Loading...
hidden

View Mobile version

Meta navigation

Startseite – Hochschule Luzern

Language selection and important links

  • Contents
  • Contact
  • Login
  • De
  • En
Search

Main navigation

School navigation

  • Engineering and Architecture
  • Business
  • Computer Science
  • Social Work
  • Art and Design
  • Music

Sub-navigation

  • Degree Programmes
  • Continuing Education
  • Research
  • International
  • Campus
  • About us
  • News

Sub-navigation

Breadcrumbs

  1. Research Research
  2. DEMETER - Combining NLP and trust to automate access to relevant and transparent knowledge on agricultural markets DEMETER - Combining NLP and trust to automate access to relevant and transparent knowledge on agricultural markets

DEMETER - Combining NLP and trust to automate access to relevant and transparent knowledge on agricultural markets

Extracting contextual information from data sources for agricultural markets is done manually by analysts. This makes the information biased, expensive and controlled by a few. DEMETER aims to switch this to automatically provide generated market insights.

Brief information

School:

Engineering and Architecture

Status:

Ongoing

Period:

01.08.2022 - 31.07.2024

Overview

Agricultural producers and smaller buyers and sellers of agricultural commodities need to be able to make informed decisions in order to plan their business.

To do this, they would need to analyse data from a variety of sources on a regular basis. Currently, however, there is no feasible way for them to process the flood of data, which also varies greatly in quality and often comes from intransparent ecosystems. This makes it difficult to determine the origin, accuracy and timeliness of the data.

Today, only corporations and large companies can compile and use this data to gain fact-based information.

Although contextual data exists, for example in publications of new regulations, in annual reports of large companies or in social networks, small and medium-sized customers do not have the necessary resources and skills to benefit from these sources, especially since they are often not even aware of their existence.

To address this market need, DEMETER is developing a natural language processing (NLP) platform that will automatically process and analyse text from the various sources to provide transparent, accurate and timely knowledge about key agricultural markets in a cost-effective and scalable manner.

Integrated into the platform will be a trust tool that monitors and evaluates the reliability of the knowledge gained from the data and adjusts the NLP parameters as needed.

The platform will provide clients with the ability to obtain up-to-date, fact-based and high-quality knowledge, enabling them to quickly grasp and understand market needs and movements.

This will enable clients to make their decisions based on high-quality market insights and a better understanding of the market.

One of the biggest challenges is to deal with the heterogeneous, often untrustworthy data sources as well as the domain-specific agricultural content. The approach taken in the project is based on the latest state-of-the-art transformer technologies, which extract the interesting information from unstructured text data and generate up-to-date and valuable knowledge about agricultural markets.

By presenting the relevant content in a comprehensible way, the platform will improve the range of services offered by the implementation partner AgFlow to existing customers and open up new customer segments (agricultural producers / primary processing chain).

Translated with www.DeepL.com/Translator (free version)

hidden

Facts

Type of project

Forschung

Internal organisations involved
  • iHomeLab
External project funder
  • AgFlow SA
  • HES-SO Univ. of applied Sciences and Arts, West. Switzerland
Funding
  • SBFI
  • Andere Bundesstellen
  • Private / Stiftungen
  • Forschungsfinanzierung allgemein
hidden

Links

  • Weitere Forschungsprojekte des iHomeLab im Bereich Smart Energy Management

hidden

Persons involved: internal

Project manager
  • Guido Kniesel
Member of project team
  • Martin Camenzind
  • Martin Friedli
  • Andrew Paice
  • Andreas Rumsch
  • Raphael Schranz
  • Manuel Vogel

Brief information

School:

Engineering and Architecture

Status:

Ongoing

Period:

08/01/2022 - 07/31/2024

Project Head

Guido Kniesel

Senior Research Associate

+41 41 349 33 27

Show email

Footer(s)

FH Zentralschweiz

Social media links

  •  Facebook
  •  Instagram
  •  Twitter
  •  LinkedIn
  •  YouTube
  •  Flickr

Contact

Logo Lucerne University of Applied Sciences and Arts

Lucerne University of Applied Sciences and Arts


Werftestrasse 4
CH- 6002 Luzern

+41 41 228 42 42

info@hslu.ch

Direct entry

  • A bachelor's degree –
  • A master's degree –
  • Prospective Students (Continuing & Executive Programmes)
  • Unternehmen & Institutionen
  • Media Relations
  • For Students
  • For Members of Staff

Quick link

  • People Finder
  • University Buildings & Campus Locations
  • News
  • Libraries
  • Events
  • Jobs & Karriere
  • Home
  • Hiring Rooms

Static links

  • Newsletter
  • Data protection notice
  • Publishing Acknowledgements
Logo Swissuniversities

QrCode

QrCode
We use cookies on this site to give you the best browsing experience. By continuing to navigate this site or closing this banner you accept this use of cookies. For more information please visit our privacy policy.
OK