U.S. patent number RE41,608 [Application Number 11/509,551] was granted by the patent office on 2010-08-31 for system and method to acquire audio data packets for recording and analysis.
This patent grant is currently assigned to Verint Americas Inc.. Invention is credited to Christopher Douglas Blair, Roger Louis Keenan.
United States Patent |
RE41,608 |
Blair , et al. |
August 31, 2010 |
System and method to acquire audio data packets for recording and
analysis
Abstract
A signal monitoring apparatus and method involving devices for
monitoring signals representing communications traffic, devices for
identifying at least one predetermined parameter by analyzing the
context of the at least one monitoring signal, a device for
recording the occurrence of the identified parameter, a device for
identifying the traffic stream associated with the identified
parameter, a device for analyzing the recorded data relating to the
occurrence, and a device, responsive to the analysis of the
recorded data, for controlling the handling of communications
traffic within the apparatus.
Inventors: |
Blair; Christopher Douglas
(South Chailey, GB), Keenan; Roger Louis (London,
GB) |
Assignee: |
Verint Americas Inc. (Melville,
NY)
|
Family
ID: |
10800525 |
Appl.
No.: |
11/509,551 |
Filed: |
August 24, 2006 |
Related U.S. Patent Documents
|
|
|
|
|
|
|
Application
Number |
Filing Date |
Patent Number |
Issue Date |
|
|
11477124 |
Jun 28, 2006 |
|
|
|
|
09500800 |
Feb 10, 2000 |
6404857 |
|
|
|
08936428 |
Sep 24, 1997 |
|
|
|
Reissue of: |
10073966 |
Feb 14, 2002 |
06757361 |
Jun 29, 2004 |
|
|
Foreign Application Priority Data
|
|
|
|
|
Sep 26, 1996 [GB] |
|
|
9620082 |
|
Current U.S.
Class: |
379/67.1;
704/275 |
Current CPC
Class: |
G10L
17/00 (20130101); H04M 3/5175 (20130101); G10L
15/26 (20130101); G10L 17/26 (20130101); H04M
3/42323 (20130101); H04M 3/2272 (20130101); H04M
3/42221 (20130101); H04M 2201/40 (20130101) |
Current International
Class: |
H04M
1/64 (20060101) |
Field of
Search: |
;371/40.1 ;379/67.1,188
;704/275 ;709/213,216,240 ;380/239 ;370/248,352,60.1 ;714/769
;455/422 |
References Cited
[Referenced By]
U.S. Patent Documents
Foreign Patent Documents
|
|
|
|
|
|
|
0 510 412 |
|
Oct 1992 |
|
EP |
|
2 257 872 |
|
Jan 1993 |
|
GB |
|
Other References
Cohen, D. "A Voice Message System", Proceedings of the IFIP TC-6
International Symposium on Computer Message Systems, Computer
Message Systems, edited by Ronald P. Uhlig, Bell Northern Research
Limited, Ottawa, Canada, Apr. 6-8, 1981, pp. 17-28. cited by other
.
Cohen, D. "On Packet Speech Communication", Proceedings of the
Fifth International Conference, Computer Communications: Increasing
Benefits to Society, The International Council for Computer
Communication, Hosted by American Telephone and Telegraph Company.,
Atlanta, Georgia, Oct. 27-30, 1980, pp. 269-274. cited by other
.
Cohen, Danny, "Packet communication of online speech", USCI
Information Sciences Institute, Marina del Rey, CA, National
Computer Conference, 1981, pp. 169-176. cited by other .
Cohen, Danny, NWG/RFC 741, "Specification for the Network Voice
Protocol (NVP)", ISI, DC, Nov. 22, 1977, 40 pages. cited by other
.
Holfelder, Wieland, Tenet Group, International Computer Science
Institute and University of California, "VCR(1), MBone VCR--Mbone
Video Conference Recorder", Berkley, CA., Nov. 5, 1995, pp. 1-8.
cited by other .
Information Sciences Institute, University of Southern California,
Marina del Rey, "RFC:791 Internet Protocal DARPA Internet Program
Protocol Specification", Prepared for Defense Advanced Research
Projects Agency Information Processing Techniques Office,
Arlington, VA., Sep. 1981, pp. 1-45. cited by other .
Schulzrinne, Henning, "NeVoTImplementation and Program Structure",
GMD Fokus, Berlin, Feb. 9, 1996, pp. 1-16. cited by other .
Schulzrinne, Henning, "Voice Communication Across the Internet: A
Network Voice Terminal", Dept. of Electrical and Computer
Engineering, Dept. of Computer Science, Univ. of Massachusetts,
Amherst, MA. Jul. 29, 1992, pp. 1-34. cited by other .
Terry, Douglas B. and Daniel C. Swinehart, "Managing Stored Voice
in the Etherphone System", Computer Science Laboratory, Xerox Palo
Alto Research Center, 1987, pp. 103-104. cited by other .
Zellweger, Polle T., Douglas B. Terry, and Daniel C. Swinehart, "An
Overview of the Etherphone System and Its Applications", Xerox Palo
Alto Research Center, Palo Alto, CA., 1988, pp. 160-168. cited by
other .
