Engine for human language comprehension of intent and command execution

Abstract

The invention provides a computer system for interacting with a user. A set of concepts initially forms a target set of concepts. An input module receives a language input from the user. An analysis system executes a plurality of narrowing cycles until a concept packet having at least one concept has been identified. Each narrowing cycle includes identifying at least one portion of the language and determining a subset of concepts from the target set of concepts to form a new target subset. An action item identifier identifies an action item from the action items based on the concept packet. An action executer that executes an action based on the action item that has been identified.

What is claimed: 
     
         1 . A network system comprising:
 a user computer system for interacting with a user, comprising:
 a processor; 
 a storage medium connected to the processor; and 
 a set of instructions on the storage medium and executable by the processor, the set of instructions including:
 at least one data store; 
 a set of concepts in the data store, the set of concepts initially forming a target set of concepts; 
 a plurality of action items in the data store; 
 an input module receiving an input from the user, the input including language; 
 an analysis system that executes a plurality of narrowing cycles until a concept packet having at least one concept has been identified, wherein each narrowing cycle includes:
 i) identifying at least one portion of the language; and 
 ii) based on the portion of the language identifying a subset of concepts from the target set of concepts, the subset of concepts forming the target set of concepts to the exclusion of concepts previously forming part of the target set of concepts that are not based on the portion of the language; 
 
 an action item identifier that identifies an action item from the action items based on the concept packet; 
 an action executer that executes an action based on the action item that has been identified; 
 
 a concept management module transmitting user context over a network when the user computer system is connected to the network; 
 a server comprising:
 a processor; 
 a storage medium connected to the processor; and 
 a set of instructions on the storage medium and executable by the processor, the set of instructions including:
 a cloud vertical knowledge container holding a plurality of concepts; and 
 a user context trigger that receives user context from the user computer system when the server is connected to the user computer system over a network and delivering user based data based on the user context from the cloud vertical knowledge container to the user device when the user device is connected to the server over the network, the concept management module storing the context based data as part of the set of concepts. 
 
 
   
     
     
         2 . The network system of  claim 1 , wherein at least one data store comprises:
 a concept store holding the concepts; and   an action item store holding the action items.   
     
     
         3 . The network system of  claim 1 , wherein the input module receives a voice input from the user. 
     
     
         4 . The network system of  claim 1 , wherein the analysis system includes:
 an affix detector that identifies a prefix of a word, a suffix of a word and a space between the prefix and the suffix; and   a lexicalizer that determines the respective target set based on a query with the prefix, suffix and space being criteria for the query.   
     
     
         5 . The network system of  claim 4 , wherein the analysis system includes:
 a phonemizer that breaks the language into phonemes, the affix detector determining the prefix and suffix from the phoneme.   
     
     
         6 . The network system of  claim 1 , wherein the affix detector determines boundaries of a word in the language based on the determination of the prefix and the suffix. 
     
     
         7 . The network system of  claim 1 , wherein the concept packet includes a plurality of concepts. 
     
     
         8 . The network system of  claim 1 , wherein the set of instructions includes:
 an accumulator that accumulates the language in the time domain;   a dispatcher that receives the language from the accumulator after being buffered by the accumulator;   a normalizer that receives the language from the dispatcher in the time domain and normalizes the language;   a windower that receives the language from the normalizer that creates windows of the language in the time domain; and   a fast Fourier Transform that receives the language from the windower in the time domain and transforms the language to the frequency domain before reaching the analysis system.   
     
     
         9 . The network system of  claim 8 , wherein the fast Fourier Transform uses fixed point calculation. 
     
     
         10 . The network system of  claim 1 , wherein the analysis system includes:
 a grammar checker that receives the concept packet and performs a grammar check on the concept packet to determine whether a combination of parts of the language match one of a plurality of reference combinations.   
     
     
         11 . The network system of  claim 1 , wherein the set of instructions further includes:
 a clarifier; and   an action template specializer that activates the clarifier to communicate with the user before causing the action executer to execute the action, if the concept packet fails the grammar checker or bypass the clarifier if the concept packet passes the grammar checker.   
     
     
         12 . The network system of  claim 1 , wherein the set of instructions further includes:
 an abstract syntax tree generator that generates a syntax tree based on the concept packet, the action executer providing components of the syntax tree as an input; and   an executable application receiving the input from the action executer and executing an action based on the input.   
     
     
         13 . The network system of  claim 1 , wherein the set of instructions further includes:
 a data marshaller that enters a concept into the set of concepts based on an output from the action executer.   
     
     
         14 . The network system of  claim 1 , further comprising:
 a network interface device connected to the processor, wherein the analysis system determines whether at least one concept that is sufficient is identified and communicates over the network interface device with a topic loader to supplement the target set with at least one concept if the concepts in the target are sufficient.   
     
     
         15 . A computer-based method of interacting with a user, comprising:
 storing, with a processor of a user computer system, a set of concepts in a data store of the computer system, the set of concepts initially forming a target set of concepts;   storing, with the processor of the user computer system, a plurality of action items in the data store;   receiving, with the processor of the user computer system, an input from the user, the input including language;   executing, with the processor of the user computer system, a plurality of narrowing cycles until a concept packet having at least one concept has been identified, wherein each narrowing cycle includes:
 i) identifying at least one portion of the language; and 
 ii) based on the portion of the language identifying a subset of concepts from the target set of concepts, the subset of concepts forming the target set of concepts to the exclusion of concepts previously forming part of the target set of concepts that are not based on the portion of the language; 
   identifying, with the processor of the user computer system, an action item from the action items based on the concept packet;   executing, with the processor of the user computer system, an action based on the action item; and   transmitting user context over a network when the user computer system is connected to the network.   
     
     
         16 . A non-transitory computer-readable medium having storage thereon and a set of instructions executable by a processor of a computer to perform a computer-based method of interacting with a user, comprising:
 storing, with a processor of a user computer system, a set of concepts in a data store of the computer system, the set of concepts initially forming a target set of concepts;   storing, with the processor of the user computer system, a plurality of action items in the data store;   receiving, with the processor of the user computer system, an input from the user, the input including language;   executing, with the processor of the user computer system, a plurality of narrowing cycles until a concept packet having at least one concept has been identified, wherein each narrowing cycle includes:
 i) identifying at least one portion of the language; and 
 ii) based on the portion of the language identifying a subset of concepts from the target set of concepts, the subset of concepts forming the target set of concepts to the exclusion of concepts previously forming part of the target set of concepts that are not based on the portion of the language; 
   identifying, with the processor of the user computer system, an action item from the action items based on the concept packet;   executing, with the processor of the user computer system, an action based on the action item; and   transmitting user context over a network when the user computer system is connected to the network.