WO2020000803A1 - Procédé et appareil de règlement d'indemnisation d'assurance, dispositif informatique et support de stockage lisible - Google Patents

Procédé et appareil de règlement d'indemnisation d'assurance, dispositif informatique et support de stockage lisible Download PDF

Info

Publication number
WO2020000803A1
WO2020000803A1 PCT/CN2018/111379 CN2018111379W WO2020000803A1 WO 2020000803 A1 WO2020000803 A1 WO 2020000803A1 CN 2018111379 W CN2018111379 W CN 2018111379W WO 2020000803 A1 WO2020000803 A1 WO 2020000803A1
Authority
WO
WIPO (PCT)
Prior art keywords
insurance
data
originating user
storage location
reference data
Prior art date
Application number
PCT/CN2018/111379
Other languages
English (en)
Chinese (zh)
Inventor
顾宝宝
Original Assignee
平安科技（深圳）有限公司
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 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2020000803A1 publication Critical patent/WO2020000803A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION 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
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08—Insurance

Definitions

  • the present application relates to the field of computer technology, and in particular, to an insurance compensation method and device, computer equipment, and a readable storage medium.
  • the embodiments of the present application provide an insurance compensation method and device, computer equipment, and readable storage medium, which are used to solve the problem of large consumption of human resources costs in the prior art that depends on the subjective determination of the claim amount by humans. .
  • an embodiment of the present application provides an insurance compensation method, including:
  • the claim reference data includes at least one of physical condition data, asset condition data, and accident-related data;
  • an insurance payment is made to the originating user.
  • an insurance compensation device including:
  • An obtaining unit configured to obtain claims reference data of an originating user of the insurance claim application, wherein the claims reference data includes at least one of physical condition data, asset condition data, and accident-related data;
  • a processing unit configured to process the claim reference data of the originating user by using a machine learning algorithm to obtain a claim reference amount of the originating user;
  • a compensation unit is configured to perform insurance compensation for the originating user according to the claim reference amount.
  • the present application provides a computer device including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, wherein the processor executes all When describing computer-readable instructions, the following steps are implemented:
  • the claim reference data includes at least one of physical condition data, asset condition data, and accident-related data;
  • an insurance payment is made to the originating user.
  • the present application provides a computer non-volatile readable storage medium storing computer-readable instructions, which is characterized in that when the computer-readable instructions are executed, the following steps are performed:
  • the claim reference data includes at least one of physical condition data, asset condition data, and accident-related data;
  • an insurance payment is made to the originating user.
  • the claim reference data of the originating user is obtained, and based on these claim reference data, based on the machine learning algorithm, the claim reference amount is directly obtained, reducing staff work. Compared with manual labor, the error of the compensation reference amount obtained based on the user's compensation reference data is smaller. Therefore, the technical solution provided by the present application can solve the problem that the consumption of human resources cost is relatively large in the prior art, which depends on the subjective determination of the claims.
  • FIG. 1 is a flowchart of an optional insurance payment method according to an embodiment of the present application
  • FIG. 3 is a flowchart of an optional insurance payment method provided by an embodiment of the present application.
  • FIG. 4 is a functional block diagram of an optional insurance compensation device according to an embodiment of the present application.
  • FIG. 5 is a functional block diagram of an optional computer device according to an embodiment of the present application.
  • the word “if” as used herein can be interpreted as “at” or “when” or “responding to determination” or “responding to detection”.
  • the phrases “if determined” or “if detected (the stated condition or event)” can be interpreted as “when determined” or “responded to the determination” or “when detected (the stated condition or event) ) “Or” in response to a test (statement or event stated) ".
  • the embodiments of the present application provide the following solution:
  • an insurance claim application initiated by any user is received,
  • the error of the reference amount of claims is even smaller.
  • the embodiment of the present application provides a method for insurance compensation. Please refer to FIG. 1, the method may include the following steps:
  • the claim reference data includes at least one of physical condition data, asset condition data and accident-related data.
  • the physical condition data involved in this application is used to characterize a user's physical health condition.
  • the physical condition data may include, but is not limited to, at least one of medical records, family medical history, personal injury records, historical body insurance purchases and claims records.
  • the asset status data involved in this application is used to characterize the user's asset status, such as whether they are in debt, whether they are loans, and whether the transaction credit is good.
  • the asset status data may include, but is not limited to, at least one of transaction credit data, payment records, loan records, asset transaction data, and shopping transaction data;
  • the accident-related data involved in the embodiments of the present application is used to characterize data related to the accident and its site.
  • the accident-related data may include, but is not limited to, at least one of accident liability determination data and accident scene description data.
  • the accident scene description data may be text descriptions, pictures, or multimedia data, which is not particularly limited in the embodiment of the present application.
  • S108 Perform insurance compensation for the initiating user according to the reference amount of claim settlement.
  • Step S104 includes:
  • S1042 Identify whether the storage location of the claim reference data of the originating user is its own storage location.
  • the storage location of the claims reference data of the originating user can be obtained, and then, the storage location of the originating user's claims is searched according to the path of the storage location. , It is determined that the storage location is its own storage location; otherwise, if the claim reference data of the originating user cannot be found according to the path, the storage location is determined to be a non-self storage location.
  • the self-storage location referred to in the embodiment of the present application refers to the storage location in its own storage space, or the storage location belongs to other storage locations under the control of the current device, for example, a mobile hard disk device controlled by the current device.
  • the storage location is under the control of the current device, and the data can be recalled directly from its own storage location without having to request data from other devices.
  • this method can also be combined with blockchain technology. Specifically, if the device currently executing the insurance payment method is used as a node on a blockchain, the claim reference data is stored in its own storage location on the current device, so based on the security of the blockchain In the verification scheme, the identity of the current device can be verified through the blockchain, so that when the identity verification of the current device passes, the reference data for claims can be obtained by directly downloading.
  • S1044B When the storage location is not its own storage location, send a data call request carrying the insurance claim request to the storage location; and receive the claim reference data fed back by the storage location according to the data call request.
  • the non-self storage location involved in the embodiments of the present application means that the storage location is not under the control of the current device, and therefore, the data cannot be directly called or read. Therefore, it can be obtained by sending a data calling request to the storage location. These data.
  • the device currently executing the insurance payment method may not store the data. Therefore, a data call request carrying the insurance payment request may be sent to the hospital server, so that the hospital server can The insurance payment request confirms that the device has data calling authority. In this way, the hospital server can feed back the medical record data stored in the hospital to the device.
