ARTIFICIAL INTELLIGENCE AND ROBOTIC PROCESS AUTOMATION FOR AUTOMATED DATA MANAGEMENT

• US 20190180746A1
• Filed: 11/30/2018
• Published: 06/13/2019
• Est. Priority Date: 12/07/2017
• Status: Active Grant

• Current Assignee: Accenture Global Solutions Limited (Accenture PLC)
• Original Assignee: Accenture Global Solutions Limited (Accenture PLC)
• Inventors: DIWAN, Gaurav, GOGUEN, Tracy Ann
• Granted Patent: US 10,452,674 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/252 between a Database Management System and a front-end application
• 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 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/006 based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: H04L 67/306 User profiles

Abstract

A device receives, from a virtual assistant device, a first user input associated with a first account of a user, and causes a natural language processing analysis to be performed on the first user input to identify first information, the first account, and a first operation to be performed in association with first information in the first account. The device identifies a first data management platform, associated with the first account, that is configured to maintain the first information in a first data structure associated with the first data management platform, and determines that the first data management platform is a first type of data management platform based on the first data structure. The device causes the first operation to be performed using a RPA, that uses a user interface of the first data management platform, based on the first data management platform being the first type of data management platform.

Claims

1. A method, comprising:

receiving, by a device, a user input,

wherein the user input is received via a communication with a user,

wherein the user input is received from a virtual assistant device, and

wherein the communication is associated with an account of the user;

causing, by the device, a natural language processing model to analyze the user input,

wherein the natural language processing model is configured to identify, from the user input, an operation associated with the account;

identifying, by the device, the operation that is to be performed,

wherein the operation is performed according to the user input, and

wherein the operation is performed in association with the account;

identifying, by the device, a data management platform associated with the account;

determining, by the device, whether the operation can be performed using an application programming interface (API) associated with the data management platform,

wherein determining whether the operation can be performed using the API includes;

determining whether the data management platform permits a backend service to be used to perform the operation; and

determining whether the backend service is able to perform the operation; and

selectively causing, by the device, the operation to be performed on the data management platform using;

an API call, or

a robotic process automation (RPA) that uses a user interface associated with the data management platform,

wherein the operation is to be performed using the API call when the operation is capable of being performed using the API associated with the data management platform, and

wherein the operation is to be performed using the RPA when the operation is not capable of being performed using the API associated with the data management platform.

2. The method of claim 1, further comprising:

identifying the account of the user based on at least one of;

the natural language processing model identifying the account,

a voice recognition analysis of the user input, or

information associated with the virtual assistant device.

3. The method of claim 1, wherein the natural language processing model comprises a machine learning model,

wherein the machine learning model is trained based on at least one of:

historical data associated with receiving previous user inputs from the user,

historical data associated with receiving previous user inputs from one or more other users, or

one or more parameters associated with identifying, from the user input, at least one of;

the operation,

information in the account that is to be updated according to the operation,

the account, or

the data management platform.

4. The method of claim 1, wherein the operation comprises at least one of:

creating the account,

editing user information associated with the account,

adding information to the account,

removing information from the account,

removing an association to the account,

adding a service associated with the data management platform, or

linking the account to another data management platform that is different from the data management platform.

5. The method of claim 1, further comprising:

identifying, using the natural language processing model, information, in the user input, that is associated with the operation,

wherein the natural language processing model indicates that the operation is to update the account with the information;

determining a level of accuracy associated with the information;

obtaining new information based on the level of accuracy not satisfying a threshold; and

replacing the information with the new information to permit the operation to be performed based on the new information.

6. The method of claim 1, further comprising:

determining that the operation is capable of being performed using an API when the virtual assistant device is associated with the data management platform.

7. The method of claim 1, further comprising:

determining that the operation is not capable of being performed using an API when the virtual assistant device is not associated with the data management platform.

8. The method of claim 1, wherein causing the operation to be performed using the RPA comprises:

identifying information in the user input that is to be used to update the account;

identifying the user interface associated with the data management platform;

identifying an element of the user interface that permits the account to be updated with the information according to the operation; and

causing the element to update the account by automatically entering the information via the user interface.

9. A device, comprising:

one or more memories; and

one or more processors, communicatively coupled to the one or more memories, to;

receive, from a virtual assistant device, a first user input associated with a first account of a user;

causing a natural language processing analysis to be performed on the first user input to identify;

a first operation,

first information, and

the first account of the user,

wherein the first operation is to be performed in association with the first information in the first account;

identify a first data management platform associated with the first account,

wherein the first data management platform is configured to maintain the first information in a first data structure associated with the first data management platform;

determine that the first data management platform is a first type of data management platform based on the first data structure,

wherein, when determining that the first data management platform is the first type of data management platform, the one or more processors are to;

 

determine that the first data management platform does not permit a backend service to be used to perform the first operation, and

 

determine that the backend service of the first data management platform is not able to perform the first operation; and

cause the first operation to be performed using a robotic process automation (RPA) based on the first data management platform being the first type of data management platform,

wherein the RPA uses a user interface of the first data management platform.

