مسائل عملی در استفاده از فن آوری گفتار به شبکه و برنامه های کاربردی خدمات مشتری

This paper proposes a simple model to characterise the different stages of short telephone transactions. It also discusses the impact of the context of the caller when entering an automated service. Three different styles of service were then identified, namely, large vocabulary information gathering, spoken language command and natural language task identification for helpdesks. By considering human dialogue equivalents, the requirements for each style are considered. Consequently, it is shown that each style pushes different technological limits. Three case studies, selected from current project from BT laboratories, are presented to highlight the practical design issues in these different styles. The styles and case studies presented are: • Information gathering – UK name and address recognition. • Spoken language command – network service configuration. • Natural language helpdesks – BT operator services. It is shown that large vocabulary information gathering systems require high accuracy, careful data modelling and well-designed strategies to boost confidence and accuracy. Spoken language command requires dialogue and grammar design and test complexity to be managed. Natural language task identification requires large volumes of training data, good learning algorithms and good data generalisation techniques. These styles can be mixed into a single interaction meaning that design frameworks of the future will have to address all of the aspects of the different interaction styles.

1.1.1. Caller context The context of a call to an automated service is very important. We note two important related dimensions: • Victim or volunteer – was the caller expecting automation or were they unsuspecting victims? • Frequent or infrequent – is the caller well primed and experienced or do they rarely call the service? It is the clear experience of the authors that these two dimensions strongly dictate what can be achieved, and in what style, for a given service. It is also extremely common for these two dimensions to pair-up into frequent volunteers and infrequent victims. By definition, frequent callers to a service will quickly come to expect automation and become volunteers if they continue to call. The term victim is deliberately emotive. In the UK IVR services, especially those based on touch tone, are widely disliked when callers are not expecting them ( Attwater et al., 1998a). Early indications are that acceptance of dialogue-based speech recognition systems is higher, but there are currently no well-established norms for talking with machines. Consequently, spoken language behaviour from callers who have not been primed for a service can be difficult to predict. 1.1.2. Four-layer call handling model There are typically four phases during a transaction with a service: • Problem specification – in which the problem to be solved is identified. • Task identification – in which the customer intent is identified within the framework of available services. • Information gathering – in which all details necessary to achieve the task are gathered from the customer • Task completion – in which the customer receives the service or information they require. In practice, when a customer calls a human agent there is often significant overlap between these various phases. For example, there may be several stages of negotiation in order to discover the actual problem experienced by the customer, during which several potential services may be offered to the customer. Fig. 1shows a real call to a BT international operator, annotated into these four phases. Full-size image (11 K) Fig. 1. Straightforward call to an international operator annotated as four-layer call handling model. Figure options This model is helpful for analysing operator-based and automatic interactions. It is important to note that the first two phases of a transaction may also be implicitly satisfied. For example, the BT directory enquiries service on “192” uses a human operator to achieve information gathering and then automates the task completion phase by use of recorded number announcement. Since the directory enquiry service is very well known, the first two phases are implicitly fulfilled when the customer dials the “192” access number.

This paper has presented a simple model to characterise different stages of short telephone transactions. It also discussed the impact of the context of the caller when entering an automated service. Three different styles of service were then identified, namely, large vocabulary information gathering, spoken language command and natural language task identification for helpdesks. These three styles of interaction mirror the different types of dialogue that humans use in these instances. Each style, however, pushes different technological limits. With the aid of three case studies, some of these design issues were investigated. Large vocabulary information gathering systems require high accuracy, careful data modelling and well-designed strategies to boost confidence and accuracy. Spoken language command requires dialogue and grammar design and test complexity to be managed. Natural language task identification requires large volumes of training data, good learning algorithms and good data generalisation techniques. It is perfectly feasible to have all three styles as different phases of the same interaction. For this reason, successful design frameworks of the future will have to address all of the aspects of the different interaction styles. Automation approaches for helpdesks where callers present problems to be resolved, rather than request solutions, are an active area of research. Careful analysis has been shown to be important before selecting a particular technical solution and style of dialogue.