Title of Invention

A METHOD FOR OPERATING AN INTERACTIVE RESPONSE SYSTEM

Abstract ABSTRACT An interactive voice and data response system then directs input to a voice, text, and web-capable software-based router, which is able to intelligently respond to the input by drawing on a combination of human agents, advanced speech recognition and expert systems, coimected to the router via a TCP/IP network. The digitized input is broken down into components so that the customer interaction is managed as a series of small tasks rather than one ongoing conversation. The router manages the interactions and keeps pace with a real-time conversation. The system utilizes both speech recognition and human intelligence for purposes of interpreting customer utterance or customer text. The system may use more than one human agent, or both human agents and speech recognition software, to interpret simultaneously the same component for error-checking and interpretation accuracy.
Full Text

APPARATUS AND METHOD FOR PROCESSING SERVICE INTERACTIONS Cross-Reference to Related Application
This application is related to and claims the benefit of U.S. Provisional Apphcation No. 60/467,935, filed May 5, 2003, the entire disclosure of which is hereby incorporated herein by reference. Field of the Invention
This invemion relates to the field of interactive response communication systems, and, more particularly to an interactive response communications systems that use human, interpretation of customer intent and data as input to a workflow on a computer. Background of tbe Invention
Many companies interact ;vith tlieir customers via electronic means (most commonly via telephone, e-mail, and online text chat). Such electronic systems save the companies a large amount of money by limiting the number of customer service or support agents needed. These electronic systems, however, generally provide a less than satisfactory customer experience. The customer experience may be acceptable for simple transactions, but are frequently inconsistent or downright frustrating if the customer is not adept at talking to or interacting with a coiTiputer,
Such interactive response systems are well known in the art. For example, pro%'iding customer service via telephone using an interactive voice response (IVR) system is one such system. An example of customer service systems utilizing IVR technology is described in U.S. Patent No. 6,411,686. An IVR system typically communicates with customers using a set of prerecorded phrases, responds to some spoken input and touch-tone signals, and can route or transfer calls. A drawback to such IVR systems is that they are normally built around a "menu" structure, whicli presents callers with just a few valid options at a time and require a narrow range of responses from callers.
Many of these IVR systems now incorporate speech recognition technology. An example of a system incorporating speech recognition technology is described in U.S, Patent No. 6,499,013. The robustness oftlie speech recognition technology used by IVR systems vary, but at present all have a predetermined range of responses that they listen for and can understand, which limits the ability of the end user to interact with the system in everyday language. Therefore, the caller will often feel tiiat they are being forced to speak to the system "as though
0i/05/2O04]S47SS7,01

they are talldng to a computer," Moreo%'er, even Avhen interacting v/itli a system that utilizes speech recognition, customer input is often either not recognized or incorrectly determined, causing the customer to seek a connection to a human customer service agent as soon as possible.
Human customer service agents continue to be used for more involved customer service requests. These agents may speak to the customer over the phone, respond to customer e-mails, and chat with customers online. Agents noraially answer customer questions or respond to customer requests. Companies have customer service groups, which are sometimes outsourced to businesses that specialize in "customer relations management." Such businesses run centers staffed by hundreds of agents who spend Uieir entire working day on the phone or otherwise interacting with customers, An example of such system is described in U.S. Patent No. 5,987,116.
The typical model of customer service interaction is for one agent to assist a customer for the duration of the customer's interaction, At times, one agent (for example, a technical support representative) may transfer the customer to another agent (such as a sales representative) if the customer needs help with multiple requests. But in general, one agent spends his or her time assisting that one customer for the full duration of tlie customer's call or chat session, or is occupied resolving the customer's issue via e-raai]. Most call centers also expect the agent to take the time to log (document) tlie call. Deficiencies in this heavy agent interface model is (1) there is a high agent turnover rate and (2) a great deal of initial and ongoing agent training is usually required, which all add up to making customer service a significant expense for these customer service providers.
hi order to alleviate some of the expenses associated with agents, some organizations outsource their customer service needs. One trend in the United States in recent years, as high-speed fiber optic voice and data networks have proliferated, is to locate customer service centers overseas to take advantage of lower labor costs. Such outsourcing requires that the overseas customer service agents be fluent m English. In cases where these agents are used for telephone-based support, the agent's ability to understand and spealc clearly in English is often an issue. An unfortunate result of off shore outsourcing is misunderstanding and a less than satisfactory customer service experience for the person seeking service.

