U.S. patent application number 12/022723 was filed with the patent office on 2008-07-31 for systems and methods for producing build calls.
This patent application is currently assigned to Eliza Corporation. Invention is credited to Alexandra Drane, Ivy Krull, Lucas Merrow.
Application Number | 20080181371 12/022723 |
Document ID | / |
Family ID | 39667985 |
Filed Date | 2008-07-31 |
United States Patent
Application |
20080181371 |
Kind Code |
A1 |
Merrow; Lucas ; et
al. |
July 31, 2008 |
Systems and Methods for Producing Build Calls
Abstract
Techniques are disclosed for making an automated telephone call
more interactive and intelligent by saving responses gathered from
a previous call and using that information to build more personal
and engaging subsequent interactions. An initial telephone call can
be designed with data needs in mind. Relevant responses from the
initial calls can be captured and stored and a follow-up call can
be created that includes dialogs that reference specific
information from the previous interactions with the system. Such
build call techniques can be utilized on outbound, as well as
inbound calls, and can simulate a human being's ability to listen,
remember and refer to past conversations, making the automated
telephone calls more interactive and effective.
Inventors: |
Merrow; Lucas; (York,
ME) ; Drane; Alexandra; (Winchester, MA) ;
Krull; Ivy; (Andover, MA) |
Correspondence
Address: |
MCDERMOTT WILL & EMERY LLP
28 STATE STREET
BOSTON
MA
02109-1775
US
|
Assignee: |
Eliza Corporation
Beverly
MA
|
Family ID: |
39667985 |
Appl. No.: |
12/022723 |
Filed: |
January 30, 2008 |
Related U.S. Patent Documents
|
|
|
|
|
|
Application
Number |
Filing Date |
Patent Number |
|
|
60898351 |
Jan 30, 2007 |
|
|
|
Current U.S.
Class: |
379/88.01 ;
379/88.18 |
Current CPC
Class: |
H04M 3/5158 20130101;
H04M 11/10 20130101; H04M 2203/2011 20130101; H04M 2201/36
20130101; H04M 2201/40 20130101; H04M 3/46 20130101; H04M 3/5166
20130101 |
Class at
Publication: |
379/88.01 ;
379/88.18 |
International
Class: |
H04M 1/64 20060101
H04M001/64; H04M 11/00 20060101 H04M011/00 |
Claims
1. A method of producing a telephone call for telephony-based
informational interaction, the method comprising: conducting an
initial call with a called person; gathering information from the
called person during the initial call; and conducting at least one
subsequent call with the called person, the subsequent call
utilizing information from the called person from the initial call
and any other previous call.
2. The method of claim 1, wherein conducting an initial call
comprises recognizing a called person.
3. The method of claim 1, wherein gathering information from the
called person during the initial call comprises storing responses
to specific questions posed during the call.
4. The method of claim 1, wherein conducting a subsequent call
comprises recognizing the called person.
5. The method of claim 4, wherein recognizing the called person
comprises conveying recognition to the called person in the
subsequent call.
6. The method of claim 1, wherein conducting an initial call
comprises using an automated system to place the initial call to
the called person.
7. The method of claim 1, wherein conducting an initial call
comprises using an automated system to convey voice prompts to the
called person.
8. The method of claim 1, wherein conducting a subsequent call
comprises using an automated system to place the subsequent call to
the called person.
9. The method of claim 1, wherein conducting a subsequent call
comprises using an automated system to convey voice prompts to the
called person.
10. The method of claim 1, wherein information gathered from the
called person comprises healthcare information.
11. The method of claim 1, wherein information gathered from the
called person comprises health plan information.
12. The method of claim 1, further comprising utilizing information
from an external data source outside of the initial call to the
called person.
13. The method of claim 12, wherein the external data source
comprises insurance claim data.
14. The method of claim 12, wherein the external data source
comprises census demographic data.
15. The method of claim 12, wherein the external data source
comprises consumer purchase data.
