Disclosed herein are system, method, and computer program product embodiments for machine learning systems to process incoming call-center calls based on inferred sentiments. An incoming call is routed to a call agent based on an inferred topic, classified based on one or more inferred sentiments of a current caller's speech, determining, based on the call classification, that a complaint has been articulated and initiating an automated assistance by searching for one or more similar callers to the current caller. Based on finding a successful call outcome associated with one or more similar callers, the system suggests one or more phrases to the call agent for use in a dialog with the current caller to improve the one or more inferred sentiments.

A system and method provide an automation solution for guiding a contact center agent during a communication session by providing contextual in-line assistance. Robotic process automation (RPA) is used for automating workflows and processes with robots that capture information from multiple applications of a contact center system and generate contextual guidance for the contact center agent via callout activities during the communication session.

The invention relates to a system (100) and method (200) for providing contextual information and actions to make a conversation meaningful and engaging. The method (200) comprises the steps of identifying a contact from various data sources (101) and collecting the relevant information from one or more web-based applications and databases, wherein the collected information is mapped to create one or more discussion points by one or more prediction servers (102). Post-conversation suggestions are provided by one or more suggestion servers (103), wherein the discussion points and the post-conversation suggestions are displayed on a user interface device (104) for allowing the user to have meaningful and engaging conversations.

Disclosed herein are system, method, and computer program product embodiments for machine learning systems to process incoming call-center calls based on inferred sentiments. An incoming call is routed to a call agent based on an inferred topic, classified based on one or more inferred sentiments of a current caller's speech, determining, based on the call classification, that a complaint has been articulated and initiating an automated assistance by searching for one or more similar callers to the current caller. Based on finding a successful call outcome associated with one or more similar callers, the system suggests one or more phrases to the call agent for use in a dialog with the current caller to improve the one or more inferred sentiments.

Systems and methods for executing a robotic process automation (RPA) workflow are provided. The RPA workflow is executed by a first robot. The execution of the RPA workflow is suspended by the first robot. A current context of the RPA workflow is serialized at a time of the suspension and the current context of the RPA workflow is stored. The execution of the RPA workflow is resumed by a second robot based on a triggering condition by retrieving the current context of the RPA workflow. The first robot and the second robot may be the same robot or different robots.

Methods to reduce agent effort and improve customer experience quality through artificial intelligence. The Agent Assist tool provides contact centers with an innovative tool designed to reduce agent effort, improve quality and reduce costs by minimizing search and data entry tasks The Agent Assist tool is natively built and fully unified within the agent interface while keeping all data internally protected from third-party sharing.

Systems and methods are disclosed for generating a dynamic customized script to facilitate communication between a user and a service provider. The method includes receiving, via an interactive voice response (IVR) system, a request from a mobile device associated with at least one user. The contextual information associated with at least one user is processed, in real-time, based, at least in part, on the request. A dynamic customized script specific to the request is generated, in real-time, based, at least in part, on the processing of the contextual information. The request is routed, via the IVR system, to an agent from a pool of agents of the service provider. A presentation of the dynamic customized script is generated in a user interface of a device associated with the agent, wherein the dynamic customized script is step-by-step guidance to the agent for handling the request of at least one user.

A device, system and method for role based data collection and public-safety incident response is provided. A computing device receives a call to report a public-safety incident. The computing device determines a role of a caller on the call, the role of the caller being relative to the public-safety incident. The computing device retrieves, from one or more memories, data dependent on the role of the caller. The computing device controls a notification device to provide the data dependent on the role of the caller.

Embodiments provide a method for providing a call center supplemental workflow tool, including: receiving from a database a workflow decisional matrix, a plurality of questions, and a plurality of scripts; displaying a web-based graphical user interface on a display providing at least one question or one script; receiving user input; determining, at least another question or at least another script, to be displayed, wherein determining is based upon the user input and the decisional matrix and advances the workflow; based upon the decisional matrix, determining that the workflow has been completed; providing an output of the questions displayed and the user input received; and the output being provided to a primary software application. Other aspects are described and claimed.

Techniques are provided for training, by a system operatively coupled to a processor, an attention weighted recurrent neural network encoder-decoder (AWRNNED) using an iterative process based on one or more paragraphs of agent sentences from respective transcripts of one or more conversations between one or more agents and one or more customers, and based on one or more customer response sentences from the respective transcripts, and generating, by the system, one or more groups respectively comprising one or more agent sentences and one or more customer response sentences selected based on attention weights of the AWRNNED.