Global Analytics, Inc.

Patent Trials and Appeals Board

Aug 23, 2021

2020002376 (P.T.A.B. Aug. 23, 2021)

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.
14/549,505 11/20/2014 Krishna Gopinathan 372566-991121 2764
26379 7590 08/23/2021
DLA PIPER LLP (US )
2000 UNIVERSITY AVENUE
EAST PALO ALTO, CA 94303-2248
EXAMINER
LERNER, MARTIN
ART UNIT PAPER NUMBER
2657
NOTIFICATION DATE DELIVERY MODE
08/23/2021 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):
PatentDocketingUS-PaloAlto@dlapiper.com
PTOL-90A (Rev. 04/07)
UNITED STATES PATENT AND TRADEMARK OFFICE
____________

BEFORE THE PATENT TRIAL AND APPEAL BOARD
____________

Ex parte KRISHNA GOPINATHAN, JAGAT CHAITANYA, SUDALAI
RAJ KUMAR, and SRIRAM RANGARAJAN
___________

Appeal 2020-002376
Application 14/549,505
Technology Center 2600
____________

Before ERIC B. CHEN, MIRIAM L. QUINN, and ADAM J. PYONIN,
Administrative Patent Judges.

CHEN, Administrative Patent Judge.

DECISION ON APPEAL

Appeal 2020-002376
Application 14/549,505

2
STATEMENT OF THE CASE
Pursuant to 35 U.S.C. § 134(a), Appellant1 appeals from the
Examiner’s decision to reject claims 1, 2, 4–9, 11–25, 27–32, and 34–46.
Claims 3, 10, 26, and 33 have been cancelled. We have jurisdiction under
35 U.S.C. § 6(b).
We AFFIRM.

CLAIMED SUBJECT MATTER
The claims are directed to credit risk decision management using
voice analytics. (Abstract.)
Claim 1, reproduced below, is illustrative of the claimed subject
matter, with disputed limitations in italics:
1. A voice analytic based predictive modeling
system, comprising:
a processor and a memory;
the processor configured to receive information from an
entity and third party information about the entity;
the processor configured to receive voice recordings from
a telephone call with the entity, the telephone call with the
entity including a call center agent voice and an entity voice;
a voice analyzer component, executed by the processor,
that removes the call center agent voice from the voice
recording to isolate the entity voice, separates the entity voice
recording into one or more voice recording segments, processes
the entity voice in the one or more voice recording segments to
identify a plurality of features of the entity voice from the voice

1 We use the word “Appellant” to refer to “applicant” as defined in
37 C.F.R. § 1.42(a). Appellant identifies the real party in interest as Gain
Credit Holdings, Inc. (Appeal Br. 1.)
Appeal 2020-002376
Application 14/549,505

3
recordings and generate a plurality of voice feature pieces of
data; and
a predictor component, executed by the processor, that
generates a credit risk assessment for the entity based on the
voice features piece of data for the entity, the information from
the entity and third party information about the entity.

REFERENCES
Name Reference Date
McIntosh et al. US 8,095,369 B1 Jan. 10, 2012
Wasserblat et al. US 2006/0285665 A1 Dec. 21, 2006
Lee et al. US 2007/0016419 A1 Jan. 18, 2007
Gutierrez et al. US 2010/0305960 A1 Dec. 2, 2010
Bezar US 2012/0262296 A1 Oct. 18, 2012
Neuhauser et al. US 2014/0180675 A1 June 26, 2014

REJECTIONS
Claims 1, 12–15, 20, 23, 24, 35–38, 43, and 46 stand rejected under
35 U.S.C. § 103 as being unpatentable over Wasserblat and McIntosh.
Claims 2, 22, 25, and 45 stand rejected under 35 U.S.C. § 103 as
being unpatentable over Wasserblat, McIntosh, and Gutierrez.
Claims 4–9, 11, 27–32, and 34 stand rejected under 35 U.S.C. § 103
as being unpatentable over Wasserblat, McIntosh, and Lee.
Claims 16, 17, 19, 21, 39, 40, 42, and 44 stand rejected under 35
U.S.C. § 103 as being unpatentable over Wasserblat, McIntosh, and Bezar.
Claims 16–18 and 39–41 stand rejected under 35 U.S.C. § 103 as
being unpatentable over Wasserblat, McIntosh, and Neuhauser.2

2 Appellant does not present any arguments with respect to the rejection of
dependent claims 2, 4–9, 11, 16–19, 21, 22, 25, 27–32, 34, 39–42, 44, and
Appeal 2020-002376
Application 14/549,505

4
OPINION
We are unpersuaded by Appellant’s arguments (Appeal Br. 5) that the
combination of Wasserblat and McIntosh would not have rendered obvious
independent claim 1, which includes the limitation “a predictor component,
executed by the processor, that generates a credit risk assessment for the
entity based on the voice features piece of data for the entity, the information
from the entity and third party information about the entity.”
The Examiner found that fraud detection system 40 of Wasserblat,
which assigns a fraud probability based upon credit history, voice prints, and
other data, corresponds to the limitation “a predictor component, executed
by the processor, that generates a credit risk assessment for the entity based
on the voice features piece of data for the entity, the information from the
entity and third party information about the entity.” (Final Act. 5–6; see also
Ans. 19–24.) We agree with the Examiner’s findings.
Wasserblat relates to voice analysis for fraud detection. (¶ 2.)
Figure 1 of Wasserblat illustrates a block diagram of the environment for
Wasserblat’s system, which includes “site 1” 10 to “site N” 11 (e.g., bank or
credit card operator) and fraud detection system 40. (¶ 19.) Wasserblat
explains that fraud detection system 40 includes “fraud detection component
44 that checks each interaction transferred by any of selection systems 36
and issues a combined fraud probability for the interaction, taking into
account the results generated by fraud detection component 44 and the fraud
probability as assigned by selection system 36.” (Id.) Additionally,
Wasserblat explains that “[f]raud detection component 44 . . . comprises a

