Today, the aging of the population and the increase in life expectancy are leading to an increase in the number of people looins their autonomy and frailty. Noting the lack of places available in specialized institutions, an alternative is home care (HAD). Home-based care structures help reduce hospital overcharge and provide a better environment for patients. IN our projet, we target french structures such as : HAD (Hospitalization at Home), SSIAD (Home Nursing Services), SPASAD (Multipurpose Services of Help and Home Care), and SAAD (home help not medicalized). The management of these structures and more particularly the planning of the speakers is generally complicated and often manual. The production of a planning is therefore often realized ad-hoc and it is a real organizational challenge to deal with hazards such as the integration of new patients or lack of staff.
To meet this need, we are exploring the creation of a planning generation tool that can take into account a maximum of constraints and criteria related to the home care structure. We have implemented an ant colony-based algorithm to solve the problem of planning and optimizing stakeholder tours. These artificial intelligence algorithms work with undeveloped intelligences (i.e. ants) to bring out a highly developed collective intelligence that will solve very complex problems. These tools are being developed by Berger-Levrault’s R&D unit and we hope soon to be able to put them in experimentation situations with actors in the field.