An automatic tool for planning forest management.

The main objective of the kratt was to identify the traffic load within Tallinn, ie how many cars drive into and out of the city in a day, to make decisions related to city transport planning relying on such data. Three cameras were selected at intersections in Tallinn to train the kratt to count the vehicles passing by the cameras. The training of the kratt for counting was a crucial step in the development of the solution as there was no pre-existing product that suited the specific conditions in Tallinn. The outcome was a kratt that uses machine vision to count buses, conventional vehicles, trucks and motorcycles and hopefully, in the next stage, also pedestrians and non-motorised road users.

The project resulted in the completion of the prototype and analysis of the name similarity assessment assistant INNA (INvented NAme). The analysis reveals the possibility of conducting a similarity search for medicine names and provides a description of the technical implementation together with proposals for further development, potential administrative costs and volume estimates.

Identification of all analysed sectors and a description of problem enterprises (ie a precise description of the sectors as well as which enterprises in which sectors receive exactly which warnings). Primary models created as of January 2023.

Bürokratt is an interoperable network of chatbots on the websites of public authorities that allows people to obtain information from these authorities through a chat window using everyday language. It provides individuals, or users, with the opportunity to access direct public and information services through virtual assistants using everyday language.

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 (incl 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).

As part of the project, the calls made to the hotline of the PBGB were transcribed. The Feelingstream application provides both a statistical overview and a comprehensive understanding of customer concerns across different communication channels, including calls, emails and chatbots. An analysis of customer contacts is the fastest and most direct way to identify areas in services where customers encounter difficulties and to make prompt improvements. This analysis provides insights for management decision-making which, in turn, leads to better and more effective public services.

Chatbots for patients in the ICU to allow them to contact their loved ones through video links. The robots operating in the North Estonia Medical Centre also provide assistance to doctors by allowing them to navigate the ICU using their phone or computer, chat with patients and monitor their health indicators on the screens.

A pilot project for the development of a tool, aimed at exploring ways to improve the efficiency of tax collection.

The primary objective of the analysis project for the development of the customer enquiry management and maintenance functionality is to determine the optimal solutions for automating the activities involved in customer enquiry management. Among other things, the analysis seeks to address the issued of how to obtain a complete overview of customer enquiries, how to quickly locate customer enquiries, how to conveniently manage enquiries and easily assign them as work tasks and how to minimise the need for additional contact with persons. As a result of the analysis project, an analysis was carried out for the development of the customer enquiry management and maintenance functionality, the findings of which revealed the use cases and development volumes necessary for achieving the objectives. A finished prototype of the future solution was also completed.

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 (incl 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).

In previous audits, the National Audit Office of Estonia has found the process of identifying and recording election campaigns on public channels (TV, radio, foreign media) to be labour-intensive and ineffective. Furthermore, as advertising increasingly shifts to social media channels, state and local government agencies are also using different social media channels to inform their residents. At the same time, it is not possible to retrospectively identify the information shared on social media channels (Facebook, Instagram, Twitter). Consequently, the National Audit Office of Estonia is unable to verify whether these channels have been used for personal political gain. The daily monitoring and manual verification of newsletters funded by public money and social media content is unreasonably time-consuming and resource-intensive for the officials of the National Audit Office of Estonia. Therefore, the National Audit Office of Estonia is looking for an effective IT solution to address the problem.