Insulin recommendation method and device and blood glucose level monitoring system

Abstract

The invention relates to the field of physiological signal processing, and provides an insulin recommendation method and device and a blood glucose level monitoring system. The method comprises the steps of conducting regularization on key feature data of a user, to obtain at least two matched feature values; performing matching in a case library based on the at least two matching feature values; if the matching succeeds, selecting a first insulin recommendation scheme based on the ranking of the scores; if the matching fails, outputting a second insulin recommendation scheme; updating the case library based on feedback information of the user for the recommendation, wherein when the user accepts the recommendation, the feedback information comprises a first insulin recommendation scheme and a score thereof or a second insulin recommendation scheme and a score thereof, when the user does not accept the recommendation, the feedback information comprises the insulin response scheme adopted by the user and the score of the insulin response scheme, and the score is determined based on the target blood glucose time proportion and / or the blood glucose concentration change rate of the second time period. According to the invention, a user can enjoy richer and more reasonable recommendation, and the user experience is improved.

Description

technical field [0001] The invention relates to the field of physiological signal processing, in particular to an insulin recommendation method and device, and a system for monitoring blood sugar levels. Background technique [0002] Diabetes is a chronic metabolic disorder that results from the inability of the pancreas to produce sufficient amounts of the hormone insulin, reducing the body's ability to metabolize glucose. The most prevalent forms of diabetes are those that result from decreased insulin secretion (type 1 diabetes, the first recognized form) or from decreased sensitivity of body tissues to insulin (type 2 chronic diabetes, the most common form). Treatment of the former requires insulin injections, while the latter is generally controlled with oral medications. [0003] With the development of biosensor technology, the emergence of continuous monitoring system of blood glucose concentration (continuously providing real-time blood glucose concentration data ...

AI Technical Summary

Problems solved by technology

There is no single solution to combine information into a more reasonable insulin recommendation

Furthermore, effective insulin recommendations cannot be achieved simply by combining the various pieces of information available in the field, each of which has specific elements that must be developed and adjusted for the entire process to have the desired safety, Recommended levels of accuracy and robustness

[0004] In the process of realizing the embodiment of the present invention, the inventor found that there are at least the following defects in the background technology: some existing recommendation schemes do not take into account the influence of the short-term blood sugar concentration change rule brought about by the user input data on the blood sugar level , such as the user's current blood sugar level, insulin usage, carbohydrate intake or consumption, exercise, medication, etc., or error data, without taking into account the user's personalized recommendation and the actual effect of the recommendation, and lead to poor user experience

Images