A machine and process for managing restrictions of a wireless device associated with an inmate service account. The machine and process include a kiosk operable to exchange data with the wireless device, including limited-use restrictions related to: an inmate associated with the inmate service account, a correctional facility, and/or a parole requirement. The kiosk may also unlock the wireless device when the inmate is released from the correctional facility by removing the limited-use restrictions from the wireless device.

Embodiments are described for a pattern-based control system that learns and applies device usage patterns for identifying and disabling devices exhibiting abnormal usage patterns. The system can learn a user's normal usage pattern or can learn abnormal usage patterns, such as a typical usage pattern for a stolen device. This learning can include human or algorithmic identification of particular sets of usage conditions (e.g., locations, changes in settings, personal data access events, application events, IMU data, etc.) or training a machine learning model to identify usage condition combinations or sequences. Constraints (e.g., particular times or locations) can specify circumstances where abnormal pattern matching is enabled or disabled. Upon identifying an abnormal usage pattern, the system can disable the device, e.g., by permanently destroying a physical component, semi-permanently disabling a component, or through a software lock or data encryption.

An example method performed by a processing system obtaining a first port-in number for a first mobile device from a first mobile communications service provider, wherein the first port-in number is known to be involved in fraudulent activity, constructing a social graph of communications between the first port-in number and a plurality of other numbers associated with a plurality of other communications devices, identifying, by the processing system, a maximal subgraph of the social graph, wherein the maximal subgraph connects the first port-in number and a subset of the plurality of other numbers that includes those of the plurality of other numbers for which a usage metric is below a predefined threshold for a defined period of time prior to the first port-in number being ported into the first mobile communications service provider, and identifying, by the processing system, a potential fraud ring, based on the maximal subgraph.

Aspects of the subject disclosure may include, for example, a non-transitory, machine-readable medium, comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations including receiving a call; selecting a next carrier to handoff the call; generating a call data record (CDR) for the handoff to the next carrier; encrypting the CDR using a call encryption key, thereby creating an encrypted CDR; encrypting the encrypted CDR using a committee encryption key, thereby creating a double encrypted CDR; recording the double encrypted CDR to a blockchain; and sending the call encryption key to the next carrier. Other embodiments are disclosed.

A system for customizing time limits for inmate communications in a correctional facility is disclosed. The system includes a profile subsystem that stores an inmate profile of the inmate and a communication processing subsystem comprising one or more processors configured to receive data of an inmate communication of an inmate, identify a type of communication device of the inmate and a call recipient of the inmate communication based on the data of the inmate communication, retrieve the inmate profile of the inmate form the profile subsystem, identify a plurality of behaviors of the inmate based on the inmate profile, determine a time limit based on at least one of the type of communication device, the call recipient of the inmate communication, and the plurality of behaviors of the inmate, and assign the time limit to the inmate communication of the inmate.

Detecting fraudulent activity can be a complex, manual process. In this paper, we adapt statistical properties of count data in a novel algorithm to uncover records exhibiting high risk for fraud. Our method identifies shelves, partitioning data under the counts using a Student's t-distribution. We apply this methodology on a univariate dataset including cumulative results from phone calls to a customer service center. Additionally, we extend this technique to multivariate data, illustrating that the same method is applicable to both univariate and multivariate data.

A system for customizing time limits for inmate communications in a correctional facility is disclosed. The system includes a profile subsystem that stores an inmate profile of the inmate and a communication processing subsystem comprising one or more processors configured to receive data of an inmate communication of an inmate, identify a type of communication device of the inmate and a call recipient of the inmate communication based on the data of the inmate communication, retrieve the inmate profile of the inmate form the profile subsystem, identify a plurality of behaviors of the inmate based on the inmate profile, determine a time limit based on at least one of the type of communication device, the call recipient of the inmate communication, and the plurality of behaviors of the inmate, and assign the time limit to the inmate communication of the inmate.

A telecommunications service provider's real time analysis system analyzes communications data to detect potentially fraudulent communications data, where the analysis is performed in real time in the routing path of the communications data. The communications data may include calls (e.g., SS7, VoIP, etc. based calls) and messages (e.g., SMS, MMS, etc.). The real time analysis system rejects potentially fraudulent communications data and non-fraudulent communications data in order to be used in real time in the routing path of the communications data. A rejection by the real time analysis system may cause non-fraudulent communications data to still be sent to the intended destination of the communications data. The real time analysis system can be in the routing path of the communications data without further routing non-fraudulent communications data traffic to the next appropriate hop in the routing path.

There is provided a method for relaying a sensitive information detail during a telephone call between a user's telephone and a recipient's telephone, the user's telephone storing the sensitive information detail therein, the method comprising: initiating a telephone call between the user and the recipient; the user's telephone receiving a predetermined input; during the telephone call, the user's telephone accessing the sensitive information detail stored in the user's telephone based on the predetermined input; and the user's telephone audibly relaying to the recipient the accessed sensitive information detail, wherein audibly relaying to the recipient the accessed sensitive information detail comprises the user's telephone converting, using at least one text-to-speech algorithm, the accessed sensitive information detail to an audible message containing the sensitive information detail and audibly relaying the audible message during the telephone call.

The present disclosure describes techniques that facilitate detecting a Voice over Long-Term Evolution (VoLTE) call request with a recipient call number that lacks a country code. The VoLTE call request may be initiated by a subscriber device while roaming in a VPLMN. Specifically, a Normalization and Alert Policy (NAP) system is described that is configured to analyze the VoLTE call request and determine an intended country code and adjust the recipient call number to include the country code. Further, the NAP system may analyze the adjusted recipient call number to determine whether initiating a VoLTE call in response to the VoLTE call request may trigger an alert condition. An alert condition may relate to determining that the VoLTE call request may initiate a cost-prohibitive VoLTE communication or that the VoLTE call request relates a fraudulent communication.