Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing a spam telephone call reducer are disclosed. In one aspect, a method includes the actions of receiving first telephone call data that reflects telephone calls received by a first user and second telephone call data that reflects telephone calls received by a second user. The actions further include comparing the first telephone call data and the second telephone call data. The actions further include determining that the first user received more spam telephone calls than the second user. The actions further include determining a first characteristic of the first user and a second characteristic of the second user. The actions further include determining an action that increases a similarity of the first characteristic to the second characteristic. The actions further include performing the action on the first characteristic.

An alert generator in a communication system for processing a call includes at least one machine learning model generating call classifiers from outputs of an audio signal processor and a natural language processor configure to operate on the call. Heuristic logic is configured to transform the call classifiers into a plurality of weighted sub-metrics for the call, and aggregate normalized Gaussian logic is configured to transform the weighted sub-metrics into a metric control. A threshold analyzer is configured to generate an alert signal to the communication system based on the metric control meeting a condition.

An alert generator in a communication system for processing a call includes at least one machine learning model generating call classifiers from outputs of an audio signal processor and a natural language processor configure to operate on the call. Heuristic logic is configured to transform the call classifiers into a plurality of weighted sub-metrics for the call, and aggregate normalized Gaussian logic is configured to transform the weighted sub-metrics into a metric control. A threshold analyzer is configured to generate an alert signal to the communication system based on the metric control meeting a condition.

Systems and methods forecast inbound telecommunications, and more particularly, analyze real-time and historical call center data, and apply a forecasting model to the data in order to predict inbound call volume. These systems and methods employ tools that manipulate call center data and generate visual representations of metrics pertaining to forecasting call center data via a dashboard.

The invention provides an interrogator for obtaining information associated with a caller identification, such as a telephone number, transmitted within an incoming telephone call including: a receiving device configured to receive the incoming telephone call and to extract the caller identification from the incoming telephone call; an interrogating device configured to receive the extracted caller identification from the receiving device and to interrogate information associated with the caller identification from an external data base, which is configured to operate independently from the user voice communication device for which the incoming telephone call is intended for; and a forwarding device configured to receive and to forward the interrogated information.

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. Other embodiments are disclosed herein.

A system and method for configuring network pairings enabling end-to-end communications between electronic devices is disclosed. The system receives a network pairing request from a requesting device to communicate with a target device. The system identifies historic data associated with the communication object and determines whether an affinity group associated with the requesting device is found. Further, the system determines whether the communication object has a valid permission token associated therewith. If a valid permission token is unavailable, the system checks whether a subscriber filter criteria is met by the requesting device. If the filter criteria is met, system calculates a subscriber access score (SAS) for the requesting device and compares the score to a threshold. When the SAS is greater than the predetermined threshold value, system creates a dynamic network pairing between the requesting device and the target device.

The present invention relates to a method for assisting an interviewing party in deciding a response action in response to an interview between said interviewing party and an interviewee party. The method comprises providing a processing unit and inputting the voice of the interviewee party into the processing unit as an electronic signal, and processing the electronic signal by means of said processing unit in parallel with the interview taking place. The method further includes an anomaly routine comprising a statistically learned model, and by means of said statistically learned model determining a respective number of samples of said sequence of samples being an anomaly of said statistically learned model and returning to said anomaly routine for processing a subsequent number of samples of said sequence of samples by said anomaly routine.

The disclosed system identifies international calling performance issues of a wireless telecommunication network. The system receives network traffic data for international calls including information about call attempts to a country. The system categorizes the country into a major category and a minor category based on the call attempts information. For a subset of countries, and for each key performance indicator in a subset of selected key performance indicators, the system monitors performance using an anomaly detection model to identify an anomaly in network performance, determines an actual value of the key performance indicator for the detected anomaly, and computes a variation value of the determined actual value based on a predicted range of values. The system ranks countries using the computed variation values, to indicate problematic parts of the wireless telecommunication network.

A system and method may classify a plurality of interactions, by: obtaining a plurality of voiceprints of the plurality of interactions, wherein each voiceprint of the plurality of voiceprints represents a speaker participating in an interaction of the plurality of interactions; calculating, for each interaction, a plurality of scores, wherein each score of the plurality of scores is indicative of a similarity between the voiceprint of the interaction and one voiceprint of a set of benchmark voiceprints; calculating, for each interaction, statistics of the scores; and determining that a plurality of interactions pertain to a single cluster of interactions based on statistics of the scores of the interactions in the cluster.