IP Library Granted Patent US 12695754
Granted Patent B2
US 12695754 · App. 18/947,623 · Granted Jul 28, 2026

Automatic responsive generative reporting

Inventors: Sanjay Jeyakumar (El Cerrito, CA); Abhijit Bagri (Atlanta, GA); Mickey Dang (New York City, NY); Shrivastava Shankar (San Francisco, CA)
Assignee: Abnormal AI, Inc.
H04L63/101G06F16/2455
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 12695754
App. No.
18/947,623
Granted
Jul 28, 2026
Kind
B2
Abstract

A report message including a machine generated security report is provided. A reply message to the report message is received, wherein the reply message includes an inquiry. Data associated with the inquiry and determined to be accessible with a security privilege of a sender of the reply message is retrieved. A machine learning language model query is automatically generated using the retrieved data and at least a portion of the generated security report. A second report generated by a machine learning language model executed in response to the machine learning language model query is received. The second report is provided as a response to the reply message in a responsive message from an artificial intelligence service.

Claims (41)

1 . A method, comprising:

providing a report message including a machine generated security report;

receiving a reply message to the report message, wherein the reply message includes an inquiry;

retrieving data associated with the inquiry and determined to be accessible with a security privilege of a sender of the reply message;

automatically generating a machine learning language model query using the retrieved data and at least a portion of the machine generated security report;

receiving a second report generated by a machine learning language model executed in response to the machine learning language model query including by receiving content generated by the machine learning language model, formatting the received content generated by the machine learning language model into a non-visual format, and rendering the non-visual format into a visual digital report format; and

providing as a response to the reply message, the second report in a responsive message from an artificial intelligence service.

2 . The method of claim 1 , wherein the reply message is an email message.

3 . The method of claim 1 , wherein retrieving the data associated with the inquiry and determined to be accessible with the security privilege of the sender of the reply message includes generating a data query using a second machine learning language model.

4 . The method of claim 3 , wherein the data query corresponds to a vector search, a database query, or an application programming interface (API) call.

5 . The method of claim 1 , further comprising analyzing one or more headers of the reply message to determine the security privilege of the sender.

6 . The method of claim 1 , wherein the report message including the machine generated security report is an automated and scheduled message.

7 . The method of claim 1 , wherein the retrieved data associated with the inquiry and determined to be accessible with the security privilege of the sender of the reply message includes at least one of a company logo, a company name, or company colors associated with the sender.

8 . The method of claim 1 , wherein the inquiry included in the reply message is a natural language inquiry.

9 . The method of claim 1 , further comprising:

receiving a second reply message in response to the responsive message, wherein the second reply message includes a second inquiry, and wherein a context of the second inquiry includes at least the report message, the reply message, or the responsive message.

10 . The method of claim 9 , wherein the context is used to generate the machine learning language model query for generating a second responsive report.

11 . A system, comprising:

one or more processors; and

a memory coupled to the one or more processors, wherein the memory is configured to provide the one or more processors with instructions which when executed cause the one or more processors to:

provide a report message including a machine generated security report;

receive a reply message to the report message, wherein the reply message includes an inquiry;

retrieve data associated with the inquiry and determined to be accessible with a security privilege of a sender of the reply message;

automatically generate a machine learning language model query using the retrieved data and at least a portion of the machine generated security report;

receive a second report generated by a machine learning language model executed in response to the machine learning language model query including by being configured to receive content generated by the machine learning language model, format the received content generated by the machine learning language model into a non-visual format, and render the non-visual format into a visual digital report format; and

provide as a response to the reply message, the second report in a responsive message from an artificial intelligence service.

12 . The system of claim 11 , wherein the reply message is an email message.

13 . The system of claim 11 , wherein to retrieve the data associated with the inquiry and determined to be accessible with the security privilege of the sender of the reply message includes to generate a data query using second machine learning language model.

14 . The system of claim 13 , wherein the data query corresponds to a vector search, a database query, or an application programming interface (API) call.

15 . The system of claim 11 , wherein the memory is further configured to provide the one or more processors with instructions which when executed cause the one or more processors to: analyze one or more headers of the reply message to determine the security privilege of the sender.

16 . The system of claim 11 , wherein the report message including the machine generated security report is an automated and scheduled message.

17 . The system of claim 11 , wherein the retrieved data associated with the inquiry and determined to be accessible with the security privilege of the sender of the reply message includes at least one of a company logo, a company name, or company colors associated with the sender.

18 . A computer program product, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:

providing a report message including a machine generated security report;

receiving a reply message to the report message, wherein the reply message includes an inquiry;

retrieving data associated with the inquiry and determined to be accessible with a security privilege of a sender of the reply message;

automatically generating a machine learning language model query using the retrieved data and at least a portion of the machine generated security report;

receiving a second report generated by a machine learning language model executed in response to the machine learning language model query including by receiving content generated by the machine learning language model, formatting the received content generated by the machine learning language model into a non-visual format, and rendering the non-visual format into a visual digital report format; and

providing as a response to the reply message, the second report in a responsive message from an artificial intelligence service.

19 . The computer program product of claim 18 , wherein the reply message is an email message.

20 . The computer program product of claim 18 , wherein retrieving the data associated with the inquiry and determined to be accessible with the security privilege of the sender of the reply message includes generating a data query using a second machine learning language model.