Predictive self-healing system for computer architectures

Patent metadata

Field	Value
Publication number	US-2026023643-A1
Application number	US-202418779789-A
Country	US
Kind code	A1
Filing date	Jul 22, 2024
Priority date	Jul 22, 2024
Publication date	Jan 22, 2026
Grant date	—

Abstract

Aspects discussed herein may relate to methods and techniques for using a multi-step approach to automatically analyze the computer architecture to determine the possible points of failure. A first stage may process, such as by using machine learning, one or more architecture diagrams the system architecture using hardware and/or software. The first stage may create a data graph that summarizes the network architecture and its relationships. A second stage may take the data graph and process it to determine likely points of failure and/or areas where redundancy may be needed. The system may then determine remedial steps to take in the case of failure

First claim

What is claimed is:

1 . A method comprising:
receiving one or more images depicting a computer architecture comprising one or more components; determining, by a first machine learning model performing spatial analysis of the one or more images, a mapping of metadata to the one or more components, wherein the first machine learning model is trained to output the mapping based on historical component descriptions; constructing, based on the mapping, an ordered graph indicating one or more relationships between the one or more components, wherein the ordered graph comprises the mapped metadata; determining, by a second machine learning model performing structural analysis on the ordered graph, one or more failure points associated with the one or more components; and presenting, using a display, a user interface depicting the one or more failure points.

2 . The method of claim 1 , wherein the one or more components comprise one or more of:
hardware components, or software components.

3 . The method of claim 1 , further comprising training the first machine learning model based on the historical component descriptions, wherein the historical component descriptions comprise:
domain-specific language associated with the computer architecture; and labeled images of diagram components.

4 . The method of claim 1 , further comprising training the second machine learning model based on historical data associated with real-world failures.

5 . The method of claim 1 , further comprising de-noising the one or more images prior to the determining the mapping.

6 . The method of claim 1 , wherein the ordered graph is formatted according to JavaScript Object Notation (JSON).

7 . The method of claim 1 , further comprising:
determining, based on the one or more failure points, one or more remedial actions for the computer architecture; and performing, based on detecting a failure of a subset of the one or more components, the one or more remedial actions.

8 . A system comprising:
a computing device; a first machine learning model; and a second machine learning model; wherein the computing device is configured to:
receive one or more images depicting a computer architecture comprising one or more components;
receive, from the first machine learning model, a mapping of metadata to the one or more components;
construct, based on the mapping, an ordered graph indicating one or more relationships between the one or more components, wherein the ordered graph comprises the metadata;
receive, from the second machine learning model, one or more failure points associated with the computer architecture; and
present, using a display, a user interface depicting the one or more failure points;
wherein the first machine learning model is configured to determine the mapping by performing spatial analysis of the one or more images; and wherein the second machine learning model is configured to determine the one or more failure points by performing structural analysis on the ordered graph.

9 . The system of claim 8 , wherein the one or more components comprise one or more of:
hardware components, or software components.

10 . The system of claim 8 , wherein the first machine learning model is trained based on:
domain-specific language associated with the computer architecture; and labeled images of diagram components.

11 . The system of claim 8 , wherein the second machine learning model is trained based on historical data associated with real-world failures.

12 . The system of claim 8 , wherein the computing device is further configured to:
de-noise the one or more images; and prior to receiving the mapping, send the de-noised one or more images to the first machine learning model, wherein the first machine learning model is configured to perform the determining the mapping by performing the spatial analysis of the de-noised one or more images.

13 . The system of claim 8 , wherein the ordered graph is formatted according to JavaScript Object Notation (JSON).

14 . The system of claim 8 , wherein the computing device is further configured to:
determine, based on the one or more failure points, one or more remedial actions for the computer architecture; and perform, based on detecting a failure of a subset of the one or more components, the one or more remedial actions.

15 . A non-transitory computer-readable medium storing computer instructions that, when executed by one or more processors, cause performance of actions comprising:
receiving one or more images depicting a computer architecture comprising one or more components; determining, by a first machine learning model performing spatial analysis of the one or more images, a mapping of metadata to the one or more components; constructing, based on the mapping, an ordered graph indicating one or more relationships between the one or more components, wherein the ordered graph comprises the metadata; determining, by a second machine learning model performing structural analysis on the ordered graph, one or more failure points associated with the one or more components; determining, based on the one or more failure points, one or more remedial actions for the computer architecture; and performing, based on detecting a failure of a subset of the one or more components, the one or more remedial actions.

16 . The non-transitory computer-readable medium storing computer instructions of claim 15 , wherein the one or more components comprise one or more of:
hardware components, or software components.

17 . The non-transitory computer-readable medium storing computer instructions of claim 15 , when executed by the one or more processors, further cause performance of actions comprising:
training the first machine learning model based on one or more of:
domain-specific language associated with the computer architecture, or labeled images of diagram components; and
training the second machine learning model based on historical data associated with real-world failures.

18 . The non-transitory computer-readable medium storing computer instructions of claim 15 , when executed by the one or more processors, further cause performance of actions comprising de-noising the one or more images prior to the determining the mapping.

19 . The non-transitory computer-readable medium storing computer instructions of claim 15 , wherein the ordered graph is formatted according to JavaScript Object Notation (JSON).

20 . The non-transitory computer-readable medium storing computer instructions of claim 15 , when executed by the one or more processors, further cause performance of actions comprising:
determining, based on the one or more failure points, one or more remedial actions for the computer architecture; and performing, based on detecting a failure of a subset of the one or more components, the one or more remedial actions.

Assignees

• Capital One Services Llc

Inventors

• Ciramdas Vamshi Krishna
• Chikkaveerappa Satish
• Gaynor Kevin
• Russo Matthew Attilio

Classifications

• G06F16/9024 Primary

  Graphs; Linked lists (G06F16/9027 takes precedence) · CPC title

• G06F11/079

  Root cause analysis, i.e. error or fault diagnosis (in a hardware test environment G06F11/22; in a software test environment G06F11/36) · CPC title

• G06F11/0709

  in a distributed system consisting of a plurality of standalone computer nodes, e.g. clusters, client-server systems · CPC title

• G06F11/0793 Primary

  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) · CPC title

• G06F11/0751

  Error or fault detection not based on redundancy (power supply failures G06F1/30; network fault management H04L41/06) · CPC title