Method and system for presenting a user selectable interface in response to a natural language request

• US 10,552,410 B2
• Filed: 11/14/2017
• Issued: 02/04/2020
• Est. Priority Date: 11/14/2017
• Status: Active Grant

• Current Assignee: MindBridge Analytics, Inc.
• Original Assignee: MindBridge Analytics, Inc.
• Inventors: Milligan, Nicolas Yvon Elijah, Grosset, Robin Neil
• Primary Examiner(s): Jacob, Ajith
• Application Number:
  US15/812,710
• Publication Number:
  US 20190147083A1
• Time in Patent Office: 812 Days
• CPC Class Codes: G06F 16/2428 Query predicate definition using graphical user interfaces, including menus and forms G06F16/2423 takes precedence
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/3344 using natural language analysis

Abstract

The present invention discloses numerous implementations of system and method which receives a user request and, using methods of natural language processing including part of speech tagging, analyses the user request to generate a query to a database of information. Based on the machine understanding, the system presents an interactive representation of the uttered request back to the user. This provides context to the user, which explains the machine understanding of the request and acts as an interface to iteratively refine or adjust the machine understanding by altering specific elements of the uttered language. The methods of altering specific elements of the uttered language may vary depending on the element and a variety of user selectable interfaces may be used to display one or more queried elements along with alternative elements pertaining to the queried element. The user could select an alternative element and change the database query.

Claims

1. A method comprising:

receiving a natural language request for a database query from a user;

identifying a plurality of words in the natural language request including at least one queried element, the queried element associated with an intent by the user for the database query;

determining at least one alternative element for the queried element, the alternative element associated with a possible alternative intent for the database query not included in the natural language request; and

presenting a visual representation of the natural language request to the user, the visual representation comprising a set of the words identified in the natural language request and a user selectable interface enabling the user to select the queried element or the alternative element to include in the database query.

2. The method according to claim 1 further comprising:

causing a first database query to a database using elements from the natural language request including the queried element;

receiving results from the database in response to the first database query; and

presenting the results of the first database query to the user concurrently with presenting the visual representation of the natural language request including the user selectable interface to the user.

3. The method according to claim 2 further comprising:

receiving a selection of the alternative element from the user selectable interface;

causing a second database query to the database using elements from the natural language query with the selected alternative element instead of the queried element;

receiving results from the database in response to the second database query; and

presenting the results of the second database query to the user.

4. The method according to claim 3 further comprising presenting the visual representation of the natural language query with the selected alternative element replacing the queried element.

5. The method according to claim 1, wherein the user selectable interface comprises a selectable element within the visual representation of the natural language query;

and wherein, if the user selects the selectable element, the method comprises presenting a menu with the queried element and the alternative element selectable by the user.

6. The method according to claim 5, wherein the selectable element is a visual representation of the queried element.

7. The method according to claim 1, wherein the determining at least one alternative element for the queried element comprises determining a plurality of alternative elements for the queried element, each of the plurality of alternative elements being associated with a different possible alternative intent for the database query not included in the natural language request.

8. The method according to claim 3, wherein the database comprises a plurality of records, each record comprising an entry for each of a plurality of attributes of the records;

wherein the queried element comprises one of the attributes of the records as a queried attribute and the alternative element comprises another one of the attributes of the records as an alternative attribute; and

wherein the results from the first database query comprises a subset of the plurality of records at least partially determined based upon the queried attribute and the results from the second database query comprises a subset of the plurality of records at least partially determined based upon the alternative attribute.

9. The method according to claim 3, wherein the database comprises a plurality of records sortable by a plurality of metadata components, each of the records comprising a value for each of the metadata components;

wherein the queried element comprises one of the metadata components and the alternative element comprises another one of the metadata components; and

wherein the results from the first query comprises a subset of the plurality of records determined based upon the metadata component of the queried element and the results from the second query comprises a subset of the plurality of records determined based upon the metadata component of the alternative element.

