Yu Cheng

US Patent:

20100241684, Sep 23, 2010

Filed:

Mar 17, 2009

Appl. No.:

12/405259

Inventors:

Yu Cheng - Newcastle WA, US
Kaifeng Yao - Beijing, CN
Wenwu Zhu - Basking Ridge NJ, US

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

G06F 15/16
G06Q 99/00

US Classification:

709202, 709203, 709206, 709230, 705 11

Abstract:

Architectures for supporting diverse client types in transactional systems are provided. These architectures provide computer-based systems that include any number of processors. These systems may also include computer-readable storage media that provide a transaction assistant module. In turn, the transaction assistant module may include an adaptive presentation layer and a shared logic layer. The adaptive presentation layer includes presentation components that correspond respectively to various types of client devices. The shared logic layer includes back-end components that are shared between the client devices to perform common functions on behalf of the client devices.

US Patent:

20230084845, Mar 16, 2023

Filed:

Sep 13, 2021

Appl. No.:

17/473623

Inventors:

- Redmond WA, US
Lynsey LIU - Seattle WA, US
Andrei A. GAIVORONSKI - Redmond WA, US
Yu CHENG - Redmond WA, US
Dinei Afonso Ferreira FLORENCIO - Redmond WA, US
Cha ZHANG - Bellevue WA, US
John Richard CORRING - Bellevue WA, US

International Classification:

G06K 9/00
G06K 9/32
G06K 9/62
G06F 40/284
G06N 20/00

Abstract:

The disclosure herein describes providing signature data of an input document. Text data of the input document is obtained (e.g., OCR data generated from image data) and a first set of signature fields are identified using signature key-value pairs of the text data. A first subset of signed signature fields and a first subset of unsigned signature fields are determined based on mapping to a set of predicted values. A second set of signature fields are determined using a region prediction model applied to image data of the input document. Region images associated with the first subset of unsigned signature fields and with second set of signature fields are obtained and a second set of signed signature fields and a second set of unsigned signature fields are determined using a signature recognition model. Signature output data is provided including signed signature fields and/or unsigned signature fields.

US Patent:

20210224315, Jul 22, 2021

Filed:

Dec 21, 2020

Appl. No.:

17/129176

Inventors:

- Armonk NY, US
Rogerio S. Feris - Hartford CT, US
Yu Cheng - Ossining NY, US
Xiaoxiao Guo - Mountain View CA, US

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G06F 16/583
G06F 16/242
G06F 16/951

Abstract:

A search engine is modified to perform increasingly precise image searching using iterative Natural Language (NL) interactions. From an NL search input, the modification extracts a set of input features, which includes a set of response features corresponding to an NL statement in the NL search input and a set of image features from a seed image in the NL search input. The modification performs image analysis on an image result in a result set of a query including at least some of the input features. In a next iteration of NL interactions, at least some of the result set is provided. An NL response in the iteration is added to a cumulative NL basis, and a revised result set is provided, which includes a new image result corresponding to a new response feature extracted from the cumulative NL basis.

US Patent:

20190294702, Sep 26, 2019

Filed:

Mar 21, 2018

Appl. No.:

15/927309

Inventors:

- Armonk NY, US
Rogerio S. Feris - Hartford CT, US
Yu Cheng - Ossining NY, US
Xiaoxiao Guo - Mountain View CA, US

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G06F 17/30

Abstract:

A search engine is modified to perform increasingly precise image searching using iterative Natural Language (NL) interactions. From an NL search input, the modification extracts a set of input features, which includes a set of response features corresponding to an NL statement in the NL search input and a set of image features from a seed image in the NL search input. The modification performs image analysis on an image result in a result set of a query including at least some of the input features. In a next iteration of NL interactions, at least some of the result set is provided. An NL response in the iteration is added to a cumulative NL basis, and a revised result set is provided, which includes a new image result corresponding to a new response feature extracted from the cumulative NL basis.