Lieberman et al., "Some Aspects of Fundamental Frequency and
Envelope Amplitude as Related to the Emotional Content of Speech",
The Journal of the Acoustical Society of America, vol. 34,
previously presented, 922-927 (Jul. 1962). cited by other .
So-Lin Yen et al. "Intelligent MTS Monitoring System", Oct. 1994,
pp. 185-187, Scientific and Research Center for Criminal
Investigation, Taiwan, Republic of China. cited by other .
Network Resource Group of Lawrence Berkeley National Laboratory,
vat-LBNL Audio Conference Tool, at
web.archive.org/web/19980126183021/www-nrg.ee.lbl.gov/vat (Jan. 26,
1998), 5 pp. cited by other .
Mash Research Team, vic-video conference, at
b.archive.org/web/19980209092254/mash.cs.berkeley.edu/mash (Feb. 9,
1998), 11 pp. cited by other .
Mash Research Team, Player, at
web.archive.org/web/19980209092521/mash.cs.berkely.edu/mash (Feb.
9, 1998), 3 pp. cited by other .
Intel Corporation, Intel Internet Video Phone Trial Applet 2.1: The
Problems and Pitfalls of Getting H.323 Safety Through Firewalls, at
web.archive.org/web/19980425132417/http://support.intel.com/support/video-
phone/trial21/h323_wpr.htm.TM.a18 (Apr. 24, 1998), 32 pp. cited by
other .
Posting of Brett Eldridge to muc.lists.firewalls: MS NetMeeting 2.0
and Raptor Eagle vers. 4.0, at
groups-beta.google.com/groups/muc.lists.firewalls/browse_thread/thread/ec-
0255b64bf36ad4?tvc=2 (May 2, 1997), 3 pp. cited by other .
Press Release, RADCOM, Breakthrough Internetworking Application for
Latency & Loss Measurements from RADCOM, at
http://web.archive.org/web/19980527022443/www.radcom-inc.com/press21.htm
(May 27, 1998), 2 pp. cited by other .
RADCOM, Supported Protocols, at
http://web.archive.org/web/19980527014033/www.radcom-inc.com/protocol.htm
(May 27, 1998), 10 pp. cited by other .
Press Release, RADCOM, RADCOM Adds UNI 4.0 Signalling and MPEG-II
Support to ATM Analysis Solutions, at
http://web.archive.org/web/19980527022611/www.radcom-inc.com/press13.htm
(May 27, 1998), 1 p. cited by other .
RADCOM, Prism200 Multiport WAN/LAN/ATM Analyzer, at
http://web.archive.org/web/19980527020144/www.radcom-inc.com/pro-p1.htm
(May 27, 1998), 3 pp. cited by other .
Beckman, Mel, See and hear your networkat
//web.archive.org/web/19990224183147/macworld.zdnet.com/pages/june.96/Rev-
iews.2144.htm1 (Feb. 24, 1999), 3 pp. cited by other .
AG Group, Inc., About Satellite, at
//web.archive.org/web/19980206033053/www.aggroup.com/skyline (Feb.
6, 1998), 1 p. cited by other .
Check Point, Supported Applications, at
web.archive.org/web/19980212233542/www.checkpoint.com/products/technology-
/index.html (Feb. 12, 1998), 6 pp. cited by other .
Check Point, Stateful Inspection in Action, at
web.archive.org/web/19980212235911/www.checkpoint.com/products/technology-
/page2.html (Feb. 12, 1998), 4 pp. cited by other .
Check Point, Check Point FireWall-1: Extensible Stateful
Inspection, at
//web.archive.org/web/19980212235917/www.checkpoint.com/products/technolo-
gy/page3.html (Feb. 12, 1998), 3 pp. cited by other .
RADCOM, PrismLite: Portable WAN/LAN/ATM Protocol Analyzer, at
web.archive.org/web/19980527020156/www.radcom-inc.com/pro-p2.htm
(May 27, 1998), 3 pp. cited by other .
Simpson, David, Viewing RTPDump Files, at
//bmrc.berkeley.edu/.about.davesimp/viewingNotes.html (Oct. 12,
1996), 1 p. cited by other .
Waldbusser, S., RFC 1757--Remote Network Monitoring Management
Information Base, at //www.faqs.org/rfcs/rfc1747.html (Feb. 1995),
65 pp. cited by other.
|
Primary Examiner: Cumming; William D
Attorney, Agent or Firm: Lawrence A. Aaronson, P.C.
Parent Case Text
.Iadd.CROSS-REFERENCE TO RELATED APPLICATIONS
Notice: More than one reissue application has been filed for the
reissue of U.S. Pat. No. 6,757,361. The reissue applications are:
"Voice Interaction Analysis Module," Ser. No. 11/509,553, filed on
Aug. 24, 2006; "Machine Learning Based Upon Feedback From Contact
Center Analysis," Ser. No. 11/509,550, filed on Aug. 24, 2006;
"Distributed Analysis of Voice Interaction Data," Ser. No.
11/509,554, filed on Aug. 24, 2006; "Distributed Recording of Voice
Interaction Data," Ser. No. 11/509,552, filed on Aug. 24, 2006;
"VoIP Voice Interaction Monitor," Ser. No. 11/509,549, filed on
Aug. 24, 2006; "VoIP Voice Interaction Recorder," Ser. No.
