# US 12,192,784 B2 · Method and network apparatus for generating real-time radio coverage map in wireless network > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,192,784 B2 - Document ID: US12192784B2 - Status: Granted - Kind: B2 - Application number: 17/878,521 - Filed: 2022-08-01 - Published: 2023-02-09 - Granted: 2025-01-07 - Earliest claimed: 2021-08-02 - Assignees: Samsung Electronics Co., Ltd. - Applicants: Samsung Electronics Co., Ltd. - Inventors: Satya Kumar Vankayala; Swaraj Kumar; Seungil Yoon; Samuel Ignatius Kanakaraj - Web page: https://patentgrep.com/patent/US12192784B2 ## CPC - G06F 18/24133: {Distances to prototypes} - H04W 16/18: Network planning tools - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06V 20/13: Satellite images - H04W 24/00: Supervisory, monitoring or testing arrangements - G06N 3/045: Combinations of networks - G06N 3/0475: Generative networks - G06N 3/092: Reinforcement learning - G06N 3/094: Adversarial learning - H04W 36/32: by location or mobility data, e.g. speed data - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Embodiments herein provide a method for generating a real-time radio coverage map in a wireless network by a network apparatus. The method includes: receiving real-time geospatial information from one or more geographical sources in the wireless network; determining handover information of at least one user equipment (UE) in the wireless network from a plurality of base stations based on the real-time geospatial information; and generating the real-time radio coverage map based on the handover information of at least one UE and the real-time geospatial information. ## Claims ### Claim 1 A method for generating a real-time radio coverage map in a wireless network, wherein the method comprises: receiving, by a network apparatus in the wireless network, real-time geospatial information from one or more geographical sources in the wireless network; determining, by the network apparatus, handover information of at least one user equipment (UE) in the wireless network from a plurality of base stations based on the real-time geospatial information; and generating, by the network apparatus, the real-time radio coverage map based on the handover information of the at least one UE and the real-time geospatial information. ### Claim 2 (depends on 1) The method as claimed in claim 1, wherein the geographical sources comprise at least one of: a satellite image system configured to capture a geographical image of at least one geographical area associated with the one or more geographical sources, drones configured to capture real time images of the at least one geographical area associated with the one or more geographical sources, a drive test system configured to determine drive test information in the at least one geographical area associated with the one or more geographical sources, a two dimensional (2D) and a three dimensional (3D) geospatial map system configured to generate a 2D and a 3D geospatial map of the at least one geographical area associated with the one or more geographical sources, a traffic monitoring system configured to monitor real-time traffic data of the at least one geographical area associated with the one or more geographical sources, or a weather monitoring system configured to determine weather information of the at least one geographical area associated with the one or more geographical sources. ### Claim 3 (depends on 1) The method as claimed in claim 1, wherein the real-time geospatial information comprises at least one of satellite image of at least one geographical area associated with the one or more geographical sources, a 2D and a 3D geospatial map of the at least one geographical area associated with the one or more geographical sources, real-time traffic data of the at least one geographical area associated with the one or more geographical sources, weather information of the at least one geographical area associated with the one or more geographical sources, or drive test information identifying at least one of areas with no cellular connectivity, handover issues, call drops, low throughputs, or no data. ### Claim 4 (depends on 1) The method as claimed in claim 1, wherein generating, by the network apparatus, the real-time radio coverage map based on the handover information of at least one UE and the real-time geospatial information comprising: feeding, by the network apparatus, the real-time geospatial information and the handover information onto at least one machine learning (ML) model; marking, by the network apparatus, a location of the plurality of base stations in the wireless network from the real-time geospatial information using the at least one ML model; determining, by the network apparatus, material characteristic of objects in the location of the plurality of base stations in the wireless network based on the real-time geospatial information using the at least one ML model, wherein the material characteristic comprises a number of buildings, tree density, landscape data, and structure of objects; and generating, by the network apparatus, the real time radio coverage map using the at least one ML model based on the material characteristic of the objects, the real-time geospatial information, and the handover information of at least one UE. ### Claim 5 (depends on 4) The method as claimed in claim 4, further comprising: training, the network apparatus, the at least one ML model by: receiving multiple inputs from the plurality of the geographical sources in the wireless network while rendering the radio maps in real time; creating a dataset by collecting