Browse Prior Art Database

System and Process for Identifying Building Blocks Service based on Machine Learning

IP.com Disclosure Number: IPCOM000248186D
Publication Date: 2016-Nov-04
Document File: 3 page(s) / 81K

Publishing Venue

The IP.com Prior Art Database

Abstract

Disclosed are a system and method for the automated creation of targeted solutions based on customer requirements.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 51% of the total text.

Page 01 of 3

System and Process for Identifying Building Blocks Service based on Machine Learning

Generic solution construction templates allow the automatic creation and deployment of customized application solutions based on specific customer requirements. However, due to the number of services and components available, the number of combinations possible is large. Manually creating a solution by piecing together services into a new template can be time consuming and can lead to the creation of redundant templates.

Automatically selecting and creating all possible combinations is computationally

expensive and can produce a large number of solutions, many of which may be unnecessary. In short, different components of solutions are often re-created for customer solutions because providers are unaware of existing components ahead of time.

Solutions providers need automated tools as a means for suggesting new solutions and identifying areas of business need and insufficient support.

The novel contribution is a system and method for the automated creation of targeted solutions based on customer requirements. This approach first transforms existing customer requirements and templates into a machine-readable format. The approach then applies machine learning methods (e.g., hierarchical clustering) to create a mapping between templates and solutions. The solution creates an ontology of services, solutions, and sub-components with the semantics of the service and associated dependencies.

When an organization receives a new customer requirement, the system translates those requirements into a machine-readable format and then inputs the translated requirements into a trained machine learning model. The model iteratively provides feedback to the customer based on the customer's specifications. Specifically, the approach is to first identify the specific requirements the organization is able to meet or those requirements for which similar solutions are available to the customer. In addition, the method identifies any requirements that the customer might have not realized were needed. Finally, by analyzing the model itself, the method identifies any areas for which there is a demand, but a lack of viable solutions.

At a high level, the process follows:

1. Business requirements gap analysis, suggestions of additional business requirement to produce recursive identification of better matching building blocks

2. Segregation of the business requirements that have not been covered by the building blocks identified in #1; then the solutions provider can provide suggestions

3. Gap analysis for existing building blocks capabilities driven from unmatched business requirements, leads to an enhance building block

4. Creation of services and sub-components ontology with the semantics of the service and their dependency

Figure: Overall Idea

1


Page 02 of 3

The automated tool comprises three distinct phases, as f...