Medical corpus labeling method

Abstract

The invention provides a medical corpus labeling method, which comprises the following steps: registering an account, and allocating a task to a user; wherein the labeling interface presents the original corpus, and the user finds the corresponding option according to the original corpus to perform single selection; if there is no standard result in the plurality of options, inputting needing to be the same as the normal ICD9 and ICD10 coding dictionaries under the options; allowing the user to mark the selected result; if the corpus is marked as the composite corpus, performing splitting on asplitting interface, and setting a splitting list; if the corpus is labeled as a normal corpus, setting the corpus as a normal labeling list, otherwise, setting the corpus as a discarding list; if the corpus is an unrecognizable corpus, marking the corpus as a question corpus; after checking is completed, determining that tasks are submitted without errors; sharing and deriving inspection results. According to the method, the medical corpus can be normalized, and the generated data can provide a convenient method, a unified process and an efficient progress for informatization of the medicaldata.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a medical corpus labeling method. Background technique [0002] In today's era of gradual medical informatization, if you want to incorporate medical information into big data, you must standardize it. Because many kinds of disease names are too difficult to remember and not easy to pronounce, doctors will simplify or colloquialize the disease names when entering patient information, resulting in irregular information, poor versatility, and inconvenient query. The job of medical record coders is to standardize these non-standard information, but the manual speed is slow, the workload is heavy, and the classification is not clear, resulting in low work efficiency. Contents of the invention [0003] The aim of the present invention is to solve at least one of said technical drawbacks. [0004] For this reason, the object of the present invention is to propose a kind of ...

AI Technical Summary

Problems solved by technology

Because many kinds of disease names are too difficult to remember and not easy to pronounce, doctors will simplify or colloquialize the disease names when entering patient information, resulting in irregular information, poor versatility, and inconvenient query

The job of medical record coders is to standardize these non-standard information, but the manual speed is slow, the workload is heavy, and the classification is not clear, resulting in low work efficiency

Images