Dinesh Garg et al.

Patent Trials and Appeals Board

Dec 20, 2019

13682415 - (D) (P.T.A.B. Dec. 20, 2019)

UNITED STATES PATENT AND TRADEMARK OFFICE
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
APPLICATION NO. FILING DATE FIRST NAMED INVENTOR ATTORNEY DOCKET NO. CONFIRMATION NO.
13/682,415 11/20/2012 Dinesh Garg IN920120121US1 2011
77351 7590 12/20/2019
IBM CORP. (AUS)
C/O THE LAW OFFICE OF JAMES BAUDINO, PLLC
2313 ROOSEVELT DRIVE
SUITE A
ARLINGTON, TX 76016
EXAMINER
PATEL, DHAIRYA A
ART UNIT PAPER NUMBER
2453
MAIL DATE DELIVERY MODE
12/20/2019 PAPER
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.
PTOL-90A (Rev. 04/07)

UNITED STATES PATENT AND TRADEMARK OFFICE

BEFORE THE PATENT TRIAL AND APPEAL BOARD

Ex parte DINESH GARG
and RAMASURI NARAYANAM

Appeal 2018–002290
Application 13/682,415
Technology Center 2400

Before JOYCE CRAIG, SCOTT. E. BAIN, and
MICHAEL T. CYGAN, Administrative Patent Judges.

CYGAN, Administrative Patent Judge.

DECISION ON APPEAL
STATEMENT OF THE CASE
Pursuant to 35 U.S.C. § 134(a), Appellant appeals from the
Examiner’s decision to reject claims 9, 11, 12, 14–17, 19, 20, and 22–26.1
Appeal Br. 17–22. We have jurisdiction under 35 U.S.C. § 6(b).
We AFFIRM IN PART.

1 We use the word “Appellant” to refer to “applicant” as defined in
37 C.F.R. § 1.42. Appellant identifies the real party in interest as
International Business Machines Corporation. Appeal Br. 2.
Appeal 2018–002290
Application 13/682,415

2
CLAIMED SUBJECT MATTER
The claims are directed to ranking one user’s connections in an
electronic social network. Abstr. An electronic apparatus may be used to
identify those connections, analyze data sources for electronic
communications with other users, and calculate the probability of future
communications with those users. Id. The probability calculations may be
used to rank the connections with other users, remove connections based
upon the rankings. Id. A diagnostic model of the social network may be
formed based upon the ranked connections with other users. Appeal Br. 2
(citing Spec. ¶¶ 82, 156). Independent claim 9 is illustrative, with the
limitation at issue italicized for emphasis:
1. A computer system, comprising:
a processor;
a memory; and
a program comprising a plurality of instructions stored in the
memory that are executed by the processor to:
identify one user's connections with other users in an electronic
social network;
create a data structure in the memory that represents the one
user, the other users, and the one user's connections with the
other users;
analyze a plurality of data sources for electronic
communications between the one user and the other users;
assign a relative importance value to each data source of the
plurality of data sources;
assign a weight to each connection between the one user and
the other users, the weight being an encoded value computed
based on a link structure of the connections, the link structure
including metadata indicating a category and a status of the
respective connections, the weight enabling an emulation and
Appeal 2018–002290
Application 13/682,415

3
behavioral prediction of the electronic social network in
response to a stimulus applied to the electronic social network;
calculate for each of the other users the probability that the one
user will communicate with that other user based on the
analyzed plurality of data sources and the weight values;
rank the one user's connections with the other users based on
the calculated probabilities;
remove from the data structure one or more data structure
elements of the one user's connections based on the ranked one
user's connections to create a signature graph; and
form a diagnostic model of the electronic social network, the
diagnostic model including the signature graph to accelerate a
processing speed of the diagnostic model on a social network
analysis system.
Appeal Br. 17–18 (Claims App.).
Independent claim 17 recites a computer program product having
limitations commensurate in scope with claim 1. Id. at 19–20. Dependent
claims 11, 12, 14–16, and 19–26 each incorporate the limitations of their
respective independent claims. Id. at 18–22. Claims 1–8, 10, and 13 have
been cancelled. Final Act. 2.
REFERENCES
Name Reference Date
Darr US 2007/0226248 A1 Sept. 27, 2007
Filed Feb. 12, 2007
Chakraborty et al.
(“Chakraborty”)
US 2009/0192809 A1 July 30, 2009
Filed Jan. 28, 2008
Carthcart et al.
(“Carthcart”)
US 2013/0212173 A1 Aug. 15, 2013
Filed Feb. 13, 2012

