US6665640B1 — Interactive speech based learning/training system…

Claim 1

Independent Claim 216 words

An interactive learning system adapted for responding to speech-based queries concerning topics addressed by such interactive learning system, the system comprising: a query file for storing a plurality of topic query entries, each topic query entry including a query relating to one or more of the topics covered by the speech-based interactive learning system; and an answer file for storing a plurality of topic answer entries, each topic answer entry including an answer to one or more of said plurality of topic query entries, such that each topic query entry has at least one associated topic answer entry; and a speech recognition system for generating recognized speech utterance data from partially processed speech data associated with a speech-based query concerning one of said topics, said partially processed speech data being received from a remote speech capturing system; and said speech recognition system further cooperating with a natural language engine, which processes said recognized speech utterance data using a morphological analysis and a phrase analysis to form recognized speech sentence data corresponding to said speech-based query; a query formulation system for converting said recognized speech sentence data into a search query suitable for identifying a topic query entry corresponding to said speech-based query, and for locating at least one topic answer entry best matching said speech-based query.

Claim 2

Dependent Claim 216 words

An interactive learning system adapted for responding to speech-based queries concerning topics addressed by such interactive learning system, the system comprising: a query file for storing a plurality of topic query entries, each topic query entry including a query relating to one or more of the topics covered by the speech-based interactive learning system; and an answer file for storing a plurality of topic answer entries, each topic answer entry including an answer to one or more of said plurality of topic query entries, such that each topic query entry has at least one associated topic answer entry; and a speech recognition system for generating recognized speech utterance data from partially processed speech data associated with a speech-based query concerning one of said topics, said partially processed speech data being received from a remote speech capturing system; and said speech recognition system further cooperating with a natural language engine, which processes said recognized speech utterance data using a morphological analysis and a phrase analysis to form recognized speech sentence data corresponding to said speech-based query; a query formulation system for converting said recognized speech sentence data into a search query suitable for identifying a topic query entry corresponding to said speech-based query, and for locating at least one topic answer entry best matching said speech-based query.

Claim 3

Dependent Claim 34 words

The system of claim 1 , wherein said remote speech capturing system is located at a client site, and said speech recognition system is distributed across said client site and a separate server site.

Claim 4

Dependent Claim 67 words

The system of claim 1 , wherein said speech recognition system is comprised of a first portion at a client based computing system for performing first signal processing operations on a speech input signal to create said partially processed speech data, and a second portion at a server based computing system for performing a second signal processing operation for completing processing of said partially processed speech data.

Claim 5

Dependent Claim 19 words

The system of claim 1 , wherein said query formulation system uses context parameters for recognizing said speech-based query.

Claim 6

Dependent Claim 35 words

The system of claim 4 , wherein said context parameters include any one or more of the following: a course, chapter, and/or section of said lesson information selected by said user during the interactive session.

Claim 7

Dependent Claim 28 words

The system of claim 4 , wherein said context parameters include any one or more visible text words or objects presented to said user during the interactive session.

Claim 8

Dependent Claim 30 words

The system of claim 4 , wherein said context parameters are used for dynamically determining and loading an appropriate grammar and dictionary file to be used for said speech-based query.

Claim 9

Dependent Claim 170 words

A speech based interactive learning system comprising: an instructional file containing instructional materials arranged in a hierarchical structure that includes at least a first level of instruction data and a second level of instruction data; and wherein users of such system can navigate said hierarchical structure and formulate a user query concerning instructional materials located at least at said second level of instruction data; further wherein said user query can be correlated with a corresponding instructional material question taken from a list of predefined questions, said set of predefined questions being paired with a corresponding set of responsive answers; a speech recognition engine for generating recognized words from a user query; a natural language engine for parsing said words contained in said user query to generate recognized speech sentence data; a query formulation engine for converting said recognized speech sentence data into a search query suitable for identifying a corresponding instructional material question for said user query, and for locating a corresponding responsive answer for said corresponding instructional material question.

