Jun Wu

7118854, Oct 10, 2006

Sep 28, 2001

09/967624

Peter Chu - San Francisco CA, US
Jorge Pardo - San Francisco CA, US
Congfen Li - Davis CA, US
Haoran Zhao - Foster City CA, US
Jun Wu - Sunnyvale CA, US

Rigel Pharmaceuticals, Inc. - South San Francisco CA

C12Q 1/70
C12Q 1/68
C07H 21/04

435 4, 435 6, 536 231

The present invention relates to regulation of lymphocyte activation. More particularly, the present invention is directed to nucleic acids encoding PAK2, which is involved in modulation of lymphocyte activation. The invention further relates to methods for identifying and using agents, including small organic molecules, peptides, circular peptides, antibodies, lipids, antisense nucleic acids, and ribozymes, that modulate lymphocyte activation via modulation of PAK2; as well as to the use of expression profiles and compositions in diagnosis and therapy related to lymphocyte activation and suppression.

7478033, Jan 13, 2009

Mar 16, 2004

10/802479

Jun Wu - Los Altos CA, US
Hulcan Zhu - San Jose CA, US
Hongjun Zhu - Sunnyvale CA, US

Google Inc. - Mountain View CA

G06F 17/28

704 2, 704 1, 704 9, 704 10

Systems and methods to process and translate pinyin to Chinese characters and words are disclosed. A Chinese language model is trained by extracting unknown character strings from Chinese inputs, e. g. , documents and/or user inputs/queries, determining valid words from the unknown character strings, and generating a transition matrix based on the Chinese inputs for predicting a word string given the context. A method for translating a pinyin input generally includes generating a set of Chinese character strings from the pinyin input using a Chinese dictionary including words derived from the Chinese inputs and a language model trained based on the Chinese inputs, each character string having a weight indicating the likelihood that the character string corresponds to the pinyin input. An ambiguous user input may be classified as non-pinyin or pinyin by identifying an ambiguous pinyin/non-pinyin ASCII word in the user input and analyzing the context to classify the user input.

7769751, Aug 3, 2010

Jan 17, 2006

11/334157

Jun Wu - Saratoga CA, US
Zhengzhu Feng - Cupertino CA, US
Quji Guo - Sunnyvale CA, US
Zhe Qian - Saratoga CA, US

Google Inc. - Mountain View CA

G06F 7/00
G06F 17/30

707728, 707736, 707748, 707749, 707750

One embodiment of the present invention provides a system that automatically classifies documents (such as web pages) based on user inputs. During operation, the system obtains a “classified” set of documents which are classified as relating to a specific topic. The system also obtains queries related to the specific topic. These queries produce “query results” which enable the user to access documents related to the query. The queries also include “click information” which specifies how one or more users have accessed the query results. The system uses this click information to identify documents in the classified set of documents which are not related to the specific topic or are off-topic. If such documents are identified, the system shifts the identified documents so that they are regarded as off-topic and/or spam, and removes the identified documents from the classified set of documents.

7810030, Oct 5, 2010

Oct 3, 2007

11/866991

Jun Wu - Saratoga CA, US
Liren Chen - Mountain View CA, US

Google Inc. - Mountain View CA

G06F 17/21
G06F 17/28

715257, 715221, 715224, 715226, 715255, 715256, 715264, 715265

Fault-tolerant systems and methods to process and correct input errors are disclosed. Original inputs can be received, each original input being defined as mapping to multiple characters in a language, each original input having one or more associated proximity measurements. Original inputs that have proximity measurements with one or more non-zero probabilities for respective intended inputs are identified as potentially incorrect original inputs. Each of the potentially incorrect original inputs is expanded to the respective intended inputs, and each of the original inputs and each of the respective intended inputs are converted to characters in the language, each of the conversions being a combination of the converted original inputs and/or the respective intended inputs. Likelihoods of conversions of the original inputs and the respective intended inputs to the characters based in part on the proximity measurements are determined, and most likely conversions are identified for presentation.

7917355, Mar 29, 2011

Aug 23, 2007

11/844153

Jun Wu - Saratoga CA, US
Tang Xi Liu - Beijing, CN
Feng Hong - Foster City CA, US
Yonggang Wang - Beijing, CN
Bo Yang - Beijing, CN
Lei Zhang - Beijing, CN

Google Inc. - Mountain View CA

G06F 17/21
G06F 17/27
G06F 17/20

704 10, 704 1, 704 9

Methods, systems, and apparatus, including computer program products, in which data from web documents are partitioned into a training corpus and a development corpus are provided. First word probabilities for words are determined for the training corpus, and second word probabilities for the words are determined for the development corpus. Uncertainty values based on the word probabilities for the training corpus and the development corpus are compared, and new words are identified based on the comparison.

7983902, Jul 19, 2011

Aug 23, 2007

11/844067

Jun Wu - Saratoga CA, US
Tang Xi Liu - Beijing, CN
Feng Hong - Foster City CA, US
Yonggang Wang - Beijing, CN
Bo Yang - Beijing, CN
Lei Zhang - Beijing, CN

Google Inc. - Mountain View CA

G06F 17/21
G06F 17/20
G06F 17/27

704 10, 704 1, 704 9

Methods, systems, and apparatus, including computer program products, to identify topic words in a document corpus that includes topic documents related to a topic are disclosed. A reference topic word divergence value based on the document corpus and the topic document corpus is determined. A candidate topic word divergence value for a candidate topic word is determined based on the document corpus and the topic document corpus. The candidate topic word is determined to be a topic word if the candidate topic word divergence value is greater than the reference topic word divergence value.

8019748, Sep 13, 2011

Nov 14, 2007

11/940079

Jun Wu - Saratoga CA, US
Hang Cui - Tianjin, CN
Hangjun Ye - Beijing, CN

Google Inc. - Mountain View CA

G06F 17/30

707713

Similar queries are identified so that suggested search queries may be provided to a user. A first search query having at least one term associated with a semantic weight is received. A second query having at least one term associated with a semantic weight is received. A first vector is generated based on the first query and the at least one semantic weight of the first query, and a second vector is generated based on the second query and the at least one semantic weight of the second query. A similarity measurement between the first and second search queries is made based at least in part on a comparison of the first vector to the second vector.

8321403, Nov 27, 2012

Apr 11, 2011

13/084482

Jun Wu - Saratoga CA, US
Hang Cui - Tianjin, CN
Hangjun Ye - Beijing, CN

Google Inc. - Mountain View CA

G06F 17/30

707713

Similar queries are identified so that suggested search queries may be provided to a user. A first search query having at least one term associated with a semantic weight is received. A second query having at least one term associated with a semantic weight is received. A first vector is generated based on the first query and the at least one semantic weight of the first query, and a second vector is generated based on the second query and the at least one semantic weight of the second query. A similarity measurement between the first and second search queries is made based at least in part on a comparison of the first vector to the second vector.