Patents by Inventor Nish Parikh
Nish Parikh 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: 11720641Abstract: In various example embodiments, a system and method for retrieving database records are presented. A method includes receiving an access request for database records, identifying a primary database record corresponding to the access request, and selecting a set of secondary database records corresponding to a portion of the access request. The method determines a set of differentiating elements within records of the set of secondary database records. Each differentiating element distinguishes at least one record of the set of secondary database records from one or more of the primary database record and a portion of the records included in the set of secondary database records. The method generates a formatted search interface including a set of selectable interface icons representing one or more differentiating elements and causes presentation of the formatted search interface at a client device associated with the access request.Type: GrantFiled: August 6, 2020Date of Patent: August 8, 2023Assignee: eBay Inc.Inventors: Narayanan Seshadri, Gyanit Singh, Justin Nicholas House, Nish Parikh, David Goldberg, Daniel Fain, Huai-ter Chong, Stephen Neola, Jonas Oscar Klink
-
Patent number: 11636135Abstract: Systems and methods generate browse node pages. A combination of a category and one or more aspects is identified by analyzing historical user behavior data associated with a network-based system. A determination is made regarding whether existing browse node pages for the network-based system includes a browse node page for the identified combination. Each browse node page for the network-based system is accessible by a respective uniform resource location (URL) and provides a grouping of items in a respective category with one or more respective aspects. Based on a determination that a browse node page does not exist for the identified combination of the category and the one or more aspects, a browse node page for the identified combination is generated. The generated browse node page corresponds with a URL and provides items matching the identified combination of the category and the one or more aspects.Type: GrantFiled: May 18, 2021Date of Patent: April 25, 2023Assignee: EBAY INC.Inventors: Atiq Islam, Nish Parikh, Neeraj Garg
-
Publication number: 20210279261Abstract: Systems and methods generate browse node pages. A combination of a category and one or more aspects is identified by analyzing historical user behavior data associated with a network-based system. A determination is made regarding whether existing browse node pages for the network-based system includes a browse node page for the identified combination. Each browse node page for the network-based system is accessible by a respective uniform resource location (URL) and provides a grouping of items in a respective category with one or more respective aspects. Based on a determination that a browse node page does not exist for the identified combination of the category and the one or more aspects, a browse node page for the identified combination is generated. The generated browse node page corresponds with a URL and provides items matching the identified combination of the category and the one or more aspects.Type: ApplicationFiled: May 18, 2021Publication date: September 9, 2021Inventors: Atiq Islam, Nish Parikh, Neeraj Garg
-
Patent number: 11080302Abstract: To improve the user experience, browse nodes for popular combinations of categories and aspects are desirable. When a particular combination of category and aspects is found to have been requested at a frequency that exceeds a threshold, the existence of a browse node for that combination is checked and, if the browse node is missing, a request to create the browse node is generated. In some example embodiments, an entire set of missing browse nodes is generated based on recognition of a pattern of category and aspect combinations being requested.Type: GrantFiled: October 11, 2016Date of Patent: August 3, 2021Assignee: eBay Inc.Inventors: Atiq Islam, Nish Parikh, Neeraj Garg
-
Publication number: 20210056265Abstract: In various example embodiments, a system and method for a Target Language Engine are presented. The Target Language Engine augments a synonym list in a base dictionary of a target language with one or more historical search queries previously submitted to search one or more listings in listing data. The Target Language Engine identifies a compound word and a plurality of words present in the listing data that have a common meaning in the target language. Each word from the plurality of words is present in the compound word. The Target Language Engine causes a database to create an associative link between the portion of text and a word selected from at least one of the synonym list or the plurality of words.Type: ApplicationFiled: November 9, 2020Publication date: February 25, 2021Inventors: Chandra Prakash Khatri, Selcuk Kopru, Nish Parikh, Justin Nicholas House, Sameep Navin Solanki
-
