Processing natural language user inputs using context data

• US 10,276,154 B2
• Filed: 04/23/2014
• Issued: 04/30/2019
• Est. Priority Date: 04/23/2014
• Status: Active Grant

• Current Assignee: Lenovo PC International Limited (Lenovo Group Ltd.)
• Original Assignee: Lenovo Singapore Pte Limited (Lenovo Group Ltd.)
• Inventors: Waltermann, Rod D., Beaumont, Suzanne Marion, VanBlon, Russell Speight, Robinson, Douglas Warren
• Primary Examiner(s): Colucci, Michael C
• Application Number:
  US14/259,672
• Publication Number:
  US 20150310861A1
• Time in Patent Office: 1,833 Days
• Field of Search: 704275, 704246, 704235, 7042701, 707766, 707771, 715719, 715728
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning

Abstract

An embodiment provides a method, including: receiving, at a device, user input; identifying, using a processor, elements included in the user input; determining, using a processor, that at least one of the identified elements renders the user input ambiguous; identifying, using a processor, a source of context data; accessing, using a processor, context data associated with the user input from the source of context data; disambiguating, using a processor, the user input based on the context data associated with the user input; and forming, using a processor, an altered input based on the disambiguating. Other embodiments are described and claimed.

Claims

1. A method, comprising:

receiving, at a user device, user input;

identifying, using a processor, at least one element included in the user input, wherein

the at least one element renders the user input ambiguous;

identifying, using a processor, context data associated with the user input from a source of context data comprising another user device producing active media;

disambiguating, using a processor, the user input based on an association between the at least one element and an aspect of the active media, wherein the aspect is identified at least in part during a duration of the active media that the user input is received; and

automatically forming, using a processor, an altered input based on the disambiguating.

2. The method of claim 1, further comprising identifying one or more other user devices;

wherein the source of context data is located on at least one of the one or more other user devices.

3. The method of claim 2, wherein the identifying one or more other user devices comprises utilizing short range wireless communication of the device to identify that the one or more other user devices are proximate to the user device.

4. The method of claim 3, further comprising sending a request for contextual data from the device to the one or more other user devices.

5. The method of claim 4, wherein the request for contextual data includes an indication selected from the group consisting of a media type identifier, a word derived from the user input, and a request for additional data capture.

6. The method of claim 5, wherein the request includes an instruction to capture additional data using one or more sensors of the one or more other user devices.

7. The method of claim 6, wherein the one or more sensors are selected from the group of sensors consisting of a camera and a microphone.

8. The method of claim 7, wherein the additional data is utilized to prepare contextual data.

9. The method of claim 1, further comprising committing a predetermined action based on the altered input.

10. The method of claim 9, wherein the predetermined action comprises transmitting the altered input to at least one other device for execution.

11. A device, comprising:

an input device;

a processor; and

a memory device that stores instructions executable by the processor to;

receive, via the input device, user input;

identify at least one element included in the user input, wherein

the at least one element renders the user input ambiguous;

identify context data associated with the user input from a source of context data comprising another user device producing active media;

disambiguate the user input based on an association between the at least one element and an aspect of the active media, wherein the aspect is identified at least in part during a duration of the active media that the user input is received; and

automatically form an altered input based on the disambiguated user input.

12. The device of claim 11, wherein the instructions are executable by the processor to identify one or more other user devices;

wherein the source of context data is located on at least one of the one or more other user devices.

13. The device of claim 12, wherein to identify one or more other user devices comprises utilizing short range wireless communication of the device to determine that the one or more other user devices are proximate to the device.

14. The device of claim 13, wherein the instructions are executable by the processor to send a request for contextual data from the device to the one or more other user devices.

15. The device of claim 14, wherein the request for contextual data includes an indication selected from the group consisting of a media type identifier, a word derived from the user input, and a request for additional data capture.

16. The device of claim 15, wherein the request includes an instruction to capture additional data using one or more sensors of the one or more other user devices.

17. The device of claim 16, wherein the one or more sensors are selected from the group of sensors consisting of a camera and a microphone.

18. The device of claim 17, wherein the additional data is utilized to prepare contextual data.

19. The device of claim 11, wherein the instructions are executable by the processor to commit a predetermined action based on the disambiguated input.

20. A product, comprising:

a storage medium having code stored therewith, the code being executable by a processor and comprising;

code that receives, via an input device, user input;

code that identifies, using a processor, at least one element included in the user input, wherein

the at least one element renders the user input ambiguous;

code that identifies, using a processor, context data associated with the user input from a source of context data comprising another user device producing active media;

code that disambiguates, using a processor, the user input based on an association between the at least one element and an aspect of the active media, wherein the aspect is identified at least in part during a duration of the active media that the user input is received; and

code that automatically forms, using a processor, an altered input based on the disambiguated user input.

21. A method, comprising:

receiving, from a device, data relating to a user input;

the data being used to identify, using a processor, at least one ambiguity contained in the user input, wherein the at least one ambiguity is based upon at least one element included within the user input;

identifying, using a processor, context data associated with the user input from a source of context data comprising another user device producing active media;

disambiguating, using a processor, the user input based on an association between the at least one element and an aspect of the active media, wherein the aspect is identified at least in part during a duration of the active media that the user input is received; and

automatically forming, using a processor, an altered input based on the disambiguated user input.