Chi ZhangSan Jose, CA

8645367, Feb 4, 2014

Mar 8, 2010

12/719762

Nissan Hajaj - Foster City CA, US
Chi Zhang - Sunnyvale CA, US
Changxun Wu - Sunnyvale CA, US
Erik Gross - Palo Alto CA, US

Google Inc. - Mountain View CA

G06F 7/00

707727, 707750, 707917

One or more hierarchies of string patterns are generated a plurality of URL strings according to a pattern extraction procedure. Repeated string patterns are selected from the generated hierarchies of string patterns. A URL class is defined for each of selected repeated string patterns. Each URL class is associated with a respective group of URL strings in the plurality of URL strings, where the respective group of URL strings contains a repeated string pattern that defines the URL class. Respective aggregated data is calculated for each URL class. The respective aggregated data is based on respective data of each respective document of each URL string in the group of URL strings associated with the URL class. Respective data for a respective document referenced by a lookup-URL is predicted based on respective aggregated data of one or more of the URL classes.

2003005, Mar 20, 2003

Sep 17, 2001

09/954549

Bin Xu - Milpitas CA, US
Chi Zhang - Milpitas CA, US

G10L021/00

704/270000

This invention discloses methods and approaches for accessing information residing on ordinary PCs using voice phones calls through telephone lines; either landline telephones or wireless phones can be used. Four techniques are described in this invention to enable effective speech recognition and information retrieval based on normal PC hardware and software platform: i) natural language-based speech recognition; ii) SQL-like information retrieval commands; iii) dynamic dialog-based key content dictations; iv) dynamically generated rule grammars for speech dictations. Through software implementations, these four techniques combined will let ordinary users remotely access the information residing on their PCs by making voice phone calls. Security handling of the voice calls is also disclosed and described in this invention.

2021033, Oct 28, 2021

Apr 27, 2020

16/859165

- Beijing, CN
- Wilmington DE, US
Guifang Dong - Beijing, CN
Jia Lin - Mountain View CA, US
Zijing Zou - Beijing, CN
Chi Zhang - Fremont CA, US

G06Q 30/06
G06F 16/9535
G06F 16/906
G06F 16/532
G06N 3/08
G06K 9/62
G06K 9/46

A system and a method for recommending a set of fashion items. The method includes: providing fashion categories, fashion graphs each corresponding to one fashion category, and fitting formulas for each fashion graph; receiving a query fashion item having a query fashion attribute; selecting a fashion category, where the query fashion attribute in the selected fashion category has a highest number of fashion items; performing a similarity search between image of the query fashion item and images of fashion items in the fitting formulas; mapping the searched fitting formula to the fashion graph of the selected fashion category to obtain nodes matching the fashion items in the searched fitting formula; and recommending the set of fashion items respectively selected from fashion items in the matched nodes. The fitting formulas are generated based on co-appearance of fashion items from any two nodes of the corresponding fashion graph.

2021003, Feb 4, 2021

Aug 4, 2019

16/531102

- Beijing, CN
- Mountain View CA, US
Jui-Hsin Lai - Mountain View CA, US
Chi Zhang - Fremont CA, US

G06Q 30/06
G06F 16/583
G06F 16/535
G06F 16/538
G06F 16/9535
G06N 20/00
G06T 7/11
G06T 11/60

A method, a device, and a non-transitory computer readable medium for item recommendation based on visual elements. The method includes: determining, by one or more processors, visual elements from an item image of an item; generating, by the one or more processors, an element descriptor for the item based on at least a part of the visual elements; and calculating, by the one or more processors, a compatibility value between the element descriptor and one or more other element descriptors for one or more other items.

2020009, Mar 26, 2020

Sep 24, 2018

16/139149

- Tokyo, JP
Ahmed Khairy FARAHAT - Santa Clara CA, US
Chi ZHANG - San Jose CA, US
Marcos VIEIRA - San Francisco CA, US
Chetan GUPTA - San Mateo CA, US

G06Q 10/00
G06N 3/08

In some examples, a computer system may receive historical repair data for first equipment, and may extract features from the historical repair data for the first equipment as training data including one or more of: free-text variables associated with comments related to the first equipment; usage attributes associated with the first equipment; equipment attributes associated with the first equipment; sensor data associated with the first equipment; or event data associated with the first equipment. The system may determine a repair hierarchy including a plurality of repair levels for the equipment. The system may use the training data to train a machine learning model as a multilayer model trained to perform multiple tasks for predicting individual levels of the repair hierarchy. The system may receive a repair request associated with second equipment and uses the machine learning model to determine at least one repair action based on the received repair request.

2020008, Mar 19, 2020

Mar 21, 2018

16/496883

- St. Louis MO, US
Eric Borrowman - St. Peters MO, US
Jarrett R. Ceglinski - St. Louis MO, US
Govind Chaudhary - Maryland Heights MO, US
Kevin L. Deppermann - St Charles MO, US
Xiaofei Fan - Chesterfield MO, US
Jeffrey L. Kohne - Kirkwood MO, US
Brad D. White - Creve Coeur MO, US
Chi Zhang - San Jose CA, US

B07C 5/342
B07C 5/04
G06T 7/60

A seed sorting system for sorting seeds includes a seed transfer station configured to move seeds through the system. An imaging assembly includes a D camera configured to acquire D images of the seeds as the seeds move through the system and a D camera configured to acquire D images of the seeds as the seeds move through the system. A sorting assembly is configured to sort the seeds into separate bins based on the acquired D and D images of the seeds.

2020008, Mar 19, 2020

Sep 18, 2018

16/134738

- Cupertino CA, US
Chi Zhang - Cupertino CA, US
Haowei Wang - Cupertino CA, US
Lucas R. Compton - Cupertino CA, US

G06F 1/16
G06F 1/18

An electronic device may be provided with a display and conductive sidewalls. The display may include conductive display structures and a cover layer. The cover layer may be mounted to the sidewalls. The sidewalls may define antenna apertures for antennas in the device. Grounding structures may be coupled between the conductive display structures and the sidewalls at locations that at least partially overlap the antenna apertures. The grounding structures may include conductive tape having an adhesive surface. The conductive tape may have a first end at which the adhesive surface is coupled to the conductive display structures. The conductive tape may have a second end that is folded around a layer of heat-activated film and that is coupled to both the display cover layer and the conductive sidewalls. Conductive tape overlapping each antenna aperture may be concurrently assembled into the electronic device as the display is mounted to the sidewalls.

2020007, Mar 5, 2020

Aug 14, 2019

16/541120

- Beijing, CN
- Mountain View CA, US
Rong Yuan - Mountain View CA, US
Chi Zhang - Fremont CA, US
Di Wu - Mountain View CA, US

G06N 3/04
G06N 3/08
G06F 17/11

A system and a method for time series forecasting. The method includes: providing input feature vectors corresponding to a plurality of future time steps; performing bi-directional long-short term memory network (BiLSTM) on the input feature vectors to obtain hidden outputs corresponding to the plurality of future time steps; for each future time step: performing temporal convolution on the hidden outputs using a plurality of temporal scales to obtain context features at the plurality of temporal scales, and summating the context features at the plurality of temporal scales using a plurality of weights to obtain multi-scale context features; and converting the multi-scale context features to obtain the time series forecasting corresponding to the future time steps.