Publication number: 20200364281Abstract: In various example embodiments, a system and method for retrieving database records are presented. A method includes receiving an access request for database records, identifying a primary database record corresponding to the access request, and selecting a set of secondary database records corresponding to a portion of the access request. The method determines a set of differentiating elements within records of the set of secondary database records. Each differentiating element distinguishes at least one record of the set of secondary database records from one or more of the primary database record and a portion of the records included in the set of secondary database records. The method generates a formatted search interface including a set of selectable interface icons representing one or more differentiating elements and causes presentation of the formatted search interface at a client device associated with the access request.Type: ApplicationFiled: August 6, 2020Publication date: November 19, 2020Applicant: eBay Inc.Inventors: Narayanan Seshadri, Gyanit Singh, Justin Nicholas House, Nish Parikh, David Goldberg, Daniel Fain, Huai-ter Chong, Stephen Neola, Jonas Oscar Klink
-
Patent number: 10831842Abstract: In various example embodiments, a system and method for retrieving database records are presented. A method includes receiving an access request for database records, identifying a primary database record corresponding to the access request, and selecting a set of secondary database records corresponding to a portion of the access request. The method determines a set of differentiating elements within records of the set of secondary database records. Each differentiating element distinguishes at least one record of the set of secondary database records from one or more of the primary database record and a portion of the records included in the set of secondary database records. The method generates a formatted search interface including a set of selectable interface icons representing one or more differentiating elements and causes presentation of the formatted search interface at a client device associated with the access request.Type: GrantFiled: May 3, 2017Date of Patent: November 10, 2020Assignee: eBay Inc.Inventors: Narayanan Seshadri, Gyanit Singh, Justin Nicholas House, Nish Parikh, David Goldberg, Daniel Fain, Huai-ter Chong, Stephen Neola, Jonas Oscar Klink
-
Publication number: 20200320370Abstract: Systems, methods and media are provided for training a snippet extractor to create snippets based on information extracted from published descriptions. In one example, a computer-implemented method includes creating, based on a non-RNN (Recurrent Neural Network) extraction technique performed on the published descriptions, a plurality of base models, each base model including one or more sample description summaries; evaluating the base models using an evaluation technique; selecting an optimum base model; developing a classification model using RNN extraction, the classification model based on description summaries contained in the optimum base model; and using the classification model to train the snippet extractor by machine learning.Type: ApplicationFiled: April 24, 2020Publication date: October 8, 2020Inventors: Chandra Prakash Khatri, Nish Parikh, Sameep Navin Solanki, Justin Nicholas House, Gyanit Singh
-
Publication number: 20200117855Abstract: In various example embodiments, a system and method for a Target Language Engine are presented. The Target Language Engine augments a synonym list in a base dictionary of a target language with one or more historical search queries previously submitted to search one or more listings in listing data. The Target Language Engine identifies a compound word and a plurality of words present in the listing data that have a common meaning in the target language. Each word from the plurality of words is present in the compound word. The Target Language Engine causes a database to create an associative link between the portion of text and a word selected from at least one of the synonym list or the plurality of words.Type: ApplicationFiled: August 21, 2019Publication date: April 16, 2020Inventors: Chandra Prakash Khatri, Selcuk Kopru, Nish Parikh, Justin Nicholas House, Sameep Navin Solanki
-
Patent number: 10521509Abstract: In various example embodiments, a system and method for a Target Language Engine are presented. The Target Language Engine augments a synonym list in a base dictionary of a target language with one or more historical search queries previously submitted to search one or more listings in listing data. The Target Language Engine identifies a compound word and a plurality of words present in the listing data that have a common meaning in the target language. Each word from the plurality of words is present in the compound word. The Target Language Engine causes a database to create an associative link between the portion of text and a word selected from at least one of the synonym list or the plurality of words.Type: GrantFiled: August 15, 2016Date of Patent: December 31, 2019Assignee: eBay Inc.Inventors: Chandra Prakash Khatri, Selcuk Kopru, Nish Parikh, Justin Nicholas House, Sameep Navin Solanki
-
Publication number: 20190361987Abstract: Method for analyzing review content is described herein. The method starts by generating a helpfulness score for each review in the plurality of reviews. A first set of reviews is selected based on the helpfulness scores for each review in the plurality of review and a helpfulness score for each sentence in each review in the first set of reviews is generated. The review summary is then generated by selecting sentences in each review in the first set of reviews based on the helpfulness score of each sentence. The review summary includes the selected sentences. Other embodiments are also described.Type: ApplicationFiled: May 23, 2018Publication date: November 28, 2019Inventors: Qifeng Qiao, Nish Parikh, Saratchandra Indrakanti, Gyanit Singh, Justin Nicholas House
