Abstract: 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.

Abstract: Voice and video features of a software platform are integrated to enable customization of software services of the software platform on a customer-basis. Routing rules are defined to route calls to certain phone numbers or extensions to certain software services. Thereafter, when a call is received via a telephony system associated with the software platform, a routing rule customized for the software platform is identified based on information signaled with the call, such as a phone number or extension dialed to place the call. A software service is determined based on the routing rule, and the phone is connected with the software system that provides the software service.

Abstract: A method and a system for reporting metrics relating to customer calls for fungible agents that are utilizing multiple servicing applications in a contact center environment are provided. The method includes: receiving a service request call from a customer; determining applications that are usable for responding to the service request call from among a predetermined plurality of applications; monitoring the service request call in order to obtain information relating to call timing and events occurring during the call; when the service request call is completed, determining call-specific metrics such as hold time, number of transfers, and or idle time based on the information obtained during the monitoring; and reporting the metrics to a repository. Additional metrics that are specific to an agent assigned to handle the call may also be determined.

Abstract: In various embodiments, a device receives profile data regarding users or devices of an on-premise telephony system. The device identifies, based on the profile data, group features associated with the users or devices of the on-premise telephony system. The device forms a candidate set of users or devices of the on-premise telephony system for migration to a cloud-hosted call agent, based on them sharing at least one of the group features. The device provides data indictive of the candidate set of users or devices to a user interface for display.

Abstract: One disclosed system includes dialer device with a dialer identifier that initiates a call with a receiver device with a receiver identifier over a voice channel. A database stores: interaction data in association with both the receiver identifier and the dialer identifier; a content quality metric in association with the interaction data; and a network topology in which the receiver identifier and the dialer identifier are associated with nodes and are connected by an edge. A server is programmed to: update, based on the content quality metric and the network topology, a rankings associated with the receiver identifier and the dialer identifier; and one of: surface the ranking associated with the dialer identifier and the ranking associated with the receiver identifier to an external searching agent using an external data channel and without using any voice channel; or rank the dialer identifier for an internal searching agent using the ranking.

Abstract: A computer-implemented method and system for streamlining interactions between a customer and a company representative. Information related to a customer is received by a company representative. A predicted future action by the customer is then calculated by a computer process wherein the calculation is based on the received information. The predicted future action is then caused to be displayed on a computer operated by a representative of the company. A conversation plan may be generated according to the information and a business rule which may be displayed on the representative's computer.

Abstract: In an example embodiment, a cloud-based unified communications solution and collaboration platform is provided that includes private branch exchange (PBX) business phone service, among other services, in one interface. Furthermore, in an example embodiment, this cloud-based unified communications solution enables a feature called “call flip,” which allows a user to transfer an active phone call from one device of the user to another device of the same user, without disconnecting the phone call, and despite both devices sharing a common extension or phone number. More particularly, the system is able to detect that a user wishes to perform a “call flip”, identify the device from which the user is attempting to perform the call flip, identify the other devices associated with the user, and then ring only the other devices and not the device from which the user is attempting to perform the call flip.

Abstract: 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.

Abstract: A system and method for hybrid callback management and failure recovery, utilizing a callback cloud and an on-premise callback system, allowing brands to utilize a hybrid system that protects against any premise outages or cloud service faults and failures by introducing redundancies and co-maintenance of data key to callback execution.

Abstract: A system and method for unified autodial campaign management, comprising a campaign management console, a data services engine, a traffic shaper, an agent desktop, Control agent desktop, an auto-dialer, and a simple dialer which allows enterprises to conduct unified communications campaigns without differentiating between prior expressed written consent consumers, and those who have not provided prior expressed written consent, to being autodialed or receiving artificial or pre-recorded voice messages, allowing for compliance with regulations regarding such consent without splitting or bifurcating or otherwise hampering communications campaigns for the enterprise customers.

Abstract: In a predictor device, a method for predicting a metric of a contact center includes receiving contact center operational data associated with a time duration; training a set of algorithms and their available hyperparameters with the contact center operational data to generate a set of data models; generating a score associated with each data model of the set of data models, the score quantifying a performance of each algorithm and its available hyperparameters on the contact center operational data; identifying the data model having the largest score as a best learning model for the time duration; and generating a contact center metric prediction based on the best learning model for the time duration.

