Intelligent triage method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of medical science and technology, and particularly provides an intelligent triage method and device, electronic equipment and a storage medium. The methodcomprises the following steps: acquiring at least one symptom of a patient, wherein the at least one symptom comprises a symptom obtained by the current round of symptom inquiry; acquiring a department recommendation result corresponding to the patient according to the at least one symptom; acquiring feedback for the department recommendation result; determining the symptom obtained by the current round of symptom inquiry as a target symptom according to the feedback; and performing a next round of symptom inquiry based on the target symptom, and repeatedly executing multiple rounds of symptom inquiry until a recommended department is returned to the patient. According to the embodiment of the invention, the method facilitates the reduction of the number of turns of interaction with a patient during triage, and also facilitates the improvement of triage accuracy.

Description

technical field [0001] The application relates to the technical field of image processing, in particular to an intelligent triage method, device, electronic equipment and storage medium. Background technology [0002] Patient triage is an important work in the daily work of the hospital. Rapid and accurate triage can save patients' treatment time and improve their treatment experience. Most of the traditional triage methods are manual triage. Due to the different levels of hospitals and the uneven level of medical personnel, the accuracy of manual triage is also different, and requires certain human investment. Under this background, intelligent triage was born. At present, intelligent triage often uses reinforcement learning model to determine the specific number of rounds of consultation. The existing reinforcement learning methods do not distinguish the symptoms of patients, and the symptoms that do not help the Department recommendation are also considered. In addition, both ...

AI Technical Summary

Problems solved by technology

The traditional triage methods are mostly manual triage. Due to the different levels of hospitals in various places and the level of medical personnel are also uneven, the accuracy of manual triage is also not the same, and a certain amount of manpower is required. Under this background , the birth of intelligent triage

The current intelligent triage often uses the reinforcement learning model to decide the number of consultation rounds. The existing reinforcement learning method does not distinguish the patient's symptoms, and the symptoms that do not help the department recommendation are also considered emphatically. In addition, , set both symptom inquiry and department recommendation as the learning objectives of the reinforcement learning model, which makes the model learning task more complicated, which will affect the accuracy of triage

Images