  • a data call request carrying an insurance payment request may be sent to a bank, a lending institution, and a hospital storing the transaction credit data of the user, and thus, the servers of these institutions After confirming the data calling authority based on the insurance claim, the transaction credit data stored by the institution can be fed back, so that the transaction credit data can be obtained.
  • the reference data for claim settlement in S104 can be achieved.
  • step S106 when performing step S106, please refer to FIG. 3.
  • This step also includes the following two small steps:
  • the input of the insurance claim model is the claim reference data of the originating user, and the output of the insurance claim model is the claim reference amount.
  • the claim reference data of the originating user is input into the insurance claim model, and the claim reference amount of the originating user is obtained.
  • the process of constructing an insurance claim model in S1062 may be: constructing an initial insurance claim model and obtaining historical claim records of multiple sample users; then, using the historical claim records to train the initial insurance claim model to obtain an insurance claim model.
  • the initial insurance claim model can be constructed according to a machine learning algorithm, and then the initial insurance claim model is trained through the historical claims records of the sample users to obtain the insurance claim model.
  • the historical claims records of the sample users include: the historical claims reference data of the sample users and the historical claims reference amount.
  • sample users can choose according to their needs.
  • the machine learning algorithms involved in the embodiments of the present application may include, but are not limited to, decision tree algorithms, neural network algorithms, and the like.
  • a neural network algorithm is used as an example to briefly explain the process of training a machine learning model.
  • an initial insurance claim model with input reference data and output reference amount based on the architectural relationship of the neural network model is constructed; on the other hand, the historical claim records of multiple sample users are subjected to feature extraction to obtain each sample. Historical claims characteristics of users; then, the historical claims characteristics of multiple sample users are imported into the initial insurance claims model for training to confirm the weight of each input parameter, thereby obtaining the final trained insurance claims model.
  • step S108 Based on the insurance claim model constructed in step S1062 and the claim reference data of the initiating user obtained in step S104, then when step S108 is performed, only the claim reference data of the initiating user is input into the insurance claim model, and the initiating user can be obtained The reference amount of the claim.
  • the first type the claim reference amount is paid to the originating user as an insurance payment amount.
  • This method can be carried out without manual operation, and realizes fully automatic processing, which greatly reduces the cost of human resources and improves the efficiency of claim settlement.
  • the second type output prompt information carrying a reference amount of claims, so as to prompt the user to use the reference amount of claims as a reference in the process of making claims to the initiating user.
  • an embodiment of the present application further provides a computer non-volatile readable storage medium including computer-readable instructions, which are used to execute any of the above-mentioned instructions when the computer-readable instructions are executed. Realization of an insurance payment method.
  • the claim reference data of the originating user is obtained, and based on these claim reference data, based on the machine learning algorithm, the claim reference amount is directly obtained to reduce staff work Compared with manual labor, the error of the compensation reference amount obtained based on the user's compensation reference data is smaller. Therefore, the technical solution provided in the embodiment of the present application can solve the problem that in the prior art, the consumption of human resources costs is relatively large depending on the subjective determination of the claim amount by humans.
  • the embodiment of the present application further provides an apparatus embodiment for implementing each step and method in the foregoing method embodiment.
  • an embodiment of the present application provides an insurance compensation device. Please refer to FIG. 4.
  • the insurance compensation device 400 includes:
  • a receiving unit 41 configured to receive an insurance claim application
  • the obtaining unit 42 is configured to obtain claim reference data of an originating user of an insurance claim application, wherein the claim reference data includes at least one of physical condition data, asset condition data, and accident related data;
  • the processing unit 43 is configured to process the claim reference data of the originating user by using a machine learning algorithm to obtain the claim reference amount of the originating user;
  • a compensation unit 44 is configured to perform insurance compensation for the initiating user according to the reference amount of claim settlement.
  • the physical condition data involved in the embodiments of the present application may include, but is not limited to, at least one of medical records, family medical history, personal injury records, and historical body insurance purchases and claims records;
  • Asset status data may include, but is not limited to, at least one of payment records, loan records, asset transaction data and shopping transaction data;
  • the accident-related data may include, but is not limited to, at least one of accident liability determination data and accident scene description data.
  • the obtaining unit 42 may be specifically configured to:
  • the claim reference data of the originating user is called.
  • processing unit 43 is specifically configured to:
  • the input of the insurance claim model is the claim reference data of the originating user, and the output of the insurance claim model is the claim reference amount;
  • the claim reference data of the originating user is input into the insurance claim model, and the claim reference amount of the originating user is obtained.
  • processing method of the processing unit 43 when specifically used to construct the insurance claim model may include the following methods:
  • the compensation unit 44 is specifically configured to:
  • the claim reference amount is paid to the originating user as an insurance claim.
  • the embodiment of the present application also provides a computer device. Please refer to FIG. 5.
  • the computer device 500 includes: a memory 51, a processor 52, and a computer stored in the memory 51 and capable of running on the processor 52.
  • the processor 52 executes the computer-readable instructions to implement the steps of the insurance payment method according to any one of the embodiments.
  • the claim reference data of the originating user is obtained, and based on these claim reference data, based on the machine learning algorithm, the claim reference amount is directly obtained to reduce staff work Compared with manual labor, the error of the compensation reference amount obtained based on the user's compensation reference data is smaller. Therefore, the technical solution provided in the embodiment of the present application can solve the problem that in the prior art, the consumption of human resources costs is relatively large depending on the subjective determination of the claim amount by humans.
  • the disclosed systems, devices, and methods may be implemented in other ways.
  • the device embodiments described above are only schematic.
  • the division of the unit is only a logical function division.
  • multiple units or components may be combined.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, which may be electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objective of the solution of this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each of the units may exist separately physically, or two or more units may be integrated into one unit.
  • the above integrated unit may be implemented in the form of hardware, or in the form of hardware plus software functional units.
  • the above integrated unit implemented in the form of a software functional unit may be stored in a computer-readable storage medium.
  • the above software functional unit is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) or a processor to execute the methods described in the embodiments of the present application. Some steps.
  • the foregoing storage media include: U disks, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks or compact discs and other media that can store program codes .

