Systems and methods include identifying sets of communications using AB testing based on a difference in metadata values between the sets for a first type of metadata, determining at least one similarity between communications in a first set based on metadata values of a second type of metadata, determining at least one similarity between the communications in the second set based on metadata values of the second type of metadata or a third type of metadata, comparing the at least one similarity from the first set to the at least one similarity of the second set to identify differences in metadata values or types of metadata, and determining, based on the differences, a suggested action for an agent for a future communication with respect to at least one of a desired script, a target phrase, or a desired acoustic characteristic.

A system and method for managing a customer's experience with a contact center that takes available data about the customer, the agents of the contact center, and the organization represented by the contact center, for identifying opportunities for additional conversations/interactions with the customer and engaging in those additional conversations/interactions at a time and with a resource predicted to maximize outcomes for the organization. A processor is configured to identify express and/or implied intents for an interaction between the customer and the contact center. A business goal related to the express and/or implied intents is also identified for determining a current performance of the contact center and for identifying any performance gaps. Contact center targets are identified based on their performance in handling the express and/or implied intents, and the identified performance gaps. An available one of the identified targets is then selected for routing the interaction to the target.

A computer-implemented system and method for facilitating appointments within a call center is provided. A list of agents within a call center is received from a user. Each agent is associated with a call queue and handles incoming customer calls to the call queue. An availability of each of the agents on the list is determined. One of the agents is selected as a most available agent. The user is provided with records for the most available agent and is automatically connected with the most available agent.

A computing device having the capability to dynamically select a voice that will be used by a speech synthesizer in creating synthesized speech for use in communicating with a user of the computing device is provided. For example, in some embodiments, the computing device: i) employs the speech synthesizer to have a first audible communication with the user using a first voice; ii) stores user satisfaction data that can be used to determine a user's satisfaction with an action the user took in response to the first audible communication; and iii) determines whether a different voice should be used during a second audible communication with the user based on the stored user satisfaction data.

Contact centers often provide a restricted amount of time for agents to perform post-call activities, including identifying and selecting a relevant completion code from a large set of codes. Providing automated systems and methods to identify the relevant code or codes can present a limited number of the codes (e.g., quick release codes) to the agent and/or automatically enter the completion code. When the quick release code is entered, the record of the call is then updated with the code and the communication is terminated as a single step.

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.

Real-time speech analytics (RTSA) provides maintaining real-time speech conditions, rules, and triggers, and real-time actions and alerts to take. A call between a user and an agent is received at an agent computing device. The call is monitored to detect in the call one of the real-time speech conditions, rules, and triggers. Based on the detection, at least one real-time action and/or alert is initiated.

A system, computer program product, and method are disclosed. In an approach to train customer service agent using chatbots. The method includes training a chatbot for a customer chat simulation based on a customer service conversation data, a task scenario, and a customer persona. The method also includes monitoring an interaction between a customer service agent and the chatbot. The method further includes determining an assessment of the performance of the customer service agent based on the interaction between the customer service agent and the chatbot. The method additionally includes generating feedback for the customer service agent based on the assessment of the performance of the customer service agent.

The present invention is a system and method of continuous sentiment tracking and the determination of optimized agent actions through the training of sentiment models and applying the sentiment models to new incoming interactions. The system receives conversations comprising incoming interactions and agent actions and determines customer sentiment on a micro-interaction level for each incoming interaction. Based on interaction types, the system correlates the determined sentiment with the agent action received prior to the sentiment determination to create and train sentiment models. Sentiment models include agent action recommendations for a desired sentiment outcome. Once trained, the sentiment models can be applied to new incoming interactions to provide CSRs with actions that will yield a desired sentiment outcome.

Disclosed herein are system, method, and computer program product embodiments for categorizing customer complaints on social media using a model trained on customer voice calls or chats with agents. Additionally, users interested in monitoring regulatory compliance issues based on customer complaints can receive notifications regarding complaints that are linked to regulatory topic areas, without the need to manually scan vast numbers of social media postings.