SYSTEM AND METHOD FOR PROVIDING SYSTEM-INITIATED DIALOG BASED ON PRIOR USER INTERACTIONS
In certain implementations, a system-initiated dialog with a user may be provided based on prior user interactions. In an implementation, context information determined based on one or more prior interactions of the user with the system may be obtained. A dialog-initiation opportunity may be detected based on the context information. A natural language dialog with the user may be initiated based on the dialog-initiation opportunity. In an implementation, the one or more prior interactions of the user may comprise one or more prior conversations between the user and the system. At least one of the one or more prior conversations may, for example, comprise a natural language utterance of the user and a natural language response of the system to the natural language utterance.
1 . A method for providing system-initiated dialog with a user based on one or more prior user interactions, the method being implemented on a computer system having one or more physical processors executing computer program instructions which, when executed, perform the method, the method comprising:
obtaining, by the computer system, context information determined based on one or more prior interactions of the user with the system;
detecting, by the computer system, a dialog-initiation opportunity based on the context information; and
initiating, by the computer system, a natural language dialog with the user based on the dialog-initiation opportunity.
2 . The method of claim 1 , wherein the context information comprises a preference related to one or more of an estimated time of arrival, an amount of intermediate stops while en route to a destination, avoidance of traffic, a contact, preferred routes, frequently requested tasks, a user need, or user interests.
3 . The method of claim 1 , wherein the one or more prior interactions of the user comprises one or more prior conversations between the user and the system, and wherein at least one of the one or more prior conversations comprises a natural language utterance of the user and a natural language response of the system to the natural language utterance.
4 . The method of claim 1 , wherein initiating the natural language dialog with the user comprises providing, based on the dialog-initiation opportunity, a speech-based output that includes a question for the user related to the context information.
5 . The method of claim 1 , wherein initiating the natural language dialog with the user further comprises providing, based on the dialog-initiation opportunity, a non-voice output related to the context information.
6 . The method of claim 1 , further comprising:
obtaining, by the computer system, a current location associated with the user;
determining, by the computer system, an advertisement based on the current location and the dialog-initiation opportunity; and
providing, by the computer system, the advertisement for presentation to the user, wherein the initiated dialog is related to the advertisement.
7 . The method of claim 6 , wherein determining the advertisement comprises selecting, from one or more available advertisements, the advertisement based on the current location and the dialog-initiation opportunity.
8 . The method of claim 1 , wherein detecting the dialog-initiation opportunity comprises detecting the dialog-initiation opportunity based on (i) the context information and (ii) one or more of community information, traffic information, weather information, event information, user schedule information, personal user information, or user location information.
9 . The method of claim 1 , wherein the context information indicates a user need determined based on the one or more prior interactions of the user with the system, and wherein detecting the dialog-initiation opportunity comprises detecting an opportunity to stop en route to address the user need.
10 . The method of claim 1 , wherein the context information indicates a preferred contact determined based on the one or more prior interactions of the user with the system, and wherein detecting the dialog-initiation opportunity comprises detecting an opportunity to stop at a location related to the preferred contact while en route to another location.
11 . The method of claim 1 , wherein the context information indicates a preference to avoid traffic determined based on the one or more prior interactions of the user with the system, and wherein detecting the dialog-initiation opportunity comprises detecting an opportunity to reroute the current route to avoid traffic.
12 . The method of claim 1 , wherein the context information indicates a preference related to frequently requested tasks and/or user interests, determined based on the one or more prior interactions of the user with the system, and wherein detecting the dialog-initiation opportunity comprises detecting an opportunity to attend, listen to, watch, and/or record an event.
13 . The method of claim 1 , wherein the context information indicates one or more of a preference related to a contact, a route, a frequently requested task, a user need, or a user interest, determined based on the one or more prior interactions of the user with the system, and wherein detecting the dialog-initiation opportunity comprises detecting an opportunity to stop at a location related to one or more of the preferred contact, the route, the frequently requested task, the user need, or the user interest while en route to another location.
14 . A system for providing system-initiated dialog with a user based on one or more prior user interactions, the system comprising:
one or more physical processors programmed with computer program instructions which, when executed, cause the one or more physical processors to:
obtain context information determined based on one or more prior interactions of the user with the system;
detect a dialog-initiation opportunity based on the context information; and
initiate a natural language dialog with the user based on the dialog-initiation opportunity.
15 . The system of claim 14 , wherein the context information comprises a preference related to one or more of an estimated time of arrival, an amount of intermediate stops while en route to a destination, avoidance of traffic, a contact, preferred routes, frequently requested tasks, a user need, or user interests.
16 . The system of claim 14 , wherein the one or more prior interactions of the user comprises one or more prior conversations between the user and the system, and wherein at least one of the one or more prior conversations comprises a natural language utterance of the user and a natural language response of the system to the natural language utterance.
17 . The system of claim 14 , wherein the initiation of the natural language dialog further comprises providing, based on the dialog-initiation opportunity, a speech-based output that includes a question for the user related to the context information.
18 . The system of claim 14 , wherein the one or more physical processors are further caused to:
obtain a current location associated with the user;
determine an advertisement based on the current location and the dialog-initiation opportunity; and
provide the advertisement for presentation to the user, wherein the initiated dialog is related to the advertisement.
19 . The system of claim 14 , wherein the dialog-initiation opportunity is detected based on (i) the context information and (ii) one or more of community information, traffic information, weather information, event information, user schedule information, personal user information, or user location information.
20 . The system of claim 14 , wherein the context information indicates one or more of a preference related to a contact, route, frequently requested tasks, user needs, or user interests, determined based on the one or more prior interactions of the user with the system, and wherein the detection of the dialog-initiation opportunity comprises the detection of an opportunity to stop at a location related to one or more of the preferred contact, route, frequently requested tasks, user needs, or user interests while en route to another location.