Patents by Inventor Dingxian Wang
Dingxian Wang 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).
-
Publication number: 20240380822Abstract: One of the important signals that online platforms rely upon is the click-through rate prediction. This allows a platform, such as a video platform, to provide items, such as videos, to users based on how likely the user is to interact with the item. A hypergraph model is provided to exploit the temporal user-item interactions to guide the representation learning with multi-modal features, and further predict the user click-through rate of an item. The hypergraph model is built upon the hyperedge notion of hypergraph neural networks. In this way, item modalities, such as visual, acoustic, and textual aspects can be used to enhance the click-through rate prediction and, thus, enhance the likelihood that the online platform will provide relevant content. The technology leverages hypergraphs, including interest-based hypergraphs and item hypergraphs that uniquely provide the relationship between user and items. The hypergraph model described demonstrably outperforms various state-of-the-art methods.Type: ApplicationFiled: August 26, 2021Publication date: November 14, 2024Inventors: Dingxian WANG, Guandong XU, Hongxu CHEN, Li HE
-
Publication number: 20240346604Abstract: Technologies are shown for mapping micro-video hashtags to content categories that involve collecting content categories from a content service, collecting micro-video, hashtags and user interaction semantic data from a micro-video service, determining a correlation of a content category to the micro-video, hashtags and user interaction semantic data using a multi-layer graph convolution network, and providing the hashtags correlated with the content category to the content service. The correlation can be determined by processing the semantic data with a concatenation layer and a full connected layer to produce a user-specific micro-video and hashtag representations. Similarity scores for determining correlation can be calculated from category content and a dot product of the representations.Type: ApplicationFiled: August 13, 2021Publication date: October 17, 2024Inventors: Dingxian WANG, Guandong XU, Hongxu CHEN, Li HE
-
Patent number: 12079227Abstract: A categorization analysis system is provided. The categorization analysis system includes one or more hardware processors, a memory including a first plurality of listings categorized in a first target category, and a categorization analysis engine executing on the one or more hardware processors. The categorization analysis engine is configured to determine a label for each listing including performing a search on title, select a set of training listings based on the determined labels, train a first model using the set of training listings and the determined labels, the first model being a classification model configured to classify categorization of listings, identify a suspect listing categorized in the first target category, apply the suspect listing to the first model, thereby generating a categorization result for the suspect listing, the categorization result indicating miscategorization of the suspect listing, and identify the suspect listing in the memory as miscategorized.Type: GrantFiled: April 19, 2023Date of Patent: September 3, 2024Assignee: EBAY INC.Inventors: Dingxian Wang, David Goldberg, Xiaoyuan Wu, Yuanjie Liu
-
Publication number: 20240220537Abstract: A method for automatic metadata tag identification for videos is described. Content features are extracted from a video into respective data structures. The extracted content features are from at least two different feature modalities. The respective data structures are encoded into a common data structure using an encoder of a recurrent neural network (RNN) model. The common data structure is decoded using a decoder of the RNN model to identify content platform metadata tags to be associated with the video on a social content platform. Decoding is based on group tag data for users of the social content platform that identifies groups of the users and corresponding group metadata tags of interest for the groups of users.Type: ApplicationFiled: March 18, 2024Publication date: July 4, 2024Applicant: eBay Inc.Inventors: Dingxian Wang, Hongxu Chen, Guandong Xu, Li He
-
Patent number: 11966440Abstract: A method for automatic metadata tag identification for videos is described. Content features are extracted from a video into respective data structures. The extracted content features are from at least two different feature modalities. The respective data structures are encoded into a common data structure using an encoder of a recurrent neural network (RNN) model. The common data structure is decoded using a decoder of the RNN model to identify content platform metadata tags to be associated with the video on a social content platform. Decoding is based on group tag data for users of the social content platform that identifies groups of the users and corresponding group metadata tags of interest for the groups of users.Type: GrantFiled: October 13, 2021Date of Patent: April 23, 2024Assignee: eBay Inc.Inventors: Dingxian Wang, Hongxu Chen, Guandong Xu, Li He
-
Publication number: 20240104621Abstract: Various embodiments improve search technologies and computer information retrieval by executing a query via ranking a set of search result candidates higher than another set search result candidates based at least in part on the query and determining that a first set of search result candidates are indicative of a sub-accessory to an accessory or an accessory itself.Type: ApplicationFiled: December 1, 2023Publication date: March 28, 2024Inventor: Dingxian WANG