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Technology Law (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

La présente invention concerne un procédé et un appareil de règlement d'indemnisation d'assurance, un dispositif informatique et un support de stockage lisible. Dans le mode de réalisation de la présente invention, le procédé consiste à : recevoir une revendication d'assurance, acquérir des données de règlement de revendication de référence d'un client effectuant la revendication d'assurance, les données de règlement de revendication de référence comprenant au moins une catégorie de données suivante : des données de condition physique, des données de biens et des données concernant un incident, traiter les données de règlement de revendication de référence du client revendiquant grâce à un algorithme d'apprentissage automatique pour obtenir un montant de règlement de revendication de référence pour le client revendiquant, et régler l'indemnisation d'assurance avec le client revendiquant selon le montant de règlement de revendication de référence. La solution technique fournie dans le mode de réalisation de la présente invention peut résoudre le problème dans l'état de la technique de coût de main-d'œuvre élevé lors de la détermination manuelle du montant de règlement de revendication.
PCT/CN2018/111379 2018-06-28 2018-10-23 Procédé et appareil de règlement d'indemnisation d'assurance, dispositif informatique et support de stockage lisible WO2020000803A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810690847.5A CN109255718A (zh) 2018-06-28 2018-06-28 保险赔付方法与装置、计算机设备与可读存储介质
CN201810690847.5 2018-06-28

Publications (1)

Publication Number Publication Date
WO2020000803A1 true WO2020000803A1 (fr) 2020-01-02