Therefore, there is a need in the ait for an iuteractii'e system that provides a consistently high-quality experience without the expense of a large staff of dedicated, highly trained agents. Summary of the Ipvention
It is therefore an object of tlie invention to provide an interactive response s>^tem with interactions portioning. That is, a human agent would be able to interact intermittently tlirough a customer call by hearing only those portions of the call requiring his or her inteipretation so no one customer sen'ice agent is tied to the customer's conversation for its full duration.
It is an additional object of tlie invention to provide an interactive response system with multiple-agent checking so that a customer's intent, input (data) or both, is accurately determined. Using double, triple or more checking, more than one human agent evaluates and chooses an interpretation for an instance of customer input, thus improving accuracy of the call and providing an objective measure of each human agent's speed and accuracy.
It is also an object of the invention to provide an interactive response system with agent portabihty so that customer service agents can be located nearly anywhere in the world. If a human agent is needed to interpret intent, data, or both, one, or advantageously two or more, agents hear or see only the component of the interaction need to be interpreted or translated into a context that the interactive response system understands. The interactive response system handles outgoing conmiunication to tlie end user, including speaking (using text-to-speech or professionally recorded clips) so the human agent's voice would never be heard by the customer, eliminatmg any concern of an agent's accent. The actual interaction with the customer is managed by a softwaj'e-based router whose front end is email, interactive data or speech capable.
It is a further object of the invention to provide an interactive response system in which the customer can speak in a conversational tone instead of responding as if "speaking to a computer." A router in accordance with this in'i'ention seamlessly blends both human customer service agents (for interpretation of written or spoken input) and software speech recognition (for spoken word input) to interpret customer input in real-time for intelligent interpretation.
It is an even further object of the invention to provide an interactive response system that allows for simplified human agent ti-aining and evaluation. This invention provides

the ability for multiple agents to evaluate the same component of customer input simultaneously. Further, tliis invention provides a means to objectively rate the speed and accuracy of an agent's response to input, wliich greatly simplifies the hiring and training process. New agents can act in the customer service agent role without their response being weighted by the router, but the agent can still receive feedback on tlieir performance. An objective performance measure then exists to decide when to promote a new liire from trainee status, hi addition, all responses to customers used by the system are scripted and engineered, removing the huge requirements of ti-aining customer sendee agents in how to spealc to customers.
It is another object of the invention to provide an interactive response system that allows for workload balancing by dyiiamicaily adjusting the number of agents assigned to each component of customer interaction for purposes of multiple agent checking. For example, in times of heavier end-user traffic, the system advantageously evaluates and executes a tradeoff between agent accuracy and availability. To effect such balancing, some components of customer input are single-checked by the most accurate agents - thereby maintaining 100% availability of the system. At times of lower traffic, accuracy is increased tlirough triple or quadruple cliecking, which also creates a steady pace of work forbun^an agents. Being able to ramp up availabilit}' without severe])' degj-ading accuracy is a significant enhancement over current call center models.
It is yet another obj ect of the invention to provide an interactive response system that provides speech acceleration to enable faster customer service and response time. Acceleration applied to audio being streamed across a TCP/IP network to help overcome delays introduced by application setup times.
It is even yet another object of the invention to provide an interactive response system with interaction control such tliat interactive steps with customers are determined by choices in a workflow. Advantageously, workflows are updated any time by business analysts, process engineer, or company appointed personnel.
It is a still further object of the invention to provide an interactive response system with end user security so that customer confidential data is kept secure. Workflows may be advantageously designed so that the automated portion of the system can handle taska involving sensiti^'e data such as social security numbers, credit cards, etc., whereby the human agents never have access to this data. Even if a workflow requires that customer service agents do handle

sensitive dats, rhe workflow may be engiiieered to distribute the components of the input in a inamier such that no one agent handles the whole of the customer data, For exanipJe, one aeent might see or hear a fliH customer name, while another has access to the customer's social security niunber, and neither ieams the customer's home address.
These and other objects of the invention are accompUshed in accordance with the principles of the invention by providing an interactive response system that uses human agents to interpret and input customer intent and data from customer utterances or written text. This invention provides a system and metliod of blending human interpretation, speech recognition teciinology, text parsing and lexical analysis, text-to-speech capabilities and other resources in a system for the automated processing of customer-company interactions.
Tliis system is a solution for customer relations management. The central element of the system is a software-based router that manages the conversation with the end user either in real-time (voice, online text chats) or correspondence (e-mail). The router follows rules (herein caljed "workflows") developed and tweaked over time by business analysts. These rules fonn a script for the router to follow when interacting with end users. The router draws on botli text-to-speech capabilities and prerecorded responses when replying to an end user. For interpretation of user utterances, the router employs both speech recognition technology and the interpretive abilities of human customer sen'ice agents, seamlessly blending the two. This blending can be performed in real-time or neai' real-time to allow the router to cany on a conversation-like interaction with an end user. The incorporation of human interpretation of user utterances or written text allows the router to use open-ended, conversational prompts, and to respond in context to user input that software might find ambiguous. Users are thus able to interact witli the system using everyday language, a:id are not forced into a nari'ow range of responses.
The system integrates human agents in an innovative way. Because user input is digitized, the router can direct only ttiose portions of the input that require human interpretation to human agents. No one customer service agent is tied to a customer conversation for its entire duration; the interaction is managed by the router itself. Also, the router is able to send the digitized input to more than one human agent for simultaneous interpretation, which provides double and triple checltiug of each answer from the agents. Such double and triple check also provides an objective measure and ranking of the speed and accuracy of the agents. The system is designed to work over a TCP/A? network, so that the customer service agents can be located