16. The method of claim 1, further comprising conveying a news
alert to the called person during the subsequent call.
17. The method of claim 16, wherein the news alert comprises a
public safety message.
18. The method of claim 16, wherein the news alert comprises a
weather report.
19. The method of claim 1, wherein subsequent call includes
healthcare information.
20. The method of claim 1, wherein the subsequent call includes
health plan information.
21. The method of claim 1, wherein information gathered from the
called person comprises language preference, time of day for a
call, thoughts on a program, planned behavior that relates to
health, or other life events.
22. The method of claim 16, wherein the news alert comprises
community event information.
23. The method of claim 22, wherein the community event information
comprises information about local health clinics or seminars.
24. The method of claim 12, wherein the external data source
comprises publicly accessible data.
25. The method of claim 24, wherein the external data comprises
information from the Behavioral Risk Factor Surveillance System
(BRFSS) of the National Center for Chronic Disease Prevention and
Health Promotion.
26. The method of claim 24, wherein the publicly accessible data
comprises cultural indicator data.
27. A system for conducting build calls to a target person, the
system comprising: an automated calling system configured and
arranged to place an automated initial call including one or more
spoken voice prompts to a target person at a called party telephone
and to conduct one or more subsequent build calls to the target
person; and a storage system configured and arranged to record
responses of the target person.
28. The system of claim 27, further comprising an automated speech
recognition system configured and arranged to process auditory
responses of the target person as made in response to the one or
more voice prompts.
29. The system of claim 27, wherein the one or more build calls
incorporate information related to a response from the target
person during the initial call.
30. The system of claim 27, wherein the one or more build calls
incorporate information from an external data source external to
the initial call.
31. The system of claim 30, wherein the external data source
comprises insurance claim data.
32. The system of claim 30, wherein the external data source
comprises census demographic data.
33. The system of claim 30, wherein the external data source
comprises consumer purchase data.
34. The system of claim 27, wherein the system is configured and
arranged to dynamically recognize an inbound or outbound call
conducted with the targeted caller.
35. The system of claim of claim 27, wherein the one or more build
calls includes information including an absence of a response from
the called person.
36. The system of claim 35, wherein information includes that the
called person did take an action that they were requested to
take.
37. The system of claim 36, wherein the action requested to take is
a call to a particular phone number.
Description
RELATED APPLICATION
[0001] This application claims the benefit of U.S. Provisional
Patent Application No. 60/898,351 filed 30 Jan. 2007, the entire
content of which is incorporated herein by reference.
FIELD OF THE DISCLOSURE
[0002] The present disclosure relates generally to automated
telephone calling techniques and, and more particularly, to methods
and systems used to capture specific responses from an initial
automated telephone conversation and using that data to build or
create a more personal and intelligent future interactions with the
person involved with the initial telephone call.
BACKGROUND OF THE DISCLOSURE
[0003] In the new, connected economy, it has become increasingly
important for companies or service providers to become more in tune
with their clients and customers. Such contact can be facilitated
with automated telephonic transaction systems, in which
interactively-selected prompts are played in the context of a
telephone transaction, and the replies of a human user are
recognized by an automatic speech recognition system.
[0004] The answers given by the respondent are processed by the
system in order to convert the spoken words to meaning, which can
then be utilized interactively, or stored in a database. One
example of such a system is described in U.S. Pat. No. 6,990,179,
issued in the names of Lucas Merrow et al. on 24 Jan. 2006 and
assigned to the assignee of the present application, further
discussed below, the entire content of which is incorporated herein
by reference.
[0005] In order for a computer system to recognize the words that
are spoken and convert these words to text, the system must be
programmed to phonetically break down the spoken words and convert
portions of the words to their textural equivalents. Such a
conversion requires an understanding of the components of speech
and the formation of the spoken word. The production of speech
generates a complex series of rapidly changing acoustic pressure
waveforms. These waveforms comprise the basic building blocks of
speech, known as phonemes.
