Disclosed are a text content quality evaluation method, apparatus and device, and a storage medium, which relate to the technical field of artificial intelligence, and are used for improving the accuracy of text content quality evaluation. The method comprises: acquiring initial text from preset medical record text, wherein the initial text comprises chief complaint information, existing medical history information, physical examination information, first-time disease course record information, disease course record information, ward round record information and operation record information (101); performing text pre-processing on the initial text by means of a natural language processing algorithm to obtain target text (102); performing text coding on the target text by means of a preset bag-of-words model and a preset automatic coding model to obtain a first text feature (103); performing feature extraction on the target text to obtain second text features, wherein the second text features comprise a text complexity feature, a text syntax style feature and a medical semantic feature, and the feature extraction comprises calculating the number of each type of word, the ratio of each type of symbol and the ratio of each type of word (104); and performing evaluation processing on the first text feature and the second text features by means of a trained logistic regression model to obtain an evaluation result, wherein the evaluation result is used for identifying a content quality grade of the preset medical record text (105). The method also relates to blockchain technology, and the target text is stored in a blockchain.