Ex Parte Coleman

Board of Patent Appeals and Interferences

Mar 17, 2011

09697497 (B.P.A.I. Mar. 17, 2011)

UNITED STATES PATENT AND TRADEMARK OFFICE
UNITED STATES DEPARTMENT OF COMMERCE
United States Patent and Trademark Office
Address: COMMISSIONER FOR PATENTS
P Alexandria, 0 Box 1450 Virginia 22313- 1450
www uspto gov
75127 7590 03/21/2011
KING & SPALDING LLP (CITI CUSTOMER NUMBER)
ATTN: Eric Sophir
1700 PENNSYLVANIA AVENUE, NW
SUITE 200
WASHINGTON, DC 20006
APPLICATION NO.
EXAMINER
AKWTOLA, OLABODE
091697,497 1012712000 Ronald Coleman CITI0192-US 3524
FILING DATE
I ARTUNIT I PAPERNUMBER I
FIRST NAMED INVENTOR
Please find below andlor attached an Office communication concerning this application or proceeding.
NOTIFICATION DATE
The time period for reply, if any, is set in the attached communication.
ATTORNEY DOCKET NO.
DELIVERY MODE
Notice of the Office communication was sent electronically on above-indicated "Notification Date" to the
following e-mail address(es):
Citi-Docket @kslaw.com
CONFIRMATION NO.
03/21/2011 ELECTRONIC
PTOL-90A (Rev. 04/07)
UNITED STATES PATENT AND TRADEMARK OFFICE
BEFORE THE BOARD OF PATENT APPEALS
AND INTERFERENCES
Ex parte RONALD COLEMAN
Appeal 2010-004097
Application 091697,497
Technology Center 3600
Before MURRIEL E. CRAWFORD, HUBERT C. LORIN, and
ANTON W. FETTING, Administrative Patent Judges.
FETTING, Administrative Patent Judge.
The two-month time period for filing an appeal or commencing a civil
action, as recited in 37 C.F.R. 5 1.304, or for filing a request for rehearing,
as recited in 37 C.F.R. 5 41.52, begins to run from the "MAIL DATE"
(paper delivery mode) or the "NOTIFICATION DATE" (electronic delivery
mode) shown on the PTOL-90A cover letter attached to this decision.
Appeal 2010-004097
Application 091697,497
Ronald Coleman (Appellant) seeks review under 35 U.S.C. 5 134 (2002)
of a final rejection of claims 1-9, the only claims pending in the application
on appeal. We have jurisdiction over the appeal pursuant to
35 U.S.C. 5 6(b) (2002).
The Appellant invented a way of measuring financial risks associated
with trading portfolios (Specification 1:6-9).
An understanding of the invention can be derived from a reading of
exemplary claim 1, which is reproduced below [bracketed matter and some
paragraphing added].
1. A method for identifying plausible sources of error in a risk
assessment system, comprising:
[I] identifying at least one variable of the risk assessment
system;
[2] determining a first hypothesis about the at least one
variable;
[3] providing an initial probability of the first hypothesis about
the at least one variable;
[4] identifying a change of value in the at least one variable of
the risk assessment system;
2 Our decision will make reference to the Appellant's Appeal Brief ("App.
Br.," filed June 29, 2009) and Reply Brief ("Reply Br.," filed December 15,
2009), and the Examiner's Answer ("Ans.," mailed October 15, 2009).
Appeal 2010-004097
Application 091697,497
[5] determining by probabilistic induction at least one cause of
the change of value in the at least one variable of the risk
assessment system, wherein the at least one cause is a plausible
source of error; and
[6] evaluating the initial probability of the first hypothesis
based on the at least one cause.
The Examiner relies upon the following prior art:
Dumais US 6,192,360 B1 Feb. 20, 2001
Matthews, Jr. US 6,526,358 B1 Feb. 25, 2003
Fogel US 6,542,905 B1 Apr. 1, 2003
Claims 1-9 stand rejected under 35 U.S.C. 5 103(a) as unpatentable over
Fogel, Matthews, and Dumais.
ISSUES
The issue of obviousness turns on whether Matthews evaluates the initial
probability of Fogel's first hypothesis based on at least one cause.
FACTS PERTINENT TO THE ISSUES
The following enumerated Findings of Fact (FF) are believed to be
