Ex Parte Krishnappa et al

Patent Trial and Appeal Board

Jul 24, 2015

12427615 (P.T.A.B. Jul. 24, 2015)

UNITED STA TES p A TENT AND TRADEMARK OFFICE
APPLICATION NO. FILING DATE
12/427,615 04/21/2009
22879 7590 08/26/2015
HEWLETT-PACKARD COMPANY
3404 E. Harmony Road
Mail Stop 35
FORT COLLINS, CO 80528
FIRST NAMED INVENTOR
Nagendra Krishnappa
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.
82240493 7258
EXAMINER
POLLACK, MEL VIN H
ART UNIT PAPER NUMBER
2445
NOTIFICATION DATE DELIVERY MODE
08/26/2015 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):
ipa.mail@hp.com
barbl@hp.com
yvonne.bailey@hp.com
PTOL-90A (Rev. 04/07)
UNITED STATES PATENT AND TRADEMARK OFFICE
BEFORE THE PATENT TRIAL AND APPEAL BOARD
Ex parte NAGENDRA KRISHNAPP A and SUD HIND RA PRASAD
Appeal2013-001920
Application 12/427,615 1
Technology Center 2400
Before MICHAEL J. STRAUSS, KIMBERLY J. McGRAW, and
ROBERT L. KINDER, Administrative Patent Judges.
McGRAW, Administrative Patent Judge.
DECISION ON APPEAL
Pursuant to 35 U.S.C. § 134(a), Appellants appeal from the
Examiner's final rejections of 1-8, 142, 16, and 20. App. Br. 4. We have
jurisdiction under 35 U.S.C. § 6(b).
We affirm.
1 Appellants identify Hewlett-Packard Development Company, LP, as the
real party in interest. App. Br. 2.
2 Although the Status of Claims recites claim 15 as being subject to final
rejection and currently on appeal, we treat this as a typographical error and
that claim 14, not 15 (which is among claims indicated as allowable), was
intended to be recited.
Appeal2013-001920
Application 12/427,615
STATEMENT OF THE CASE
The present invention relates to methods of computer clustering.
Claims 1 and 3 are representative of the subject matter appeal (disputed
limitations italicized)
1. A method of forming a computer cluster comprising:
receiving, at a node, a request to create said cluster;
acquiring a specified number of member nodes for cluster
formation based on a node selection criteria;
electing a cluster coordinator from the member nodes;
wherein the cluster coordinator is elected based on a mean
time between failures value for each of the respective member nodes.
3. The method of claim 1 wherein the mean time between
failures value of member nodes is assigned randomly on initialization
of the cluster.
App. Br. 20 (Claims App'x).
REJECTIONS ON APPEAL3
Claims 1, 2, and 5 stand rejected under 35 U.S.C. § 103(a) as being
unpatentable over Hoover (US 2007/0255813 Al, published Nov. 1, 2007),
Natanzon (US 7,840,662 Bl, issued Nov. 23, 2010 ("the '662 patent")), and
Islam (US 5,944,793, issued Aug. 31, 1999 ("the '793 patent")). Final
3 Appellants request review of the Examiner's objections of claims 1--4, 8,
12, 14--16, and 19. App. Br. 17-18. However, these objections relate to
petitionable subject matter under 3 7 C.F .R § 1.181 and, therefore, are not
properly before us. See MPEP § 706.01 ("[T]he Board will not hear or
decide issues pertaining to objections and formal matters which are not
properly before the Board."); see also MPEP § 1201 ("The Board will not
ordinarily hear a question that should be decided by the Director on
petition .... ").
2
Appeal2013-001920
Application 12/427,615
Act. 6.
Claim 3 is rejected under 35 U.S.C. § 103(a) as being unpatentable
over Hoover, the '662 patent, the '793 patent, and Gruber (US
2002/0091506 Al, published Jul. 11, 2002). Final Act. 9.
Claims 4, 6, 14, 16, and 20 are rejected under 35 U.S.C. § 103(a) as
being unpatentable over Hoover, the '662 patent, the '793 patent, and
Hamilton (US 2005/0034027 Al, published Feb. 10, 2005). Final Act. 10.
Claim 7 is rejected under 35 U.S.C. § 103(a) as being unpatentable
over Hoover, the '662 patent, the '793 patent, and Bridgelall (US
2005/0201301 Al, published Sept. 15, 2005). Final Act. 14.
Claim 8 is rejected under 35 U.S.C. § 103(a) as being unpatentable
over Hoover, the '662 patent, and Hamilton. Final Act. 15.
ISSUES
1. Did the Examiner err in finding the '662 patent in combination
with the '793 patent teaches or suggests "electing a cluster coordinator from
the member nodes, wherein the cluster coordinator is elected based on a
mean time between failures value for each of the respective member nodes,"
as recited in claim 1?
2. Did the Examiner err in finding the '793 patent in combination
with Gruber teaches or suggests "mean time between failures value of
member nodes is assigned randomly on initialization of the cluster" as
recited in claim 3?
3. Did the Examiner err in finding Hamilton teaches a "fail over
weight" as recited in claims 8 and 20?
3
Appeal2013-001920
Application 12/427,615
Issue 1 - Claim 1
ANALYSIS
Appellants argue that none of the cited references, Hoover, the '662
patent, or the '793 patent, teaches or suggests "electing a cluster coordinator
from the member nodes [] wherein the cluster coordinator is elected based
on a mean time between failures value for each of the respective member
nodes" as set forth in independent claim 1. App. Br. 9-12.
This argument is not persuasive as Appellants cannot show
nonobviousness by attacking references individually where the rejection is
based on combinations of references. See In re Keller, 642 F.2d 413, 426
(CCPA 1981); In re Merck & Co., Inc., 800 F.2d 1091, 1097 (Fed. Cir.
1986).
Appellants next argue that the '662 patent does not teach or suggest a
process for forming a computing cluster by electing a cluster coordinator
because it only teaches a protocol for selecting subsequent cluster
coordinators rather than the initial cluster coordinator. App. Br. 10.
