# US 2023/0054912 A1 · Asset Error Remediation for Continuous Operations in a Heterogeneous Distributed Computing Environment > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2023/0054912 A1 - Document ID: US20230054912A1 - Status: Published application - Kind: A1 - Application number: 17/445,206 - Filed: 2021-08-17 - Published: 2023-02-23 - Earliest claimed: 2021-08-17 - Assignees: Kyndryl, Inc. - Applicants: Kyndryl, Inc. - Inventors: Prasanna Kumar Dixit J; Sharat K. Tripathy; Mohammed Amjed Ali - Web page: https://patentgrep.com/patent/US20230054912A1 ## CPC - H04L 41/0654: using network fault recovery (ring fault isolation or reconfiguration in loop networks without recovery actions by a network management system H04L12/437) - G06F 40/30: Semantic analysis - G06V 30/153: {using recognition of characters or words} - G06V 30/16: Image preprocessing - G06V 30/18: Extraction of features or characteristics of the image - G06V 30/19: Recognition using electronic means - H04L 67/10: in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46) - H04L 41/0677: Localisation of faults - H04L 41/16: using machine learning or artificial intelligence - H04L 41/22: comprising specially adapted graphical user interfaces [GUI] - H04L 41/5019: Ensuring fulfilment of SLA - H04L 43/0817: by checking functioning - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Asset error remediation is provided. Risk and classification of an asset error are analyzed to prioritize asset error remediation for an asset based on risk criticality, risk context, and vulnerability level corresponding to the asset by detecting suspicious behavior and risk exposure to the asset in a heterogeneous distributed computing environment using artificial intelligence. A priority of the asset error remediation is determined to fix the asset within the heterogeneous distributed computing environment based on the risk and the classification of the asset error. A set of action steps is performed to fix the asset within the heterogeneous distributed computing environment based on the priority of the asset error remediation. ## Claims ### Claim 1 A computer-implemented method for asset error remediation, the computer-implemented method comprising: analyzing, by a computer, risk and classification of an asset error to prioritize asset error remediation for an asset based on risk criticality, risk context, and vulnerability level corresponding to the asset by detecting suspicious behavior and risk exposure to the asset in a heterogeneous distributed computing environment using artificial intelligence; determining, by the computer, a priority of the asset error remediation to fix the asset within the heterogeneous distributed computing environment based on the risk and the classification of the asset error; and performing, by the computer, a set of action steps to fix the asset within the heterogeneous distributed computing environment based on the priority of the asset error remediation. ### Claim 2 (depends on 1) The computer-implemented method of claim 1 further comprising: performing, by the computer, an asset availability analysis during the risk exposure to the asset to demonstrate security governance and regulatory compliance of the heterogeneous distributed computing environment. ### Claim 3 (depends on 1) The computer-implemented method of claim 1 further comprising: discovering, by the computer, assets across the heterogeneous distributed computing environment automatically, wherein the assets include edge devices connected to the heterogeneous distributed computing environment that change in number and type over time; and assessing, by the computer, operational health of each respective asset in the heterogeneous distributed computing environment continuously to manage security governance and regulatory compliance of the heterogeneous distributed computing environment to decrease risk exposure by monitoring for indications of asset errors. ### Claim 4 (depends on 1) The computer-implemented method of claim 1 further comprising: receiving, by the computer, an image of an error message corresponding to the asset; analyzing, by the computer, the image of the error message using computer vision; segmenting, by the computer, the image of the error message to identify a relevant text portion corresponding to the asset error; extracting, by the computer, the relevant text portion corresponding to the asset error from the image; performing, by the computer, text classification of the relevant text portion corresponding to the asset error extracted from the image using natural language processing; and mapping, by the computer, the relevant text portion corresponding to the asset error to a nearest predefined error description. ### Claim 5 (depends on 1) The computer-implemented method of claim 1 further comprising: receiving, by the computer, a description of the asset error from a user in a free text format; processing, by the computer, the description of the asset error in the free text format using natural language processing; calculating, by the computer, a similarity score between each predefined reason for error and the description of the asset error; and identifying, by the computer, a nearest predefined reason for error neighbor based on a particular predefined reason for error having a highest similarity score. ### Claim 6 (depends on 1) The computer-implemented method of claim 1 further comprising: selecting, by the computer, a set of predefined key phrases corresponding to a description of the asset error; performing, by the computer, similarity scoring between the description of the asset error and each of the set of predefined key phrases; generating, by the computer, an error characteristic matrix for the asset error based on similarity scores of the set of predefined key phrases; and generating, by the computer, a set of predefined fix recommendation procedures based on information contained in the error characteristic matrix. ### Claim 7 (depends on 6) The computer-implemented method of claim 6 further comprising: calculating, by the computer, a similarity score between each respective predefined key phrase in the set of predefined key phrases and each respective fix in the set of predefined fix recommendation procedures; identifying, by the computer, a fix having a highest similarity score; and using, by the computer, the fix having the highest similarity score to correct the asset error. ### Claim 8 (depends on 1) The computer-implemented method of claim 1 further comprising: retrieving, by the computer, a reference asset image and a defective asset image corresponding to the asset using an identifier of the asset; performing, by the computer, differencing between the reference asset image and the defective asset image using computer vision; performing, by the computer, contour tracing of the reference asset image and the defective asset image; performing, by the computer, localization of the asset error in the defective asset image based on the differencing and the contour tracing; and identifying, by the computer, a localized defect in the asset in the defective asset image based on the localization. ### Claim 9 (depends on 1) The computer-implemented method of claim 1, wherein the heterogeneous distributed