viitually any\\'here in the world. Advantageously, the system comprises off-the-shelf hardware and software, some cuslomized software (as noted below), and can be integrated with existing company resources, such as databases and telephone networks. Brief Description of tbePiawiiios
Finther features of tlie invention, its nature and various advantages will be more apparent from the following detailed description of the preferred embodiment, taken in conjunction with the accompanying drawings, in which h'ke reference characters refer to like parts throughout, and in which:
FIG. 1 is a block diagram iJIustrating one embodiment of an architecture of an interactive response system according to an exemplary embodiment of this invention;
FIG. 2 is a flow chart illustrating an embodiment of a method of the present invention for communication among a customer, the interactive response system and a human interface;
FIG. 3A is a chart illustrating one embodiment of a customer/interactive response system interaction in the context of FIG. 2;
FIG. 3B is a computer screen illustrating one embodiment for capturing customer intent and data in the context of FIG. 2;
FIG. 4A is a chart illustrating one embodiment of a customer/interactive response system interaction in the context of FIG. 2;
FIG. 4B is a computer screen illush-ating one embodiment for capturing customer intent and data in the context of FIG. 2;
FIG. 5 A is a chart illustrating one embodiment of a customer/interactive response system interaction in the context of FIG. 2;
FIG. SB is a computer screen illustrating one embodiment for capturing customei-intent and data in the context of FIG. 2; and
FIG. 6 is a flow chart of processing an email in the context of an interactive response system in accordance with another aspect of this invention. Detailed Descriptioo
FIG.I illustrates one embodiment of an arcliitecture, of the type in which the present invention can be used, for connecting an interactions platform 102 to an interactive response system 100 through an interactive router 101 (herein referred to as an "iRouter"). As

sboivji in FIG. I, intej-actious pisiform 102 is connected to a customer 103 tlirough commumcations link 104. hi.teractions platform 102 is also cormected to interactive response system 100 at iRouter 101 via a datalink, which comprises a TCP/IP data liiik in this exemplaiy embodiment. Interactions platform 102 in this exemplary embodiment comprises a computer server. The exact configuration of the computer server varies wath the implementation but typically consists of a Pentium-based server miuiing an operating system such as Windows XP Professional or Linux, using a voice board from a vendor such as Dialogic. Iijteractions platform 102 can also be an e-mail gateway or web sei-ver. Thus, customer input enters interactive response system 100 via telephone or intercom and text is entered via email or an interactive chatting interface {e.g., a web page or a stand-alone application such as AOL Instant Messenger).
In this architecture of FIG. 1, a number of different types of devices can be used to implement each of the interactions pIatfom:i 102 and communications links 104. ibiteracfions platfoim 102 may be implemented by any device enable of commwiicatingwilli tlie customei-103. For example, interactioiis platform 102 may be a telephony server in interactive response system 100 where the customer is calling by telephone. The telephony server handles answering, transferring and disconnecting incoming calls. The telephony server is also a storehouse for prerecorded audio clips so that it can play any welcome prompt and as other audio clips as directed by iRouter 101.
A telephony sei-ver in accordance with this embodiment is assembled from off-the-shelf components, for example Windows XP Professional for an operating system, a central processor, such as a Pentium processor, and an Intel Dialogic voice board. Using this architecture, the commmiications link 104 may be implemented by any means of providmg an interface between the customer's telephone and the telephony server. For example, communications link 104 may be a dial-up connection or a two-way wireless conmiunication
link.
hi another exemplary embodiment, interactions platform 102 may be a gateway server in interactive response systems 100. In accordance with this exemplary embodiment, the customer interacts with the interactivft response server by e-mail or by interactive text chats. The gateway server runs customised open source e-mail or www server software, Fuither, a gateway server in accordance with tliis exemplary embodiment is designed to conduct e-mai] and Jiiteractive text chat transactions with customers., wliile also foi"wai-ding and receiving data to

otlier eJemeiits of the system. Llsing tlais architecture, tlie commumcations link ] 04 may be implemented by any means of providing an interface between the customer's computer and tlie gateway server. For example, communications linlc 104 may be a dedicated interface, a single network, a combination of networks, a dial-up comiection or a cable modem.
While only one interactions platfomi 102 is illustrated in FIG.l, one skilled in the art will appreciate that multiple interactions platforms 102 may be used in fliis system after studying this specification. With multiple interactions platfomis 102, an interactive response system may communicate via voice and text data with a customer. Further, multiple customer bases may be accommodated by a dedicated interactions platform 102 for each of the customer bases. In this manner, a workflow (as will be described further, below) can be selected by determining which of the multiple interactions platforms 102 initiated the interaction.
In the architecture of FIG. 1, the iRouter 101 comprises software to control interactive response system 100. iRouter 101 "owns" the interaction with customer 103 from beginning to end by coordinating activity among other components and managing tlie transaction. iRouter 101 manages interactions with customer 103 according to one or more programmable scripts, called, according to this exemplary embodiment, "workflows." In general, a workflow comprises an interaction flow wherein the path through the workflow depends upon intent and data input from the customer. Workflows are preprogrammed by systen^ engineers and, advantageously, periodically "tweaked" in order to improve customer satisfaction, speed, accuracy, etc. In accordance with this exemplary embodiment and in contrast to the prior art, iRouter 101 is almost always "in charge" of selecting the next step or path in the workflow.
iRouter 101 receives interaction input from interactions platform 102 in the fomi of audio clips, email, text data or other interaction type — depending on the form of customer communication - and forwards the input to one or more human agents 105, speech recognition engines or expert systems (collectively 108) and uses tlie responses to advance its current workflow, Whenhmnan interpretation (or translation) of the input is necessary, iRouter 101 directs human agent desktop software to display an appropriate visual context of the current workflow. Once iRouter IOI understands tlie input, iRouter 101 advances through the worltflow and directs interactions platform 102 to respond appropriately to customer 103.

