Abstract: Systems and methods for detecting indications of a scam caller are disclosed. Call data, such as call audio, is received and used to create a training dataset. Using the training dataset, a machine learning model is trained to detect indications of a scam caller in a phone call. An Interactive Voice Response (IVR) model is trained or configured, using voice samples of speech of a subscriber of a telecommunications service provider, to simulate speech and conversation of the subscriber. A conversational agent is generated using the IVR model and the trained machine learning model. The conversational agent receives a phone call, engages a caller in simulated conversation, and detects indications of whether the caller is a likely scam caller. If the caller is determined to be a likely scam caller, an alert can be generated and/or the call can be disconnected.

Abstract: Systems and methods for detecting indications of a scam caller are disclosed. Call data, such as call audio, is received and used to create a training dataset. Using the training dataset, a machine learning model is trained to detect indications of a scam caller in a phone call. An Interactive Voice Response (IVR) model is trained or configured, using voice samples of speech of a subscriber of a telecommunications service provider, to simulate speech and conversation of the subscriber. A conversational agent is generated using the IVR model and the trained machine learning model. The conversational agent receives a phone call, engages a caller in simulated conversation, and detects indications of whether the caller is a likely scam caller. If the caller is determined to be a likely scam caller, an alert can be generated and/or the call can be disconnected.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for automatically generating enhanced caller identification data are disclosed. In one aspect, a method includes the actions of receiving telephone call placement data that indicates the placement of a telephone call from a calling party to a called party. The actions further include receiving caller identification data. The actions further include accessing first telephone call data that reflects characteristics of telephone calls placed and received by the calling party. The actions further include based on the first telephone call data and the identity of the calling party, determining additional data to combine with the caller identification data. The actions further include generating enhanced caller identification data by combining the additional data with the caller identification data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for automatically generating enhanced caller identification data are disclosed. In one aspect, a method includes the actions of receiving telephone call placement data that indicates the placement of a telephone call from a calling party to a called party. The actions further include receiving caller identification data. The actions further include accessing first telephone call data that reflects characteristics of telephone calls placed and received by the calling party. The actions further include based on the first telephone call data and the identity of the calling party, determining additional data to combine with the caller identification data. The actions further include generating enhanced caller identification data by combining the additional data with the caller identification data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for managing a phone number list are disclosed. In one aspect, a method includes the actions of receiving, by a computing device, telephone call data that reflects characteristics of telephone calls placed and received by a first user. Based on the telephone call data, the actions further include generating, by the computing device, a first telephone number whitelist for the first user. The actions further include determining, by the computing device, whether to combine the first telephone number whitelist and a second telephone number whitelist for a second user. The actions further include storing, by the computing device, the first telephone number whitelist or the combined telephone number whitelist in association with the first user.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for automatically generating enhanced caller identification data are disclosed. In one aspect, a method includes the actions of receiving telephone call placement data that indicates the placement of a telephone call from a calling party to a called party. The actions further include receiving caller identification data. The actions further include accessing first telephone call data that reflects characteristics of telephone calls placed and received by the calling party. The actions further include based on the first telephone call data and the identity of the calling party, determining additional data to combine with the caller identification data. The actions further include generating enhanced caller identification data by combining the additional data with the caller identification data.

Abstract: Systems and methods for detecting indications of a scam caller are disclosed. Call data, such as call audio, is received and used to create a training dataset. Using the training dataset, a machine learning model is trained to detect indications of a scam caller in a phone call. An Interactive Voice Response (IVR) model is trained or configured, using voice samples of speech of a subscriber of a telecommunications service provider, to simulate speech and conversation of the subscriber. A conversational agent is generated using the IVR model and the trained machine learning model. The conversational agent receives a phone call, engages a caller in simulated conversation, and detects indications of whether the caller is a likely scam caller. If the caller is determined to be a likely scam caller, an alert can be generated and/or the call can be disconnected.

Abstract: Systems and methods for detecting indications of a scam caller are disclosed. Call data, such as call audio, is received and used to create a training dataset. Using the training dataset, a machine learning model is trained to detect indications of a scam caller in a phone call. An Interactive Voice Response (IVR) model is trained or configured, using voice samples of speech of a subscriber of a telecommunications service provider, to simulate speech and conversation of the subscriber. A conversational agent is generated using the IVR model and the trained machine learning model. The conversational agent receives a phone call, engages a caller in simulated conversation, and detects indications of whether the caller is a likely scam caller. If the caller is determined to be a likely scam caller, an alert can be generated and/or the call can be disconnected.