Natural Language Module Store

• US 20170154628A1
• Filed: 11/30/2015
• Published: 06/01/2017
• Est. Priority Date: 11/30/2015
• Status: Active Grant

• Current Assignee: Soundhound AI IP LLC (SoundHound AI, Inc. (f/k/a Archimedes Tech SPAC Partners Co.))
• Original Assignee: SoundHound, Inc. (SoundHound AI, Inc. (f/k/a Archimedes Tech SPAC Partners Co.))
• Inventors: Mohajer, Kamyar, Singh, Pranav, Mohajer, Keyvan, Mont-Reynaud, Bernard
• Granted Patent: US 10,102,201 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06Q 20/102 Bill distribution or payments
• CPC Class Codes: G06Q 30/0283 Price estimation or determination
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

The present invention extends to methods, systems, and computer program products for a natural language module store. In general, the invention can be used to manage natural language modules offered through a natural language module store. Natural language module (NLM) developers can post NLMs at a NLM store to make the NLMs available for use by others. Developers can select NLMs for inclusion in natural language interpreters (NLIs) containing (and possibly integrating the functionality of) one or more NLMs. Prior to selecting a NLM, a developer can search or browse NLMs to identify an appropriate NLM. Optionally, a developer can test a NLM in the NLM store prior to inclusion in an NLI. For example, multiple NLMs purporting to provide the same specified natural language functionality can be tested relative to one another prior to selection of one of the NLMs for inclusion in an NLI.

Claims

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

receiving the natural language query for the application;

a natural language processor using one or more natural language modules to interpret the natural language query for the application; and

for each of the one or more natural language modules;

calculating a charge for processing the natural language query, the charge determined in accordance with a pricing model defined for the natural language module.

2. The method of claim 1, further comprising transferring payment for a portion of the calculated charge from an owner of the application to a developer of the natural language module.

3. The method of claim 1, further comprising transferring payment for a portion of the calculated charge from an owner of the application to an owner of the natural language processor.

4. The method of claim 1, wherein the natural language query is a spoken command.

5. The method of claim 4, wherein calculating the charge for processing the natural language query comprises calculating part of the charge based on the duration of verbal input used to issue the spoken command.

6. The method of claim 1, wherein the natural language query is text input.

7. The method of claim 1, wherein calculating a charge for processing the natural language query comprises calculating a module usage charge for using the natural language module to interpret the natural language query.

8. The method of claim 1, wherein calculating a charge for processing the natural language query comprises:

determining an additional charge for use of a third party service, the third party service used to identify data or take action responsive to the natural language query; and

adding the additional charge to the charge for processing the natural language query.

9. A method for assembling natural language recognition functionality in a language interpreter, the method comprising:

selecting one or more natural language modules from a natural language module store, each natural language module associated with a pricing model for determining charges associated with usage of the natural language module by the natural language interpreter;

sending instructions to add the one or more natural language modules to the natural language interpreter; and

sending an instruction to register the natural language interpreter with an owner of the natural language module store so that charges associated with the one or more natural language modules can be assessed for the owner of the natural language interpreter.

10. The method of claim 9, wherein the natural language interpreter is an application.

11. The method of claim 10, wherein sending instructions to add the one or more natural language modules to the natural language interpreter comprises sending instructions to add the one or more natural language modules to the application;

and

wherein sending an instruction to register the natural language interpreter with an owner of the natural language module store comprises sending an instruction to register the application with an owner of the natural language module store so that charges associated with the one or more natural language modules can be assessed for the owner of the application.

12. The method of claim 9, wherein the natural language interpreter is a natural language package.

13. The method of claim 12, wherein sending instructions to add the one or more natural language modules to the natural language interpreter comprises sending instructions to add the one or more natural language modules to the natural language package.

14. The method of claim 12, further comprising accessing an additional pricing model for the natural language package, the additional pricing model for determining charges associated with usage of the natural language package.

