Systems and Methods for Enabling Natural Language Processing

• US 20120233207A1
• Filed: 05/24/2012
• Published: 09/13/2012
• Est. Priority Date: 07/29/2010
• Status: Active Grant

• Current Assignee: Soundhound AI IP LLC
• Original Assignee: SoundHound Incorporated
• Inventors: Mohajer, Keyvan
• Granted Patent: US 8,694,537 B2
• Time in Patent Office: Days
• US Class Current: 707/769
• CPC Class Codes: G06F 16/1748 De-duplication implemented within the file system, e.g. based on file segments de-duplication techniques in storage systems for the management of data blocks G06F3/0641
• CPC Class Codes: G06F 16/3334 Selection or weighting of terms from queries, including natural language queries
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 2015/0635 updating or merging of old and new templates; Mean values; Weighting

Abstract

Systems and methods for searching databases by sound data input are provided herein. A service provider may have a need to make their database(s) searchable through search technology. However, the service provider may not have the resources to implement such search technology. The search technology may allow for search queries using sound data input. The technology described herein provides a solution addressing the service provider'"'"'s need, by giving a search technology that furnishes search results in a fast, accurate manner. In further embodiments, systems and methods to monetize those search results are also described herein.

Claims

1. A method for processing natural language queries, the method comprising:

receiving two or more natural language libraries from service providers via a network, where each natural language library comprises;

natural language queries for interacting with a client application; and

responses for the natural language queries;

generating an aggregated natural language library from the received natural language libraries;

receiving a search query via the network;

comparing the search query to the aggregated natural language library to determine at least one natural language query that corresponds to the search query; and

providing a response to the search query from the aggregated natural language library to a client device.

2. The method according to claim 1, further comprising storing the two or more natural language libraries and the aggregated natural language library in a database.

3. The method according to claim 1, wherein the aggregated natural language library includes a plurality of aggregated natural language sub-libraries, each of the aggregated natural language sub-libraries comprising natural language libraries with substantially similar subject matter that are combined together.

4. The method according to claim 3, wherein each natural language sub-library is associated with a client application that provides a service.

5. The method according to claim 3, further comprising providing access to an aggregated natural language sub-library to a service provider having a client application that provides a service that is substantially similar to the service associated with the aggregated natural language sub-library.

6. The method according to claim 1, further comprising determining a natural language query for a requested service included in the search query, the search query comprising sound input.

7. The method according to claim 6, wherein when the natural language query does not correspond to at least one query included in the aggregated natural language library, the natural language query is provided to a plurality of service providers that each have an application that provides a service that is substantially similar to the requested service associated with the natural language query.

8. The method according to claim 7, further comprising receiving at least one response to the natural language query from the plurality of service providers.

9. The method according to claim 8, further comprising receiving feedback from the client regarding accuracy of the response.

10. The method according to claim 1, wherein a natural language query comprises a request to interact with a client application that provides a service.

11. The method according to claim 1, wherein the aggregated natural language library comprises a rule-based model for processing natural language queries.

12. A natural language query processor, comprising:

a memory for storing executable instructions;

a processor for executing instructions stored in memory to;

receive natural language libraries from service providers via a network, where each natural language library comprises;

natural language queries for interacting with a client application; and

responses for the natural language queries;

generate an aggregated natural language library from the received natural language libraries;

receive a search query via the network from at least one client;

compare the search query to the aggregated natural language library to determine at least one natural language query that corresponds to the search query; and

providing a response to the search query from the aggregated natural language library to a client device.

13. The processor according to claim 12, wherein the processor further stores the natural language libraries and the aggregated natural language library in a database.

14. The processor according to claim 12, wherein the aggregated natural language library includes a plurality of aggregated natural language sub-libraries, each of the aggregated natural language libraries comprising substantially similar natural language libraries that are combined together based upon the service associated with the natural language libraries.

15. The processor according to claim 14, wherein the processor further provides access to an aggregated natural language sub-library to a service provider having a client application that provides a service that is substantially similar to the service associated with the aggregated natural language sub-library.

16. The processor according to claim 12, wherein the processor further determines a natural language query included in the search query, the natural language query being associated with a requested service, the search query comprising sound input.

17. The processor according to claim 16, wherein when the natural language query does not correspond to at least one natural language query included in the aggregated natural language library, the natural language query is provided to a plurality of service providers that each have an application that provides a service that is substantially similar to the requested service associated with the natural language query.

18. The processor according to claim 17, wherein the processor further receives at least one response to the natural language query from the plurality of service providers.

19. The processor according to claim 18, wherein the processor further receives feedback from the service provider regarding accuracy of the response.

20. The processor according to claim 12, wherein a natural language query comprises a request to interact with a client application that provides a service.

21. A method for processing natural language queries, the method comprising:

receiving a search query via the network;

comparing the search query to a customized natural language library to determine a customized response for the search query, the natural language library comprising customized responses for the natural language queries that are tailored to any of the service provider and the client application; and

providing a response to the search query from the aggregated natural language library to a client device.

22. The method according to claim 21, wherein the customized response comprises any of an action relative to the client application, meta-data corresponding to an object, or combinations thereof.

23. The method according to claim 21, further comprising selecting the customized natural language library based upon an accuracy of the customized response relative to other customized responses generated by other customized natural language libraries.

24. The method according to claim 21, further comprising generating an aggregated natural language library from two or more customized natural language libraries.

25. The method according to claim 24, further comprising periodically updating the aggregated natural language library by any of:

adding one or more additional customized natural language libraries, updating at least one of the two or more customizable customized natural language libraries, or combinations thereof.

26. The method according to claim 21, the customized natural language library comprising a rule-based model for processing natural language queries, the rule-based model being trained on natural language queries for interacting with a client application.

27. A method for processing a search query, the method comprising:

receiving a sound input from a client device via a network;

analyzing at least a portion of terms included in the sound input to determine a subject matter for the sound input;

selecting a customized language model for fulfilling the sound input based upon the subject matter of the sound input, the customized language model being utilizable by a speech engine to translate sound input to text;

translating the sound input to text; and

providing the text to the client device via the network.

28. The method according to claim 27, wherein analyzing at least a portion of terms included in the sound input to determine a subject matter for the sound input comprises matching at least a portion of the sound input to a natural language library, the natural language library comprising a subject matter.