Digital assistant and associated methods for a transportation vehicle

• US 9,972,312 B2
• Filed: 08/19/2016
• Issued: 05/15/2018
• Est. Priority Date: 08/19/2016
• Status: Active Grant

• Current Assignee: Panasonic Avionics Corporation (Panasonic Holdings Corporation)
• Original Assignee: Panasonic Avionics Corporation (Panasonic Holdings Corporation)
• Inventors: Hilal, Rawad, Khabrani, Gurmukh, Perng, Chin, Kaji, Ruchi
• Primary Examiner(s): Hang, Vu B
• Application Number:
  US15/241,376
• Publication Number:
  US 20180053501A1
• Time in Patent Office: 634 Days
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• 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 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/225 Feedback of the input speech

Abstract

Methods and systems for a transportation vehicle are provided. For example, one method includes receiving a user input by a processor executable, digital assistant at a device on a transportation vehicle; determining by the digital assistant a relationship between words of the user input; using a trained dataset by the digital assistant to ascertain an intended action based on the user input; and providing a response by the digital assistant for the user input, where the response includes performing the intended action using another device on the transportation vehicle.

Claims

1. A machine implemented method, the method comprising:

receiving a user input by a processor executable, digital assistant at a device on a transportation vehicle;

determining by the digital assistant an initial relationship between words of the user input by tagging user input words with a grammatical connotation;

using a trained dataset selected from among a plurality of categories by the digital assistant to generate a constituent tree for establishing a detailed relationship between words of the user input;

wherein the plurality of categories store metadata identifying actions for each of the plurality of categories that include one or more of an entertainment data category for entertainment related actions, a shopping category for shopping related actions, a crew instructions category, and a security category associated with transportation vehicle security and wherein the trained dataset is machine learned and updated based on user feedback over time; and

providing a response by the digital assistant for the user input based on evaluation of the constituent tree, where the response includes performing an intended action for the user input by making an application programming interface (API) call to another device on the transportation vehicle.

2. The method of claim 1, wherein a natural language parser of the digital assistant determines the relationship between words of the user input.

3. The method of claim 1, wherein a natural language interpreter of the digital assistant uses the trained dataset for determining the intended action.

4. The method of claim 1, wherein the other device provides entertainment on the transportation vehicle.

5. The method of claim 1, wherein the other device is a seat function controller for controlling functions associated with a seat on the transportation vehicle.

6. The method of claim 1, wherein the user input is a voice command that is converted to text for a natural language parser evaluation.

7. The method of claim 1, wherein the transportation vehicle is one of an aircraft, a train, a bus, a ship and a recreation vehicle, the method further comprising training of the dataset onboard the transportation vehicle.

8. A machine implemented method, the method comprising:

storing a trained dataset for training a processor executable, digital assistant executed by a seat device of an aircraft, where the trained dataset is selected from among a plurality of categories to generate a constituent tree for establishing a detailed relationship between one or more words in a user request received by the seat device on the aircraft;

wherein the plurality of categories store metadata identifying actions for each of the plurality of categories that include one or more of a flight data category for flight data related actions, an entertainment data category for entertainment related actions, a shopping category for shopping related actions, a crew instructions category, and a security category associated with aircraft security, and wherein the trained dataset is machine learned and updated based on user feedback over time;

converting the user request into text by the digital assistant, when the user request is a voice command;

determining by the digital assistant an initial relationship between words in the user request by tagging user input words with a grammatical connotation;

using the trained dataset by the digital assistant to ascertain the intended action by evaluating the constituent tree; and

providing a response by the digital assistant by performing an intended action for the user request, where the intended action involves generating an application programming interface (API) call for using an inflight entertainment system on the aircraft.

9. The method of claim 8, wherein the intended action involves using a seat function controller that controls functions associated with an aircraft seat.

10. The method of claim 8, wherein the intended action is for executing a shopping request using the seat device on the aircraft.

11. The method of claim 8, wherein the intended action is for providing flight data to the user.

12. The method of claim 8, wherein the intended action is for providing assistance by a crew member on the aircraft.

13. The method of claim 8, wherein the intended action is to set a reminder for the user on the aircraft, the method further comprising providing training of the dataset onboard the vehicle.

14. A system comprising:

a memory including a machine readable medium comprising machine executable code; and

a processor module coupled to the memory, the processor module executing the machine executable code for a digital assistant to;

receive a user input at a device on a transportation vehicle;

determine an initial relationship between words of the user input by tagging user input words with a grammatical connotation;

use a trained dataset selected from among a plurality of categories to generate a constituent tree for establishing a detailed relationship between words of the user input;

wherein the plurality of categories store metadata identifying actions for each of the plurality of categories that include one or more of an entertainment data category for entertainment related actions, a shopping category for shopping related actions, a crew instructions category, and a security category associated with transportation vehicle security and wherein the trained dataset is machine learned and updated based on user feedback over time; and

provide a response for the user input based on evaluation of the constituent tree, where the response includes performing an intended action for the user input by making an application programming interface (API) call to another device on the transportation vehicle.

15. The system of claim 14, wherein a natural language parser of the digital assistant determines the relationship between words of the user input.

16. The system of claim 14, wherein a natural language interpreter of the digital assistant uses the trained dataset for determining the intended action.

17. The system of claim 14, wherein the other device provides entertainment on the transportation vehicle.

18. The system of claim 14, wherein the other device is a seat function controller for controlling functions associated with a seat on the transportation vehicle.

19. The system of claim 14, wherein the user input is a voice command that is converted to text for a natural language parser evaluation.

20. The system of claim 14, wherein the transportation vehicle is one of an aircraft, a train, a bus, a ship and a recreation vehicle, and the trained dataset is based at least in part on training of the dataset onboard the transportation vehicle.