# US 12,217,511 B1 · Real time management of detected issues > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,217,511 B1 - Document ID: US12217511B1 - Status: Granted - Kind: B1 - Application number: 18/739,260 - Filed: 2024-06-10 - Granted: 2025-02-04 - Earliest claimed: 2024-06-10 - Assignees: Autobrains Technologies Ltd - Applicants: Autobrains Technologies Ltd - Inventors: Igal Raichelgauz; Idan Geller; Lior Eldar - Web page: https://patentgrep.com/patent/US12217511B1 ## CPC - G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle - B60W 60/001: {Planning or execution of driving tasks} - G06N 3/045: Combinations of networks - G06N 3/0985: Hyperparameter optimisation; Meta-learning; Learning-to-learn - G06V 10/764: using classification, e.g. of video objects - G06V 10/82: using neural networks - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A method for real time management of detected issues, the method includes producing, by a classification unit having a neural network, a classification decision for sensed information obtained in an environment of a vehicle; generating, by one or more computing devices with auto-labeling capabilities, an automated ground truth labeling for the sensed information; detecting, by the one or more computing devices and based on a performance indication related to the automated ground truth labeling, an issue with respect to the classification decision; and responsive to the detecting, addressing the detected issue in a driving in the environment of the vehicle by a computer device associated with the vehicle, using a signature generated in association with at least the classification decision or with the detected issue. The neural network is in a same state in the producing of the classification decision, the detecting the issue, and the addressing the detected issue. ## Claims ### Claim 1 A method for real time management of detected issues, the method comprising: producing, by a classification unit having a neural network, a classification decision for sensed information obtained in an environment of a vehicle; generating, by one or more computing devices with auto-labeling capabilities, an automated ground truth labeling for the sensed information; detecting, by the one or more computing devices and based on a performance indication related to the automated ground truth labeling, an issue with respect to the classification decision; and responsive to the detecting, addressing the detected issue in a driving in the environment of the vehicle by a computer device associated with the vehicle, using a signature generated in association with at least the classification decision or with the detected issue; wherein the neural network is in a same state in the producing of the classification decision, the detecting the issue, and the addressing the detected issue. ### Claim 2 (depends on 1) The method according to claim 1, wherein the signature is generated in association with the classification decision and the addressing of the detected issue comprise flagging the signature as being associated with a classification error. ### Claim 3 (depends on 1) The method according to claim 1, further comprising determining to ignore the detected issue. ### Claim 4 (depends on 1) The method according to claim 1, comprising addressing the detected issue when the detected issue resulted in an unnecessary movement of the vehicle. ### Claim 5 (depends on 1) The method according to claim 1, further comprising generating, by the one or more computing devices, a key performance indicator (KPI) report. ### Claim 6 (depends on 1) The method according to claim 1, further comprising analyzing detected issues over a period of time and marking the detected issues for further downstream analysis. ### Claim 7 (depends on 1) The method according to claim 1, wherein the addressing the detected issue involves addressing other detected issues that are classifiably similar to the detected issue, using the signature. ### Claim 8 (depends on 1) The method according to claim 1, wherein the addressing the detected issue involves addressing other detected issues that are classifiably similar to the detected issue, using the signature. ### Claim 9 (depends on 1) The method according to claim 1, wherein the addressing of the detected issue involves addressing other classification decisions that are classifiably similar to the classification decision, using the signature. ### Claim 10 (depends on 1) The method according to claim 1, wherein the neural network of the classification unit, another neural network of the one or more computing devices with auto-labeling capabilities are trained with a same training dataset. ### Claim 11 (depends on 1) The method according to claim 1, further comprising generating the signature for the detected issue using a further neural network that is trained with a same training dataset as the neural network of the classification unit. ### Claim 12 A non-transitory computer readable medium for real time management of detected issues, the non-transitory computer readable medium that stores instructions for: producing, by a classification unit having a neural network, a classification decision for sensed information obtained in an environment of a vehicle; automatically generating, by one or more computing devices with auto-labeling capabilities, an automated ground truth labeling for the sensed information; detecting, by the one or more computing devices and based on a performance indication related to the automated ground truth labeling, an issue with respect to the