Ex Parte Dickinson

Board of Patent Appeals and Interferences

Apr 24, 2012

11016101 (B.P.A.I. Apr. 24, 2012)

UNITED STATES PATENT AND TRADEMARK OFFICE
____________

BEFORE THE BOARD OF PATENT APPEALS
AND INTERFERENCES
____________

Ex parte YOLANDA KAY DICKINSON
___________

Appeal 2009-014107
Application 11/016,101
Technology Center 2400
____________

Before ALLEN R. MACDONALD, ERIC S. FRAHM, and ERIC B. CHEN,
Administrative Patent Judges.

CHEN, Administrative Patent Judge.

DECISION ON APPEAL

This is an appeal under 35 U.S.C. § 134(a) from the final rejection of
claims 1-14, all the claims pending in the application. We have jurisdiction
under 35 U.S.C. § 6(b). We affirm-in-part.

Appeal 2009-014107
Application 11/016,101

2
STATEMENT OF THE CASE
Appellant’s invention relates to a computer program product for
determining one of a plurality of servers on which to install and execute an
application, including: (i) obtaining information from each of the plurality
of servers as to amounts of availability of their respective CPUs, RAMs and
storage; (ii) determining one or more of the servers which have sufficient
CPU, RAM and storage to execute the application; (iii) determining a weight
for each of the amounts for the one or more servers; (iv) summing together
for each of the one or more servers the weights for their respective amounts
of availability of the CPUs, RAMs and storage; and (v) determining which
of the one or more servers has a highest sum, such that the server with the
highest sum is recommended to execute the application.
Claims 1, 4, and 11 are exemplary, with disputed limitations in italics:
1. A computer program product for determining one of a
plurality of servers on which to install and execute an application, said
program product comprising:
a computer readable storage medium;
first program instructions to obtain information from each of
said plurality of servers as to amounts of availability of their
respective CPUs, RAMs and storage;
second program instructions to determine one or more of said
servers which have sufficient CPU, RAM and storage to execute said
application;
third program instructions to determine a weight for each of
said amounts for said one or more servers;
fourth program instructions to sum together, for each of said
one or more servers, the weights for their respective amounts of
availability of said CPUs, RAMs and storage; and
Appeal 2009-014107
Application 11/016,101

3
fifth program instructions to determine which of said one or
more servers has a highest sum, whereby said server with the highest
sum is recommended to execute said application; and wherein
said first, second, third, fourth and fifth program instructions
are tangibly recorded on said computer readable storage medium and
executed by a computer.

4. A computer program product as set forth in claim 1
further comprising:
sixth program instructions to obtain information of a financial
reason to install said application on each of said one or more servers
and determine a weight for the value of said financial reason in
relation to the weights for said amounts of availability of said CPU,
RAM and storage within each of said one or more servers.

11. A computer program product for determining one of a
plurality of servers on which to install and execute an application, said
program product comprising:
a computer readable medium;
first program instructions to obtain information from each of
said plurality of servers as to amounts of utilization of their respective
CPUs at a multiplicity of sample times;
second program instructions to obtain an estimate of amounts
of CPU utilization of said application on each of said servers at said
multiplicity of sample times; and
third program instructions to combine together, for each of said
plurality of servers at each of said sample times, the amounts of
utilization of their respective CPUs and the estimated amounts of
CPU utilization of said application, and determine which of said
plurality of servers on which to execute said application based in part
on the respective combined amounts of utilization of their respective
CPUs and the estimated amounts of CPU utilization of said
application; and wherein
Appeal 2009-014107
Application 11/016,101

4
said first, second and third program instructions are tangibly
recorded on said computer readable storage medium and executed by
a computer.
Claims 1-14 stand rejected under 35 U.S.C. § 103(a) as being obvious
over Uematsu (U.S. Patent No. 6,606,658 B1) and Lele (U.S. Patent
No. 7,181,524 B1).
The Examiner has withdrawn the rejection of claims 1-4, 11, and 12
under 35 U.S.C. § 101. (Ans. 14.)

