Ex Parte O

Board of Patent Appeals and Interferences

Apr 12, 2006

09608595 (B.P.A.I. Apr. 12, 2006)

The opinion in support of the decision being entered today was not written
for publication and is not binding precedent of the Board.

UNITED STATES PATENT AND TRADEMARK OFFICE

________________

BEFORE THE BOARD OF PATENT APPEALS
AND INTERFERENCES
________________

Ex parte KENNETH W. O’FLAHERTY
________________

Appeal No. 2005-2561
Application No. 09/608,595
________________

ON BRIEF
________________

Before BARRY, BLANKENSHIP and NAPPI, Administrative Patent Judges.

NAPPI, Administrative Patent Judge.

DECISION ON APPEAL

This is a decision on the appeal under 35 U.S.C. § 134 from the examiner’s
rejection of claims 1 through 42. For the reasons stated infra we reverse the examiner’s
rejection of these claims.
Appeal No. 2005-2561
Application No. 09/608,595

2

The Invention
The invention relates to a management system which makes use of predictive
models that have been constructed by a model- building mechanism in a data mining
system. The system is for users who are unfamiliar with data mining. See page 3 of
appellant’s specification.
Claim 1 is representative of the invention and is reproduced below:
1. A method for using predictive models within a computer-implemented
business analysis environment, comprising:
(a) applying a derived measure against a segment, wherein the derived
measure comprises a predictive model previously-built by a model-building
mechanism in a data mining system; and
(b) generating output for the segment from the predictive model in the form of
measure values.

Reference
The reference relied upon by the examiner is:
Amado 5,701,400 December 23, 1997

Rejection at Issue
Claims 1 through 42 stand rejected under 35 U.S.C. § 102 as being anticipated
by Amado.
Opinion
We have carefully considered the subject matter on appeal, the rejection
advanced by the examiner and the evidence of anticipation relied upon by the examiner
as support for the rejection. We have, likewise, reviewed and taken into consideration,
in reaching our decision, the appellant’s arguments set forth in the briefs, along with the
Appeal No. 2005-2561
Application No. 09/608,595

3
examiner’s rationale in support of the rejection and arguments in rebuttal set forth in the
examiner’s answer. With full consideration being given to the subject matter on appeal,
the examiner’s rejection and the arguments of appellant and examiner, for the reasons
stated infra, we will not sustain the examiner’s rejection of claims 1 through 42.
Appellant asserts, on pages 4 and 5 of the brief, that Amado does not teach the
limitation of “applying a derived measure against a segment, wherein the derived
measure comprises a predictive model previously-built by a model-building mechanism
in a data mining system” as recited in independent claims 1, 15 and 29. Appellant
argues Amado merely describes predictive modeling and data mining generally, but
does not teach a measure, which comprises a predictive model.
On page 13 of the answer, the examiner equates the records in the database of
Amado with the claimed “segments”. The examiner equates the claimed “measures”
with formulas in Amado. On pages 13 and 14 of the answer, the examiner reasons that:
Amado does teach a formula applied to a segment data structure (“count the
number of records in PRRESULT containing the field PER equal to or larger than
PerIni and smaller or equal than PerFin and then store this number the count in
variable CountDiag”, column 88, lines 64-67), wherein a record is a data
structure that is identical to the claimed segments. A ‘count’ is a formula applied
against said segments or records … Since a count … produces the numerical
result of a counting formula or function, it is in fact a measure of the number of
records...”

Further, the examiner asserts two different aspects of Amado teach the use of
predictive models. On page 6 of the answer, the examiner cites Amado, column 17,
lines 18 through 26 as teaching forecasting and predictions. Also on, page 14 of the
answer, the examiner equates Amado’s “diagnostics” with the claimed predictive mode.
We disagree with the examiner’s rationale. Claim 1 contains the limitation
Appeal No. 2005-2561
Application No. 09/608,595

4
“applying a derived measure against a segment, wherein the derived measure
comprises a predictive model previously-built by a model-building mechanism in a data
mining system.” Claims 15 and 29 contain similar limitations. Appellant’s specification,
on pages 4 and 5, defines a segment as “a grouping of data elements organized about
one or more attributes” and defines a measure as “a formula applied against a Segment
or Sub-segment. A measure may involve simply aggregating values retrieved from a
database, computing a formula, or executing a previously-built predictive model.” Thus,
we concur with the examiner’s finding equating Amado’s database and formula with the
claimed segment and measures. However, claim 1 identifies the measure as being a
predictive model.
We do not find that Amado teaches that the formulas (measures) applied to the
data in the database (segments) are predictive measures. The discussion of predictive
models, in column 17 of Amado, is directed to the background of the invention but
Amado does not teach that such models are used as part of Amado’s invention. Nor
does Amado teach that the predictive models are built by a model-building mechanism
in a data mining system. Similarly, we are not persuaded by the examiner’s assertion,
on page 14 of the answer: “Amado’s does teach a predictive model (‘the ability to
identify and execute specific actions as soon as particular diagnostics are generated or
activated. Each diagnostic may have an associated set of actions. Suggested actions
are generated the very same instant the diagnostics are generated’, column 25, lines
43-47).” We fail to see how the disclosure of Amado’s diagnostics meets a predictive
model. Thus, we do not find that Amado teaches all of the limitations of independent
claims 1, 15 and 29.
Appeal No. 2005-2561
Application No. 09/608,595

5
For the foregoing reasons, we will not sustain the examiner’s rejection of claims 1
through 42 under 35 U.S.C. § 102. The decision of the examiner is reversed.

REVERSED

LANCE LEONARD BARRY )
Administrative Patent Judge )
)
)
)
)
HOWARD B. BLANKENSHIP ) BOARD OF PATENT
Administrative Patent Judge ) APPEALS AND
) INTERFERENCES
)
)
)
ROBERT E. NAPPI )
Administrative Patent Judge )

REN /gjh

JAMES M. STOVER
NCR CORPORTION
1700 SOUTH PATTERSON BLVD, WHQ4
DAYTON, OH 45479