CN111612638A - Method for identifying insurance fraud risk based on big data of Internet of vehicles - Google Patents
Method for identifying insurance fraud risk based on big data of Internet of vehicles Download PDFInfo
- Publication number
- CN111612638A CN111612638A CN202010431471.3A CN202010431471A CN111612638A CN 111612638 A CN111612638 A CN 111612638A CN 202010431471 A CN202010431471 A CN 202010431471A CN 111612638 A CN111612638 A CN 111612638A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- risk
- data
- insurance
- internet
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000000605 extraction Methods 0.000 claims description 4
- 230000006855 networking Effects 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a method for identifying insurance fraud risk based on Internet of vehicles big data, which comprises the steps of obtaining insurance information data reported by vehicles; acquiring the data of the Internet of vehicles before and after the vehicle goes out of danger according to the reported data; extracting risk event characteristics; a fraud risk is identified. According to the method, the key risk characteristics related to the driving behavior are extracted while the satellite positioning data amount is effectively reduced by acquiring a large amount of driving tracks, and fraud risks are accurately identified.
Description
Technical Field
The invention relates to a method for identifying insurance fraud risk, in particular to a method for identifying insurance fraud risk based on Internet of vehicles big data, and belongs to the technical field of insurance.
Background
Insurance fraud and the development of insurance markets are always just like the video. It has been reported that insurance fraud is second only to drug crime once even in the U.S. with developed insurance. Insurance fraud causes huge loss to insurance industry, and related data show that the fraud loss of international insurance business is about 10% -30% on average, while in China, with the development of insurance industry, the business range of insurance companies is continuously expanded, and the loss caused by fraud is increased to more than 10%.
In order to actively promote the development of the internet of things, an anti-fraud system is established by applying technologies such as big data modeling and the like, and fraud guarantee behaviors are screened, the vehicle network data of the heavy truck is used for assisting in analyzing the driving behavior of the vehicle, the possibility of vehicle fraud risk is judged, insurance company claim settlement check is effectively supported, and the invalid claim payment cost is reduced.
Disclosure of Invention
The invention aims to solve the problems and provide a method for identifying insurance fraud risk based on Internet of vehicles big data.
The invention realizes the purpose through the following technical scheme: a method for identifying insurance fraud risk based on Internet of vehicles big data comprises the following steps:
(1) acquiring the insurance information data reported by the vehicle;
(2) acquiring the data of the Internet of vehicles before and after the vehicle goes out of danger according to the reported data;
(3) extracting risk event characteristics;
(4) identifying a fraud risk.
As a further scheme of the invention: the insurance information data comprises:
in order to provide service better and faster, the accident process does not need to be described in detail during query, and only necessary insurance information data need to be provided, wherein the insurance information data comprises a vehicle license plate number, a vehicle identification code/frame number, insurance time and insurance position.
As a further scheme of the invention: the step of acquiring the vehicle networking data before and after the vehicle is out of danger according to the reported data comprises the following steps:
travel data within thirty days before and after the vehicle insurance leaving time are obtained according to the vehicle insurance leaving time, the obtained satellite positioning data are analyzed, and the satellite positioning time, the satellite positioning longitude and latitude and the like of the data point are mainly analyzed.
As a further scheme of the invention: the step of extracting risk event features comprises:
the extraction of the risk feature is to extract a risk feature that can represent a driving behavior of the vehicle from a driving trajectory within 30 days before and after the vehicle is out of danger. The risk event characteristics include: risk characteristics before, during and after an emergency.
As a further scheme of the invention: the step of identifying a risk of fraud comprises:
and carrying out weight quantitative configuration according to the importance degree of the risk event on the identification of the insurance fraud risk, and carrying out weight summation on each single feature to calculate the grade of the vehicle fraud risk probability.
The invention has the beneficial effects that: the method for identifying the insurance fraud risk based on the Internet of vehicles big data is reasonable in design, overcomes the defect that anti-fraud work highly depends on the complex flow of field survey and loss assessment and manual background check of claim settlement personnel, does not need to consume a large amount of manpower, and reduces the cost for loss assessment of insurance companies. Further, the track journey processing is carried out by acquiring mass Internet of vehicles data. Furthermore, the vehicle networking data is subjected to dimensionality reduction and aggregation, the data volume is reduced, key information of vehicle driving is kept, and refined and comprehensive risk characteristics are provided; furthermore, the fraud risk is identified through the risk characteristics, the insurance company claim settlement check is effectively supported, and the invalid claim payment cost is reduced.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a method for identifying insurance fraud risk based on internet of vehicles big data includes the following steps:
step S10, acquiring the insurance information data
After the vehicle goes out of the insurance, the vehicle owner should immediately give an alarm and report to the insurance company. When reporting a case, the owner of the vehicle needs to correctly describe the passing and loss conditions of the accident. In this embodiment, the insurance information data of the vehicle must include: the number plate number, the vehicle identification code/frame number, the danger time and the danger position of the vehicle;
step S20, obtaining the data of the vehicle network before and after the vehicle is out of danger
In the embodiment, travel data within thirty days before and after the vehicle insurance leaving time is obtained according to the vehicle insurance leaving time, the obtained satellite positioning data is analyzed, and the satellite positioning time and the satellite positioning longitude and latitude of the data point are mainly analyzed;
step S30, extracting risk characteristics
In the embodiment, the extraction of the risk characteristics refers to extraction from a driving track within 30 days before and after the vehicle is in danger. The above risk characteristics specifically defined include:
specifically defined pre-emergence risk events include:
1) whether the vehicle uploads the travel data within the threshold range days before the accident;
2) whether the journey data is uploaded on the day of the insurance;
3) whether the total driving mileage of the vehicle is less than a certain threshold value within 30 days before the danger;
4) whether the satellite positioning position of the vehicle is abnormal within 30 minutes before the emergency
The abnormal satellite positioning position means that the journey data is uploaded within 30 minutes before the vehicle is in danger, but the movement range is smaller than a certain threshold value, and the accumulated mileage is smaller than a certain threshold value.