In an exemplary embodiment wherein interactions piatforai 102 comprises a telephony sen'er, iRouter 10} may deliver sound clips to play back to a customer, send text-to-speech clips or both. Alternatively, interactions platform 102 may store sound clips, have text-to-speech capability or both, hi this embodiment, iRouter directs interactions platform 102 as to what to play to a custcraei" and when.
iRouter 101 comprises, in this exemplary embodiment, a networked, off-the-shelf commercially available processor running an operating system such as Windows XP or Linux. Further, iRouter 101 software includes a modified open VXML browser and voice XML script incorporating objects appropriate to the specific application. One sldlled in the art will understand how to construct these objects after studying this specification.
in accordance with the exemplaiy arcliitecture of FIG. 1, interactive response system 100 includes at least one pool of human agents 105. A pool of human agents 105 is often located at a contact center site. Human agents 105, m accordance with the present embodiment of this invention, use speciahzed deslctop software specific to system 100 (as will be described fiuther, below, in connection witli FIGs. 3B, 4B and 5B) that presents a given workflow on their screen —along with a history or context of tlie customer interaction to that point. The human agent or agents 105 interpret tlie input and select an appropriate customer intent, data or both in the workflow.
For telephone interactions, human agents 105 wear headphones and hear sound clips streamed from the telephony server 102 at the direction of iRouter 101. hi accordance with one aspect of this invention, a single luunan agent 105 will not handle the entire transaction for customer 103, Rather, human agent 105 handles some piece of the transaction that has been designated by the workflow designer as requiring human interpretation of customer's 103 utterance, IRouter 101 can send the same customer 103 interaction to any number of human agents 105, and may distribute pieces of a given interaction to many different human agents 105.
In accordance with tire exemplary embodiment of this invention, human agents 105 are preferably off-site, Furtlaer, human agents 105 maybe in diverse geographic areas of the world, such as India, the Pliilippines and Mexico. Human agents 105 may be in groups in a building or may be working from home, hi applications that require 24/7 human agent support, Jiuman agejits may be disposed ai-oimd the world so tliat each human agent may work during suitable business hours.

Interactive response system lOO of the present invention employs custom human agent application sofhii'are. Human agents 105 use a custom applicalion developed in Java and running on a standard call center computer network workstation. Generally speaking, interactive response sysXem 100 applies human intelligence towards interpretation of cnslomer 103 input into "intent" (what the customer wants) and data (any input requires to determine what the customer wants). Tlie interpretation normally comprises selecting the most-correct interpretation of what was said from a list of choices, in this exemplary embodiment.
Workflow server ] 06 of tlie present invention, an off-tlie-sheif component, is an archive of the workflows used by tlie Interactions router. Workflow server 106 can be built with 0 ff-the-she2f hardware using a commercially available processor rumiing a standard server operating system, with the workflow documents written in XML in this exemplary embodiment. Workflow server 106 maintains a compilation of business rales that govern the behavior of iRouter 101.
Interactive response system IQO employs a workflow designer used by a business analyst or process engineer to map out workflows. A workflow serves as the map that iRouter 100 follows in a given interaction, with speech recognition or human agents. The workflow "steers" iRouter 100 along a path in the workflow in response to customer input. A place in the workflow, along with data collected to that point is called a "context."
A visual version of the workflow is seen by htmian agent 105. Tlieworkflow designer builds instructions for human agent 105 into the workflow in order to guide human agent 105 in choosing the next appropriate step. The workflow designer preferably consists of a version of Eclipse software development enviromiienf customized to focus on building XML documents. However, one skilled in the ait will be able to develop a workflow designer after studying this specification.
Performance and interactions archive 107 of tlie present invention comprises a
database that can be maintained on any common computer server hardware. Performance and
interactions archive 107 contains both archival data of system transactions with customers 103
(i.e., a repository of sound clips, e-mails, chats, etc. from interactions with customer 103) as well
as performance data for human agents 105. ..
The present invention employs "reporter" software to generate statistics about a
group of interactions or to display performance ranking for human agent 105. Repoiler software