However, the Examiner found that the '662 patent also teaches selection of
the initial cluster coordinator as the reference teaches how to choose the
leader candidate (cluster coordinator) prior to running the protocol used to
select the leader nodes (Ans. 2, citing the '662 patent 3: 10-15). Appellants
have not provided sufficient evidence or argument to persuade us the
Examiner erred in these findings. See e.g., Reply Br. 5.
Appellants also argue that, although the '793 patent teaches selecting
content providers based on a mean time to failure of a provider/node, the
'793 patent does not teach the disputed limitation of claim 1 because content
providers are not cluster coordinators. App. Br. 11-12. However, the
4
Appeal2013-001920
Application 12/427,615
Examiner found, and Appellants do not persuasively rebut, that the content
providers also act as cluster coordinators. Ans. 3 (stating inter alia "the
primary content provider is capable of node coordination activities, i.e.,
evaluating metrics and moving requests from node to node").
Additionally, the Examiner found that the '662 patent also teaches
electing a cluster coordinator from the member nodes and that it would have
been obvious to one skilled in the art to utilize the '793 patent's teaching to
select a leader node based on mean time between failures with the '662
patent in order to increase reliability of the selected leader node by
increasing the amount of time between lead node changes due to a leader
node failing. Final Act. 8. Appellants have not provided persuasive
argument why the combination of the '662 patent (which teaches electing a
cluster coordinator from member nodes) and the '793 patent (which teaches
electing a node based on mean time between failures value) would not
collectively teach or suggest the disputed claim limitation. As such, we
sustain the Examiner's rejection of claim 1.
Issue 2 - Claim 3
Appellants contend the Examiner has not shown the combination of
the '793 patent and Gruber teaches or suggests "wherein the mean time
between failures value of member nodes is assigned randomly on
initialization of the cluster" as recited in claim 3. App. Br. 13-14.
Specifically, Appellants assert that Gruber merely teaches simulating a
failure in a link between nodes where a random number generator provides a
link time to failure for that link (App. Br. 13) and that this does not equate to
a randomly assigning a mean time between failures value of member nodes
5
Appeal2013-001920
Application 12/427,615
on initiation of the cluster. App. Br. 13-14. Appellants further argue that
no combination of the references suggests this subject matter. Reply Br. 10.
Appellants' arguments are not persuasive as Appellants cannot show
nonobviousness by attacking references individually where the rejection is
based on combinations of references. Specifically, Examiner relies on the
'793 patent for teaching the mean time between failures value of member
nodes is assigned on initialization of the cluster (Ans. 10, citing the '793
patent 5: 13-1 7, 8: 13-1 7) and on Gruber for teaching the mean time between
failures value of member nodes may be assigned randomly (Ans. 10, citing
Gruber i-f 13). The Examiner found that one of skill in the art would
understand that systems used to create clusters in a simulation environment
could be applicable and used to improve initialization at the time of link
selection and connection formation. Ans. 4. Appellants have not
persuasively addressed the combination of these teachings.
We, therefore, conclude the Examiner did not err in finding the
combination of the '793 patent and Gruber teaches or suggests the disputed
limitation of claim 3.
Issue 3 - Claims 8 and 20
Appellants assert the Examiner erred in rejecting claims 8 and 20 as
Hamilton does not teach "failover weight" as defined in the Specification as
calculated by a specific formula. App. Br. 15-17, citing Spec. i-fi-146-48.
We disagree. During prosecution we must give claims their broadest
reasonable interpretation consistent with the specification. In re ICON
Health & Fitness, Inc., 496 F.3d 1374, 1379 (Fed. Cir. 2007). As applicants
may amend claims to narrow their scope, a broad but reasonable
construction during prosecution creates no unfairness to the applicant or
6
Appeal2013-001920
Application 12/427,615
patentee. Here, the Specification merely states that the failover weight "may
be calculated" using a particular formula. However, particular embodiments
appearing in the specification may not be read into a claim where the claim
language is broader than the embodiment. SuperGuide Corp. v. DirecTV
Enterprises, Inc., 358 F.3d 870. 875 (Fed. Cir. 2004). The Examiner found,
and we agree, that Hamilton teaches that the failover weight is a weighting
factor attached to a possibility of a failing node (Ans. 5, citing Hamilton,
Fig. 11, #553 and i-f 60) and thus teaches the failover weight of claims 8 and
20.
Claims 2, 4-6, 7, 14, and 16
Appellants argue that claims 2, 4---6, 7, 14, and 16 are patentable for
the same reasons as claim 1. App. Br. 9-12, 14--16. As we sustained the
Examiner's rejection of claim 1, this argument is not persuasive and we
sustain the Examiner's rejection of claims 2, 4--6, 7, 14, and 16.
DECISION
The Examiner's rejection of claims 1-8, 14, 16, and 20 under 35
U.S.C. § 103(a) is affirmed.
No time period for taking any subsequent action in connection with
this appeal may be extended under 37 C.F.R. § 1.136(a)(l )(iv).
AFFIRMED
mat
7