Methods and systems for identifying communication sources across channels
Systems and method are provided for identifying a source of communications for improved communications. A computing device may receive a communication from a first device over a first time interval and extract a set of features from the communication. The features may correspond to characteristics indicative of how the communication was generated over the first time interval. The computing device may execute a machine-learning model using the set of features to generate a predicted identity associated with a source of the communication. A response can be generated based on the predicted identify and transmitted to the first device.
1 . A method comprising:
receiving, over a time interval, a communication via a communication channel from a device;
extracting a set of features from the communication, wherein features of the set of features correspond to characteristics indicative of how portions of the communication are generated by the device over the time interval;
executing a machine-learning model using the set of features, the machine-learning model generating a predicted identity of a user of the device;
facilitating a connection of a terminal device to a communication session based on the predicted identity of the user, wherein the terminal device is selected based on a previous communication session between the terminal device and the user, and wherein the terminal device is configured to communicate with the device over the communication channel; and
facilitating a transmission of a response to the communication by the terminal device via the communication channel, the response being tailored to the user of the device based on historical communications associated with the device.
2 . The method of claim 1 , further comprising:
generating an interface based on the predicted identity of the user of the device, the interface including additional information associated with the user of the device, wherein the additional information includes an identifier of the user of the device.
3 . The method of claim 1 , further comprising:
generating an interface based on the predicted identity of the user of the device, the interface including additional information associated with the user of the device, wherein the additional information includes an identification of other communications received from the user of the device.
4 . The method of claim 1 , wherein the communication includes alphanumeric characters.
5 . The method of claim 1 , wherein the communication includes voice communications.
6 . The method of claim 1 , wherein the set of features includes characteristics of user interaction derived during one or more web-browsing sessions.
7 . The method of claim 1 , further comprising:
determining that a confidence value generated by the machine-learning model is less than a threshold; and
executing a two-factor authentication process by transmitting a sequence via an alternative communication channel to verify the predicted identity.
8 . A system comprising:
one or more processors; and
a machine-readable storage medium storing instructions that when executed by the one or more processors, cause the one or more processors to perform operations including:
receiving, over a time interval, a communication via a communication channel from a device;
extracting a set of features from the communication, wherein features of the set of features correspond to characteristics indicative of how portions of the communication are generated by the device over the time interval;
executing a machine-learning model using the set of features, the machine-learning model generating a predicted identity of a user of the device;
facilitating a connection of a terminal device to a communication session based on the predicted identity of the user, wherein the terminal device is selected based on a previous communication session between the terminal device and the user, and wherein the terminal device is configured to communicate with the device over the communication channel; and
facilitating a transmission of a response to the communication by the terminal device via the communication channel, the response being tailored to the user of the device based on historical communications associated with the device.
9 . The system of claim 8 , wherein the operations further include:
generating an interface based on the predicted identity of the user of the device, the interface including additional information associated with the user of the device, wherein the additional information includes an identifier of the user of the device.
10 . The system of claim 8 , wherein the operations further include:
generating an interface based on the predicted identity of the user of the device, the interface including additional information associated with the user of the device, wherein the additional information includes an identification of other communications received from the user of the device.
11 . The system of claim 8 , wherein the communication includes alphanumeric characters.
12 . The system of claim 8 , wherein the communication includes voice communications.
13 . The system of claim 8 , wherein the set of features includes characteristics of user interaction derived during one or more web-browsing sessions.
14 . The system of claim 8 , further comprising:
determining that a confidence value generated by the machine-learning model is less than a threshold; and
executing a two-factor authentication process by transmitting a sequence via an alternative communication channel to verify the predicted identity.
15 . A non-transitory machine-readable storage medium storing instructions that when executed by one or more processors, cause the one or more processors to perform operations including:
receiving, over a time interval, a communication via a communication channel from a device;
extracting a set of features from the communication, wherein features of the set of features correspond to characteristics indicative of how portions of the communication are generated by the device over the time interval;
executing a machine-learning model using the set of features, the machine-learning model generating a predicted identity of a user of the device;
facilitating a connection of a terminal device to a communication session based on the predicted identity of the user, wherein the terminal device is selected based on a previous communication session between the terminal device and the user, and wherein the terminal device is configured to communicate with the device over the communication channel; and
facilitating a transmission of a response to the communication by the terminal device via the communication channel, the response being tailored to the user of the device based on historical communications associated with the device.
16 . The non-transitory machine-readable storage medium of claim 15 , wherein the operations further include:
generating an interface based on the predicted identity of the user of the device, the interface including additional information associated with the user of the device, wherein the additional information includes an identifier of the user of the device.
17 . The non-transitory machine-readable storage medium of claim 15 , wherein the operations further include:
generating an interface based on the predicted identity of the user of the device, the interface including additional information associated with the user of the device, wherein the additional information includes an identification of other communications received from the user of the device.
18 . The non-transitory machine-readable storage medium of claim 15 , wherein the communication includes alphanumeric characters.
19 . The non-transitory machine-readable storage medium of claim 15 , wherein the communication includes voice communications.
20 . The non-transitory machine-readable storage medium of claim 15 , wherein the set of features includes characteristics of user interaction derived during one or more web-browsing sessions.