Online doctor-patient dynamic stable matching model based on regret theory under incomplete information

With the development of the Internet era, online medical community is increasingly favored by patients and health care workers. How to make a reasonable doctor-patient matching and meet patients' relevant needs through online medical platform is the key to realizing effective allocation of medical resources. This paper proposes an online doctor-patient dynamic stable matching model to deeply investigate the online doctor-patient matching problem under incomplete information. Firstly, we assign the score to each doctor based on the patient's attribute expectations and the doctor's evaluation information. Considering the difficulty of obtaining complete information in real life and different attribute representations, we propose incomplete information filling methods based on collaborative filtering algorithm. To make the filling result more reasonable, we introduce probabilistic linguistic information entropy to process the incomplete information. Secondly, considering psychological behavior, we use regret theory to calculate patients' satisfaction with doctors. Finally, with the definitions of rational matching and stable matching, we propose a doctor-patient dynamic stable matching model. This model can solve the problems like a temporary appointment and private matching and ensure the stability of matching. In addition, the model proposed in this paper considers not only patients' but also the doctors' needs. The case of online doctor-patient matching is based on “haodf.com”, and through comparative analysis can prove the effectiveness and superiority of this method.