Appeal 2018–002290
Application 13/682,415

4
REJECTIONS
Claims 9, 11, 12, 17, 19, 20, 25, and 26 are rejected under 35 U.S.C.
§ 103(a) as being obvious over Carthcart and Chakraborty.
Claims 14–16, and 22–24 are rejected under 35 U.S.C. § 103(a) as
being obvious over Carthcart, Chakraborty, and Darr.
OPINION
A. Obviousness Over Carthcart and Chakraborty
The first issue in this appeal is the following limitation of claim 9:
assign a weight to each connection between the one user and
the other users, the weight being an encoded value computed
based on a link structure of the connections, the link structure
including metadata indicating a category and a status of the
respective connections[.]
With respect to this limitation, the Examiner finds Carthcart teaches
assigning a weight to each connection between one user and other users.
Final Act. 5. The Examiner explains that Carthcart teaches weighting user
connections using an affinity score as well as weighting individual users
based on a variety of features such as age, common friends, and how long a
user has been using a social network system. Id. at 5–6 (citing Carthcart
¶¶ 17–18). The Examiner states that Carthcart does not explicitly teach that
the assigned weight is an encoded value that is computed based on a link
structure of the connections, where the link structure includes metadata
indicating a category and a status of the respective connections; further, the
weight enabling an emulation and behavioral prediction of the electronic
network in response to a stimulus applied to the electronic social network.
Id. at 6–7.
Appeal 2018–002290
Application 13/682,415

5
The Examiner finds Chakraborty supplies the missing teachings. The
Examiner cites to Chakraborty’s teaching of “computing the weight for
connections, edges, between nodes using a CDR (Call Detail Record) that
records various data on different nodes and the connections . . . wherein the
CDR can include data describing the nodes and their connections [which is]
similar to the categories and status information described by the
[Appellant’s] Specification.” Id. at 7–8 (citing Chakraborty ¶¶ 21–22, 57,
and Fig. 7).
Appellant first contends that the Examiner errs in determining that the
applied combination teaches or suggests an encoded weight value based on
link structure metadata indicating a category and a status of a connection.
Appeal Br. 5. Appellant contends that the Examiner errs in relying on
Chakraborty to teach link structure metadata indicating a category or status
of a connection. Id. at 8–9. Specifically, Appellant argues that Figure 7
discloses call frequency and call duration features, as well as whether a call
was made to or from a churner or between adjacent churners. Id. at 9.
Appellant argues that call frequency and call duration are not the type of
category and status of a connection as claimed. Id. Appellant further argues
that none of the features of Figure 7, except for those also in paragraph 22,
are used to derive a weight value. Appellant points to Chakraborty’s
paragraph 29, which states that the weight of a directed edge is the aggregate
of all calls made by A to B. Id. at 4.
We turn to the Specification to understand the scope of the claimed
category and status of a connection. The Specification provides examples of
“status” of a connection that include “pending, accepted, avoided, or
rejected” calls. The Specification provides examples of a “category” of a
Appeal 2018–002290
Application 13/682,415

6
connection that include “user-to-user, business-to-user, system-to-user, and
system-to-business connections.” Spec. ¶ 66.
In view of the Specification, we agree with the Examiner that
Chakraborty teaches link structure metadata, which includes metadata
including a category of connections; i.e., the category of user-to-user
specified as user-to-churner neighbors. Final Act. 8; Ans. 2–4; Chakraborty
¶ 57, Fig. 7. We also agree that Chakraborty teaches that the metadata
includes a status of connections, in that the calls used in the measurement
calculations are “accepted” calls, i.e., those having a duration of 5 seconds
or longer. Chakraborty ¶ 29; Ans. 4.
We further agree that the weight is calculated for the call frequency
and volume, which may, as shown in the Call Detail Record to be indicative
of user-to-churner connections. Ans, 3 (citing Chakraborty ¶¶ 21, 22, 57,
Fig. 7). Although Appellant argues that Chakraborty’s weight calculation is
solely from call frequency and volume, the Examiner shows that
Chakraborty’s weight calculation is from call frequency and volume
indicating accepted calls (a status of the connection) and indicating user-to-
churner calls (a category of the connection). Appellant’s argument that
Chakraborty computes the weight as the aggregate of all calls made by A to
B; i.e., the call frequency or call volume, is not inconsistent with the
Examiner’s explanation that the Call Data Record includes metadata
indicating the user-to-churner category of the accepted calls. Accordingly,
we are not persuaded that the Examiner errs in determining that
Chakraborty, combined with Carthcart, teaches that the weight is computed
based on a linked structure of the connections, including metadata indicating
a category and status of the respective connections.
Appeal 2018–002290
Application 13/682,415

