Skip to content

金融相关PDF数据结构化提取,可迁移到其他领域

Notifications You must be signed in to change notification settings

Lin-A1/FinanInfoExt

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

开始前注意删除workspace/data.json

然后修改当前目录下的data.json的结构作为自己要提取的结构

请根据自己的数据的密集程度调整自己使用的模型的参数量大小-config/config2.yaml

{
    "product_info": {
        "product_name": "",           # 基金名称
        "product_abbreviation": "",   # 基金简称
        "product_code": "",           # 基金代码
        "management_company": "",     # 管理公司
        "product_type": "",           # 产品类型
        "custodian_institution": "",  # 托管机构(托管银行)
        "currency_type": "",          # 货币种类(发行货币)
        "start_issuance_date": "",    # 开始发行日期(募集开始日期)
        "end_issuance_date": "",      # 发行结束日期(募集结束日期)
        "issuance_scale": "",         # 发行规模
        "initial_minimum_subscription_amount": "",  # 首次最低认购金额
    },
    "risk_and_return": {
        "risk_return_characteristics": "",  # 风险收益特征
        "risk_control_measures": "",       # 风险管控措施
        "return_distribution_method": "",  # 收益分配方法
    },
    "regulatory_info": {
        "csrc_approval_number": "",        # 证监会批复编号
        "csrc_approval_date": "",          # 证监会批复日期
        "development_rules": "",           # 开发规则
        "open_frequency": "",              # 开放频率
    },
    "fees_and_expenses": {
        "management_fee": "",              # 管理费
        "sales_service_fee": "",          # 销售服务费
        "custodian_fee": "",              # 托管费
        "subscription_fee": "",           # 认购费
        "purchase_fee": "",               # 申购费
        "redemption_fee": "",             # 赎回费
    },
    "investment_info": {
        "investment_target": "",          # 投资目标
        "investment_scope": "",           # 投资范围
        "investment_objects": "",         # 投资对象
        "investment_ratio": "",           # 投资比例
        "portfolio_restrictions": "",     # 组合限制
        "prohibited_behaviors": "",       # 禁止行为
        "investment_limit_modifications": "",  # 投资限制修改
        "primary_investment_strategy": "",  # 主要投资策略
        "subscription_target": "",        # 募集对象
        "performance_benchmark": "",      # 业绩比较基准
    },
    "fund_manager": {
        "fund_manager_name": "",          # 基金经理
        "fund_manager_introduction": "",  # 基金经理介绍
    }
}

About

金融相关PDF数据结构化提取,可迁移到其他领域

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published