15. The method of claim 14, further comprising:

detecting use of a natural language module in the natural language package by an application;

determining a package charge to be assessed by the owner of the natural language package against the owner of the application, the package charge determined in accordance with the additional pricing model;

determining a module charge to be assessed by the owner of the natural language module against the owner of the natural language package, the module charge determined in accordance with a pricing model for the natural language module;

transferring payments between one or more accounts within a natural language store to settle the package charge and the module charge.

16. The method of claim 9, further comprising, prior to adding the natural language module to the natural language interpreter, comparing the natural language module to one or more other natural language modules in a side-by-side comparison.

17. The method of claim 9, wherein comparing the natural language module to one or more other natural language modules in a side-by-side comparison comprises comparing one or more of:

a brand identity of the each natural language module provider, survey ratings for the each natural language module provider, and pricing models for the one or more other natural language modules.

18. The method of claim 9, wherein a natural language module, from among the selected one or more natural language modules, is a private natural language module, further comprising sending access credentials for the natural language module prior to sending instructions to add the one or more natural language modules to the natural language interpreter.

19. A method for assessing natural language recognition functionality for one or more natural language recognition modules, the method comprising:

selecting one or more natural language modules, each of the one or more natural language modules configured to provide specified natural language functionality;

for the one or more natural language modules, testing each of the one or more natural language modules another by;

for each natural language module, exercising one or more test cases including evaluating the ability of the natural language module to interpret a natural language query input to the natural language module; and

verifying the accuracy of results from such interpretation.

20. The method of claim 19, further comprising, prior to adding a natural language module to a natural language module package, comparing the results of testing the plurality of natural language modules to one another in a side-by-side comparison.

21. The method of claim 20, wherein comparing the results in a side-by-side comparison comprises testing the plurality of natural language modules using one or more pre-defined test use cases

22. The method of claim 20, wherein comparing the results in a side-by-side comparison comprises testing the performance of each of the plurality of natural language modules against one or more test databases.

23. The method of claim 19, wherein selecting one or more natural language modules comprises entering access credentials for at least one private natural language module.

24. A method for selecting a natural language module from a natural language module store comprising:

inputting a natural language query to the natural language module store;

receiving from the natural language module store a list of one or more natural language modules, each of the one or more natural language modules capable of interpreting at least a part of the natural language query; and

selecting a natural language module from among the one or more natural language modules.

25. The method of claim 24, wherein selecting a natural language module from a natural language module store comprises:

browsing through a plurality of natural language modules presented by the natural language module store; and

selecting a natural language module from among the plurality of natural language modules.

26. The method of claim 24, wherein receiving from the natural language module store a list of one or more natural language modules comprises receiving a private natural language module;

and

wherein selecting a natural language module from among the one or more natural language modules comprises entering access credentials for the private natural language module.

27. A method for making natural language recognition functionality available for inclusion in a natural language interpreter, the method comprising

submitting a natural language module to a natural language module store;

submitting a pricing model to the natural language module store, the pricing model for use in tracking charges for using the natural language module; and

instructing the owner of the natural language module store to associate the pricing model with the natural language module so that the pricing model can be used to track charges for using the natural language module when the natural language module is included in a natural language interpreter.

28. A method for making natural language recognition functionality available for inclusion in a natural language interpreter, the method comprising:

receiving a natural language module from a developer;

receiving a corresponding pricing model from the developer, the corresponding pricing model for use in tracking charges for the natural language module;

receiving an instruction from the developer to associate the corresponding pricing model with the natural language module so that the pricing model can be used to track charges for the natural language module when the natural language module is included in a natural language interpreter; and

associating the pricing model with the natural language module.

29. The method of claim 28, further comprising:

receiving a selection of one or more natural language modules from a party creating a natural language interpreter, each of the one or more natural language modules associated with a corresponding module pricing model, each corresponding module pricing model for determining charges associated with usage of a natural language module;

adding the one or more natural language modules to the natural language interpreter,

receiving an additional pricing model for the package, the additional pricing model for determining charges associated with used of the natural language interpreter; and

registering the natural language interpreter with an owner of the natural language module store so that the corresponding pricing models and the additional pricing model can be used to assess charges against appropriate entities.

30. The method of claim 28, further comprising receiving an instruction from the developer to make the natural language module a private natural language module.