Providing relevant messages to an automotive virtual assistant

Abstract

A method of providing relevant messages to an automotive virtual assistant is provided. The method includes receiving a spoken utterance and corresponding first geolocation information detected by a subsystem of a first automobile, parsing the spoken utterance to determine concepts and storing the concepts in a concept database indexed by the corresponding first geolocation information. The method further includes receiving second geolocation information detected by a subsystem of a second automobile, searching the concept database for an index based on the second geolocation information to find a stored concept of the stored concepts, searching a natural language expression database using the stored concept as an index to find an assistive natural language expression, wherein the assistive natural language expression includes a constituent part, and sending the assistive natural language expression to the second automobile with the stored concept in place of the constituent part.

What is claimed is: 
     
         1 . A method of providing relevant messages to an automotive virtual assistant, the method comprising:
 receiving a spoken utterance and corresponding first geolocation information detected by a subsystem of a first automobile;   parsing the spoken utterance to determine concepts;   storing the concepts in a concept database indexed by the corresponding first geolocation information;   receiving second geolocation information detected by a subsystem of a second automobile;   searching the concept database for an index based on the second geolocation information to find a stored concept of the stored concepts;   searching a natural language expression database using the stored concept as an index to find an assistive natural language expression, wherein the assistive natural language expression includes a constituent part; and   sending the assistive natural language expression to the second automobile with the stored concept in place of the constituent part.   
     
     
         2 . The method of  claim 1 , further comprising:
 storing an action indicator in an action database indexed by the first geolocation information, the action indicator corresponding to the spoken utterance and the first geolocation information; and   searching the action database for an index based on the second geolocation information to find the action indicator,   wherein the sending of the assistive natural language expression is conditional based on the action indicator.   
     
     
         3 . The method of  claim 1 , further comprising:
 determining a motion vector associated with the second automobile; and   computing a forward projection of the second geolocation information based on the motion vector,   wherein the index based on the second geolocation information is the forward projection of the second geolocation.   
     
     
         4 . The method of  claim 1 , wherein the assistive natural language expression sent to the second automobile comprises an advertisement. 
     
     
         5 . A system including one or more processors coupled to memory, the memory loaded with computer instructions to provide relevant messages to an automotive virtual assistant, the computer instructions, when executed on the one or more processors, causing the one or more processors to implement the method of  claim 1 . 
     
     
         6 . A method of an automotive virtual assistant receiving relevant messages, the method comprising:
 providing geolocation information detected by a subsystem of an automobile to a server; and   receiving, by the subsystem of the automobile and from the server, an assistive natural language expression, the received assistive natural language expression being found by:
 searching a concept database for an index based on the geolocation information to find a stored concept obtained from a subsystem of another automobile along with a spoken utterance having been parsed to determine the concept; and 
 searching a natural language expression database using the found stored concept as an index to find an assistive natural language expression, wherein the assistive natural language expression includes a constituent part, 
   wherein the assistive natural language expression is received by the subsystem of the automobile with the stored concept in place of the constituent part.   
     
     
         7 . A system including one or more processors coupled to memory, the memory loaded with computer instructions to provide relevant messages to a user of an automotive virtual assistant, the computer instructions, when executed on the one or more processors, causing the one or more processors to implement the method of  claim 7 .