Natural language intent and location determination method and apparatus

Abstract

Methods, apparatus, and system to parse an unstructured, natural language input of a user, infer a semantic meaning of an intent of the user, and determine a present or future user state, including a location and a time, in which the intent can be fulfilled.

1 . (canceled) 
     
     
         2 .- 25 . (canceled) 
     
     
         26 . A computing device comprising:
 at least one input device to receive a speech input from a user;   at least one output device to output a reminder;   memory; and   processor circuitry to:
 initiate speech recognition to recognize at least one word in the speech input; 
 initiate a determination of an intent of the user based on the at least one word in the speech input and an identification of a past pattern of actions corresponding to the intent of the user; and 
 cause the output device to output the reminder based on a comparison between a current condition and a past condition associated with the past pattern of actions, the current condition not included in the speech input from the user. 
   
     
     
         27 . The computing device as defined in  claim 26 , wherein the at least one input device includes a microphone. 
     
     
         28 . The computing device as defined in  claim 26 , wherein the at least one output device includes a speaker. 
     
     
         29 . The computing device as defined in  claim 26 , wherein the reminder is audible. 
     
     
         30 . The computing device as defined in  claim 26 , wherein the processor circuitry is to convert the speech input into text. 
     
     
         31 . The computing device as defined in  claim 26 , wherein the speech input includes natural language from the user. 
     
     
         32 . The computing device as defined in  claim 26 , wherein the processor circuitry is to identify the past pattern of actions as a time series of spatial locations. 
     
     
         33 . The computing device as defined in  claim 26 , wherein the processor circuitry is to perform a machine learning algorithm to estimate a present action of the user based on the current condition and the past pattern of actions. 
     
     
         34 . The computing device as defined in  claim 26 , wherein the processor circuitry is to determine the current condition based on at least one output of at least one of a sensor, a mobile telephone, or a network interface circuit. 
     
     
         35 . The computing device as defined in  claim 26 , wherein the processor circuitry is to determine the current condition based on at least one of movement information, rate of change of movement information, heart rate information, blood pressure information, time of day information, location information, or gaze information. 
     
     
         36 . At least one storage device comprising machine-readable instructions that, when executed, cause one or more processors to at least:
 initiate speech recognition to recognize at least one word in a speech input from a user;   initiate a determination of an intent of the user based on the at least one word in the speech input from the user and an identification of a past pattern of actions corresponding to the intent of the user; and   cause an output device to output a reminder based on a comparison between a current condition and a past condition associated with the past pattern of actions, the current condition not included in the speech input from the user.   
     
     
         37 . The at least one storage device as defined in  claim 36 , wherein the instructions, when executed, cause the one or more processors to initiate conversion of the speech input into text. 
     
     
         38 . The at least one storage device as defined in  claim 36 , wherein the instructions, when executed, cause the one or more processors to initiate identification of the past pattern of actions as a time series of spatial locations. 
     
     
         39 . The at least one storage device as defined in  claim 36 , wherein the instructions, when executed, cause the one or more processors to initiate application of a machine learning classification algorithm to estimate a present action of the user based on the current condition and the past pattern of actions. 
     
     
         40 . The at least one storage device as defined in  claim 36 , wherein the instructions, when executed, cause the one or more processors to initiate determination of the current condition based on at least one output of at last one of a sensor, a mobile telephone, or a network interface circuit. 
     
     
         41 . The at least one storage device as defined in  claim 36 , wherein the instructions, when executed, cause the one or more processors to initiate determination of the current condition based on at least one of movement information, rate of change of movement information, heart rate information, blood pressure information, time of day information, location information, or gaze information. 
     
     
         42 . A server, comprising:
 memory; and   processor circuitry to:
 perform speech recognition to recognize at least one word in speech information from a user of a remote computer device; 
 identify an intent of the user based on the at least one word in the speech information and an identification of a past pattern of actions corresponding to the intent of the user; and 
 transmit a signal to cause an output device of the remote computer device to output a reminder based on a comparison between a current condition and a past condition associated with the past pattern of actions, the current condition not included in the speech information from the user. 
   
     
     
         43 . The server as defined in  claim 42 , wherein the speech information is from a microphone of the remote computer device. 
     
     
         44 . The server as defined in  claim 42 , wherein the output device of the remote computer device is a speaker. 
     
     
         45 . The server as defined in  claim 42 , wherein the processor circuitry is to convert the speech information into text. 
     
     
         46 . The server as defined in  claim 42 , wherein the processor circuitry is to process the speech information as natural language from the user. 
     
     
         47 . The server as defined in  claim 42 , wherein the processor circuitry is to identify the past pattern of actions as a time series of spatial locations. 
     
     
         48 . The server as defined in  claim 42 , wherein the processor circuitry is to perform a machine learning classification algorithm to estimate a present action of the user based on the current condition and the past pattern of actions. 
     
     
         49 . The server as defined in  claim 42 , wherein the remote computer device is at least one of a mobile telephone, or a network interface circuit. 
     
     
         50 . The server as defined in  claim 49 , wherein the processor circuitry is to determine the current condition based on at least one of movement information, rate of change of movement information, heart rate information, blood pressure information, time of day information, location information, or gaze information from the at least one of the mobile telephone or the network interface circuit. 
     
     
         51 . A server, comprising:
 means for receiving speech information from a remote computer device via a network, the speech information corresponding to a user of the remote computer device;   means for recognizing at least one word in the speech information;   means for identifying a past pattern of actions corresponding to the user;   means for comparing a current condition and a past condition associated with the past pattern of actions corresponding to the user, the current condition not included in the speech information;   means for determining an intent of the user based on the at least one word in the speech information and the past pattern of actions corresponding to the user; and   means for sending information to the remote computer device via the network to cause an output device of the remote computer device to output a reminder based on the comparison between the current condition and the past condition associated with the past pattern of actions corresponding to the user.   
     
     
         52 . The server as defined in  claim 51 , wherein the receiving means is to receive the speech information from the remote computer device after detection of the speech information by a microphone of the remote computer device. 
     
     
         53 . The server as defined in  claim 51 , wherein the output device is a speaker of the remote computer device. 
     
     
         54 . The server as defined in  claim 51 , wherein the recognizing means is to convert the speech information into text. 
     
     
         55 . The server as defined in  claim 51 , wherein the recognizing means is to process the speech information as natural language. 
     
     
         56 . The server as defined in  claim 51 , wherein the determining means is to estimate a present action of the user with a machine learning algorithm, the estimate based on the current condition and the past pattern of actions. 
     
     
         57 . The server as defined in  claim 51 , wherein the comparing means is to determine the current condition based on at least one output of at least one of a sensor, a mobile telephone, or a network interface circuit. 
     
     
         58 . The server as defined in  claim 51 , wherein the comparing means is to determine the current condition based on at least one of movement information, rate of change of movement information, heart rate information, blood pressure information, time of day information, location information, or gaze information.