Intuitive defect prevention with swarm learning intelligence over blockchain network
Aspects of the disclosure relate to a computing system that is configured to use heuristic and/or metaheuristic algorithms based on swarm learning (SL) intelligence frameworks and combine SL with blockchain and edge computing frameworks to provide a technologically efficient, responsive, and/or adaptable solution to detecting and preventing defects in software applications.
1 . A swarm learning (SL) computing system that analyzes cognitive response to application defects, the computing system comprising:
a swarm of boids comprising agents communicatively coupled on a communications network for peer-to-peer communication without requiring a centralized server;
a virtual reality (VR) simulation headset that collects cognitive responses of a user;
a blockchain comprising a plurality of blocks corresponding to a plurality of software application failure logs and defects data, wherein the plurality of software application failure logs indicate events associated with a plurality of software applications that failed, and wherein the defects data corresponds to what caused the plurality of software applications to fail; and
a particle swarm optimization (PSO) model that categorizes the defects as either a false positive defect or a true positive defect and to generate a defect prevention learning dataset to test one or more software applications,
wherein the VR simulation headset immersively displays step-by-step guidance for fixing the true positive defect, and
wherein the defect prevention learning dataset provides a feedback loop to an input of a machine learning model to iteratively generate output used in an evolving VR simulation via the VR simulation headset to prevent a future defect, and wherein the peer-to-peer communication provides interoperability between the defect prevention learning dataset and the blockchain.
2 . The SL computing system of claim 1 , wherein the step-by-step guidance for fixing the true positive defect is generated using the defect prevention learning dataset and includes simulations of the software applications with defects to collect insights into cognitive responses by the user when encountering software issues.
3 . The SL computing system of claim 1 , wherein the blockchain stores immutable records of at least defect lifecycle events comprising: detection, classification, assignment, and resolution, and wherein the swarm of boids uses pattern identification by learning from historical data from the blockchain.
4 . The SL computing system of claim 1 , wherein a first quality assurance (QA) agent of the swarm of boids is executing on a first edge node while a second QA agent is simultaneously executing on a second edge node that is not the first edge node, wherein the first edge node and the second edge node are communicatively coupled on the communication network.
5 . The SL computing system of claim 4 , wherein the first QA agent autonomously adheres to code scanning rules and interactions with other agents in the swarm of boids without the centralized server dictating which parts of the plurality of software applications to analyze by each QA agent.
6 . The SL computing system of claim 1 , wherein the swarm of boids self-organize into groups for optimal division of labor and adaptation.
7 . The SL computing system of claim 1 , wherein the PSO model receives, both asynchronously and non-sequentially, the plurality of software application failure logs and the defects data.
8 . The SL computing system of claim 1 , wherein the defect prevention learning dataset is stored in a memory of a first quality assurance (QA) agent and comprises embeddings for use with one or more machine learning models that provide the feedback loop.
9 . The SL computing system of claim 1 , wherein the PSO model comprises an ant colony optimization (ACO).
10 . The SL computing system of claim 1 , wherein the PSO model comprises a genetic algorithm (GA), and wherein parameters of the GA comprise crossover rate, mutation rate, and population size.
11 . A method for analyzing cognitive response to application defects using a plurality of nodes communicatively coupled to a peer-to-peer network, wherein the plurality of nodes correspond to a swarm of boids comprising agents, the method comprising:
(a) collecting, by a virtual reality (VR) simulation device, cognitive responses of a user;
(b) accessing a blockchain, which comprises a plurality of blocks corresponding to a plurality of software application failure logs indicating events associated with software application failures and defects data that caused the software application failures;
(c) categorizing, by a particle swarm optimization (PSO) model, the defects data as either a false positive defect or a true positive defect;
(d) generating, by the PSO model, a defect prevention learning dataset to test one or more software applications;
(e) displaying, by the VR simulation device, step-by-step guidance for fixing the true positive defect; and
(f) providing a feedback loop, using the defect prevention learning dataset, to an input of a machine learning model to iteratively generate output used in an evolving VR simulation via the VR simulation device to prevent a future defect,
wherein peer-to-peer communication provides interoperability between the defect prevention learning dataset and the blockchain.
12 . The method of claim 11 , wherein the VR simulation device comprises a VR simulation headset.
13 . The method of claim 11 , wherein the PSO model comprises an ant colony optimization (ACO).
14 . The method of claim 11 , wherein the PSO model comprises a genetic algorithm (GA).
15 . The method of claim 11 , wherein the swarm of boids self-organize into groups for optimal division of labor and adaptation.
16 . A non-transitory computer-readable medium storing instruction that, when executed by one or more computer processors, cause the one or more computer processors to perform a method comprising steps of:
(a) collecting, by a virtual reality (VR) simulation device, cognitive responses of a user;
(b) accessing a blockchain, which comprises a plurality of blocks corresponding to a plurality of software application failure logs indicating events associated with software application failures and defects data that caused the software application failures;
(c) categorizing, by a particle swarm optimization (PSO) model, the defects data as either a false positive defect or a true positive defect;
(d) generating, by the PSO model, a defect prevention learning dataset to test one or more software applications;
(e) displaying, by the VR simulation device, step-by-step guidance for fixing the true positive defect; and
(f) providing a feedback loop, using the defect prevention learning dataset, to an input of a machine learning model to iteratively generate output used in an evolving VR simulation via the VR simulation device to prevent a future defect,
wherein peer-to-peer communication provides interoperability between the defect prevention learning dataset and the blockchain.
17 . The non-transitory computer-readable medium of claim 16 , wherein the step-by-step guidance for fixing the true positive defect is generated using the defect prevention learning dataset and includes simulations of the software applications with defects to collect insights into cognitive responses by the user when encountering software issues.
18 . The non-transitory computer-readable medium of claim 16 , wherein the collecting of the cognitive response of the user comprises corresponding the cognitive response to user to a category type of the true positive defect.
19 . The non-transitory computer-readable medium of claim 16 , storing instruction further comprising:
(g) analyzing, using predictive algorithms, historical data in the blockchain to identify patterns leading to emergence of the true positive defects.
20 . The non-transitory computer-readable medium of claim 16 , wherein a swarm of boids uses pattern identification by learning from historical data from the blockchain.