Claim 10

Dependent Claim 170 words

A speech based interactive learning system comprising: an instructional file containing instructional materials arranged in a hierarchical structure that includes at least a first level of instruction data and a second level of instruction data; and wherein users of such system can navigate said hierarchical structure and formulate a user query concerning instructional materials located at least at said second level of instruction data; further wherein said user query can be correlated with a corresponding instructional material question taken from a list of predefined questions, said set of predefined questions being paired with a corresponding set of responsive answers; a speech recognition engine for generating recognized words from a user query; a natural language engine for parsing said words contained in said user query to generate recognized speech sentence data; a query formulation engine for converting said recognized speech sentence data into a search query suitable for identifying a corresponding instructional material question for said user query, and for locating a corresponding responsive answer for said corresponding instructional material question.

Claim 11

Dependent Claim 169 words

A speech based interactive learning system comprising: an instructional file containing instructional materials arranged in a hierarchical structure that includes at least a first level of instruction data and a second level of instruction data; and wherein users of such system can navigate said hierarchical structure and formulate a user query concerning instructional materials located at least at said second level of instruction data; further wherein said user query can be correlated with a corresponding instructional material question taken from a list of predefined questions, said set of predefined questions being paired with a corresponding set of responsive answers; a speech recognition engine for generating recognized speech data from a user query; a query formulation engine for converting said recognized speech data into a search query suitable for identifying a corresponding instructional material question for said user query, and for locating a corresponding responsive answer for said corresponding instructional material question; wherein said search query is formulated using a natural language engine parsing words contained in said user query.

Claim 12

Dependent Claim 169 words

A speech based interactive learning system comprising: an instructional file containing instructional materials arranged in a hierarchical structure that includes at least a first level of instruction data and a second level of instruction data; and wherein users of such system can navigate said hierarchical structure and formulate a user query concerning instructional materials located at least at said second level of instruction data; further wherein said user query can be correlated with a corresponding instructional material question taken from a list of predefined questions, said set of predefined questions being paired with a corresponding set of responsive answers; a speech recognition engine for generating recognized speech data from a user query; a query formulation engine for converting said recognized speech data into a search query suitable for identifying a corresponding instructional material question for said user query, and for locating a corresponding responsive answer for said corresponding instructional material question; wherein said search query is formulated using a natural language engine parsing words contained in said user query.

Claim 13

Dependent Claim 32 words

The system of claim 9 , wherein said natural language engine compares said user query with one or more of said list of predefined questions to determine said corresponding instructional material question.

Claim 14

Dependent Claim 51 words

The system of claim 8 , where a set of potential questions corresponding to said user query is derived from said list of predefined questions by partially recognizing said user query, and said corresponding instructional material question is derived by fully recognizing said user query from said set of potential questions.

Claim 15

Dependent Claim 52 words

The system of claim 9 , wherein said first level of instruction data is associated with one or more lesson chapters for a particular course, and said second level of instruction data is associated with one or more sections, said one or more sections being linked to said one or more chapters.

Claim 16

Dependent Claim 34 words

The system of claim 8 , further including an animated visible agent for assisting said user to navigate said instructional materials, and for articulating said corresponding responsive answer in audible form to said user.

Claim 17

Dependent Claim 31 words

The system of claim 9 , further including an animated visible agent for assisting said user to navigate said instructional materials, and for articulating said corresponding responsive answer to said user.

Claim 18

Dependent Claim 189 words

A speech based system for assisting a user in connection with an interactive lesson tutorial having question and answer capability, the system comprising: a lesson file containing instructional materials arranged to include a list of predefined questions and a corresponding list of predefined answers for said lesson; and a speech recognition engine for generating recognized speech word data from a user query pertaining to said lesson; and a natural language engine for generating recognized speech sentence data from said speech word data; and a query recognition engine for locating a corresponding predefined question for said user query using said recognized speech sentence data; and a conversion engine for converting a corresponding predefined answer for said corresponding predefined question into a form perceptible to the user; said query recognition system being adapted to process said user query, even before said user has completed articulating said user query, to identify said corresponding predefined answer and thus emulate a human response time in response to a user query, so that the user perceives interaction with such system in essentially the same way that would be experienced from interacting with a real human.

