Yandex.Lavka has started adding product information to its app using YandexGPT and OCR (Optical Character Recognition) text recognition technology, the service said in a statement.
The new tools analyze the photograph of each product label and independently complete its file. As Lavka reported, this speeds up the updating of product information three times and simplifies the work of content managers.
Now, to add information about a new product, you need to take a photo of its packaging and upload it to the Lavki content system. Text recognition technology will analyze the photo and translate it into text, and the YandexGPT neural network will take product characteristics from it and fill in your card.
To train the neural network, Lavka showed it 16 thousand ready-made cards. In the future, with the help of YandexGPT, the service plans to create detailed product descriptions and provide advice on what they can be combined with.
Yandex launched YandexGPT in May 2023. The neural network can create and process texts, retell them, perform tasks, offer new ideas and take into account the context of the conversation with the user. The company also implemented it in its Masterpiece application and in sellers’ personal accounts on Yandex.Market.
On September 7, Yandex released a new version of its neural network: YandexGPT 2. It is capable of solving more different types of problems than the first version and the quality of its answers has also been improved.
Author:
Anastasia Marina
Source: RB
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
