# US 12,007,831 B2 · Devices and components for machine learning-based signal error correction and methods of use thereof > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,007,831 B2 - Document ID: US12007831B2 - Status: Granted - Kind: B2 - Application number: 17/405,877 - Filed: 2021-08-18 - Published: 2023-02-23 - Granted: 2024-06-11 - Earliest claimed: 2021-08-18 - Assignees: Capital One Services, LLC - Applicants: Capital One Services, LLC - Inventors: Austin Walters; Jeremy Goodsitt; Vincent Pham - Web page: https://patentgrep.com/patent/US12007831B2 ## CPC - G06F 11/0793: {Remedial or corrective actions (recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40)} - G06F 11/0721: {within a central processing unit [CPU]} - G06F 11/0751: {Error or fault detection not based on redundancy (power supply failures G06F1/30; network fault management H04L41/06)} - G06N 3/04: Architecture, e.g. interconnection topology - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/0455: Auto-encoder networks; Encoder-decoder networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/084: Backpropagation, e.g. using gradient descent - G06N 20/00: Machine learning - G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06N 20/10: using kernel methods, e.g. support vector machines [SVM] - G06N 20/20: Ensemble learning - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract The present disclosure enables signal error correction using a first processor and a memory on a first substrate, where the first processor is operationally connected to a second processor on a second substrate and the memory stores computer code having a machine learning model. The first processor executes computer code to: automatically receive from the second processor, a first output signal intended to be received by a target recipient device. The first processor automatically inputs the first output signal into the machine learning model, where the machine learning model determines that the first output signal includes an error signal that would cause a malfunction in the target recipient device, and output an instruction to cause the first processor to generate a second output signal that corrects the error signal. The first processor automatically generates the second output signal and transmits the second output signal to the target recipient device. ## Claims ### Claim 1 An apparatus comprising: a first substrate; a first processor and a memory coupled to the first substrate; wherein the first processor is operationally connected to a signaling device comprising a second processor coupled to a second substrate; wherein the memory stores computer code having at least one machine learning model; wherein the first processor executes computer code stored in the memory that causes the first processor to: automatically receive from the second processor, a first output signal intended to be received by a target recipient device, wherein the first output signal comprises at least one instruction to the target recipient device, the at least one instruction being configured to cause the target recipient device to perform at least one action; automatically input the first output signal into the at least one machine learning model; wherein the at least one machine learning model is configured to perform at least: determine that the first output signal comprises an error signal that would cause a malfunction of at least one function performed by the target recipient device; and (ii) output an instruction that is configured to cause the first processor to generate a second output signal that is a corrected version of the first output signal; automatically generate the second output signal; and automatically instructing, via the second output signal instead of the first output signal, the target recipient device to perform the at least one action so as to facilitate error-corrected communication between the signaling device and the target recipient device. ### Claim 2 (depends on 1) The apparatus according to claim 1, wherein the first substrate and the second substrate are each a printed circuit board. ### Claim 3 (depends on 1) The apparatus according to claim 1, wherein the first substrate and the second substrate are the same substrate. ### Claim 4 (depends on 1) The apparatus according to claim 1, wherein the memory is a read only memory. ### Claim 5 (depends on 1) The apparatus according to claim 1, further comprising a microcontroller coupled to the first substrate; wherein the microcontroller comprises the first processor, and wherein the first processor is configured to receive updates to the at least one machine learning model through a communication circuitry in the microcontroller over a communication network. ### Claim 6 (depends on 1) The apparatus according to claim 1, wherein the at least one machine learning model is a sequence-to-sequence model. ### Claim 7 (depends on 1) The apparatus according to claim 1, wherein the at least one machine learning model is a recurrent network model. ### Claim 8 (depends on 1) The apparatus according to claim 1, further comprising at least one sensor, and wherein the first processor is configured to receive at least one sensor output from the at least one sensor that is inputted to the at least one machine learning model. ### Claim 9 (depends on 8) The apparatus according to claim 8, wherein the first processor is configured to determine that the error signal causes the malfunction of the at least one function of the target recipient device by applying the at least one sensor output to the at least one machine learning model. ### Claim 10 (depends on 1) The apparatus according to claim 1, wherein the first processor is configured to correct the error signal when the at least one machine learning model determines that a probability that the error signal causes the malfunction exceeds a predefined confidence level. ### Claim 11 A method, comprising: automatically receiving, by a first processor coupled to a first substrate and operationally connected to a signaling device comprising a second processor coupled to a second substrate, a first output signal intended to be received by a target recipient device wherein the first output signal comprises at least one instruction to the target recipient device, the at least one instruction being configured to cause the target recipient device to perform at least one action; automatically inputting, by the first processor, the first output signal into at least one machine learning model; wherein the at least one machine learning model is configured to perform at least: determining that the first output signal comprises an error signal that would cause a malfunction of at least one function performed by the target recipient device; and (ii) output an instruction that is configured to cause the first processor to generate a second output signal that is a corrected version of the first output signal; automatically generating, by the first processor, the second output signal; and automatically instructing, by the first processor, via the second output signal instead of the first output signal, the target recipient device to perform the at least one action so as to facilitate error-corrected communication between the signaling device and the target recipient device. ### Claim 12 (depends on 11) The method according to claim 11, wherein the at least one machine learning model is a sequence-to-sequence model. ### Claim 13 (depends on 11) The method according to claim 11, wherein the at least one machine learning model is a recurrent network model. ### Claim 14 (depends on 11) The method according to claim 11, further comprising receiving, by the first processor, updates to the at least one machine learning model through a microcontroller over a communication network; wherein the microcontroller comprises the first processor and a communication circuitry operationally coupled to the communication network. ### Claim 15 (depends on 11) The method according to claim 11, further comprising receiving, by the first processor, at least one sensor output from at least one sensor that is inputted to the at least one machine learning model. ### Claim 16 (depends on 15) The method according to claim 15, wherein determining that the error signal causes the malfunction of the at least one function of the target recipient device comprises applying the at least one sensor output to the at least one machine learning model. ### Claim 17 (depends on 11) The method according to claim 11, wherein correcting the error signal in the first output signal comprises correcting the error signal from the first output signal when the at least one machine learning model determines that a probability that the error signal causes the malfunction exceeds a predefined confidence level. ### Claim 18 (depends on 11) The method according to claim 11, further comprising sending, by the first processor, over a communication network to a third-party server, a dataset comprising a plurality of error signals from the first output signal over a predefined time interval that causes the malfunction of the at least one function of the target recipient device for retraining the at least one machine learning model.