Abstract: A method starts with processor retrieving member's initial context data. Processor receives a string that is a transcribed utterance or an electronic message from the communication session established between member client device and agent client device. Processor determines potential relationships between the member and a patient that is the subject of the string by processing the string using Long Short-Term Memory (LSTM) neural networks to generate a plurality of relationship values. Relationship values are associated with relationship types. Processor generates weight values based on member's initial context data for each of the plurality of relationship types, and generates probability values for the relationship types based on the relationship values and the weight values. Processor narrows the potential relationships, generates relationship data that includes the narrowed potential relationships, and causes the relationship data to be displayed by the agent client device.

Abstract: Methods and systems for communicating active voice calls through messaging systems are disclosed. Active voice calls are identified as connected between a call participant and a first account of a messaging system. A set of instructions is established and associated with the active voice call that are executable to cause display of a call user interface for accounts of the messaging system. A message including a reference to the set of instructions for the active voice call is generated and transmitted to a second account of the messaging system through the messaging system using messaging functions of the messaging system to cause display of the call user interface to the second account, allowing the second account to interact with the active voice call.

Abstract: Systems, methods, and computer-readable media are disclosed for dynamic selection of a primary wireless earbud device. In one embodiment, an example system may include a first wireless earbud device having first memory and at least one first processor configured to access the first memory. The at least one first processor may execute computer-executable instructions to determine a first RSSI value for a first connection to a device, determine a first packet error rate value for the first connection, and determine a first link quality score using the first RSSI value and the first packet error rate value. The at least one first processor may execute computer-executable instructions to determine that the first link quality score is less than or equal to a handover threshold, disconnect from the device, and cause a second wireless earbud device to establish a second connection to the device.

Abstract: Tangible, non-transitory, machine-readable media include instructions that cause a processor to receive a first indication that a user is attempting to communicate with a provider, and intercept communication between the user and the provider based on the first indication being received. The instructions also cause the processor to send user information to a provider application server based on the first indication being received, and display a visual interface that establishes communication with the relevant provider department or performs a transaction based on the first indication being received. The instructions further cause the processor to receive a second indication associated with performing the action associated with the provider via the visual interface; and performing the action based on the second indication being received.

Abstract: Systems and methods for call handling optimization of a call center are disclosed. A system is configured to: obtain a plurality of agent demand variables; obtain an indication of available agents that are associated with a plurality of skills; generate a multi-skill routing matrix depicting a routing problem from the agent demand variables and the available agents; deconstruct the multi-skill matrix into one or more band routing matrices; and identify, for each band routing matrix, a number of agents from the available agents to be used in solving the band routing matrix. Identifying the number of agents includes recursively simulating a plurality of possible routing solutions, measuring a quality metric for each simulation, and reducing the range of available agents based on the quality metric. The system may indicate the number of agents to be used for each routing sub-problem (which may be at the staff group level).

Abstract: To enable analysis of the performance of a customer contact center handling interactions across multiple types of communication channels, a system is provided that collects and analyzes data across the multiple channels and allows a user, such as an analyst, to analyze customer journeys that comprise multiple interactions, or contacts, across multiple communication channel types. That analysis can be used to identify journeys with similar, perhaps problematic, characteristics and provide the analyst user with the ability to examine the collected data for each identified journey individually. Once a journey is selected, the system displays the collected data in a coordinated display of journey timeline, text history, and sequence of automatically detected significant events.

Abstract: A dialogue device of a dialogue system relating to provision of a response to an inquiry from a user terminal includes an input unit that acquires the inquiry from the user terminal, a transmission unit that connects the user terminal and an operator terminal responding to the inquiry in accordance with the inquiry, an output unit that outputs questions for ascertaining details of the inquiry to the user terminal before connection made by the transmission unit, and a determination unit that determines a mode of the questions made by the output unit in accordance with an operating status of the operator terminal that can respond to the inquiry.

Abstract: A system for providing dialogue monitoring and communications is disclosed. The system may comprise a data access interface, a processor, and an output interface. The data access interface may receive data associated with a customer-initiated event from a data source. The processor may identify a category type and a stage associated with the customer-initiated event. The processor may also calculate a metric using an artificial intelligence (AI) based technique. The processor may also generate a recommendation based on the calculated metric, wherein the recommendation, which when acted upon, improves a customer journey and experience. The output interface may transmit, to a user device, at least one of the customer-initiated event, the category type, the stage, the metric, and the recommendation in a dashboard.

Abstract: Techniques are described that update a caller on call progress status using various effects based on a likelihood that the call will connect with the callee, and/or a likelihood that the caller will prematurely terminate the call. In some examples, a machine-learned model may determine a likelihood that a call will connect based on conditions associated with the callee. In some cases, a machine-learned model may determine a likelihood that a call will be prematurely terminated by the caller based on conditions associated with the caller. Animations, haptic outputs, sounds, and/or other content may be used to indicate likelihood of the call connecting to the caller.