can also reconstruct an mteraction with customer 103 from sound clips, e-mails, or chat text that constituted customer's 103 contact stored in interactions arcliive 107. Reporter software is a series of simple scripts, and can nm on any common server hardwai'e.
The present invention also comprises, in this exemplary embodiment, manager/administrator software, usually mn from tlie same station as reporter software. Manager/administrator software sets operating parameters for interactive response system 100. Such operating parameters include, but ai"e not limited to, business rules for load balancing, uploading changes in workflow, and other administrative changes. Manager/administrator soft\vare is often a small custom Java apphcation running on a standard call center computer workstation.
Support system 108 of the present invention consist of numerous databases and customer proprietary systems (also including off-the-shelf speech recognition software such as Speechworks) that may be employed in responding to customer 103 requests. For example, support system 108 may include a database for customer information or a knowledge base. Speech recognition softwai-e is, in this exemplary embodiment, an off-the-shelf component used to interpret customer 103 utterances. Support system 108 may also include a text-to-speech capability, often off-the-shelf software that reads text to customei" 103.
Company agents 109 of the present invention consist of human agents that handle customer 103 requests not relevant to interactive response system 100 matters. For example, should customer 103 require specific assistance with a company matter that an outsourced human agent 105 is not capable of handling, interactive response system 100 ti-ansfers the call to company agent 109.
The elements of interacti^'e response system 100 communicate over a TCP/IP network in this exemplary embodiment. Communication is driven by the workflow that IRouter 101 follows. "Database" in the present embodiment can be a flat file database, a relational database, an object database, or some combination thereof A database is searchable using any database searching language, such as Structured Query Language (SQL).
"Server" and "workstation" refer to any general purpose computer system which is programmable using a computer progranmiing language, such as C-H-, Java, or other language, such as a scripting language or assembly language. These computer systems may also include specially programmed, special puipose hmdware, for example Intel Dialogic voice boards.

The invention is not limited to a particular computer platform, particulai" processor, particulac operating system, or particular high-level programming language. Additionally, the computer system may be a multiprocessor computer system or may include multiple computers connected over a computer network. The invention is not limited to any particular implementation using software or hardware or firmware, or any combination thereof.
Turning now to FIG.'s 2 through 5, these figures illustrate an example of how information is retrieved and handled by interactive response system 100 when a customer niteracts with the interacti^'e response system 100 via telephone. The example shown in FIG. 2 presupposes that all required hardware, software, networking and system integi-ation is complete, and that a business analyst has mapped out the possible steps in a customer interaction using die graphic workflow designer. The business analyst also has scripted the text for anything tliat the interactive response system may say to a customer, including, but not limited to, the initial prompt (e.g.. "Thank you for calling, how can I help you today?"), response(s) to a customer, requests for additional information, "stutter speech" (sounds sent to tlie customer while die iRouter is determining a response), and a closing statement. Either text-to-speech sofhvare or voice talent records the server-side speech pieces as written by the business analyst. This workflow is then loaded into the interactive response system where it is available to the iRouter.
As shown in block 201, the interaction begins with the customer calling the customer service telephone number of a company. The interactions platform, in this case a telephony ser\'er, answers the telephone call and retrieves the appropriate workflow stored in the workflow database, based on either (1) ANI/DNIS information of the caller or (2) other business ]-ules (e.g., line or trunk the call came in on), as illustrated at 202. The telephony server then plays tlie appropriate welcome prompt as illustrated at 203 and the customer then responses to diat prompt (block 204).
For purpose of example, an imaginary au'Iine, Interair, provides customer service via an interactive response system in accordance witli a call center embodiment of this invention. The interaction platform is therefore a telephony interface and iRouter selects a workflow appropriate Co Interair.
A first point or context in the workflow is shown in the illustrative workflow of FIG. 3 A. There is no customer utterance, thus no intent or data to capture (and respond to). The only response is the greeting and the prompt for customer input.

Processing proceeds lo box 204 in the flowchart of FIG. 2. The telephony sen'er begins digitising the customer's spoken inpul ajid coniiects to the iRouler. At this point, workflow or business rules determine if the interactive response to the customer needs to be handled by a himian agent or speech recognition soihvai-e. That is, tlie iRouter selects the appropriate workflow for the call from the woritflow repository and follows the workflow rules to conduct a conversation with the customer.
To interpret customer speech, iRouter uses software-based speech recognition from the support systems or has the customer's audio streamed to human agents in contact centers as appropriate, as illustrated in block 205, If human agents are required by the workflow, iRouter identifies available human agents by applj-ing a load balancing algorithm, triggers workflow pop-up on their screens (as illustrated in the initially blank pop-up screen, FIG. 3B), and begins streaming customer audio to the one or more identified human agents, as shown at block 207. Tlie human agent(s) hear the customer utterance in headphones, and computer software prompts for an interpretation of the utterance as shown in blocks 210 and 211.
In accordance with the exemplary workflow of FIG. 4 A, the customer utterance that the human agent or agents hear is "I need to check my flight from Chicago to London this afternoon." The agents' screen indicates the cun'enl context (or point in the workflow) as illustrated in FIG. 4B. la this illustrative screen shot, there ai'e 12 possible requests (including unanswerable and terminate) that the human agent can select. In operation, there are several hundred possible interpretations available to the agents. Such multiplicity of selection allows the agents interpretive flexibility, which enables the iRouter to jump around in its workflow according to the interpreted intent. Thus, ui accordance with one aspect of this invention, the iRouter can respond appropriately even if the customer changes subjects in midstream.
In each case, each agent selects what he or she feels is the best fit interpretation of the customer utterance in the current context of the workflow. In example of FIG. 4B, the human agent(s) selects "CFT" (Check Flight Time) and enters or selects from drop down menus the departure and arrival cities (or otiier, preprogranuned information that the customer could
possibly utter).
Note that, in blocks 20S and 209, human agents can elect to apply acceleration to the customer audio clip(s) received at the station in order to compensate for any response delay
(usually due to lag time in application set-up - the time it will take for human agent desktop