7
Next we consider whether the references disclose an emulation and
behavioral prediction of a social network in response to a stimulus applied
thereto. Appeal Br. 9. Appellant contends that the Examiner improperly
relies upon Chakraborty’s removal of links as corresponding to two separate
claim limitations; i.e., to “remove from the data structure one or more data
structure elements of the one user’s connection” and the “stimulus.” Id.
Appellant argues that the claim requires a signature graph to be created from
the removal of data structure elements, and that the signature graph then be
used to form a diagnostic model, upon which a stimulus may be applied to
provide an emulation and behavioral prediction of the network. Id.
Appellant contends that Chakraborty, while removing links, does not apply a
stimulus to the network after their removal. Id.
The claim requires that “the weight enabl[es] an emulation and
behavioral prediction of the electronic social network in response to a
stimulus applied to the electronic social network.” Appellant characterizes
Chakraborty as “the influence of a churner on another to churn appears to be
predicted based on the strength of ties between the users.” Reply Br. 8.
Thus, Appellant’s characterization itself admits that in Chakraborty, the
weight (strength of ties between the users) enables behavioral prediction (the
influence of a churner on another to churn). Although Appellant argues that
Chakraborty does not appear to apply a stimulus to the network after the
removal of links, the claim only requires that the weight “enables” such
prediction in response to an applied stimulus; it does not set forth a positive
recitation of a step of applying a stimulus. Appeal Br. 10. Thus, we are not
persuaded that the Examiner errs in assigning the same feature of
Chakraborty to the removal of links (claimed) and the application of a
Appeal 2018–002290
Application 13/682,415

8
stimulus to the network (unclaimed). Based on Appellant’s characterization,
we are not persuaded that the Examiner has not shown that Chakraborty
teaches that “the weight enabl[es] an emulation and behavioral prediction of
the electronic social network in response to a stimulus applied to the
electronic social network.”
Appellant next contends that the Examiner’s rationale for combining
the teachings and suggestions of Chakraborty with those of Carthcart is
erroneous. Appellant characterizes the Examiner’s rationale as being based
on the advantages of removing and adding links, and using weights assigned
to links to simulate user behavior, stated to provide a more robust and
automatic method. Appeal Br. 11 (citing Final Act. 8–9). Appellant argues
that the primary reference (Carthcart) already contains these features, so that
there would be no purpose in adding the same features from Chakraborty.
Id.
We are not persuaded by Appellant that the Examiner errs, because
the Examiner provides a rationale for combining the references beyond that
cited by Appellant. The test for obviousness is “what the combined
teachings of the references would have suggested to those of ordinary skill
in the art.” In re Keller, 642 F.2d 413, 425 (CCPA 1981). With respect to
the rationale for combining the teachings or suggestions of Carthcart and
Chakraborty, the Examiner has stated, “[o]ne ordinary skill in the art would
have been motivated to combine the teachings in order to create a more
robust and automatic method for enabling users to computationally analyze
social network to determine/detect context based patterns within social
interaction data.” Final Act. 9.
Appeal 2018–002290
Application 13/682,415