computing environment is a multi-cloud environment comprised of a plurality of clouds corresponding to different cloud providers and a plurality of edge devices. ### Claim 10 A computer system for asset error remediation, the computer system comprising: a bus system; a storage device connected to the bus system, wherein the storage device stores program instructions; and a processor connected to the bus system, wherein the processor executes the program instructions to: analyze risk and classification of an asset error to prioritize asset error remediation for an asset based on risk criticality, risk context, and vulnerability level corresponding to the asset by detecting suspicious behavior and risk exposure to the asset in a heterogeneous distributed computing environment using artificial intelligence; determine a priority of the asset error remediation to fix the asset within the heterogeneous distributed computing environment based on the risk and the classification of the asset error; and perform a set of action steps to fix the asset within the heterogeneous distributed computing environment based on the priority of the asset error remediation. ### Claim 11 (depends on 10) The computer system of claim 10, wherein the processor further executes the program instructions to: perform an asset availability analysis during the risk exposure to the asset to demonstrate security governance and regulatory compliance of the heterogeneous distributed computing environment. ### Claim 12 (depends on 10) The computer system of claim 10, wherein the processor further executes the program instructions to: discover assets across the heterogeneous distributed computing environment automatically, wherein the assets include edge devices connected to the heterogeneous distributed computing environment that change in number and type over time; and assess operational health of each respective asset in the heterogeneous distributed computing environment continuously to manage security governance and regulatory compliance of the heterogeneous distributed computing environment to decrease risk exposure by monitoring for indications of asset errors. ### Claim 13 A computer program product for asset error remediation, the computer program product comprising a computer-readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method of: analyzing, by the computer, risk and classification of an asset error to prioritize asset error remediation for an asset based on risk criticality, risk context, and vulnerability level corresponding to the asset by detecting suspicious behavior and risk exposure to the asset in a heterogeneous distributed computing environment using artificial intelligence; determining, by the computer, a priority of the asset error remediation to fix the asset within the heterogeneous distributed computing environment based on the risk and the classification of the asset error; and performing, by the computer, a set of action steps to fix the asset within the heterogeneous distributed computing environment based on the priority of the asset error remediation. ### Claim 14 (depends on 13) The computer program product of claim 13 further comprising: performing, by the computer, an asset availability analysis during the risk exposure to the asset to demonstrate security governance and regulatory compliance of the heterogeneous distributed computing environment. ### Claim 15 (depends on 13) The computer program product of claim 13 further comprising: discovering, by the computer, assets across the heterogeneous distributed computing environment automatically, wherein the assets include edge devices connected to the heterogeneous distributed computing environment that change in number and type over time; and assessing, by the computer, operational health of each respective asset in the heterogeneous distributed computing environment continuously to manage security governance and regulatory compliance of the heterogeneous distributed computing environment to decrease risk exposure by monitoring for indications of asset errors. ### Claim 16 (depends on 13) The computer program product of claim 13 further comprising: receiving, by the computer, an image of an error message corresponding to the asset; analyzing, by the computer, the image of the error message using computer vision; segmenting, by the computer, the image of the error message to identify a relevant text portion corresponding to the asset error; extracting, by the computer, the relevant text portion corresponding to the asset error from the image; performing, by the computer, text classification of the relevant text portion corresponding to the asset error extracted from the image using natural language processing; and mapping, by the computer, the relevant text portion corresponding to the asset error to a nearest predefined error description. ### Claim 17 (depends on 13) The computer program product of claim 13 further comprising: receiving, by the computer, a description of the asset error from a user in a free text format; processing, by the computer, the description of the asset error in the free text format using natural language processing; calculating, by the computer, a similarity score between each predefined reason for error and the description of the asset error; and identifying, by the computer, a nearest predefined reason for error neighbor based on a particular predefined reason for error having a highest similarity score. ### Claim 18 (depends on 13) The computer program product of claim 13 further comprising: selecting, by the computer, a set of predefined key phrases corresponding to a description of the asset error; performing, by the computer, similarity scoring between the description of the asset error and each of the set of predefined key phrases; generating, by the computer, an error characteristic matrix for the asset error based on similarity scores of the set of predefined key phrases; and generating, by the computer, a set of predefined fix recommendation procedures based on information contained in the error characteristic matrix. ### Claim 19 (depends on 18) The computer program product of claim 18 further comprising: calculating, by the computer, a similarity score between each respective predefined key phrase in the set of predefined key phrases and each respective fix in the set of predefined fix recommendation procedures; identifying, by the computer, a fix having a highest similarity score; and using, by the computer, the fix having the highest similarity score to correct the asset error. ### Claim 20 (depends on 13) The computer program product of claim 13 further comprising: retrieving, by the computer, a reference asset image and a defective asset image corresponding to the asset using an identifier of the asset; performing, by the computer, differencing between the reference asset image and the defective asset image using computer vision; performing, by the computer, contour tracing of the reference asset image and the defective asset image; performing, by the computer, localization of the asset error in the defective asset image based on the differencing and the contour tracing; and identifying, by the computer, a localized defect in the asset in the defective asset image based on the localization.