Machine-generated text creation is a relief for copywriters and content managers in e-commerce. Anyone involved in writing texts benefits from it. There are two key technologies: generative AI and rule-based data-to-text systems. Most have already had their first experiences with generative AI, most notably GPT. But how do these two technologies differ in terms of […]
The Case
The KLiNGEL Group has 15 brands and more than 60 online stores in 12 different countries. They sell millions of products and need unique and high-quality product descriptions for all sub-brands and channels in multiple languages.
The Challenge
KLiNGEL was faced with the major challenge of making product management and translation processes more efficient. This included all of their 9 company languages. In the past, the company lost a lot of time and money due to the large number of brands, products and languages. That’s why KLiNGEL decided to take a step towards automation.
Their goals:
- Generate high-quality and optimized product descriptions that match the tone of the respective brands.
- Dramatically increase the speed of product description creation.
- Relieve the editorial teams and free up time for other tasks, such as optimizations.
- Ability to adapt and update product descriptions quickly and on scale.
The Solution
The KLiNGEL team knew they needed to find a way to speed up their content creation processes. So they decided to use the AX Semantics software.
Automation of product descriptions
With the AX Semantics content automation software, KLiNGEL can automatically generate product descriptions based on structured data from a PIM system. KLiNGEL has successfully switched the product management and translation team to a hybrid editorial model. The configuration of the content is in the hands of editors. After the configuration, the team was able to replace short and generic product descriptions with unique content that consisted of individual wording and style for various brands.Content in multiple languages
Since content automation is possible in 110 languages with AX Semantics, internationalization is definitely an option. This is a massive advantage for internationally operating companies like KLiNGEL, as translation processes are often complex, lengthy, and therefore cost-intensive. With content automation, KLiNGEL can provide brand-specific product descriptions for all markets and in all the languages they need.Fast time to market of the products
Products no longer wait for publication because the product descriptions have not yet been written or translated. As soon as product data is available, a product description is generated automatically.Always up-to-date content
When product information changes, it is necessary to adapt the content accordingly. But it is very time-consuming to do that manually. With the help of AX Semantics, KLiNGEL can implement changes centrally in the tool and roll them out to all relevant texts in all languages and for all platforms like online stores, Amazon and eBay. This saves a lot of time and the product descriptions are always up-to-date.
The Results
Since choosing AX Semantics, the company has generated millions of unique and high-quality product descriptions in multiple languages and now generates 50 million product descriptions every month.Also, KLiNGEL has massively reduced the time and effort required to create product descriptions and translations. Not only for their online stores, but also for their catalogs in all 9 languages, as the company decided to use AX Semantics for their print product as well. Thanks to using content automation, the translation work was drastically reduced by up to 95 percent per double page.By generating high-quality product descriptions with added value for the reader and automating FAQs that answer common questions, KLiNGEL has also reduced call center inquiries. This has resulted in cost savings of more than 1 Million Euro per year.Also, the time to market was extremely reduced, as KLiNGEL was able to produce new product descriptions in 24 hours instead of two to four weeks.
