Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

Fully automated transformation removes thresholds for digitizing invoicing in Sweden

Reference number
Coordinator ESYNERGETICS AB
Funding from Vinnova SEK 1 000 000
Project duration June 2023 - October 2024
Status Completed
Venture AI - Competence, ability and application
Call Scaling up of AI solutions with municipalities and civil society

Important results from the project

The project had ambitious goals of a model in production that handle the absolute majority of different invoice types. A lot of time has gone into creating a large amount of training data. We see that the result is good, but the complexity of different invoices needs a greater amount and variety of training data to meet our high objective. The project is successful as the model is used in production and creates value for customers, but we have as objective higher generalizability for wider use.

Expected long term effects

In the long term, we will deliver a model that creates great automation. The model creates the possibility for very competitive pricing and to really reduce the manual handling of manual invoices in the private- and civil society. The benefit of eliminating these manual flows is very large as thousands of hours each month are spent on tasks that are unnecessary, inefficient and costly.

Approach and implementation

The project has been carried out according to plan with the objective having a model in production. More time than estimated and higher costs have been spent on producing and securing training data. The plan has been followed, but some activities have been running for a longer period of time but could then be done in parallel with other. Unexpected and unplanned problems always arise, but these have been managed within the project and with the organization´s regular activities

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 6 December 2024

Reference number 2023-01159