Abstract: Communications channels between systems can be managed such that unnecessary use of the channels is limited. A computer system can initiate a request to establish communications channels between a client device and the computer system. A notification is sent to the client device, which causes the client device to prompt the user to either accept the request or reschedule the requested establishing of the communications channel.

Abstract: A cloud based in-line survey system that works in conjunction with conventional interactive voice response systems. The survey system employs hardware and software that are stored and/or facilitated apart from that of the host interactive voice response system (“IVR”). The survey system uses a cloud based data collection model, the “survey data model.” The functionality of the survey data model is hosted and/or accessible through an on-line user interface or viewer, which provides the functionality of the survey model to the enterprise users and survey participants. The survey system can be accessed indirectly by the enterprise IVR transferring the participant to a survey model at the end of a service call, or by requesting the participant to call in directly to the survey system.

Abstract: A method can be used for the generation of personalized Profile Package data in integrate circuit cards. A table includes data records corresponding to subscriptions to be generated. Each record includes personalization fields to store different types of personalization values. For a given subscription, a file for the Profile Package is in an ASCII format and includes fields to be personalized corresponding to one or more of the fields to store different types of personalization values. The file for the Profile Package in the ASCII format is converted into a hexadecimal code. An offset table is calculated for the given subscription indicating for each field to be personalized a corresponding offset in the hexadecimal profile. The personalization values from the personalization fields are substituted in the corresponding personalization fields to be personalized.

Abstract: An audio signal processing device comprises: a receiver for receiving an input audio signal; a processor for generating loudness metadata corresponding to the input audio signal; and an outputter for transmitting the loudness metadata generated by the processor. The processor is configured to acquire loudness information analyzed from input content, acquires loudness information about the input audio signal by measuring the loudness of the input audio signal, generates the loudness metadata by converting the loudness information, and transmits, through the outputter, the generated loudness metadata to an output device for outputting the input audio signal.

Abstract: Method starts with processing, by a processor, audio signal to generate audio caller utterance. Processor generates an agent action ranking score associated with the audio caller utterance and determines whether the agent action ranking score is below a minimum threshold. In response to determining that the agent action ranking score is below the minimum threshold, processor generates a transcribed caller utterance using a speech-to-text processor and generates an identified task based on the transcribed caller utterance. Using the transcribed caller utterance and a task-specific agent coaching neural network associated with the identified task, processor generates an ideal response. Processor generates a feedback result and causes the feedback result to be displayed on a display device of the agent client device. Other embodiments are disclosed herein.

Abstract: A computer retrieves a dialog information records of the active call of the first operator. The computer extracts features from the dialog information records. The computer determines a feature vector from the extracted features and determines a transfer probability value based on the feature vector and previous call transfers to the second operator.

Abstract: An intelligent interface responds to text messages, which in a particular embodiment are addressed to a landline phone number. An IP network interface receives requests including a source phone number, message content and the destination phone number. The intelligent interface includes access to a serialized intent file created by a vectorizer. An intent classifier determines one intent from the serialized intent file based on the received message content. A response is generated according to the one intent. A reply generator generates a reply including the source phone number as a destination, the landline phone number as a source and the response.

Abstract: A method for providing coachable events for agents within a call center is provided. Behavior score waveforms for interactions and behaviors can be determined. Events can be identified in the behavior score waveforms within identified durations, and a relevancy of one or more events to one or more behaviors can be determined.

Abstract: A method of voice call diversion includes detecting an incoming voice call communication from a calling device, identifying an alternate communication option, providing the alternate communication option to the calling device, detecting a selection of the alternate communication option from the calling device, and diverting the incoming voice call communication so as to utilize the selected alternate communication option.

Abstract: Embodiments automatically establish a communication link with a conference platform using data received from a user device of a user. A conferencing device may interact with a user device to initiate a data transmission from the user device. An application on the user device may scan the contents of the user device for information associated one or more conference calls scheduled for a current time period. Upon identifying a matching conference call, the user device may transmit data associated with the conference call to the conferencing device. The application on the user device or the conferencing device may extract the call-in details (e.g. telephone number, conference code, conference PIN, URL or some other link to the conference) from the information associated with the conference call. The conferencing device may automatically initiate a call (e.g. establish the communication link) with the conference platform using the call-in details.

Abstract: A contact center system for performing call progress analysis including tone and speech classification according to an embodiment includes at least one processor and at least one memory comprising a plurality of instructions stored thereon that, in response to execution by the at least one processor, causes the contact center system to determine a cumulative average of an entropy of an audio signal received by the contact center system, determine a cumulative average power spectral amplitude and a cumulative average spectral entropy of the audio signal, calculate a difference measure of the audio signal as a difference between the cumulative average of the entropy and the cumulative average spectral entropy, distinguish tones from speech of the audio signal based on the difference measure, and process one or more tones of the audio signal in response to identification of the one or more tones in the audio signal.