Daniel T Richards

US Patent:

6741986, May 25, 2004

Filed:

Nov 9, 2001

Appl. No.:

10/038197

Inventors:

Raymond J. Cho - Sunnyvale CA
Richard O. Chen - Mountain View CA
Ramon M. Felciano - San Carlos CA
Daniel R. Richards - Palo Alto CA
Philippa Norman - Los Altos CA

Assignee:

Ingenuity Systems, Inc. - Mountain View CA

International Classification:

G06F 1730

US Classification:

707 5, 707 3, 707 6, 707101

Abstract:

A system and method of information extraction and storage extracts information from a plurality of articles in a distributed manner and stores the extracted information in an information store. In one embodiment, the system includes identification of a plurality of articles from which information is to be extracted and a plurality of information extractors for extracting the information from the articles. A database is provided for storing information related to the plurality of articles and the plurality of information extractors. The plurality of articles are assigned to the plurality of information extractors for information extraction and the extracted information is then stored in the information store.

US Patent:

6772160, Aug 3, 2004

Filed:

Dec 8, 2000

Appl. No.:

09/733495

Inventors:

Raymond J. Cho - Sunnyvale CA
Richard O. Chen - Mountain View CA
Ramon M. Felciano - San Carlos CA
Daniel R. Richards - Palo Alto CA
Philippa Norman - Los Altos CA

Assignee:

Ingenuity Systems, Inc. - Mountain View CA

International Classification:

G06F 1730

US Classification:

707 10, 707 3, 707 6, 707102, 709203, 709219, 706 50, 706 61, 702 19, 702 82

Abstract:

The method and system for extracting information from a plurality of articles and for storing the extracted information in a knowledge-based information store. The method and system identify a plurality of articles from which information is to be extracted. The method and system identify and assign a plurality of information extractors for extracting information from the plurality of articles. The method and system receive information extracted by an information extractor from an article assigned to the information extractor. The method and system enable a content reviewer to review the extracted information received from the information extractor and the content reviewer identifies errors associated with the extracted information. If the error count is above the threshold level, the article may be reassigned for information extraction. If the error count is equal to or below the threshold level, the content reviewer may change the extracted information to correct the errors.

US Patent:

7577683, Aug 18, 2009

Filed:

Feb 2, 2004

Appl. No.:

10/770864

Inventors:

Raymond J. Cho - San Mateo CA, US
Richard O. Chen - Cupertino CA, US
Ramon M. Felciano - San Francisco CA, US
Daniel R. Richards - Palo Alto CA, US

Assignee:

Ingenuity Systems, Inc. - Redwood CA

International Classification:

G06F 17/30

US Classification:

7071041, 702 19, 706 46, 707E1799

Abstract:

Methods for constructing and maintaining knowledge representation systems are disclosed herein. The knowledge representation system is initially organized and populated using knowledge engineers. After the initial organization, scientific domain experts digest and structure source texts for direct entry into the knowledge representation system using templates created by the knowledge engineers. These templates constrain both the form and content of the digested information, allowing it to be entered directly into the knowledge representation system. Although knowledge engineers are available to evaluate and dispose of those instances when the digested information cannot be entered in the form required by the templates, their role is much reduced from conventional knowledge representation system construction methods. The methods disclosed herein permit the construction and maintenance of a much larger knowledge representation system than could be constructed and maintained using known methods.

US Patent:

7650339, Jan 19, 2010

Filed:

Jun 8, 2004

Appl. No.:

10/864163

Inventors:

Raymond J. Cho - Sunnyvale CA, US
Richard O. Chen - Mountain View CA, US
Ramon M. Felciano - San Carlos CA, US
Daniel R. Richards - Palo Alto CA, US
Philippa Norman - Los Altos CA, US

Assignee:

Ingenuity Systems, Inc. - Redwood City CA

International Classification:

G06F 17/30

US Classification:

707 10, 7071041, 707E17099, 706 46

Abstract:

A method, system, and computer program product are provided for extracting information from a plurality of articles in a distributed manner and for storing the extracted information in an information store. The invention identifies a plurality of articles from which information is to be extracted and a plurality of information extractors for extracting the information from the articles. Each article is assigned a priority score and ranking the articles from highest to lowest priority, thereby generating a queue; wherein the priority score for each article is calculated using a user-configurable priority calculation algorithm. The plurality of articles is assigned to the plurality of information extractors based on order in the queue, wherein an article with a higher rank is presented for information extraction before an article with a lower rank. Information extracted by information extractors from the articles is stored in the information store.

