Machine Cognition Workflow Engine With Feedback-Based Recommendations

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional online chatbots lack a feedback mechanism to learn from user interactions, leading to a static user experience and inability to adapt strategies based on past experiences, limiting their ability to refine task fulfillment and provide personalized responses.

Innovation Solution

A machine cognition workflow engine that generates workflow instances based on user prompts, evaluates responses, and recommends optimized workflow definitions using a scoring model or generative model to enhance adaptability and personalization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional chatbots use predefined algorithms to fulfill tasks, then they can operate with simple structure, but they cannot learn from past interactions and adapt strategies

Engineering Contradiction:

Improveability to learn from past interactionsVSAvoidsystem structure complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements a feedback mechanism where chatbot interactions are stored in a database, evaluated by a scoring model that assigns quality scores, and used to train a workflow recommendation model. This closed-loop feedback system enables the chatbot to learn from past interactions and continuously improve its performance without requiring complex manual reprogramming.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system employs self-service through automated evaluation and recommendation components that automatically analyze interaction quality, generate workflow recommendations, and update the system without human intervention. The chatbot autonomously learns from its own performance data, reducing the need for manual system configuration and maintenance.

Inventive Principle:

Principle #25Self-service

2Measurement precision

If conventional chatbots treat each interaction in isolation, then they maintain simple processing logic, but they cannot develop nuanced understanding of user preferences

Engineering Contradiction:

Improveunderstanding of user preferencesVSAvoidtime for learning and adaptation

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary action by pre-processing and storing interaction data in a structured database format, pre-evaluating responses with scoring models, and pre-generating workflow recommendations before they are needed. This preparation work enables rapid, personalized responses when actual user interactions occur, without sacrificing understanding precision.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements dynamics by making the chatbot's behavior adaptive rather than static. The workflow recommendation model dynamically adjusts its suggestions based on learned patterns from historical data, allowing the system to evolve its understanding of user preferences over time while maintaining efficient real-time performance.

Inventive Principle:

Principle #15Dynamics

3Adaptability or versatility

If conventional chatbots lack feedback mechanisms, then they maintain simple operational flow, but they cannot evolve or adapt based on new experiences

Engineering Contradiction:

Improveability to evolve and adaptVSAvoidfeedback system complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system introduces intermediary components including a database that mediates between interactions and learning, a scoring model that mediates between responses and evaluation, and a workflow recommendation model that mediates between historical data and future actions. These intermediaries structure the feedback flow to enable adaptation without overwhelming system complexity.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20250224980A1Machine cognition workflow engine

Publication Date: 2025.07.10 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

A machine cognition workflow engine and a recommendation subsystem are provided in a computing system. The workflow engine receives a plurality of prompts, extracts a message and a context of each of the plurality of prompts, for each prompt, generates a workflow instance according to a recommended workflow definition that specifies a plurality of calls to one or more components, and for each prompt, executes the generated workflow instance to perform the calls to the one or more components to thereby generate responses for the plurality of prompts. The recommendation subsystem evaluates the responses to generate a score for each response generated by the workflow instances, receives a request from the machine cognition workflow engine for the recommended workflow definition for a current prompt, and outputs the recommended workflow definition to the machine cognition workflow engine based on the scores of responses generated by the workflow instances.