Ex Parte Agapi et al

Patent Trial and Appeal Board

Sep 9, 2013

11291064 (P.T.A.B. Sep. 9, 2013)

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.
11/291,064 11/30/2005 Ciprian Agapi BOC920050073US1 (068) 9476
46322 7590 09/09/2013
CAREY, RODRIGUEZ, GREENBERG & O''''KEEFE, LLP
STEVEN M. GREENBERG
7900 Glades Road
SUITE 520
BOCA RATON, FL 33487
EXAMINER
NGUYEN, PHUNG HOANG JOSEPH
ART UNIT PAPER NUMBER
2656
MAIL DATE DELIVERY MODE
09/09/2013 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 CIPRIAN AGAPI, BAIJU D. MANDALIA,
and PRADEEP P. MANSEY
__________

Appeal 2011-008444
Application 11/291,064
Technology Center 2600
__________

Before ERIC GRIMES, JEFFREY N. FREDMAN, and
ERICA A. FRANKLIN, Administrative Patent Judges.

FREDMAN, Administrative Patent Judge.

DECISION ON APPEAL
This is an appeal1 under 35 U.S.C. § 134 involving claims to a method
for assessing the quality of a call recipient response during an interactive
voice dialog. The Examiner rejected the claims as obvious. We have
jurisdiction under 35 U.S.C. § 6(b). We reverse.

1 Appellants identify the Real Party in Interest as International
Business Machines Corporation (see App. Br. 2).
Appeal 2011-008444
Application 11/291,064

2
Statement of the Case
“The present invention relates . . . to a system and method that
analyzes call center agent biometric patterns in order to detect and prevent
potential problems thus assuring improved customer call handling and
satisfaction” (Spec. 1 ¶ 0001).
The Claims
Claims 1, 2, 4-11, 13-20, and 22-26 are on appeal. Claim 1 is
representative and reads as follows:
1. A method for assessing the quality of a call recipient
response during an interactive voice dialog, the method
comprising:
establishing a call between a caller and a call
recipient, the call creating the interactive call dialog;
analyzing in a biometric quality assurance system
(BQAS) executing in a computer with at least one processor
and memory, call recipient behavioral characteristics during
the call dialog, wherein the call recipient behavioral
characteristics include facial expressions;
comparing in the BQAS the call recipient's behavioral
characteristics to a set of pre-defined behavioral rules; and
determining by the BQAS if a behavioral pattern
exists based upon the comparison of the call recipient's
behavioral characteristics to the set of predefined behavioral
rules.

The issues
A. The Examiner rejected claims 1, 2, 10, 11, 19, and 20 under 35 U.S.C.
§ 103(a) as obvious over Hackbarth Jr.2 and Conway3 (Ans. 3-5).

2 Hackbarth, Jr. et al., US 2006/0271418 A1, published Nov. 30,
2006.
3 Conway et al., US 2006/0262920 A1, published Nov. 23, 2006.
Appeal 2011-008444
Application 11/291,064

3
B. The Examiner rejected claims 4, 13, and 22 under 35 U.S.C. § 103(a)
as obvious over Hackbarth Jr., Conway, Kirsch,4 and Hristova5 (Ans. 6-7).
C. The Examiner rejected claims 5-9, 14-18, and 23-26 under 35 U.S.C.
§ 103(a) as obvious over Hackbarth Jr., Conway, and Kreiner6 (Ans. 7-9).
A. 35 U.S.C. § 103(a) over Hackbarth, Jr. and Conway
The Examiner finds that “Hackbarth, via Abstract and Fig. 2, teaches
a method, a computer program product and a system for assessing the
quality of a call recipient response during an interactive voice dialog” (Ans.
3). The Examiner finds that “Hackbarth does not teach the call recipient
behavioral characteristics include facial expressions.” (Ans. 5). The
Examiner finds that “Conway teaches the call recipient behavioral
characteristics include facial expressions” (Ans. 5).
The Examiner finds it obvious to “incorporate the teaching of Conway
into the teaching of Hackbarth for the purpose of applying a[ ] psychological
behavioral model in the call contact environment for a satisfactory business
transaction” (Ans. 5).
The issue with respect to this rejection is: Does the evidence of record
support the Examiner’s conclusion that Hackbarth, Jr. and Conway teach a
method which includes analyzing “call recipient behavioral characteristics
including facial expressions” as required by claim 1?