11/509,551, filed on Aug. 24, 2006(the present application); and,
"Communication Management System for Network-Based Telephones,"
Ser. No. 11/583,381, filed on Oct. 19, 2006, all of which are
divisional reissues of "Signal Monitoring Apparatus Analyzing Voice
Communication Content," Ser. No. 11/477,124, filed on Jun. 28,
2006, which is a reissue of U.S. Pat. No. 6,757,361, issued on Jun.
29, 2004. .Iaddend.
Claims
What is claimed is:
.[.1. A signal monitoring system for monitoring and analyzing
communications passing through a monitoring point, the system
comprising: a digital voice recorder (18) for monitoring two-way
conversation traffic streams passing through the monitoring point,
said digital voice recorder having connections (20) for being
operatively attached to the monitoring point; a digital processor
(30) connected to said digital voice recorder for identifying at
least one predetermined parameter by analyzing the voice
communication content of at least one monitored signal taken from
the traffic streams; a recorder (38) attached to said digital
processor for recording occurrences of the predetermined parameter;
a traffic stream identifier (36) for identifying the traffic stream
associated with the predetermined parameter; a data analyzer (36)
connected to said digital processor for analyzing the recorded data
relating to the occurrences; and a communication traffic controller
(34) operatively connected to said data analyzer and, operating
responsive to the analysis of the recorded data, for controlling
the handling of communications traffic within said monitoring
system..].
.[.2. The monitoring system of claim 1, wherein said at least one
predetermined parameter includes a frequency of keywords identified
in the voice communication content of the at least one monitored
signal..].
.[.3. The monitoring system of claim 1, wherein said digital
processor further identifies episodes of anger or shouting by
analyzing amplitude envelope..].
.[.4. The monitoring system of claim 1, wherein said at least one
predetermined parameter is a prosody of the voice communication
content of the at least one monitored signal..].
.[.5. The monitoring system of claim 1, wherein said connections
for being operatively attached to the telephony exchange switch are
attached via high impedance taps (20) to telephone signal lines
(24, 26) attached to said telephony exchange switch..].
.[.6. The monitoring system of claim 1, wherein said communication
traffic controller serves to identify at least one section of
traffic relative to another so as to identify a source of the
predetermined parameter..].
.[.7. The monitoring system of claim 1, wherein said communication
traffic controller serves to influence further monitoring actions
within the apparatus..].
.[.8. The monitoring system of claim 1, wherein the analyzed
contents of the at least one monitored signal comprise the
interaction between at least two signals representing an at least
two-way conversation..].
.[.9. The monitoring system of claim 1, wherein the recorder
operates in real time to provide a real-time indication of the
occurrence..].
.[.10. The monitoring system of claim 1, wherein said digital voice
recorder comprises an analog/digital convertor (18) for converting
analog voice into a digital signal..].
.[.11. The monitoring system of claim 1, wherein said digital
processor as a Digital Signal Processor (30) arranged to operate in
accordance with an analyzing algorithm..].
.[.12. The monitoring system of claim 1, wherein the digital
processor is arranged to operate in real time..].
.[.13. The monitoring system of claim 1, further comprising a
replay station (32) connected to said digital processor and
arranged such that the voice communication content of the at least
one monitored signal can be recorded and monitored by said digital
processor for identifying the at least one parameter at some later
time..].
.[.14. The monitoring system of claim 1, wherein the at least one
predetermined parameter comprises plural predetermined parameters
and wherein said recorder records the occurrence of the plural
predetermined parameters in each of the two directions of traffic
separately..].
.[.15. The monitoring system of claim 1, wherein said traffic
stream identifier comprises a means for receiving an identifier
tagged onto the traffic so as to identify its source..].
.[.16. The monitoring system of claim 1, wherein said digital voice
recorder for monitoring the traffic streams is operative responsive
to an output from said traffic stream identifier identifying the
source of the conversation in which the predetermined parameter has
been identified, or a threshold occurrence of the predetermined
parameter has been exceeded..].
.[.17. The monitoring system of claim 1, wherein said digital voice
recorder, said digital processor, said recorder, said traffic
stream identifier, and said data analyzer reside on an add-in card
to a telecommunications system..].
.Iadd.18. A method for recording audio data packets, comprising:
monitoring audio data packets received at a switch associated with
a call center, the audio data packets being transmitted over a
compputer network and comprising packet headers and packet bodies;
examining data within the audio data packets by using a processor
that is communicatively connected to the switch to identify at
least one speaker-independent predetermined parameter associated
with two-way voice communication; and storing at least a portion of
the audio data packets in a storage device communicatively
connected to the prpcessor in accordance with the at least one
speaker-independent predetermined parameter. .Iaddend.
.Iadd.19. The method of claim 18, wherein the processor analyzes
the packet headers..Iaddend.
.Iadd.20. The method of claim 18, wherein examining includes
determining telephone interactions to which the audio data packets
belong. .Iaddend.
.Iadd.21. The method of claim 18, wherein examining includes
sorting the audio data packets in accordance with a timestamp.
.Iaddend.
.Iadd.22. The method of claim 18, further comprising identifying,
by the processor, the voice communication content included in the
packet bodies of the audio data packets. .Iaddend.
