Item locator system utilizing item and location bar codes
View Patent ↗An item location system uses voice activation and responsiveness to identify location(s) of item(s) sought by a user. The system may include a continuous speech recognition digital signal processor, a programmable microprocessor interfaced therewith, voice input and user feedback mechanisms, including audio and/or video feedback. Some embodiments utilize audio feedback to the user. The system also includes sufficient software and equipment to create item-identification/corresponding location-identification data pairs by utilizing item identifying bar codes on the items and matching them to location identifying bar codes physically situated on the corresponding locations. The continuous speech recognition engine may utilize Hidden Markov Models to create real time continuous speech recognition and feedback.
1. A method comprising:
converting, by a voice recognition system, an acoustic signal, representing a request for location information associated with an item having an association with an aisle and a shelf, into a digital signal;
monitoring, by the voice recognition system, for a user-definable setting, wherein the user-definable setting comprises a trigger word transmitted to the voice recognition system;
determining, by the voice recognition system, one or more words included in the acoustic signal based at least in part on the digital signal and said monitoring; and
providing, by the voice recognition system, feedback to the request for location information based at least in part on the determined one or more words, wherein the feedback includes an aisle identifier that identifies the aisle and a shelf identifier that identifies the shelf.
2. The method of claim 1 , wherein determining the one or more words included in the acoustic signal comprises:
processing, by the voice recognition system, the digital signal into one or more observations;
selecting, by the voice recognition system, one or more models for the one or more observations, wherein the one or more models represent one or more sounds that when combined form a pronunciation of the digital signal; and
identifying, by the voice recognition system, the one or more words from a database that includes words and corresponding models by comparing the selected one or more models with the corresponding models.
3. The method of claim 1 , wherein said providing feedback to the request for location information comprises providing visual feedback to the request for location information.
4. The method of claim 1 , wherein said providing feedback to the request for location information comprises providing auditory feedback to the request for location information.
5. The method of claim 1 , further comprising:
providing, by the voice recognition system, one or more default instructions in response to a determination that the acoustic signal does not represent a request for location information.
6. The method of claim 1 , further comprising:
receiving, by the voice recognition system, the acoustic signal representing the request for the location information via a receiver.
7. A voice recognition system, comprising:
an audio controller configured to convert an acoustic signal into a digital signal, wherein the acoustic signal represents a request for location information associated with an item having an association with an aisle and a shelf; and
a voice recognition unit coupled to the audio controller and configured to:
monitor for a trigger word transmitted to the voice recognition system and, in response to receipt of the trigger word, determine one or more words included in the acoustic signal based on the digital signal; and
provide feedback, via an input/output device, to the request for location information, wherein the feedback is provided based at least in part on the determined one or more words, and wherein the feedback includes an aisle identifier that identifies the aisle and a shelf identifier that identifies the shelf.
8. The voice recognition system of claim 7 , wherein the voice recognition unit is further configured to process the digital signal into one or more observations, select one or more models to represent the one or more observations, wherein the one or more models are associated with one or more sounds that when combined form a pronunciation of the digital signal, and identify the one or more words from a database by comparing the selected one or more models with corresponding models in the database.
9. The voice recognition system of claim 7 , further comprising:
a text to speech generator coupled to the voice recognition unit and the input/output device, and configured to enable feedback to be provided via the input/output device as an audio response to the request to locate the item.
10. The voice recognition system of claim 8 , further comprising:
a storage unit coupled to the voice recognition unit and configured to store the database.
11. The voice recognition system of claim 7 , wherein the input/output device is configured to receive the request for the location information and includes a visual display.
12. An apparatus, comprising:
means for converting an acoustic signal into a digital signal, wherein the acoustic signal represents a request for location information associated with an item having an association with an aisle and a shelf;
means for monitoring for a trigger word transmitted to the apparatus, and in response to receipt of the trigger word, determining one or more words included in the acoustic signal based on the digital signal; and
means for providing feedback to the request for location information based at least in part on the determined one or more words, wherein the feedback includes an aisle identifier that identifies the aisle and a shelf identifier that identifies the shelf.
13. The apparatus of claim 12 , wherein the means for determining the one or more words included in the acoustic signal further comprises:
means for processing the digital signal into one or more observations;
means for selecting one or more models for the one or more observations, wherein the one or more models represent one or more sounds that when combined form a pronunciation of the digital signal; and
means for identifying the one or more words from a database that includes words and corresponding models by comparing the selected one or more models with the corresponding models.
14. The apparatus of claim 12 , further comprising:
means for receiving the acoustic signal.
15. An article of manufacture including a tangible digital storage medium having instructions stored thereon that, if executed by a voice recognition system, cause the voice recognition system, to perform operations including:
converting an acoustic signal into a digital signal, wherein the acoustic signal represents a request for location information associated with an item having an association with an aisle and a shelf;
monitoring for a user-definable setting, wherein the user-definable setting comprises a trigger word transmitted to the voice recognition system;
determining one or more words included in the acoustic signal based at least in part on the digital signal and said monitoring; and
providing feedback to the request for location information based at least in part on the determined one or more words, wherein the feedback includes an aisle identifier that identifies the aisle and a shelf identifier that identifies the shelf.
16. The article of manufacture of claim 15 , wherein said determining one or more words:
processing the digital signal into one or more observations;
selecting one or more models for the one or more observations, wherein the one or more models represent one or more sounds that when combined form a pronunciation of the digital signal; and
identifying the one or more words from a database that includes words and corresponding models by comparing the selected one or more models with the corresponding models.