9
Although some features relied upon in the teachings of Chakraborty
are of the same general nature (e.g., use of weights to simulate user
behavior), the Examiner has relied upon different specific teachings not
found in Carthcart; e.g., in the specific types of user behavior being
weighted, so as to determine and detect context based patterns within social
interaction data. Ans. 13. Moreover, we are not persuaded that combining
the respective familiar elements of the cited references in the manner
proffered by the Examiner would have been “uniquely challenging or
difficult for one of ordinary skill in the art” at the time of Appellant’s
invention. Leapfrog Enters., Inc. v. Fisher-Price, Inc., 485 F.3d 1157, 1162
(Fed. Cir. 2007) (citing KSR, 550 U.S. at 418); See also KSR Int’l Co. v.
Teleflex Inc., 550 U.S. 398, 417 (Fed. Cir. 2007) (“[I]f a technique has been
used to improve one device, and a person of ordinary skill in the art would
recognize that it would improve similar devices in the same way, using the
technique is obvious unless its actual application is beyond his or her skill”).
Accordingly, because the Examiner provides a reasoned rationale
comprising a motivation to combine the specific teachings of Carthcart and
Chakraborty, we are not persuaded that the Examiner errs by providing an
insufficient rationale to combine the references.
Accordingly, we are not persuaded of error in the Examiner’s
rejection of claim 9. Appellant states that independent claim 17, and
dependent claims 11, 12, 17, 19, 20, 25, and 26, which are rejected under the
same combination of references, are patentable for the same reasons as set
forth with respect to the rejection of claim 9. Appeal Br. 11–12. For the
same reasons as discussed with respect to claim 9, we sustain the
Appeal 2018–002290
Application 13/682,415

10
obviousness rejection of claims 11, 12, 17, 19, 20, 25, and 26. See 37 C.F.R.
§ 41.67(c)(iv).
B. Obviousness over Carthcart, Chakraborty, and Darr
Appellant argues that dependent claims 14–16 and 22–24 are
patentable because of the alleged defects in the rejection of claim 9, and
further because those defects are not cured by teachings of Darr. Appeal Br.
12–14.
With respect to claims 14 and 22–24, we are not persuaded by
Appellant’s arguments. As discussed, supra, we have determined that the
Examiner does not err in rejecting claim 9, and independent claim 17 not
separately argued. Consequently, we are not persuaded that the Examiner
errs in relying on the same base combination of references for the same
limitations in their respective dependent claims. Furthermore, Appellant
merely alleges, without explanation, that the additional limitations of the
dependent claims are not taught by the applied combination of references.
Id. However, merely pointing out what a claim recites will not be
considered an argument for separate patentability of the claim. 37 C.F.R.
§ 41.37(c)(1)(iv). As stated by the Federal Circuit, Rule 41.37 “require[s]
more substantive arguments in an appeal brief than a mere recitation of the
claim elements and a naked assertion that the corresponding elements were
not found in the prior art.” In re Lovin, 652 F.3d 1349, 1357 (Fed. Cir.
2011). Appellant’s arguments are, therefore, not persuasive to show error in
the Examiner’s rejection of claims 14–16 and 22–24, and we sustain the
obviousness rejection of those claims.
With respect to claims 15 and 16, Appellant further argues that
dependent claim 15 is patentable for the further reason that the combination
Appeal 2018–002290
Application 13/682,415

11
of references, and particularly Darr, does not disclose assigning an
“importance level” to data sources for electronic communications between
users as recited in claim 9. Appeal Br. 13–14. The Examiner points to
Darr’s “marking interaction patterns of a real world social network as
important when a score of a data pattern is above a certain threshold” as
teaching or suggesting the claimed “assign[ing] a relative importance [level]
to each data source of the plurality of data sources.” Final Act. 13–14;
Appeal Br. 17 (Claims App.). The Examiner does not explain how marking
the patterns of the network corresponds with assigning an importance level
to each data source. Accordingly, we are persuaded by Appellant that the
Examiner errs in rejecting claim 15, and claim 16 depending therefrom. We,
therefore, reverse the Examiner’s rejection of claims 15 and 16.

CONCLUSION
For the above-described reasons, we affirm the Examiner’s rejection
of claims 9, 11, 12, 14, 17, 19, 20, and 22–26, and reverse the Examiner’s
rejection of claims 15 and 16, as being obvious under 35 U.S.C. § 103(a).

DECISION SUMMARY
In summary:
Claims
Rejected
35 U.S.C. § References/Grounds Affirmed Reversed
9, 11, 12,
17, 19,
20, 25, 26
103(a) Carthcart,
Chakraborty
9, 11, 12,
17, 19, 20,
25, 26

14–16,
22–24
103(a) Carthcart,
Chakraborty, Darr
14, 22–24 15, 16
Overall 9, 11, 12, 15, 16
Appeal 2018–002290
Application 13/682,415

12
Outcome 14, 17, 19,
20, 22–26

AFFIRMED IN PART