WO2017148161A1 - 用于评估保险标的风险的核保和精算数据库系统 - Google Patents

用于评估保险标的风险的核保和精算数据库系统 Download PDF

Info

Publication number
WO2017148161A1
WO2017148161A1 PCT/CN2016/103039 CN2016103039W WO2017148161A1 WO 2017148161 A1 WO2017148161 A1 WO 2017148161A1 CN 2016103039 W CN2016103039 W CN 2016103039W WO 2017148161 A1 WO2017148161 A1 WO 2017148161A1
Authority
WO
WIPO (PCT)
Prior art keywords
database
underwriting
actuarial
index
risk
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2016/103039
Other languages
English (en)
French (fr)
Inventor
张贯京
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Qianhai AnyCheck Information Technology Co Ltd
Original Assignee
Shenzhen Qianhai AnyCheck Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Qianhai AnyCheck Information Technology Co Ltd filed Critical Shenzhen Qianhai AnyCheck Information Technology Co Ltd
Publication of WO2017148161A1 publication Critical patent/WO2017148161A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0635Risk analysis of enterprise or organisation activities
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08Insurance

Definitions

  • the present invention relates to the field of data processing technologies, and in particular, to a underwriting and actuarial database system for evaluating risks of an insurance subject.
  • bioinformatics to carry out insurance products, which has led to an increased risk of assessing the subject matter of insurance.
  • bioinformatics we provide orderly data and related information with exponential growth. After analysis and collation, we can obtain new risk control concepts and innovative thinking from massive information.
  • bioinformatics software programming technology, actuarial technology, underwriting technology, and risk control technology as the background, it can comprehensively guide risk forecasting, utilize the latest bioinformatics technology, handle large amounts of information, and have fast conclusions, which can be applied to industries such as manual insurance. .
  • the main object of the present invention is to provide a underwriting and actuarial database system for evaluating the risk of an insurance target, which aims to solve the problem that the prior art cannot combine the bioinformatics technology to evaluate the insurance subject, and the insurance product cannot be combined with the human body to predict. Bio-information leads to technical problems with a higher risk of assessing the subject matter of insurance.
  • the present invention provides a underwriting and actuarial database system for evaluating the risk of an insurance subject.
  • the underwriting and actuarial database system for evaluating the risk of the subject-matter insured is installed and operated in a server, including a historical risk assessment index module, a realistic risk assessment index module, a predictive risk assessment index module, a financial risk rating index module, a biometric risk assessment index module, a nuclear insurance index module, and an actuarial rate index module, the server invoking the underwriting and actuarial database system by executing a underwriting and actuarial software system
  • the data information of each module calculates the insurance premium and the service content.
  • the historical risk assessment index module comprises: a group life table database, a family genetic database, a family disease database, an individual past medical history database, an individual growth environment database, a living area infectious disease incidence index database, and Behavior-related life information database and disease burden information library.
  • the real risk assessment index module includes an air pollution index model of an individual living area, a vehicle quantity and a traffic accident occurrence index model, an individual implemented physical examination index database, an individual real biochemical indicator database, and an individual life.
  • the predictive risk assessment index module comprises a disease gene database and a disease protein database.
  • the financial risk rating index module includes a demand index function library, a financial condition index model, an implemented financial index model, and a income insured ratio model.
  • the biometric risk assessment index module includes an insured fingerprint database and an insured iris database for storing insured fingerprint information and iris information, respectively.
  • the underwriting index module is configured to store an index model related to underwriting, including a standard body core insurance index model, a secondary standard body core insurance index model, an extended warranty index model, a refusal index model, and Underwriting composite index model.
  • an index model related to underwriting including a standard body core insurance index model, a secondary standard body core insurance index model, an extended warranty index model, a refusal index model, and Underwriting composite index model.
  • the actuarial rate index module is used to store data related to actuarial rate, including a multi-function life function library, an interest function library, a basic annuity database, an actuarial present value database, a policy cash value database, and a reimbursement Capability index model.
  • the underwriting and actuarial database system for assessing the risk of insurance targets of the present invention establishes a predictive risk assessment index module by using a database and an index, and uses the latest biological information to combine historical risks. Evaluation Index Module, Reality Risk Assessment Index Module, Financial Risk Rating Index Module, Biometric Risk Assessment Index Module, Underwriting Index Module and Actuarial Rate Index Module to assess the risk of the subject matter of insurance, combined with the above factors Underwriting and actuarializing the subject-matter insured reduces the probability of assessing the risk of the subject-matter.
