ML Bot Integration Using Compatibility Matrix and Classifier
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods struggle to integrate bots performing dissimilar tasks, such as in a procurement process, without affecting overall performance, and require significant time to develop new solutions or revise existing ones to meet changing requirements.
Innovation Solution
A Machine Learning (ML) based integration method and system that uses a trained classifier to compute end-user and technical compatibility values for bots, updating a dynamic compatibility matrix, and creating a bot package by integrating bots based on these values, allowing for the combination of similar or dissimilar bots through a Graphical User Interface (GUI).
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If conventional methods are used to integrate bots performing dissimilar tasks, then integration complexity increases, but integration success rate decreases
Solution Approach 1:
The patent introduces an intermediary system comprising a compatibility matrix and trained classifier that mediates between dissimilar bots. This intermediary evaluates end-user compatibility and technical compatibility, bridging the gap between bots performing different tasks and enabling successful integration without direct complex pairing.
Solution Approach 2:
The patent transforms the integration problem by changing parameters from direct bot-to-bot compatibility assessment to a structured evaluation using compatibility scores and matrices. The system computes end-user bot compatibility values and technical compatibility values based on multiple parameters, converting an unstructured complex problem into a parameterized decision-making process.
2Adaptability or versatility
If new solutions are developed to meet changing requirements, then adaptability improves, but development time increases
Solution Approach 1:
The patent implements preliminary action by pre-training classifiers on bot feature data and pre-computing compatibility matrices before actual integration needs arise. When requirements change, the system can quickly evaluate new bot combinations using pre-established compatibility frameworks, avoiding time-consuming development while maintaining adaptability.
Solution Approach 2:
The patent creates a universal integration framework that can handle multiple bot types and tasks through a single compatibility evaluation system. The trained classifier and compatibility matrix approach provides multi-functional capability to assess end-user compatibility and technical compatibility across diverse bot combinations, eliminating the need for task-specific integration development.
3Adaptability or versatility
If existing solutions are revised to meet new requirements, then adaptability improves, but revision time increases
Solution Approach 1:
The patent implements dynamics by creating a flexible compatibility matrix that can be dynamically updated and queried for different bot combinations. The system adapts to new requirements by evaluating existing bots against new compatibility criteria without requiring revision of the underlying bot functionalities, enabling rapid adaptation through reconfiguration rather than revision.
Data Source
AI summary
Developing a new solution or revising an existing solution to meet organizational requirements is often time consuming. One solution to overcome the above problem is to integrate existing solution providers like bots without affecting the overall performance. Conventional methods integrate bots performing similar operations. To overcome the challenges in the conventional approaches, the present disclosure provides a method and system for Machine learning (ML) based integration of bots. The present disclosure integrates a plurality of dissimilar bots using ML approach. Further, the present disclosure enables an end-user to combine two or more similar or dissimilar bots using an interface. The end-user/user can create, combine, validate and test the combined dissimilar bots without any prior knowledge of programming. Furthermore, the present disclosure auto-recommends the end-user regarding which bots can be combined with the selected bots by checking the technical and end-user feasibility.