Ex Parte Rolia et al

Patent Trial and Appeal Board

Aug 31, 2016

12252395 (P.T.A.B. Aug. 31, 2016)

UNITED STA TES p A TENT AND TRADEMARK OFFICE
APPLICATION NO. FILING DATE FIRST NAMED INVENTOR
12/252,395 10/16/2008 Jerome Rolia
56436 7590 09/02/2016
Hewlett Packard Enterprise
3404 E. Harmony Road
Mail Stop 79
Fort Collins, CO 80528
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.
82237013 7343
EXAMINER
ELKASSABGI, ZAHRA
ART UNIT PAPER NUMBER
3623
NOTIFICATION DATE DELIVERY MODE
09/02/2016 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):
hpe.ip.mail@hpe.com
mkraft@hpe.com
chris.mania@hpe.com
PTOL-90A (Rev. 04/07)
UNITED STATES PATENT AND TRADEMARK OFFICE
BEFORE THE PATENT TRIAL AND APPEAL BOARD
Ex parte JEROME ROLIA, LUDMILA CHERKASOV A,
SVEN GRAUPNER, and MICHAEL POGREBISKY
Appeal2014-004371 1
Application 12/252,3952
Technology Center 3600
Before HUBERT C. LORIN, KENNETH G. SCHOPPER, and
BRADLEY B. BAY AT, Administrative Patent Judges.
BAY AT, Administrative Patent Judge.
DECISION ON APPEAL
STATEMENT OF THE CASE
Appellants appeal under 35 U.S.C. § 134(a) from the decision
rejecting claims 1-20 under 35 U.S.C. § 103(a) as being unpatentable over
Liu3 and Wasserman.4 We have jurisdiction under 35 U.S.C. § 6(b).
1 Our decision references Appellants' Appeal Brief ("Br.," filed Dec. 3,
2012), the Examiner's Answer ("Ans.," mailed May 10, 2013), and the Final
Office Action ("Final Act.," mailed June 29, 2012).
2 Appellants identify "Hewlett-Packard Development Company, LP" as the
real party in interest. Br. 3.
3 Liu et al., US 2007/0219944 Al, published Sept. 20, 2007.
4 Wasserman et al., US 7,769,735 B2, iss. Aug. 3, 2010.
Appeal2014-004371
Application 12/252,395
BACKGROUND
Appellants' invention is related to the field of enterprise application
systems (Spec. i-f 1 ). Independent claim 1, reproduced below, is illustrative
of the subject matter on appeal:
1. A computer-implemented method for sizing enterprise
application systems, said method comprising:
determining, by a processor, a ratio of a plurality of pre-
defined benchmarks, wherein a workload of said ratio of said
plurality of pre-defined benchmarks corresponds to a desired
workload of an enterprise application system, and
wherein determining the ratio of the plurality of
pre-defined benchmarks includes determining a
percentage value for each of the plurality of pre-defined
benchmarks with respect to a predetermined total value;
and
using said percentage values of said plurality of pre-
defined benchmarks to determine a second benchmark for
testing said enterprise application system.
Br. 13, Claims Appendix.
ANALYSIS
In rejecting claim 1, the Examiner acknowledges that Liu does not
disclose "wherein determining the ratio of the plurality of pre-defined
benchmarks includes determining a percentage value for each of the
plurality of pre-defined benchmarks with respect to a predetermined total
value," and instead finds that the teachings of Wasserman at "column 7,
lines 8-55, including Table 1, noting average CPU utilization%" (Final Act.
4 (emphasis omitted); see also Ans. 4) remedy this deficiency.
Appellants challenge this finding, arguing that
each of the Average CPU Utilization(%) values in Table 1 of
Wasserman is an averaged percentage of the total CPU
2
Appeal2014-004371
Application 12/252,395
Br. 8.
utilization to execute a query. For example, as shown in Table 1
of Wasserman, the System A utilizes an average of 72% of the
CPUs to execute Query Number 1, 25% of the CPUs to execute
Query Number 2, and 61 % o[fJ the CPUs to execute Query
Number 3. However, Wasserman does not show a breakdown
of the ratios or percentage values for a plurality of benchmarks
that are used to execute a query. For example, Wasserman does
not show a ratio or percentage value for each of a plurality of
benchmarks that may be used to execute the Query Number 1,