  • FIG. 1 is a schematic diagram of a preferred embodiment of the underwriting and actuarial database system operating environment for assessing the risk of an insurance subject
  • FIG. 2 is a schematic diagram of the functional modules of a preferred embodiment of the underwriting and actuarial database system for assessing the risk of an insurance subject.
  • the present invention provides a underwriting and actuarial database system for assessing the risk of an insurance subject, the system comprising seven risk assessment database modules, specifically a historical risk assessment index module, Reality risk assessment index module, predictive risk assessment index module, financial risk rating index module, biometric risk assessment index module, underwriting index module and actuarial rate index module.
  • FIG. 1 is a schematic diagram of a preferred embodiment of an operating environment of a underwriting and actuarial database system for assessing the risk of an insurance subject.
  • the operating environment includes a server 01 and a client 02, and the server 01 and the client 02 are connected through a network 03.
  • the client 02 performs data interaction with the server 01 via the network 03.
  • the underwriting and actuarial database system 100 for assessing the risk of an insurance target is run in a server 01, through which the client 02 can access a core running in the server 01 for assessing the risk of an insurance target Preserving the actuarial database system 100.
  • the server 01 further comprises a underwriting and actuarial software system 200 that invokes the data information in the underwriting and actuarial database system 100 for assessing the risk of the insurance target by means of a database link.
  • the existing insurance underwriting and actuarial algorithms are used to calculate insurance premiums and service content.
  • FIG. 2 is a functional block diagram of a preferred embodiment of the underwriting and actuarial database system for assessing the risk of an insurance subject.
  • the core for evaluating the risk of the insurance target The Bohol Actuarial Database System 100 includes seven risk assessment database modules, specifically a historical risk assessment index module 10, a realistic risk assessment index module 20, a predictive risk assessment index module 30, and a financial risk rating index model. Group 40, biometric risk assessment index module 50, underwriting index module 60, and actuarial rate index module 70.
  • the historical risk assessment index module 10 includes, but is not limited to, a group life table database 101, a family genetic database 102, a family disease database 103, an individual past history database 104, an individual growth environment database 105, The living area infectious disease incidence index database 106, the behavior-related life information database 107, and the disease burden information database 108.
  • the above databases and information bases can be established by existing algorithms and data models, and will not be described in detail in the present invention.
  • the real risk assessment index module 20 includes an air pollution index model 201 of an individual living area, a vehicle quantity and a traffic accident occurrence rate index model 202, an individual implementation physical examination index database 203, and an individual real biochemical indicator database 204.
  • the predictive risk assessment index module 30 includes a disease gene database 301 and a disease protein database 312.
  • the early onset of disease predicts the use of molecular markers.
  • molecular markers fall into two categories, one is the prediction of disease occurrence based on mutations, deletions, and methylation of specific genes in specific diseases.
  • the abnormal methylation of the RASSF1A-encoding gene is used to predict the occurrence of non-small cell lung cancer; the BRC A gene mutation predicts the high incidence of breast cancer.
  • genetic testing is the main killer of human cardiovascular disease and cancer. In the very early stage, the anti-cancer genes and oncogenes are detected to be defective, and the probability of onset is high.
  • the gene detection technology has been relatively mature, and it is possible to use the AMICAP technology to manufacture IgY gene antibodies, and to develop "gene antibodies" for various liver diseases, Helicobacter pylori diseases and cardiovascular diseases.
  • Some genes are originally weak due to heredity, but if they are in an inappropriate environment, they are very susceptible to disease.
  • a daughter born to a mother of breast cancer is 15 times more likely to have breast cancer than a normal person.
  • People with detoxification genes such as CYP and G ST in the liver often eat stinky tofu, preserved food, and smoke, drink, etc. habit, The chance of developing liver cancer is 60 times higher than that of the average person.
  • the above factors are used as predictive letters to evaluate the index, which is sufficient to accurately assess the subject matter of insurance and reduce the risk of underwriting.
  • the latest research findings have found that the genetic susceptibility genes of hepatitis B help to predict the risk of hepatitis B. If the Apo E gene on the 19th chromosome is defective, it is easy to suffer from heart disease and Alzheimer's disease (dementia in the elderly). If the CETP gene on the 16th chromosome has a problem, it is easy to be arteriosclerosis, vascular embolism, and myocardial infarction. These genes can be detected by genetic testing.