-
Publication number: 20240054571Abstract: Various embodiments include systems, methods, and non-transitory computer-readable media for identifying and matching influencers with categorized products using multimodal machine learning technologies. Consistent with these embodiments, a method includes identifying an influencer based on a set of criteria; determining a first attribute of the influencer based on context data associated with the influencer; identifying a second attribute of an item; generating a first vector that represents the first attribute of the influencer and a second vector that represents the second attribute of the item; generating a similarity score that represents a degree of similarity between the influencer and the item based on the first vector and the second vector; and causing display of the similarity score in a user interface of a device.Type: ApplicationFiled: August 9, 2022Publication date: February 15, 2024Inventors: Hongxu Chen, Li He, Dingxian Wang, Xianzhi Wang, Guangdong Xu, Haoran Yang
-
Patent number: 11875390Abstract: Various embodiments improve search technologies and computer information retrieval by executing a query via ranking a set of search result candidates higher than another set search result candidates based at least in part on the query and determining that a first set of search result candidates are indicative of a sub-accessory to an accessory or an accessory itself.Type: GrantFiled: November 3, 2020Date of Patent: January 16, 2024Assignee: eBay Inc.Inventor: Dingxian Wang
-
Publication number: 20230252035Abstract: A categorization analysis system is provided. The categorization analysis system includes one or more hardware processors, a memory including a first plurality of listings categorized in a first target category, and a categorization analysis engine executing on the one or more hardware processors. The categorization analysis engine is configured to determine a label for each listing including performing a search on title, select a set of training listings based on the determined labels, train a first model using the set of training listings and the determined labels, the first model being a classification model configured to classify categorization of listings, identify a suspect listing categorized in the first target category, apply the suspect listing to the first model, thereby generating a categorization result for the suspect listing, the categorization result indicating miscategorization of the suspect listing, and identify the suspect listing in the memory as miscategorized.Type: ApplicationFiled: April 19, 2023Publication date: August 10, 2023Inventors: Dingxian Wang, David Goldberg, Xiaoyuan Wu, Yuanjie Liu
-
Patent number: 11663225Abstract: A categorization analysis system is provided. The categorization analysis system includes one or more hardware processors, a memory including a first plurality of listings categorized in a first target category, and a categorization analysis engine executing on the one or more hardware processors. The categorization analysis engine is configured to determine a label for each listing including performing a search on title, select a set of training listings based on the determined labels, train a first model using the set of training listings and the determined labels, the first model being a classification model configured to classify categorization of listings, identify a suspect listing categorized in the first target category, apply the suspect listing to the first model, thereby generating a categorization result for the suspect listing, the categorization result indicating miscategorization of the suspect listing, and identify the suspect listing in the memory as miscategorized.Type: GrantFiled: August 13, 2021Date of Patent: May 30, 2023Assignee: eBay Inc.Inventors: Dingxian Wang, David Goldberg, Xiaoyuan Wu, Yuanjie Liu
-
Publication number: 20230115897Abstract: A method for automatic metadata tag identification for videos is described. Content features are extracted from a video into respective data structures. The extracted content features are from at least two different feature modalities. The respective data structures are encoded into a common data structure using an encoder of a recurrent neural network (RNN) model. The common data structure is decoded using a decoder of the RNN model to identify content platform metadata tags to be associated with the video on a social content platform. Decoding is based on group tag data for users of the social content platform that identifies groups of the users and corresponding group metadata tags of interest for the groups of users.Type: ApplicationFiled: October 13, 2021Publication date: April 13, 2023Applicant: eBay Inc.Inventors: Dingxian WANG, Hongxu CHEN, Guandong XU, Li HE
-
Publication number: 20220138826Abstract: Various embodiments improve search technologies and computer information retrieval by executing a query via ranking a set of search result candidates higher than another set search result candidates based at least in part on the query and determining that a first set of search result candidates are indicative of a sub-accessory to an accessory or an accessory itself.Type: ApplicationFiled: November 3, 2020Publication date: May 5, 2022Inventor: Dingxian Wang
-