Abstract: Systems and methods for detecting indications of a scam caller are disclosed. Call data, such as call audio, is received and used to create a training dataset. Using the training dataset, a machine learning model is trained to detect indications of a scam caller in a phone call. An Interactive Voice Response (IVR) model is trained or configured, using voice samples of speech of a subscriber of a telecommunications service provider, to simulate speech and conversation of the subscriber. A conversational agent is generated using the IVR model and the trained machine learning model. The conversational agent receives a phone call, engages a caller in simulated conversation, and detects indications of whether the caller is a likely scam caller. If the caller is determined to be a likely scam caller, an alert can be generated and/or the call can be disconnected.

Abstract: An interactive voice response system for interpreting sentiment of a conversation in real time is provided. The system may include a receiver. The receiver may be operable to receive a plurality of sentiment signals and a first portion of a conversation. The first portion of the conversation may include a plurality of interaction pairs. Each interaction pair may include an utterance and a system response. The system may include an utterance sentiment category determination module that may be operable to determine a sentiment category for each utterance. The system may include a sequential module. The sequential module may determine a conversation sentiment category based on the utterance sentiment categories and the order in which the utterance sentiment categories are received. The system may include an output module. The output module may output the conversation sentiment category. The conversation sentiment category may be used to determine a future system response.

Abstract: A request for a contact center agent interaction is received from a user device associated with a user. The user device is connected to a virtual waiting room that includes waiting users of a contact center queue. The virtual waiting room enables the user to virtually interact with at least a subset of the waiting users. Responsive to an indication to activate a private session between the user device and an agent device associated with a contact center agent, the user is removed from the virtual waiting room.

Abstract: Systems and methods of managing customer journeys are implemented using one or more processors in a computing system. Each journey may comprise a succession of interactions at interaction points such as telephone conversations, responses to an interactive voice response “IVR” system and viewing a web page. Customer journey scores are determined for customers at one or more interaction points along the customer journey and the customer journey score is used to determine whether and when an intervention should take place. Models for determining customer journey scores may be created for a set of customers based on one or both of subjective and objective data relating to a subset of the set of customers that have made some or part of the journey, e.g. customers that have responded to polls. An intervention may take place during the journey or after completion of the journey.

Abstract: A computer server system comprises a communications module; a processor coupled with the communications module; and a memory coupled to the processor and storing processor-executable instructions which, when executed by the processor, configure the processor to receive, via the communications module and from a first device, a signal including a request to schedule access to a shared resource within a time window; identify, based on a load projection for the shared resource, at least one time period within the time window for the access to the shared resource; send, via the communications module and to the first device, a signal including the at least one time period and requesting confirmation that a particular one of the at least one time period is acceptable; receive, via the communications module and from the first device, a signal including confirmation that the particular one of the at least one time period is acceptable; determine that a current time has reached the particular one of the at least one ti

Abstract: Users receiving incoming messages may provide their preferences for how they wish to be notified of the incoming messages. A plurality of user devices may be caused to output indicators of the incoming messages, and at least one of the user devices may also provide an acknowledgement of the notification, and the indicators may be cleared.

Abstract: Systems and methods for providing secure communication between an inmate and an outside user are disclosed. In various aspects, account information of both the user and the inmate is stored. A message transmission is received from a first device that includes a header portion and an encrypted payload portion. The system verifies that confidential communication between the inmate and the outside user is permitted based on the header portion and the stored account information. Once verified, the message is transmitted to a second device without decrypting the payload portion of the message.

Abstract: A system and method for optimizing callback times to increase the success rate of callbacks while managing overflow of calls to alternate sites when callbacks are unsuccessful. The system and method use a pacing algorithm to determine when callbacks are likely to be successful from a preferred contact site, routing to alternate callback sites when callbacks are unsuccessful, and preferences for re-routing back to the preferred site when a callback is successful and the agent with whom the caller has interacted previously is available.

Abstract: A system and method for callback management, utilizing a callback cloud, a digital ledger, and smart callback contracts, brokering user to user communications and session establishment using an automated workflow built upon extensible root smart contract templates which can be configured to connect various users and brands. The system may comprise callback cloud, that may further comprise a callback manager, a brand interface server, arm interaction manager, a media server, one or more blockchain digital ledgers, and various smart contracts which are used to autonomously respond to received user requests.