# US 10,771,994 B2 · Method and test system for mobile network testing as well as a network testing system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,771,994 B2 - Document ID: US10771994B2 - Status: Granted - Kind: B2 - Application number: 16/242,878 - Filed: 2019-01-08 - Published: 2019-08-08 - Granted: 2020-09-08 - Earliest claimed: 2018-02-07 - Assignees: Rohde & Schwarz GmbH & Co. KG - Applicants: Rohde & Schwarz GmbH & Co. KG - Inventors: Miguel Angel Roman; David Gonzalez - Web page: https://patentgrep.com/patent/US10771994B2 ## CPC - H04W 24/08: Testing, {supervising or monitoring} using real traffic - G06N 3/045: Combinations of networks - G06N 3/0475: Generative networks - G06N 3/088: Non-supervised learning, e.g. competitive learning - G06N 3/0895: Weakly supervised learning, e.g. semi-supervised or self-supervised learning - G06N 3/094: Adversarial learning - H04L 41/16: using machine learning or artificial intelligence - H04L 43/50: Testing arrangements - H04W 24/06: Testing, {supervising or monitoring} using simulated traffic - H04W 24/10: Scheduling measurement reports {; Arrangements for measurement reports} - H04L 43/0852: Delays - H04L 43/0888: Throughput - 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 - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract A method for mobile network testing uses at least one testing device that is configured to be connected to the mobile network. A predefined set of test procedures is run on the at least one testing device for generating at least one heat map assigned to the mobile network. The test results of the test procedures are evaluated via a machine learning model. The machine learning model is trained to complete missing information on an already present heat map based on the test results obtained. ## Claims ### Claim 1 A method for mobile network testing by using at least one testing device configured to be connected to the mobile network, comprising: running a predefined set of test procedures on the at least one testing device for generating at least one heat map assigned to the mobile network, the test procedures running on the at least one testing device simulating the behavior of participants of the mobile network; evaluating the test results of the test procedures via a machine learning model; and training the machine learning model to complete missing information on an already present heat map based on the test results obtained, the machine learning model being trained such that the trained machine learning model is configured to predict heat map information in order to fill empty areas of an incomplete heat map with respective information. ### Claim 2 (depends on 1) The method according to claim 1, wherein calls, web browsing, video playing and/or downloads are simulated. ### Claim 3 (depends on 1) The method according to claim 1, wherein the training of the machine learning model is based on inputting heat map information obtained from the test results. ### Claim 4 (depends on 3) The method according to claim 3, wherein the heat map information comprises network characteristics. ### Claim 5 (depends on 4) The method according to claim 4, wherein the network characteristics correspond to coverage information, information regarding covered networks, throughput network information, bandwidth information, signal strength information, interference information and/or latency information. ### Claim 6 (depends on 1) The method according to claim 1, wherein the at least one testing device records network characteristics obtained from different network measurements. ### Claim 7 (depends on 1) The method according to claim 1, wherein the training of the machine learning model is also based on geolocation information and/or time information. ### Claim 8 (depends on 1) The method according to claim 1, wherein the test results are evaluated on the testing device itself and/or wherein the test results are forwarded to a separate evaluation unit that evaluates the test results. ### Claim 9 (depends on 1) The method according to claim 1, wherein the machine learning model is provided by generative adversarial networks and/or a derivative of generative adversarial networks. ### Claim 10 A test system for mobile network testing, comprising at least one testing device and a processing unit configured to run a machine learning model to be trained, wherein the processing unit is configured to receive test results of a set of test procedures run on the at least one testing device and to evaluate the test results via the machine learning model, wherein the test procedures running on the at least one testing device simulate the behavior of participants of the mobile network, wherein the processing unit is configured to train the machine learning model to complete missing information on an already present heat map based on the test results obtained, and wherein the machine learning model is trained such that the trained machine learning model is configured to predict heat map information in order to fill empty areas of an incomplete heat map with respective information. ### Claim 11 (depends on 10) The test system according to claim 10, wherein the test system is configured to: run a predefined set of test procedures on the at least one testing device for generating at least one heat map assigned to the mobile network; evaluate the test results of the test procedures via a machine learning model; and train the machine learning model to complete missing information on an already present heat map based on the test results obtained. ### Claim 12 (depends on 10) The test system according to claim 10, wherein the machine learning model is provided by generative adversarial networks and/or a derivative of generative adversarial networks. ### Claim 13 A method for mobile network testing by using at least one testing device configured to be connected to a mobile network, comprising: providing a network testing system configured to complete missing information on an already present heat map by running a trained machine learning model, wherein the trained machine learning model is configured to predict heat map information in order to fill empty areas of an incomplete heat map with respective information; performing a single test by using the at least one testing device; evaluating the test result of the single test, wherein the test result corresponds to a heat map with missing information; and obtaining the missing information for the heat map of the test result from the network testing system to form a complete heat map, wherein the missing information is completed by the trained machine learning model. ### Claim 14 (depends on 13) The method according to claim 13, wherein the machine learning model is provided by generative adversarial networks and/or a derivative of generative adversarial networks. ### Claim 15 A network testing system for outputting a complete heat map, comprising: a processing unit configured to run a machine learning model, wherein the machine learning model is trained by: running a predefined set of test procedures on at least one testing device for generating at least one heat map assigned to a mobile network, the test procedures running on the at least one testing device simulating the behavior of participants of the mobile network; evaluating the test results of the test procedures via a machine learning model; and training the machine learning model to complete missing information on an already present heat map based on the test results obtained, the machine learning model being trained such that the trained machine learning model is configured to predict heat map information in order to fill empty areas of an incomplete heat map with respective information.