.Iadd.23. The method of claim 22, wherein identifying voice
communication content includes identifying a frequency of keywords
identified in the audio data packets received over the computer
network. .Iaddend.
.Iadd.24. The method of claim 22, wherein identifying voice
communication content includes identifying episodes of anger or
shouting based upon an amplitude envelope associated with the audio
data packets. .Iaddend.
.Iadd.25. The method of claim 22, wherein identifying voice
communication content includes identifying a prosody associated
with the voice communication content of the audio data packets.
.Iaddend.
.Iadd.26. The method of claim 22, wherein storing in the storage
device is based upon identification of voice communication content
that includes the at least one speaker-independent predetermined
parameter. .Iaddend.
.Iadd.27. The method of claim 22, wherein identifying voice
communication content includes examining incoming and outgoing
traffic streams to identify whether a talk-over condition exists
with respect to the audio data packets. .Iaddend.
.Iadd.28. The method of claim 22, wherein identifying voice
communication content includes identifying whether one or more of a
predetermined group of words exists with respect to the audio data
packets. .Iaddend.
.Iadd.29. The method of claim 22, wherein identifying voice
communication content includes identifying stress in voice content
associated with the audio data packets. .Iaddend.
.Iadd.30. The method of claim 29, wherein stress is identified by
determining changes in volume, speed and tone of voice content
associated with the audio data packets. .Iaddend.
.Iadd.31. The method of claim 22, wherein identifying voice
communication content includes identifying a delay between audio
data packet transmissions in opposite directions. .Iaddend.
.Iadd.32. The method of claim 18, wherein the examining includes
analyzing the packet bodies by the processor. .Iaddend.
.Iadd.33. A system operable to acquire audio data packets for
recording and analysis, comprising: an audio data recorder operable
to acquire data packets associated with a voice interaction
transmitted over a computer network to a call center, the audio
data packets comprising packet headers and a packet bodies; an
analysis module operable to analyze the data packets by identifying
at least one speaker-independent predetermined parameter associated
with two-way voice communication; and a storage module operable to
store at least a portion of the audio data packets in accordance
with the at least one speaker-independent predetermined parameter.
.Iaddend.
.Iadd.34. The system of claim 33, wherein the analysis module is
operable to extract data from the packet header, and to analyze the
packet body. .Iaddend.
.Iadd.35. The system of claim 33, wherein the audio data recorder
is further operable to determine telephone interactions to which
the data packets belong. .Iaddend.
.Iadd.36. The system of claim 33, wherein the audio data packets
are sorted in accordance with a timestamp. .Iaddend.
.Iadd.37. The system of claim 33, wherein analysis of the packet
bodies comprises identifying voice communication content included
in the packet bodies of the audio data packets..Iaddend.
.Iadd.38. The system of claim 37, wherein identifying voice
communication content includes identifying a frequency of keywords
identified in the audio data packets received over the computer
network. .Iaddend.
.Iadd.39. The system of claim 37, wherein identifying voice
communication content includes identifying episodes of anger or
shouting based upon an amplitude envelope associated with the audio
data packets. .Iaddend.
.Iadd.40. The system of claim 37, wherein identifying voice
communication content includes identifying a prosody associated
with the voice communication content of the audio data packets.
.Iaddend.
.Iadd.41. The system of claim 37, wherein the storage module stores
the portion of the audio data packets based upon identification of
voice communication content that includes the at least one
speaker-independent predetermined parameter. .Iaddend.
.Iadd.42. The system of claim 37, wherein identifying voice
communication content includes examining incoming and outgoing
traffic streams to identify whether a talk-over condition exists
with respect to the audio data packets. .Iaddend.
.Iadd.43. The system of claim 37, wherein identifying voice
communication content includes identifying whether one or more of a
predetermined group of words exists with respect to the audio data
packets. .Iaddend.
.Iadd.44. The system of claim 37, wherein identifying voice
communication content includes identifying stress voice content
associated with the audio data packets. .Iaddend.
.Iadd.45. The system of claim 37, wherein stress is identified by
determining changes in volume, speed and tone of voice content
associated with the audio data packets. .Iaddend.
.Iadd.46. The system of claim 37, wherein identifying voice
communication content includes identifying a delay between data
packet transmissions in opposite directions. .Iaddend.
Description
BACKGROUND OF THE INVENTION
The present invention relates to signal monitoring apparatus and in
particular, but not exclusively to telecommunications monitoring
apparatus which may be arranged for monitoring a plurality of
telephone conversations.
DESCRIPTION OF THE RELATED ART
Telecommunications networks are increasingly being used for the
access of information and for carrying out commercial and/or
financial transactions. In order to safeguard such use of the
networks, it has become appropriate to record the two-way
telecommunications traffic, whether voice traffic or data traffic,
that arises as such transactions are carried out. The recording of
such traffic is intended particularly to safeguard against abusive
and fraudulent use of the telecommunications network for such
purposes.
More recently, so-called "call-centers" have been established at
which operative personnel are established to deal with enquiries
and transactions required of the commercial entity having
established the call-center. An example of the increasing use of
such call-centers is the increasing use of "telephone banking"
services and the telephone ordering of retail goods.
