Prescription recommendation method based on tongue image retrieval

Abstract

The invention discloses a prescription recommendation method based on tongue image retrieval, and the method comprises the following steps: S1, enabling a server to analyze prescription information of a database, and carrying out the vectorization expression of a prescription; s2, performing training to obtain a feature extractor of the tongue picture according to the vector representation of the prescription; s3, using a feature extractor to pre-extract the feature vector of each tongue picture in the database; s4, enabling the client to submit a tongue picture to be queried; s5, enabling the server to use a feature extractor to extract a feature vector of the query tongue picture; s6, enabling the server to use a similarity calculation module to calculate the feature similarity between the query tongue picture and each tongue picture in the database; and S7, enabling the server to use a prescription recommendation module to perform sorting according to the feature similarity calculated in the S6, and return the prescriptions corresponding to the K tongue pictures with relatively high similarity to the client. According to the method, deep learning and prescription recommendation are combined, and the prescription recommendation method based on the tongue picture is realized for the first time.

Description

technical field [0001] The invention relates to image retrieval in the field of computer vision, target detection and prescription recommendation in the field of traditional Chinese medicine, in particular to a prescription recommendation method based on tongue image retrieval. Background technique [0002] In the era of rapid development of artificial intelligence technology, the diagnosis of TCM diseases mainly relies on the rich knowledge and experience of experts. As the case database grows day by day, intelligent assisted medical treatment is an inevitable trend based on historical case information. However, due to the large amount of case data, manual search for reference cases becomes time-consuming and laborious. Therefore, how to apply artificial intelligence technology to effectively retrieve cases similar to the current patient from the database, and assist doctors in assisting the diagnosis of the patient's condition, especially intractable diseases, has become ...

AI Technical Summary

Problems solved by technology

[0005] However, currently no prescription recommendation method takes into account the dosage information in the prescription, and the current prescription recommendation method has the following shortcomings

A method for recommending traditional Chinese medicinal materials based on deep neural network (public number 108182967A) uses tongue pictures to recommend medicinal materials, but there is no guarantee that the recommended medicinal materials can form an effective prescription

Images