  • CETP is B1/B1 type
  • blood fat is very easy to stick to the blood vessel wall, which is a high risk group of hardening and embolization of blood vessels. This kind of person accounts for 25%-30 ⁇ 3 ⁇ 4 of the population.
  • the other type predicts the occurrence of disease based on changes in the expression of specific proteins or post-translational modifications. For example: Increased expression of alpha-fetoprotein AFP predicts the occurrence of liver cancer; interferon IFN-r detection predicts the occurrence of tuberculosis; expression of CEA, CA242 and other proteins is used to predict the occurrence of pancreatic cancer.
  • the present invention comprehensively utilizes the latest bioinformatics technology to incorporate early disease prediction into the risk assessment of the subject matter of insurance, which can reduce the risk of assessing the subject matter of insurance.
  • the financial risk rating index module 40 includes a demand index function library 401, a financial status index library 502, an implementation financial index library 403, and a revenue insured ratio model 404.
  • a demand index function library 401 For example: As China's economy continues to grow, the demand index function is increasingly used for health and life insurance. Health, life and education are the main components of human capital, and stability, health and health investments can directly increase social productivity. Therefore, studying the needs of life insurance and health insurance has important economic and social significance, and is more realistic for insurance companies and actuaries.
  • the present invention proposes a method for estimating life, health insurance demand function and health service demand function in China. Life, health insurance and health services are two different concepts that are closely related.
  • the invention uses internationally accepted The model, under the framework of human capital, estimates the demand function of China's life insurance. It is impossible for people to directly purchase the health of a unit or the life of a year, but people may directly purchase health insurance or life insurance for one unit (one).
  • the need for stability, health and longevity is achieved through factors such as health services and insurance services. To understand the need for stability, health and longevity, research on the demand for health services and insurance services is indispensable.
  • the present invention also estimates the demand function of health services and insurance services and a range of indicators associated with them, such as income elasticity of health services and insurance demand, price elasticity, and the like. Different experiments and measurement methods will be used to control the possible selectivity bias, endogenous bias and missing variable bias to distinguish the need for stability, health and longevity from institutional changes, and the impact on health and insurance service needs.
  • the biometric risk assessment index module 50 includes an insured fingerprint database 501 and an insured iris database 502 for storing fingerprint information and iris information of the insured, respectively.
  • the underwriting index module 60 is configured to store an index model related to underwriting, including a standard body core insurance index model 601, a secondary standard body core insurance index model 602, an extended warranty index model 603, and a refusal index model. 604 and the underwriting comprehensive index model 605.
  • the actuarial rate index module 70 is configured to store data related to actuarial rate, including a multi-function function library 701, an interest function library 702, a basic annuity database 703, an actuarial present value database 704, and a policy cash value database. 705 and the solvency index model 706 and the like.
  • the underwriting and actuarial database system for assessing the risk of insurance targets establishes a database and an index model, and uses the latest biological information to establish a predictive risk assessment index module, combined with a historical risk assessment index module, and reality.
  • the sexual Risk Assessment Index Module, the Financial Risk Assessment Index Module, the Biometric Risk Assessment Index Module, the Underwriting Rate Index Module, and the Actuarial Rate Index Module to assess the risk of the subject-matter insured, and the underwriting of the subject-matter insured in combination with the above factors And actuarial, reducing the probability of risk of insurance underwriting.
  • the underwriting and actuarial database system for assessing the risk of insurance targets of the present invention establishes a predictive risk assessment index module by using a database and an index, and uses the latest biological information to combine historical risks. Evaluation Index Module, Reality Risk Assessment Index Module, Financial Risk Rating Index Module, Biometric Risk Assessment Index Module, Underwriting Index Module and Actuarial Rate Index Module to assess the risk of the subject matter of insurance, combined with the above factors Underwriting and actuarializing the subject-matter insured reduces the probability of assessing the risk of the subject-matter.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Marketing (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Technology Law (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