[0006] Vowels and consonants are phonemes and have many different
characteristics, depending on which components of human speech are
used. The position of a phoneme in a word has a significant effect
on the ultimate sound generated. A spoken word can have several
meanings, depending on how it is said. Linguists have identified
allophones as acoustic variants of phonemes and use them to more
explicitly describe how a particular word is formed.
[0007] Automated telephone calls that use speech recognition are a
cost effective method of engaging large populations; organizations
use this methodology to reach out to thousands of people in a
single day.
[0008] While such prior art automated telephone call techniques can
be effective for their intended purposes, such techniques can
present certain problems and limitations. For example, if the
telephone calls are perceived by the recipient as being impersonal
or context-insensitive, and thus not approximating a conversation
with a live human being, the call(s) can be ineffective.
SUMMARY OF THE DISCLOSURE
[0009] The present disclosure addresses the limitations and
problems noted previously for prior art automated phone call
techniques by providing methods and systems for capturing specific
responses from an initial automated telephone conversation and
using that data to build or create a more personal and intelligent
subsequent interaction with the person involved with the initial
telephone call. A primary purpose of any such subsequent "build
calls" includes that information conveyed or acquired during a
previous or initial call or information concerning an action (or
lack thereof) requested during a previous or initial call is
utilized (or built upon) for a subsequent call.
[0010] An embodiment of the present disclosure includes a method of
creating an engaging and intelligent series of speech-activated
telephone calls, where a follow-up conversation with an individual
builds upon responses gathered from a previous call that the system
conducted with that person. An initial telephone call can be made
or conducted to a call recipient or targeted person. Information
can be gathered or received from that person during the initial
call and saved for subsequent use. One or more subsequent calls can
be made to the same person, with the one or more subsequent calls
being built with or incorporating information received from the
called person during the initial call. An automated system can be
used to make the initial call and/or the subsequent call as well as
for recording responses of the called person.
[0011] Another embodiment of the present disclosure includes a
system configured to initiate and conduct (hold) initial and/or
subsequent calls to one or more targeted people over a telephone
system. For such calls, the system can produce spoken voice prompts
for telephony-based informational interaction. The system can
record responses given during an initial call. The information
recorded by the system can be used for one or more subsequent
calls, or build calls, to the same individual(s). Each subsequent
call can incorporate or be based (or built) on information gathered
from the called person during the previous call(s), forming a
so-called "build call". The system can include an automated calling
system, a storage system/medium, and a speech recognition system.
For populations (e.g., large) of targeted or potential call
recipients, the speech recognition system can be
speaker-independent so that it does not require any voice training
by the individual call recipients.
BRIEF DESCRIPTION OF THE DRAWINGS
[0012] Aspects and embodiments of the present disclosure may be
more fully understood from the following description when read
together with the accompanying drawings, which are to be regarded
as illustrative in nature, and not as limiting. The drawings are
not necessarily to scale, emphasis instead being placed on the
principles of the disclosure. In the drawings:
[0013] FIG. 1 depicts a flow chart according to an exemplary
embodiment of the present disclosure;
[0014] FIG. 2 depicts a flow chart according to an exemplary
embodiment of the present disclosure;
[0015] FIG. 3 depicts further method portions in accordance with
exemplary embodiments of the present disclosure; and
[0016] FIG. 4 depicts a diagrammatic view of a system in accordance
with an exemplary embodiment of the present disclosure.
[0017] While certain embodiments depicted in the drawings, one
skilled in the art will appreciate that the embodiments depicted
are illustrative and that variations of those shown, as well as
other embodiments described herein, may be envisioned and practiced
within the scope of the present disclosure.
DETAILED DESCRIPTION
[0018] Aspects and embodiments of the present disclosure are
directed to techniques, including methods and systems, for creating
an engaging and intelligent series of speech-activated telephone
calls, where a follow-up conversation with an individual builds
upon responses gathered from a previous call the system conducted
with that person.