the multiple inputs; collecting information associated with the base station, a corresponding radio-map in a situation, and an information for a geospatial data and weather and satellite date, wherein the at least one at least one ML model is trained by feeding the multiple input, wherein an output of the at least one ML model is a generated radiomap compared with a real radiomap collected from the base station and a difference between the generated radiomap and the real radiomap is used to update the at least one ML model. ### Claim 6 (depends on 5) The method as claimed in claim 5, the method further comprising: receiving, by the network apparatus, a plurality of real-time radio coverage maps generated by other network apparatuses in the wireless network, wherein each real-time radio coverage map of the plurality of real-time radio coverage maps comprises local data of the UEs connected to a local network apparatus of the other network apparatuses; receiving, by the network apparatus, the trained weights of each real-time radio coverage map of the plurality of real-time radio coverage maps from each of the network apparatuses in the wireless network; aggregating, by the network apparatus, the trained weights of each real-time radio coverage map of the plurality of real-time radio coverage maps; generating, by the network apparatus, a global ML model based on the trained weights of each real-time radio coverage map of the plurality of real-time radio coverage maps; and sending, by the network apparatus, the global ML model to each of the network apparatuses in the wireless network for generating the real-time radio coverage map. ### Claim 7 (depends on 5) The method as claimed in claim 5, wherein the at least one ML model is hosted in at least one of a base station in the wireless network, virtualized radio access networks (vRANs) in the wireless network, open radio access network (O-RAN) in the wireless network, or a cloud radio access network (CRAN) in the wireless network. ### Claim 8 (depends on 1) The method as claimed in claim 1, the method further comprising: determining, by the network apparatus, shadow regions in the real-time radio coverage map due to which coverage is limited in location of the base stations in the wireless network; determining, by the network apparatus, at least one remedial action to be performed to improvise the coverage in location of the base stations based on at least one of antenna tilt, modulation and coding scheme, or transmission mode; and automatically performing, by the network apparatus, the at least one remedial action in location of the base stations in the wireless network. ### Claim 9 (depends on 8) The method as claimed in claim 8, wherein the at least one remedial action comprises: changing antenna parameters of at least one radio resource for the at least one UE in the wireless network, and increasing or decreasing a power of at least one radio resource for the at least one UE in the wireless network, deploying the at least one radio resource for the at least one UE in the wireless network, and removing the at least one radio resource for the at least one UE in the wireless network, wherein the antenna parameters comprises at least one of an orientation, a tilt angle, or a height of the antenna, and wherein the at least one radio resource comprises a base station, a drone, a macro cell, and a small cell. ### Claim 10 (depends on 9) The method as claimed in claim 9, wherein the shadow regions in the real-time radio coverage map is determined using a convolutional neural network (CNN). ### Claim 11 (depends on 10) The method as claimed in claim 10, the method further comprising: training the CNN for determining the shadow regions by: creating a dataset by collecting multiple inputs; and collecting information associated with the base station, a corresponding radio-map in a situation, and an information for a geospatial data and weather and satellite data, wherein the CNN is trained by feeding the input, wherein an output of the CNN is a radiomap which is compared with a real radiomap collected from the base station and a difference between the generated radiomap and the real radiomap is used to update at the CNN. ### Claim 12 (depends on 1) The method as claimed in claim 1, wherein the network apparatus includes one of a base station, a centralized server handling different base stations in the wireless network, virtualized radio access networks (vRANs), open radio access network (O-RAN), a cloud radio access network (CRAN), a distributive server handling different base stations in the wireless network, or an edge server handling different base stations in the wireless network. ### Claim 13 A network apparatus configured to generate a real-time radio coverage map in a wireless network, the network apparatus comprising: a memory comprising information of cells and user equipments (UEs) available in the wireless network; a processor connected to the memory; and a real-time radio coverage map controller, communicatively connected to the memory and the processor, configured to: receive real-time geospatial information from one or more geographical sources in the wireless network; determine handover information of at least one UE in the wireless network from a plurality of base stations based on the real-time geospatial information; and generate the real-time radio coverage map based on the handover information of at least one UE and the real-time geospatial information. ### Claim 14 (depends on 13) The network apparatus as claimed in claim 13, wherein the geographical sources comprise at least one of: a satellite