Disclosed are systems and methods for forecasting inbound telecommunications, and more particularly, for analyzing real-time and historical call center data, and applying a forecasting model to said data in order to predict inbound call volume. Additionally, tools are disclosed for manipulating call center data and generating visual representations of metrics pertaining to forecasting call center data via a dashboard.

A computerized-method for operating an Omni Session Handling (OSH) engine for proactive OSH to determine that an outreach is required, according to one or more predefined requirements, to maximize capacity of an agent in a contact center by omni session handling, is provided herein. The computerized-method may retrieve one or more interactions from a Customer-Relations-Management database based on a requirement for an outreach to be stored in a queue of proactive contacts. The computer-implemented method may further allocate a queue of one or more interactions to an agent or to a team of agents and then present the agent with a digital preview of an interaction from the queue of one or more interactions for consideration via a display unit, while the agent is handling one or more interactions. The computer-implemented method may further receive from the agent a decision upon review of the presented digital preview of the interaction.

Certain exemplary aspects of the present disclosure are directed to a data-communications system including a networked contact center for which, in an example embodiment, a communication is received by a networked contact center. In determining whether to allow the communication to reach contact center resources, a contact rate value is examined. The contact rate value may represent an allowable quantity of contact within a time interval. For some example embodiments, a determination of whether the network contact center is to accept or reject the communication is made based on the contact rate value.

Systems and methods are used to generate contact type predictions that route user customer service requests within a support platform. The contact type predictions are generated using a hybrid model that includes a deep learning component and a business logic component. The deep learning component may generate a multi-channel output based on text features and context features. The multi-channel output is modified based on one or more business rules to generate the contact type predictions.

A redirection and messaging system receives telephony information identifying a caller and call context from a telephony system. The system selects one of a plurality of messaging operators based on the call context, optionally sends an introductory message to the caller via a messaging service, and generates a message interface for the selected message operator. The message interface includes the caller and call context and any messages sent between the caller and the selected message operator, with an input interface allowing the selected message operator to input and send messages to the caller.

As described herein, an automated call distribution system, method, and computer program are provided that use multi-skill based routing. An opportunity to make customer service-related contact with a customer is detected. A plurality of skills required to handle the customer service-related contact is determined, where each required skill is defined as a skill type and one or more corresponding skill values. A plurality of skills of each customer service agent among one or more available customer service agents is determined. The customer service-related contact is managed based on the plurality of skills required to handle the customer service-related contact and the plurality of skills of each customer service agent among the one or more available customer service agents.

A system and method for enhanced interaction processing in a contact center that includes routing interactions based on adaptable business objectives. A processor detects a pending interaction with a customer. The processor identifies first and second objectives of the contact center in response to detecting the pending interaction, where the first objective is identified as more important to the contact center than the second objective. The processor identifies a first agent for handling the first objective, and determines a likelihood of success of the first agent in achieving the first objective. The processor identifies a second agent for handling the second objective, and determines a likelihood of success of the second agent in achieving the second objective. In the event that the likelihood of success in achieving the second objective by the second agent is higher than the likelihood of success of achieving the first objective by the first agent, the processor transmits instructions to route the pending interaction to the second agent. The processor also prompts the second agent to pursue the second objective.

Embodiments of the present disclosure include computer-implemented systems and methods for routing incoming customer requests or inquiries in a customer service center. The system may include at least one processor configured to execute instructions to perform steps. The steps may include receiving a plurality of incoming customer calls and a plurality of incoming customer chat sessions. The steps may include blending the received plurality of customer calls and the received plurality of customer chat sessions into a total queue for presentation to at least one user device. The steps may additionally include determining a respective priority for each of the blended plurality of customer calls and the blended plurality of customer chat sessions and sending, based on the determined priority, to the at least one user device at least one of the blended plurality of customer calls or the blended plurality of customer chat sessions.

Method starts with processing, by a processor, audio signal to generate audio caller utterance. Processor generates an agent action ranking score associated with the audio caller utterance and determines whether the agent action ranking score is below a minimum threshold. In response to determining that the agent action ranking score is below the minimum threshold, processor generates a transcribed caller utterance using a speech-to-text processor and generates an identified task based on the transcribed caller utterance. Using the transcribed caller utterance and a task-specific agent coaching neural network associated with the identified task, processor generates an ideal response. Processor generates a feedback result and causes the feedback result to be displayed on a display device of the agent client device. Other embodiments are disclosed herein.

This document discusses, among other things, limiting contact to a networked contact center that is a host to multiple tenants. In an example embodiment, a communication is received by a networked contact center. In determining whether to allow the communication to reach contact center resources, a contact rate value may be examined. The contact rate value may represent an allowable quantity of contact within a time interval. For some example embodiments, a determination of whether the network contact center is to accept or reject the communication is made based on the contact rate value.