of probabilities, each of which predicts a likelihood of a reaction of a corresponding one of the audiences to the input context of the ad opportunity.Type: ApplicationFiled: April 1, 2022Publication date: October 5, 2023Inventors: Martin Pavlovski, Djordje Gligorijevic, Jelena Gligorijevic, Ivan Stojkovic, Srinath Ravindran, Shubham Agrawal, Narayan Bhamidipati
-
Patent number: 11755594Abstract: One or more computing devices, systems, and/or methods are provided. In an example, an internet resource identification item associated with one or more internet resources may be identified. User activity information associated with a plurality of events may be analyzed to determine a plurality of sets of text associated with the internet resource identification item, wherein each set of text of the plurality of sets of text is associated with an event, of the plurality of events, associated with an internet resource of the one or more internet resources. A plurality of term representations may be determined based upon the plurality of sets of text. A user intention-based representation associated with the internet resource identification item may be generated based upon the plurality of term representations. A content item may be selected for presentation via a client device based upon the user intention-based representation.Type: GrantFiled: April 13, 2022Date of Patent: September 12, 2023Assignee: Yahoo Ad Tech LLCInventors: Chander Jayaraman Iyer, Ivan Stojkovic, Eric Ye, Lakshmi Narayan Bhamidipati, Srinath Ravindran, Shubham Agrawal
-
Publication number: 20220237220Abstract: Technologies for template generation using directed acyclic word graphs (DAWGs). The technologies can include receiving a first plurality of titles from a first plurality of title feeds, and sorting the first plurality of titles into a plurality of category sets. And, for each category set of the plurality of category sets, the technologies can include transforming the respective titles belonging to the category set into a trie data structure by separating words in the respective titles into nodes of the trie data structure. For each category set, the technologies can also include transforming the trie data structure into a directed acyclic word graph (DAWG) data structure. Also, for each category set, the technologies can also include generating one or more unique templates based on the DAWG data structure.Type: ApplicationFiled: April 15, 2022Publication date: July 28, 2022Inventors: Srinath RAVINDRAN, Mahmoudreza ABASI, Narayan BHAMIDIPATI
-
Publication number: 20220237442Abstract: One or more computing devices, systems, and/or methods for generating time-preserving embeddings are provided. User trails of user activities performed by users are generated. Frequencies at which the activities were performed are identified. Indices are assigned to a set of activities identified from the activities as having frequencies above a threshold. Activity descriptions of the set of activities are mapped to the indices to generate a vocabulary. A model is trained using the user trails, timestamps of the activities, and the vocabulary to learn a set of time-preserving embeddings.Type: ApplicationFiled: January 25, 2021Publication date: July 28, 2022Inventors: Jelena Gligorijevic, Ivan Stojkovic, Martin Pavlovski, Shubham Agrawal, Djordje Gligorijevic, Srinath Ravindran, Richard Hin-Fai Tang, Shabhareesh Komirishetty, Chander Jayaraman Iyer, Lakshmi Narayan Bhamidipati
-
Patent number: 11308141Abstract: Technologies for template generation using directed acyclic word graphs (DAWGs). The technologies can include receiving a first plurality of titles from a first plurality of title feeds, and sorting the first plurality of titles into a plurality of category sets. And, for each category set of the plurality of category sets, the technologies can include transforming the respective titles belonging to the category set into a trie data structure by separating words in the respective titles into nodes of the trie data structure. For each category set, the technologies can also include transforming the trie data structure into a directed acyclic word graph (DAWG) data structure. Also, for each category set, the technologies can also include generating one or more unique templates based on the DAWG data structure.Type: GrantFiled: December 26, 2018Date of Patent: April 19, 2022Assignee: YAHOO ASSETS LLCInventors: Srinath Ravindran, Mahmoudreza Abasi, Narayan Bhamidipati
-
Patent number: 11019379Abstract: One or more computing devices, systems, and/or methods for selecting content for transmission to devices are provided. First activity performed using a content interface on a device may be detected. First activity information associated with the first activity may be stored in an activity profile associated with the device. An activity database may be analyzed based upon the activity profile to identify one or more activity identifiers of the activity database. The activity database may comprise a plurality of activity identifiers and/or funnel stage tags associated with the plurality of activity identifiers. A request for content, associated with an entity, may be received from the device. A funnel stage score may be determined based upon one or more funnel stage tags associated with the entity and/or the one or more activity identifiers. A content item, associated with the entity, may be selected based upon the funnel stage score.Type: GrantFiled: December 10, 2018Date of Patent: May 25, 2021Assignee: Verizon Media Inc.Inventors: Shaunak Mishra, Richard Hin-Fai Tang, Yichao Zhou, Vishal Ramesh Raithatha, Lakshmi Narayan Bhamidipati, Mahmoudreza Abasi, Srinath Ravindran
-