classification detection; and responsive to the detecting, addressing the detected issue in a driving in the environment of the vehicle by a computer device associated with the vehicle, using a signature generated in association with at least the classification decision or with the detected issue; wherein the neural network is in a same state in the producing of the classification decision, the detecting the issue, and the addressing the detected issue. ### Claim 13 (depends on 12) The non-transitory computer readable medium according to claim 12, wherein the signature is generated in association with the classification decision and the addressing of the detected issue comprise flagging the signature as being associated with a classification error. ### Claim 14 (depends on 12) The non-transitory computer readable medium according to claim 12, that stores instructions for generating, by the one or more computing devices, a key performance indicator (KPI) report. ### Claim 15 (depends on 12) The non-transitory computer readable medium according to claim 12, that stores instructions for analyzing detected issues over a period of time and marking the detected issues for further downstream analysis. ### Claim 16 (depends on 12) The non-transitory computer readable medium according to claim 12, wherein the addressing the detected issue involves addressing other detected issues that are classifiably similar to the detected issue, using the signature. ### Claim 17 A method for real time management of detected issues, the method comprising: automatically generating, by one or more computing devices with auto-labeling capabilities, an automated ground truth labeling for sensed information obtained in an environment of a vehicle; detecting, by the one or more computing devices and based on a performance indication related to the automated ground truth labeling, an issue with respect to a classification detection made for the sensed information using a neural network in a specified state; and responsive to the detecting, addressing the detected issue in a driving in the environment of the vehicle by a computer device associated with the vehicle, using a signature generated in association with at least the classification decision or with the detected issue; wherein the neural network in the specified state in the detecting of the issue. ### Claim 18 (depends on 17) The method according to claim 17, wherein the signature is generated in association with the classification decision and the addressing of the detected issue comprise flagging the signature as being associated with a classification error. ### Claim 19 (depends on 17) The method according to claim 17, further comprising determining to ignore the detected issue. ### Claim 20 (depends on 17) The method according to claim 17, comprising addressing the detected issue when the detected issue resulted in an unnecessary movement of the vehicle. ### Claim 21 (depends on 17) The method according to claim 17, further comprising generating, by the one or more computing devices, a key performance indicator (KPI) report. ### Claim 22 (depends on 17) The method according to claim 17, further comprising analyzing detected issues over a period of time and marking the detected issues for further downstream analysis. ### Claim 23 A non-transitory computer readable medium for real time management of detected issues, the non-transitory computer readable medium that stores instructions for: automatically generating, by one or more computing devices with auto-labeling capabilities, an automated ground truth labeling for sensed information obtained in an environment of a vehicle; detecting, by the one or more computing devices and based on a performance indication related to the automated ground truth labeling, an issue with respect to a classification detection made for the sensed information using a neural network in a specified state; and responsive to the detecting, addressing the detected issue in a driving in the environment of the vehicle by a computer device associated with the vehicle, using a signature generated in association with at least the classification decision or with the detected issue; wherein the neural network in the specified state in the detecting of the issue; wherein the neural network is in a same state in the producing of the classification decision, the detecting the issue, and the addressing the detected issue. ### Claim 24 (depends on 23) The non-transitory computer readable medium according to claim 23, wherein the signature is generated in association with the classification decision and the addressing of the detected issue comprise flagging the signature as being associated with a classification error. ### Claim 25 (depends on 23) The non-transitory computer readable medium according to claim 23, further storing instructions for determining to ignore the detected issue. ### Claim 26 (depends on 23) The non-transitory computer readable medium according to claim 23, further storing instructions for addressing the detected issue when the detected issue resulted in an unnecessary movement of the vehicle. ### Claim 27 (depends on 23) The non-transitory computer readable medium according to claim 23, further storing instructions for generating, by the one or more computing devices, a key performance indicator (KPI) report. ### Claim 28 (depends on 23) The non-transitory computer readable medium according to claim 23, further storing instructions for analyzing detected issues over a period of time and marking the detected issues for further downstream analysis.