Abstract:
Managing resources in a contact center including assigning each resource to one of a first set of resources each comprising a proficiency level above a first threshold for a first resource attribute, or a second set of resources each comprising a proficiency level below the first threshold for the first resource attribute and a proficiency level above a second threshold for a second resource attribute. An expected number of contacts requiring resources possessing one of the first or second resource attribute is predicted for a time period, and a correlation between the first and second resource attribute is identified. Based on the correlation, a minimum number of resources from each set required to handle the expected number of contacts at a predetermined service level for the time period is forecasted. The minimum number of resources from the first set is less than a number of resources required without the correlation.
Abstract:
A contact center, communication system, and method are disclosed. An illustrative contact center includes a conversational analysis engine that is applied to media exchanged between a customer and a first agent during a first interaction and determines a context of the first interaction. The illustrative contact center further includes a repository of greetings for a second agent and a greeting from the repository of greetings for the second agent is selectable based on the determined context of the first interaction. The illustrative contact center further includes a network interface that facilitates a presentation of the selected greeting to the customer when the customer is transferred from the first agent to the second agent.
Abstract:
Allocating agent resources in a contact center including receiving a new contact at the contact center and instantiating a contact object corresponding to the new contact. A first set of information is received by the contact center, and a first unmanned aerial vehicle (UAV) is selected for deployment to a target destination. At least one characteristic of the first UAV is associated with the contact object; an additional set of information related to at least one of the contact object or the first UAV is received by the contact center during a travel period of the first UAV to the target destination; and a dynamic prediction is made regarding a particular agent of the contact center to connect to the contact object. The contact object is then connected to an agent device associated with the particular agent.
Abstract:
A video stream of a video call between a communication endpoint of customer and a communication endpoint of a contact center agent is received. The video stream of the video call is processed in real-time to generate a real-time emotion transcript. The real-time emotion transcript tracks a plurality of separate emotions based on non-verbal expressions (e.g. facial expressions) that occur in the video stream of the video call. For example, different emotions of both the customer and the contact center agent may tracked in the real-time emotion transcript. The real-time emotion transcript is compared to an emotion transcript of at least one previous video call to determine if the video call should be handled differently in the contact center. In response to determining that video call should be handled differently in the contact center, an action determined to change how the video call is managed in the contact center.
Abstract:
Artificial agents utilized for voice interactions continue to improve in their capacity to conduct more sophisticated interactions. Rather than just presenting a limited set of options, artificial agents are continuing to narrow the gap between generated speech and natural human speech. A requirement is often in place that spoken interactions be recorded, however, storing speech, even with data compression, is a resource-demanding task. Generated speech may be provided from content, such as text, and speech data. By recording an identifier of the content and associated speech data, storage processing and space requirements can be greatly reduced. Playback may be provided from a waveform of audio provided by the human participant and by selecting the content associated with the content identifier and generating speech of the content utilizing settings provided by the speech data.
Abstract:
Detecting fraud in a contact center including receiving an incoming Real-Time Transport Protocol (RTP) media stream associated with a contact, and determining, based on a real-time biometric analysis of the incoming RTP media stream, that the contact is a potential fraudulent contact. The incoming RTP media stream comprises at least one of an audio stream or a video stream. At least one characteristic related to one or more of an audio quality or a video quality of the incoming RTP media stream is altered without altering any characteristics of an outgoing RTP media stream from the contact center to the potential fraudulent contact, and an altered incoming RTP media stream associated with the potential fraudulent contact is received. In some embodiments, at least one subsequent communications session is automatically scheduled and initiated and a subsequent incoming RTP media stream is received during each subsequent communications session.
Abstract:
System and method to improve quality of a high-availability recording of a media stream, the method including: recording the media stream by at least a first and second recorders at separate network locations, to produce first and second recordings; comparing quality metrics of the first and second recordings; and creating an archival copy of the media stream based upon a comparison of quality metrics. In some embodiments, the method may further include: segmenting the first and second recordings into a respective first and second plurality of coextensive segments; and for substantially each segment of the first plurality of segments: comparing a quality metric of said segment with a quality metric of a corresponding segment from the second plurality of segments; and creating an archival copy of a segment of the media stream based upon a comparison of quality metrics for said segment.