Automating whois parsing and understanding with generative artificial intelligence

Patent metadata

Field	Value
Publication number	US-2026058895-A1
Application number	US-202418814216-A
Country	US
Kind code	A1
Filing date	Aug 23, 2024
Priority date	Aug 23, 2024
Publication date	Feb 26, 2026
Grant date	—

Abstract

Various techniques for automating WHOIS parsing and understanding with generative artificial intelligence are disclosed. In some embodiments, a system, a process, and/or a computer program product for automating WHOIS parsing and understanding with generative artificial intelligence includes receiving a WHOIS record (e.g., the WHOIS record can include unstructured data); processing the WHOIS record at least in part using a generative artificial intelligence (GenAI) model (e.g., including a Large-Language Model (LLM)) to determine a set of predefined data block values applied to meta information for parsing the WHOIS record; and generating an enriched version of the WHOIS record.

First claim

What is claimed is:

1 . A system, comprising:
a processor configured to:
receive a WHOIS record;
process the WHOIS record at least in part using a generative artificial intelligence (GenAI) model to determine a set of predefined data block values applied to meta information for parsing the WHOIS record; and
generate an enriched version of the WHOIS record; and
a memory coupled to the processor and configured to provide the processor with instructions.

2 . The system of claim 1 , wherein the WHOIS record includes unstructured data.

3 . The system of claim 1 , wherein the GenAI model includes a Large-Language Model (LLM).

4 . The system of claim 1 , wherein the GenAI model includes a Large-Language Model (LLM), and wherein iterative prompting of the LLM based on learned domain knowledge is performed for enriching WHOIS records.

5 . The system of claim 1 , wherein the GenAI model provides syntactic analysis of the WHOIS record.

6 . The system of claim 1 , wherein the GenAI model provides semantic analysis of the WHOIS record.

7 . The system of claim 1 , wherein the GenAI model identifies privacy related redactions in the WHOIS record.

8 . The system of claim 1 , wherein the GenAI model identifies one or more fields of the WHOIS record that are inconsistently redacted or anonymized.

9 . The system of claim 1 , wherein the processor is further configured to:
prompt the GenAI model using iterative prompting to provide enriched WHOIS records.

10 . The system of claim 1 , wherein the processor is further configured to:
automatically determine whether an Internet resource associated with a parsed and enriched WHOIS record result is malicious or benign.

11 . A method, comprising:
receiving a WHOIS record; processing the WHOIS record at least in part using a generative artificial intelligence (GenAI) model to determine a set of predefined data block values applied to meta information for parsing the WHOIS record; and generating an enriched version of the WHOIS record.

12 . The method of claim 11 , wherein the WHOIS record includes unstructured data.

13 . The method of claim 11 , wherein the GenAI model includes a Large-Language Model (LLM).

14 . The method of claim 11 , wherein the GenAI model includes a Large-Language Model (LLM), and wherein iterative prompting of the LLM based on learned domain knowledge is performed for enriching WHOIS records.

15 . The method of claim 11 , wherein the GenAI model provides syntactic analysis of the WHOIS record.

16 . The method of claim 11 , wherein the GenAI model provides semantic analysis of the WHOIS record.

17 . The method of claim 11 , wherein the GenAI model identifies privacy related redactions in the WHOIS record.

18 . The method of claim 11 , wherein the GenAI model identifies one or more fields of the WHOIS record that are inconsistently redacted or anonymized.

19 . A computer program product embodied in a non-transitory computer readable medium and comprising computer instructions for:
receiving a WHOIS record; processing the WHOIS record at least in part using a generative artificial intelligence (GenAI) model to determine a set of predefined data block values applied to meta information for parsing the WHOIS record; and generating an enriched version of the WHOIS record.

20 . The computer program product of claim 19 , wherein the GenAI model includes a Large-Language Model (LLM).

Assignees

• Palo Alto Networks Inc

Inventors

• Chen Zhenhua
• Liu Daiping
• Li Wanjin
• Fei Fan

Classifications

• H04L63/1425

  Traffic logging, e.g. anomaly detection · CPC title

• G06F40/30

  Semantic analysis · CPC title

• H04L43/18 Primary

  Protocol analysers · CPC title

• G06F40/211 Primary

  Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars · CPC title