# US 12,120,001 B1 · Systems and methods for detecting network congestion and automatically deploying a network slice > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,120,001 B1 - Document ID: US12120001B1 - Status: Granted - Kind: B1 - Application number: 18/476,969 - Filed: 2023-09-28 - Granted: 2024-10-15 - Earliest claimed: 2023-09-28 - Assignees: Verizon Patent and Licensing Inc. - Applicants: Verizon Patent and Licensing Inc. - Inventors: Deepak Chadaga; Antonio M. Osorio; Tyler Kates - Web page: https://patentgrep.com/patent/US12120001B1 ## CPC - H04L 41/40: using virtualisation of network functions or resources, e.g. SDN or NFV entities - H04L 41/0895: Configuration of virtualised networks or elements, e.g. virtualised network function or OpenFlow elements - H04L 41/16: using machine learning or artificial intelligence - H04L 47/11: Identifying congestion - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract A device may receive network congestion data associated with a network providing a network slice to a user device and that includes data identifying a number of users, an average throughput, a latency, and one or more key performance indicators associated with the network. The device may receive media data associated with the user device and may receive weather data associated with the user device. The device may process the number of users, the average throughput, the latency, and the one or more key performance indicators, with a deep learning model, to generate a congestion decision for the network. The device may selectively activate a new network slice for the user device based on the congestion decision indicating congestion in the network, or may maintain the network slice for the user device based on the congestion decision indicating no congestion in the network. ## Claims ### Claim 1 A method, comprising: receiving, by a device, network congestion data associated with a network providing a network slice to a user device and that includes data identifying a number of users, an average throughput, a latency, and one or more key performance indicators associated with the network; receiving, by the device, media data associated with the user device; receiving, by the device, weather data associated with the user device; processing, by the device, the number of users, the average throughput, the latency, and the one or more key performance indicators, with a deep learning model, to generate a congestion decision for the network; selectively: activating, by the device, a new network slice for the user device based on the congestion decision indicating congestion in the network, or maintaining, by the device, the network slice for the user device based on the congestion decision indicating no congestion in the network; selecting a region, a duration, and a type for the new network slice based on activating the new network slice and based on the media data and the weather data; and causing the network to provision the new network slice for the user device based on the region, the duration, and the type for the new network slice. ### Claim 2 (depends on 1) The method of claim 1, wherein the network causes the user device to utilize the new network slice in the region and for the duration. ### Claim 3 (depends on 1) The method of claim 1, wherein the user device is configured to utilize an application via the new network slice. ### Claim 4 (depends on 1) The method of claim 1, further comprising: causing the network to instruct the user device to provide a provisioned application on the new network slice. ### Claim 5 (depends on 1) The method of claim 1, wherein the user device is associated with a public safety user. ### Claim 6 (depends on 1) The method of claim 1, wherein the user device is configured for the new network slice. ### Claim 7 A device, comprising: one or more processors configured to: receive network congestion data associated with a network providing a network slice to a user device, wherein the network congestion data includes data identifying a number of users, an average throughput, a latency, and one or more key performance indicators associated with the network; receive media data associated with the user device; receive weather data associated with the user device; process the number of users, the average throughput, the latency, and the one or more key performance indicators, with a deep learning model, to generate a congestion decision for the network; activate a new network slice for the user device based on the congestion decision indicating congestion in the network; select a region, a duration, and a type for the new network slice based on activating the new network slice and based on the media data and the weather data; and cause the network to provision the new network slice for the user device based on the region, the duration, and the type for the new network slice. ### Claim 8 (depends on 7) The device of claim 7, wherein the deep learning model is a recurrent neural network model. ### Claim 9 (depends on 7) The device of claim 7, wherein the media data includes data identifying one or more of social media events affecting the user device, news events affecting the user device, or planned events affecting the user device. ### Claim 10 (depends on 7) The device of claim 7, wherein the weather data includes data identifying one or more of a natural disaster affecting the user device or a weather event affecting the user device. ### Claim 11 (depends on 7) The device of claim 7, wherein the type of the new network slice includes one or more of a public safety application type, a streaming service type, an industrial application type, a voice-over-new-radio application type, or an autonomous vehicle application type. ### Claim 12 (depends on 7) The device of claim 7, wherein the network is a radio access network. ### Claim 13 (depends on 7) The device of claim 7, wherein the network experiences congestion when a bandwidth of the network required to serve all active applications is substantially equal to or exceeds an available bandwidth that the network supports. ### Claim 14 A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising: one or more instructions that, when executed by one or more processors of a device, cause the device to: receive network congestion data associated with a network providing a network slice to a user device, wherein the network congestion data includes data identifying a number of users, an average throughput, a latency, and one or more key performance indicators associated with the network; receive media data associated with the user device; receive weather data associated with the user device; process the number of users, the average throughput, the latency, and the one or more key performance indicators, with a deep learning model, to generate a congestion decision for the network; selectively: activate a new network slice for the user device based on the congestion decision indicating congestion in the network, or maintain the network slice for the user device based on the congestion decision indicating no congestion in the network; select a region, a duration, and a type for the new network slice based on activating the new network slice and based on the media data and the weather data; and cause the network to provision the new network slice for the user device based on the region, the duration, and the type for the new network slice. ### Claim 15 (depends on 14) The non-transitory computer-readable medium of claim 14, wherein the user device is associated with a public safety user and is configured for the new network slice. ### Claim 16 (depends on 14) The non-transitory computer-readable medium of claim 14, wherein the media data includes data identifying one or more of social media events affecting the user device, news events affecting the user device, or planned events affecting the user device. ### Claim 17 (depends on 14) The non-transitory computer-readable medium of claim 14, wherein the weather data includes data identifying one or more of a natural disaster affecting the user device or a weather event affecting the user device. ### Claim 18 (depends on 14) The non-transitory computer-readable medium of claim 14, wherein the network experiences congestion when a bandwidth of the network required to serve all active applications is substantially equal to or exceeds an available bandwidth that the network supports. ### Claim 19 (depends on 1) The method of claim 1, wherein the weather data includes data identifying a natural disaster or a weather event and timing associated with the natural disaster or the weather event. ### Claim 20 (depends on 14) The non-transitory computer-readable medium of claim 14, wherein the deep learning model includes a bi-directional artificial neural network.