A digital messaging system is arranged to aggregate digital messages from a plurality of sources, the system comprising context extraction means arranged to extract context information from the messages and classification means arranged to classify the messages according to the extracted context information.

Secure system and method of detecting and preventing inmate to inmate message relays. A system and method which monitors inmate communications for similar phrases that occur as part of two or more separate inmate messages. These similar phrases may be overlapping in real time as in a conference call or can occur at separate times in separate messages. The communications that appear similar are assigned a score and the score is compared to a threshold. If the score is above a certain threshold, the communication is flagged and remedial actions are taken. If the flagged communication contains illegal matter then the communication can be disconnected or restricted in the future.

Techniques are provided for evaluating multiple machine learning models to identify issues with a communication. One method comprises applying an audio signal associated with a communication to at least two of: (i) a trigger word analysis module that evaluates contextual information to determine if a trigger word is detected in the audio signal; (ii) an audio activity pattern analysis module that determines if a silence pattern anomaly is detected; and (iii) a communication application analysis module that evaluates features provided by a communication application relative to applicable thresholds; and combining results of the at least two of the trigger word analysis module, the audio activity pattern analysis module and the communication application analysis module to identify a communication issue. The combining may evaluate an accuracy of the trigger word analysis module, the audio activity pattern analysis module and/or the communication application analysis module to combine the results.

A system and method for detecting and preventing PSTN fraud and abuse in real time includes a detection engine and a call management engine. The system includes at least one user record, at least one call data record, at least one fraud score record, and at least one remediation record. A call management engine enables users to establish VoIP calls connections to destination phone numbers. A fraud detection engine screens VoIP call connections to detect potential fraud and generates fraud records and remediation records when potential fraud is detected. The fraud detection engine may additionally direct the call management to terminate a VoIP call connection.

Systems and methods for dissemination of information from a controlled-environment facility may offer a non-resident and/or resident an option to subscribe to notifications about a particular resident of a controlled-environment facility and/or notifications about the controlled-environment facility. Identification and contact information may be accepted from the non-resident to establish the non-resident as a paid or non-paid subscriber to notifications about the resident and/or the controlled-environment facility. A determination may be made, or an indication may be received from a controlled-environment facility administration and management system, when information about the resident hosted by the controlled-environment administration and management system changes and/or when a change is made to information about the controlled-environment facility. As a result, the subscriber is contacted and notified of the change(s).

Secure system and method of detecting and preventing inmate to inmate message relays. A system and method which monitors inmate communications for similar phrases that occur as part of two or more separate inmate messages. These similar phrases may be overlapping in real time as in a conference call or can occur at separate times in separate messages. The communications that appear similar are assigned a score and the score is compared to a threshold. If the score is above a certain threshold, the communication is flagged and remedial actions are taken. If the flagged communication contains illegal matter then the communication can be disconnected or restricted in the future.

A Lawful Interception (LI) method performed between a network and a terminal operating in Device-to-Device (D2D) communication mode to intercept D2D communication content are provided. The lawful interception method includes a D2D communication terminal according to the present disclosure includes activating a lawful interception function, storing information exchanged with a peer terminal through D2D communication, and transmitting a lawful interception report including the stored information.

A method and system for discovering and locating the source of unwanted communication origination in a communications network, the method comprising compiling a communication campaign database storing data of one or more communication campaigns along with automatically identified instances of those campaigns, and simultaneously or sequentially matching those instances against known communication traffic of a set of cooperating telecommunication carriers. The one or more communications campaigns include a grouping of related fingerprints and patterns that identify a sequence of characters, audio or video associated with instances of a same likely campaigns, either legitimate or illegitimate/fraudulent.

Agencies issue recording devices to personnel for administrating and monitoring controlled calls during the course of their duties. To provide flexible capabilities to agencies, a virtual number is provisioned and configured to enable an operator to administrate controlled calls without dedicated recording devices. Using the virtual number, the operator may setup a controlled call between a victim and a baddie. The victim is contacted via the virtual number by the operator and optionally informed about the controlled call process. In turn, the baddie is contacted using number information of the victim's phone and connected with the victim. Call audio between the victim and baddie is transmitted to the operator. When necessary, the operator may terminate the call remotely from the telephonic device the operator used to setup the call.

Novel tools and techniques might provide for implementing call monitoring, and, in particular embodiments, to methods, systems, apparatuses, and computer software for implementing self-learning corrections facility call monitoring. In some embodiments, a method might comprise an automated call monitor monitoring a voice or video call between a call participant and a prison inmate, and analyzing at least one of conversation content of the call, voice characteristics of the call participant and/or the prison inmate, and/or (for video calls) body language of the parties to the call, to determine whether the conversation content, voice characteristics, and/or body language are indicative of impermissible content and/or impermissible conduct (i.e., indicative of past, present, and/or future criminal behavior or acts, and the like). The automated call monitor might flag calls that present such indications of impermissible content and/or conduct, for review by corrections facility personnel, and might self-learn based on input by such personnel.