Scaling content efficiency with Doc to XML and Content Reuse Analyzer

A global industrial manufacturer needed to improve how documentation is managed across multiple product variants, where similar content was duplicated across separate manuals. By combining the use of Doc to XML and Content Reuse Analyzer, two of Etteplan’s rAIse tools, Etteplan made content reuse visible and measurable for the customer, revealing that a significant share of content could be reused, thereby reducing manual effort and translation work.

The project in a nutshell

Challenge
Documentation for multiple product variants contained significant overlap, but each manual was managed separately. Identifying reusable content manually across hundreds of pages was time-consuming and made updates, translations, and maintenance inefficient.
Solutions and Services
Doc to XML and Content Reuse Analyzer enabled documentation to be converted into structured XML and analyzed across product variants. This made it possible to identify reusable content and quantify reuse across product variants.
Added value
Approximately 70% of content was reusable as-is and around 20% with minor adjustments. The approach reduced analysis work from months to days and enabled completion of the project in weeks instead of months. It also reduced translation work and simplified ongoing maintenance.

Similar products, separate manuals, repeated work

The customer was managing documentation for multiple product variants, each with its own manual stored as a separate PDF. Although the products shared a common structure, the documentation process treated them as independent. This led to duplicated work, repeated translations, and inefficient updates across multiple documents. Understanding how much content could actually be reused was difficult, as manually comparing hundreds of pages across documents would have taken a significant amount of time.

Turning static documents into structured, comparable content

The work began with Doc to XML, which was used to convert the documentation into structured XML packages.

The Doc to XML tool uses AI-assisted processing to convert Word and PDF documents into structured XML, automatically identifying and modularizing content into topics such as tasks, concepts, and references. This creates a consistent, comparable structure that enables further analysis.

Making reuse visible instead of guessing

With structured content in place, Content Reuse Analyzer provided clear insights into similarities, differences, and reuse potential across product variants.

This tool uses AI-based similarity analysis to compare structured XML topics and identify which content is identical, which can be reused with minor adjustments, and which is unique. Instead of manually comparing documents and tracking results in spreadsheets, reuse potential becomes visible and structured.

From manual comparison to structured insight

The results were clear and actionable. Approximately 70% of the content was identical and could be reused directly, while around 20% required only minor adjustments and less than 10% was unique. The overall work was completed in roughly two weeks instead of an estimated two months. Instead of manually reading and comparing hundreds of pages, reusable content was quickly identified, allowing the work to focus on the relatively small set of topics that required refinement and rewriting.

Reducing duplication across translation and maintenance

By maximizing content reuse, translation work can be reduced, as shared content only needs to be translated once. Updates also become more efficient, since changes can be made in one place instead of across multiple documents.

From fragmented content to structured reuse

By combining structured content conversion with automated reuse analysis, Etteplan transformed a time-consuming and manual comparison process into a clear and data-driven workflow. Instead of working document by document, reuse potential could be identified across entire content sets, allowing effort to be directed where it was needed.

This not only improved efficiency during the project but also created a foundation for more consistent, maintainable, and scalable documentation going forward.