Chinese patent medicine recommendation system and method based on deep learning

Abstract

The invention discloses a Chinese patent medicine recommendation system based on deep learning, which belongs to the technical field of medicines and comprises a chief complaint library, a tongue coating image library, an inquiry history database, a Chinese patent medicine library, a data acquisition module, a deep learning module, a user information receiving module, a chief complaint / image uploading module, an inquiry question library, a medicine recommendation module and a feedback module. Compared with an existing medicine recommendation method based on electronic medical records, various detection operations such as blood drawing and testing are not needed, the method does not depend on previous diagnosis (namely the electronic medical records), the method is a medicine scheme based on traditional Chinese medicine dialectical experience, an inquiry question library is distributed for a patient only through inquiry, namely according to the complaint of the patient, and the patient answers each inquiry question, and inputs an inquiry result into the trained AI model to obtain a most suitable Chinese patent medicine recommendation result. In addition, the tongue coating picture is used as a training and detection basis, and the Chinese patent medicine recommendation precision is further improved.

Description

technical field [0001] The invention relates to the field of medical technology, in particular to a system and method for recommending Chinese patent medicines based on deep learning. Background technique [0002] After retrieval, Chinese Patent No. CN109087691A discloses an over-the-counter drug recommendation system and recommendation method based on deep learning. Although the invention can provide patients with progressive drug recommendations through electronic medical records, it depends on previous diagnoses (ie, electronic medical records), and now There is a serious problem of hospital information islands, so it is difficult to obtain; Chinese patent medicines, under the guidance of traditional Chinese medicine theory, use Chinese herbal pieces as raw materials, and make dosage forms with certain specifications according to prescribed prescriptions and standards; It is more and more widely used in clinical practice; at present, when ordinary patients have symptoms s...

AI Technical Summary

Problems solved by technology

[0002] After retrieval, Chinese Patent No. CN109087691A discloses an over-the-counter drug recommendation system and recommendation method based on deep learning. Although the invention can provide patients with progressive drug recommendations through electronic medical records, it depends on previous diagnoses (ie, electronic medical records), and now There is a serious problem of hospital information islands, so it is difficult to obtain; Chinese patent medicines, under the guidance of traditional Chinese medicine theory, use Chinese herbal pieces as raw materials, and make dosage forms with certain specifications according to prescribed prescriptions and standards; It is more and more widely used in clinical practice; at present, when ordinary patients have symptoms such as cold, fever, cough, diarrhea or toothache, they often first give priority to seeking help from the nearest community pharmacy, and most pharmacists in pharmacies I was born as a western pharmacist, and I don't have a rigorous and comprehensive grasp of the syndrome differentiation theory and professional knowledge of Chinese medicine. In addition, there are many varieties of Chinese patent medicines. Pharmacists often recommend Chinese patent medicines with higher gross profit due to their own interests and other reasons. Therefore, It is difficult for most ordinary patients to obtain a truly efficient TCM syndrome differentiation treatment plan, and with the continuous development of Internet medical services and express delivery services, more and more people choose to conduct pharmacy consultations and purchase medicines online, but because Internet medical services cannot In the absence of evidence-based data, it is difficult for doctors to make a correct diagnosis of diseases when completing offline blood tests and other equipment testing operations; therefore, it is particularly important to invent a Chinese patent medicine recommendation system and method based on deep learning ;

[0003] Most of the existing drug recommendation systems and recommendation methods rely on previous diagnosis (ie, electronic medical records) for recommendation, but electronic medical records need to go to the hospital for a comprehensive examination to obtain, and due to the serious problem of existing hospital information islands, in general other The platform or system cannot directly obtain electronic medical records, and the existing drug recommendation system only recommends drugs based on text descriptions, and its recommendation accuracy is low; therefore, we propose a Chinese patent medicine recommendation system and method based on deep learning

Images