10. The method according to claim 1 further comprising identifying a subject in the natural language query associated with the queried element;

wherein the queried element is a relative term associated with the subject;

wherein the queried element relates to a first context of the subject and the alternative element relates to a second context of the subject.

11. The method according to claim 10, wherein the first context of the subject comprises one of an increase in value and a decrease in value of the subject and the second context of the subject comprises the other one of the increase in value and the decrease in value of the subject.

12. The method according to claim 1 further comprising:

identifying a queried relative term associated with the queried element in the natural language query, the queried relative term relating to a first context of the queried element; and

determining at least one alternative relative term to the queried relative term, the alternative relative term relating to a second context of the queried element;

wherein the user selectable interface comprises a first user selectable interface and the visual representation of the natural language query comprises a second user selectable interface enabling the user to select the queried relative term or the alternative relative term to include in the natural language query.

13. The method according to claim 12, wherein the first context of the queried element comprises one of an increase in value and a decrease in value of the queried element and the second context of the queried element comprises the other one of the increase in value and the decrease in value of the queried element.

14. The method according to claim 1, wherein the identifying at least one queried element comprises identifying first and second queried elements in the natural language query;

and wherein the determining at least one alternative element to the queried element comprises determining at least one first alternative element to the first queried element and determining at least one second alternative element to the second queried element, the first alternative element being categorized with the first queried element and the second alternative element being categorized with the second queried element; and

wherein the user selectable interface comprises a first user selectable interface enabling the user to select one of the first queried element and the first alternative element to include in the natural language query and the visual representation of the natural language query comprises a second user selectable interface enabling the user to select one of the second queried element and the second alternative element to include in the natural language query.

15. The method according to claim 1, wherein the receiving a natural language query from a user comprises receiving a verbal query from the user and the method further comprises interpreting the verbal query to determine a textual representation of the verbal query;

wherein the identifying at least one queried element in the natural language query comprises identifying at least one queried element in the textual representation of the verbal query.

16. The method according to claim 1, wherein the receiving a natural language query from a user comprising receiving a textual query from the user;

wherein the identifying at least one queried element in the natural language query comprises identifying at least one queried element in the textual query.

17. A computing system operable to be coupled to a user input device and a visual display, comprising:

a database interface; and

a processing apparatus coupled to the database interface, the processing apparatus operable to receive a natural language request for a database query from a user via the user input device;

to identify a plurality of words in the natural language request including at least one queried element, the queried element associated with an intent by the user for the database query;

to determine at least one alternative element for the queried element, the alternative element associated with a possible alternative intent for the database query not included in the natural language request; and

to present a visual representation of the natural language request on the visual display, the visual representation comprising a set of the words identified in the natural language request and a user selectable interface enabling the user to select the queried element or the alternative element to include in the database query.

18. The computing system according to claim 17, wherein the processing apparatus is further operable to cause a first database query to a database via the database interface using elements from the natural language request including the queried element;

to receive results from the database via the database interface in response to the first database query; and

to present the results of the first database query on the visual display concurrently with presenting the visual representation of the natural language request including the user selectable interface on the visual display.

19. The computing system according to claim 18, wherein the processing apparatus is further operable to receive a selection of the alternative element from the user selectable interface;

to cause a second database query to the database via the database interface using elements from the natural language query with the selected alternative element instead of the queried element;

to receive results from the database via the network interface in response to the second database query;

to present the results of the second database query on the visual display; and

to present the visual representation of the natural language query with the selected alternative element replacing the queried element on the visual display.

20. Non-transitory computer-readable media containing a program element executable by a computing system to perform a method for presenting a visual representation of a natural language query, the computer-readable media comprising:

first program code for receiving a natural language request for a database query from a user;

second program code for identifying a plurality of words in the natural language request including at least one queried element, the queried element associated with an intent by the user for the database query;

third program code for determining at least one alternative element for the queried element, the alternative element associated with a possible alternative intent for the database query not included in the natural language request; and

fourth program code for presenting a visual representation of the natural language request to the user, the visual representation comprising a set of the words identified in the natural language request and a user selectable interface enabling the user to select the queried element or the alternative element to include in the database query.