Department recommendation method and device, electronic equipment and storage medium

Abstract

The invention relates to the field of artificial intelligence, and discloses a department recommendation method which comprises the following steps: cleaning inquiry data in an inquiry text to obtain a standard text; recognizing disease entities in the standard text by using a disease entity recognition model, then constructing an entity relation graph, generating a first disease entity according to the entity relation graph, screening the disease entities from the standard text by using a disease entity regular expression, calculating the matching degree between the screened disease entities and the disease entities in the disease entity dictionary database, and generating a second disease entity according to the matching degree; collecting the first disease entity and the second disease entity after dimension reduction, calculating the correlation degree between the collected disease entities and the departments in the medical department library, selecting the departments with the correlation degree larger than the preset correlation degree from the medical departments, and obtaining a target department. In addition, the invention also relates to a block chain technology, and the target disease entity can be stored in a block chain. According to the invention, the department recommendation difficulty can be reduced.

Description

Technical field [0001] The present invention relates to the field of artificial intelligence, and in particular, to a department recommendation method, apparatus, electronic device, and computer readable storage medium. Background technique [0002] The continuous development and improvement of artificial intelligence technology, greatly enriched and convenient for people's daily lives. For example, in the medical field, many hospitals have configured machines that include intelligent trainee services, the purpose is to achieve online intelligent trainee functions through Internet technology platforms and machine learning, statistical learning methods, with data-driven methods, to patient recommendation The departments and doctors have led to the maximum subjective initiative of the personnel, making it effective and accurately to find the medical services they need. At the same time, online consultation platforms also have an urgent intelligent guided demand, the number of consu...

AI Technical Summary

Problems solved by technology

First, because many medical institutions tend to be more detailed and specialized in the division of departments for different diseases, and the names of departments in different hospitals are different, and the general patients lack professional medical knowledge, which leads to the relationship between patient knowledge and medical terminology and hospitals. Information asymmetry increases the difficulty of guidance; second, current guidance services are usually based on statistical or text classification methods for department and doctor recommendations, but statistical methods cannot provide personalized recommendation strategies based on patients' own symptoms , and the latter is difficult to distinguish the noise data in the text and extract key medical factors (diseases, symptoms, etc.), which will also add a certain degree of difficulty to the guidance

Images