一种用于评估保险标的风险的核保和精算数据库系统。该系统包括历史性风险评估指数模组(10)、现实性风险评估指数模组(20)、预测性风险评估指数模组(30)、财务风险等级评估指数模组(40)、生物识别风险评估指数模组(50)、核保指数模组(60)以及精算费率指数模组(70)。通过建立数据库和指数模型,利用最新生物信息建立预测性风险评估指数模组(30),结合历史性风险评估指数模组(10)、现实性风险评估指数模组(20)、财务风险等级评估指数模组(40)、生物识别风险评估指数模组(50)、核保指数模组(60)以及精算费率指数模组(70)来综合评估保险标的风险,结合上述因素对保险标的进行核保和精算,降低了评估保险标的风险的概率。

Description

说明书 发明名称:用于评估保险标的风险的核保和精算数据库系统 技术领域
[0001] 本发明涉及数据处理技术领域, 尤其涉及一种用于评估保险标的风险的核保和 精算数据库系统。
背景技术
[0002] 保险行业在近年来的发展越发迅猛, 各种保险产品层出不穷, 但是大都没有结 合生物信息学进行保险产品幵发, 导致对保险标的的评估风险加大。 若以生物 信息学为基础, 提供以指数增长的有序数据及相关信息, 经过分析与整理, 从 海量信息中可以获得新的风险控制理念和创新思维。 以生物信息技术、 软件编 程技术、 精算技术、 核保技术、 风险控制技术为背景, 可以全面指导性风险预 测、 利用最新生物信息技术、 处理信息量大、 结论快速、 可以应用于人手保险 等行业。
技术问题
[0003] 本发明的主要目的在于提供一种用于评估保险标的风险的核保和精算数据库系 统, 旨在解决现有技术不能结合生物信息技术评估保险标的, 导致保险产品不 能结合人体可预测的生物信息而导致保险标的评估风险较大的技术问题。
问题的解决方案
技术解决方案
[0004] 为实现上述目的, 本发明提供了一种用于评估保险标的风险的核保和精算数据 库系统。
[0005] 所述用于评估保险标的风险的核保和精算数据库系统安装并运行于服务器中, 包括历史性风险评估指数模组、 现实性风险评估指数模组、 预测性风险评估指 数模组、 财务风险等级评估指数模组、 生物识别风险评估指数模组、 核保指数 模组以及精算费率指数模组, 所述服务器通过执行核保和精算软件系统调用所 述核保和精算数据库系统中各个模组的数据信息计算保险标的保费以及服务内 容。 [0006] 优选地, 所述历史性风险评估指数模组包括, 群体生命表数据库、 家族遗传数 据库、 家族疾病数据库、 个体既往病史数据库、 个体生长环境数据库、 生活地 区传染病发病率指数数据库、 与行为有关的寿命信息库以及疾病负担信息库。
[0007] 优选地, 所述现实性风险评估指数模组包括个体生活地区大气污染指数模型、 机动车数量和交通事故发生率指数模型、 个体实施体检指标数据库、 个体实吋 生化指标数据库、 个体生活方式和社会学指数模型以及个体生活地区社会安定 和治安指数模型。
[0008] 优选地, 所述预测性风险评估指数模组包括疾病基因数据库和疾病蛋白质数据 库。
[0009] 优选地, 所述财务风险等级评估指数模组包括需求指数函数库、 财务状况指数 模型、 实施金融指数模型以及收入保额比值模型。
[0010] 优选地, 所述生物识别风险评估指数模组包括被保险人指纹数据库以及被保险 人虹膜数据库, 分别用于存储被保险人的指纹信息和虹膜信息。
[0011] 优选地, 所述核保指数模组用于存储与核保相关的指数模型, 包括标准体核保 指数模型、 次标准体核保指数模型、 延保指数模型、 拒保指数模型以及核保综 合指数模型。
[0012] 优选地, 所述精算费率指数模组用于存储于精算费率相关的数据, 包括多元生 命函数库、 利息函数库、 基础年金数据库、 精算现值数据库、 保单现金价值数 据库以及偿付能力指数模型。
发明的有益效果
有益效果
[0013] 相较于现有技术, 本发明所述用于评估保险标的风险的核保和精算数据库系统 通过建立数据库和指数, 利用最新生物信息建立预测性风险评估指数模组, 结 合历史性风险评估指数模组、 现实性风险评估指数模组、 财务风险等级评估指 数模组、 生物识别风险评估指数模组、 核保指数模组以及精算费率指数模组来 评估保险标的风险, 结合上述因素对保险标的进行核保和精算, 降低了评估保 险标的风险的概率。
对附图的简要说明 附图说明
[0014] 图 1是本发明用于评估保险标的风险的核保和精算数据库系统运行环境较佳实 施例示意图;
[0015] 图 2是本发明用于评估保险标的风险的核保和精算数据库系统较佳实施例的功 能模块示意图。
实施该发明的最佳实施例
本发明的最佳实施方式
[0016] 为更进一步阐述本发明为达成上述目的所采取的技术手段及功效, 以下结合附 图及较佳实施例, 对本发明的具体实施方式、 结构、 特征及其功效进行详细说 明。 应当理解, 此处所描述的具体实施例仅仅用以解释本发明, 并不用于限定 本发明。