[0019] To utilize automated telephone calls to interact
successfully with a broad range of people, it is desirable to be as
precise and personal as possible for such communication.
Embodiments of the present disclosure provide for successive
automated calls that are personalized, context-sensitive, and thus
life-like. A primary purpose of any such subsequent "build calls"
includes that information conveyed or acquired during a previous or
initial call or information concerning an action (or lack thereof)
requested during a previous or initial call is utilized (or built
upon) for a subsequent call.
[0020] As was described previously, automated telephone calls that
use speech recognition are a cost effective method of engaging
large populations; organizations use this methodology to reach out
to thousands of people in a single day. Research has shown that
automated calls can be more effective to the extent they are
personalized, context-sensitive, and thus approximate a
conversation with a live human being. People are more likely to
engage in an automated telephone call, using speech recognition
technology, if the conversation approximates an interaction between
two human beings, instead of the more traditional approach to
automated calls, which often involves one-way, repetitive
communication from the computer to the human being at the other end
of the telephone line.
[0021] There are a number of ways to make an automated conversation
more "real," as described herein; embodiments of the present
disclosure utilize a unique approach that includes "remembering"
past interactions and intelligently using that information to
engage someone in a subsequent follow-up conversation. Such
building on an initial conversation does not require the caller to
access a record created on a past call, even if the person is
calling inbound to engage in the second conversation. Rather,
embodiments of the present disclosure include the ability to
dynamically recognize an inbound or outbound caller and share
relevant information based upon the last time the system "spoke"
(e.g., interacted) with them.
[0022] Referring now to the drawings, FIG. 1 depicts a flow chart
according to an exemplary embodiment of the present disclosure. An
initial telephone call can be designed and conducted to engage
individuals, as described at 102. Information or data can be
gathered from the individual during the initial call, as described
at 104. One or more subsequent calls can be designed for the called
person, with the subsequent call(s) building upon and utilizing
information from the previous conversation of the initial call, as
described at 106. The subsequent calls can be inbound or outbound
calls, i.e., the initially called person can make or receive the
subsequent build call(s).
[0023] During (or subsequent to) the initial conversation, each
called person can be recognized, as described at 108. During the
subsequent call(s), the called person (e.g., caller) can be
recognized and that recognition can be conveyed to the caller, as
described at 110. In such a way, the called person can be engaged
in a personal and intelligent conversation based upon past
interactions with that person (and his/her responses).
[0024] FIG. 2 depicts a flow chart according to an exemplary
embodiment of the present disclosure. An automated system can be
used to convey voice prompts to the called person during an initial
call, as described at 202. Similarly, an automated system can be
used to convey voice prompts to the called person during one or
more subsequent calls (inbound or outbound), as described at
204.
[0025] Continuing with the description of method 200, responses to
specific questions posed during the initial call can be stored
and/or processed, e.g., by a voice recognition system, as described
at 206. Information and/or data from the initial call can be taken
and used to build or schedule a subsequent call, as described at
208.
[0026] FIG. 3 depicts further method portions in accordance with
exemplary embodiments of the present disclosure. An automated
system, e.g., as described for FIG. 4, may be used to place an
initial call to a called/targeted person, as described at 302.
Similarly, an automated system may be used to place one or more
subsequent calls to the called/targeted person, as described at
304.
[0027] Continuing with the description of 300, information about
the called/targeted person from an external data source (relative
to the initial call) can be used for one or more subsequent calls
to that person, as described at 306. The external data or
information can be used in conjunction with the information/data
gathered during the initial call. Moreover, news alerts and/or
other information may be conveyed to the called person during a
subsequent call, as described at 308. In exemplary embodiments, and
without limitation, the external data source can include insurance
claim data, census demographic data, consumer purchase data,
community service information, police alerts, commuter system
information, and the like.