Claim 19

Dependent Claim 189 words

A speech based system for assisting a user in connection with an interactive lesson tutorial having question and answer capability, the system comprising: a lesson file containing instructional materials arranged to include a list of predefined questions and a corresponding list of predefined answers for said lesson; and a speech recognition engine for generating recognized speech word data from a user query pertaining to said lesson; and a natural language engine for generating recognized speech sentence data from said speech word data; and a query recognition engine for locating a corresponding predefined question for said user query using said recognized speech sentence data; and a conversion engine for converting a corresponding predefined answer for said corresponding predefined question into a form perceptible to the user; said query recognition system being adapted to process said user query, even before said user has completed articulating said user query, to identify said corresponding predefined answer and thus emulate a human response time in response to a user query, so that the user perceives interaction with such system in essentially the same way that would be experienced from interacting with a real human.

Claim 20

Dependent Claim 149 words

A speech based system for assisting a user in connection with an interactive lesson tutorial having question and answer capability, the system comprising: a lesson file containing instructional materials arranged to include a list of predefined questions and a corresponding list of predefined answers for said lesson; and a speech recognition engine for generating recognized speech data from a user query pertaining to said lesson; and a query recognition engine for locating a corresponding predefined question for said user query using said recognized speech data; and a conversion engine for converting a corresponding predefined answer for said corresponding predefined question into a form perceptible to the user; said query recognition system being adapted to emulate a human response time in response to a user query, so that the user perceives interaction with such system in essentially the same way that would be experienced from interacting with a real human.

Claim 21

Dependent Claim 149 words

A speech based system for assisting a user in connection with an interactive lesson tutorial having question and answer capability, the system comprising: a lesson file containing instructional materials arranged to include a list of predefined questions and a corresponding list of predefined answers for said lesson; and a speech recognition engine for generating recognized speech data from a user query pertaining to said lesson; and a query recognition engine for locating a corresponding predefined question for said user query using said recognized speech data; and a conversion engine for converting a corresponding predefined answer for said corresponding predefined question into a form perceptible to the user; said query recognition system being adapted to emulate a human response time in response to a user query, so that the user perceives interaction with such system in essentially the same way that would be experienced from interacting with a real human.

Claim 22

Dependent Claim 43 words

The system of claim 16 , wherein said system responds to a user query in less than approximately 10 seconds for a list of predefined questions having at least 100 entries, not accounting for data transmission latencies between the user and the system.

Claim 23

Dependent Claim 23 words

The system of claim 16 , wherein said system further includes a visible interactive agent that receives and responds to said user query.

Claim 24

Dependent Claim 30 words

The system of claim 16 , wherein said interactive agent is configured with an appearance and mannerism that emulates a corresponding human appearance and mannerism appropriate for said lesson tutorial.

Claim 25

Dependent Claim 31 words

The system of claim 15 , wherein said query recognition engine is distributed across multiple computing systems so that said more than one lesson file is consulted for said user query.

Claim 26

Independent Claim 228 words

A method of implementing a speech-based interactive query system, including the steps of: (a) storing a plurality of topic query entries, each topic query entry including a query relating to one or more of topics covered by the speech-based interactive learning system; and (b) storing a plurality of topic answer entries, each topic answer entry including an answer to one or more of said plurality of topic query entries, such that each topic query entry has at least one associated topic answer entry; and (c) generating recognized speech utterance data associated with a speech-based query concerning one of said topics, such that said recognized speech utterance data is generated by partial recognition processing of said speech-based query by a first signal processing routine executing at a first computing device, and then completing recognition of said speech-based query through processing performed by a second signal processing routine executing at a second computing device; and (d) converting said recognized speech utterance data with a natural language process into recognized speech sentence data, said recognized speech data being used by a search query suitable for identifying a topic query entry corresponding to said speech-based query; and (e) locating at least one topic answer entry best matching said speech-based query; wherein step (e) is initiated before said natural language engine has converted said recognized speech utterance data into recognized speech sentence data.