[0017] 为实现本发明目的, 本发明提供了一种用于评估保险标的风险的核保和精算数 据库系统, 该系统包括七个风险评估数据库模组, 具体为历史性风险评估指数 模组、 现实性风险评估指数模组、 预测性风险评估指数模组、 财务风险等级评 估指数模组、 生物识别风险评估指数模组、 核保指数模组以及精算费率指数模 组。
[0018] 参照图 1所示, 图 1是本发明用于评估保险标的风险的核保和精算数据库系统的 运行环境较佳实施例示意图。 在本实施例中, 所述运行环境包括服务器 01和客 户端 02, 所述服务器 01和客户端 02之间通过网络 03连接。 所述客户端 02通过所 述网络 03与所述服务器 01进行数据交互。 所述用于评估保险标的风险的核保和 精算数据库系统 100运行于服务器 01中, 所述客户端 02可以通过所述网络 03访问 运行于所述服务器 01中的用于评估保险标的风险的核保和精算数据库系统 100。 可以理解地, 所述服务器 01还包括核保和精算软件系统 200, 该核保和精算软件 系统 200通过数据库链接方式调用用于评估保险标的风险的核保和精算数据库系 统 100中的数据信息, 并采用现有的保险核保和精算算法计算保险标的保费以及 服务内容。
[0019] 参考图 2所示, 图 2是本发明用于评估保险标的风险的核保和精算数据库系统较 佳实施例的功能模块示意图。 在本实施例中, 所述用于评估保险标的风险的核 保和精算数据库系统 100包括七个风险评估数据库模组, 具体为历史性风险评估 指数模组 10、 现实性风险评估指数模组 20、 预测性风险评估指数模组 30、 财务 风险等级评估指数模组 40、 生物识别风险评估指数模组 50、 核保指数模组 60以 及精算费率指数模组 70。
[0020] 具体地, 所述历史性风险评估指数模组 10包括, 但不仅限于, 群体生命表数据 库 101、 家族遗传数据库 102、 家族疾病数据库 103、 个体既往病史数据库 104、 个体生长环境数据库 105、 生活地区传染病发病率指数数据库 106、 与行为有关 的寿命信息库 107以及疾病负担信息库 108。 上述数据库和信息库可以通过现有 的算法及数据模型来建立, 本发明不作具体描述。
[0021] 所述现实性风险评估指数模组 20包括个体生活地区大气污染指数模型 201、 机 动车数量和交通事故发生率指数模型 202、 个体实施体检指标数据库 203、 个体 实吋生化指标数据库 204、 个体生活方式和社会学指数模型 205以及个体生活地 区社会安定和治安指数模型 206。 例如, 个人生活方式和社会学指数可以表示为 X, X=体格指数 BMI; 智力指数 IQ+EQ; 婚姻状况; 孩子数量; 抽烟饮酒习惯; 体育锻炼; 睡眠; 教育程度; 职业; 变迁; 社交情况; 住处与上班地点距离。
[0022] 所述预测性风险评估指数模组 30包括疾病基因数据库 301和疾病蛋白质数据库 3 02。 目前疾病的早期发病预测多利用分子标志物的手段, 总的来说分子标志物 分为两大类, 一类为根据特定疾病中特定基因的突变、 缺失、 甲基化预测疾病 的发生。 例如 RASSF1A编码基因异常甲基用来预测非小细胞肺癌的发生; BRC A基因突变则预示着乳腺癌的高发。 由基因检测数据为主, 采用基因检测对人类 健康主要杀手心脏血管疾病和癌症, 在非常早期就测得抗癌基因和致癌基因是 否有缺陷, 可能发病的几率有多大。 对于家族会有人罹患癌症或者心脏病者、 生活习惯不良者、 长期暴露在高度环境污染者, 都是很重要的健康指标。 基因 检测技术已经比较成熟, 可以利用 AMICAP技术、 制造 IgY基因抗体, 针对各种 肝病、 幽门杆菌因其的胃肠疾病以及心脏血管疾病研发的"基因抗体"。 一些基因 原本因为遗传就较弱, 但如果处在不当的环境中, 就很容易发病。 又例如: 乳 腺癌母亲所生的女儿罹患乳腺癌的几率是常人的 15倍, 肝脏内解毒基因 CYP、 G ST有缺陷的人, 如果又经常吃臭豆腐、 腌制食品以及抽烟、 喝酒等不良习惯, 发生肝癌的机会比一般人高 60倍。 将上述因素作为预测性封信啊评估指数, 育 够准确评估保险标的, 降低在核保吋的风险。 又例如: 乙肝带原者演变成肝癌 的机会是平常人的 223倍。 最新研究成果发现乙肝的遗传易感基因, 有助于对乙 肝进行风险预测。 如果第 19对染色体上的 Apo E基因有缺陷, 就容易罹患心脏病 和阿兹海默症 (老年人痴呆症) 。 如果第 16对染色体上的 CETP基因出问题, 容 易动脉硬化、 血管栓塞、 心肌梗塞。 这些基因都可通过基因检测检测出来。 血 液中男性荷尔蒙偏高以及 CYP基因、 GST谷胱甘肽转移酵素低落者, 容易患癌症 , 早检测可以早预防。 