[0028] The following example is provided for further understanding
of the methods and systems of the present disclosure.
EXAMPLE
A Follow-up Conversation from a Car Dealership
[0029] In our last conversation, we spoke about the importance of
routine maintenance for your car, most of which is covered under
the warranty you presently have on your automobile.
[0030] NOTE: A caller at the targeted telephone number said no to
having arranged an oil change when queried in previous call.
[0031] Specifically, we talked about the importance of having your
oil changed every 5,000 miles. Last time we spoke, your car was due
for this maintenance. Please tell me, have you had a chance to get
the oil changed?
[0032] Yes--That's excellent! CONTINUE to next flagged
maintenance.
[0033] No--Okay. Are you planning to get it changed?
[0034] Yes--That's excellent. Remember, having the oil changed
every 5,000 miles can have a significant impact on the health of
your engine. CONTINUE TO next flagged maintenance.
[0035] No--All right. Please do consider following-up with the
dealership to get your oil changed since it can have a significant
impact on the health of your engine. We can even have one of our
technicians come to your home or work place to change the oil for
you. CONTINUE TO next flagged maintenance.
[0036] NOTE: If yes to fluids in previous call, Go to electrical;
if no to fluids, CONTINUE
[0037] We also talked about the importance of getting your car's
fluids checked every three months. Have you had a chance to get
your car's fluids checked since our last conversation?
[0038] As the preceding example indicates, the follow-up call
builds on a past conversation by referring to a prior call,
referencing information the person shared in the earlier call, and
cuing up specific questions based upon an individual's response to
a question in the past, all of which approximate a live
conversation between two human beings.
[0039] FIG. 4 depicts a diagrammatic view of a system 400 in
accordance with an exemplary embodiment of the present disclosure.
System 400 can be used in conjunction with methods of the present
disclosure, e.g., as shown and described for FIGS. 1-3, and can
include an automated subsystem 412 that includes an automated
telephone calling system 414 and a speech recognition system 416.
System 400 can include a called party telephone 418, and a storage
system 420, as shown. Storage system 420 can include any suitable
voice recording device and/or voice recording media, e.g., magnetic
tape, flash memory, etc. for recording information from the called
person during an initial call and/or subsequent build calls.
[0040] The automated telephone calling system 414 can be of any
suitable kind, and may include a personal computer, although a main
frame computer system can also (or alternatively) be used. All of
the components of telephone calling system 414 can reside on a
particular computer system, thus enabling the system to
independently process data received from a respondent in the manner
described below. Alternatively, the components of system 414 may be
included in different systems that have access to each other via a
LAN or similar network. For example, the automated telephone
calling device 414 may reside on a server system that is configured
to receive the audio response from a telephone 418 and transmit the
response to the speech recognition device 416.
[0041] The automated telephone calling system 414 may also include
a network interface that facilitates receipt of audio information
by any of a variety of networks, such as telephone networks,
cellular telephone networks, the Web, Internet, local area networks
(LANs), wide area networks (WANs), private networks, virtual
private networks (VPNs), intranets, extranets, wireless networks,
and the like, or some combination thereof. The automated subsystem
412 may be accessible by any one or more of a variety of input
devices capable of communicating audio information. Such devices
may include, but are not limited to, a standard telephone or
cellular telephone 418.
[0042] With continued reference to FIG. 4, automated telephone
calling system 414 can include a database of persons to whom the
automated subsystem 412 is capable of initiating telephone calls, a
telephone number associated with each person and a recorded data
file that includes the target person's name. Such automated
telephone calling devices are known in the art. As is described
below, the automated telephone calling system 414 is capable of
initiating a telephone call to a target person and playing a
prerecorded greeting prompt, asking for the target person, and/or
other voice prompts and then recording responses of the
called/target person. System 414 can then interact with speech
recognition system 416 to analyze responses received from the
person on telephone 418. The automated subsystem 412 can also
respond to an inbound call from (directly or indirectly) the
initially called person.