Although the telecommunications traffic handled by such
call-centers is monitored in an attempt to preserve the integrity
of the call-centre, the manner in which such communications
networks, and their related call-centers, are monitored are
disadvantageously limited having regard to the data/information
that can be provided concerning the traffic arising in association
with the call-center.
For example, in large call-centers, it is difficult for supervisors
to establish with any confidence that they have accurately, and
effectively, monitored the quality of all their staff's work so as
to establish, for example, how well their staff are handling
customers' enquiries and/or transaction requirements, or how well
their staff are seeking to market/publicise a particular product
etc.
SUMMARY OF THE INVENTION
The present invention seeks to provide for telecommunications
monitoring apparatus having advantages over known such
apparatus.
According to one aspect of the present invention there is provided
signal monitoring apparatus comprising: means for monitoring
signals representing communications traffic, means for identifying
at least one predetermined parameter by analysing the content of at
least one monitored signal, means for recording the occurrence of
the identified parameter, means for identifying the traffic stream
associated with the identified parameter, means for analysing the
recorded data relating to the said occurrence, and means,
responsive to the analysis of the said recorded data, for
controlling the handling of communications traffic within the
apparatus.
Preferably, the means for controlling the handling of the
communications traffic serves to identify at least one section of
traffic relative to another.
Also, the means for controlling may serve to influence further
monitoring actions within the apparatus.
Advantageously, the analysed contents of the at least one signal
comprise the interaction between at least two signals of traffic
representing an at least two-way conversation. In particular, the
at least two interacting signals relate to portions of interruption
or stiltedness within the traffic.
Preferably, the means for monitoring signals can include means for
recording signals.
Preferably, the means for recording the occurrence of the parameter
comprises means for providing, in real time, a possibly
instantaneous indication of said occurrence, and/or comprises means
for storing, permanently or otherwise, information relating to said
occurrence.
Dependent upon the particular parameter, or parameters, relevant to
a call-center provider, the present invention advantageously allows
for the improved monitoring of traffic so as to identify which
one(s) of a possible plurality of data or voice interactions might
warrant further investigation whilst also allowing for statistical
trends to be recorded and analysed.
The apparatus is advantageously arranged for monitoring speech
signals and indeed any form of telecommunication traffic.
For example, by analysing a range of parameters of the signals
representing traffic such as speech, data or video, patterns,
trends and anomalies within a plurality of interactions can be
readily identified and these can then be used for example, to
influence future automated analysis, and rank or grade the
conversations and/or highlight conversations likely to be worthy of
detailed investigation or playback by the call-center provider. The
means for monitoring the telecommunications signals may be
advantageously arranged to monitor a plurality of separate two-way
voice, data or video conversations, and this makes the apparatus
particularly advantageous for use within a call-centre.
The means for monitoring the telecommunications signals
advantageously arranged to monitor the signals digitally by any one
variety of appropriate means which typically involve the use of
high impedance taps into the network and which have little, or no,
effect on the actual network.
It should of course be appreciated that the invention can be
arranged for monitoring telecommunications signals transmitted over
any appropriate medium, for example a hardwired network comprising
twisted pair or co-axial lines or indeed a telecommunications
medium employing radio waves.
In cases where the monitored signal is not already in digital form,
the apparatus can advantageously include analogue/digital
conversion means for operating on the signal produced by the
aforesaid means for monitoring the telecommunications signals.
It should also be appreciated that the present invention can
comprise means for achieving passive monitoring of a
telecommunications network or call-centre etc.
The means for identifying the at least one predetermined parameter
advantageously includes a Digital Signal Processor which can be
arranged to operate in accordance with any appropriate algorithm.
Preferably, the signal processing required by the means for
identifying the at least one parameter can advantageously be
arranged to be provided by spare capacity arising in the Digital
Signal Processors found within the apparatus and primarily arranged
for controlling the monitoring, compression and/or recording of
signals.
As mentioned above, the particular parameters arranged to be
identified by the apparatus can be selected from those that are
considered appropriate to the requirements of, for example, the
call-centre provider.
However, for further illustration, the following is a
non-exhaustive list of parameters that could be identified in
accordance with the present invention and assuming that the
telecommunications traffic concerned comprises a plurality of
two-way telephone interactions such as conversations: non-voice
elements within predominantly voice-related interactions for
example dialling, Interactive Voice Response Systems, and recorded
speech such as interactive voice response prompts, computer
synthesized speech or background noise such as line noise, the
relationship between transmissions in each direction, for example
the delay occurring, or the overlap between, transmissions in
opposite directions, the amplitude envelope of the signals, so as
to determine caller anger or episodes of shouting, the frequency
spectrum of the signal in various frequency bands, advanced
parameters characterizing the actual speaker which may
advantageously be used in speech authentication; measures of the
speed of interaction, for example for determining the ratio of word
to inter-word pauses, the language used by the speaker(s), the sex
of the speaker(s), the presence or absence of particular words, for
example word spotting using advanced speech recognition techniques,
the frequency and content of prosody including pauses, repetitions,
stutters, and nonsensical utterances in the conversation, vibration
or tremor within a voice, and the confidence/accuracy with which
words are recognized by the receiving party to the conversation so
as to advantageously identify changes in speech patterns arising
from a caller.
