Modeling method for parallel smart case recommendation model

Abstract

The invention relates to a modeling method for a parallel smart case recommendation model. The method comprises the following steps of obtaining existing patient cases from an electronic case database, carrying out denoising, clustering and word segmentation on the patient cases, and establishing a patient case corpus database; defining that TFIDFi, j shows the importance degree of a word or an expression in a case of the patient case corpus database, establishing an LSI vector space model according to the TFIDFi, j, and moreover, establishing a BOW word bag model according to all words and expressions in the patient case corpus database; calculating history case vectors and to-be-processed case vectors in the patient case corpus database through utilization of the LSI vector space model and the BOW word bag model; calculating cosine similarity among the history patient cases and storing the cosine similarity; and calculating the cosine similarity between the to-be-processed case vectors and the history patient case vectors, and searching similar cases of to-be-processed cases according to the cosine similarity. The model established through adoption of the method provided by the invention is high in accuracy and low in error. A recommendation result is high in quality.

Description

technical field [0001] The invention relates to the technical field of medical data mining, and relates to a case recommendation model for auxiliary diagnosis, in particular to a modeling method of the case recommendation model. Background technique [0002] In their daily work, doctors often need to refer to the treatment plan of existing cases according to the symptoms of current patients. The patient's sign data and inspection data together constitute a multi-dimensional disease feature vector. Searching for similar cases means finding matching feature vectors from a huge case database. Obviously, the traditional keyword-based search method cannot meet the needs of multi-dimensional features. Match and make recommendations on demand. [0003] On the other hand, as an important process of database knowledge discovery, data mining technology has been widely used in many fields, such as e-commerce, social network, advertisement recommendation, search engine, etc. Classific...

AI Technical Summary

Problems solved by technology

[0008] (1) The user's behavior data has a large sparsity and poor accuracy;

[0009] (2) It is difficult to quickly respond to new user behaviors. If you want to respond to new user behavior records, you must recalculate the user-user or item-item similarity matrix, and the calculation time complexity of these two matrices is very high. , need to traverse the entire user-item matrix;

[0010] (3) The scalability is poor. As the number of users or items increases, the user-item matrix and the similarity matrix continue to increase. In the end, the recommendation system will not be able to continue to use due to insufficient space or too long calculation time. ;

[0012] (5) Due to the lack of sufficient and accurate historical data, the system recommended poor quality at the beginning

Images