# US 12,114,175 B2 · Intelligent wireless network design system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,114,175 B2 - Document ID: US12114175B2 - Status: Granted - Kind: B2 - Application number: 17/566,612 - Filed: 2021-12-30 - Published: 2023-07-06 - Granted: 2024-10-08 - Earliest claimed: 2021-12-30 - Assignees: ITRA Wireless AI, LLC - Applicants: ITRA Wireless Ai, LLC - Inventors: Andriy Khomenko; Maxim Kormilitsin - Web page: https://patentgrep.com/patent/US12114175B2 ## CPC - H04W 16/18: Network planning tools - B64C 39/024: {of the remote controlled vehicle type, i.e. RPV} - B64U 10/13: Flying platforms - G06N 3/045: Combinations of networks - G06N 3/08: Learning methods - G06N 3/126: Evolutionary algorithms, e.g. genetic algorithms or genetic programming - G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06N 20/00: Machine learning - G06N 20/10: using kernel methods, e.g. support vector machines [SVM] - G06N 20/20: Ensemble learning - H04B 17/3913: {Predictive models, e.g. based on neural network models} - H04L 41/12: Discovery or management of network topologies - H04L 41/145: {involving simulating, designing, planning or modelling of a network} - H04L 41/16: using machine learning or artificial intelligence - H04W 16/22: Traffic simulation tools or models - B64U 2101/30: for imaging, photography or videography - H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72) - B64C: AEROPLANES; HELICOPTERS - B64U: UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - H04B: TRANSMISSION - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract A system for an automated ML-based design of a wireless network. The system includes a processor of a design server node connected to at least one local, edge, or cloud server node over a network and a memory on which are stored machine-readable instructions that when executed by the processor, cause the processor to: acquire aerial 3-D mapping data of a target area from an unmanned aircraft system (UAS) flying over the target area; acquire surface 3-D mapping data from a ground robotic crawler; parse the 3-D mapping data to derive an at least one feature vector; provide the at least one feature vector to a machine learning (ML) module residing on the at least one local, edge, or cloud server node for generating a predictive model of a wireless network for some or all of the target area; receive outputs of the predictive model; and generate a wireless network design for the some or all of the target area based on the predictive outputs. ## Claims ### Claim 1 A system, comprising: a processor of a design server node connected to at least one cloud server node over a network; and a memory on which are stored machine-readable instructions that when executed by the processor, cause the processor to: acquire aerial surveillance data of a target area from an unmanned aircraft system (UAS) flying over the target area; parse the aerial surveillance data to derive an at least one feature vector; provide the at least one feature vector to a machine learning (ML) module residing on the at least one cloud server node for generating a predictive model of a wireless network for the target area; receive outputs of the predictive model; generate a wireless network design for the target area based on the predictive outputs; and configure the ML module to codify deterministic base relationships characterizing known profiles and behaviors of radio frequency (RF) and other electronic elements to be used in the wireless network design for the target area. ### Claim 2 (depends on 1) The system of claim 1, wherein the aerial surveillance data comprises 3-D mapping data comprising any of: photogrammetry data, LiDAR data and thermal imagery data. ### Claim 3 (depends on 2) The system of claim 2, wherein the aerial surveillance data further comprises 3-D sequential signal strength data collected by the UAS passing through a plurality of vertical flight planes located at a standard distance from each other over the target area. ### Claim 4 (depends on 3) The system of claim 3, wherein the instructions further cause the processor to configure the ML module to implement ML regression modeling of a signal strength within each plane of the plurality of the vertical flight planes. ### Claim 5 (depends on 3) The system of claim 3, wherein the instructions further cause the processor to record the 3-D sequential signal quality data onto a blockchain, wherein the design server node is a blockchain peer node. ### Claim 6 (depends on 3) The system of claim 3, wherein the instructions further cause the processor to determine a usable signal strength area definition within each plane of the plurality of the vertical flight planes. ### Claim 7 A method, comprising: acquiring, by a design server node, aerial surveillance data of a target area from an unmanned aircraft system (UAS) flying over the target area; parsing, by the design server node, the aerial surveillance data to derive an at least one feature vector; providing, by the design server node, the at least one feature vector to a machine learning (ML) module residing on the at least one cloud server node for generating a predictive model of a wireless network for the target area; receiving, by the design server node, a plurality of outputs of the predictive model; generating a wireless network design for the target area based on the plurality of the predictive outputs; and configuring the ML module to codify deterministic base relationships characterizing known profiles and behaviors of radio frequency (RF) and other electronic elements to be used in the wireless network design for the target area. ### Claim 8 (depends on 7) The method of claim 7, further comprising receiving the aerial surveillance data comprising 3-D mapping data comprising any of: photogrammetry data, LiDAR data and thermal imagery data. ### Claim 9 (depends on 8) The method of claim 8, further comprising configuring the ML module to implement ML regression modeling of a signal strength within each plane of the plurality of the vertical flight planes. ### Claim 10 (depends on 8) The method of claim 8, further comprising recording the 3-D sequential signal strength data onto a blockchain, wherein the design server node is a blockchain peer node. ### Claim 11 (depends on 8) The method of claim 8, further comprising determining a usable signal strength area definition within each plane of the plurality of the vertical flight planes. ### Claim 12 (depends on 7) The method of claim 7, further comprising receiving the aerial surveillance data further comprising 3-D sequential signal strength data collected by the UAS passing through a plurality of vertical flight planes located at a standard distance from each other over the target area. ### Claim 13 A non-transitory computer readable medium comprising instructions, that when read by a processor, cause the processor to perform: acquiring aerial surveillance data of a target area from an unmanned aircraft system (UAS) flying over the target area; parsing the aerial surveillance data to derive an at least one feature vector; providing the at least one feature vector to a machine learning (ML) module residing on the at least one cloud server node for generating a predictive model of a wireless network for the target area; receiving a plurality of outputs of the predictive model; generating a wireless network design for the target area based on the plurality of the predictive outputs; and configuring the ML module to codify deterministic base relationships characterizing known profiles and behaviors of radio frequency (RF) and other electronic elements to be used in the wireless network design for the target area. ### Claim 14 (depends on 13) The non-transitory computer readable medium of claim 13, further comprising instructions, that when read by the processor, cause the processor to receive the aerial surveillance data comprising 3-D mapping data and 3-D sequential signal strength data collected by the UAS passing through a plurality of vertical flight planes located at a standard distance from each other over the target area. ### Claim 15 (depends on 14) The non-transitory computer readable medium of claim 14, further comprising instructions, that when read by the processor, cause the processor to configure the ML module to implement ML regression modeling of a signal strength within each plane of the plurality of the vertical flight planes. ### Claim 16 (depends on 14) The non-transitory computer readable medium of claim 14, further comprising instructions, that when read by the processor, cause the processor to record the 3-D sequential signal strength data onto a blockchain. ### Claim 17 (depends on 14) The non-transitory computer readable medium of claim 14, further comprising instructions, that when read by the processor, cause the processor to determine a usable signal strength area definition within each plane of the plurality of the vertical flight planes. ### Claim 18 (depends on 14) The non-transitory computer readable medium of claim 14, further comprising instructions, that when read by the processor, cause the processor to determine a usable signal strength area definition in a 3-D space based on a smart interpolation provided by the ML module.