Abstract:
A method for training AI models and interacting with customers during customer service sessions using one or more of the AI models is described. The method can be implemented on a cloud architecture where processing and storage resources used to support the AI models can be scaled based on demand. Customer interactions can be recorded and/or monitored in order to provide data for additional training for the AI models. In some embodiments, customer interactions are monitored in real-time in order to make decisions about whether to switch to an AI model more likely to provide a customer more accurate answers and/or a higher level of customer satisfaction.
Abstract:
A system and method for configuring routing logic for a contact center is provided. A plurality of routing templates is displayed for user selection. Each of the routing templates is associated with metadata defining one or more parameters of the corresponding routing template. A contact center administrator selects one of the displayed templates and further identifies an entry point to the contact center to which the selected routing template applies. The parameters defined for the selected template are displayed for prompting user input. The administrator provides input values for the displayed parameters. The user input values are saved in association with the corresponding parameters and further in association with the identified entry point. The saved user input values are then retrieved for routing a particular interaction arriving at the entry point.
Abstract:
A method for routing transactions from customers to agents follows a process of receiving, at a routing server, a transaction to route, and soliciting the customers before connection to an agent, to rate the agents after agent interaction, and checking for existing customer routing profiles. Upon finding an existing routing profile for a customer, checking for existing routing profiles of available agents, and finding existing agent routing profiles, routing customer to agent by matching routing profiles. If no existing routing profile is found for a customer, routing to an agent by a default routing strategy.
Abstract:
A system that supports multiple contact centers includes a communications network that is coupled between a private network (e.g. MPLS network) and a remote computing environment (e.g. cloud environment). A server system in the remote computing environment monitors health of different network segments (e.g. bandwidth of the connection between the communications network and the remote computing environment, bandwidth of a link used by a tenant to access the private network, etc.). When it is determined that quality of service for voice conversations for one or more contact centers is at risk due to a health status parameter of a network segment reaching a threshold, an appropriate system reaction is triggered. The system reaction may be to offload future calls to a peer remote computing environment to service future calls. The system reaction may also be to cancel outbound campaigns, provide pre-determined “sorry” messages, and the like.
Abstract:
A system that supports multiple contact centers includes a communications network that is coupled between a private network (e.g. MPLS network) and a remote computing environment (e.g. cloud environment). A server system in the remote computing environment monitors health of different network segments (e.g. bandwidth of the connection between the communications network and the remote computing environment, bandwidth of a link used by a tenant to access the private network, etc.). When it is determined that quality of service for voice conversations for one or more contact centers is at risk due to a health status parameter of a network segment reaching a threshold, an appropriate system reaction is triggered. The system reaction may be to offload future calls to a peer remote computing environment to service future calls. The system reaction may also be to cancel outbound campaigns, provide pre-determined “sorry” messages, and the like.
Abstract:
A system that supports multiple contact centers includes a communications network that is coupled between a private network (e.g. MPLS network) and a remote computing environment (e.g. cloud environment). A server system in the remote computing environment monitors health of different network segments (e.g. bandwidth of the connection between the communications network and the remote computing environment, bandwidth of a link used by a tenant to access the private network, etc.). When it is determined that quality of service for voice conversations for one or more contact centers is at risk due to a health status parameter of a network segment reaching a threshold, an appropriate system reaction is triggered. The system reaction may be to offload future calls to a peer remote computing environment to service future calls. The system reaction may also be to cancel outbound campaigns, provide pre-determined “sorry” messages, and the like.
Abstract:
A system that supports multiple contact centers includes a communications network that is coupled between a private network (e.g. MPLS network) and a remote computing environment (e.g. cloud environment). A server system in the remote computing environment monitors health of different network segments (e.g. bandwidth of the connection between the communications network and the remote computing environment, bandwidth of a link used by a tenant to access the private network, etc.). When it is determined that quality of service for voice conversations for one or more contact centers is at risk due to a health status parameter of a network segment reaching a threshold, an appropriate system reaction is triggered. The system reaction may be to offload future calls to a peer remote computing environment to service future calls. The system reaction may also be to cancel outbound campaigns, provide pre-determined “sorry” messages, and the like.