A phone tree traversal system includes an input device configured to receive a user call request, a memory, and one or more processors. The one or more processors analyze the user call request to identify an entity to call and an objective of the call, and obtain a map of a phone tree utilized by an automated call receiving system of the entity. The phone tree includes at least one node with multiple path segments that branch from the node, and each node includes a respective prompt. The one or more processors determine a route along the map to an endpoint of the phone tree associated with the objective. During the call, the one or more processors navigate the phone tree to reach the endpoint by submitting information in response to the respective prompt at each node along the route that is determined.

In the field of telecommunications, methods, systems, and tangible, non-transitory computer-readable mediums comprising program code are disclosed that comprise receiving a first agent, a second agent, a third agent, and a fourth agent available for pairing to a contact; and selecting the first agent for pairing to the contact based on a pairing strategy, wherein the pairing strategy is configured such that if the third agent and fourth agent had not been available, the second agent would have been selected for pairing to the contact, wherein the pairing strategy is configured such that if the first agent had not been available, the third agent would have been selected for pairing to the contact.

A computer based system and method for identifying complaint interactions, including: detecting appearances of linguistic structures related to complaints in an interaction; calculating at least one sentiment metric of the interaction; and classifying the interaction as being or not being a complaint interaction based on the detected linguistic structures and the at least one sentiment metric, for example using a trained supervised learning model.

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.

An enhanced routing system determines a service provider best suited to fulfill a user's request to interact and establishes a communication session between the user's client device and a device of the service provider. The enhanced routing system may use user characteristics and behavior to select the service provider. For example, the enhanced routing system receives a request to connect to a customer service system from a user who has recently started a new job and has been accessing a banking application on his mobile phone. The enhanced routing system may determine that a payroll service provider is best suited to fulfill the user's request. For example, the enhanced routing system uses a machine learning model that has been trained on previously fulfilled requests. In this way, the enhanced routing system improves upon systems that continuously prompt the user for information by selecting a service provider without overburdening the user.

Techniques for behavioral pairing in a contact center system are disclosed. In one particular embodiment, the techniques may be realized as a method for pairing in a contact center including ordering one or more contacts, ordering one or more agents, comparing a first difference in ordering between a first contact and a first agent in a first pair with a second difference in ordering between a second contact and a second agent in a second pair, and selecting the first pair or the second pair for connection based on the comparing, wherein the first contact and the second contact are different or the first agent and the second agent are different.

The present disclosure relates to techniques for automatically training a chatbot using utterances not understood by the chatbot itself and thus improve its understanding in a fast, effective and unsupervised way. This disclosure implements techniques to update known intents, to create new ones, and to modify the dialog manager so that new responses can be provided. Known intents can be updated with the chatbot's non-understood messages in three different ways: 1) when the user is asked to reformulate his request due to the chatbot not understanding the user, and the confidence of the new intent is greater than a confidence threshold, and the new detected intent is the same as the previous intent; 2) when the user accepts an intent suggestion from the chatbot; and 3) when the agent accepts a response suggestion from the chatbot. New intents, on the other hand, can be automatically created and automatically associated with real answers provided by human agents. These two strategies used simultaneously allow unsupervised training of a dialog system. The benefits of this approach are twofold: 1) there is no need for human intervention to improve the chatbot (unsupervised training), and 2) the new learning introduced in the models comes from real data, not from utterances produced artificially by a human.

One example method of operation may include determining a call received from a calling party and intended for a subscriber device has an elevated likelihood of being a scam call, determining a percentage of calls over a current period of time being filtered as scam calls by a carrier server, when the percentage of calls being filtered as scam calls during the current period of time is above a call threshold percentage, retrieving call history information associated with a subscriber profile of the subscriber device, identifying one or more call patterns from the call history information of the subscriber profile corresponding to the received call, and determining whether to permit the received call based on the identified one or more call patterns.

A system and method for an optimized, self-learning and self-organizing contact center has been developed. This system and method uses principles and tools of information theory, including the latent Dirichlet allocation which reduces information to specific predetermined topics and a distribution of topic related words to infer its hidden, generative underpinnings so to self-organize a contact center, infer its desired electronic versus human make up, and optimally route all customer requests to an electronic resource or a specific human agent best suited to respond to the request for maximal business value per interaction.

A call management system of a call center retrieves from a customer database enterprise customer data associated with an identified customer in a customer call, which may include customer event data, attributions data, and activity event data. The customer database tracks prospects, leads, new business, and purchasers of an enterprise. The system retrieves customer demographic data associated with the identified customer. A predictive model is selected from a plurality of predictive models based on retrieved enterprise customer data. The selected predictive model, including a logistic regression model, and tree-based model, determines a value prediction signal for the identified customer, then classifies the identified customer into a first value group or a second value group. The system routes a customer call classified in the first value group to a first call queue assignment, and routes a customer call classified in the second value group to a second call queue assignment.