Family

ID=65050760

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/111379 WO2020000803A1 (fr) 2018-06-28 2018-10-23 Procédé et appareil de règlement d'indemnisation d'assurance, dispositif informatique et support de stockage lisible

Country Status (2)

Country Link
CN (1) CN109255718A (fr)
WO (1) WO2020000803A1 (fr)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109658273B (zh) * 2019-01-24 2020-06-12 易保互联医疗信息科技（北京）有限公司 基于区块链的商业保险快速理赔方法、存储介质和设备
CN110443716A (zh) * 2019-06-17 2019-11-12 中国平安财产保险股份有限公司 理赔方法、装置、计算机设备及存储介质
CN110689191A (zh) * 2019-09-24 2020-01-14 深圳前海微众银行股份有限公司 农业保险赔偿额预测方法、装置、设备及可读存储介质
CN111292159A (zh) * 2020-01-17 2020-06-16 青梧桐有限责任公司 基于多因素影响的赔付金额计算方法及系统
CN111275523A (zh) * 2020-01-17 2020-06-12 青梧桐有限责任公司 基于不规则数据计算推荐金额的方法及系统

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110082712A1 (en) * 2009-10-01 2011-04-07 DecisionQ Corporation Application of bayesian networks to patient screening and treatment
CN107679995A (zh) * 2017-08-31 2018-02-09 平安科技（深圳）有限公司 电子装置、保险案件理赔审核方法及计算机可读存储介质
CN107730215A (zh) * 2017-11-08 2018-02-23 泰康保险集团股份有限公司 保险理赔在线处理方法和系统

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106204282B (zh) * 2015-05-04 2021-02-26 腾讯科技（深圳）有限公司 一种数据处理方法及装置
CN107895286B (zh) * 2017-11-13 2021-11-26 天津幸福生命科技有限公司 理赔金额确定方法及装置、存储介质和电子设备
CN107798514A (zh) * 2017-11-22 2018-03-13 阿里巴巴集团控股有限公司 基于信用实现理赔的方法和装置

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110082712A1 (en) * 2009-10-01 2011-04-07 DecisionQ Corporation Application of bayesian networks to patient screening and treatment
CN107679995A (zh) * 2017-08-31 2018-02-09 平安科技（深圳）有限公司 电子装置、保险案件理赔审核方法及计算机可读存储介质
CN107730215A (zh) * 2017-11-08 2018-02-23 泰康保险集团股份有限公司 保险理赔在线处理方法和系统

Also Published As

Publication number Publication date
CN109255718A (zh) 2019-01-22

Similar Documents

Publication Publication Date Title
WO2020000803A1 (fr) Procédé et appareil de règlement d'indemnisation d'assurance, dispositif informatique et support de stockage lisible
WO2019178914A1 (fr) Procédé de détection de fraude et d'évaluation de risque, système, dispositif, et support de stockage
CA3102678C (fr) Dispositif de traitement d'informations, procede de traitement d'informations et programme informatique
US20200302315A1 (en) Digital blockchain for lending
US20060178983A1 (en) Mortgage broker system allowing broker to match mortgagor with multiple lenders and method therefor
WO2020019963A1 (fr) Procédé et dispositif de vérification d'identité et procédé et dispositif de modification d'informations de compte
US10482544B2 (en) Methods, systems and computer program products for masking tax data during collaborative tax return preparation
US10789643B1 (en) Accountant account takeover fraud detection
US20200090269A1 (en) Data collection method and apparatus for risk evaluation, and electronic device
US20160323247A1 (en) Systems and methods for anonymously obtaining data
JP6697484B2 (ja) 代理支払方法、代理支払装置および電子デバイス
US20160098791A1 (en) Method, terminal and system for resetting payment password
US11588762B1 (en) Simulation-based virtual advisor
US20160328794A1 (en) Methods and systems for improved application submissions
WO2022036702A1 (fr) Procédé et appareil d'avertissement pour produit de sécurité d'actif, dispositif électronique et support de stockage
CN110415104A (zh) 数据处理方法和装置，电子设备和存储介质
CN109791676A (zh) 基于共享内存的交易处理
CA2960654C (fr) Acces intermediaire aux profils d'information d'entite
CN110009481B (zh) 一种基于人脸识别的贷款审批方法及系统
US20170213283A1 (en) Device and a computer software for provisioning a user with requested services
KR20150061539A (ko) 허위판매 방지 시스템 및 그 제공방법
US20160004880A1 (en) Method and System for Personal Identity Verification
US10009432B1 (en) Intelligent real-time lead management systems, methods and architecture
US20160358262A1 (en) System for use of retirement funds for investment
KR20170046525A (ko) 정보 처리방법 및 장치와 기록매체

Legal Events

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

Ref document number: 18923982

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18923982

Country of ref document: EP

Kind code of ref document: A1