112 lines
3.4 KiB
Python
112 lines
3.4 KiB
Python
import jieba
|
||
from paddlenlp import Taskflow
|
||
from paddleocr import PaddleOCR
|
||
|
||
"""
|
||
项目配置
|
||
"""
|
||
# 每次从数据库获取的案子数量
|
||
PHHD_BATCH_SIZE = 10
|
||
# 没有查询到案子的等待时间(分钟)
|
||
SLEEP_MINUTES = 5
|
||
# 是否发送报错邮件
|
||
SEND_ERROR_EMAIL = True
|
||
# 是否开启布局分析
|
||
LAYOUT_ANALYSIS = False
|
||
|
||
"""
|
||
信息抽取关键词配置
|
||
"""
|
||
# 患者姓名
|
||
PATIENT_NAME = ["患者姓名"]
|
||
# 入院日期
|
||
ADMISSION_DATE = ["入院日期"]
|
||
# 出院日期
|
||
DISCHARGE_DATE = ["出院日期"]
|
||
# 发生医疗费
|
||
MEDICAL_EXPENSES = ["费用总额"]
|
||
# 个人现金支付
|
||
PERSONAL_CASH_PAYMENT = ["个人现金支付"]
|
||
# 个人账户支付
|
||
PERSONAL_ACCOUNT_PAYMENT = ["个人账户支付"]
|
||
# 个人自费金额
|
||
PERSONAL_FUNDED_AMOUNT = ["自费金额", "个人自费"]
|
||
# 医保类别
|
||
MEDICAL_INSURANCE_TYPE = ["医保类型"]
|
||
# 就诊医院
|
||
HOSPITAL = ["医院"]
|
||
# 就诊科室
|
||
DEPARTMENT = ["科室"]
|
||
# 主治医生
|
||
DOCTOR = ["主治医生"]
|
||
# 住院号
|
||
ADMISSION_ID = ["住院号"]
|
||
# 医保结算单号码
|
||
SETTLEMENT_ID = ["医保结算单号码"]
|
||
# 年龄
|
||
AGE = ["年龄"]
|
||
# 大写总额
|
||
UPPERCASE_MEDICAL_EXPENSES = ["大写总额"]
|
||
|
||
SETTLEMENT_LIST_SCHEMA = \
|
||
(PATIENT_NAME + ADMISSION_DATE + DISCHARGE_DATE + MEDICAL_EXPENSES + PERSONAL_CASH_PAYMENT
|
||
+ PERSONAL_ACCOUNT_PAYMENT + PERSONAL_FUNDED_AMOUNT + MEDICAL_INSURANCE_TYPE + ADMISSION_ID + SETTLEMENT_ID
|
||
+ UPPERCASE_MEDICAL_EXPENSES)
|
||
|
||
DISCHARGE_RECORD_SCHEMA = \
|
||
HOSPITAL + DEPARTMENT + PATIENT_NAME + ADMISSION_DATE + DISCHARGE_DATE + DOCTOR + ADMISSION_ID + AGE
|
||
|
||
COST_LIST_SCHEMA = PATIENT_NAME + ADMISSION_DATE + DISCHARGE_DATE + MEDICAL_EXPENSES
|
||
|
||
"""
|
||
别名配置
|
||
"""
|
||
# 使用别名中的value替换key。考虑到效率问题，只会替换第一个匹配到的key。
|
||
HOSPITAL_ALIAS = {
|
||
"沐阳": ["沭阳"],
|
||
"连水": ["涟水"],
|
||
"唯宁": ["睢宁"], # 雕宁
|
||
"九〇四": ["904"],
|
||
"漂水": ["溧水"],
|
||
}
|
||
DEPARTMENT_ALIAS = {
|
||
"耳鼻喉": ["耳鼻咽喉"],
|
||
"急症": ["急诊"],
|
||
}
|
||
|
||
"""
|
||
搜索过滤配置
|
||
"""
|
||
# 默认会过滤单字
|
||
HOSPITAL_FILTER = ["医院", "人民", "第一", "第二", "第三", "大学", "附属"]
|
||
|
||
DEPARTMENT_FILTER = ["医", "伤", "西", "新"]
|
||
|
||
"""
|
||
分词配置
|
||
"""
|
||
jieba.suggest_freq(("肿瘤", "医院"), True)
|
||
jieba.suggest_freq(("骨", "伤"), True)
|
||
jieba.suggest_freq(("感染", "性"), True)
|
||
jieba.suggest_freq(("胆", "道"), True)
|
||
jieba.suggest_freq(("脾", "胃"), True)
|
||
|
||
"""
|
||
模型配置
|
||
"""
|
||
SETTLEMENT_IE = Taskflow("information_extraction", schema=SETTLEMENT_LIST_SCHEMA, model="uie-x-base",
|
||
task_path="model/settlement_list_model", layout_analysis=LAYOUT_ANALYSIS, precision="fp16")
|
||
DISCHARGE_IE = Taskflow("information_extraction", schema=DISCHARGE_RECORD_SCHEMA, model="uie-x-base",
|
||
task_path="model/discharge_record_model", layout_analysis=LAYOUT_ANALYSIS, precision="fp16")
|
||
COST_IE = Taskflow("information_extraction", schema=COST_LIST_SCHEMA, model="uie-x-base", device_id=1,
|
||
task_path="model/cost_list_model", layout_analysis=LAYOUT_ANALYSIS, precision="fp16")
|
||
|
||
OCR = PaddleOCR(
|
||
device="gpu:0",
|
||
ocr_version="PP-OCRv4",
|
||
use_textline_orientation=False,
|
||
# 检测像素阈值，输出的概率图中，得分大于该阈值的像素点才会被认为是文字像素点
|
||
text_det_thresh=0.1,
|
||
# 检测框阈值，检测结果边框内，所有像素点的平均得分大于该阈值时，该结果会被认为是文字区域
|
||
text_det_box_thresh=0.3,
|
||
) |