Artificial intelligence-based chatbot system with machine learning-based processing of data structures

Inventors: Divya Maddi (Round Rock, TX); Bijan Kumar Mohanty (Austin, TX); Hung T. Dinh (Austin, TX)

Assignee: Dell Products L.P.

H04L51/02 G06N3/0442

View Patent ↗

Loading inventors, assignments & file history…

Monitor This Case

Get email alerts when status or documents change.

Order Certified Copies

Most orders are placed with the USPTO same day — all within 24 business hours.

Order via The Patent Place →

Pre-filled with this patent's details

Quick Facts

Patent No.: US 12665866
App. No.: 18/794,285
Granted: Jun 23, 2026
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

Methods, apparatus, and processor-readable storage media for artificial intelligence-based chatbot systems with machine learning-based processing of data structures are provided herein. An example computer-implemented method includes processing data pertaining to one or more interactions between at least one user device and at least one artificial intelligence-based chatbot into one or more data structures; predicting at least one future task of at least a portion of the one or more interactions by processing at least portions of the one or more data structures using one or more machine learning techniques; and identifying at least one task handler component related to at least one chatbot functionality associated with the at least one predicted future task.

Claims (36)

1 . A computer-implemented method comprising:

processing data pertaining to one or more interactions between at least one user device and at least one artificial intelligence-based chatbot into one or more data structures;

predicting at least one future task of at least a portion of the one or more interactions by processing at least portions of the one or more data structures using one or more machine learning techniques;

identifying at least one task handler component related to at least one chatbot functionality associated with the at least one predicted future task; and

performing one or more automated actions related to providing dynamic and independent access to each of the at least one task handler component via the at least one artificial intelligence-based chatbot, wherein providing dynamic and independent access comprises independently plugging each of the at least one task handler component into at least one user interface associated with the at least one artificial intelligence-based chatbot;

wherein the method is performed by at least one processing device comprising a processor coupled to a memory.

2 . The computer-implemented method of claim 1 , wherein predicting at least one future task of at least a portion of the one or more interactions comprises processing at least portions of the one or more data structures using at least one deep neural network-based long short-term memory (LSTM) model.

3 . The computer-implemented method of claim 2 , wherein processing at least portions of the one or more data structures using at least one deep neural network-based LSTM model comprises processing the at least portions of the one or more data structures using the at least one deep neural network-based LSTM model in an unsupervised manner by implementing at least one autoencoder architecture.

4 . The computer-implemented method of claim 1 , wherein processing at least portions of the one or more data structures comprising using the one or more machine learning techniques trained using historical user-chatbot interaction data and historical user behavior in connection with the at least one artificial intelligence-based chatbot.

5 . The computer-implemented method of claim 1 , further comprising:

incorporating multiple chatbot functionalities into multiple respective task handler components.

6 . The computer-implemented method of claim 5 , wherein identifying at least one task handler component comprises comparing the at least one predicted future task to the multiple chatbot functionalities of the multiple respective task handler components.

7 . The computer-implemented method of claim 1 , wherein processing data pertaining to one or more interactions between at least one user device and at least one artificial intelligence-based chatbot into one or more data structures comprises processing at least a portion of the data as time series data.

8 . The computer-implemented method of claim 1 , wherein predicting at least one future task of at least a portion of the one or more interactions comprises processing at least portions of the one or more data structures using at least one of a cosine similarity algorithm, a Euclidian distance algorithm, and a Manhattan distance algorithm.

9 . 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 the at least one processing device:

to process data pertaining to one or more interactions between at least one user device and at least one artificial intelligence-based chatbot into one or more data structures;

to predict at least one future task of at least a portion of the one or more interactions by processing at least portions of the one or more data structures using one or more machine learning techniques;

to identify at least one task handler component related to at least one chatbot functionality associated with the at least one predicted future task; and

to perform one or more automated actions related to providing dynamic and independent access to each of the at least one task handler component via the at least one artificial intelligence-based chatbot, wherein providing dynamic and independent access comprises independently plugging each of the at least one task handler component into at least one user interface associated with the at least one artificial intelligence-based chatbot.

10 . The non-transitory processor-readable storage medium of claim 9 , wherein predicting at least one future task of at least a portion of the one or more interactions comprises processing at least portions of the one or more data structures using at least one deep neural network-based long short-term memory (LSTM) model.

11 . The non-transitory processor-readable storage medium of claim 10 , wherein processing at least portions of the one or more data structures using at least one deep neural network-based LSTM model comprises processing the at least portions of the one or more data structures using the at least one deep neural network-based LSTM model in an unsupervised manner by implementing at least one autoencoder architecture.

12 . An apparatus comprising:

at least one processing device comprising a processor coupled to a memory;

the at least one processing device being configured:

to process data pertaining to one or more interactions between at least one user device and at least one artificial intelligence-based chatbot into one or more data structures;

to identify at least one task handler component related to at least one chatbot functionality associated with the at least one predicted future task; and

13 . The apparatus of claim 12 , wherein predicting at least one future task of at least a portion of the one or more interactions comprises processing at least portions of the one or more data structures using at least one deep neural network-based long short-term memory (LSTM) model.

14 . The apparatus of claim 13 , wherein processing at least portions of the one or more data structures using at least one deep neural network-based LSTM model comprises processing the at least portions of the one or more data structures using the at least one deep neural network-based LSTM model in an unsupervised manner by implementing at least one autoencoder architecture.

15 . The apparatus of claim 12 , wherein processing at least portions of the one or more data structures comprising using the one or more machine learning techniques trained using historical user-chatbot interaction data and historical user behavior in connection with the at least one artificial intelligence-based chatbot.

16 . The apparatus of claim 12 , wherein processing data pertaining to one or more interactions between at least one user device and at least one artificial intelligence-based chatbot into one or more data structures comprises processing at least a portion of the data as time series data.

17 . The apparatus of claim 12 , wherein predicting at least one future task of at least a portion of the one or more interactions comprises processing at least portions of the one or more data structures using at least one of a cosine similarity algorithm, a Euclidian distance algorithm, and a Manhattan distance algorithm.

18 . The non-transitory processor-readable storage medium of claim 9 , wherein processing at least portions of the one or more data structures comprising using the one or more machine learning techniques trained using historical user-chatbot interaction data and historical user behavior in connection with the at least one artificial intelligence-based chatbot.

19 . The non-transitory processor-readable storage medium of claim 9 , wherein processing data pertaining to one or more interactions between at least one user device and at least one artificial intelligence-based chatbot into one or more data structures comprises processing at least a portion of the data as time series data.

20 . The non-transitory processor-readable storage medium of claim 9 , wherein predicting at least one future task of at least a portion of the one or more interactions comprises processing at least portions of the one or more data structures using at least one of a cosine similarity algorithm, a Euclidian distance algorithm, and a Manhattan distance algorithm.