Granted Patent B2

US 11,694,686 · App. 17/209,372 · Granted Jul 4, 2023

Inventors: Bijan Kumar Mohanty (Austin, TX); Dhilip S. Kumar (Bangalore, IN); Jaganathan Subramanian (Bangalore, IN); Hung Dinh (Austin, TX)

Assignee: Dell Products L.P.

G10L15/22G06F9/453G06F16/9024G10L15/1815G10L15/30G06N20/00G10L2015/223

Abstract

Claims (61)

1. A method comprising:

receiving at least one natural language input directed to at least one user;

determining a plurality of attributes characterizing the at least one natural language input;

converting the at least one natural language input to a graphical input;

retrieving relationship data from a graph database based at least in part on the graphical input;

identifying from the relationship data one or more additional users having a relationship with the at least one user;

generating at least one natural language response of a virtual assistant to the at least one natural language input based at least in part on the relationship data from the graph database and the plurality of attributes characterizing the at least one natural language input; and

recommending at least one action to perform in response to the at least one natural language input based at least in part on the relationship data from the graph database and the plurality of attributes characterizing the at least one natural language input, wherein the at least one action comprises coordinating communication between the at least one user and the one or more additional users;

wherein at least the determining, generating and recommending are performed using one or more machine learning models; and

wherein the steps of the method are executed by a processing device operatively coupled to a memory.

2. The method claim 1 wherein:

determining the plurality of attributes characterizing the at least one natural language input comprises determining an intent of the at least one natural language input; and

the at least one natural language response of the virtual assistant is based at least in part on the determined intent.

3. The method claim 1 wherein:

determining the plurality of attributes characterizing the at least one natural language input comprises determining a sentiment of the at least one natural language input; and

the at least one natural language response of the virtual assistant is based at least in part on the determined sentiment.

4. The method of claim 1 wherein the graph database comprises one or more relationship graphs comprising the relationship data, the one or more relationship graphs comprising relationships between a plurality of nodes, wherein the relationships comprise edges of the one or more relationship graphs.

5. The method of claim 4 wherein the plurality of nodes comprise at least one of one or more persons, one or more domains, one or more sub-domains, one or more functions, one or more utilities and one or more activities.

6. The method of claim 5 wherein the relationships comprise interactions between respective pairs of the plurality of nodes.

7. The method of claim 4 wherein the one or more relationship graphs are in one of a resource description framework (RDF) format and a labeled property graph (LPG) format.

8. The method of claim 4 further comprising:

receiving a plurality of natural language inputs corresponding to the at least one user of a plurality of users;

analyzing the plurality of natural language inputs; and

generating a relationship graph of the one or more relationship graphs corresponding to the at least one user based at least in part on the analyzing;

wherein the analyzing and generating are performed using the one or more machine learning models.

9. The method of claim 8 wherein the analyzing of the plurality of natural language inputs comprises determining at least one of intent and sentiment of the plurality of natural language inputs.

10. The method of claim 1 further comprising training the one or more machine learning models with data comprising at least one of a plurality of intents, a plurality of sentiments, a plurality of priorities and a plurality of contexts corresponding to respective ones of a plurality of actions.

11. The method of claim 1 wherein the at least one natural language input is in a speech format and the method further comprises converting the at least one natural language input from the speech format to a text format.

12. The method of claim 1 further comprising:

receiving a plurality of natural language inputs corresponding to the at least one user of a plurality of users; and

training the one or more machine learning models with data from the plurality of natural language inputs.

13. The method of claim 1 , wherein converting the at least one natural language input to a graphical input comprises:

identifying a plurality of pairs of nodes from the at least one natural language input; and

calculating respective scores corresponding to a plurality of relationship types for the plurality of pairs of nodes.

14. The method of claim 1 wherein the coordinating of communication between the at least one user and the one or more additional users comprises scheduling a conference between the at least one user and the one or more additional users.

15. An apparatus comprising:

a processing device operatively coupled to a memory and configured:

to receive at least one natural language input directed to at least one user;

to determine a plurality of attributes characterizing the at least one natural language input

to convert the at least one natural language input to a graphical input;

to retrieve relationship data from a graph database based at least in part on the graphical input;

to identify from the relationship data one or more additional users having a relationship with the at least one user;

to generate at least one natural language response of a virtual assistant to the at least one natural language input based at least in part on the relationship data from the graph database and the plurality of attributes characterizing the at least one natural language input; and

to recommend at least one action to perform in response to the at least one natural language input based at least in part on the relationship data from the graph database and the plurality of attributes characterizing the at least one natural language input, wherein the at least one action comprises coordinating communication between the at least one user and the one or more additional users;

wherein the processing device is configured to use one or more machine learning models to perform at least the determining, generating and recommending.

16. The apparatus of claim 15 wherein the graph database comprises one or more relationship graphs comprising the relationship data, the one or more relationship graphs comprising relationships between a plurality of nodes, wherein the relationships comprise edges of the one or more relationship graphs.

17. The apparatus of claim 16 wherein the plurality of nodes comprise at least one of one or more persons, one or more domains, one or more sub-domains, one or more functions, one or more utilities and one or more activities.

18. The apparatus of claim 16 wherein the processing device is further configured:

to receive a plurality of natural language inputs corresponding to the at least one user of a plurality of users;

to analyze the plurality of natural language inputs; and

to generate a relationship graph of the one or more relationship graphs corresponding to the at least one user based at least in part on the analyzing;

wherein the processing device is configured to use one or more machine learning models to perform the analyzing and generating.

19. An article of manufacture comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes said at least one processing device to perform the steps of:

receiving at least one natural language input directed to at least one user;

determining a plurality of attributes characterizing the at least one natural language input converting the at least one natural language input to a graphical input;

retrieving relationship data from a graph database based at least in part on the graphical input;

identifying from the relationship data one or more additional users having a relationship with the at least one user;

generating at least one natural language response of a virtual assistant to the at least one natural language input based at least in part on the relationship data from the graph database and the plurality of attributes characterizing the at least one natural language input; and

recommending at least one action to perform in response to the at least one natural language input based at least in part on the relationship data from the graph database and the plurality of attributes characterizing the at least one natural language input, wherein the at least one action comprises coordinating communication between the at least one user and the one or more additional users;

wherein at least the determining, generating and recommending are performed using one or more machine learning models.

20. The article of manufacture of claim 19 wherein the coordinating of communication between the at least one user and the one or more additional users comprises scheduling a conference between the at least one user and the one or more additional users.

Assignments (10)