Ex Parte Bateni et al

Patent Trial and Appeal Board

Jun 7, 2016

12649005 (P.T.A.B. Jun. 7, 2016)

UNITED STA TES p A TENT AND TRADEMARK OFFICE
APPLICATION NO. FILING DATE
12/649,005 12/29/2009
26890 7590 06/09/2016
JAMES M, STOVER
TERADATA US, INC.
10000 INNOVATION DRIVE
DAYTON, OH 45342
FIRST NAMED INVENTOR
Arash Bateni
UNITED STATES DEPARTMENT OF COMMERCE
United States Patent and Trademark Office
Address: COMMISSIONER FOR PATENTS
P.O. Box 1450
Alexandria, Virginia 22313-1450
www .uspto.gov
ATTORNEY DOCKET NO. CONFIRMATION NO.
20170 4816
EXAMINER
PRASAD, NANCY N
ART UNIT PAPER NUMBER
3624
NOTIFICATION DATE DELIVERY MODE
06/09/2016 ELECTRONIC
Please find below and/or attached an Office communication concerning this application or proceeding.
The time period for reply, if any, is set in the attached communication.
Notice of the Office communication was sent electronically on above-indicated "Notification Date" to the
following e-mail address( es):
michelle. boldman @teradata.com
jam es.stover@teradata.com
td.uspto@outlook.com
PTOL-90A (Rev. 04/07)
UNITED STATES PATENT AND TRADEMARK OFFICE
BEFORE THE PATENT TRIAL AND APPEAL BOARD
Ex parte ARASH BATENI, EDWARD KIM,
PHILIPPE HAMEL, and BLAZIMIR RADOVIC
Appeal2013-010427
Application 12/649,005 1
Technology Center 3600
Before PHILIP J. HOFFMANN, TARA L. HUTCHINGS, and
SHEILA F. McSHANE, Administrative Patent Judges.
McSHANE, Administrative Patent Judge.
DECISION ON APPEAL
The Appellants seek our review under 35 U.S.C. § 134(a) of the
Examiner's final decision to reject claims 1, 3, 4, and 6. We have
jurisdiction under 35 U.S.C. § 6(b ).
We REVERSE.
1 According to the Appellants, the real party in interest is Teradata US,
Incorporated. Appeal Brief filed January 7, 2013, hereafter "App. Br.," 2.
Appeal2013-010427
Application 12/649,005
BACKGROTJND
The invention relates to forecasting and modeling product demand for
a product. Abstract. A product demand forecast is generated by blending
influencing causal factors in accordance with corresponding regression
coefficients determined by analysis of historical product demand and factor
information, including the determination of regression coefficients and
removal of redundant causal variables from the regression analysis.
Specification, hereafter "Spec.," 3:8-13, filed December 29, 2009.
Representative claim 1 is reproduced from pages 11 and 12 of the
Appeal Brief (Claims App'x) as follows, with emphasis added to relevant
claim limitations:
1. A computer-implemented method for forecasting product
demand for a product, the method comprising the steps of:
maintaining, on a computer, an electronic database of
historical product demand information and historical
causal factor information for a plurality of factors
influencing demand for said product;
analyzing, by said computer, said causal factor
information to identify nonredundant causal factors, said
step of analyzing said causal factor information to
identify non-redundant causal factors comprising the
steps of:
selecting first and second causal factors for
examination;
comparing historical values for said first causal
factor with historical values of said second causal
factor to identifj; a linear relationship between the
historical values of said first and second causal
factors;
identifying said first causal factor as a non-
redundant causal factor and said second causal
factor as a redundant causal factor when a linear
2
Appeal2013-010427
Application 12/649,005
relationship is identified between the historical
values of said first and second causal factors; and
identifying said first causal factor as a non-
redundant causal factor and said second causal
factor as a non-redundant causal factor when a
linear relationship is not identified between the
historical values of said first and second causal
factors;
analyzing, by said computer, said historical product
demand information and said historical causal factor
information for said product to determine a plurality of
regression coefficients corresponding to said non-
redundant causal factors; and
blending, by said computer, said plurality of regression
coefficients and future values for said corresponding non-
redundant causal factors to determine a product demand
forecast for said product[].
In a Final Rejection, the Examiner rejects claims 1, 3, 4, and 6 under
35 U.S.C. § 103(a) as obvious under Singh2 and Pinto3. Final Action,
hereafter "Final Act.," 2-5, mailed May 25, 2012; Answer, hereafter "Ans.,"
2-5, mailed June 20, 2013.
DISCUSSION
The Appellants argue issues common to both independent claims 1
and 4, with no separate arguments presented for the other claims. App. Br.
6-9. We select claim 1 as representative. 37 C.F.R. § 41.37(c)(l)(iv).
The Examiner finds that the combination of Singh and Pinto discloses