Parameters such as the following, and having no direct relationship
to each call's content, can also be monitored date, time, duration
and direction of call, externally generated "tagging" information
for transferred calls or calls to particular customers,
As will be appreciated, the importance of each of the above
parameters and the way in which they can be combined to highlight
particular good, or bad, caller interactions can be readily defined
by the call-center provided.
Advantageously, the apparatus can be arranged so as to afford each
of the parameters concerned a particular weighting, or relative
value.
The apparatus may of course also be arranged to identify the nature
of the data monitored, for example whether speech, facsimile, modem
or video etc. and the rate at which the signals are monitored can
also be recorded and adjusted within the apparatus.
According to a further feature of the invention, the means for
identifying the at least one parameter can be arranged to operate
in real time or, alternatively, the telecommunications signals can
be recorded so as to be monitored by the means for identifying at
least one parameter at some later stage.
Advantageously, the means for recording the actual occurrence of
the identified parameter(s) can be arranged to identify an absolute
value for such occurrences within the communications network and/or
call-centre as a whole or, alternatively, the aforementioned
recording can be carried out on a per-conversation or a
per-caller/operative basis.
The means for recording the occurrence of the identified
parameter(s) can advantageously be associated means for analysing
the results of the information recorded so as to identify patterns,
trends and anomalies within the telecommunications network and/or
call-center.
Advantageously, the means for recording the occurrence of the
identified parameter(s) can, in association with the means for
identifying the predetermined parameter and the means for
monitoring the telecommunications signals, be arranged to record
the aforementioned occurrence in each of the two directions of
traffic separately.
Preferably, the means for identifying the source of the two-way
traffic includes means for receiving an identifier tagged on to the
traffic so as to identify its source, i.e. the particular operative
within the call-centre or the actual caller. Alternatively, means
can be provided within the telecommunications monitoring apparatus
for determining the terminal number, i.e. the telephone number, of
the operative and/or the caller.
The aforementioned identification can also be achieved by way of
data and/or speech recognition.
It should also be appreciated that the present invention can
include means for providing an output indicative of the required
identification of the at least one predetermined parameter. Such
output can be arranged to drive audio and/or visual output means so
that the call-centre provider can readily identify that a
particular parameter has been identified and in which particular
conversation the parameter has occurred. Alternatively, or in
addition, the occurrence of the parameter can be recorded, on any
appropriate medium for later analysis.
Of course, the mere single occurrence of a parameter need not
establish an output from such output means and the apparatus can be
arranged such that an output is only provided once a decision rule
associated with such parameter(s) has been satisfied. Such a
decision rule can be arranged such that it depends on present
and/or past values of the parameter under consideration and/or
other parameters.
Further, once a particular conversation has been identified as
exhibiting a particular predetermined parameter, or satisfying a
decision rule associated with such parameters, the apparatus can be
arranged to allow ready access to the telecommunications "line"
upon which the conversation is occurring so that the conversation
can be interrupted or suspended as required.
As mentioned previously, the apparatus can be arranged to function
in real time or, alternatively, the apparatus can include recording
means arranged particularly to record the telecommunications
traffic for later monitoring and analysis.
Preferably, the apparatus includes means for reconstructing the
signals of the telecommunications traffic to their original form so
as, for example, to replay the actual speech as it was delivered to
the telecommunications network and/or call-center.
The apparatus can therefore advantageously recall the level of
amplification, or attenuation, applied to the signal so as to allow
for the subsequent analysis of the originating signal with its
original amplitude envelope.
Further, the apparatus may include feedback means arranged to
control the means for monitoring the telecommunications signals
responsive to an output from means being provided to identify the
source of the conversation in which the parameter has been
identified, or the decision rule associated with the parameter has
been exceeded.
A further embodiment of the present invention comprises an
implementation in which means for recording and analysing the
monitored signals are built into the actual system providing the
transmission of the original signals so that the invention can
advantageously take the form of an add-in card to an Automatic Call
Distribution System or any other telecommunications system.
Also, it will be appreciated that the present invention can be
advantageously arranged so as to be incorporated into a call-centre
and indeed the present invention can provide for such a call-centre
including apparatus as defined above.
In accordance with another aspect of the present invention, there
is provided a method of monitoring signals representing
communications traffic, and comprising the steps of: identifying at
least one predetermined parameter associated with a monitored
signal; recording the occurrence of the identified parameter; and
identifying the traffic stream in which the parameter was
identified.
The invention is therefore particularly advantageous in allowing
the monitoring of respective parts of an at least two-way
conversation and which may include the of analysis of the
interaction of those parts.
Of course, the method of the present invention can advantageously
be arranged to operate in accordance with the further apparatus
features defined above.
.Iadd.BRIEF DESCRIPTION OF THE DRAWINGS .Iaddend.
The invention is described further hereinafter, by way of example
only, with reference to the accompanying drawings in which:
FIG. 1 is a block diagram of a typical recording and analysis
system embodying the present invention; .[.and.].
FIG. 2 is a diagram illustrating a typical data packetisation
format employed within the present invention;
.Iadd.FIG. 3 is a flowchart of an example process for monitoring
communications traffic; and .Iaddend.
.Iadd.FIG. 4 is a list of exemplary parameters..Iaddend.