45 under 35 U.S.C. § 103. (Appeal Br. 6.) Thus, any such arguments are
deemed to be waived.
Appeal 2020-002376
Application 14/549,505

5
threshold determination component 46 for controlling the tradeoff between
false alarms and miss[ed] detect[ion] in the system,” and that such threshold
can be based upon account holder credit history. (Id.) Moreover,
Wasserblat explains that “[i]f the total fraud or fraud attempt probability
exceeds a threshold, a notification is issued.” (Abstract.)
In another embodiment, Figure 3 of Wasserblat illustrates fraud
detection component 140, including selection component 147, weighting
component 151, and voice print collection 152. (¶ 21.) Wasserblat explains
that “[s]election component 147 preferably searches for an earlier voice
recording or a previously constructed voice print of the same alleged
customer” from voice print collection 152 and “[w]eighting component 151
outputs an overall risk level, or combined probability to being a fraud.” (Id.)
Moreover, Wasserblat explains that “[t]he voice prints in the selection
against which the voice is scored are preferably filtered according to data
associated with the interaction, such as area code of calling number, gender,
age, language or the like.” (¶ 20.)
Because Wasserblat explains that fraud detection system 40 uses
weighting component 151 to output an overall risk level for fraud, and also
accesses voice print collection 152, which includes data associated with the
interaction (e.g., area code of calling number, gender, age, or language),
Wasserblat teaches the limitation “a predictor component, executed by the
processor, that generates a credit risk assessment for the entity based on the
voice features piece of data for the entity, the information from the entity
and third party information about the entity.”
Appellant argues that “Wasserblat uses that threshold (based in part
on the credit history or account holder service level) to filter out interactions
Appeal 2020-002376
Application 14/549,505

6
whose probabilities are less than the threshold” and “[a]s a result, in
Wasserblat, not every voice interaction (due to the filtering by the threshold)
is used to generate an outcome of an event for the entity.” (Appeal Br. 5.)
While Wasserblat explains that threshold determination component 46
controls “the tradeoff between false alarms and miss[ed] detect[ion] in the
system” (¶ 19), Wasserblat also explains that such threshold is used to issue
a notification (Abstract). Thus, because fraud detection component 44
outputs a combined fraud probability for the interaction, and such threshold
is used to issue notifications, Appellant’s argument that “not every voice
interaction (due to the filtering by the threshold) is used to generate an
outcome of an event for the entity” is unsupported by Wasserblat.
Appellant further argues that “this claim element requires that the
‘third party information about the entity’ is used to generate the outcome of
the event for the entity that does not occur in Wasserblat.” (Appeal Br. 5.)
However, the Examiner also cited to the data associated with the voice prints
of Wasserblat, for example, “area code of calling number[s], gender, age,
language or the like,” for teaching the limitation “the information from the
entity and third party information about the entity.” (Ans. 22.) Appellant
has not provided any persuasive arguments or evidence as to why the
Examiner’s findings with respect to Wasserblat are in error.
Thus, we agree with the Examiner that the combination of Wasserblat
and McIntosh would have rendered obvious independent claim 1, which
includes the limitation “a predictor component, executed by the processor,
that generates a credit risk assessment for the entity based on the voice
features piece of data for the entity, the information from the entity and third
party information about the entity.”
Appeal 2020-002376
Application 14/549,505

7
Accordingly, we sustain the rejection of independent claim 1 under 35
U.S.C. § 103. Claims 12–15, 20, and 23 depend from claim 1, and
Appellant has not presented any additional substantive arguments with
respect to these claims. Therefore, we sustain the rejection of claims 12–15,
20, and 23 under 35 U.S.C. § 103 for the same reasons discussed with
respect to independent claim 1.
Independent claim 24 recites 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 claim 24, as well as dependent claims 35–38, 43, and 46 for
the same reasons discussed with respect to claim 1.

CONCLUSION
We affirm the Examiner’s decision rejecting claims 1, 2, 4–9, 11–25,
27–32, and 34–46 under 35 U.S.C. § 103.

DECISION
In summary:
Claims
Rejected
35 U.S.C. § Reference(s)/Basis Affirmed Reversed
1, 12–15,
20, 23, 24,
35–38, 43,
46
103 Wasserblat,
McIntosh
1, 12–15,
20, 23, 24,
35–38, 43,
46

2, 22, 25,
45
103 Wasserblat,
McIntosh,
Gutierrez
2, 22, 25,
45

4–9, 11,
27–32, 34
103 Wasserblat,
McIntosh, Lee
4–9, 11,
27–32, 34

Appeal 2020-002376
Application 14/549,505

8
16, 17, 19,
21, 39, 40,
42, 44
103 Wasserblat,
McIntosh, Bezar
16, 17, 19,
21, 39, 40,
42, 44

16–18, 39–
41
103 Wasserblat,
McIntosh,
Neuhauser
16–18, 39–
41

Overall
Outcome
1, 2, 4–9,
11–25, 27–
32, 34–46

TIME PERIOD FOR RESPONSE
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