Мы используем файлы cookie для быстрой и удобной работы сайта. Выберите, какие файлы cookie вы разрешаете нам использовать. Подробнее в Политике конфиденциальности.
We use cookies to ensure our website works quickly and easily. Choose which cookies you allow us to use. Learn more in our Privacy Policy.
Discuss the project
Send a request and our specialists will contact you within 1 hour.
By clicking the "Send" button, you give your unambiguous consent to the processing of your personal data to the extent and for the purposes defined in the Personal Data Processing Policy.
Get development
Submit a request and gain access to a training manual from a leading company expert!
By clicking the "Send" button, you give your unambiguous consent to the processing of your personal data to the extent and for the purposes defined in the Personal Data Processing Policy.
Automating the Matching of Restaurant and Supplier Product Lists with LLM
AI-powered chatbots and the LLM
15
50%
search time has been reduced
by
by
costs for replacement and return of goods have been reduced
times
Customer
A large restaurant holding in St. Petersburg with branches throughout the Russian Federation
CHALLENGES/FEATURES
The selection of an analog must be carried out according to the specified criteria for dividing goods from the database into three categories: exactly suitable items; potentially suitable items; unsuitable items.
The system must automatically generate criteria for dividing into categories based on the received product name and rules that take into account the product group and restaurant requirements.
As part of the pilot project, restrictions were introduced on the ranking of product lists based on criteria received from the customer for five product groups: shrimp, eel, parmesan cheese, cottage cheese, and butter.
For a given product name from a client (restaurant), it is necessary to automatically search for similar products in the general database of suppliers' products
Task
solution
Technical solution
The DUC SmartSearch digital assistant automatically compares two lists of items.
It selects the most suitable item from the supplier list for each item from the restaurant list, ensuring a unique selection.
The assistant preserves the original items intact and takes into account all abbreviations provided in the source lists.
It selects the most suitable item from the supplier list for each item from the restaurant list, ensuring a unique selection.
The assistant preserves the original items intact and takes into account all abbreviations provided in the source lists.
Result
Business values
Speed up processes by 15 times
Reducing payroll costs to 100,000 rubles per month
Improving efficiency
Reducing errors in product deliveries
Reduce the time it takes to search and compare products by 15 times
Instead of 15 minutes for manual comparison, 1 minute for checking and correction
50% reduction in costs for replacements and returns of goods
increasing customer loyalty
By clicking the "Submit" button, you expressly consent to the processing of your personal data to the extent and for the purposes defined in the Personal Data Processing Policy.
Development of software
and Big Data solutions
and Big Data solutions
Send a request and our specialists will contact you within 1 hour.
Choose a convenient method of communication
You can attach three files up to 3 MB each. Formats: doc, docx, pdf, ppt, pptx
Сообщение об успешной отправке!