A personalized diet recommendation method for diabetes mellitus by introducing adaboost probability matrix decomposition

Abstract

The invention discloses a method of introducing Adaboost probability matrix decomposition for diabetes personalized diet recommendation, comprising: step 1, establishing a dietary preference feature set U={u for diabetic patients 1 , u 2 ,...,u n} and the attribute feature set of food V={v 1 ,v 2 ,...,v m}, record the diet of diabetic patients, extract preference features and food attribute features, and form the dietary preference matrix U∈R of diabetic patients K×M and food attribute features V ∈ R K×N Step 2, determine the correlation strength between the dietary preference of the diabetic patient and the attribute characteristics of the food by quantifying the correlation between the dietary preference of the diabetic patient and the attribute characteristics of the food; Step 3, weighting the degree of association After the value distribution is basically classified, the training data set updates the weight distribution, and assigns weights to all the correlation degrees to classify and exclude unnecessary foods, and obtains the final correlation degree classification as follows: Step 4. According to the conditional probability and the correlation degree Categorize the personalized diet.

Description

technical field [0001] The invention relates to the field of intelligent medicine, in particular to a personalized diet recommendation method for diabetes by introducing Adaboost probability matrix decomposition. Background technique [0002] With the gradual acceleration of the Internet age, the amount of information has skyrocketed, and the technology of providing recommendation services for users has also been applied to various fields, so as to help users find the information they want more accurately. [0003] The current diet recommendation methods for diabetic patients mainly include association rule-based recommendation, content-based recommendation, collaborative filtering recommendation, constraint-based recommendation and other methods: (1) The main representative of association rule-based recommendation is the Apriori algorithm, and its core idea is Strong association rules are generated in the frequency set, and the defined rules must meet the minimum confidence...

AI Technical Summary

Problems solved by technology

Therefore, it is extremely difficult for the collaborative filtering recommendation method to deal with complex object attributes; (4) The constraint-based recommendation method mainly relies on the attributes of the items, that is, to recommend items that can match user needs, preference characteristics, and rigid requirements from the item collection. Some standards rigidly restrict the diet structure of diabetic patients, although it seems to meet the patient's medical index requirements and the patient's preference for food; in fact, it is not the case, if there is a demand conflict or empty solution during the constraint solving process , it may be more troublesome to deal with the problem based on constraint solving. Even if the follow-up improvement of the constraint-based recommendation method is to gradually relax the constraints by calculating the conflicting requirements to obtain the solution, although the requirement conflict and empty solution are avoided, but due to Relaxing the constraints may lead to the infiltration of individual foods that are medically incompatible with the dietary standards of a certain diabetic patient into the recommended data set

[0004] Due to the irregular changes in the physical condition indicators of diabetic patients due to various reasons, some of the above traditional methods have certain limitations: (1) The traditional diabetic diet recommendation method is easy to lose some valuable information for diabetic patients in food selection. Food; (2) The traditional diabetic diet recommendation method treats diabetic patients in a universal way, ignoring the particularity of the patient; (3) The traditional diabetic diet recommendation method cannot balance the medical indicators and the wishes of diabetic patients, or blindly To pursue the patient's dietary preference characteristics to achieve personalized requirements, or to focus on medical standards, ignoring the patient's personalized dietary preference characteristics, causing patients to be disgusted and unable to eat, showing the effect of "pseudo-recommendation"

Images