4 Kirsch, D., The Sentic Mouse: Developing a tool for Measuring
Emotional Valence, http://vismod.media.mit.edu/tech-reports/TR-
495/index.htm (May 1997).
5 Hristova et al., Ad-me: Wireless Advertising Adapted to the User
Location, Device and Emotions, Proc. 37th Hawaii Int’l Conf.
Systems Sci. 1-10 (2004).
6 Kreiner et al., US 2005/0100158 A1, published May 12, 2005.
Appeal 2011-008444
Application 11/291,064

4
Findings of Fact
1. The Specification teaches “[f]acial or body expressions might
indicate growing frustration on the part of the call agent while conversing
with an unruly customer, ultimately leading to argumentative or
unprofessional responses to the customer. By monitoring these biometric
characteristics as they occur, corrective action can be taken and quality
assurance maintained.” (Spec. 2 ¶ 0005).
2. The Specification teaches that “BQAS 170 may include video
cameras that take video images of call agent 140 during the interactive call
dialog. The captured images may then be compared to defined rules in
database 180, and an analysis is performed to determine whether the call
agent’s facial or body characteristics during the interactive voice dialog with
the caller represents a particular behavioral pattern” (Spec. 7 ¶ 0018).
3. Hackbarth, Jr. teaches that
beneficial behaviors are tracked, identified, and/or analyzed
by the module 232, by contact type and/or distribution
method. Exemplary beneficial behaviors include contacts,
one-and-done, alerts, initiates, previews, wrap-ups, hold
times having a duration within a specified time range (e.g.,
having a duration greater than a first selected threshold and
less than a second selected threshold), and less than a
selected threshold number of problem behaviors.

(Hackbarth, Jr. 5 ¶ 0082).
4. Hackbarth, Jr. teaches that the “threshold filter 320 determines
whether or not a possible target behavior instance has a requisite level of
significance warranting further investigation and determination by the target
behavior monitor 328” (Hackbarth, Jr. 6 ¶ 0090).
Appeal 2011-008444
Application 11/291,064

5
5. Hackbarth, Jr. teaches that the “the dimensional measure
filtering agent 312 applies the rules or performs comparison matching
against target behavior templates” (Hackbarth, Jr. 6 ¶ 0097).
6. Conway teaches “the psychological behavioral model used to
analyze the voice data is the Process Communication Model® (‘PCM’)
developed by Dr. Taibi Kahler. PCM is a psychological behavioral analytic
tool which presupposes that all people fall primarily into one of six basic
personality types” (Conway 11 ¶ 0105).
7. Conway teaches that the personality types’ “behavioral
characteristics may be categorized by words, tones, gestures, postures and
facial expressions, can be observed objectively with significantly high
interjudge reliability. (Conway 11 ¶ 0106).
8. Conway teaches that the “present invention mines significant
words within one or both of the separated first and second constituent voice
data, and applies PCM to the identified words” (Conway 11 ¶ 0107).
9 Conway teaches that in “addition to the behavioral assessment
of voice data, the method of the present invention may also employ distress
analysis to voice data” (Conway 12 ¶ 0112).
10. Conway teaches that “[e]ither contemporaneously with the
interaction, or after the call interaction has concluded, the recorded voice
data will be analyzed as described herein” (Conway 13 ¶ 0120).
Principles of Law
“In proceedings before the Patent and Trademark Office, the
Examiner bears the burden of establishing a prima facie case of obviousness
based upon the prior art.” In re Fritch, 972 F.2d 1260, 1265 (Fed. Cir. 1992).
Appeal 2011-008444
Application 11/291,064

