Ayse Korgav - San Mateo CA, US Raymond P. P. Chan - Mountain View CA, US Jie Feng - Foster City CA, US Michele Ann Colgan - Alameda CA, US
Assignee:
Visa U.S.A. Inc. - San Francisco CA
International Classification:
G06Q 40/00
US Classification:
705 40, 705 39, 705 42, 715706
Abstract:
A consumer installs a desktop application on a computer which renders a user interface on the computer's desktop. Upon installation, the desktop application is registered to receive offers and alerts. Each alert includes data for a transaction on an account conducted with a merchant where the account was issued by an issuer to an account holder to conduct transactions on the account with merchants. A received alert is rendered on the desktop. If the consumer, upon review of the rendered alert, deems the corresponding transaction to be fraudulent, the consumer can operate the user interface to activate a live chat with a web service, and use the live chat to send information sufficient to initiate a bona fide dispute of the transaction. The offers are rendered on the user interface as advertisement and are selectable to initiate a transaction on the account.
Ray Olson - Half Moon Bay CA, US David White - Oakland CA, US Shaun Bodington - San Leandro CA, US Jie Feng - Foster City CA, US
International Classification:
G06Q 20/38 G06Q 20/40
US Classification:
705 44, 705 39
Abstract:
Embodiments of the present invention include a dynamic and auditable rules-based spend requirement management (SRM) server configured to receive transaction data associated with a payment transaction involving an issuer of an account, where the account is associated with a first set of account level requirements (e.g., a minimum spend requirement) and a first interchange rate. The SRM is further configured to determine that the transaction data is not within the first set of account level requirements, but is within a second set of account level requirements associated with a second interchange rate, and associate the account to the second set of account level requirements by way of a final product identifier stored in a database accessible by a payment processing network (PPN).
Prescriptive Analytics In Highly Collinear Response Space
A method includes: receiving film property data associated with manufacturing parameters of manufacturing equipment; determining that the film property data is correlated and is different from target data; selecting, by a processing device, a set of data points of the film property data that are orthogonal to the target data; performing, by the processing device, feature extraction on the set of data points; and determining, based on the feature extraction, updates to one or more of the manufacturing parameters to meet the target data.
Predictive Modeling Of A Manufacturing Process Using A Set Of Inverted Models
- Santa Clara CA, US Dermot Cantwell - Sunnyvale CA, US Serghei Malkov - Hayward CA, US Jie Feng - Milpitas CA, US
International Classification:
G06N 3/08 G06N 3/04 G05B 13/02 G05B 19/418
Abstract:
Disclosed herein is technology for performing predictive modeling to identify inputs for a manufacturing process. An example method may include receiving expected output data for a manufacturing process, wherein the expected output data defines an attribute of an output of the manufacturing process; accessing a plurality of machine learning models that model the manufacturing process; determining, using a first machine learning model, input data for the manufacturing process based on the expected output data for the manufacturing process, wherein the input data comprises a value for a first input and a value for a second input; combining the input data determined using the first machine learning model with input data determined using the second machine learning model to produce a set of inputs for the manufacturing process, wherein the set of inputs comprises candidate values for the first input and candidate values for the second input.
Prescriptive Analytics In Highly Collinear Response Space
- Santa Clara CA, US Jie Feng - Milpitas CA, US Dermot Cantwell - Sunnyvale CA, US
International Classification:
G06Q 50/04 G06N 3/08 H01L 21/67
Abstract:
Methods, systems, and non-transitory computer readable medium are described for prescriptive analytics in highly collinear response space. A method includes receiving film property data associated with manufacturing parameters of manufacturing equipment. The method further includes determining that the film property data is correlated and is different from target data. The method further includes selecting a set of data points of the film property data that are orthogonal to the target data. The method further includes performing feature extraction on the set of data points. The method further includes determining, based on the feature extraction, updates to one or more of the manufacturing parameters to meet the target data.
User Input-Based Object Selection Using Multiple Visual Cues
- San Jose CA, US Scott D. Cohen - Sunnyvale CA, US Jie Feng - New York NY, US
International Classification:
G06F 3/0484 G06T 11/60
Abstract:
User input-based object selection using multiple visual cues is described. User selection input is received for selecting a portion of an image. Once the user selection input is received, one of a plurality of visual cues that convey different information about content depicted in the image is selected for each pixel. The one visual cue is selected as a basis for identifying the pixel as part of the selected portion of the image or part of an unselected remainder of the image. The visual cues are selected by determining confidences, based in part on the user selection input, that the plurality of visual cues can be used to discriminate whether the pixel is part of the selected portion or part of the remainder. The information conveyed by the selected visual cues is used to identify the pixels as part of the selected portion or part of the remainder.
Fast Interest Point Extraction For Augmented Reality
- Palo Alto CA, US Nityananda Jayadevaprakash - San Jose CA, US David Creighton Mott - Los Altos CA, US Jie Feng - New York NY, US
International Classification:
G06K 9/62 G06K 9/46 G06K 9/00 G06T 7/90
Abstract:
The subject technology provides embodiments for performing fast corner detection in a given image for augmented reality applications. Embodiments disclose a high-speed test that examines intensities of pairs of pixels around a candidate center pixel. In one example, the examined pairs are comprised of pixels that are diametrically opposite ends of a circle formed with the candidate center pixel. Further, a pyramid of images including four rings of surrounding pixels is generated. An orientation of the pixels from the four rings are determined and a vector of discrete values of the pixels are provided. Next, a forest of trees are generated for the vector of discrete values corresponding to a descriptor for a first image. For a second image including a set of descriptors, approximate nearest neighbors are determined from the forest of tree representing closest matching descriptors from the first image.
Onkareshwar V. Bijjargi - Pimple Saudagar Pune, IN Siddharth Ram R. Athreya - Lake Jackson TX, US Edoardo Nicoli - Midland MI, US Hua Liu - Pitsford NY, US Keith L. Kauffmann - Ypsilanti MI, US Jie Feng - Midland MI, US Leonardo C. Lopez - Midland MI, US Rebekah K. Feist - Midland MI, US Rahul Sharma - Pearland TX, US
Assignee:
Dow Global Technologies LLC - Midland MI
International Classification:
H02S 20/26
Abstract:
An article of manufacture includes at least two solar active elements separated by a gap, with a flexible material provided to define the gap. The article provides for enhanced resilience and conformity to an installation surface.