US Patent:

8392353, Mar 5, 2013

Filed:

Jul 8, 2009

Appl. No.:

12/499761

Inventors:

Raymond J. Cho - San Mateo CA, US
Richard O. Chen - Cupertino CA, US
Ramon M. Felciano - San Francisco CA, US
Daniel R. Richards - Palo Alto CA, US

Assignee:

Ingenuity Systems Inc. - Redwood City CA

International Classification:

G06F 17/00
G06N 5/04

US Classification:

706 60

Abstract:

Methods for constructing and maintaining knowledge representation systems (KRS) are disclosed. The KRS is initially organized and populated using knowledge engineers. After initial organization, scientific domain experts digest and structure source texts for direct entry into the KRS using templates. These templates constrain both the form and content of the digested information, allowing it to be entered directly into the KRS. The methods disclosed herein permit the construction and maintenance of a much larger KRS than could be constructed and maintained using known methods. Fact type specific fact templates are completed, accepting predefined fact types found in predetermined information sources. Fact template may comprise a user interface that constrains user entry to one of a predetermined set of valid entries. The user interface may include a user field that permits entry of new information not included in the predetermined set of valid user entries.

US Patent:

8489334, Jul 16, 2013

Filed:

Feb 3, 2003

Appl. No.:

10/502420

Inventors:

Richard O. Chen - Redwood City CA, US
Raymond J. Cho - San Mateo CA, US
Ramon M. Felciano - San Francisco CA, US
Bret Holley - New York NY, US
Viresh Patel - San Francisco CA, US
Daniel R. Richards - Palo Alto CA, US
Sushma Selvarajan - Mt. View CA, US
Keith Steward - The Woodlands TX, US
Sara Schneider - South San Francisco CA, US

Assignee:

Ingenuity Systems, Inc. - Mountain View CA

International Classification:

G06F 19/10
G06F 19/00

US Classification:

702 19, 702 20

Abstract:

Method for identifying disease-related pathways that can used to identify discovery targets, to identify new uses for known drugs, to identify markers for drug response, and related purposes.

US Patent:

20040236740, Nov 25, 2004

Filed:

Jul 21, 2004

Appl. No.:

10/802615

Inventors:

Raymond Cho - San Mateo CA, US
Richard Chen - Cupertino CA, US
Ramon Felciano - San Francisco CA, US
Daniel Richards - Palo Alto CA, US
Philippa Norman - Emerald Hills CA, US

Assignee:

InGenuity Systems, Inc. - Alviso CA

International Classification:

G06F007/00

US Classification:

707/005000

Abstract:

The present invention relates to the field of information extraction and storage and more specifically to techniques for extracting information from a plurality of articles in a distributed manner and for storing the extracted information in an information store. an embodiment of the present invention identifies a plurality of articles from which information is to be extracted and a plurality of information extractors for extracting the information from the articles. A database is provided for storing information related to the plurality of articles and the plurality of information extractors. The plurality of articles are assigned to the plurality of information extractors for information extraction. Information extracted by information extractors from the articles is stored in the information store.

US Patent:

20070178473, Aug 2, 2007

Filed:

Aug 1, 2003

Appl. No.:

10/632099

Inventors:

Richard Chen - Redwood City CA, US
Raymond Cho - Sunnyvale CA, US
Ramon Felciano - San Carlos CA, US
Brett Holley - New York NY, US
Viresh Patel - San Francisco CA, US
Daniel Richards - Palo Alto CA, US
Sushma Selvarajan - San Francisco CA, US
Keith Steward - San Jose CA, US
Sara Schneider - S. San Francisco CA, US

International Classification:

C12Q 1/68
G06F 19/00

US Classification:

435006000, 702020000

Abstract:

Methods for identifying disease-related pathways that can be used to identify drug discovery targets, to identify new uses for known drugs, to identify markers for drug response, and related purposes.