Claim 27

Independent Claim 228 words

A method of implementing a speech-based interactive query system, including the steps of: (a) storing a plurality of topic query entries, each topic query entry including a query relating to one or more of topics covered by the speech-based interactive learning system; and (b) storing a plurality of topic answer entries, each topic answer entry including an answer to one or more of said plurality of topic query entries, such that each topic query entry has at least one associated topic answer entry; and (c) generating recognized speech utterance data associated with a speech-based query concerning one of said topics, such that said recognized speech utterance data is generated by partial recognition processing of said speech-based query by a first signal processing routine executing at a first computing device, and then completing recognition of said speech-based query through processing performed by a second signal processing routine executing at a second computing device; and (d) converting said recognized speech utterance data with a natural language process into recognized speech sentence data, said recognized speech data being used by a search query suitable for identifying a topic query entry corresponding to said speech-based query; and (e) locating at least one topic answer entry best matching said speech-based query; wherein step (e) is initiated before said natural language engine has converted said recognized speech utterance data into recognized speech sentence data.

Claim 28

Independent Claim 187 words

A method of implementing a speech-based interactive query system, including the steps of: (a) storing a plurality of topic query entries, each topic query entry including a query relating to one or more of topics covered by the speech-based interactive learning system; and (b) storing a plurality of topic answer entries, each topic answer entry including an answer to one or more of said plurality of topic query entries, such that each topic query entry has at least one associated topic answer entry; and (c) generating recognized speech data associated with a speech-based query concerning one of said topics, such that said recognized speech data is generated by partial recognition processing of said speech-based query by a first signal processing routine executing at a first computing device, and then completing recognition of said speech-based query through processing performed by a second signal processing routine executing at a second computing device; and (d) converting said recognized speech data into a search query suitable for identifying a topic query entry corresponding to said speech-based query; and (e) locating at least one topic answer entry best matching said speech-based query.

Claim 29

Independent Claim 187 words

A method of implementing a speech-based interactive query system, including the steps of: (a) storing a plurality of topic query entries, each topic query entry including a query relating to one or more of topics covered by the speech-based interactive learning system; and (b) storing a plurality of topic answer entries, each topic answer entry including an answer to one or more of said plurality of topic query entries, such that each topic query entry has at least one associated topic answer entry; and (c) generating recognized speech data associated with a speech-based query concerning one of said topics, such that said recognized speech data is generated by partial recognition processing of said speech-based query by a first signal processing routine executing at a first computing device, and then completing recognition of said speech-based query through processing performed by a second signal processing routine executing at a second computing device; and (d) converting said recognized speech data into a search query suitable for identifying a topic query entry corresponding to said speech-based query; and (e) locating at least one topic answer entry best matching said speech-based query.

Claim 30

Dependent Claim 43 words

The method of claim 21 , wherein during step (d) context parameters are used for formulating said search query, and said context parameters are used for dynamically determining and loading an appropriate grammar and dictionary file to be used for said speech-based query.

Claim 31

Dependent Claim 43 words

The method of claim 1 , wherein during step (d) context parameters are used for formulating said search query, and said context parameters are used for dynamically determining and loading an appropriate grammar and dictionary file to be used for said speech-based query.

Claim 32

Independent Claim 214 words

A method of presenting an interactive lesson to a user comprising the steps of: (a) arranging instructional materials in a hierarchical structure that includes at least a first level of instruction data and a second level of instruction data; and (b) presenting the instructional materials to a user so that the user can navigate said hierarchical structure and formulate a user query concerning instructional materials located at least at said second level of instruction data; (c) defining a list of predefined questions for at least said second level of instruction data, said set of predefined questions being paired with a corresponding set of responsive answers; (d) generating recognized speech utterance data from a user query for such interactive lesson; (e) converting said recognized speech utterance data into a search query suitable for identifying a corresponding instructional material question for said user query, said search query being formulated with assistance from a natural language engine parsing words in said recognized speech utterance data; and (f) identifying a corresponding responsive answer for said corresponding instructional material question; wherein a set of potential questions corresponding to said user query is derived by partially processing said speech utterance data during step (e), and then said corresponding instructional material question is determined by fully processing said speech utterance data.