software to accept the streaming audio and display the appropriate workflow). Network latency might be around 0.2 seconds, where application delay could be more in the 1+ second range. To compensate for the application delay, the interactive response system accelerates the voice clip (although not to the point of discernible distortion). Tlie purpose is to strive for a more "real¬time" conversational interaction, so tliat the customer does not experience a notable delay while awaiting a response. The acceleration is applied to the speech as it is streaming from the telephony server. The acceleration can ne^'ei- overcome the inherent latency of the link but will allow human agents to "recover" any apphcation set-up time and reduce tlie amount of lag time in the interaction, ideally up to the limits imposed by latency in the network. However, acceleration is optional, wherein a novice agent may need a slower playback, while a more experienced agent in2y apply acceleration.
In test 213, tlie iRouter evaluates the accuracy, in real time, of the customer audio interpretation and updates each agent's speed/accuracy profile. Next, in block 214, the iRouter processes the interpretation and perfomis the next step(s) in the workflow (e.g., database lookup based on input data) and then forwards an appropriate response 218 to the customer through the telephony sen'er (if tlie interpretation is deemed accurate), If the iRouter determines the interpretation is accurate, it directs the playback of responses to the customer from the telephony server based on the interpretation of either the speech recognition software or by applying key algorithms to the responses of one or more human agents, hi this example, the response is given in the last block of screen 2, FIG. 4A.
To delemiine accuracy, the iRouter compares the interpretation of two human agents, and, if no consensus is reached, plays the customer audio clip for a third human agent for a frjrther interpretation (i.e., "majority rule" determines which is the accurate response). Other business rules may also be used to determine the accurate inteipretation. For example, an interpretation from the agent with the best accuracy score may be selected. Alternatively, one of the interpretations may be selected and played back to the customer ("I understood you to say ,..") and the customer response determines whether the interpretation was correct. Further, the interpretations may be selected from laiowii data (e.g., two interpretations of an email address could be compared against a database of ctistoraer email addresses, only one..of.two_. . interpretations of a credit card number will pass a checksum algoritlmi, etc.).

The interacti-\'e response system allows for virtually any nujinber of human agents lo handle to same customer interaction at once. That is, an interactive response system could have two agents listening during a busy time or liave seven human agents listening during a more idle time. Moreover, during times of high call voliune, accuracy can be decreased by removing the "double-checking" rule to maintain high response time. An agent assigned a high trust ranlcing based on the agent's speed/accuracy profile may be asked to work without the double-checking. In addition to trading off accuracy for quicker system availability, a steady flow of audio clips is flowing by each agent, thereby decreasing human agent "slack" time.
Returning to the flowchart of FIG. 2, either the customer will respond again as seen in block 204, tlie call will be IransfeiTed (if so directed by a step in the workflow or by business rules), or the customer tenninates the call, as shown in block 215. If the interpretation is deemed inaccurate in block 213, the iRouter plays a stall speech to the customer (block 216) and send the audio clip to another human agent for anotlier interpretation (block 217) and then reevaluate Its accuracy.
The iRouter manages interaction with the customer to call completion, using the workflow as its guide. The jRouter may stream customer utterances to hmnan agents for interpretation at numerous points in the call. Once the call has concluded, a snapshot of the customer interaction is preserved in the archive database. Human agents' speed/accuracy profiles are constantly updated and maintained.
If human intervention is not needed to interpret customer's request, speech recognition software interprets the audio clip and the iRouter determines the appropriate response as shown in blocks 206 and 214.
Continuing with the Interair example, the captured customer utterance, as seen in FIG. 5A, has two requests: food and entertainment queries. In accordance with another aspect of tliis invention, the human agent captures two intents: meal and movie. There is no relevant data to enter because the interactive response system already knows the flight information from the previous data entered in FIG. 4B (this data is visible in FIG. 5B). As seen in FIG. 5B, the human agent enters "General" and "Meal." The human agent also enters "Movie." As seen in FIG. 5A, the interactive response-system then provides the appropriate response. As seen in FIG. 5B, if ..-the customer requests furtlier information regarding the meal or movie such as: "what meal is

offered?", "Aj-e their special meals?", "Wliat is the movie rated?", the appropriate human agent interpretation options are located on the computer screen.
FIG. 6 illustrates an example of how information is retrieved and handled by the interactive response system when a customer interacts via electronic mail (email, as it is commonly known in the art). As shown in block 601, the interaction begins with the customer emailing to the customer service email of a company. The interactions platform, in this exemplary embodiment, a gateway server, opens the email and retrie^'es the appropriate workflow stored in the workflow database based on eitlier (1) the to/from infoiination of the customer or (2) other business rules, as illustrated at 602. The gateway server then sends the appropriate response acknowledgement as illustrated at 602. Then tlie iRouter identifies available human agent(s) to handle the email by applying a load balancing algoritlim, triggers workflow pop-up on their screens, and begins streaming customer audio to the or those human agents, as shown at block 603. The human agent(s) interpret the email as shown in blocks 604 and 605. After test 606, where the iRouter evaluates the accuracy, in real time, of the customer email interpretation and updates each agent's speed/accuracy profile, the iRouter processes the interpretation and performs the next steps in the workflow accordingly. Eventually, the iRouter forwards an appropriate email response to the customer tlu'ough the gateway server (if the interpretation is deemed accurate) as seen in block 607. The emails are then arcliived in the appropriate database as illustrated in block 60S. If the interpretation is deemed inaccurate, the iRouter sends the email to another human agent for another interpretation (block 609) and then reevaluate its accuracy. The iRouter manages interaction with the customer to email response, using the workflow as its guide.
Other features of the present invention include: a seamless blend of speech recognition software and human agent interaction to provide added customer privacy and security such that human access to confidential customer data is minimized. In a customer contact center environment, customer personal data, such as credit card information, social security number and address, is routinely made available to human agents interacting with customers. The present invention uses a software-based front-end that incorporates speech recognition technology to allow a computer to capture, verify, or update a customer's sensitive data. The software manages the customer interaction so that confidential data is stored in a database and not passed to any human agent. The software can stream audio clips of the