Publication number: 20210374150Abstract: A categorization analysis system is provided. The categorization analysis system includes one or more hardware processors, a memory including a first plurality of listings categorized in a first target category, and a categorization analysis engine executing on the one or more hardware processors. The categorization analysis engine is configured to determine a label for each listing including performing a search on title, select a set of training listings based on the determined labels, train a first model using the set of training listings and the determined labels, the first model being a classification model configured to classify categorization of listings, identify a suspect listing categorized in the first target category, apply the suspect listing to the first model, thereby generating a categorization result for the suspect listing, the categorization result indicating miscategorization of the suspect listing, and identify the suspect listing in the memory as miscategorized.Type: ApplicationFiled: August 13, 2021Publication date: December 2, 2021Inventors: Dingxian Wang, David Goldberg, Xiaoyuan Wu, Yuanjie Liu
-
Patent number: 11126631Abstract: A categorization analysis system is provided. The categorization analysis system includes one or more hardware processors, a memory including a first plurality of listings categorized in a first target category, and a categorization analysis engine executing on the one or more hardware processors. The categorization analysis engine is configured to determine a label for each listing including performing a search on title, select a set of training listings based on the determined labels, train a first model using the set of training listings and the determined labels, the first model being a classification model configured to classify categorization of listings, identify a suspect listing categorized in the first target category, apply the suspect listing to the first model, thereby generating a categorization result for the suspect listing, the categorization result indicating miscategorization of the suspect listing, and identify the suspect listing in the memory as miscategorized.Type: GrantFiled: May 18, 2018Date of Patent: September 21, 2021Assignee: eBay Inc.Inventors: Dingxian Wang, David Goldberg, Xiaoyuan Wu, Yuanjie Liu
-
Publication number: 20180329913Abstract: A categorization analysis system is provided. The categorization analysis system includes one or more hardware processors, a memory including a first plurality of listings categorized in a first target category, and a categorization analysis engine executing on the one or more hardware processors. The categorization analysis engine is configured to determine a label for each listing including performing a search on title, select a set of training listings based on the determined labels, train a first model using the set of training listings and the determined labels, the first model being a classification model configured to classify categorization of listings, identify a suspect listing categorized in the first target category, apply the suspect listing to the first model, thereby generating a categorization result for the suspect listing, the categorization result indicating miscategorization of the suspect listing, and identify the suspect listing in the memory as miscategorized.Type: ApplicationFiled: May 18, 2018Publication date: November 15, 2018Inventors: Dingxian Wang, David Goldberg, Xiaoyuan Wu, Yuanjie Liu
-
Patent number: 9996590Abstract: A categorization analysis system is provided. The categorization analysis system includes one or more hardware processors, a memory including a first plurality of listings categorized in a first target category, and a categorization analysis engine executing on the one or more hardware processors. The categorization analysis engine is configured to determine a label for each listing including performing a search on title, select a set of training listings based on the determined labels, train a first model using the set of training listings and the determined labels, the first model being a classification model configured to classify categorization of listings, identify a suspect listing categorized in the first target category, apply the suspect listing to the first model, thereby generating a categorization result for the suspect listing, the categorization result indicating miscategorization of the suspect listing, and identify the suspect listing in the memory as miscategorized.Type: GrantFiled: December 31, 2015Date of Patent: June 12, 2018Assignee: eBay Inc.Inventors: Dingxian Wang, David Goldberg, Xiaoyuan Wu, Yuanjie Liu
-
Publication number: 20170192975Abstract: A categorization analysis system is provided. The categorization analysis system includes one or more hardware processors, a memory including a first plurality of listings categorized in a first target category, and a categorization analysis engine executing on the one or more hardware processors. The categorization analysis engine is configured to determine a label for each listing including performing a search on title, select a set of training listings based on the determined labels, train a first model using the set of training listings and the determined labels, the first model being a classification model configured to classify categorization of listings, identify a suspect listing categorized in the first target category, apply the suspect listing to the first model, thereby generating a categorization result for the suspect listing, the categorization result indicating miscategorization of the suspect listing, and identify the suspect listing in the memory as miscategorized.Type: ApplicationFiled: December 31, 2015Publication date: July 6, 2017Inventors: Dingxian Wang, David Goldberg, Xiaoyuan Wu, Yuanjie Liu