Claim 33

Independent Claim 214 words

A method of presenting an interactive lesson to a user comprising the steps of: (a) arranging instructional materials in a hierarchical structure that includes at least a first level of instruction data and a second level of instruction data; and (b) presenting the instructional materials to a user so that the user can navigate said hierarchical structure and formulate a user query concerning instructional materials located at least at said second level of instruction data; (c) defining a list of predefined questions for at least said second level of instruction data, said set of predefined questions being paired with a corresponding set of responsive answers; (d) generating recognized speech utterance data from a user query for such interactive lesson; (e) converting said recognized speech utterance data into a search query suitable for identifying a corresponding instructional material question for said user query, said search query being formulated with assistance from a natural language engine parsing words in said recognized speech utterance data; and (f) identifying a corresponding responsive answer for said corresponding instructional material question; wherein a set of potential questions corresponding to said user query is derived by partially processing said speech utterance data during step (e), and then said corresponding instructional material question is determined by fully processing said speech utterance data.

Claim 34

Dependent Claim 29 words

The method of claim 25 , wherein said response undergoes a text to speech process so that said topic answer entry is expressed in audible form to a user.

Claim 35

Independent Claim 172 words

A method of presenting an interactive lesson to a user comprising the steps of: (a) arranging instructional materials in a hierarchical structure that includes at least a first level of instruction data and a second level of instruction data; and (b) presenting the instructional materials to a user so that the user can navigate said hierarchical structure and formulate a user query concerning instructional materials located at least at said second level of instruction data; (c) defining a list of predefined questions for at least said second level of instruction data, said set of predefined questions being paired with a corresponding set of responsive answers; (d) generating recognized speech data from a user query for such interactive lesson; (e) converting said recognized speech data into a search query suitable for identifying a corresponding instructional material question for said user query, said search query being formulated with assistance from a natural language engine parsing words in said recognized speech data; and (f) identifying a corresponding responsive answer for said corresponding instructional material question.

Claim 36

Independent Claim 172 words

A method of presenting an interactive lesson to a user comprising the steps of: (a) arranging instructional materials in a hierarchical structure that includes at least a first level of instruction data and a second level of instruction data; and (b) presenting the instructional materials to a user so that the user can navigate said hierarchical structure and formulate a user query concerning instructional materials located at least at said second level of instruction data; (c) defining a list of predefined questions for at least said second level of instruction data, said set of predefined questions being paired with a corresponding set of responsive answers; (d) generating recognized speech data from a user query for such interactive lesson; (e) converting said recognized speech data into a search query suitable for identifying a corresponding instructional material question for said user query, said search query being formulated with assistance from a natural language engine parsing words in said recognized speech data; and (f) identifying a corresponding responsive answer for said corresponding instructional material question.

Claim 37

Dependent Claim 40 words

The method of claim 27 , wherein during step (f) said natural language engine operates on said recognized speech data as well as on one or more of said list of predefined questions to determine said corresponding instructional material question.

Claim 38

Dependent Claim 52 words

The method of claim 27 , wherein said first level of instruction data is associated with one or more lesson chapters for a particular course, and said second level of instruction data is associated with one or more sections, said one or more sections being linked to said one or more chapters.

Claim 39

Independent Claim 163 words

A method of operating a speech-based lesson tutorial system having question and answer capability, the method comprising the steps of: (a) configuring a list of retrievable predefined questions and a corresponding list of predefined answers for said lesson; and (b) generating recognized speech data from a user query pertaining to said lesson; and wherein said recognized speech data is generated by a combination of both speech utterance recognition and natural language processing; (c) locating a corresponding predefined question for said user query using said recognized speech data; and (d) converting a corresponding predefined answer for said corresponding predefined question into a form perceptible to the user; and wherein at least step (b) is performed at least in part while a user is articulating said query so as to emulate a human response time in response to a user query, so that the user perceives interaction with such system in essentially the same way that would be experienced from interacting with a real human.

