Use cases

Find out how artificial intelligence has been implemented or is currently being developed in Estonia.

Data analysis tool OTT

The Estonian Unemployment Insurance Fund

Already implemented

OTT is a data analysis tool that forecasts the probability of the unemployed getting a job, identifies the factors influencing it and thus helps to offer the unemployed assistance based on individual needs and increase the efficiency of the Unemployment Fund.

Analysis of customer calls

Social Insurance Board

Already implemented

The Social Insurance Board, in cooperation with Feelingstream, conducted five pilot projects aimed at analyzing customer calls and web chats in detail and finding patterns in the reasons for customer inquiries. As part of the pilot, the Feelingstream application transcribed Social Security Board calls from May to August 2020 (3 months) in Estonian and Russian.

Machine translation in the Land Register search portal

Centre of Registers and Information Systems

Already implemented

Forecast models

The Estonian Road Administration

Already implemented

The Estonian Road Administration develops forecast models to identify the status of roads and the return on investments. This helps forecast the direction of the investments to achieve the greatest benefit from projects.

ESTNLTK

The Ministry of Education and Research

Already implemented

EstNLTK (NLTK, i.e., Natural Language ToolKit) is a collection of libraries, mainly written in Python, for processing texts in Estonian.
The purposes of EstNLTK include the mutual interfacing of existing language technology tools, making them accessible, and creating new ones. The solution is funded from the National Programme for Estonian Language Technology (https://www.keeletehnoloogia.ee/en).

Identifying tree species in the forest

Information Technology Centre of the Ministry of the Environment

Already implemented

The Environment Agency and KEMIT have, together with a development partner, created a remote sensing information system for forests which enables records of forest resources to be kept in a geo-referenced manner, and forest information to be collected and shared in an operative manner. The created solution is semi-automatic, being partially based on machine learning algorithms, partially on the visual verification of remote sensing data, and partially on the software solutions of third parties. Remote sensing data are mainly used as primary data, but forest notifications, soil maps, and other such data (including teaching and validation data) also act as inputs. The processing will create Estonia-wide map layers about more important survey characteristics, such as a raster map of tree species in woody flora (for identification based on the main tree species).

Calculating the height of a forest

Information Technology Centre of the Ministry of the Environment

Already implemented

The Environment Agency and KEMIT have, together with a development partner, created a remote sensing information system for forests which enables records of forest resources to be kept in a geo-referenced manner, and forest information to be collected and shared in an operative manner. The created solution is semi-automatic, being partially based on machine learning algorithms, partially on the visual verification of remote sensing data, and partially on the software solutions of third parties. Remote sensing data are mainly used as primary data, but forest notifications, soil maps, and other such data (including teaching and validation data) also act as inputs. The processing will create Estonia-wide map layers about more important survey characteristics, such as a raster map about the height of woody flora (for calculation of the average height of the forest).

Classification of citizen messages

The Ministry of Economic Affairs and Communications

In development

The threat assessment helper of the Emergency Response Centre

Emergency Response Centre

Already implemented

The AI solution assesses the threat level of an incoming case to optimise the work of the Emergency Response Centre. The aim is to perform development works to determine, as a result of pre-analysis – including on the basis of time-related transcribing of sound files of previous emergency calls and prototyping – whether and in which way can artificial intelligence help a rescue leader in making a threat assessment.

Monitoring and species identification with the help of image recognition

The Environment Agency

In development

Ilme – object recognition

The National Archives

Already implemented

Ilme is an internal development of the National Archives that uses image recognition to identify objects. Users are able to upload photos of their ancestors and receive matches from FOTIS.

Keeping records of forest resources with remote sensing methods

Information Technology Centre of the Ministry of the Environment and the Environment Agency

Already implemented

Since 1999, during the annual statistical inventory of Estonian forests (SMI), field measurements take place on 5600 sample plots every year. The data provides statistical assessments of forest resources, which are the basis for national reporting and the shaping of forestry policy. The aim of the project is to develop a suitable methodology for Estonian SMI for the use of multispectral space images and aeroplane laser scanning data, to obtain assessments of forest resources as maps. The project searches for solutions for the preparation of assessment maps concerning species composition, height and stem volume of forest stands, using accurate measurement data of trees growing on sample plots as an input for the models. The results can be used for monitoring forests and planning economic decisions on the forest stand level.

AI solution for opitimizing teaching

Information Technology Foundation for Education

In development

The purposes of the pilot are to determine and validate requirements for the use of AI and data analytics in conducting personalised studies, using data the collection of which does not constitute additional work for students or teachers.

Cyber security

The Information System Authority

In development

Ice map

Estonian Weather Service, Information Technology Centre of the Ministry of the Environment

Already implemented

Chatbot

The Information System Authority, the Police and Border Guard Board

In development

Improving traffic safety

The Estonian Road Administration, the Police and Border Guard Board

Already implemented

The aims of the project are to create a mathematical machine learning model for forecasting traffic accidents, evaluate its accuracy and usability, and to create a prototype of the model.

Remote sensing in the construction sector

The Ministry of Economic Affairs and Communications

Already implemented

The aim of remote sensing is to prototype different methods of remote sensing, and to create use cases on the basis of these, which the construction sector would be able to put to use.

Mapping of flooded areas and the moisture regime of swamps from satellite images

The Ministry of the Environment, the Estonian Research Council (RITA project)

Already implemented

A sustainable application plan will be created so that the Ministries responsible would be able to implement research-intensive activities in the longer term, and that Estonia would be able to put modern space technologies to use.

Smart positioning of a person

The Estonian Academy of Security Sciences

In development

AI solution for institutions of internal security. A video stream and GIS data will be interconnected to create an ISR tool.

Chatbot

The National Library of Estonia

Already implemented

Assessment of the condition and storage periods of museum pieces

The National Heritage Board

In development

This is a forecast model that could help predict the ageing of museum pieces, in order to move over to need-based inventory, to conserve man-hours.

Analysis of customer messages

The Estonian Unemployment Insurance Fund

Already implemented

The application developed by Feelingstream provides an opportunity to get both a statistical overview and a detailed understanding of customers' concerns across several customer communication channels - calls, emails and chat bots. Analysis of customer communications’ is the fastest and most immediate way to find out which parts of the services the customer is having troubles with and in turn that can be changed quickly. The analysis creates insights for managerial decision-making, which in turn leads to better and more efficient public services.

Information routing

The Consumer Protection and Technical Regulatory Authority

Already implemented

Start-up aid information and recommendation index

Enterprise Estonia

In development

Analysis of innovation shares has been performed to understand whether AI is able to resolve this.

Quality monitoring of streaming

Estonian Public Broadcasting

Already implemented

Grammar checker

The Ministry of Education and Research

In development

Collecting information from free text fields

The Rescue Board

Already implemented

Removing personal data from data

The Ministry of Education and Research

Already implemented

Speech recognition in sessions of the Riigikogu - HANS

Chancellery of the Riigikogu

Already implemented

Forecasting the health and treatment needs of the chronically ill

The Estonian Health Insurance Fund

Already implemented

The model for forecasting the health and treatment needs of the chronically ill helps the Health Insurance Fund detect the health status and treatment needs of patients and better organise health planning for high risk patient populations, such as diabetics or cardiovascular patients.

Analysis of customer messages

Statistics Estonia

Already implemented

Identifying field actions

The Agricultural Registers and Information Board

Already implemented

AI solution for bringing jobseekers and businesses together

Skillific

Already implemented