# US 12,764,032 B2 · Systems and methods for generating computing network infrastructure from natural-language descriptions > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,764,032 B2 - Document ID: US12764032B2 - Status: Granted - Kind: B2 - Application number: 18/989,841 - Filed: 2024-12-20 - Published: 2025-04-17 - Granted: 2026-10-13 - Earliest claimed: 2022-10-19 - Assignees: The MITRE Corporation - Applicants: The MITRE Corporation - Inventors: Michael Bastian Kouremetis; Christopher David Jellen; William Bryan Booth; Andrew Fred Applebaum - Web page: https://patentgrep.com/patent/US12764032B2 ## CPC - H04L 41/145: {involving simulating, designing, planning or modelling of a network} - G06F 40/295: Named entity recognition - G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Described herein are systems and methods for generating a computing network from natural language descriptions of the computing network are provided. In one or more examples, the systems and methods described below can be used harvest publicly available (or even privately available) natural language descriptions of a computing network, and convert those descriptions into an operational replica of the described computing network. By harvesting both publicly available data, as well as other resources, the systems and methods described herein can allow for an analyst tasked with analyzing a given computing network to generate a fully operational replica of the computing network without having to have direct access to the network. In one or more examples, the analyst can recreate a fully-functional replica of the network to be analyzed based on partial descriptions of the computing network, thereby greatly improving the level of analysis capable of being performed. ## Claims ### Claim 1 A method for generating a computing network based on natural language descriptions of the computing network, the method comprising: receiving a preliminary network report comprising one or more network entities extracted from one or more natural language descriptions of the computing network; generating additional information associated with the one or more network entities from the preliminary network report; modifying the preliminary network report with the generated additional information; and generating a replica of the computing network based on the modified network report. ### Claim 2 (depends on 1) The method of claim 1, wherein the one or more network entities comprise a first software application, and wherein generating additional information comprises determining one or more additional software applications that are known to co-exist with the first software application. ### Claim 3 (depends on 2) The method of claim 2, wherein determining one or more additional software applications that are known to co-exist with the first software application comprises accessing one or more databases, wherein the one or more databases comprise information about software applications that are known to co-exist with one another. ### Claim 4 (depends on 2) The method of claim 2, wherein determining one or more additional software applications that are known to co-exist with the first software application comprises applying one or more machine learning models. ### Claim 5 (depends on 1) The method of claim 1, further comprising receiving one or more textual descriptions of the computing network, wherein the received one or more textual descriptions of the computing network are formatting in a computer-readable format that is configured to enable natural language processing. ### Claim 6 (depends on 5) The method of claim 5, wherein generating additional information comprises applying a textual nearest neighbors process to the received one or more textual descriptions of the computing network. ### Claim 7 (depends on 1) The method of claim 1, wherein generating additional information comprises determining one or more vulnerabilities associated with the one or more network entities. ### Claim 8 (depends on 7) The method of claim 7, wherein determining one or more vulnerabilities associated with the one or more network entities comprises accessing one or more databases, wherein the one or more databases comprise information about vulnerabilities of network entities. ### Claim 9 A system for generating a computing network based on natural language descriptions of the computing network, the system comprising a memory and one or more processors, wherein the memory stores one or more programs that when executed by the one or more processors, cause the one or more processors to: receive a preliminary network report comprising one or more network entities extracted from one or more natural language descriptions of the computing network; generate additional information associated with the one or more network entities from the preliminary network report; modify the preliminary network report with the generated additional information; and generate a replica of the computing network based on the modified network report. ### Claim 10 (depends on 9) The system of claim 9, wherein the one or more network entities comprise a first software application, and wherein generating additional information comprises determining one or more additional software applications that are known to co-exist with the first software application. ### Claim 11 (depends on 10) The system of claim 10, wherein determining one or more additional software applications that are known to co-exist with the first software application comprises accessing one or more databases, wherein the one or more databases comprise information about software applications that are known to co-exist with one another. ### Claim 12 (depends on 10) The system of claim 10, wherein determining one or more additional software applications that are known to co-exist with the first software application comprises applying one or more machine learning models. ### Claim 13 (depends on 9) The system of claim 9, wherein the processors receive one or more textual descriptions of the computing network, wherein the received one or more textual descriptions of the computing network are formatting in a computer-readable format that is configured to enable natural language processing. ### Claim 14 (depends on 13) The system of claim 13, wherein generating additional information comprises applying a textual nearest neighbors process to the received one or more textual descriptions of the computing network. ### Claim 15 (depends on 9) The system of claim 9, wherein generating additional information comprises determining one or more vulnerabilities associated with the one or more network entities. ### Claim 16 (depends on 15) The system of claim 15, wherein determining one or more vulnerabilities associated with the one or more network entities comprises accessing one or more databases, wherein the one or more databases comprise information about vulnerabilities of network entities. ### Claim 17 A non-transitory computer readable storage medium storing one or more programs for generating a computing network based on natural language descriptions of the computing network, the programs for execution by one or more processors of an electronic device that when executed by the device, cause the device to: receive a preliminary network report comprising one or more network entities extracted from one or more natural language descriptions of the computing network; generate additional information associated with the one or more network entities from the preliminary network report; modify the preliminary network report with the generated additional information; and generate a replica of the computing network based on the modified network report. ### Claim 18 (depends on 17) The non-transitory computer readable storage medium of claim 17, wherein the one or more network entities comprise a first software application, and wherein generating additional information comprises determining one or more additional software applications that are known to co-exist with the first software application. ### Claim 19 (depends on 18) The non-transitory computer readable storage medium of claim 18, wherein determining one or more additional software applications that are known to co-exist with the first software application comprises accessing one or more databases, wherein the one or more databases comprise information about software applications that are known to co-exist with one another. ### Claim 20 (depends on 18) The non-transitory computer readable storage medium of claim 18, wherein determining one or more additional software applications that are known to co-exist with the first software application comprises applying one or more machine learning models. ### Claim 21 (depends on 17) The non-transitory computer readable storage medium of claim 17, wherein the processors receive one or more textual descriptions of the computing network, wherein the received one or more textual descriptions of the computing network are formatting in a computer-readable format that is configured to enable natural language processing. ### Claim 22 (depends on 21) The non-transitory computer readable storage medium of claim 21, wherein generating additional information comprises applying a textual nearest neighbors process to the received one or more textual descriptions of the computing network. ### Claim 23 (depends on 17) The non-transitory computer readable storage medium of claim 17, wherein generating additional information comprises determining one or more vulnerabilities associated with the one or more network entities. ### Claim 24 (depends on 23) The non-transitory computer readable storage medium of claim 23, wherein determining one or more vulnerabilities associated with the one or more network entities comprises accessing one or more databases, wherein the one or more databases comprise information about vulnerabilities of network entities.