10. The device of claim 9, wherein the one or more processors are further to:

identify the first information that is to be used to update the first account;

identify the user interface associated with the first data management platform;

determine an element of the user interface that permits the first operation to be performed via the user interface; and

cause the element to update data associated with the first data management platform, by automatically entering the first information via the user interface,

wherein the data is associated with the first data management platform.

11. The device of claim 9, wherein the natural language processing analysis is a first natural language processing analysis, and the one or more processors are further to:

determine that the first operation cannot be performed based on the first user input;

send, to the virtual assistant device, a request that the user provide additional information associated with the first operation,

wherein the request is configured to cause the virtual assistant device to indicate that the user is to provide the additional information;

receive, from the virtual assistant, a second user input associated with the request, wherein the second user input includes second information associated with the first operation;

perform a second natural language processing analysis on the second user input to identify the second information associated with the first operation; and

cause the first operation to be performed using the RPA based on the second information.

12. The device of claim 9, wherein the one or more processors are further to:

determine that the first operation involves editing the first information in the first account,

wherein the one or more processors, when causing the first operation to be performed using the RPA, are to;

identify an edit to the first information;

identify the user interface associated with the first data management platform;

identify an element associated with the user interface,

wherein the element is configured to enable the edit to the first information to be made; and

cause the element to make the edit to the first information.

13. The device of claim 9, wherein the one or more processors are further to:

receive, from the virtual assistant device, a second user input associated with a second account of the user;

perform the natural language processing analysis on the second user input to identify;

a second operation,

second information, and

the second account of the user,

wherein the second operation is to be performed in association with the second information in the second account;

identify a second data management platform associated with the second account,

wherein the second data management platform is configured to maintain the second information in a second data structure associated with the second data management platform;

determine that the second data management platform is a second type of data management platform based on the second data structure,

wherein the second type of data management platform is different than the first type of data management platform; and

cause the second operation to be performed using an application programming interface (API) call based on the second data management platform being the second type of data management platform.

14. The device of claim 9, wherein the first type of data management platform comprises a type of data management platform that is not associated with an available application programming interface to perform the first operation in association with the first information in the first data structure.

15. A non-transitory computer-readable medium storing instructions, the instructions comprising:

one or more instructions that, when executed by one or more processors, cause the one or more processors to;

monitor, in real time, a communication associated with updating an account of a user,

wherein the communication is between a virtual assistant device of the user and a service platform;

cause a natural language processing model to analyze the communication;

obtain, from the natural language processing model, an indication that an operation is to be performed to update information in the account of the user,

wherein the user requested the operation and identified the information during the communication;

determine that the account is associated with a first data management platform of a plurality of data management platforms;

determine a configuration of the first data management platform,

wherein the one or more instructions, that cause the one or more processors to determine the configuration of the first data management platform, cause the one or more processors to;

determine whether the first data management platform permits a backend service to be used to perform the operation, and

determine whether the backend service is able to perform the operation; and

perform, in real time, an action associated with the operation,

wherein the action is performed, based on the configuration of the first data management platform, using at least one of;

an application programming interface (API) call, or

a robotic process automation (RPA) that uses a user interface of the first data management platform.

16. The non-transitory computer-readable medium of claim 15, wherein the natural language processing model comprises a machine learning model,

wherein the machine learning model is trained based on at least one of:

historical data associated with previous communications involving the user, and

one or more parameters that cause the machine learning model to identify, from the communication, at least one of;

the operation,

information in the account that is to be updated according to the operation,

the account, or

the first data management platform.

17. The non-transitory computer-readable medium of claim 15, wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:

determine a level of accuracy associated with the information;

obtain new information based on the level of accuracy not satisfying a threshold; and

replace the information with the new information to permit the action associated with the operation to be performed based on the new information.

18. The non-transitory computer-readable medium of claim 15, wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:

determine, based on the indication, that the user is to provide additional information to perform the operation,

wherein the additional information is associated with the information;

cause, via the communication, the virtual assistant device to request that the user provide the additional information via the virtual assistant device; and

receive, via the communication and from the virtual assistant device, the additional information,

wherein the action associated with the operation is performed based on the received additional information.

19. The non-transitory computer-readable medium of claim 15, wherein the one or more instructions, that cause the one or more processors to perform the action, cause the one or more processors to:

cause the operation to be performed using the API call based on the configuration enabling the first data management platform to be accessed via the API.

20. The non-transitory computer-readable medium of claim 15, wherein the one or more instructions, that cause the one or more processors to perform the action, cause the one or more processors to:

cause the operation to be performed using the RPA based on the configuration not enabling the first data management platform to be accessed via the API.