Claim 40

Independent Claim 163 words

A method of operating a speech-based lesson tutorial system having question and answer capability, the method comprising the steps of: (a) configuring a list of retrievable predefined questions and a corresponding list of predefined answers for said lesson; and (b) generating recognized speech data from a user query pertaining to said lesson; and wherein said recognized speech data is generated by a combination of both speech utterance recognition and natural language processing; (c) locating a corresponding predefined question for said user query using said recognized speech data; and (d) converting a corresponding predefined answer for said corresponding predefined question into a form perceptible to the user; and wherein at least step (b) is performed at least in part while a user is articulating said query so as to emulate a human response time in response to a user query, so that the user perceives interaction with such system in essentially the same way that would be experienced from interacting with a real human.

Claim 41

Dependent Claim 35 words

The method of claim 27 , further including a step (g): displaying an animated visible agent for assisting said user to navigate said instructional materials, and for articulating said corresponding responsive answer to said user.

Claim 42

Dependent Claim 43 words

The method of claim 27 , wherein during step (e) context parameters are used for recognizing said speech-based query, and said context parameters are used for dynamically determining and loading an appropriate grammar and dictionary file to be used for said speech-based query.

Claim 43

Independent Claim 133 words

A method of operating a speech-based lesson tutorial system having question and answer capability, the method comprising the steps of: (a) configuring a list of retrievable predefined questions and a corresponding list of predefined answers for said lesson; and (b) generating recognized speech data from a user query pertaining to said lesson; and (c) locating a corresponding predefined question for said user query using said recognized speech data; and (d) converting a corresponding predefined answer for said corresponding predefined question into a form perceptible to the user; and wherein steps (b) to (d) are performed so as to emulate a human response time in response to a user query, so that the user perceives interaction with such system in essentially the same way that would be experienced from interacting with a real human.

Claim 44

Independent Claim 133 words

A method of operating a speech-based lesson tutorial system having question and answer capability, the method comprising the steps of: (a) configuring a list of retrievable predefined questions and a corresponding list of predefined answers for said lesson; and (b) generating recognized speech data from a user query pertaining to said lesson; and (c) locating a corresponding predefined question for said user query using said recognized speech data; and (d) converting a corresponding predefined answer for said corresponding predefined question into a form perceptible to the user; and wherein steps (b) to (d) are performed so as to emulate a human response time in response to a user query, so that the user perceives interaction with such system in essentially the same way that would be experienced from interacting with a real human.

Claim 45

Dependent Claim 46 words

The method of claim 33 , wherein step (d) occurs in response to a user query in less than approximately 10 seconds for a list of predefined questions having at least 100 entries, not accounting for data transmission latencies between the user and the tutorial system.

Claim 46

Dependent Claim 28 words

The method of claim 30 , wherein step (c) occurs across multiple computing systems so that said more than one lesson file is consulted for said user query.

Claim 47

Dependent Claim 30 words

The method of claim 35 , wherein said interactive agent is configured with an appearance and mannerism that emulates a corresponding human appearance and mannerism appropriate for said lesson tutorial.

Claim 48

Dependent Claim 43 words

The method of claim 33 , wherein during step (c) context parameters are used for recognizing said speech-based query, and said context parameters are used for dynamically determining and loading an appropriate grammar and dictionary file to be used for said speech-based query.

Claim 49

Dependent Claim 28 words

The method of claim 33 , wherein step (c) occurs across multiple computing system so that said more than one lesson file is consulted for said user query.

Annuity Stage	Window Opens	Payment Deadline	Surcharge Period Until	Estimated Fee	Status
3.5 Years (Year 4)	2006-12-15	2007-06-16	2007-12-16	$2000.00	Window Closed / Lapsed
7.5 Years (Year 8)	2010-12-15	2011-06-16	2011-12-16	$3760.00	Window Closed / Lapsed
11.5 Years (Year 12)	2014-12-15	2015-06-16	2015-12-16	$7700.00	Window Closed / Lapsed

Interactive speech based learning/training system formulating search queries based on natural language parsing of recognized user queries

Abstract

Inventors

Bibliographic Details

Claims Analysis

References Cited (Backward Citations)

USPTO Annuity & Maintenance Windows

Assigned Categories & Tags

Assign Category Tag