Health recommendation system and recommendation method based on medical knowledge graph

Abstract

The invention provides a health recommendation system based on a medical knowledge graph. The health recommendation system comprises an abnormal sign library, the abnormal sign library comprises medical abnormal data and time period abnormal data. A user health portrait can be established through the medical abnormal data and the time period abnormal data. The invention further provides a health recommendation method. The health recommendation method comprises the steps that the abnormal category feature tag of the user a is obtained; the occurrence time of the ith abnormal feature tag AXi is obtained, the association time period of the ith abnormal feature tag AXi is set as Delta ATi, and each association time period of the AXi comprises each occurrence time of the AXi; an abnormal category feature AF occurring in all association time periods of the abnormal category feature AXi is obtained; and all the abnormal category features AF occurring in the association time period Delta ATi of the abnormal category feature AXi is recorded as preset association features of the AXi, and a user health portrait is constructed according to the associated abnormal category features. The invention provides an optimized health recommendation system.

Description

technical field [0001] This application relates to the field of user health portraits, in particular to a health recommendation system and recommendation method based on medical knowledge graphs. Background technique [0002] With the continuous development of today's economy, the aging of the social population is becoming more and more serious, senile diseases are prevalent, and the greater life pressure also makes young adults suffer from chronic diseases. In order to facilitate the statistics of users, abnormal signs and symptoms, and tracking, existing technologies have gradually formed For each user's personal health record report, information sharing is realized through the Internet and big data; however, most of the data in the existing personal health record report only involves the physical parameters of the patient's support, and the abnormal data found in the daily life of the patient, Living conditions, work, diet, sports and other information are rarely obtained...

AI Technical Summary

Problems solved by technology

[0002] With the continuous development of today's economy, the aging of the social population is becoming more and more serious, senile diseases are prevalent, and the greater life pressure also makes young adults suffer from chronic diseases. In order to facilitate the statistics of users, abnormal signs and symptoms, and tracking, existing technologies have gradually formed For each user's personal health record report, information sharing is realized through the Internet and big data; however, most of the data in the existing personal health record report only involves the physical parameters of the patient's support, and the abnormal data found in the daily life of the patient, Living conditions, work, diet, exercise and other information are less acquired and not updated in a timely manner, and it is impossible to perform multi-dimensional and all-round real-time portraits of users, so that the multi-dimensional information of patients and users cannot be obtained in a timely manner

Because effective treatment and health care measures cannot be formed, it affects the timely reminder and effectiveness of the user's treatment; the evaluation and prediction of the user's health status in the prior art is often based on the standard physical characteristics of the same type of patient users, and cannot be based on The current user's standard physical characteristics are used as a reference, so it is not possible to effectively propose the most suitable guidance and intervention measures for the current user's patient, and the needs of individuals, enterprises, and health supervision units cannot be met.

Images