若检测数解毒基因有缺陷, 应通过改变生活习惯, 采用 健康饮食、 避免脆弱的基因变坏, 达到防癌的目的。 若检测出心血管 Apo E、 CETP基因有缺陷可预测出动脉粥状硬化、 中风、 心肌梗塞、 老年人痴呆症 的几率, 并及早采取预防措施。 例如检测出有 Apo E是四型的基因, 冠心病机会 是其他人的三倍, 如加上肥胖则增加到四倍, 病人应赶紧预防。 如检测出是 Apo E二型的基因, 则是幸运的少数人, 具有长寿的重要因子。 CETP若是 B1/B1型, 就是血脂肪极易沾粘在血管壁上, 是血管硬化栓塞的高危险群, 这种人占人口 2 5%-30<¾。 另一类则是根据特定蛋白质的表达或翻译后修饰水平的变化, 预测疾 病的发生。 比如: 甲胎蛋白 AFP的表达增加预示着肝癌的发生; 干扰素 IFN-r的 检测预测结核病的发生; CEA,CA242等蛋白质的表达用于预测胰腺癌的发生。 本发明综合利用最新的生物信息技术, 将疾病早期预测纳入到保险标的的风险 评估中, 能够降低对保险标的的评估风险。
所述财务风险等级评估指数模组 40包括需求指数函数库 401、 财务状况指数库 4 02、 实施金融指数库 403以及收入保额比值模型 404。 例如: 随着我国经济的持 续增长, 需求指数函数用于健康和人寿保险的支出不断增加。 健康、 生命和教 育一样, 是人力资本的主要组成部分, 安定、 卫生和健康投资可以直接提高社 会生产力。 因而研究人寿保险和健康保险的需求, 具有重要的经济和社会意义 , 对保险公司和精算更具现实意义。 本发明提出一种方法来估计我国的人寿、 健康保险需求函数和卫生服务需求函数。 人寿、 健康保险和卫生服务是各不相 同而又紧密联系的两个概念。 从经济学看来, 健康、 长寿是人们追求的产出, 而人寿保险、 健康保险和服务是取得这种产出的投入。 本发明运用国际通行的 模型, 在人力资本的框架下来估计我国的人寿健康保险的需求函数。 人们不可 能直接购买一个单位的健康或一年的寿命, 人们却可能直接购买一个单位 (一 份) 的健康保险或人寿保险。 人们对于安定、 健康和长寿的需求吋通过卫生服 务和保险服务等因素实现的。 要理解对人们对安定、 健康和长寿的需求, 就离 不幵对卫生服务和保险服务需求的研究。 本发明还估计卫生服务和保险服务的 需求函数以及与之相关的一系列指标, 例如卫生服务和保险需求的收入弹性、 价格弹性等等。 不同的实验和计量方法将用来控制可能发生的选择性偏差、 内 生性偏差和遗漏变量偏差, 来区分制度变化对安定、 健康和长寿的需求, 以及 对卫生、 保险服务需求产生的影响。
[0024] 所述生物识别风险评估指数模组 50包括被保险人指纹数据库 501以及被保险人 虹膜数据库 502, 用于分别存储被保险人的指纹信息和虹膜信息。
[0025] 所述核保指数模组 60用于存储与核保相关的指数模型, 包括标准体核保指数模 型 601、 次标准体核保指数模型 602、 延保指数模型 603、 拒保指数模型 604以及 核保综合指数模型 605。
[0026] 所述精算费率指数模组 70用于存储于精算费率相关的数据, 包括多元生命函数 库 701、 利息函数库 702、 基础年金数据库 703、 精算现值数据库 704、 保单现金 价值数据库 705以及偿付能力指数模型 706等。
[0027] 本发明提供的用于评估保险标的风险的核保和精算数据库系统通过建立数据库 和指数模型, 利用最新生物信息建立预测性风险评估指数模组, 结合历史性风 险评估指数模组、 现实性风险评估指数模组、 财务风险等级评估指数模组、 生 物识别风险评估指数模组、 核保指数模组以及精算费率指数模组来评估保险标 的风险, 结合上述因素对保险标的进行核保和精算, 降低了保险标的风险的概 率。
[0028] 基于上述用于评估保险标的风险的核保和精算数据库系统, 在进行保险标的风 险评估吋, 首先建立核保和精算数据库, 确定数据库中各个既定的函数、 指数 , 尤其在现有的数据库和指数模型的基础上, 增加最新的生物信息技术 (例如 : 基因检测、 蛋白质检测等) , 对保险标的进行健康预测, 从而降低评估保险 标的的风险。 [0029] 以上仅为本发明的优选实施例, 并非因此限制本发明的专利范围, 凡是利用本 发明说明书及附图内容所作的等效结构或等效功能变换, 或直接或间接运用在 其他相关的技术领域, 均同理包括在本发明的专利保护范围内。
工业实用性
[0030] 相较于现有技术, 本发明所述用于评估保险标的风险的核保和精算数据库系统 通过建立数据库和指数, 利用最新生物信息建立预测性风险评估指数模组, 结 合历史性风险评估指数模组、 现实性风险评估指数模组、 财务风险等级评估指 数模组、 生物识别风险评估指数模组、 核保指数模组以及精算费率指数模组来 评估保险标的风险, 结合上述因素对保险标的进行核保和精算, 降低了评估保 险标的风险的概率。
[0031]