2, or 3.
Responding in the Answer to Appellants' argument, the Examiner
"interpret[ s] this claim limitation in essence to disclose the following
meaning to one of ordinary skill in the art" (Ans. 14).
An enterprise has multiple (key word, plurality)
benchmarks that that corresponds to a desired workload of
the enterprise (Appellant's claim l, second limitation-directly
above argued claim limitation that would be necessarily read
with argued limitation for clarity-Examiner used Liu for
disclosure) wherein for each of the multiple benchmarks
(again, stating desired workload of the enterprises) a
determined percentage value, which in turn determines a
ratio, to the total predefined value of the benchmarks. This
in turn assigns each of the predefined benchmark a
percentage value. (claim 3, which depend on claim 2, which in
tum depends on claim 1).
Ans. 15 (italics omitted).
During examination, "claims ... are to be given their broadest
reasonable interpretation consistent with the specification, [ ] and ... claim
language should be read in light of the specification as it would be
interpreted by one of ordinary skill in the art." In re Bond, 910 F .2d 831,
833 (Fed. Cir. 1990) (internal citation and quotations omitted). Appellants'
Specification provides:
3
Appeal2014-004371
Application 12/252,395
In the example of Figure 4 B, vector 401 is multiplied by
0.1, vector 402 is multiplied by 0.3, and vector 403 is
multiplied by 0.4. In embodiments of the present invention, the
ratios of vectors 401, 402, and 403 are applied to the
corresponding benchmarks (e.g., benchmarks 201, 202, and 203
respectively of Figure 2) which they represent to create a
second benchmark 440. In other words, the workload created
when second benchmark 440 is executed comprises the sum of
ten percent of the workload created when benchmark 201 is
executed, thirty percent of the workload created when
benchmark 202 is executed, and forty percent of the workload
created when benchmark 203 is executed in addition to any
other benchmarks not represented in Figures 4A and 4B. Thus,
by creating a second vector comprising a ratio of benchmarks
201, 202, and 203 which corresponds to the workload
represented by vector 420, embodiments of the present
invention are able to create a second benchmark comprising a
ratio of pre-defined benchmarks which correspond to the
desired workload imposed on enterprise application system 200
by the customized business process model 205 created by the
client.
Spec. ,-r 32.
The Examiner's interpretation does not adequately explain how
Wasserman teaches this contested limitation in light of the Specification as it
would be interpreted by one of ordinary skill in the art. Table 1 of
Wasserman is directed to the averaged parameter values for data from a
benchmark power run (Wasserman, Table 1 ). The average CPU utilization
percentage shown in Table 1 refers to "the average utilization of the
processor( s) over the duration of query execution" (Wasserman 7: 15-1 7).
As Appellants observe, Wasserman's average CPU utilization percentage
values are not percent values of benchmarks with respect to a predetermined
total value, as required by claim 1. As such, we are persuaded by
4
Appeal2014-004371
Application 12/252,395
Appellants' arguments and do not sustain the rejection of independent claim
1, and claims 2-7 dependent thereon.
Independent claims 8 and 15 recite substantially similarly limitations
and are rejected based on the same findings as claim 1 (see Final Act. 6-7).
Accordingly, we do not sustain the rejection of independent claims 8 and 15
for the same reasons discussed with respect to claim 1. As such, we do not
sustain the rejection of claims 9-14 and 16-20, each of which depends,
directly or indirectly, from one of independent claims 8 and 15.
DECISION
The Examiner's rejection of claims 1-20 is reversed.
REVERSED
5