A method for predicting fraudulent call activity is provided. The method includes receiving one or more datasets indicating call activity corresponding to a phone number, and analyzing the one or more datasets to identify unusual call activity. The method further includes generating a fraud prediction, based at least in part on the identified unusual call activity, that the phone number will be used for fraud.

A computerized-method for determining an agent-proficiency when addressing concurrent customer sessions via one or more channel types and utilization thereof is provided herein. The computerized-method includes operating a Concurrent-Sessions-Handling-Agent-Proficiency (CSHAP) module. The CSHAP-module includes: (a) operating an interactions-module to retrieve one or more interactions and metadata thereof of the agent; (b) for each interaction, determining if the interaction has been handled with concurrent interactions; (c) for each determined interaction as handled with concurrent interactions, checking in the metadata if the interaction has one or more defocused-events; (d) calculating a CSHAP-score for the agent based on one or more attributes from the metadata of the interaction to provide an indication as to an ability of the agent to address concurrent customer sessions; (e) storing the calculated CSHAP-score in a data-store; and (f) sending the CSHAP-score to one or more applications, to take one or more follow-up actions based on the CSHAP-score.

A system, method, and computer program product to accurately route a call is disclosed, by providing a resource interface having one or more interface elements mapping a resource to a call based on current calls and predicted calls, determining a dynamic handling profile from a plurality of dynamic handling profiles that include call information which maps to a resource to provide a ruleset for handling one or more types of call requests, identifying a routing rule comprising one or more routing rules of the ruleset based on caller information, receiving an activation of a resource interface element of the resource interface to initiate a call routing request to forward an assigned call to the resource, and controlling the call routing request according to the routing rule of the dynamic handling profile to perform a call function associated with the assigned call.

Embodiments of the present invention provide systems and methods for determining an engagement level for a customer-agent interaction (e.g., a phone call, text chat, etc.), and the engagement level can be used to evaluate the performance of the agent. For example, the engagement level can be used to determine or adjust a skill level of the agent, a performance of the communication channel that facilitates the interaction, and/or an optimal workload of the agent. According to some embodiments, the engagement level is used to determine that the agent may be experiencing difficulty satisfying a customer inquiry such that the agent should be assigned resources or assistance.

A computer-implemented method for providing an objective evaluation to a customer service representative regarding his performance during an interaction with a customer may include receiving a digitized data stream corresponding to a spoken conversation between a customer and a representative; converting the data stream to a text stream; generating a representative transcript that includes the words from the text stream that are spoken by the representative; comparing the representative transcript with a plurality of positive words and a plurality of negative words; and generating a score that varies according to the occurrence of each word spoken by the representative that matches one of the positive words, and/or the occurrence of each word spoken by the representative that matches one of the negative words. Tone of voice, as well as response time, during the interaction may also be monitored and analyzed to adjust the score, or generate a separate score.

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.

Attention weights in a hierarchical attention network indicate the relative importance of portions of a conversation between an individual at one terminal and a computer or a human agent at another terminal. Weighting the portions of the conversation after converting the conversation to a standard text format allows for a computer to graphically highlight, by color, font, or other indicator visible on a graphical user interface, which portions of a conversation led to an escalation of the interaction from an intelligent virtual assistant to a human customer service agent.

A device monitors a communication between a user associated with a user device and a service representative associated with a service representative device, and causes a natural language processing model to perform a natural language processing analysis of a user input of the communication to identify a topic associated with the communication. The device determines a first score associated with the topic, and determines a second score associated with enabling the communication, where the first score and second score indicate a service performance score of an entity. The device causes a sentiment analysis model to perform a sentiment analysis of the communication to determine a sentiment score indicating a level of satisfaction the user has relative to the topic. The device updates a transaction protocol associated with the topic based on the service performance score, and/or updates a communication processing protocol associated with the communication based on the sentiment score.

Techniques described herein relate to representative monitoring in a contact center environment. Data associated with a customer interaction, including content of the interaction and video of a representative display during processing associated with the interaction, are presented to an administrator in real time or near real time for monitoring during an interaction. In some examples, a contact center server may receive an event notification when a live contact begins, and may generate data files associated with the live contact to allow the administrator to monitor the contact. In some instances, the contact center server may continue to generate data after conclusion of the live contact, to allow the administrator to monitor and guide post-contact processing performed by the representative. The contact center server also may allow administrators to select live contacts for monitoring and/or receive alerts when pre-selected representatives commence live contacts that can be monitored.

Aspects of human assisted virtual agent support are discussed. A conversation between a user and a virtual agent may be monitored. A probability of the user abandoning the conversation may be predicted and a notification may be provided to a human agent to provide assistance in the conversation based on the probability.