image system configured to capture a geographical image of at least one geographical area associated with the one or more geographical sources, drones configured to capture real time images of the at least one geographical area associated with the one or more geographical sources, a drive test system configured to determine drive test information in the at least one geographical area associated with the one or more geographical sources, a 2D and 3D geospatial map system configured to generate a 2D and a 3D geospatial map of the at least one geographical area associated with the one or more geographical sources, a traffic monitoring system configured to monitor real-time traffic data of the at least one geographical area associated with the one or more geographical sources, or a weather monitoring system configured to determine weather information of the at least one geographical area associated with the one or more geographical sources. ### Claim 15 (depends on 13) The network apparatus as claimed in claim 13, wherein the real-time geospatial information comprises at least one of: a satellite image of at least one geographical area associated with the one or more geographical sources, a 2D and a 3D geospatial map of the at least one geographical area associated with the one or more geographical sources, real-time traffic data of the at least one geographical area associated with the one or more geographical sources, weather information of the at least one geographical area associated with the one or more geographical sources, or drive test information identifying at least one of areas with no 4G connectivity, handover issues, call drops, low throughputs, or no data. ### Claim 16 (depends on 13) The network apparatus as claimed in claim 13, wherein generating the real-time radio coverage map based on the handover information of at least one UE and the real-time geospatial information comprises: feeding the real-time geospatial information and the handover information onto the at least one Machine Learning (ML) model; marking a location of the plurality of base stations in the wireless network from the real-time geospatial information using the at least one ML model; determining a material characteristic of objects in the location of the plurality of base stations in the wireless network based on the real-time geospatial information using the at least one ML model, wherein the material characteristic comprises a number of buildings, tree density, landscape data, and structure of objects; and generating the real time radio coverage map using the at least one ML model based on the material characteristic of the objects, the real-time geospatial information, and the handover information of at least one UE. ### Claim 17 (depends on 13) The network apparatus as claimed in claim 13, wherein the real-time radio coverage map controller is configured to train the at least one ML model by: receiving multiple inputs from the plurality of the geographical sources in the wireless network while rendering the radio maps in real time; creating a dataset by collecting the multiple inputs; and collecting information associated with the base station, a corresponding radio-map in a situation, and an information for a geospatial data and weather and satellite date, wherein the at least one at least one ML model is trained by feeding the multiple input, wherein an output of the at least one ML model includes a generated radiomap compared with the real radiomap collected from the base station and a difference between the generated radiomap and the real radiomap is used to update the at least one ML model. ### Claim 18 (depends on 17) The network apparatus as claimed in claim 17, wherein the real-time radio coverage map controller is configured to: receive a plurality of real-time radio coverage map generated by other network apparatuses in the wireless network, wherein each real-time radio coverage map of the plurality of real-time radio coverage maps comprises local data of the UEs connected to a local network apparatus of the other network apparatuses; receive the trained weights of each real-time radio coverage map of the plurality of real-time radio coverage maps from each of the network apparatuses in the wireless network; aggregate the trained weights of each real-time radio coverage map of the plurality of real-time radio coverage maps; generate a global ML model based on the trained weights of each real-time radio coverage map of the plurality of real-time radio coverage maps; and send the global ML model to each of the network apparatuses in the wireless network for generating the real-time radio coverage map. ### Claim 19 (depends on 17) The network apparatus as claimed in claim 17, wherein the at least one ML model is hosted in at least one of a base station in the wireless network, virtualized radio access networks (vRANs) in the wireless network, open radio access network (O-RAN) in the wireless network, or a cloud radio access network (CRAN) in the wireless network. ### Claim 20 (depends on 13) The network apparatus as claimed in claim 13, wherein the real-time radio coverage map controller is configured to: determine shadow regions in the real-time radio coverage map due to which coverage is limited in location of the base stations in the wireless network; determine at least one remedial action to be performed to improvise the coverage in location of the base stations based on at least one of antenna tilt, modulation and coding scheme, or transmission mode and automatically perform the at least one remedial action in location of the base stations in the wireless network.