Method and system for performing a task based on user input

• US 10,304,455 B1
• Filed: 03/26/2018
• Issued: 05/28/2019
• Est. Priority Date: 02/09/2018
• Status: Active Grant

• Current Assignee: Wipro Limited
• Original Assignee: Wipro Limited
• Inventors: Ulaganathan, Sethuraman, Ramachandra, Manjunath
• Primary Examiner(s): Diallo, Mamadou L
• Application Number:
  US15/935,466
• Time in Patent Office: 428 Days
• CPC Class Codes: G05B 13/027 using neural networks only
• CPC Class Codes: G05B 17/02 electric
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• 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: G06Q 10/06311 Scheduling, planning or task assignment for a person or group
• CPC Class Codes: G06Q 30/0611 Request for offers or quotes
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

Disclosed herein is a method and system for performing a task based on user input. One or more requirements related to the task are extracted from the user input. Based on the requirements, plurality of resources required for performing the task are retrieved and integrated to generate action sequences. Further, a simulated model is generated based on the action sequences and provided to the user for receiving user feedback. Finally, the action sequences are implemented based on the user feedback for performing the task. In an embodiment, the method of present disclosure is capable of automatically selecting and integrating resources required for implementing a task, thereby helps in reducing overall time required for implementing a task intended by the user.

Claims

1. A method comprising:

extracting, by a task management system, by natural language processing one or more requirements from intent in user input data that corresponds to a task;

retrieving, by the task management system, a plurality of resources comprising one or more software modules and one or more hardware components from a configuration repository required for performing the task based on the one or more requirements;

generating, by the task management system, one or more automated action sequences for performing the task by integrating each of the one or more software modules and the one and more hardware components;

providing, by the task management system, a simulated model generated based on one of the one or more action sequences to validate the one of the one or more action sequences in a virtual environment, wherein the simulated model of the one of the one or more action sequences is regenerated in the virtual environment based on received user feedback data comprising one or more modifications or a new requirement and provided until the validation is received to; and

implementing, by the task management system, the one of the one or more action sequences based on the validation.

2. The method as claimed in claim 1, wherein the user input data is at least one of a voice input data or a text input data.

3. The method as claimed in claim 1, wherein the extracting the one or more requirements from the user input data comprises:

capturing one or more task-specific keywords from the user input data;

mapping each of the one or more task-specific keywords with one or more predetermined action frames for identifying missing information in the user input data; and

prompting for providing the missing information.

4. The method as claimed in claim 1, wherein the integrating each of the plurality of resources is based on one or more parameters including a predetermined reference integration design, historical data related to similar tasks, metadata associated with one or more software modules and one or more hardware components, nature of input to the plurality of resources, or hypothetical analysis related to the task.

5. The method as claimed in claim 1, wherein the one of the one or more action sequences is selected based on predetermined factors.

6. The method as claimed in claim 1, wherein the user feedback comprises one or more modifications for the one of the one or more action sequences or an approval for implementing the one of the one or more action sequences.

7. The method as claimed in claim 6 further comprises incorporating each of the one or more modifications to the one of the one or more action sequences before implementing the one of the one or more action sequences.

8. A task management system for performing a task based on user input, the task management system comprising:

a processor; and

a memory, communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which on execution cause the processor to;

extract by natural language processing one or more requirements from intent in user input data that corresponds to a task;

retrieve a plurality of resources comprising one or more software modules and one or more hardware components from a configuration repository required for performing the task based on the one or more requirements;

generate one or more action sequences for performing the task by integrating each of the one or more software modules and the one and more hardware components;

provide a simulated model, generated based on one of the one or more action sequences to validate the one of the one or more action sequences in a virtual environment, wherein the simulated model of the one of the one or more action sequences is regenerated in the virtual environment based on received user feedback data comprising one or more modifications or a new requirement and provided until the validation is received; and

implement the one of the one or more action sequences based on the validation.

9. The task management system as claimed in claim 8, wherein the user input data is at least one of a voice input data or a text input data.

10. The task management system as claimed in claim 8, wherein for the extract the one or more requirements from the user input data, the instructions cause the processor to:

capture one or more task-specific keywords from the user input data;

map each of the one or more task-specific keywords with one or more predetermined action frames to identify missing information in the user input data; and

prompt for providing the missing information.

11. The task management system as claimed in claim 8, wherein the processor integrates each of the plurality of resources based on one or more parameters including a predetermined reference integration design, historical data related to similar tasks, metadata associated with one or more software modules and one or more hardware components, nature of input to the plurality of resources, or hypothetical analysis related to the task.

12. The task management system as claimed in claim 8, wherein the processor selects the one of the one or more action sequences based on predetermined factors.

13. The task management system as claimed in claim 8, wherein the user feedback comprises one or more modifications to the one of the one or more action sequences or an approval for implementing the one of the one or more action sequences.

14. The task management system as claimed in claim 13, wherein the instructions further cause the processor to incorporate each of the one or more modifications to the one of the one or more action sequences before implementing the one of the one or more action sequences.

15. A non-transitory computer readable medium including instructions stored thereon that when processed by at least one processor causes a task management system to perform operations comprising:

extracting by natural language processing one or more requirements from intent in user input data that corresponds to a task;

retrieving a plurality of resources comprising one or more software modules and one or more hardware components from a configuration repository required for performing the task based on the one or more requirements;

generating one or more action sequences for performing the task by integrating each of the one or more software modules and the one and more hardware components;

providing a simulated model generated based on one of the one or more action sequences to validate the one of the one or more action sequences in a virtual environment, wherein the simulated model of the one of the one or more action sequences is regenerated in the virtual environment based on received user feedback data comprising one or more modifications or a new requirement and provided until the validation is received; and

implementing the one of the one or more action sequences based on the validation.