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.

Attention weights in a hierarchical attention network indicate the relative importance of portions of a conversation between an individual at one terminal and a computer or a human agent at another terminal. Weighting the portions of the conversation after converting the conversation to a standard text format allows for a computer to graphically highlight, by color, font, or other indicator visible on a graphical user interface, which portions of a conversation led to an escalation of the interaction from an intelligent virtual assistant to a human customer service agent.

A system for a graphical user interface for fraud detection for a call center system includes a processor and a visual display in communication with the processor. The processor causes the visual display to present an identifier corresponding to a communication received; a graphical representation of a threat risk associated with the identifier; a numeric score associated with the threat risk, wherein the numeric score is a weighted score based on a plurality of predetermined factors updated substantially continuously.

Systems and methods for sender profile and/or recipient profile disambiguation and/or confirmation are disclosed. In instances where a sender profile is not indicated by a user sending a communication from a communal device, heuristic data may be utilized to infer the sender profile. Similar heuristic data may also be used when selection of the sender profile is associated with a low confidence level. Heuristic data may also be used to infer the recipient profile when the user does not indicate the recipient profile or when selection of the recipient profile is associated with a low confidence. Various confirmations may result from the sender and recipient profile disambiguation.

A call management system of a call center retrieves from a customer database enterprise customer data associated with an identified customer in a customer call, which may include customer event data, attributions data, and activity event data. The customer database tracks prospects, leads, new business, and purchasers of an enterprise. The system retrieves customer demographic data associated with the identified customer. A predictive model is selected from a plurality of predictive models based on retrieved enterprise customer data. The selected predictive model, including a logistic regression model, and tree-based model, determines a value prediction signal for the identified customer, then classifies the identified customer into a first value group or a second value group. The system routes a customer call classified in the first value group to a first call queue assignment, and routes a customer call classified in the second value group to a second call queue assignment.

Systems and methods for sender profile and/or recipient profile disambiguation and/or confirmation are disclosed. In instances where a sender profile is not indicated by a user sending a communication from a communal device, heuristic data may be utilized to infer the sender profile. Similar heuristic data may also be used when selection of the sender profile is associated with a low confidence level. Heuristic data may also be used to infer the recipient profile when the user does not indicate the recipient profile or when selection of the recipient profile is associated with a low confidence. Various confirmations may result from the sender and recipient profile disambiguation.

A user interface for a fraud detection application includes a visual display; a plurality of panes displayed on the visual display, each pane including an identifier corresponding to a communication received; a graphical representation of a threat risk associated with the identifier; a numeric score associated with the threat risk, wherein the numeric score is a weighted score based on a plurality of predetermined factors updated substantially continuously. The graphical representation may include a status bar indicative of a threat risk associated with the identifier, the threat risk provided by the fraud detection algorithm and based on a weighted score. Each pane may include additional information about the identifier, such as a number of accounts accessed or attempted to be accessed associated with the identifier; a number of days the identifier has been active; a type of channel associated with the identifier; and a number of communications initiated by the identifier over a predetermined period of time. A user may access further information by activating a portion of the visual display to access additional information related to the threat risk. The communication may be a phone call, a chat, a web interaction or the like.

A device is provided. The device includes a processor and a memory configured to store instructions executable by the processor. The processor is configured to execute the instructions to extract context information from displayed data based on an application which is being executed by the device, identify an identifier from the context information, search for at least one recommended contact related to the identifier based on the identifier and a relation graph obtained by inputting information regarding a communication between a plurality of users into a first training model for determining an association between the plurality of users, identify a priority of the at least one recommended contact, and control to display the at least one recommended contact according to the priority.

There is disclosed in one example a mobile telephone, including: a hardware platform including a processor and a memory; a telecommunication transceiver; and instructions encoded within the memory to instruct the processor to: identify a call made via the telecommunication transceiver; analyze the call and assign the call a predicted local reputation according to the analysis, including a legitimacy confidence score; if the legitimacy confidence score is less than a first threshold, terminate the call; if the legitimacy confidence score is greater than a second threshold, cease analysis of the call; and if the legitimacy confidence score is between the first and second thresholds, continue analysis of the call.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing a spoofed telephone call identifier are disclosed. In one aspect, a method includes the actions of receiving, by a first computing device, data indicating a placement of a telephone call from a second computing device to a third computing device, wherein the data includes a phone number of the second computing device. The actions further include determining characteristics of the phone number of the second computing device. The actions further include, based on the characteristics of the phone number of the second computing device, determining a likelihood that the phone number of the second computing device is spoofed. The actions further include, based on the likelihood that the phone number of the second computing device is spoofed, determining whether to transmit a notification of the telephone call to the third computing device.