Method and system for bridging disparate platforms to automate a natural language interface

• US 10,846,481 B2
• Filed: 01/24/2019
• Issued: 11/24/2020
• Est. Priority Date: 06/29/2018
• Status: Active Grant

• Current Assignee: Certinia, Inc.
• Original Assignee: FinancialForce.com Incorporated
• Inventors: Willcock, Stephen Paul, Wood, Matthew David
• Primary Examiner(s): McFadden, Susan I
• Application Number:
  US16/256,069
• Publication Number:
  US 20200004824A1
• Time in Patent Office: 670 Days
• Field of Search: 704 9
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 3/0481 based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation

Abstract

Presented here is a system and method to bridge the gap between the disparate platforms, and to allow the user to interface with the disparate platforms using a natural language interface. The system can improve user interface for electronic devices because the user does not have to switch between the disparate platforms. Instead, the user can interact with the disparate platforms through a single natural language interface. The disparate platforms, some of which may not have a natural language user interface, can be enabled to interact with the user through the natural language interface when the system interfaces between a natural language processing platform and the remainder of the disparate platforms.

Claims

1. A method comprising:

obtaining a plurality of disparate platforms and a plurality of actions, wherein each action in the plurality of actions can be performed by at least one platform in the plurality of disparate platforms, wherein a platform in the plurality of disparate platforms cannot communicate with a remainder of the plurality of disparate platforms;

receiving a natural language request from a user by a groupware platform, wherein the groupware platform is a part of the plurality of disparate platforms;

based on the plurality of actions and the plurality of disparate platforms, deciding to send the natural language request from the user to a natural language processing platform, wherein the groupware platform and the natural language processing platform are not configured to communicate to each other;

formatting the natural language request into a formatted natural language request accepted by the natural language processing platform;

sending the formatted natural language request to the natural language processing platform;

interpreting, by the natural language processing platform, the natural language request to identify a user requested action associated with the natural language request;

based on the plurality of actions and the plurality of disparate platforms, determining the platform in the plurality of disparate platforms that can perform the user requested action, wherein the platform, the groupware platform and the natural language processing platform are not configured to communicate to each other;

formatting the user requested action into a formatted user requested action accepted by the platform;

sending the formatted user requested action to the platform; and

performing the action.

2. The method of claim 1, comprising:

receiving a natural language response from the user in response to performing the action; and

providing a feedback to the natural language processing platform, wherein the feedback is reinforcing when the natural language response comprises a positive feedback and the feedback is discouraging when the natural language response comprises a negative feedback.

3. The method of claim 1, the plurality of disparate platforms comprising the natural language processing platform, an image analysis platform, and a human capital management database.

4. The method of claim 1, the user requested action comprising creating an expense report, or requesting a vacation.

5. The method of claim 1, said determining the platform comprising:

determining the platform that upon performing the user requested action has received a positive feedback more frequently than the remainder of the plurality of disparate platforms.

6. A method comprising:

receiving, by a multiplatform management system, a natural language request from a user;

interfacing, by the multiplatform management system, with a plurality of disparate platforms including a natural language processing platform, wherein each platform in the plurality of disparate platforms is configured to perform an action in a plurality of actions, said interfacing comprising formatting the natural language request into a formatted natural language request accepted by the natural language processing platform, and forwarding the formatted natural language request to the natural language processing platform;

receiving a user requested action from the natural language processing platform;

facilitating communication between the plurality of disparate platforms by determining a platform in the plurality of disparate platforms that can perform the user requested action, formatting the user requested action into a formatted user requested action accepted by the platform and sending the formatted user requested action to the platform; and

performing the action.

7. The method of claim 6, comprising:

receiving a natural language response from the user in response to performing the action; and

providing a feedback to the natural language processing platform, wherein the feedback is reinforcing when the natural language response comprises a positive feedback and the feedback is discouraging when the natural language response comprises a negative feedback.

8. The method of claim 6, the plurality of disparate platforms comprising the natural language processing platform, an image analysis platform, and a human capital management database.

9. The method of claim 6, the user requested action comprising creating a timecard entry, or an active project query.

10. The method of claim 6, said determining the action comprising:

determining a first confidence level associated with a first action in the plurality of actions and a second confidence level associated with a second action in the plurality of actions;

determining that the first confidence level is greater than the second confidence level; and

in response to said determining, selecting the first action as the action.

11. The method of claim 10, comprising:

when the first confidence level is below a predetermined threshold, asking the user for a confirmation prior to performing the action.

12. The method of claim 10, comprising:

upon receiving a positive feedback in response to selecting the first action, increasing the first confidence level; and

upon receiving a negative feedback in response to selecting the first action, decreasing the first confidence level.

13. The method of claim 6, said interpreting the natural language request comprising:

obtaining a natural language input from the user entered prior to the natural language request; and

interpreting the natural language request based on the natural language input entered prior to the natural language request.

14. A system comprising:

a groupware platform to receive a natural language request from a user and to forward the natural language request to a multiplatform management system;

the multiplatform management system to interface with a plurality of disparate platforms and to obtain a plurality of actions, each action in the plurality of actions can be performed by at least one platform in the plurality of disparate platforms, the multiplatform management system to receive the natural language request, to format the natural language request into a formatted natural language request accepted by a natural language processing platform, and to forward the formatted natural language request to the natural language processing platform;

the natural language processing platform to receive the formatted natural language request, to identify a user requested action associated with the natural language request, and to forward the identified user requested action to the multiplatform management system;

the multiplatform management system to facilitate communication between the plurality of disparate platforms by determining a platform in the plurality of disparate platforms that can perform the user requested action, formatting the user requested action into a formatted user requested action accepted by the platform and sending the formatted user requested action to the platform; and

the platform to perform the action.

15. The system of claim 14, comprising:

the groupware platform to receive a natural language response from the user and to forward the natural language request to the multiplatform management system; and

the multiplatform management system to provide a feedback to the natural language processing platform, wherein the feedback is reinforcing when the natural language response comprises a positive feedback and the feedback is discouraging when the natural language response comprises a negative feedback.

16. The system of claim 14, the multiplatform management system comprising:

a cloud elastic compute platform to receive a communication in a first programming language to determine a type of the communication, and based on the type of the communication to determine a second platform to which to send the communication; and

a polyglot platform to receive the communication in the first programming language and the second platform from the cloud elastic compute platform, to translate the communication from the first programming language associated with a first platform to a second programming language associated with the second platform, and to send the translated communication to the second platform.

17. The system of claim 16, the type of communication comprising an image or a text.

18. The system of claim 14, the plurality of disparate platforms comprising a plurality of incompatible databases storing information regarding a workplace, or an image analysis platform to analyze an image received from the user.

19. The system of claim 14, the groupware platform comprising a user interface receiving a text or a spoken language.

20. The system of claim 14, comprising the groupware platform to:

enable a plurality of users to interact by a user interface associated with the groupware platform;

receive a user input from the user in the plurality of users;

determine whether the user input is directed to the groupware platform; and

upon determining that the user input is directed to the groupware platform, forward the user input to the multiplatform management system.