Machine-Learned Document Linking Reduces User Interactions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current computing systems require cumbersome processes for users to link external documents within documents being edited, involving highlighting text, selecting links, and navigating file systems, which increases user interaction and reduces efficiency.
Innovation Solution
A computing system that uses machine-learned models to predict and suggest candidate documents for linking by analyzing the textual context and context associated with the edited document, allowing users to select from suggested links directly, thereby reducing the number of interactions needed to add links.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional manual hyperlinking process is used, then users have full control over link creation, but the number of user interactions increases and efficiency decreases
Solution Approach 1:
The system performs preliminary actions by automatically identifying candidate anchor texts and suggesting relevant target documents before the user completes the hyperlinking process. The machine learning model pre-processes the content to generate link suggestions, reducing the user's workload during the actual linking operation.
Solution Approach 2:
The system enables self-service by allowing the machine learning model to autonomously identify potential hyperlinks and suggest target documents based on the content being edited. The system serves itself by generating link recommendations without requiring manual intervention at each step, while still allowing user oversight and modification.
2Loss of time
If manual navigation through file systems is required, then users can precisely select target documents, but the time and interactions required increase
Solution Approach 1:
The machine learning model performs preliminary action by pre-identifying and ranking potential target documents based on the anchor text and document context. This pre-processing eliminates the need for users to manually navigate through the entire file system, as the system has already prepared a curated list of relevant targets.
Solution Approach 2:
The machine learning model acts as an intermediary between the user's linking intent and the file system. Instead of directly navigating the complex file system structure, the user interacts with the model's simplified suggestions, which mediate the connection between content and potential targets.
3Productivity
If automatic document linking is implemented, then the number of user interactions decreases, but the precision of link selection may be compromised
Solution Approach 1:
The system implements feedback by presenting multiple ranked suggestions to the user and allowing selection or modification. The machine learning model's predictions are fed back to the user for validation, enabling correction or refinement of automatically generated link suggestions to maintain precision.
Solution Approach 2:
The system changes parameters by adjusting the ranking and filtering criteria of suggested links based on the specific document context, anchor text characteristics, and user preferences. This dynamic parameter adjustment allows the system to optimize both speed and accuracy for different linking scenarios.
Data Source
AI summary
A system may use a machine-learned model to determine whether to classify a sequence of one or more words within a first document that is being edited as a candidate hyperlink based at least in part on context associated with the first document. In response to classifying the sequence of one or more words as the candidate hyperlink, the system may use the machine-learned model and based at least in part on the sequence of one or more words and the context to determine one or more candidate document to be hyperlinked from the sequence of one or more words. In response to receiving an indication of a second document being selected out of the one or more candidate documents, the system may modify the first document to associate the sequence of one or more words with a hyperlink to the second document.