Neural Network Cloud Service Recommendation System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud computing service designers face challenges in selecting the best computing services from a large number of available options to create custom cloud computing solutions, as the variety of services can be overwhelming and time-consuming without prior knowledge of specific functionalities.
Innovation Solution
A method using a neural network system that receives user descriptions of computing service functionalities, converts them into embedded vectors, and applies supervised learning to recommend suitable computing services and their arrangements, leveraging recurrent neural networks and softmax activation functions to determine service probabilities and connections.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a designer selects from a large number of available cloud computing services to create a custom solution, then the variety and functionality of the solution is improved, but the time and complexity required to design the solution increases
Solution Approach 1:
The system enables self-service by automatically generating computing service recommendations and architecture diagrams based on functional requirements. The neural network model processes user descriptions and autonomously selects appropriate services, eliminating the need for manual selection from hundreds of options and significantly reducing design time while maintaining functionality variety.
Solution Approach 2:
The patent introduces an intermediary system consisting of a neural network model and processing system that mediates between the user's functional requirements and the available cloud services. This intermediary automatically translates high-level descriptions into specific service recommendations and architectural configurations, reducing the cognitive load and time required for designers.
2Ease of operation
If a designer manually selects computing services without prior knowledge, then the ease of operation is improved, but the accuracy and quality of service selection deteriorates
Solution Approach 1:
The system performs self-service by automatically analyzing functional requirements and generating accurate service recommendations. The neural network model processes user descriptions and autonomously determines the most appropriate computing services, maintaining high selection accuracy while requiring minimal user expertise or manual intervention.
Solution Approach 2:
The patent implements feedback mechanisms where the system learns from user interactions and refines its recommendations. The processing system can incorporate feedback about service performance and user preferences to improve the accuracy of future recommendations, ensuring that service selection becomes both easier and more accurate over time.
3Adaptability or versatility
If a designer creates custom cloud computing solutions from scratch, then the adaptability to specific requirements is improved, but the complexity of the design process increases
Solution Approach 1:
The patent applies segmentation by breaking down the complex design process into discrete components: functional requirement analysis, service recommendation generation, architecture diagram creation, and configuration assembly. This segmentation reduces overall complexity by handling each aspect separately through automated processes while maintaining the ability to customize solutions to specific requirements.
Solution Approach 2:
The neural network processing system acts as an intermediary that simplifies the design process complexity. It automatically translates high-level functional requirements into detailed service configurations and architecture diagrams, reducing the cognitive complexity for designers while preserving full customization capability for specific requirements.
Data Source
AI summary
A computing system module facilitates designing a cloud computing services application that comprises multiple disparate cloud computing services available from multiple sources, vendors, or platforms. A description, in textual or verbal form, of desired functionality of the application is converted into a context vector. A trained supervised learning model having a number of nodes corresponding to a number of available computing services, analyzes the context vector and determines a relative probability for each node with respect to probability thresholds. The learning model identifies in a recommendation report that the application should include a service if a probability corresponding to the service satisfies a respective criterion. Edges may be determined from the context vector and analyzed by the learning model to determine an architecture of recommended services. The architecture may be rendered as a visual diagram based on the edges. Information from actual use may update training of the learning model.