IP Library › Granted Patent US 12664364
Granted Patent B2
US 12664364 · App. 18/763,295 · Granted Jun 23, 2026

Electronic text analysis for detecting computer-generated interaction in text-based communications

Inventors: Amit Janbandhu (Princeton, NJ); Priyeshkumar Patel (Hillsborough, NJ); Jennifer Corzo (Ewing, NJ); Bartholomew Sanjeevinathan (Chennai, IN); Bhushan Patel (Piscataway, NJ); Jitender Singh (Robbinsville, NJ)
Assignee: Bank of America Corporation
G06F40/253G06F40/289
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 12664364
App. No.
18/763,295
Granted
Jun 23, 2026
Kind
B2
Abstract

A text analysis processing for detecting computer-generated text is provided. In some cases, a text-based chat interaction may be initiated and analyzed to determine whether the text-based chat generated by a communicating entity is computer-generated. The text of the chat session may be analyzed to evaluate punctuation, use of emojis, spacing, grammar, words, phrases, and the like to determine a further likelihood of whether the text is computer-generated. A duration of the chat session may be used as a scoring factor. The various probabilities and scores may be combined to provide a composite score.

Claims (73)

1 . A method for electronic text analysis for detecting computer-generated interaction, the method comprising:

detecting, by a text analysis computing platform, an initiation of a text-based interactive session through a computer network, the text-based interactive session being between a first entity and a second entity;

receiving, by the text analysis computing platform, text entered by the second entity in the text-based interactive session;

analyzing, by the text analysis computing platform using a first machine learning model, the entered text, the first machine learning model configured to generate a text score indicating a similarity between the entered text and text entered by a human by analyzing one or more words and punctuation used in the entered text;

monitoring, by the text analysis computing platform, a duration of the text-based interactive session;

generating, by the text analysis computing platform, a duration score, the duration score indicating a likelihood that the text-based interactive session is computer-generated by comparing the duration of the text-based interactive session with an expected duration for the text-based interactive session;

determining, by the text analysis computing platform, a composite interaction score for the text-based interactive session based on the text score and the duration score;

determining, by the text analysis computing platform, whether the composite interaction score is greater than a first threshold score; and

in response to determining that the composite interaction score is greater than the first threshold score, generating and transmitting, by the text analysis computing platform, a command to a text interaction device different from the text analysis computing platform, the command configured to cause the text interaction device to terminate the text-based interactive session.

2 . The method of claim 1 , further comprising:

determining a characteristic associated with the text-based interactive session, the characteristic including at least one of: a product, a service, a geographic location, and an account type of the second entity; and

selecting the first machine learning model from at least two machine learning models based on the determined characteristic.

3 . The method of claim 2 , further comprising:

determining the expected duration for the text-based interactive session based on the characteristic associated with the text-based interactive session.

4 . The method of claim 1 , further comprising:

in response to determining that the composite interaction score is less than the first threshold score but greater than a second threshold score, generating and transmitting a second command to the text interaction device, the second command configured to cause the text interaction device to display an alert.

5 . The method of claim 1 , further comprising:

in response to determining that the composite interaction score is greater than the first threshold score, initiating a trace on a network connection to identify a source of the text-based interactive session.

6 . The method of claim 1 , further comprising:

in response to determining that the composite interaction score is greater than the first threshold score, transmitting information about the text-based interactive session for user review; and

upon receiving confirmation by the user review, providing information about the text-based interactive session and the confirmation to further train the first machine learning model.

7 . The method of claim 1 , further comprising:

receiving a further text comprising additional text entered by the second entity as part of the text-based interactive session;

processing the further text using the first machine learning model; and

updating the text score based on the processing of the further text.

8 . The method of claim 7 , further comprising:

updating the duration score based on an updated duration of the text-based interactive session; and

updating the composite interaction score by combining the updated text score and the updated duration score.

