Use cases

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

A chatbot that introduces Estonia in all the world’s languages

AlphaBlues

Already implemented

AlphaBlues, an Estonian startup building virtual assistants, has developed a chatbot that talks about Estonia in any language possible.

Machine translation of Riigi Teataja's Official Announcements

Ministry of Justice

Already implemented

The Official Announcements is an electronic journal that publishes all notices, invitations and announcements prescribed by the legislation.

Machine translation in the information system of the Commercial Register

Centre of Registers and Information Systems

Already implemented

Machine translation

The Ministry of Education and Research, the University of Tartu, the Ministry of Economic Affairs and Communications

Already implemented

Multilingual, multi-field neural machine translation. The current version supports seven languages as source and target languages: Estonian, Latvian, Lithuanian, English, Russian, German and Finnish.

Pilot project for transcribing calls to the Police and Border Guard Board’s information hotline (612-3000)

The Police and Border Guard Board

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.

Identification of clear cutting of forests

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 vector map of felled areas (for identification of clear cutting > 0.5 ha).

Libraries of processing of Estonian-language texts

The University of Tartu, the Ministry of Education and Research

Already implemented

Transcription of crisis hotline 1247

Emergency Response Centre

In development

AI solution will transcribe calls made to the number 1247.

Transcription of emergency calls

Emergency Response Centre

Already implemented

AI solution will transcribe calls made to the number 112.

Identification of forbidden advertising

The Consumer Protection and Technical Regulatory Authority

In development

Analytics on the usability of the state portal

The Information System Authority

In development

Water level monitoring in coastal seas and lakes, using satellite altimetry

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

In development

Three different prototypes will be developed in the course of the project: hydrological operative monitoring of the satellite information on flooding; resource charge verification in peat deposits, using radar remote sensing data; and water level remote sensing data for improving hydrological monitoring and sea forecast services. Hydrological monitoring includes on-site measurements of water levels and flow rates at national hydrometry stations. Resource charge verification: from Sentinel-1 data, it is possible to determine on which deposits, and how many times in a quarter, peat was extracted. This overview provides an opportunity to verify the data reflected in the resource charge declaration. When combined, the water level remote sensing prototypes enable remote sensing data, the forecast model, and artificial intelligence, to be used to ensure better water level information for interested parties and the public. Integrating altimetry data into hydrological monitoring would help to improve the spatial coverage of surveying on major lakes and improve the accuracy of sea level forecasting.

Salme – speech recognition in courts

Centre of Registers and Information Systems

In development

Speech recognition software; enables transcription of the written stenographic record (hereinafter the verbatim report) of the hearing, based on a real-time sound recording or digitally stored sound recording, which will be used to prepare minutes of the hearing.

AI solution for identifying data exchange anomalies of the X-Road

The Information System Authority

Already implemented

Automating customer communications of the Social Insurance Board

Social Insurance Board

Already implemented

AI solution for opitimizing learning

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.

Identifying residential buildings that are fire hazards

The Rescue Board

In development

Identifying crops from Sentinel-1 and Sentinel-2 time series, using deep learning methods

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

In development

In the course of project RITA1/02-52 “Use of remote sensing data for elaboration and development of public services”, in cooperation with Estonian universities, we are developing a methodology for the identification of crops that are suitable for Estonian conditions.

Remote sensing in the management of wildfires

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

Automatic border control

The Police and Border Guard Board, Information Technology Centre of the Ministry of Internal Affairs

In development

A face recognition solution and automatic border control gates will be implemented at Estonian border crossing points.

Automatic keywording of publications

The National Library of Estonia

Already implemented

The National Library of Estonia is developing an innovative solution in Estonia which will make the keywording of publications automatic. In the future, other libraries will also be able to use artificial intelligence to facilitate their work.
The automatic text keywording AI solution will make describing the content of a publication quicker and more effective. In addition, the project will support the development of Estonian language technologies. A prototype will be completed as a result of the project, which in the future could be used by both the National Library of Estonia as well as other libraries to optimise their activities. If the prototype is successful, the project will move to the stage of creating the application, and opportunities will be created for interfacing the application with library systems and digital archives, such as the online catalogue ESTER and the digital archive DIGAR. 

Describing museum show pieces

The National Heritage Board

Chatbot Iti

Statistics Estonia

Already implemented

Statistics Estonia is using the chatbot for customer communication.

Virus protection

Estonian Public Broadcasting

Already implemented

Chatbot

Enterprise Estonia – e-residency

Already implemented

Analysis of real-time users of the news portal

Estonian Public Broadcasting

Already implemented

Traffic sign identification

The Estonian Road Administration, Teede Tehnokeskus

Already implemented

Removing personal data from court decisions

Ministry of Justice, the Information System Authority

Already implemented

Estonian text-speech synthesis

The Ministry of Education and Research, Institute of the Estonian Language

Already implemented

In cooperation with the University of Tartu, the project “Estonian speech synthesis with neural networks” is underway; the purpose of the project is to create new synthetic voices using the neural networks method. The primary goal of the Institute of the Estonian Language’s speech synthesis project “Diversification of Estonian text-to-speech synthesis” is to achieve a considerable improvement of the naturalness and expressiveness of the output speech of Estonian text-to-speech synthesis, in the longer term allowing a wider use of speech synthesis as a result of its better quality. The project has resulted in and will result in the creation of natural and diverse synthetic voices that are based on different methods of synthesis, correspond to the expectations of different target groups, and can be used for various purposes.

Speech recognition in radiology

The North Estonia Medical Centre

Already implemented

Mapping the species composition of forests

The State Forest Management Centre

Already implemented


Optimizing the home delivery of parcels by robot couriers

Cleveron

Already implemented

Allergy drug production planning

Visory

Already implemented

Better management of traffic


Tallinn Transport Board

Already implemented

Chat bot for resolving the issues of clients

Telia

Already implemented

Chat bot for resolving the issues of clients.