70 lines
2.3 KiB
Python
70 lines
2.3 KiB
Python
from paddlenlp import Taskflow
|
|
from paddleocr import PaddleOCR
|
|
|
|
"""
|
|
项目配置
|
|
"""
|
|
# 项目奔溃的重试次数
|
|
RETRY_TIME = 1
|
|
# 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"]
|
|
# 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"]
|
|
|
|
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
|
|
|
|
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
|
|
|
|
"""
|
|
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(use_angle_cls=False, lang="ch", show_log=False, gpu_id=1)
|