cuouvjuier's utterances over a TCP/IP network to client software being used by human agents any lime that human intei-vention is required. In cases where the workflow does require that a human agent handle sensitive customer infomiation, the transaction is portioned into discrete, logical units allo\vE business analysts to engineer the process so that the same human agent never sees more than one element of a given set of customer data. For example, if two agents see a particular customer's credit card number, two different agents see the customer's name. No one agent sees a full record or profile for a given customer. This helps call center operations, which often experience high agent turnover, minimize the problem of identity theft.
Other features of the present invention include: interactions platform 102 may also accommodate still pictures in any foraiat (e.g.Jpeg, tiff), motion pictures, scamied data, facsimiles, web pages, eic, wliich can be foi-warded to a human agent's station. Such facihty is usefaJ, for example, for monitoring alarms, parsing faxes, etc. The human agent's interpretation is then delivered to the iRouter in the context of the workflow, as above.
It will be understood that the foregoing is only illustrative of the principles of the in\'ention and that \'arious modifications can be made by those skilled in the art without departing fonn the scope of the invention, which is limited only by the claims that follow.



WHAT IS CLAIMED IS:
1. A method for operating an interactive response system comprising:
selecting a computer-operated workflow depending upon how input is received;
receiving free form input;
interpreting said free form input into intent and data in the context of a current point the workflow;
determining automatically a next point in said workflow based on the interpreted mtent and data at the cun-ent point in the workflow; and
taking flnther action responsive to the next point in the workflow.
2. A method in accordance with claim 1 wherein interpreting said free form input
comprises:
detennining a best fit of said free form input in the cun'ent context of said workflow.
3. A method in accordance with claim 2 wherein determining a best fit
comprises:
interpreting said free form input automatically.
4. A method in accordance with claim 2 wherein determining a best fit
comprises:
interpreting said free form input by a human agent.
5. A method in accordance with claim 2 wherein detennining a best fit
comprises:
interpreting said free form input by a plurality of human agents.
6. A metiiod in accordance with claim 5 wherein detemiining a best fit
comprises:
interpreting said free form input by said plurality of human agents; and interpreting said free form input by another human agent if said plm'ahty of human agents do not agree.
7. A method in accordance with claim 5 wherein determining a best fit
comprises:
interpreting said free form input by said plurality of human agents, and, if said
plurality of human operators do not agree:

acting on one inteipretation of said free form input of the majority of said hujnan operators.
S. A method in accordance with claim 5 wherein determining a best fit comprises:
interpreting said free form input by said plurality of human agents, and, if said plurality of human agents do not agree;
acting on one interpretation of said free form input based on past perfonnance of the plurality of human agents.
9. A method in accordance with claim 5 wherein determining a best fit comprises:
interpreting said free fonn input by said plurality of human agents, and, if said
plurality of human agents do not agree;
selecting an interpretation of said input and transmitting the interpretation to a customer for verification.
10. A method in accordance with claim 5 wherein determining a best fit
comprises:
interpreting said freefomiinput by said plurality of human agents, and, if said plurality of human agents do not agree;
acting on one interpretation of said free form input based on known data or algorithms.
U. A method in accordance with claim 1 wherein taking further action comprises:
changmg said next point to said current point in the worlcflow;
prompting for ftirther input;
receiving fiirther fi-ee form input;
interpreting said ftirther free fomi input into said content and data in said context of said current point in said workflow;
determining said next point in said workflow based on the interpreted intent and data at said current point in said workflow; and
taking further action responsive to said next point in said worlcflow.
12. A method in accordance with claim 11 wherein interpreting said free form input comprises inteipreting said free form input at a first means for interpretation and wherein

interpreting said further free form input comprises interpreting said further free form input at a second means for interpretation.
13. A method in accordance with claim 11 wherein interpreting said free fom: input comprises interpreting said free form input at a furst human agent station and wherein interpreting said further free form input comprises interpreting said further free form input at a second human agent station.
14. A metiiod in accordance with claim 1! wherein said interactive response system includes a plurality of human agent stations further including:
delivering said fi-ee fonn input to one or more of said plurality of human agent stations such that each of said plurality of human agent stations only receives selected free form input during said workflow.
15. A method in accordance with claim 14 wherein delivering said free form input comprises delivering said free fonn input so tliat each of said plurality of human agents stations receives limited access to confidential data.
16. An interactive response system comprising:
one or more interactions platforms connected to a network configured to receive free fomi input over the network;
a plurality of human agent position systems configured to interpret said free form input into intention and data; and
an interactions router connected to said interactions platform and said plurality of human agent positions configured to receive said free form input from said one or more interactions platfomis, forward said free form input to one or more of said plurality of human agent position systems, receive said intenrion and data from said one or more of said plurality of human agent position systems and talce further action based on said intention and data from said free form input.
17. An interactive response system in accordance with claim 16 wherein one or more of said plurality of human agent position s}'stems comprises automatic speech recognition systems.
18. All interactive response system in accordance with clainil6 wherein one or more of said p]ui"ality of human agent position systems comprises human agent stations.

