# US 11,909,908 B2 · Method and apparatus for monitoring a communication line > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,909,908 B2 - Document ID: US11909908B2 - Status: Granted - Kind: B2 - Application number: 17/142,377 - Filed: 2021-01-06 - Published: 2021-08-12 - Granted: 2024-02-20 - Earliest claimed: 2020-02-07 - Assignees: Nokia Solutions and Networks Oy - Applicants: Nokia Solutions and Networks Oy - Inventors: Nicolas Dupuis; Gert-Jan Stockman; Philippe Dierickx; Paschalis Tsiaflakis - Web page: https://patentgrep.com/patent/US11909908B2 ## CPC - H04M 3/306: {for frequencies above the voice frequency, e.g. xDSL line qualification (test methods, test equipment and test arrangements for subscriber lines using xDSL modems H04M3/304; systems modifying transmission characteristics according to link quality H04L1/0001; monitoring and/or testing of line transmission systems H04B3/46)} - H04B 3/23: using a replica of transmitted signal in the time domain, e.g. echo cancellers - H04B 3/493: Testing echo effects or singing - H04L 41/145: {involving simulating, designing, planning or modelling of a network} - H04L 41/147: for predicting network behaviour - H04L 41/149: for prediction of maintenance - H04M 1/24: Arrangements for testing - H04M 3/22: Arrangements for supervision, monitoring or testing - G06N 3/008: based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour - H04B 3/20: Reducing echo effects or singing; Opening or closing transmitting path; Conditioning for transmission in one direction or the other - H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08) - H04B: TRANSMISSION - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Embodiments relate to an apparatus comprising means configured for: obtaining echo response data representative of the echo response of a communication line, wherein the echo response data specifies the echo response based on two dimensions and includes first dimension data and second dimension data, determining at least one property of the communication line based on processing the echo response data with a neural network, wherein the neural network comprises at least: a first convolutional branch for processing the first dimension data, a second convolutional branch for processing the second dimension data, a dense part for processing the outputs of the first and second convolutional branches. ## Claims ### Claim 1 An apparatus comprising at least one processor and at least one memory storing computer program code, the memory and the computer program code being configured to cause, with the processor, the apparatus to: obtain echo response data representative of the echo response of a communication line, wherein the echo response data specifies the echo response based on two dimensions, the two dimensions include a first dimension data including real data or magnitude data and a second dimension data including imaginary data or phase data, determine at least one property of the communication line based on processing the echo response data with a neural network, wherein the neural network comprises at least: a first convolutional branch for processing the first dimension data, a second convolutional branch for processing the second dimension data, a dense part for processing outputs of the first and second convolutional branches. ### Claim 2 (depends on 1) The apparatus according to claim 1, wherein the first dimension data comprise magnitude data and the second dimension data comprise phase data or wherein the first dimension data comprise real part data and the second dimension data comprise imaginary part data. ### Claim 3 (depends on 1) The apparatus according to claim 1, wherein the first dimension data comprise magnitude data and the second dimension data comprise phase data, and wherein obtaining echo response data comprises receiving measurement data wherein the echo response is specified in a complex format comprising real part and imaginary part, and determining the magnitude data and phase data based on the echo response. ### Claim 4 (depends on 1) Apparatus according to claim 1, wherein the memory and the computer program code are further configured to cause, with the processor, the apparatus to: determine time domain data specifying a time domain reflectogram based on the echo response, wherein the neural network comprises a third convolutional branch for processing the time domain data and wherein the dense part is configured for processing output of the third convolutional branch. ### Claim 5 (depends on 1) The apparatus according to claim 1, wherein the echo response data specifies an uncalibrated echo response, and the memory and the computer program code are configured to cause, with the processor, the apparatus to: determine a calibrated echo response based on the uncalibrated echo response and calibration data. ### Claim 6 (depends on 1) The apparatus according to claim 1, wherein the memory and the computer program code are configured to cause, with the processor, the apparatus to: determine at least one other property of the communication line based on processing the echo response data with another neural network, wherein the other neural network comprises at least: a fourth convolutional branch for processing first dimension data, a fifth convolutional branch for processing the second dimension data, another dense part for processing outputs of the fourth and fifth convolutional branches and said at least one property. ### Claim 7 (depends on 1) The apparatus according to claim 1, wherein said at least one property include at least one of a line termination, a line length, a type of a cable, a presence of impairment, a type of impairment, a location of impairment. ### Claim 8 (depends on 6) The apparatus according to claim 6, wherein said at least one property include a line termination and said at least one other property include a line length. ### Claim 9 (depends on 1) The apparatus according to claim 1, wherein the memory and the computer program code are configured to cause, with the processor, the apparatus to: control a display based on the determined at least one property and/or configure a network element associated with the communication line based on the determined at least one property. ### Claim 10 (depends on 1) The apparatus according to claim 1, wherein the memory and the computer program code are configured to cause, with the processor, the apparatus to: determine a training set based on generating echo response of modelled communication lines with a circuit simulator, and training the neural network based on the training set. ### Claim 11 A computer-implemented method for monitoring a communication line, comprising: obtaining echo response data representative of the echo response of a communication line, wherein the echo response data specifies the echo response based on two dimensions, the two dimensions include a first dimension data including read data or magnitude data and a second dimension data including imaginary data or phase data, determining at least one property of the communication line based on processing the echo response data with a neural network, wherein the neural network comprises at least: a first convolutional branch for processing the first dimension data, a second convolutional branch for processing the second dimension data, a dense part for processing outputs of the first and second convolutional branches. ### Claim 12 (depends on 11) The method according to claim 11, wherein the first dimension data comprise magnitude data and the second dimension data comprise phase data or wherein the first dimension data comprise real part data and the second dimension data comprise imaginary part data. ### Claim 13 (depends on 11) The method according to claim 11, comprising determining time domain data specifying a time domain reflectogram based on the echo response, wherein the neural network comprises a third convolutional branch for processing the time domain data and wherein the dense part is configured for processing the output of the third convolutional branch. ### Claim 14 (depends on 11) The method according to claim 11, comprising determining a training set based on generating echo response of modelled communication lines with a circuit simulator, and training the neural network based on the training set. ### Claim 15 A non-transitory computer readable medium storing a computer program comprising instructions for causing a computer to: obtain echo response data representative of the echo response of a communication line, wherein the echo response data specifies the echo response based on two dimensions, the two dimensions include a first dimension data including real data or magnitude data and a second dimension data, including imaginary data or phase data, determine at least one property of the communication line based on processing the echo response data with a neural network, wherein the neural network comprises at least: a first convolutional branch for processing the first dimension data, a second convolutional branch for processing the second dimension data, a dense part for processing outputs of the first and second convolutional branches.