DESCRIPTION OF THE EMBODIMENT
As mentioned above, the apparatus can advantageously form part of a
call-centre in which a plurality of telephone conversations can be
monitored so as to provide the call-centre operator with
information relating to the "quality" of the service provided by
the call-center operatives. Of course, the definition of "quality"
will vary according to the requirements of the particular
call-centre and, more importantly, the requirements of the
customers to that call-centre but typical examples are how well the
call-centre operatives handle customers telephone calls, or how
well an Interactive Voice Response System serves customers calling
for, for example, product details.
The system generally comprises apparatus for the passive monitoring
of voice or data signals, algorithms for the analysis of the
monitored signals and, apparatus for the storage and reporting of
the results of the analysis.
Optional features can include apparatus for recording the actual
monitored signals particularly if real time operation is not
required, and means for reconstructing the monitored signals into
their original form so as to allow for, for example, replay of the
speech signal.
FIG. 1 is a block diagram of a recording and analysis system for
use in association with a call-centre 10 which includes an exchange
switch 14 from which four telephone terminals 12 extend: each of
which is used by one of four call-centre operatives handling
customer enquiries/transactions via the exchange switch 14.
The monitoring apparatus 16 embodying the present invention,
comprises a digital voice recorder 18 which is arranged to monitor
the two-way conversation traffic associated with the exchange
switch 14 by way of high impedance taps 20, 22 which are connected
respectively to signal lines 24, 26 associated with the exchange
switch 14 (.Iadd.Step 302, FIG. 3.Iaddend.). As will be appreciated
by the arrows employed for the signal lines 24, 26, the high
impedance tap 20 is arranged to monitor outgoing voice signals from
the call-centre 10 whereas the high impedance tap 22 is arranged to
monitor incoming signals to the call-centre 10. The voice traffic
on the lines 24, 26 therefore form a two-way conversation between a
call-centre operative using one of the terminals 12 and a customer
(not illustrated).
The monitoring apparatus 16 embodying the present invention further
includes a computer telephone link 28 whereby data traffic
appearing at the exchange switch 14 can be monitored as
required.
The digital voice recorder 18 is connected to a network connection
30 which can be in the form of a wide area network (WAN), a local
area network (LAN) or an internal bus of a central processing unit
of a computer.
Also connected to the network connection 30 is a replay station 32,
a configuration arrangement application station 34, a station 36
providing speech and/or data analysis engine(s) and also storage
means comprising a first storage means 38 for the relevant analysis
rules and the results obtained and a second storage means 40 for
storage of the data and/or speech monitor.
FIG. 2 illustrates the typical format of a data packet 42 used in
accordance with the present invention and which comprises a packet
header 44 of typically 48 bytes and a packet header 46 of typically
of 2000 bytes.
The packet header is formatted so as to include the packet
identification 48, the data format 50, a data and time stamp 52,
the relevant channel number within which the data arises 54, the
gain applied to the signal 56 and the data length 58.
The speech, or other data captured in accordance with the apparatus
of the present invention, is found within the packet body 46 and
within the format specified within the packet header 44.
The high impedance taps 20, 22 offer little or no effect on the
transmission lines 24, 26 and, if not in digital form, the
monitored signal is converted into digital form. For example, when
the monitored signal comprises a speech signal, the signal is
typically converted to a pulse code modulated (PCM) signal or is
compressed as an Adaptive Differential PCM (ADPCM) signal.
Further, where signals are transmitted at a constant rate, the time
of the start of the recordings is identified, for example by
voltage or activity detection, i.e. so-called "vox" level
detection, and the time is recorded. With asynchronous data
signals, the start time of a data burst, and optionally the
intervals between characters, may be recorded in addition to the
data characters themselves.
The purpose of this is to allow a computer system to model the
original signal to appropriate values of time, frequency and
amplitude so as to allow the subsequent identification of one or
more of the various parameters arising in association with the
signal (.Iadd.see, FIG. 4.Iaddend.). The digital information
describing the original signals is then analysed at station 36
(.Iadd.Step 304; FIG. 3.Iaddend.), in real time or later, to
determine the required self of metrics, i.e., parameters,
appropriate to the particular application.
.Iadd.FIG. 3 is a flowchart of an example process 300 for
monitoring communications traffic. At stage 302, signals
representing communications traffic are monitored. For example, the
digital voice recorder 18 can monitor two-way conversation traffic
associated with the exchange switch 14. At stage 304, a
predetermined parameter is identified by analyzing the content. For
example, a digital signal processor programmed with an appropriate
algorithm can identify the predetermined parameter. At stage 306,
the occurrence of the identified parameter is recorded. For
example, the first storage 38(analysis rules and results) can store
the occurrence of the identified parameter. At stage 308, the
traffic stream associated with the parameter is identified. For
example, the speech/data analysis engine 36 can identify the
traffic stream. At stage 310, the recorded data relating to the
occurrence is analyzed. For example, the speech/data analysis
engine 36 can analyze the recorded data stored in the first storage
38. .Iaddend.