6
“‘[R]ejections on obviousness grounds cannot be sustained by mere
conclusory statements; instead, there must be some articulated reasoning
with some rational underpinning to support the legal conclusion of
obviousness.”’ KSR Int’l Co. v. Teleflex Inc., 550 U.S. 398, 418 (2007)
citing In re Kahn, 441 F.3d 977, 988 (Fed. Cir. 2006).
Analysis
The Examiner finds that Hackbarth, Jr. teaches assessing the quality
of a call center agent responding to a caller by using a computer to analyze
call agent behaviors (FF 3), comparing those behaviors to pre-defined rules
(FF 5), and determining “whether or not a possible target behavior instance
has a requisite level of significance warranting further investigation and
determination by the target behavior monitor 328” (Hackbarth, Jr. 6 ¶ 0090;
FF 4).
The Examiner relies upon Conway for the requirement to analyze
facial expressions (FF 7; Ans. 5). The Examiner finds that in addition to
combining known elements to yield predictable results (Ans. 5, 9), the
combination of Hackbarth, Jr. and Conway “falls well within the range of an
ordinary knowledge that is already available to an ordinary artisan. Facial
expression is an integral part of the analysis where it goes hand in hand with
vocal emotion/energy” (Ans. 13).
We are not persuaded that the ordinary artisan, provided with the
teaching of Conway that the Process Communication Model associates a
variety of behavioral characteristics with personality types, and that these
behavioral characteristics include “words, tones, gestures, postures, and
facial expressions” (Conway 11 ¶ 0106; FF 7) would have had any reason to
Appeal 2011-008444
Application 11/291,064

7
select facial expression as a quality measure of call center agents in the
method disclosed by Hackbarth Jr. That is, Conway is entirely focused on
voice and word analysis (FF 8-10), and does not provide any reason,
whether in Conway or in the Examiner’s analysis, to incorporate “facial
expression” analysis into the call center agent behavior analysis method of
Hackbarth, Jr.
We disagree with the Examiner’s finding that “Conway’s presentation
of PCM is quite adequate proof to support facial muscle/expression of a
behavior” (Ans. 14). Conway may be sufficient to demonstrate that facial
expressions are one of the types of behavior which may be analyzed to
determine behavioral types (FF 7), but Conway’s mere passing mention of
facial expressions as a way to categorize behavioral characteristics of six
personality types does not provide a reason to use these facial expressions in
assessing a call center agent’s behavior.
The Examiner cites no art which demonstrates a nexus linking facial
expression of a call center agent with the quality of the agent’s response, nor
is there any art cited showing that “facial expression” is a generally known
or widely used method associated with phone agent quality or behavior.
Indeed, while common sense might dictate that the “facial expression” of an
agent with whom a customer comes into personal contact may impact the
quality of that interaction, ordinary experience can result in an entirely
different conclusion in the context of a telephone conversation, where a
person’s voice behavior may differ from their facial expression.
Appeal 2011-008444
Application 11/291,064

8
Conclusion of Law
The evidence of record does not support the Examiner’s conclusion
that Hackbarth, Jr. and Conway teach a method which includes analyzing
“call recipient behavioral characteristics including facial expressions” as
required by claim 1.
B. and C. 35 U.S.C. § 103(a)
Each of these rejections relies upon the underlying obviousness
rejection over Hackbarth, Jr. and Conway. Having reversed the rejection
over Hackbarth, Jr. and Conway for the reasons given above, we will also
reverse these dependent obviousness rejections, since none of the additional
references are cited to teach analysis using facial expression as required by
claims 1, 10, and 19, and the Examiner has not shown that Kirsch, Hristova,
or Kreiner suggest this limitation.
SUMMARY
In summary, we reverse the rejection of claims 1, 2, 10, 11, 19, and 20
under 35 U.S.C. § 103(a) as obvious over Hackbarth Jr. and Conway.
We reverse the rejection of claims 4, 13, and 22 under 35 U.S.C. §
103(a) as obvious over Hackbarth Jr., Conway, Kirsch, and Hristova.
We reverse the rejection of claims 5-9, 14-18, and 23-26 under 35
U.S.C. § 103(a) as obvious over Hackbarth Jr., Conway, and Kreiner.

REVERSED
lp