Ambiguity resolution in digital paper-based interaction

A system, comprising:

• a memory;
• and
• at least one processor coupled to the memory, the at least one processor configured to:
• receive one or more context objects via a session for one or more applications, wherein the one or more context objects comprises a context and one or more associated objects derived from interactions engaged in by a user with the one or more applications;
• create one or more query models comprising one or more query tuples of one or more objects comprising at least a first subject, a first user intent, and first criteria associated with the one or more context objects;
• store the one or more query models;
• receive a symbolic instruction from the user, wherein the symbolic instruction comprises non-natural language inputs from the user;
• analyze the symbolic instruction to determine the first user intent and a second user intent;
• retrieve a current context object, wherein the current context object is a delta over the one or more stored context objects in the session;
• determine a current query tuple comprising at least an object for a second subject, the second user intent, and second criteria based on the symbolic instruction;
• determine that the object for the subject in the current query tuple associated with the current context object matches the one or more objects for the subject associated with the one or more context objects in the one or more query models;
• model a new query model based on the current context object and the current query tuple;
• and
• determine a resolved user intent of the symbolic instruction from between the first user intent and the second user intent based on the new query model.

A non-transitory computer-readable device having instructions stored thereon that, when executed by at least one computing device, cause the at least one computing device to perform operations comprising:

• receiving, by a user experience, one or more context objects via a session for one or more applications, wherein the one or more context objects comprises a context and one or more associated objects derived from interactions engaged in by a user with the one or more applications;
• creating one or more query models comprising one or more query tuples of one or more objects comprising at least a first subject, a first user intent, and first criteria associated with the one or more context objects;
• storing the one or more query models;
• receiving a symbolic instruction from the user, wherein the symbolic instruction comprises non-natural language inputs from the user;
• analyzing the symbolic instruction to determine the first user intent and a second user intent;
• retrieving a current context object, wherein the current context object is a delta over the one or more stored context objects in the session;
• determining a current query tuple comprising at least an object for a second subject, the second user intent, and second criteria based on the symbolic instruction;
• determining that the object for the subject in the current query tuple associated with the current context object matches the one or more objects for the subject associated with the one or more context objects in the one or more query models;
• modeling a new query model based on the current context object and the current query tuple;
• and
• determining a resolved user intent of the symbolic instruction from between the first user intent and the second user intent based on the new query model.