A particular feature of the system is in recording the two
directions of data transmission separately so allowing further
analysis of information sent in each direction independently
(.Iadd.Step 306; FIG. 3.Iaddend.). In analogue telephone systems,
this may be achieved by use of a four-wire (as opposed to two-wire)
circuit whilst in digital systems, it is the norm to have the two
directions of transmission separated onto separate wire pairs. In
the data world, the source of each data packet is typically stored
alongside the contents of the data packet.
A further feature of the system is in recording the level of
amplification or attenuation applied to the original signal. This
may vary during the monitoring of even a single interaction (e.g.
through the use of Automatic Gain Control Circuitry). This allows
the subsequent reconstruction and analysis of the original signal
amplitude.
Another feature of the system is that monitored data may be
"tagged" with additional information such as customer account
numbers by an external system (e.g. the delivery of additional call
information via a call logging port or computer telephony
integration (CTI) port).
The importance of each of the parameters and the way in which they
can be combined to highlight particularly good or bad interactions
is defined by the user of the system. One or more such analysis
profiles can be held in the system. These profiles determine the
weighting given to each of the above parameters.
The profiles are normally used to rank a large number of monitored
conversations and to identify trends, extremes, anomalies and
norms. "Drill-down" techniques are used to permit the user to
examine the individual call parameters that result in an aggregate
or average score, and, further, allow the user to select individual
conversations to be replayed to confirm or reject the hypothesis
presented by the automated analysis.
A particular variant that can be employed in any embodiment of the
present invention uses feedback from the user's own scoring of the
replayed calls to modify its own analysis algorithms. This may be
achieved using neutral network techniques or similar giving a
system that learns from the user's own view of the quality of
recordings.
A variant of the system uses its own and/or the scoring/ranking
information to determine its further patterns of operation i.e.
determining which recorded calls to retain for future analysis,
determining which agents/lines to monitor and how often, and
determining which of the monitored signals to analyse and to what
depth.
In many systems it is impractical to analyse all attributes of all
calls hence a sampling algorithm may be defined to determine which
calls will be analysed. Further, one or more of the parties can be
identified (e.g. by calling-line identifier for the external party
or by agent log-on identifiers for the internal party). This allows
analysis of the call parameters over a number of calls handled by
the same agent or coming from the same customer.
The system can use sparse capacity on the digital signal processors
(DSPs) that control the monitoring, compression or recording of the
monitored signals to provide some or all of the analysis required.
This allows analysis to proceed more rapidly during those periods
when fewer calls are being monitored.
Spare CPU capacity on a PC at an agent's desk could be used to
analyse the speech. This would comprise a secondary tap into the
speech path being recorded as well as using "free" CPU cycles. Such
an arrangement advantageously allows for the separation of the two
parties, e.g. by tapping the headset/handset connection at the
desk. This allows parameters relating to each party to be stored
even if the main recording point can only see a mixed signal.
A further variant of the system is an implementation in which the
systems recording and analysing the monitored signals are built
into the system providing the transmission of the original signals
(e.g. as an add-in card to an Automatic Call Distribution (ACD)
system).
The apparatus illustrated is particularly useful for identifying
the following parameters: degree of interruption (i.e. overlap
between agent talking and customer talking), comments made during
music or on-hold periods. delays experienced by customers (i.e. the
period from the end of their speech to an agent's response),
caller/agent talk ratios, i.e. which agents might be talking too
much.
However, it should be appreciated that the invention could be
adapted to identify parameters such as: "relaxed/stressed" profile
of a caller or agent (i.e. by determining changes in volume, speed
and tone of speech) frequency of keywords heard (separately from
agents and from callers) e.g. are agents remembering to ask
follow-up questions about a certain product/service etc; or how
often do customers swear at each agent? Or how often do agents
swear at customers? frequency of repeat calls. A combination of
line, ID and caller ID can be provided to eliminate different
people calling from single switchboard/business number languages
used by callers? abnormal speech patterns of agents. For example if
the speech recognition applied to an agent is consistently and
unusually inaccurate for, say, half an hour, the agent should be
checked for: drug abuse, excessive tiredness, drunkenness, stress,
rush to get away etc.
It will be appreciated that the illustrated and indeed any
embodiments of the present invention can be set up as follows.
The Digital Trunk Lines (e.g. T1/E1) can be monitored trunk side
and the recorded speech tagged with the direction of speech. A
MediStar Voice Reorder chassis can be provided typically with one
or two E1/T1 cards plus a number of DSP cards for the more intense
speech processing requirements.
Much of its work can be done overnight and in time, some could be
done by the DSPs in the mediastar's own cards. It is also necessary
to remove or at least recognise, periods of music, on-hold periods,
IVR rather than real agents speaking etc. thus, bundling with
Computer Integrated Telephony Services such as Telephony Services
API (TSAPI) in many cases is appropriate.
Analysis and parameter identification as described above can then
be conducted. However, as noted, if it is not possible to analyse
all speech initially, analysis of a recorded signal can be
conducted.
In any case the monitoring apparatus may be arranged to only search
initially for a few keywords although re-play can be conducted so
as to look for other keywords.
It should be appreciated that the invention is not restricted to
the details of the foregoing embodiment. For example, any
appropriate form of telecommunications network, or signal
transmission media, can be monitored by apparatus according to this
invention and the particular parameters identified can be selected,
and varied, as required.
* * * * *
References