Claims

权利要求书
一种用于评估保险标的风险的核保和精算数据库系统, 安装并运行于 服务器中, 其特征在于, 所述用于评估保险标的风险的核保和精算数 据库系统包括历史性风险评估指数模组、 现实性风险评估指数模组、 预测性风险评估指数模组、 财务风险等级评估指数模组、 生物识别风 险评估指数模组、 核保指数模组以及精算费率指数模组, 所述服务器 通过执行核保和精算软件系统调用所述核保和精算数据库系统中各个 模组的数据信息计算保险标的保费以及服务内容。
如权利要求 1所述的用于评估保险标的风险的核保和精算数据库系统
, 其特征在于, 所述历史性风险评估指数模组包括, 群体生命表数据 库、 家族遗传数据库、 家族疾病数据库、 个体既往病史数据库、 个体 生长环境数据库、 生活地区传染病发病率指数数据库、 与行为有关的 寿命信息库以及疾病负担信息库。
如权利要求 1所述的用于评估保险标的风险的核保和精算数据库系统
, 其特征在于, 所述现实性风险评估指数模组包括个体生活地区大气 污染指数模型、 机动车数量和交通事故发生率指数模型、 个体实施体 检指标数据库、 个体实吋生化指标数据库、 个体生活方式和社会学指 数模型以及个体生活地区社会安定和治安指数模型。
如权利要求 1所述的用于评估保险标的风险的核保和精算数据库系统
, 其特征在于, 所述预测性风险评估指数模组包括疾病基因数据库和 疾病蛋白质数据库。
如权利要求 1所述的用于评估保险标的风险的核保和精算数据库系统
, 其特征在于, 所述财务风险等级评估指数模组包括需求指数函数库 、 财务状况指数模型、 实施金融指数模型以及收入保额比值模型。 如权利要求 1所述的用于评估保险标的风险的核保和精算数据库系统
, 其特征在于, 所述生物识别风险评估指数模组包括被保险人指纹数 据库以及被保险人虹膜数据库, 分别用于存储被保险人的指纹信息和 虹膜信息。 [权利要求 7] 如权利要求 1所述的用于评估保险标的风险的核保和精算数据库系统
, 其特征在于, 所述核保指数模组用于存储与核保相关的指数模型, 包括标准体核保指数模型、 次标准体核保指数模型、 延保指数模型、 拒保指数模型以及核保综合指数模型。
[权利要求 8] 如权利要求 1所述的用于评估保险标的风险的核保和精算数据库系统
, 其特征在于, 所述精算费率指数模组用于存储于精算费率相关的数 据, 包括多元生命函数库、 利息函数库、 基础年金数据库、 精算现值 数据库、 保单现金价值数据库以及偿付能力指数模型。
PCT/CN2016/103039 2016-03-04 2016-10-24 用于评估保险标的风险的核保和精算数据库系统 Ceased WO2017148161A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610127976.4 2016-03-04
CN201610127976.4A CN105809343A (zh) 2016-03-04 2016-03-04 用于评估保险标的风险的核保和精算数据库系统

Publications (1)

Publication Number Publication Date
WO2017148161A1 true WO2017148161A1 (zh) 2017-09-08

Family

ID=56467735

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/103039 Ceased WO2017148161A1 (zh) 2016-03-04 2016-10-24 用于评估保险标的风险的核保和精算数据库系统

Country Status (2)

Country Link
CN (1) CN105809343A (zh)
WO (1) WO2017148161A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220058747A1 (en) * 2015-10-28 2022-02-24 Qomplx, Inc. Risk quantification for insurance process management employing an advanced insurance management and decision platform
TWI845343B (zh) * 2023-06-13 2024-06-11 國泰人壽保險股份有限公司 罹患疾病機率預測系統及罹患疾病機率預測方法