ANALYSIS
Claims 1-3, 5-7, and 9
We are not persuaded by Appellant’s arguments (Br. 19-21) that the
combination of Uematsu and Lele would not have rendered obvious
independent claim 1, which includes the first disputed limitation, “third
program instructions to determine a weight for each of said amounts for said
one or more servers.”
The Examiner found that the processing capacity ratio management
table 3c of Uematsu corresponds to the first disputed limitation. (Ans. 4, 14-
15; Uematsu, col. 4, ll. 56-63.) We agree with the Examiner.
Uematsu “relates to a method for displaying server resource usage
status in a network in which a plurality of servers and a plurality of clients
are connected in such a manner as to be able to communicate with each
other.” (Col. 1, ll. 10-14.) For a network 4, servers 1-1 to 1-m are
connected to clients 2-1 to 2-n with a data processing server 3. (Col. 1, l. 66
to col. 2, l. 2; Fig. 1.) In one example, a CPU processing time on the
computing server 11-1 is represented by 1, a processing time on the
computing server 11-2 is ½ and a processing time on the computing server
Appeal 2009-014107
Application 11/016,101

5
11-3 is 1/3. (Col. 4, ll. 56-59.) “Accordingly, when the CPU processing
capacity of the computing server 11-1 is denoted by x, then the CPU
processing capacity of the computing server 11-2 is 2x and that of the
computing server 11-3 is 3x.” (Col. 4, ll. 60-63.) As illustrated in
Figure 2B, processing capacity ratios are stored in a processing capacity
ratio management table 3c. (Col. 2, ll. 19-22.) Therefore, Uematsu teaches
the limitation “third program instructions to determine a weight for each of
said amounts for said one or more servers.”
Appellant argues that “UEMATSU merely describes a processing
capacity ratio management table for storing processing capacity ratios as
well as a resource usage status management table for storing usage
information” which “is not the same as determining a weight for each of said
amounts for said one or more servers.” (Br. 20.) However, Appellant’s
Specification states that “[t]he greater the availability (or lower the percent
utilization of the CPU), the higher the weighting factor which translates to a
greater amount of attractiveness of the respective server to host the new
application.” (Spec. 11:2-4.) In other words, Appellant’s Specification
explains that a percent utilization of the CPU correlates to the claimed
“weight.” Thus, the claim language “weight for each of said amounts for
said one or more servers” is broad enough to encompass the processing
capacity ratio management table 3c of Uematsu.
Thus, we agree with the Examiner that the combination Uematsu and
Lele would have rendered obvious independent claim 1, which includes the
limitation “third program instructions to determine a weight for each of said
amounts for said one or more servers.”
Appeal 2009-014107
Application 11/016,101

6
We are also not persuaded by Appellant’s arguments (Br. 19-21) that
the combination of Uematsu and Lele would not have rendered obvious
independent claim 1, which includes the second disputed limitation “fourth
program instructions to sum together, for each of said one or more servers,
the weights for their respective amounts of availability of said CPUs, RAMs
and storage.”
The Examiner found that calculating the processing capacity ratio of
Uematsu corresponds to the second disputed limitation. (Ans. 4, 15-16;
Uematsu, col. 5, l. 67 to col. 6, l. 4.) We agree with the Examiner.
Figure 3 of Uematsu illustrates a process for creating the processing
capacity ratio management table (col. 5, ll. 40-41), including calculating “a
ratio relative to that of the reference computing server which is represented
by 1” (col. 5, l. 67 to col. 6, l. 2) and entering “the processing capacity ratio
of each computing server . . . into the processing capacity ratio management
table” (col. 6, ll. 2-4). Figures 6-8 of Uematsu illustrate various tabular or
graphical representations of CPU usage status of three computing servers.
(Col. 3, l. 58 to col. 4, l. 5). Therefore, by calculating and graphically
representing the processing capacity ratio, Uematsu teaches the limitation
“fourth program instructions to sum together, for each of said one or more
servers, the weights for their respective amounts of availability of said
CPUs, RAMs and storage.”
Thus, we agree with the Examiner that the combination Uematsu and
Lele would have rendered obvious independent claim 1, which includes the
limitation “fourth program instructions to sum together, for each of said one
or more servers, the weights for their respective amounts of availability of
said CPUs, RAMs and storage.”
Appeal 2009-014107
Application 11/016,101

7
We are further not persuaded by Appellant’s arguments (Br. 19-21)
that the combination of Uematsu and Lele would not have rendered obvious
independent claim 1, which includes the third disputed limitation “fifth
program instructions to determine which of said one or more servers has a
highest sum.”
The Examiner found that the performance measuring program of
Uematsu corresponds to the third disputed limitation. (Ans. 4, 16-17;
Uematsu, col. 5, ll. 14-21.) We agree with the Examiner.
Uematsu teaches that “the disk processing capacity of each of the
plurality of servers can be obtained by a performance measuring program
similar to that for measuring the memory processing capacity” and thus,
“provides a useful means when choosing a computing server suitable for a
job the client wishes to execute.” (Col. 5, ll. 14-21.) In other words, such
performance measuring program determines the server with the highest
processing capacity ratio and therefore, Uematsu teaches or suggests the
limitation “fifth program instructions to determine which of said one or more
servers has a highest sum.”
Thus, we agree with the Examiner that the combination Uematsu and
Lele would have rendered obvious independent claim 1, which includes the
limitation “fifth program instructions to determine which of said one or more
servers has a highest sum.”
Last, we are not persuaded by Appellant’s arguments (Br. 21-22) that
the combination of Uematsu and Lele would not have rendered obvious
independent claim 1, which includes the fourth disputed limitation “whereby
said server with the highest sum is recommended to execute said
application.”
Appeal 2009-014107
Application 11/016,101

