Artificial Intelligence Based System And Method For Controlling Virtual Agent Task Flow

A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to:

• perform a task cycle, wherein the task cycle includes performing the following operations for at least one user:
• receive a user utterance from a user, the utterance including a first task;
• use artificial intelligence to identify the first task from the user utterance;
• obtain a set of rules related to a plurality of tasks, wherein the plurality of tasks includes at least the first task and the set of rules comprise one or more of the following:
• mapping context variables from one task to another task within the plurality of tasks;
• defining one or more tasks of the plurality of tasks as predecessors of one or more of the other tasks of the plurality of tasks;
• invoking a task of the plurality of tasks based on the value of a context variable;
• and
• adding constraints on the plurality of tasks, such that either:
• (1) one task of the plurality of tasks is mutually exclusive with another task of the plurality of tasks or (2) one task of the plurality of tasks is compulsory with another task of the plurality of tasks;
• and
• execute the first task;
• run a probabilistic graphical model on the plurality of tasks to determine a second task based on the first task;
• suggest to the user the second task;
• and
• monitor the user's response to the suggestion of the second task.

A system for controlling a virtual agent by organizing a task flow, comprising:

• one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to:
• perform a task cycle, wherein the task cycle includes performing the following operations for at least one user:
• receive a user utterance from a user, the utterance including a first task;
• use artificial intelligence to identify the first task from the user utterance;
• obtain a set of rules related to a plurality of tasks, wherein the plurality of tasks includes at least the first task and the set of rules comprise one or more of the following:
• mapping context variables from one task to another task within the plurality of tasks;
• defining one or more tasks of the plurality of tasks as predecessors of one or more of the other tasks of the plurality of tasks;
• invoking a task of the plurality of tasks based on the value of a context variable;
• and
• adding constraints on the plurality of tasks, such that either:
• (1) one task of the plurality of tasks is mutually exclusive with another task of the plurality of tasks or (2) one task of the plurality of tasks is compulsory with another task of the plurality of tasks;
• and
• execute the first task;
• run a probabilistic graphical model on the plurality of tasks to determine a second task based on the first task;
• suggest to the user the second task;
• and
• monitor the user's response to the suggestion of the second task.