Self-correcting bot

Patent metadata

Field	Value
Publication number	US-12099435-B2
Application number	US-202318093874-A
Country	US
Kind code	B2
Filing date	Jan 6, 2023
Priority date	Jan 6, 2023
Publication date	Sep 24, 2024
Grant date	Sep 24, 2024

Abstract

Bots are typically programmed to automate tasks and provide statistically expected results. However, a bot may malfunction and generate aberrant outputs. It is technically challenging to detect the aberrant outputs and determine whether the outputs are due to an error in how the bot processes inputs or because the bot has received unusual or unexpected input data. Apparatus and methods are provided for auto-determining why a bot has generated output outside expected results. An auto-correct bot will detect problems and auto-identify potential solutions, simulate those solutions and apply those solutions to remediate the malfunctioning bot.

First claim

What is claimed is:

1. An artificial intelligence (“AI”) system for autonomously diagnosing and remediating a malfunction of a bot, the system comprising:
one or more computer servers including a processor circuit;
a plurality of bots that are each programmed to receive user inputs and generate automated outputs to the user inputs; and
a supervisory bot that is programmed to:
during a first time-window:
monitor automated outputs generated by the plurality of bots in response to the user inputs; and
detect a target bot in the plurality of bots that is generating a threshold number of aberrant automated outputs; and

during a second time-window:
intercept a user input destined for the target bot;
input the user input destined for the target bot to a secondary bot;
trace a processing by the secondary bot of the user input destined for the target bot;
in response to detecting a divergence in the processing of the user input by the target bot and the secondary bot, generate a plurality of test inputs;
submit the plurality of test inputs to the target bot and the secondary bot;
based on automated outputs generated by the target bot and the secondary bot in response to the plurality of test inputs, formulate a remedial action; and
apply the remedial action to the target bot to reduce the threshold number of aberrant automated outputs generated by the target bot.

2. The AI system of claim 1 , wherein the remedial action comprises reprogramming the target bot to change a processing parameter applied by the target bot.

3. The AI system of claim 1 , wherein the remedial action comprises adding a pre-processing module to the target bot that is configured to filter any future user inputs received by the target bot after the second time-window and before the target bot generates automated outputs based on the future user inputs.

4. The AI system of claim 1 , wherein:
the secondary bot is a digital twin of the target bot; and
the digital twin is generated prior to a start of the first time-window.

5. An artificial intelligence (“AI”) method for autonomously diagnosing a malfunction of a bot, the method comprising extracting computer readable instructions stored on a non-transitory medium and executing the computer readable instructions on a processor, wherein execution of the computer readable instructions by the processor:
monitors outputs generated by the bot;
detects a threshold number of aberrant outputs during a time-window;
identifies a potential solution for reducing the threshold number of aberrant outputs;
simulates application of the potential solution;
based on results of the simulating, autonomously adjusts at least one processing parameter of the bot;
parses inputs associated with each of the aberrant outputs;
determines whether the threshold number of aberrant outputs are due to aberrant inputs or aberrant processing of the inputs by the bot; and
in response to determining that the threshold number of aberrant outputs are due to aberrant processing of the inputs by the bot, adjusts the at least one processing parameter of the bot based on a geographic location associated with inputs received by the bot after the time-window.

6. The AI method of claim 5 , wherein execution of the computer readable instructions by the processor, during a second time window, monitors all output generated by the bot and determines whether all the output includes the threshold number of aberrant outputs.

7. The AI method of claim 5 , wherein execution of the computer readable instructions by the processor adjusts the at least one processing parameter of the bot by applying a linguistic filter to adjust for a local dialect or local accent associated with the geographic location.

8. The AI method of claim 5 , wherein execution of the computer readable instructions by the processor:
generates simulated inputs;
generates known outputs associated with the simulated inputs;
submits the simulated inputs to the bot;
determines whether outputs generated by the bot in response to the simulated inputs correspond to the known outputs;
registers the bot as being associated with a processing error when the outputs generated by the bot in response to the simulated inputs do not correspond to the known outputs; and
registers the inputs as being erroneous when the outputs generated by the bot in response to the simulated inputs correspond to the known outputs.

9. An artificial intelligence (“AI”) system for autonomously diagnosing a malfunction with a bot, the system comprising:
one or more computer servers including a processor circuit;
a first bot that is programmed to receive user inputs and generate automated outputs to the user inputs;
a second bot that is programmed to:
monitor the user inputs and automated outputs generated by the first bot during a first time-window;
detect a threshold number of aberrant automated outputs generated by the first bot;
diagnose a malfunction that is causing the first bot to generate the threshold number of aberrant automated outputs; and
autonomously reprogram the first bot to change a processing parameter applied by the first bot;

wherein:
the second bot is further programmed to simulate the change to the processing parameter before autonomously reprogramming the first bot; and
the second bot is programmed to simulate the change to the processing parameter by:
generating test inputs;
inputting the test inputs to the first bot; and
monitoring automated outputs generated by the first bot in response to the test inputs.

10. The AI system of claim 9 , wherein:
the second bot is further programmed to monitor the user inputs and automated outputs generated by the first bot during a second time-window; and
the second time-window begins after the first bot is reprogrammed to change the processing parameter.

11. The AI system of claim 9 , wherein the second bot is programmed to determine the processing parameter based on applying a machine learning analysis to automated outputs generated by a plurality of bots.

12. The AI system of claim 9 , wherein the second bot is programmed to determine the processing parameter based on applying a machine learning analysis to automated outputs generated by the first bot before and during the first time window.

13. The AI system of claim 9 , wherein the second bot is programmed to detect the threshold number of aberrant automated outputs generated by the first bot based on:
a length of an interaction of the first bot with a user that submits at least one of the user inputs;
linguistic patterns extracted from the at least one of the user inputs;
a total number of interactions serviced by the first bot during the first time-window; and
a recurrence rate associated with the total number of interactions.

Assignees

• Bank Of America

Inventors

• Dhawan Lalit
• Ravi Swetha
• Delson Kevin A
• Dande Pratap

Classifications

• G06F11/3698

  Environments for analysis, debugging or testing of software · CPC title

• G06N20/00

  Machine learning · CPC title

• G06F11/3684

  for test design, e.g. generating new test cases · CPC title

• G06F11/3692

  for test results analysis · CPC title

• G06F11/3688

  for test execution, e.g. scheduling of test suites · CPC title