supported by a preponderance of the evidence.
Facts Related to the Prior Art
Fogel
01. Fogel is directed to identifying data integrity issues and
showing how they can be resolved. Fogel 3:33-36.
02. Data integrity issues are patterns of items that could not result
from accurate assessment or are unlikely to arise. Fogel 5:41-49.
Appeal 2010-004097
Application 091697,497
03. Fogel describes some of the emergent patterns that would
suggest data validity or integrity in columns 5 and 6.
04. Fogel describes some of the tests used to discern such emergent
patterns at columns 9 and 10.
Matthews
05. Matthews is directed to an automated computer based data
integrity auditing system. Matthews 2: 1 - 17.
06. Matthews describes the use of a hypothesis tester with a
Bayesian likelihood ratio test to determine when an alternate
hypothesis becomes more likely. Matthews 6: 19-27.
Durnais
07. Dumais is directed to determining whether an object belongs to
a particular category. Dumais 1 :7-9.
08. Dumais describes how Bayesian networks operate. Dumais
3:35 - 4:42.
ANALYSIS
We are unpersuaded by the Appellant's argument that the art fails to
describe limitation [6] of evaluating the initial probability of the first
hypothesis based on the at least one cause. Appeal Br. 2-3.
Basically, Fogel describes a mechanism for evaluating data integrity (FF
01). The fundamental assumption is there are no data integrity issues until a
pattern suggesting such an issue arises. FF 02 and 03. So, Fogel identifies
its data as a set of variables whose risk of data integrity is to be assessed, and
Appeal 2010-004097
Application 091697,497
the patterns that data presents. Fogel's first hypothesis is that there are no
data integrity problems. The probability is exactly 100% until a pattern
suggesting otherwise emerges. The patterns that emerge from such data are
monitored and a pattern change that suggests data integrity issues are
identified. So far, Fogel describes limitations [I]-[4]. Now Fogel tests the
data to determine the likely cause of the emergent pattern. FF 04. Fogel
leaves the implementation details to one of ordinary skill.
To describe how one of ordinary skill would have tested the data in
Fogel, the Examiner cited Matthews which show the use of a hypothesis
tester with a Bayesian likelihood ratio test to determine when an alternate
hypothesis becomes more likely. FF 06. Thus, Matthews describes how one
of ordinary skill would have implemented Fogel's test to perform limitation
[5]. So far, none of these limitations are under contention.
Limitation [6] under contention requires evaluating the initial probability
of the first hypothesis. The Appellant has not limited the manner of
evaluation, as the Examiner found at Ans. 6. Matthews clearly performs
such an evaluation when it selects an alternate hypothesis, which implicitly
rejects the first hypothesis. The Examiner brought in Dumais to clarify the
nature of Matthews' Bayesian test. FF 08. The Appellant argues that
Matthews selects a hypothesis. Reply Br. 4. As may be, but Matthews'
selection implicitly evaluates the initial hypothesis in so doing.
CONCLUSIONS OF LAW
Rejecting claims 1-9 under 35 U.S.C. 5 103(a) as unpatentable over
Fogel, Matthews, and Dumais is not in error.
Appeal 2010-004097
Application 091697,497
DECISION
To summarize, our decision is as follows.
The rejection of claims 1-9 under 35 U.S.C. 5 103(a) as unpatentable
over Fogel, Matthews, and Dumais is sustained.
No time period for taking any subsequent action in connection with this
appeal may be extended under 37 C.F.R. 5 1.136(a). See 37 C.F.R.
5 1.136(a)(l)(iv) (2007).
AFFIRMED
mev
Address
KING & SPALDING LLP (CITI CUSTOMER NUMBER)
ATTN: Eric Sophir
1700 PENNSYLVANIA AVENUE, NW
SUITE 200
WASHINGTON DC 20006