all the limitations of claim 1. Ans. 6 (citing Singh i-fi-120, 35-38, 43-56, 62,
2 US Publication 2002/0169657 Al, published November 14, 2002.
3 US Publication 2005/0234762 Al, published October 20, 2005.
3
Appeal2013-010427
Application 12/649,005
83, Figs. 4A-D). The Examiner finds that the Specification does not use the
term "non-redundant," and, thus, there is no explicit definition for the term
provided by the Appellants. Id. at 6-7. The Examiner refers to the
Specification's use of the term "causal factors" to include "current product
sales rate, seasonality of demand, product price, promotional activities, and
other factors," finding that, in light of this use, Singh discloses "causal
variables." Id. at 7 (citing Spec. 4:13-15; Singh i-fi-135-38, 55, Figs. 4A-D).
The Examiner then refers to claim 1, and its description of "non-redundant
causal factors," asserting that the comparison of historical values for causal
factors to identify a linear relationship of the historical values would
determine "one non-redundant causal factor, whether or not a linear
relationship is actually identified." Id. at 8. The Examiner then finds that
Singh shows a "linear relationship," and, therefore, this also discloses at
least one non-redundant causal factor. Id. at 9-10 (citing Singh i-fi-120, 55-
60, 69-72, Fig. 4B).
The Appellants argue that the Examiner does not establish prima facie
obviousness of claim 1 because the references relied upon for the
obviousness rejections do not include any teaching or suggestion identifying
the redundant and non-redundant causal factors recited in the claim. App.
Br. 6. The Appellants contend that the portions of Singh relied upon for
teaching the causal factor information to identify non-redundant causal
factors instead refer to "processes for finding coefficients, not variables, and
specifically not non-redundant variables, of a forecasting algorithm that
produce a minimum squared error, and fitting the best model forecast to the
data using the maximum number of terms allowed." Id. at 6-7 (citing Singh
i1 60, Fig. 5) (emphasis in original). The Appellants argue that Singh
4
Appeal2013-010427
Application 12/649,005
describes the use of multiple forecasting algorithms and a multiple model
framework ("MMF") for forecasting, but does not teach or suggest non-
redundant causal variables. Id. at 8-9 (citing Singh i-fi-120, 43---62, 83).
The Appellants further argue that although Singh may disclose the
terms "linear forecast," "linear tendency," and "linear regression," Singh
fails to "refer[] to a linear relationship between the historical values of first
and second causal factors, and none of these terms are used in the
description of a process for identification of non-redundant causal
variables," as claim 1 requires. Reply Brief, hereafter "Reply Br.," 3, 4,
filed August 20, 2013.
After considering each of the Appellants' contentions and the
evidence presented in this Appeal, we are persuaded that the Appellants
identify reversible error in the rejections, and we reverse the Examiner's
§ 103 rejections for failing to identify prior art that teaches the claim
limitation "comparing historical values for said first causal factor with
historical values of said second causal factor to identify a linear
relationship ... "of claim 1. We add the following for emphasis.
In rejecting claims under 35 U.S.C. § 103(a), the Examiner bears the
initial burden of establishing a prima facie case of obviousness, where a
factual basis must be established to support the legal conclusion of
obviousness. See In re Fine, 837 F.2d 1071, 1073 (Fed. Cir. 1988); In re
Oetiker, 977 F.2d 1443, 1445 (Fed. Cir. 1992). Although the Examiner's
finding that Singh teaches that each of the causal factors are evaluated using
linear modeling is supported with its disclosures, we determine that Singh
lacks any disclosure that the historical values of the respective causal factors
themselves are compared to one another to determine that there is (or is not)
5
Appeal2013-010427
Application 12/649,005
a linear relationship between them. See, e.g., Singh ilil 20, 55---60, 69-72,
Fig. 4B.
On this record, the Examiner has therefore not directed us to a prior
art teaching of "comparing historical values for said first causal factor with
historical values of said second causal factor to identify a linear relationship
between the historical values of said first and second causal factors," which
are elements of both independent claims 1 and 4. Absent that teaching, the
rejections of claims 3 and 6, which depend from the independent claims,
also cannot stand. Accordingly, we reverse the rejections of claims 1, 3, 4,
and 6.
SUMMARY
The rejections of claims 1, 3, 4, and 6 under 35 U.S.C. § 103(a) are
reversed.
REVERSED
6