Publication number: 20210103953Abstract: One or more computing devices, systems, and/or methods are provided. A user profile database may be analyzed to identify a first plurality of user profiles and/or a second plurality of user profiles. A user profile of the first plurality of user profiles may be indicative of activity associated with a content item of the one or more first content items when the one or more first content items are trending. A user profile of the second plurality of user profiles may be indicative of activity associated with a content item of the one or more first content items when the one or more first content items are not trending. A first conversion score associated with a first entity may be determined based upon the first plurality of user profiles. A second conversion score associated with the first entity may be determined based upon the second plurality of user profiles.Type: ApplicationFiled: October 8, 2019Publication date: April 8, 2021Inventors: Chander Jayaraman Iyer, Srinath Ravindran, Sainath Subramanya Vellal, Lakshmi Narayan Bhamidipati
-
Patent number: 10922722Abstract: The technologies described herein serve contextually relevant advertisements under a guaranteed advertisement campaign. A publisher retrieves a guaranteed advertisement campaign related to a webpage available for serving an advertisement, and identifies a set of advertisements relating to the guaranteed advertisement campaign. Advertisement selecting circuitry of the publisher determines whether an advertisement that is contextually relevant to content published at the webpage is present in the set of advertisements. If there is no contextually relevant advertisement in the set of advertisements, the advertisement selecting circuitry selects an alternative advertisement from the set of advertisements that minimizes an under-delivery risk related to the guaranteed advertisement campaign. If there is a contextually relevant advertisement in the set of advertisements, the advertisement selecting circuitry selects the contextually relevant advertisement.Type: GrantFiled: July 31, 2015Date of Patent: February 16, 2021Assignee: Verizon Media Inc.Inventors: Suleyman Cetintas, Srinath Ravindran, Mohammad Saberian, Sandeep Soni, Kuang-chih Lee, Hong Yao, Jian Yang, Pradhan Pattanayak
-
Publication number: 20200210467Abstract: Technologies for template generation using directed acyclic word graphs (DAWGs). The technologies can include receiving a first plurality of titles from a first plurality of title feeds, and sorting the first plurality of titles into a plurality of category sets. And, for each category set of the plurality of category sets, the technologies can include transforming the respective titles belonging to the category set into a trie data structure by separating words in the respective titles into nodes of the trie data structure. For each category set, the technologies can also include transforming the trie data structure into a directed acyclic word graph (DAWG) data structure. Also, for each category set, the technologies can also include generating one or more unique templates based on the DAWG data structure.Type: ApplicationFiled: December 26, 2018Publication date: July 2, 2020Inventors: Srinath RAVINDRAN, Mahmoudreza ABASI, Narayan BHAMIDIPATI
-
Publication number: 20200186846Abstract: One or more computing devices, systems, and/or methods for selecting content for transmission to devices are provided. First activity performed using a content interface on a device may be detected. First activity information associated with the first activity may be stored in an activity profile associated with the device. An activity database may be analyzed based upon the activity profile to identify one or more activity identifiers of the activity database. The activity database may comprise a plurality of activity identifiers and/or funnel stage tags associated with the plurality of activity identifiers. A request for content, associated with an entity, may be received from the device. A funnel stage score may be determined based upon one or more funnel stage tags associated with the entity and/or the one or more activity identifiers. A content item, associated with the entity, may be selected based upon the funnel stage score.Type: ApplicationFiled: December 10, 2018Publication date: June 11, 2020Inventors: Shaunak MISHRA, Richard Hin-Fai TANG, Yichao ZHOU, Vishal Ramesh RAITHATHA, Lakshmi Narayan BHAMIDIPATI, Mahmoudreza ABASI, Srinath RAVINDRAN
-
Publication number: 20170032424Abstract: The technologies described herein serve contextually relevant advertisements under a guaranteed advertisement campaign. A publisher retrieves a guaranteed advertisement campaign related to a webpage available for serving an advertisement, and identifies a set of advertisements relating to the guaranteed advertisement campaign. Advertisement selecting circuitry of the publisher determines whether an advertisement that is contextually relevant to content published at the webpage is present in the set of advertisements. If there is no contextually relevant advertisement in the set of advertisements, the advertisement selecting circuitry selects an alternative advertisement from the set of advertisements that minimizes an under-delivery risk related to the guaranteed advertisement campaign. If there is a contextually relevant advertisement in the set of advertisements, the advertisement selecting circuitry selects the contextually relevant advertisement.Type: ApplicationFiled: July 31, 2015Publication date: February 2, 2017Applicant: Yahoo! Inc.Inventors: Suleyman Cetintas, Srinath Ravindran, Mohammad Saberian, Sandeep Soni, Kuang-chih Lee, Hong Yao, Jian Yang, Pradhan Pattanayak