Systems and methods for editing and replaying natural language queries

• US 10,318,586 B1
• Filed: 08/19/2014
• Issued: 06/11/2019
• Est. Priority Date: 08/19/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Rose, Robert Brett, Owen, Gregory Brandon, Bottner, Keith Charles
• Primary Examiner(s): Nguyen, Cam Linh T
• Application Number:
  US14/463,189
• Time in Patent Office: 1,757 Days
• Field of Search: 707740
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30

Abstract

Systems and methods are disclosed herein for processing a natural language query. A receiver circuitry receives the natural language query from a user. A natural language interpreter circuitry parses the natural language query to convert the natural language query into a plurality of categories and a plurality of variables, each variable in the plurality of variables corresponding to one category in the plurality of categories. A user interface displays to the user the plurality of categories and the plurality of variables, and allows the user to modify at least one variable in the plurality of variables by providing a natural language utterance.

Claims

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

receiving, by a processor, a first natural language utterance from a user indicative of the natural language query;

parsing the natural language query to convert the natural language query into a converted query comprising a plurality of categories and a plurality of variables, each variable in the plurality of variables corresponding to a respective category of the plurality of categories;

providing the plurality of categories and the plurality of variables of the converted query for presentation;

responsive to receiving a user request to edit the converted query, automatically providing a plurality of replacement variables for a first category of the plurality of categories for presentation, wherein the first category is provided for the presentation based on the first natural language utterance from the user;

determining a second natural language utterance indicative of a selection of a first replacement variable from the presentation of the plurality of replacement variables for the first category of the plurality of categories;

responsive to determining the second natural language utterance indicative of the selection of the first replacement variable, modifying the converted query to generate a modified converted query comprising the first replacement variable for the first category;

providing a plurality of items for presentation based on the modified converted query;

receiving a user request to identify an example utterance that would have been converted into the modified converted query; and

responsive to the user request to identify the example utterance, providing the example utterance for presentation to the user in an audio format via an audio device, wherein the example utterance is different than the first natural language utterance and the second natural language utterance.

2. The method of claim 1, wherein the natural language query is a request to display a list of files on a file storage system.

3. The method of claim 2, further comprising filtering a plurality of user files based on the modified converted query.

4. The method of claim 1, further comprising receiving a natural language utterance indicative of a selection of one or more replacement categories for the plurality of categories.

5. The method of claim 4, further comprising determining whether to modify the modified converted query or generate a new query based on a number of the one or more replacement categories.

6. The method of claim 1, further comprising:

receiving a natural language utterance indicative of a request to undo the modification to the converted query to generate the modified converted query; and

providing search results responsive to the converted query.

7. The method of claim 1, further comprising in response to receiving a user input indicative of a request for a machine-generated natural language query, providing a machine-generated natural language utterance based on the modified converted query.

8. A system for processing a natural language query, the system comprising:

a memory; and

a processor coupled to the memory, the processor to;

receive a first natural language utterance from a user indicative of the natural language query;

parse the natural language query to convert the natural language query into a converted query comprising a plurality of categories and a plurality of variables, each variable in the plurality of variables corresponding to a respective category of the plurality of categories;

provide the plurality of categories and the plurality of variables of the converted query for presentation;

responsive to receiving a user request to edit the converted query, automatically provide a plurality of replacement variable for a first category of the plurality of categories for presentation, wherein the first category is provided for presentation based on the first natural language utterance from the user;

determine a second natural language utterance indicative of a selection of a first replacement variable from the presentation of the plurality of replacement variables for the first category of the plurality of categories;

responsive to determining the second natural language utterance indicative of the selection of the first replacement variable, modify the converted query to generate a modified converted query comprising the first replacement variable for the first category;

provide a plurality of items for presentation based on the modified converted query;

receive a user request to identify an example utterance that would have been converted into the modified converted query; and

responsive to the user request to identify the example utterance, provide the example utterance for presentation to the user in an audio format via an audio device, wherein the example utterance is different than the first natural language utterance and the second natural language utterance.

9. The system of claim 8, wherein the natural language query is a request to display a list of files on a file storage system.

10. The system of claim 9, wherein the file storage system is a web-based storage system and the plurality of categories includes at least two of:

a file type, a file owner, a time, or a location.

11. The system of claim 10, the processor further to filter a plurality of user files on the web-based storage system based on the modified converted query.

12. The system of claim 8, the processor further to receive a natural language utterance indicative of a selection of one or more replacement categories for the plurality of categories.

13. The system of claim 12, wherein the processor further to determine whether to modify the modified converted query or generate a new query based on a number of one or more replacement categories.

14. The system of claim 8, the processor further to:

receive a natural language utterance indicative of a request to undo the modification to the converted query to generate the modified converted query; and

provide search results responsive to the converted query.

15. The system of claim 8, wherein the processor is part of a server system.

16. The system of claim 8, wherein the example utterance comprises a machine-generated natural language query based on the modified converted query.

17. A non-transitory computer-readable medium comprising instructions that, responsive to execution by a processor, cause the processor to perform operations comprising:

receiving, by the processor, a first natural language utterance from a user indicative of a natural language query;

parsing the natural language query to convert the natural language query into a converted query comprising a plurality of categories and a plurality of variables, each variable in the plurality of variables corresponding to a respective category of the plurality of categories;

providing the plurality of categories and the plurality of variables of the converted query for presentation;

responsive to receiving a user request to edit the converted query, automatically providing a plurality of replacement variables for a first category of the plurality of categories for presentation, wherein the first category is provided for the presentation based on the first natural language utterance from the user;

determining a second natural language utterance indicative of a selection of a first replacement variable from the presentation of the plurality of replacement variables for the first category of the plurality of categories;

responsive to determining the second natural language utterance indicative of the selection of the first replacement variable, modifying the converted query to generate a modified converted query comprising the first replacement variable for the first category;

providing a plurality of items for presentation based on the modified converted query;

receiving a user request to identify an example utterance that would have been converted into the modified converted query; and

responsive to the user request to identify the example utterance, providing the example utterance for presentation to the user in an audio format via an audio device, wherein the example utterance is different than the first natural language utterance and the second natural language utterance.