Xiang Chen - El Sobrante CA, US Dmitri Pavlovski - San Francisco CA, US Arkady Borkovsky - San Francisco CA, US Richard Collins - Sunnyvale CA, US
Assignee:
E-Centives, Inc. - Bethesda MD
International Classification:
G06F017/30
US Classification:
707 10, 707103 R
Abstract:
A computer-implemented approach for organizing input listings from various sources of input listings. Input listings are organized by mapping the input listings to consolidated listing that correspond to the input listings. The mapping of the input listings are based on various techniques such as a Stock Keeping Unit item-listing-to-consolidated-listing matching technique, a name/title item-listing-to-consolidated-listing matching technique, and a model item-listing-to-consolidated-listing matching technique.
Xiang Chen - El Sobrante CA, US Dmitri Pavlovski - San Francisco CA, US Arkady Borkovsky - San Francisco CA, US Richard Collins - Sunnyvale CA, US
Assignee:
Invenda Corporation - Bethesda MD
International Classification:
G06F 17/30
US Classification:
707 3, 707 5, 707 10, 707100
Abstract:
A computer-implemented approach for organizing input listings from various sources of input listings. Input listings are organized by mapping the input listings to consolidated listing that correspond to the input listings. The mapping of the input listings are based on various techniques such as a Stock Keeping Unit item-listing-to-consolidated-listing matching technique, a name/title item-listing-to-consolidated-listing matching technique, and a model item-listing-to-consolidated-listing matching technique.
Xiang Chen - El Sobrante CA, US Dmitri Pavlovski - San Francisco CA, US Arkady Borkovsky - San Francisco CA, US Richard Collins - Sunnyvale CA, US
Assignee:
Invenda Corporation - Bethesda MD
International Classification:
G06F 17/30
US Classification:
707609
Abstract:
A computer-implemented approach for organizing input listings from various sources of input listings. Input listings are organized by mapping the input listings to consolidated listing that correspond to the input listings. The mapping of the input listings are based on various techniques such as a Stock Keeping Unit item-listing-to-consolidated-listing matching technique, a name/title item-listing-to-consolidated-listing matching technique, and a model item-listing-to-consolidated-listing matching technique.
Intelligent And Efficient System And/Or Method For Automatic Notification And/Or Enforcement Of Legal Traffic Speed Limits And Spots
Yong Yuan - Fremont CA, US Xiang Chen - Fremont CA, US
International Classification:
G06F007/00
US Classification:
701036000, 701117000
Abstract:
The present invention provides an intelligent and efficient system () and/or method () for automatic notification and/or enforcement of legal traffic speed limits and stops, comprising roads, streets, highways, construction zones, accident sites, and anywhere needed () installed at appropriate advanced locations with information tags () written with information including the according speed limit and/or stop information and vehicles () installed or built-in with information readers () capable of wirelessly and automatically reading information from the information tags () while the vehicles () travel. The read and other on-the-road information is displayed on visual displays () inside vehicles () and/or is voiced via audio devices () inside vehicles () for automatically notifying the vehicle drivers. Furthermore the in-vehicle speed control systems () use the speed limits read in by the information readers () to automatically enforce vehicles () to travel only within the speed limits.
Xiang Chen - El Sobrante CA, US Dmitri Pavlovski - San Francisco CA, US Arkady Borkovsky - San Francisco CA, US Richard Collins - Sunnyvale CA, US
Assignee:
Invenda Corporation - Bethesda MD
International Classification:
G06F 17/30
US Classification:
707737, 707E17014
Abstract:
A computer-implemented approach for organizing input listings from various sources of input listings. Input listings are organized by mapping the input listings to consolidated listing that correspond to the input listings. The mapping of the input listings are based on various techniques such as a Stock Keeping Unit item-listing-to-consolidated-listing matching technique, a name/title item-listing-to-consolidated-listing matching technique, and a model item-listing-to-consolidated-listing matching technique.
Optimizing Send Time For Electronic Communications
- SAN JOSE CA, US Xiang Chen - Palo ALto CA, US Akangsha Sunil Bedmutha - San Mateo CA, US Viswanathan Swaminathan - Saratogaa CA, US Omar Rahman - San Jose CA, US
International Classification:
G06N 3/08 G06N 3/04
Abstract:
An improved electronic communication system schedules transmission of electronic communications based on a predicted open time and click time. The open and click times are predicted from a machine learning model that is trained to optimize for both tasks. Additionally, when training the machine learning model, the loss used for adjusting the system to achieve a desired accuracy may be a biased loss determined from a function that penalizes overpredicting the open time. As such, the loss value may be determined by different set of rules depending on whether the predicted time is greater than the actual time or not.
Generating Digital Recommendations Utilizing Collaborative Filtering, Reinforcement Learning, And Inclusive Sets Of Negative Feedback
- San Jose CA, US Xiang Chen - Palo Alto CA, US Vahid Azizi - Piscataway PA, US
International Classification:
G06Q 30/06 G06K 9/62
Abstract:
The present disclosure relates to systems, methods, and non-transitory computer readable media that utilize collaborative filtering and a reinforcement learning model having an actor-critic framework to provide digital content items across client devices. In particular, in one or more embodiments, the disclosed systems monitor interactions of a client device with one or more digital content items to generate item embeddings (e.g., utilizing a collaborative filtering model). The disclosed systems further utilize a reinforcement learning model to generate a recommendation (e.g., determine one or more additional digital content items to provide to the client device) based on the user interactions. In some implementations, the disclosed systems utilize the reinforcement learning model to analyze every negative and positive interaction observed when generating the recommendation. Further, the disclosed systems utilize the reinforcement learning model to analyze item embeddings, which encode the relationships among the digital content items, when generating the recommendation.
- New York NY, US Patrik JOHANSSON - Hoboken NJ, US Xiang CHEN - Somerset NJ, US Suman CHOPRA - Monroe NJ, US
Assignee:
Colgate-Palmolive Company - New York NY
International Classification:
A61N 5/06 A61C 19/06 A61C 1/08
Abstract:
An oral treatment device that emits electromagnetic radiation onto surfaces of a user's teeth. The oral treatment device may include an intraoral mouthpiece and a handle extending therefrom, the handle containing the control circuitry required for operation of the device. The mouthpiece may include a lamp support structure, a lamp, a lens plate, and a guard component. The lamp may include an electromagnetic radiation source that includes a flexible sheet and a plurality of illumination elements located thereon. The illumination elements may be light emitting diodes printed with an electrically conductive. Additional electronic components such as a processor and a power source may also be included in the device.
Jude and Charles Lu of Washington University. The other authors are Matthew Parker, Armita Bahrami, Alberto Pappo, Sara Federico, James Dalton, Jianmin Wang, Xiang Chen, Jared Becksfort, Jianrong Wu, Catherine Billups, David Ellison and James Downing, all of St. Jude; Satish Tickoo, Adriana Heguy a