19- An interactive response system in accordance witii claim 18 wherein said inieractions i-oiiter is fiuther configured to forward said free form input to one or more of said plurality of human agent position systems depending on a load factor.
20. An interactive response system in accordance with c2aim 19 wherein said interactions router is configured to forward said free form input to one of said plurality of human agent position systems when said load factor is high.
21. An interactive response S3'stera of claim 19 wherein said interactions router is configured to forward said free fonn input to a set of said plurality of human agent position systems when said load factor is low.
22. An interactive response system in accordance with claim 19 wherein said interactions router is configtired to forwai'd said free form input to two of said plurality of human agent position systems and, if said intention and data is not the same from said two of said plurality of liuman agent positions systems, foi-vvarding said free form input to a third one of said plurality of human agent position systems.
23. An interactive response system in accordance with claim 19 wherein said interactions router is further configured to deliver contextual infonnation with said free form input to said human agent position systems.
24. An interactive response system in accordance witli claim 23 wherein said contextual information comprises one or more display screens.
25. An interactive response system in accordance with claim 19 wherein said human agent position systems are geographically diverse.
26. An interactive response system in accordance with claim 16 wherein said free fonn input comprises voice input.
27. An interactive response system in accordance with claim 16 wherein said free fonn input comprises email.
28. An interactive response system in accordance witli claim 16 wherein said free form input comprises textura! data.
29. A method for operating an interactive response system, said interactive response system comprising an interactions platfomi connected to a network, a plurality of human agent position systems configured to intei-pret free fomi input into intention and data and

an interactions router connected to said interactions platform and said plurality of human agent positions, said method comprising:
selecting a computer-operated workflow and a context in said workflow at said interactions router responsive to data received at said interactions platform;
receiving said free form input from said network at said interactions platform;
forwarding said free form input from said interactions platform to said interactions router;
sending said free form input and data representative of context in said workflow from said interactions router to one or more of said plurality'of human agent positions;
inteipreting said free fonn input into intent and data in said context of said workflow;
sending said intent and data to said interactions router;
determining automatically a further context in said workflow at said interactions router based on said interpreted intent and said data at said current context in said workflow; and
taking further action responsive to said further context in said workflow.
30. A method in accordance with claim 29 wherein said plurality of human agent
positions comprise human agents and position systems and wherein interpreting said free fonri
input comprises interpreting said free form input by said human agent and entering said intent
and data mto said position system b>' said human agent.
31. A metliod in accordance with claim 29 where forwarding said free fomi input
comprises forwarding said free form input to said plurality of human agent positions, and
wherein said method further includes:
determining whether said intent and data received from said human agent positions agree; and
forwarding said free form input to another of said plurality of human agent positions if said intent and data received fi-om said human agent positions does not agree.
32. A method in accordance with claim 29 wherein'said free form input is only
sent to one of said plurality of human agent positions once during a worlcflow.
33. A method in accordance with cJaim 29 wherein said free fonn input comprises
human utterances, and wherein sending said free form input includes accelerating said human


Documents:

2875-CHENP-2005 CORRESPONDENCE OTHERS 23-11-2010.pdf

2875-CHENP-2005 CORRESPONDENCE OTHERS.pdf

2875-CHENP-2005 CORRESPONDENCE PO.pdf

2875-CHENP-2005 PCT.pdf

2875-chenp-2005 abstract.pdf

2875-chenp-2005 claims.pdf

2875-chenp-2005 correspondence others.pdf

2875-chenp-2005 correspondence-others.pdf

2875-chenp-2005 correspondence-po.pdf

2875-chenp-2005 description (complete).pdf

2875-chenp-2005 drawings.pdf

2875-chenp-2005 form-1.pdf

2875-chenp-2005 form-18.pdf

2875-chenp-2005 form-26.pdf

2875-chenp-2005 form-3.pdf

2875-chenp-2005 form-5.pdf


Patent Number 245680
Indian Patent Application Number 2875/CHENP/2005
PG Journal Number 05/2011
Publication Date 04-Feb-2011
Grant Date 28-Jan-2011
Date of Filing 03-Nov-2005
Name of Patentee INTERACTIONS, LLC
Applicant Address 4 Princess Road, Suite 205, lawrenceville, NJ 08648
Inventors:
# Inventor's Name Inventor's Address
1 CLORAN, Michael, Eric 45 Pine Knoll Dirve, Lawrenceville, NJ 08648
PCT International Classification Number G06Q10/00
PCT International Application Number PCT/US2004/013946
PCT International Filing date 2004-05-05
PCT Conventions:
# PCT Application Number Date of Convention Priority Country
1 60/467,935 2003-05-05 U.S.A.