The techniques herein are directed generally to methods and apparatus for automatically classifying interactions with contact center, identifying contacts as being initiated by one of a normal user, a malicious actor, an inexperienced user, or a new type of a user, and invoking mitigation actions such as forwarding the caller to a dedicated agent group based on the identification.

Integrating behavioral and lexical analysis of conversational audio signals with CRM (Customer Relationship Management) workflow analysis signals to provide real-time guidance to agents who are both speaking with a customer telephonically and interacting with the customer's information using a CRM system. This includes intaking audio and CRM analysis signals in real-time, extracting the behavioral and lexical signals from the audio. The CRM, behavioral, and lexical information are combined to produce guidance and scoring signals, which are output to the CRM in real-time to facilitate real-time guidance and scoring. The data can be stored for future reference.

A computerized-method for identifying and utilizing effectiveness of an agent elevating channels during an interaction, in an Omnichannel-Session-Handling environment, is provided herein. The computerized-method may operate, during a duty-cycle, an Elevated Interaction Efficacy (EIE) module for each agent in a data-storage of agents. The EIE-module may include: (a) operating an interaction-module to retrieve one or more interactions of the agent; (b) filtering out from the retrieved interactions, one or more elevated interactions, based on one or more attributes from metadata of the retrieved interactions; (c) calculating an Elevated Interaction Handling (EIH) score for the agent based on one or more attributes from the metadata of the one or more elevated interactions; (d) storing the calculated EIH score in the data-storage of agents; and (e) sending the EIH score to one or more applications, to take one or more follow-up actions based on the EIH score and a calculated EIH threshold.

Techniques are described for training a learning machine. One of these methods includes tracking interactions between a customer and customer service agents. The method includes generating a training set based on the tracked interactions. The method also includes generating a trained learning machine comprising training a learning machine using the training set.

The invention relates to systems/methods that enable real-time monitoring/processing of contact center communications to provide timely, actionable analytic insights and real-time critical call alerts, while simultaneously providing best-in-class protection of sensitive customer information.

Disclosed herein is a method for automated agent behavior recommendations for call quality improvement. The method performed at a server includes receiving a first data record and a second data record of a plurality of data records, each comprising communication between a first party and a second party and determining a first communication originated from the first party. The method includes determining a category for each section of the plurality of sections of the first communication, and a plurality of behavior distances between different categories associated with the plurality of sections. The method includes augmenting first metadata of the first data record and second metadata of the second data record to include associated behavior distances and determining an average performance ranking of the first party to generate a recommendation to increase the average performance ranking of the first party above a preconfigured threshold.

Systems and methods for assessing the skills of a customer support agent using one or more Artificial Intelligence/Machine Learning (AI/ML) models are disclosed. In at least one embodiment, one or more benchmarks against which the performance of the customer support agent is to be measured are established. The one or more benchmarks may be derived through direct and/or indirect analysis of historical customer service data by an AI/ML benchmark model. In at least one embodiment, data relating to performance of the customer support agent during a customer call is monitored. In at least one embodiment, the AI/ML benchmark model is used to determine one or more benchmark scores identifying whether the customer support agent is meeting the one or more benchmarks.

Various embodiments relate generally to data science and data analysis, computer software and systems, and wired and wireless network communications to interface among repositories of disparate data and computing machine-based entities configured to access, track, and/or analyze data, and, more specifically, to a computing and data storage platform to implement computerized tools to continuously (or nearly continuously) sense data describing functional states of remote computing devices and/or user interfaces configured to service electronic messages, according to at least some examples. For example, a method may include receiving a stream of data representing states of user interfaces, analyzing the states of the user interfaces, identifying activity data, identifying a state of an application, detecting an action and classifying a subset of activity data based on the action, and generating data representing a state of an application configured to interact with a digital conversation.

Systems and methods are provided for determining a rapport score for a contact. Data associated with a contact may include an audio recording, a transcript, metadata, and/or other contact data collected during or generated after a contact. One or more rapport models are applied to the contact data to generate rapport metrics that capture one aspect of the rapport during a contact. Rapport metrics can be compared to target rapport metrics to determine whether the rapport metric indicates positive rapport during the contact. From rapport metrics, a rapport score can be generated that indicates the overall rapport for the contact. Rapport metrics, rapport scores, and other information associated with a contact can be provided in a manner that allows for useful evaluation of whether contact participants developed positive rapport during a contact and/or a series of contacts over time.

The present disclosure is directed to methods including obtaining a location data of a source; obtaining at least one performance measure; correlating the location data and the at least one performance measure to obtain a correlation; and analyzing the correlation to obtain an analysis report. The present disclosure is further directed to systems that include a source related to a contact center, and a processor configured to: obtain a location data of the source; derive at least one performance measure; correlate the location data and the at least one performance measure to obtain a correlation; and analyze the correlation to obtain an analysis report.