Software Workflow Recommendation via ML Command Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing software workflow recommendation tools are ineffective as they recommend individual commands that may not be applicable to users' specific tasks and fail to provide guidance on using familiar commands in unfamiliar ways, leading to inefficient task automation.

Innovation Solution

A computer-implemented method that uses a trained machine-learning model to classify commands and recommend workflows based on expected distributions of frequencies and task weights, providing recommendations that align with users' interests and offering guidance on using familiar commands in new ways.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If command-based recommendation tools recommend individual commands to users, then the quantity of recommended items increases, but the relevance to users' specific tasks decreases

Engineering Contradiction:

Improvequantity of recommended commandsVSAvoidrelevance to users' specific tasks

Core Design Contradiction:

Quantity of substanceVSLoss of information

Solution Approach 1:

The patent segments the set of commands into task-specific subsets using a machine learning model that identifies which commands are relevant to the user's current task. This segmentation allows the system to recommend only the necessary commands rather than all available commands, improving relevance while maintaining appropriate quantity.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Instead of recommending commands and hoping they apply to user tasks, the patent inverts the approach by first identifying the user's task context and then recommending only the commands relevant to that task. This inversion ensures relevance is maintained while the quantity of recommendations is optimized.

Inventive Principle:

Principle #13The other way round (Inversion)

2Adaptability or versatility

If users manually develop workflows based on their understanding of software commands, then the adaptability to user needs improves, but the productivity decreases

Engineering Contradiction:

Improveadaptability to user needsVSAvoidworkflow development efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent implements self-service by enabling the system to automatically generate workflows for users based on their task context and the recommended commands. The machine learning model analyzes user behavior patterns and automatically constructs workflow sequences, allowing the system to serve itself in creating personalized workflows without manual user effort.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary action by pre-analyzing user task contexts and pre-generating appropriate workflow recommendations before users need them. The machine learning model is trained on historical data to anticipate user needs and prepare workflow suggestions in advance, improving productivity while maintaining adaptability.

Inventive Principle:

Principle #10Preliminary action

3Stability of the object's composition

If users continue to use manual workflows despite software upgrades, then the stability of existing processes is maintained, but the productivity decreases

Engineering Contradiction:

Improvestability of existing workflowsVSAvoidtask execution efficiency

Core Design Contradiction:

Stability of the object's compositionVSProductivity

Solution Approach 1:

The patent implements feedback mechanisms that monitor user workflow usage patterns and provide recommendations for improved workflows based on software capabilities. The system continuously learns from user behavior and feedback, analyzing whether users are using manual or automated workflows, and provides targeted recommendations to transition to more efficient automated workflows while respecting user preferences.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system applies dynamics by making workflow recommendations adaptive and evolving over time. Rather than forcing a single workflow type, the system dynamically adjusts recommendations based on user behavior patterns, task complexity, and software version capabilities. This allows gradual transition from manual to automated workflows while maintaining stability in user-controlled areas.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS11823015B2Techniques for classifying and recommending software workflows

Publication Date: 2023.11.21 AUTODESK INC

AI summary

In various embodiments, a pattern-based recommendation subsystem automatically recommends workflows for software-based tasks. In operation, the pattern-based recommendation subsystem computes an expected distribution of frequencies across command patterns based on different distributions of frequencies across the command patterns. The expected distribution of frequencies is associated with a target user, and each different distribution of frequencies is associated with a different user. The pattern-based recommendation subsystem then applies a set of commands associated with the target user to a trained machine-learning model to determine a target distribution of weights applied to a set of tasks. Subsequently, the pattern-based recommendation subsystem determines a training item based on the expected distribution of frequencies and the target distribution of weights. The pattern-based recommendation subsystem generates a recommendation that specifies the training item. Finally, the pattern-based recommendation subsystem transmits the recommendation to a user to assist the user in performing a particular task.