Integration manager and natural interaction processor

• US 7,480,619 B1
• Filed: 03/04/2004
• Issued: 01/20/2009
• Est. Priority Date: 03/04/2003
• Status: Expired due to Fees

• Current Assignee: Board of Trustees of the Leland Stanford Junior University (Stanford Management Co.)
• Original Assignee: Board of Trustees of the Leland Stanford Junior University (Stanford Management Co.)
• Inventors: Scott, Neil G.
• Primary Examiner(s): Hudspeth; David R
• Assistant Examiner(s): ALBERTALLI, BRIAN LOUIS
• Application Number:
  US10/793,183
• Time in Patent Office: 1,783 Days
• Field of Search: None
• US Class Current: 704/275
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04M 1/72475 specially adapted for disabled users
• CPC Class Codes: H04M 2250/74 with voice recognition means voice activated dialling H04M1/271; voice recognition algorithms G10L15/00

Abstract

Natural interaction command decoder implemented on small embedded microprocessors. Strings of text from multiple input sources are merged to create commands. Words that are meaningful within the current system context are linked to all dependent output events while words that have no meaning within the current system context are automatically discarded.

Claims

1. A system for interfacing a user with an electronic device, comprising:

an integration manager embedded in a small microprocessor device that receives an input message from at least one of a plurality of input devices, analyzes the input message to determine user intent, and translates user intent into a command to send to a target electronic device;

a parsing tree for detecting words in the input message that are in a predefined corpus of commands that are recognized by the system, and filtering out unrecognized words in the input message;

an event decoding matrix for reading inputs recognized by the parsing tree and determining an event associated with the recognized words, wherein the event represents a single command or a macro that initiates a plurality of commands;

a command generator for receiving an event from the event decoding matrix and generating commands for the target device; and

an output packet manager for building command packets based on the commands generated by the command generator and routing the command packets to the target electronic device to control that device.

2. The system for interfacing a user with an electronic device of claim 1 further comprising a word pointer table for receiving word pointers from the parsing tree wherein each entry in the table represents a word and the word'"'"'s corresponding synonyms, the entry pointing to a string in an array of strings that specifies where each word appears in the event decoding matrix.

3. The system for interfacing a user with an electronic device of claim 1 further comprising an event mask string array wherein each string in the array specifies each use of a recognized word in the event decoding matrix.

4. The system for interfacing a user with an electronic device of claim 1 wherein the at least one input device is selected from a group comprising a speech recognition device, a keyboard, a touch input device, a motion sensor, and a gesture recognition device.

5. The system for interfacing a user with an electronic device of claim 1 wherein the input message is derived from a user gesture or a plurality of encoded characters.

6. The system for interfacing a user with an electronic device of claim 1 wherein a separate independent input channel is used for each input device, with each input channel including a pointer to a current node in the parsing tree as the parsing tree is traversed.

7. The system for interfacing a user with an electronic device of claim 1 wherein the integration manager integrates input messages from a plurality of input devices into a single message stream for parsing by the parsing tree.

8. The system for interfacing a user with an electronic device of claim 1 wherein the event decoding matrix processes events specified by commands in which the words are received in a random order.

9. The system for interfacing a user with an electronic device of claim 1 wherein the event decoding matrix processes events in which commands for the target device must be received with the words in a defined order.

10. The system for interfacing a user with an electronic device of claim 1 wherein the event decoding matrix processes a plurality of parameters to control a timing of specific commands for execution on the target device.

11. The system for interfacing a user with an electronic device of claim 1 further comprising a command and macro manager for receiving events from the event decoding matrix and generating at least one of a command definition string and a macro definition string to input to the command generator.

12. The system for interfacing a user with an electronic device of claim 11 wherein the command definition string specifies an actual code that is sent to the target device to perform a specified command.

13. The system for interfacing a user with an electronic device of claim 11 wherein the macro definition string specifies a group of commands that are to be decoded by command definition strings and sent to the target device.

14. The system for interfacing a user with an electronic device of claim 1 wherein the integration manger operates independently of each of the plurality of input devices.