8
The Examiner acknowledged that Uematsu does not disclose
“whereby said server with the highest sum is recommended to execute said
application” (Ans. 4) and therefore, relied on Lele for teaching selection of
the server with the greatest processing capacity (Ans. 5, 16-17; Lele, col. 3,
ll. 14-21). The Examiner concluded that claim 1 would have been obvious
over the combination of Uematsu and Lele. (Ans. 5.) We agree with the
Examiner.
Lele relates “to data storage systems, and more particularly, to
balancing a load among a plurality of servers in a computer system.”
(Col. 1, ll. 9-11.) Lele teaches that a load balancer 105 selects servers in a
group to evenly distribute a load across all servers in the group such that
“[s]ervers with the greatest processing capacity are given more traffic than
servers with lesser processing capacity.” (Col. 3, ll. 19-21.) Therefore, Lele
teaches the limitation “whereby said server with the highest sum is
recommended to execute said application.”
The combination of Uematsu and Lele is nothing more than
incorporating the known load balancer 150 of Lele to give more traffic to
servers with the greatest processing capacity with the known method for
displaying server resource usage status in a network of Uematsu, to yield
predictable results. See KSR Int’l Co. v. Teleflex Inc., 550 U.S. 398, 416
(2007). Thus, we agree with the Examiner (see Ans. 5) that modifying
Uematsu to include the load balancer 150 of Lele would have been obvious.
Appellant argues that “such disclosure [in Lele] is not the same as
summing together, for each of said one or more servers, the weights for their
respective amounts of availability of said CPUs, RAMs and storage, and the
Examiner has not demonstrated otherwise.” (Br. 29.) However, the
Appeal 2009-014107
Application 11/016,101

9
Examiner relied on Uematsu, rather than Lele, for teaching the claim
limitation “sum together, for each of said one or more servers, the weights
for their respective amounts of availability of said CPUs, RAMs and
storage.” (Ans. 4, 15-16.)
Thus, we agree with the Examiner that the combination Uematsu and
Lele would have rendered obvious independent claim 1, which includes the
limitation “whereby said server with the highest sum is recommended to
execute said application.”
Accordingly, we sustain the rejection of independent claim 1 under
35 U.S.C. § 103(a). Claims 2 and 3 depend from claim 1, and Appellant has
not presented any substantive arguments with respect to these claims.
Therefore, we sustain the rejection of claims 2 and 3 under 35 U.S.C.
§ 103(a), for the same reasons discussed with respect to independent
claim 1.
Independent claims 5 and 9 recite limitations similar to those
discussed with respect to independent claim 1, and Appellant has not
presented any additional substantive arguments with respect to these claims.
We sustain the rejection of claims 5 and 9, as well as claims 6 and 7, which
depend from claim 5, for the same reasons discussed with respect to claim 1.

Claims 11-14
We are not persuaded by Appellant’s arguments (Br. 30-31) that the
combination of Uematsu and Lele would not have rendered obvious
independent claim 11, which includes the fifth disputed limitation “second
program instructions to obtain an estimate of amounts of CPU utilization.”
Appeal 2009-014107
Application 11/016,101

10
The Examiner found that the processing capacity ratio management
table 3c of Uematsu also corresponds to the fifth disputed limitation.
(Ans. 11, 17; Uematsu, col. 4, ll. 56-63.) We agree with the Examiner.
As discussed previously, as illustrated in Figure 2B, processing
capacity ratios (i.e., the claimed “estimate of amounts of CPU utilization”)
are stored in a processing capacity ratio management table 3c. (Col. 2,
ll. 19-22.) Therefore, Uematsu teaches the limitation “second program
instructions to obtain an estimate of amounts of CPU utilization.”
Appellant argues that “LELE does not teach estimated amounts of
CPU utilization of an application” because “LELE determines an estimated
load value associated with an action.” (Br. 30.) However, the Examiner
relied on Uematsu, rather than Lele, for teaching the claim limitation
“second program instructions to obtain an estimate of amounts of CPU
utilization.” (Ans. 11.)
Thus, we agree with the Examiner that the combination Uematsu and
Lele would have rendered obvious independent claim 11, which includes the
limitation “second program instructions to obtain an estimate of amounts of
CPU utilization.”
We are also not persuaded by Appellant’s arguments (Br. 30-31) that
the combination of Uematsu and Lele would not have rendered obvious
independent claim 11, which includes the sixth disputed limitation “third
program instructions to combine together, for each of said plurality of
servers at each of said sample times, the amounts of utilization of their
respective CPUs and the estimated amounts of CPU utilization of said
application.”
Appeal 2009-014107
Application 11/016,101

