Methods for optimizing the routing of customer communications include receiving a customer communication; identifying a customer associated with the customer communication; accessing a profile of the identified customer to determine customer data; receiving normalized customer metric scores for a plurality of customer metrics; identifying available agents; accessing a profile of each available agent to determine agent data; predicting interaction outcome metric values for a plurality of customer metrics based on the customer data and the agent data; normalizing the predicted interaction outcome metric values; calculating, in real-time, an aggregate agent-customer pairing score for each available agent; selecting a responding agent from the available agents with the highest aggregate agent-customer pairing score; and providing a routing recommendation to a communication distributor to route the customer communication to the responding agent with the highest aggregate agent-customer pairing score.

A virtual assistant server receives a web request such as a HTTP request with one or more call parameters corresponding to a call redirected from an interactive voice response server. The virtual assistant server inputs the received one or more call parameters to a predictive model, which identifies, based on the one or more call parameters, an intelligent communication mode to route the redirected call to. Subsequently, the virtual assistant server routes the redirected call to the intelligent communication mode.

A system comprises a service platform comprising an applications server. The applications server is configured to receive an inbound communication, route the inbound communication to a speech-enabled intelligent script, the speech-enabled intelligent script comprising one or more of predetermined prompts and dynamically-generated prompts, and determine a source of the inbound communication and a destination of the inbound communication. The applications server is configured to determine that at least one prior inbound communication directed to the destination has been received from the source of the inbound communication. The applications server is configured to receive, in response to at least one predetermined prompt or dynamically-generated prompt, a request for direct contact information associated with the destination of the inbound communication. The applications server is configured to send, to the source of the inbound communication, a message comprising the direct contact information for the destination of the inbound communication.

A system for transitioning a telephony or in-person servicing to an artificial intelligence (AI) chat session is disclosed. The system may receive a phone call from a user device associated with a user, and transmit a voice request for personally identifiable information associated with the user. The system may also receive and authenticate the requested personally identifiable information and, in response, generate an authentication token. The system may further receive a servicing intent from the user device, and generate a corresponding servicing intent token. Also, the system may generate an API call to an AI chatbot model, transmit the authentication token and the servicing intent token to the AI chatbot model, and map the servicing intent token to a stored servicing intent. Finally, the system may transmit a message to the user device via the AI chat session.

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.

A system establishes an agent communication with a customer. An agent computer with a first processor and a first memory receives a batch notification identifying a batch of one or more customer records in the agent computer, for communication in the near future. The one or more customer records is associated with one or more customers. A second computer with a second processor and a second memory provides the batch notification identifying the batch of one or more customer records in the agent computer. The system determines a next step action by taking into account touch specific outcome correlation data, marketing outcome correlation data, and/or correlation between touch specific outcome correlation data and overall outcome data.

Techniques for benchmarking pairing strategies in a contact center system are disclosed. In one embodiment, the techniques may be realized as a method for benchmarking pairing strategies in a contact center system comprising: determining for each contact of a plurality of contacts, an associated plurality of historical contact assignments; determining, for each contact, an associated outcome value; partitioning, for each contact, the associated plurality of historical assignments into a first associated subset assigned using a first pairing strategy and a second associated subset assigned using a second pairing strategy; determining, for each contact, a first portion of the associated outcome value attributable to the first associated subset and a second portion of the associated outcome value attributable to the second associated subset; outputting a difference in performance between the first and second pairing strategies according to the first and second associated portions of the associated outcome value for each contact.

Certain aspects of the disclosure are directed to template-based management of telecommunications services. According to a specific example, a VoIP server is provided comprising one or more computer processor circuits configured to interface with a remotely-situated client entity using a first programming language. The VoTP server includes a call control engine that is configured to provide a private branch exchange (PBX) for the client entity, and identify at least one call control template written in a second programming language. The call control engine is further configured to control call routing by the PBX and for the VoIP telephone call by executing the call control template to identify at least one data source that corresponds to a call property for the VoIP telephone call, retrieve data from the data source, and implement one or more call processing functions specified by the call control template as being conditional upon the retrieved data.

Methods and apparatus are described for a telephony server screening voice calls. In one embodiment, the telephony server receives, form an originating device, an incoming call to be routed to a receiving device. The server answers the incoming call to establish a communication link with the originating device. The server transmits, via the communication link, a challenge audio signal containing an audio message for playback by the originating device. The server receives, via the communication link, a response from the originating device, and, in response to authenticating the response, routes the incoming call to the receiving device. Other embodiments are also described and claimed.

Some embodiments provide a non-transitory machine-readable medium that stores a program. The program receives a set of audio files. Each audio file in the set of audio files includes audio from an audio call. The program further truncates each audio file in the set of audio files to a defined call length. For each audio call in the set of audio calls, the program also receives a transcript of the audio call based on the audio file of the audio call. For each audio call in the set of audio calls, the program further uses the transcript of the audio call as input to a machine learning model for the machine learning model to predict a category from a plurality of categories that is associated with the audio call.