9 . A text analysis computing apparatus comprising:

a processor; and

memory storing computer-readable instructions that, when executed by the processor, causes the text analysis computing apparatus to:

detect an initiation of a text-based interactive session through a computer network, the interactive session being between a first entity and a second entity;

receive text entered by the second entity in the text-based interactive session;

analyze, using a first machine learning model, the entered text, the first machine learning model configured to generate a text score indicating a similarity between the entered text and text entered by a human by analyzing one or more words and punctuation used in the entered text;

monitor a duration of the text-based interactive session;

generate a duration score, the duration score indicating a likelihood that the text-based interactive session is computer-generated by comparing the duration of the text-based interactive session with an expected duration for the text-based interactive session;

determine a composite interaction score for the text-based interactive session based on the text score and the duration score;

determine whether the composite interaction score is greater than a first threshold score; and

in response to determining that the composite interaction score is greater than the first threshold score, generate and transmit a command to a text interaction device different from the text analysis computing apparatus, the command configured to cause the text interaction call device to terminate the text-based interactive session.

10 . The text analysis computing apparatus of claim 9 , further comprising:

determining a characteristic associated with the text-based interactive session, the characteristic including at least one of: a product, a service, a geographic location, and an account type of the second entity; and

selecting the first machine learning model from at least two machine learning models based on the determined characteristic.

11 . The text analysis computing apparatus of claim 10 , wherein the text analysis computing apparatus is further caused to:

determine the expected duration for the text-based interactive session based on the characteristic associated with the text-based interactive session.

12 . The text analysis computing apparatus of claim 9 , wherein the text analysis computing apparatus is further caused to:

in response to determining that the composite interaction score is less than the first threshold score but greater than a second threshold score, generate and transmit a second command to the text interaction device, the second command configured to cause the text interaction device to display an alert.

13 . The text analysis computing apparatus of claim 9 , wherein the text analysis computing apparatus is further caused to:

in response to determining that the composite interaction score is greater than the first threshold score, initiate a trace on a network connection to identify a source of the text-based interactive session.

14 . The text analysis computing apparatus of claim 9 , wherein the text analysis computing apparatus is further caused to:

in response to determining that the composite interaction score is greater than the first threshold score, transmit information about the text-based interactive session for user review; and

upon receiving confirmation by the user review, provide information about the text-based interactive session and the confirmation to further train the first machine learning model.

15 . The text analysis computing apparatus of claim 9 , wherein the text analysis computing apparatus is further caused to:

receive a further text comprising additional text entered by the second entity as part of the text-based interactive session;

process the further text using the first machine learning model; and

update the text score based on the processing of the further text.

16 . A non-transitory computer-readable medium storing computer-readable instructions that, when executed cause a text analysis apparatus to:

detect an initiation of a text-based interactive session through a computer network, the interactive session being between a first entity and a second entity;

receive text entered by the second entity in the text-based interactive session;

analyze, using a first machine learning model, the entered text, the first machine learning model configured to generate a text score indicating a similarity between the entered text and text entered by a human by analyzing one or more words and punctuation used in the entered text;

monitor a duration of the text-based interactive session;

generate a duration score, the duration score indicating a likelihood that the text-based interactive session is computer-generated by comparing the duration of the text-based interactive session with an expected duration for the text-based interactive session;

determine a composite interaction score for the text-based interactive session based on the text score and the duration score;

determine whether the composite interaction score is greater than a first threshold score; and

in response to determining that the composite interaction score is greater than the first threshold score, generate and transmit a command to a text interaction device different from the text analysis apparatus, the command configured to cause the text interaction call device to terminate the text-based interactive session.

17 . The non-transitory computer-readable medium of claim 16 , wherein the text analysis apparatus is further caused to:

determining a characteristic associated with the text-based interactive session, the characteristic including at least one of: a product, a service, a geographic location, and an account type of the second entity; and

selecting the first machine learning model from at least two machine learning models based on the determined characteristic.

18 . The non-transitory computer-readable medium of claim 17 , wherein the text analysis apparatus is further caused to:

determine the expected duration for the text-based interactive session based on the characteristic associated with the text-based interactive session.

19 . The non-transitory computer-readable medium of claim 16 , wherein the text analysis apparatus is further caused to:

in response to determining that the composite interaction score is less than the first threshold score but greater than a second threshold score, generate and transmit a second command to the text interaction device, the second command configured to cause the text interaction device to display an alert.

20 . The non-transitory computer-readable medium of claim 16 , wherein the text analysis apparatus is further caused to:

in response to determining that the composite interaction score is greater than the first threshold score, initiate a trace on a network connection to identify a source of the text-based interactive session.