[0043] Speech recognition system 416 can function as an automated
system on which a speech recognition application, including a
series of acoustic outputs or voice prompts, which can comprise
queries about a particular topic, are programmed so that they can
be presented to a respondent, preferably by means of a telephonic
interaction between the querying party and the respondent. A speech
recognition application, however, may be any interactive
application that collects, provides, and/or shares information, or
that is capable of such. For populations (e.g., large) of targeted
or potential call recipients, the speech recognition system can be
speaker-independent so that it does not require any voice training
by the individual call recipients.
[0044] Exemplary embodiments of systems and methods of the present
disclosure can include that it isn't just healthcare or health plan
information that is gathered--it could be personal information like
language preference, time of day for a call, thoughts on a program,
planned behavior that relates to health or other life events.
[0045] Moreover, a news alert of a subsequent call can provide
community event information--examples include local health clinics,
seminars, etc. In certain embodiments, a build call can be centered
on or based upon the absence of a response. For example, it could
be that an attempt was made to contact someone, they didn't call
back in or take the action requested in the initial call (which
lack action could be ascertained or known from external data); this
knowledge could be utilized in the build call. External data
section, it should be noted, can include publicly available data,
e.g., from the Behavioral Risk Factor Surveillance System (BRFSS)
of the National Center for Chronic Disease Prevention and Health
Promotion (i.e., the public health data gathered through the CDC
and state Public Health departments). Additionally, cultural
indicator data, such as demographics linking a person to a
particular culture may also be utilized.
[0046] As examples, in the present disclosure, a speech application
may be any of a group of interactive applications, including
consumer survey applications; Web access applications; educational
applications, including computer-based learning and lesson
applications and testing applications; screening applications;
consumer preference monitoring applications; compliance
applications, including applications that generate notifications of
compliance related activities, including notifications regarding
product maintenance; test result applications, including
applications that provide at least one of standardized tests
results, consumer product test results, and maintenance results;
and linking applications, including applications that link two or
more of the above applications.
[0047] Exemplary voice/speech recognition techniques that can be
implemented within the scope of the present disclosure are
described in U.S. patent application Ser. No. 11/219,593 filed 2
Sep. 2005, entitled "Speech Recognition Method and System for
Determining the Status of an Answered Telephone During the Course
of an Outbound Telephone Call," which is a continuation of U.S.
patent application Ser. No. 09/945,282 filed 31 Aug. 2001, entitled
"Speech Recognition Method and System for Determining the Status of
an Answered Telephone During the Course of an Outbound Telephone
Call," now U.S. Pat. No. 6,990,179 (referenced above); the entire
contents of all of which are incorporated herein by reference. It
should be understood that such systems (or techniques) can further
include an inbound calling features with interaction between the
caller and the speech recognition system.
[0048] Embodiments according to the present disclosure may also be
used with or implement specifically constructed voice prompts
having specifically constructed speech parameters, such as those
disclosed in U.S. patent application Ser. No. 12/020,217 filed 25
Jan. 2008, entitled "Systems and Techniques for Producing Spoken
Voice Prompts," assigned to the assignee of the subject disclosure;
the entire content of which is incorporated herein by
reference.
[0049] Accordingly, embodiments of the present disclosure can
provide advantages relative to prior art automated phone
techniques, as described herein. Embodiments can be utilized to
build more personal and engaging subsequent interactions, can be
utilized on outbound, as well as inbound calls and can simulate a
human being's ability to listen, remember and refer to past
conversations, making the automated telephone calls more
interactive and effective.
[0050] While certain embodiments have been described herein, it
will be understood by one skilled in the art that the methods,
systems, and apparatus of the present disclosure may be embodied in
other specific forms without departing from the spirit thereof.
[0051] Accordingly, the embodiments described herein, and as
claimed in the attached claims, are to be considered in all
respects as illustrative of the present disclosure and not
restrictive.
* * * * *