Directed trajectories through communication decision tree using iterative artificial intelligence

A computer-program product tangibly embodied in a non-transitory machine-readable storage medium, including instructions configured to cause one or more data processors to perform actions including:

• availing an interface for defining communication decision trees through which trajectories corresponding to communication exchanges are extended, the interface including:
• a set of communication visual elements, each communication visual element of the set of communication visual elements representing a particular action that is to be performed when a trajectory has extended to the communication visual element, the set of communication visual elements including:
• a switch visual element that represents a decision action to identify a communication specification using a machine-learning technique;
• and
• a set of communication visual elements, each of the set of communication visual elements representing a particular type of communication channel from a set of types of communication channels;
• and
• a canvas configured to accept positioning of one or more of the set of communication visual elements;
• detecting an update to the canvas, wherein the updated canvas includes:
• a switch visual element positioned at a first position;
• a first communication visual element of the set of communication visual elements positioned at a second position, the first communication visual element representing a first particular type of communication channel, wherein the first communication visual element is connected to the switch visual element;
• a second communication visual element of the set of communication visual elements positioned a third position, the second communication visual element representing a second particular type of communication channel, wherein the second communication visual element is connected to the switch visual element;
• and
• defining a particular communication decision tree based on the updated canvas that, when implemented and in response to detecting that a particular trajectory associated with particular profile data of a user has extended to a particular decision action represented by the switch visual element, triggers:
• retrieving, based on the particular profile data, one or more particular user attributes associated with the user;
• applying a machine-learning model associated with the switch visual element to the one or more particular user attributes to generate an output indicating that that content is to be transmitted across the first particular type of communication channel represented by the first communication visual element, wherein the machine-learning model was trained using user attributes for a set of other users;
• and
• causing, based on the output, the content to be transmitted across the first particular type of communication channel.

A system comprising:

• one or more data processors;
• and
• a non-transitory computer readable storage medium containing instructions which when executed on the one or more data processors, cause the one or more data processors to perform actions including:
• availing an interface for defining communication decision trees through which trajectories corresponding to communication exchanges are extended, the interface including:
• a set of communication visual elements, each communication visual element of the set of communication visual elements representing a particular action that is to be performed when a trajectory has extended to the communication visual element, the set of communication visual elements including:
• a switch visual element that represents a decision action to identify a communication specification using a machine-learning technique;
• and
• a set of communication visual elements, each of the set of communication visual elements representing a particular type of communication channel from a set of types of communication channels;
• and
• a canvas configured to accept positioning of one or more of the set of communication visual elements;
• detecting an update to the canvas, wherein the updated canvas includes:
• a switch visual element positioned at a first position;
• a first communication visual element of the set of communication visual elements positioned at a second position, the first communication visual element representing a first particular type of communication channel, wherein the first communication visual element is connected to the switch visual element;
• a second communication visual element of the set of communication visual elements positioned a third position, the second communication visual element representing a second particular type of communication channel, wherein the second communication visual element is connected to the switch visual element;
• and
• defining a particular communication decision tree based on the updated canvas that, when implemented and in response to detecting that a particular trajectory associated with particular profile data of a user has extended to a particular decision action represented by the switch visual element, triggers:
• retrieving, based on the particular profile data, one or more particular user attributes associated with the user;
• applying a machine-learning model associated with the switch visual element to the one or more particular user attributes to generate an output indicating that that content is to be transmitted across the first particular type of communication channel represented by the first communication visual element, wherein the machine-learning model was trained using user attributes for a set of other users;
• and
• causing, based on the output, the content to be transmitted across the first particular type of communication channel.