-
公开(公告)号：US20210279261A1
公开(公告)日：2021-09-09
申请号：US17323617
申请日：2021-05-18
Applicant: eBay Inc.
Inventor： Atiq Islam , Nish Parikh , Neeraj Garg
IPC: G06F16/28 , G06F16/248 , G06F16/2455 , G06F16/2457 , G06F16/951 , G06Q30/06
Abstract: 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.
-
公开(公告)号：US20170364967A1
公开(公告)日：2017-12-21
申请号：US15282571
申请日：2016-09-30
Applicant: eBay Inc.
Inventor： Nish Parikh , Qifeng Qiao , Syeda Hudda , Naveen Kumar , Krithivasan Nagarajan , David Goldberg
CPC classification number: G06Q30/0282 , G06N20/00
Abstract: 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.
-
公开(公告)号：US20170344622A1
公开(公告)日：2017-11-30
申请号：US15290283
申请日：2016-10-11
Applicant: eBay Inc.
Inventor： Atiq Islam , Nish Parikh , Neeraj Garg
CPC classification number: G06F16/285 , G06F16/2455 , G06F16/24573 , G06F16/24575 , G06F16/24578 , G06F16/248 , G06F16/951 , G06Q30/0601 , G06Q30/0625
Abstract: 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.
-
14.发明申请公开(公告)号：US20170213130A1
公开(公告)日：2017-07-27
申请号：US15267346
申请日：2016-09-16
Applicant: eBay Inc.
Inventor： Chandra Prakash Khatri , Nish Parikh , Sameep Navin Solanki , Justin Nicholas House , Gyanit Singh
CPC classification number: G06N3/0445 , G06F16/345
Abstract: 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.
-
-
-
Search Results
14
records
(took 0.017 seconds)