11
The Examiner found that calculating the processing capacity ratio of
Uematsu also corresponds to the sixth disputed limitation. (Ans. 11, 18;
Uematsu, col. 5, l. 67 to col. 6, l. 4.) We agree with the Examiner.
As discussed previously, Figure 3 of Uematsu illustrates a process for
creating the processing capacity ratio management table (col. 5, ll. 40-41),
including calculating “a ratio relative to that of the reference computing
server which is represented by 1” (col. 5, l. 67 to col. 6, l. 2) and entering
“the processing capacity ratio of each computing server . . . into the
processing capacity ratio management table” (col. 6, ll. 2-4). Figures 6-8 of
Uematsu illustrate various tabular or graphical representations of CPU usage
status of three computing servers. (Col. 3, l. 58 to col. 4, l. 5). In other
words, by calculating and graphically representing the processing capacity
ratio, Uematsu teaches the limitation “third program instructions to combine
together, for each of said plurality of servers at each of said sample times,
the amounts of utilization of their respective CPUs and the estimated
amounts of CPU utilization of said application.”
Appellant argues that “LELE fails to teach combining together, for
each of said plurality of servers at each of said sample times, the amounts of
utilization of their respective CPUs and the estimated amounts of CPU
utilization of said application” because “LELE estimates the load on a
cluster and monitors the health of the resources on the cluster.” (Br. 31.)
However, the Examiner relied on Uematsu, rather than Lele, for teaching the
claim limitation “third program instructions to combine together, for each of
said plurality of servers at each of said sample times, the amounts of
utilization of their respective CPUs and the estimated amounts of CPU
utilization of said application.” (Ans. 11, 18.)
Appeal 2009-014107
Application 11/016,101

12
Thus, we agree with the Examiner that the combination Uematsu and
Lele would have rendered obvious independent claim 11, which includes the
limitation “third program instructions to combine together, for each of said
plurality of servers at each of said sample times, the amounts of utilization
of their respective CPUs and the estimated amounts of CPU utilization of
said application.”
Accordingly, we sustain the rejection of independent claim 11 under
35 U.S.C. § 103(a). Claim 12 depends from claim 11, and Appellant has not
presented any substantive arguments with respect to this claim. Therefore,
we sustain the rejection of claim 12 under 35 U.S.C. § 103(a), for the same
reasons discussed with respect to independent claim 11.
Independent claim 13 recites limitations similar to those discussed
with respect to independent claim 11, and Appellant has not presented any
additional substantive arguments with respect to this claim. We sustain the
rejection of claim 13, as well as claim 14, which depends from claim 13, for
the same reasons discussed with respect to claim 11.

Claims 4, 8, and 10
We are persuaded by Appellant’s arguments (Br. 34-35) that the
combination of Uematsu and Lele would not have rendered obvious
dependent claim 4, which includes the disputed limitation “sixth program
instructions to obtain information of a financial reason to install said
application on each of said one or more servers.”
The Examiner found that the Uematsu discloses the limitation “to
obtain information of a financial reason to install said application on each of
said one or more servers.” (Ans. 6, 19.) We do not agree.
Appeal 2009-014107
Application 11/016,101

13
Uematsu is expressly silent regarding any financial reasons related to
the processing capacity ratio. Furthermore, the Examiner has not provided
any citation to a column and line number in Uematsu that teaches the
limitation “sixth program instructions to obtain information of a financial
reason to install said application on each of said one or more servers.”
Thus, we do not agree with the Examiner that the combination
Uematsu and Lele would have rendered obvious dependent claim 4, which
includes the limitation “sixth program instructions to obtain information of a
financial reason to install said application on each of said one or more
servers.”
Accordingly, we do not sustain the rejection of dependent claim 4
under 35 U.S.C. § 103(a).
Dependent claims 8 and 10 recite limitations similar to those
discussed with respect to dependent claim 4. We do not sustain the rejection
of claims 8 and 10 for the same reasons discussed with respect to dependent
claim 4.

DECISION
The Examiner’s decision to reject claims 1-3, 5-7, 9, and 11-14 is
affirmed. However, the Examiner’s decision to reject claims 4, 8, and 10 is
reversed.

Appeal 2009-014107
Application 11/016,101

14
No time period for taking any subsequent action in connection with
this appeal may be extended under 37 C.F.R. § 1.136(a)(1)(iv).

AFFIRMED-IN-PART

rwk