Hospital expense prediction method and device based on knowledge graph, and computer equipment

Abstract

The invention discloses a hospital expense prediction method and device based on a knowledge graph, and computer equipment, relates to the technical field of artificial intelligence, and can solve the technical problems of large prediction workload and low accuracy of an existing hospital expense prediction mode. The method comprises the following steps: acquiring a medical knowledge graph, and carrying out representation learning on the medical knowledge graph by utilizing a graph embedding algorithm to obtain a node representation vector of each knowledge graph node; generating a first feature vector of the sample hospital patient about historical medical data according to the node representation vector, and training a hospital expense prediction model by using the first feature vector and historical expense data in the historical medical data; and obtaining target diagnosis data of the target patient in the first time period, generating a second feature vector of the target diagnosis data according to the node representation vector, inputting the second feature vector into the trained hospital expense prediction model, and obtaining a hospital expense prediction result of the target patient in the second time period.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular to a method, device and computer equipment for predicting hospitalization expenses based on knowledge graphs. Background technique [0002] The medical expense prediction of inpatients needs to estimate their potential future expenses according to the state of the patients at the time of admission. For hospitalized patients, they often need to seek medical treatment for a long time. Accurate prediction of the medical expenses required during the treatment process is conducive to the planning of long-term treatment plans for patients; The deployment and accurate prediction of medical expenses are conducive to the efficient management of hospitals. Moreover, the current medical insurance system in our country is not perfect, and there is a phenomenon of over-medication. Accurate prediction of medical expenses is conducive to the control of medical insura...

AI Technical Summary

Problems solved by technology

[0005] In view of this, this application provides a method, device, and computer equipment for predicting hospitalization expenses based on knowledge graphs, which can be used to solve the technical problems of heavy workload and low accuracy in the current method of predicting hospitalization expenses

Images