-
Publication number: 20180046611Abstract: In various example embodiments, a system and method for a Target Language Engine are presented. The Target Language Engine augments a synonym list in a base dictionary of a target language with one or more historical search queries previously submitted to search one or more listings in listing data. The Target Language Engine identifies a compound word and a plurality of words present in the listing data that have a common meaning in the target language. Each word from the plurality of words is present in the compound word. The Target Language Engine causes a database to create an associative link between the portion of text and a word selected from at least one of the synonym list or the plurality of words.Type: ApplicationFiled: August 15, 2016Publication date: February 15, 2018Inventors: Chandra Prakash Khatri, Selcuk Kopru, Nish Parikh, Justin Nicholas House, Sameep Navin Solanki
-
Publication number: 20170364967Abstract: In various example embodiments, a system and method for evaluating and sorting product feedback is presented. In one example, a system includes a learning module to train a machine learning system on feedback from a plurality of users, the machine learning system configured to generate a quality rating for individual feedback, a feedback module to collect feedback for a specific product available from the online network based marketplace and apply the machine learning system to generate a quality rating for each feedback collected, and a sorting module to sort the feedback collected according to the quality ratings generated by the machine learning system.Type: ApplicationFiled: September 30, 2016Publication date: December 21, 2017Inventors: Nish Parikh, Qifeng Qiao, Syeda Hudda, Naveen Kumar, Krithivasan Nagarajan, David Goldberg
-
Publication number: 20170344622Abstract: To improve the user experience, browse nodes for popular combinations of categories and aspects are desirable. When a particular combination of category and aspects is found to have been requested at a frequency that exceeds a threshold, the existence of a browse node for that combination is checked and, if the browse node is missing, a request to create the browse node is generated. In some example embodiments, an entire set of missing browse nodes is generated based on recognition of a pattern of category and aspect combinations being requested.Type: ApplicationFiled: October 11, 2016Publication date: November 30, 2017Inventors: Atiq Islam, Nish Parikh, Neeraj Garg
-
Publication number: 20170344615Abstract: A global aspect dictionary is created based on queries run on a search engine and responsive results to the query that are interacted with. The global aspect dictionary is used by a mapping server to look up aspects for queries received from users. A query received by the mapping server is modified by adding aspects from the dictionary to the query. in some example embodiments, tokens in the query corresponding to the added aspects are removed from the query. Results responsive to the modified query are transmitted to the user.Type: ApplicationFiled: May 30, 2017Publication date: November 30, 2017Inventors: Atiq Islam, Nish Parikh
-
Publication number: 20170322971Abstract: In various example embodiments, a system and method for retrieving database records are presented. A method includes receiving an access request for database records, identifying a primary database record corresponding to the access request, and selecting a set of secondary database records corresponding to a portion of the access request. The method determines a set of differentiating elements within records of the set of secondary database records. Each differentiating element distinguishes at least one record of the set of secondary database records from one or more of the primary database record and a portion of the records included in the set of secondary database records. The method generates a formatted search interface including a set of selectable interface icons representing one or more differentiating elements and causes presentation of the formatted search interface at a client device associated with the access request.Type: ApplicationFiled: May 3, 2017Publication date: November 9, 2017Inventors: Narayanan Seshadri, Gyanit Singh, Justin Nicholas House, Nish Parikh, David Goldberg, Daniel Fain, Huai-ter Chong, Stephen Neola, Jonas Oscar Klink
-
Publication number: 20170213130Abstract: Systems, methods and media are provided for training a snippet extractor to create snippets based on information extracted from published descriptions. In one example, a computer-implemented method includes creating, based on a non-RNN (Recurrent Neural Network) extraction technique performed on the published descriptions, a plurality of base models, each base model including one or more sample description summaries; evaluating the base models using an evaluation technique; selecting an optimum base model; developing a classification model using RNN extraction, the classification model based on description summaries contained in the optimum base model; and using the classification model to train the snippet extractor by machine learning.Type: ApplicationFiled: September 16, 2016Publication date: July 27, 2017Inventors: Chandra Prakash Khatri, Nish Parikh, Sameep Navin Solanki, Justin Nicholas House, Gyanit Singh