Medical record symptom recognition method and system based on dependency syntactic analysis
A technology that relies on syntax and recognition methods, applied in the field of intelligent medical care, can solve problems such as inability to obtain medical record symptoms, failure to consider entity dependencies, etc., and achieve the effect of deepening understanding
Inactive Publication Date: 2020-05-01
NANJING NEW GENERATION ARTIFICIAL INTELLIGENCE RES INST CO LTD
View PDF2 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In medical records, it often occurs that subject + multiple predicates, that is, multiple symptoms of one organ or tissue occur at the same time, or multiple subjects + the same predicate, that is, multiple organs or tissues have one symptom. When multiple symptoms occur in the same medical entity , the former method cannot obtain the symptoms of each subdivision in the medical record; although the latter recognizes the relationship between medical entities, it does not take into account the dependencies between entities and the semantic relationship in sentences
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0030] In order to allow the skilled person to better understand the present invention, the present invention will be described in detail below in conjunction with specific embodiments.
[0031] Such as Image 6 As shown, a schematic flow diagram of a method for identifying symptoms in medical records based on dependency syntax analysis includes the following steps:
[0032] Step 1: Medical entity identification: Mark the entities that indicate symptoms in the medical record, including the organs and tissues where the disease occurred, and words describing the disease; if the number of identified medical entities is less than 2, it is a simple case and the symptoms are displayed directly. If the number of medical entities identified is ≥2, proceed to the next step;
[0033] Step 2: Syntax analysis of inter-entity dependence: Perform syntactic relationship analysis on the medical entities marked in step 1, and determine the syntactic structure between entities, that is, the dependenc...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a medical record symptom recognition method based on dependency syntactic analysis, which comprises the following steps: step 1, medical entity recognition: marking entities representing symptoms in a medical record, which comprises diseased organs, tissues and words describing the diseased conditions; if the number of the identified medical entities is smaller than 2, themedical entities are simple cases, symptoms are directly displayed, If the number of the identified medical entities is larger than or equal to 2, the next step is executed; step 2, inter-entity dependency syntactic analysis: performing syntactic relationship analysis on the medical entities marked in the step 1, and determining syntactic structures between the entities, i.e., dependency relationships between the entities; 3, entity combination: combining the medical entities according to the dependency relationship between the entities determined in the step 2 to obtain symptoms; and step 4,sequence-to-sequence symptom mapping: performing standard statement mapping on the symptom statement obtained in the step 3. The invention further discloses a medical record symptom recognition systembased on dependency syntactic analysis.
Description
Technical field [0001] The invention belongs to the field of intelligent medical treatment, and is particularly oriented to symptom recognition in medical medical records, and specifically relates to a medical medical record symptom recognition method and system based on dependency syntax analysis. Background technique [0002] With the rapid development of artificial intelligence, artificial intelligence virtual assistants and medical imaging-assisted diagnosis are gradually applied in the medical field, bringing new value to many links in the medical and health field. The development of medical artificial intelligence will greatly alleviate the shortage of medical resources. This situation has brought about a new model of medical services, reducing the burden on doctors and improving service efficiency. In the process of intelligent assisted diagnosis and treatment, medical history analysis is an indispensable part. The medical record is the information obtained by the clinici...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F40/211G06F40/295G06F16/35G16H10/60
CPCG06F16/355G16H10/60
Inventor 张丹石霖董晓飞曹峰孙明俊
Owner NANJING NEW GENERATION ARTIFICIAL INTELLIGENCE RES INST CO LTD