SYSTEM, DEVICE, AND METHOD FOR AN ELECTRONIC DIGITAL ASSISTANT HAVING A CONTEXT DRIVEN NATURAL LANGUAGE VOCABULARY

• US 20180350344A1
• Filed: 05/30/2017
• Published: 12/06/2018
• Est. Priority Date: 05/30/2017
• Status: Abandoned Application

• Current Assignee: Motorola Solutions, Inc.
• Original Assignee: Motorola Solutions, Inc.
• Inventors: ZASLOW, BENJAMIN, MARYASKIN, EVGENY, SPENGLER, CHARLES
• Application Number:
  US15/607,791
• Publication Number:
  US 20180350344A1
• Time in Patent Office: Days
• CPC Class Codes: G06F 3/165 Management of the audio stream, e.g. setting of volume, audio stream path
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 40/247 Thesauruses; Synonyms
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08
• CPC Class Codes: G10L 13/047 Architecture of speech synthesisers
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: H04M 2201/18 Comparators
• CPC Class Codes: H04M 2242/30 Determination of the location of a subscriber
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals

Abstract

An electronic digital assistant (EDA) detects a user'"'"'s acoustical environment and substantively varys a content of a generated auditory output to the user as a function of the detected acoustical environment. The EDA receives an indication of an acoustic environment in which an auditory output will be provided to a user. The EDA then generates an auditory output having a substantive content that is varied as a function of the indicated acoustic environment. The EDA then provides the auditory output to an electronic output transducer associated with the user for reproduction to the user in the acoustic environment.

Claims

1. A method at an electronic digital assistant computing device for detecting a user'"'"'s acoustical environment and substantively varying a content of a generated auditory output to the user as a function of the detected acoustical environment, the method comprising:

receiving, at an electronic digital assistant computing device, an indication of an acoustic environment in which an auditory output will be provided by the electronic digital assistant computing device to a user;

generating, at the electronic digital assistant computing device, an auditory output having a substantive content that is varied as a function of the indication of the acoustic environment; and

providing, by the electronic digital assistant computing device, the auditory output to an electronic output transducer associated with the user for reproduction to the user in the acoustic environment.

2. The method of claim 1, wherein the indication of the acoustic environment includes one or more of a noise level, a pitch, and a periodicity of noise measured at a noise level sensor associated with the user.

3. The method of claim 2, wherein the indication of the acoustic environment is a numerical value measured in decibels.

4. The method of claim 2, wherein when the noise level is below a first threshold level, the substantive content of the auditory output is shortened to decrease a time to playback the auditory output to the user.

5. The method of claim 4, wherein the substantive content is shortened by one of:

using acronyms where possible instead of using underlying terms that the acronym represents, accessing a thesaurus and choosing terms having fewer syllables than other terms having more syllables and substantially a same meaning as one another, using 10-codes instead of underlying text descriptions of such 10-codes, using pronouns to refer to people, places, or things instead of proper names, using contractions instead of underlying terms with which the contractions are short for, and using abbreviations for terms instead of underlying terms with which the abbreviations are short for.

6. The method of claim 4, wherein the substantive content is shortened by all of:

using acronyms where possible instead of using underlying terms that the acronym represents, accessing a thesaurus database and choosing terms having fewer syllables than other terms having more syllables and substantially a same meaning as one another, using 10-codes instead of underlying text descriptions of such 10-codes, using pronouns to refer to people, places, or things instead of proper names, using contractions instead of underlying terms with which the contractions are short for, and using abbreviations for terms instead of underlying terms with which the abbreviations are short for.

7. The method of claim 4, wherein the first threshold level is between 75 and 85 dB.

8. The method of claim 2, wherein when the noise level is below a first threshold level, the substantive content of the auditory output modified by:

accessing a thesaurus database wherein synonyms having substantially a same meaning as one another are also assigned hardness ratings based on a measured change in air pressure when reproducing the synonym relative to other synonymous terms; and

choosing shorter terms having fewer syllables or terms more closely matching an intended meaning, independent of, or having a higher priority than, the hardness ratings assigned to the terms.