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105809343A (zh) * 2016-03-04 2016-07-27 深圳市前海安测信息技术有限公司 用于评估保险标的风险的核保和精算数据库系统
CN107705047B (zh) * 2017-11-08 2021-07-13 泰康保险集团股份有限公司 一种保险核保风险预测方法及装置
CN109285076A (zh) * 2018-02-07 2019-01-29 中国平安人寿保险股份有限公司 智能核保处理方法、服务器及存储介质
CN108765177B (zh) * 2018-06-14 2020-12-04 阳光保险集团股份有限公司 核保方法及核保系统
CN110119882A (zh) * 2019-04-12 2019-08-13 国家计算机网络与信息安全管理中心 一种平台风险监控方法、装置、设备及存储介质
CN110390424B (zh) * 2019-06-14 2022-05-17 平安科技(深圳)有限公司 测试对象的寿命预估方法、装置、设备及介质
CN111078684B (zh) * 2019-11-08 2023-07-18 泰康保险集团股份有限公司 保单故障的补偿方法、装置、介质及设备
CN112381655A (zh) * 2020-11-06 2021-02-19 中国人寿保险股份有限公司 一种检测逆选择投保的方法及装置
CN112926869B (zh) * 2021-03-12 2024-05-31 中国检验检疫科学研究院 植物检疫性有害生物出入境检验检疫安全风险评估系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1758281A (zh) * 2005-10-13 2006-04-12 徐汇丰 人寿保险公司对保险标的风险评估数据库系统
US20090048877A1 (en) * 2000-11-15 2009-02-19 Binns Gregory S Insurance claim forecasting system
CN101826193A (zh) * 2009-06-18 2010-09-08 张艳红 金融保险第三方海量数据与红指数池管理智能tpa平台
CN102999686A (zh) * 2011-09-19 2013-03-27 上海煜策信息科技有限公司 一种健康管理系统及其实现方法
CN105809343A (zh) * 2016-03-04 2016-07-27 深圳市前海安测信息技术有限公司 用于评估保险标的风险的核保和精算数据库系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090048877A1 (en) * 2000-11-15 2009-02-19 Binns Gregory S Insurance claim forecasting system
CN1758281A (zh) * 2005-10-13 2006-04-12 徐汇丰 人寿保险公司对保险标的风险评估数据库系统
CN101826193A (zh) * 2009-06-18 2010-09-08 张艳红 金融保险第三方海量数据与红指数池管理智能tpa平台
CN102999686A (zh) * 2011-09-19 2013-03-27 上海煜策信息科技有限公司 一种健康管理系统及其实现方法
CN105809343A (zh) * 2016-03-04 2016-07-27 深圳市前海安测信息技术有限公司 用于评估保险标的风险的核保和精算数据库系统

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220058747A1 (en) * 2015-10-28 2022-02-24 Qomplx, Inc. Risk quantification for insurance process management employing an advanced insurance management and decision platform
US12536593B2 (en) * 2015-10-28 2026-01-27 Qomplx Llc Risk quantification for insurance process management employing an advanced insurance management and decision platform
TWI845343B (zh) * 2023-06-13 2024-06-11 國泰人壽保險股份有限公司 罹患疾病機率預測系統及罹患疾病機率預測方法

Also Published As

Publication number Publication date
CN105809343A (zh) 2016-07-27

Similar Documents

Publication Publication Date Title
Zhao et al. Predicting outcomes of chronic kidney disease from EMR data based on Random Forest Regression
Silke et al. An improved medical admissions risk system using multivariable fractional polynomial logistic regression modelling
Taylor et al. Five factor model personality traits and all-cause mortality in the Edinburgh artery study cohort
Kishore et al. Clinical risk scores for predicting stroke-associated pneumonia: a systematic review
Schäfer et al. Toward machine-learning-based decision support in diabetes care: A risk stratification study on diabetic foot ulcer and amputation
Ramezankhani et al. Applying decision tree for identification of a low risk population for type 2 diabetes. Tehran Lipid and Glucose Study
WO2017148160A1 (zh) 基于生物信息的健康保险风险评估系统
Krause et al. Behavioral risk factors of mortality after spinal cord injury
Chen et al. Claims data-driven modeling of hospital time-to-readmission risk with latent heterogeneity
Dent et al. Nutritional screening tools and anthropometric measures associate with hospital discharge outcomes in older people
CN105809343A (zh) 用于评估保险标的风险的核保和精算数据库系统
Choudhury et al. Evaluating patient readmission risk: a predictive analytics approach
US20240355477A1 (en) Predicting newly incident chronic kidney disease
Mozaffarinya et al. A data-mining algorithm to assess key factors in asthma diagnosis
Ahmad et al. Estimation of annual probabilities of changing disability levels in Australians with relapsing-remitting multiple sclerosis
Trivedi et al. Evaluation of changes in Veterans Affairs Medical Centers’ mortality rates after risk adjustment for socioeconomic status
He et al. Development and validation of an interpretable machine learning for mortality prediction in patients with sepsis
Hosseini et al. Bridging genomics to cardiology clinical practice: artificial intelligence in optimizing polygenic risk scores: A systematic review
Zhang et al. Patient safety in hospitals–a bayesian analysis of unobservable hospital and specialty level risk factors
Salehnasab et al. Predictive modeling of COVID-19 hospitalization using twenty machine learning classification algorithms on cohort data.
Crespí et al. Application of a machine learning model for early prediction of in-hospital cardiac arrests: Retrospective observational cohort study
Li et al. Interpretable Machine Learning for Predicting Adverse Pregnancy Outcomes in Gestational Diabetes: Retrospective Cohort Study
Lazic et al. Improving drug safety predictions by reducing poor analytical practices
Willcox Chronic diseases in Australia: the case for changing course: background and policy paper
Peng et al. Using machine learning approach to predict short-term mortality risk of acute myocardial infarction after emergency admission

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16892342

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 01.02.2019)

122 Ep: pct application non-entry in european phase

Ref document number: 16892342

Country of ref document: EP

Kind code of ref document: A1