9. The method of claim 2, wherein when the noise level is above a second threshold level, the substantive content of the auditory output is lengthened to increase a time to playback the auditory output to the user.

10. The method of claim 9, wherein the substantive content is lengthened by one of:

not using acronyms where possible and instead using underlying terms that the acronym represents, accessing a thesaurus database and choosing terms having more syllables than other terms having fewer syllables and substantially a same meaning as one another, not using 10-codes and instead using text descriptions of such 10-codes, using proper names instead of pronouns to refer to people, places, or things, not using contractions and instead using underlying terms with which the contractions are short for, and not using abbreviations for terms and instead using underlying terms with which the abbreviations are short for.

11. The method of claim 9, wherein the substantive content is shortened by all of:

not using acronyms where possible and instead using underlying terms that the acronym represents, accessing a thesaurus and choosing terms having more syllables than other terms having fewer syllables and substantially a same meaning as one another, not using 10-codes and instead using text descriptions of such 10-codes, using proper names instead of pronouns to refer to people, places, or things, not using contractions and instead using underlying terms with which the contractions are short for, and not using abbreviations for terms and instead using underlying terms with which the abbreviations are short for.

12. The method of claim 9, wherein the second threshold level is between 95 and 105 dB.

13. The method of claim 2, wherein when the noise level is above a second threshold level, the substantive content of the auditory output modified by:

accessing a thesaurus database wherein synonyms having substantially a same meaning as one another are also assigned hardness ratings based on a measured change in air pressure when reproducing the synonym relative to other synonymous terms; and

choosing a synonymous term having a higher hardness rating assigned to the term relative to other synonymous terms independent of, or having a higher priority than, length or how closely the term matches an intended meaning.

14. The method of claim 1, wherein the electronic digital assistant computing device is a mobile computing device associated with the user and the mobile computing device further including the electronic output transducer.

15. The method of claim 1, wherein the electronic digital assistant computing device is a computing device remote from the user and that communicates with a mobile computing device associated with the user and including the electronic output transducer via a wireless radio access network.

16. The method of claim 1, wherein the electronic digital assistant computing device is a distributed computing device that includes computing components disposed at a mobile computing device associated with the user, the mobile computing device further including the electronic output transducer, and computing components disposed at a remote computing device that communicates with the mobile computing device via a wireless radio access network.

17. The method of claim 1, the method further comprising:

receiving, at the electronic digital assistant computing device, indications of a plurality of respective acoustic environments in which a plurality of users to which an auditory output will be provided by the electronic digital assistant computing device, the plurality of users forming a talkgroup of users;

generating, at the electronic digital assistant computing device, an auditory output having a substantive content that is generated as a function of the indications of the acoustic environments; and

providing, by the electronic digital assistant computing device, the auditory output to electronic output transducers associated with each user for reproduction to the user in the respective acoustic environments via a talkgroup session.

18. The method of claim 17, wherein the substantive content of the auditory output is generated based on an average of the indications of the plurality of respective acoustic environments across the talkgroup of users.

19. The method of claim 17, wherein the substantive content of the auditory output is generated based on a worst-case acoustic environment indication out of the plurality of respective acoustic environments across the talkgroup of users.

20. A computing device implementing an electronic digital assistant for detecting a user'"'"'s acoustical environment and substantively varying a content of an auditory output to the user as a function of the detected acoustical environment, the electronic computing device comprising:

a memory storing non-transitory computer-readable instructions;

a transceiver; and

one or more processors configured to, in response to executing the non-transitory computer-readable instructions, perform a first set of functions comprising;

receive, via one of the transceiver and a sensor communicably coupled to the electronic digital assistant computing device, an indication of an acoustic environment in which an auditory output will be provided by the electronic digital assistant computing device to a user;

generating an auditory output having a substantive content that is varied as a function of the indication of the acoustic environment; and

providing, via one of an electronic output transducer communicably coupled to the electronic digital assistant computing device and the transceiver, the auditory output for reproduction to the user in the acoustic environment.