Specifically defined in-risk events include:
1) whether the vehicle stays in danger or not
Wherein the presence or absence of a stop indicates whether the vehicle is continuously traveling within a pre-and post-risk threshold range time window.
Specifically defined post-emergence risk events include:
1) whether the position of the emergency is consistent with the driving track of the vehicle or not;
2) whether the driving mileage of the vehicle exceeds a certain threshold value within 7 days after the vehicle is out of danger;
3) whether the number of days of maintenance duration after the emergency is less than a certain threshold value or not;
4) whether the initial position of the vehicle is consistent with the positioning of the maintenance station after the maintenance is finished;
5) whether the vehicle enters the maintenance service station after the emergency
Step S40, identifying insurance fraud risk
Defining single factor scores according to the importance degree of the occurrence of the risk event on the identification of the insurance fraud risk, quantitatively configuring different factors according to the influence degree weight, and summing the scores of the single factors according to the weight to calculate the score of the vehicle fraud risk. Fraud risk score calculation formula:
where SCORE is insurance fraud risk SCORE, ωiScore as risk feature weightiIs the score of the ith risk profile. The higher the score, the higher the likelihood of fraud risk.
The working principle is as follows: when the method for identifying insurance fraud risk based on the Internet of vehicles big data is used, insurance information data reported by vehicles are firstly obtained, Internet of vehicles data before and after insurance of the vehicles are obtained according to the reported data, risk event features are extracted from the Internet of vehicles data, and fraud risk is further identified. Compared with the prior art, the insurance anti-fraud method in the embodiment obtains massive Internet of vehicles data, performs track routing processing, performs dimension reduction and aggregation on the Internet of vehicles, reduces the data volume, retains key information of vehicle driving, provides refined and comprehensive risk characteristic recognition fraud risk, effectively supports insurance company claim checking, and reduces the cost of invalid claim payment.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description of the embodiments is for clarity only, and those skilled in the art should make the description as a whole, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (5)
1. A method for identifying insurance fraud risk based on Internet of vehicles big data is characterized in that: the method comprises the following steps:
(1) acquiring the insurance information data reported by the vehicle;
(2) acquiring the data of the Internet of vehicles before and after the vehicle goes out of danger according to the reported data;
(3) extracting risk event characteristics;
(4) identifying a fraud risk.
2. The method for identifying insurance fraud risk based on Internet of vehicles big data according to claim 1, characterized in that: the insurance information data comprises:
in order to provide service better and faster, the accident process does not need to be described in detail during query, and only necessary insurance information data need to be provided, wherein the insurance information data comprises a vehicle license plate number, a vehicle identification code/frame number, insurance time and insurance position.
3. The method for identifying insurance fraud risk based on Internet of vehicles big data according to claim 1, characterized in that: the step of acquiring the vehicle networking data before and after the vehicle is out of danger according to the reported data comprises the following steps:
travel data within thirty days before and after the vehicle leaving time are obtained according to the vehicle leaving time, the obtained satellite positioning data are analyzed, and the satellite positioning time, the satellite positioning longitude and latitude and the like of data points are mainly analyzed.
4. The method for identifying insurance fraud risk based on Internet of vehicles big data according to claim 1, characterized in that: the step of extracting risk event features comprises:
the extraction of the risk feature is to extract a risk feature that can represent a driving behavior of the vehicle from a driving trajectory within 30 days before and after the vehicle is out of danger. The risk event characteristics include: risk characteristics before, during and after an emergency.
5. The method for identifying insurance fraud risk based on Internet of vehicles big data according to claim 1, characterized in that: the step of identifying a risk of fraud comprises:
and carrying out weight quantitative configuration according to the importance degree of the risk event on the identification of the insurance fraud risk, and carrying out weight summation on each single feature to calculate the grade of the vehicle fraud risk probability.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010431471.3A CN111612638A (en) | 2020-05-20 | 2020-05-20 | Method for identifying insurance fraud risk based on big data of Internet of vehicles |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010431471.3A CN111612638A (en) | 2020-05-20 | 2020-05-20 | Method for identifying insurance fraud risk based on big data of Internet of vehicles |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111612638A true CN111612638A (en) | 2020-09-01 |
Family
ID=72203524
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010431471.3A Pending CN111612638A (en) | 2020-05-20 | 2020-05-20 | Method for identifying insurance fraud risk based on big data of Internet of vehicles |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111612638A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112288334A (en) * | 2020-11-27 | 2021-01-29 | 上海评驾科技有限公司 | Lightgbm-based car networking risk factor extraction method |
| CN113077179A (en) * | 2021-04-21 | 2021-07-06 | 中国第一汽车股份有限公司 | Vehicle false claim identification method, system, equipment and storage medium |
| CN113657476A (en) * | 2021-08-09 | 2021-11-16 | 湖北亿咖通科技有限公司 | Method for identifying driving risk, electronic equipment and computer storage medium |
| CN116934350A (en) * | 2023-06-25 | 2023-10-24 | 深圳民太安智能科技有限公司 | Vehicle insurance fraud risk control method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080312969A1 (en) * | 2007-04-20 | 2008-12-18 | Richard Raines | System and method for insurance underwriting and rating |
| WO2014207558A2 (en) * | 2013-06-27 | 2014-12-31 | Scope Technologies Holdings Limited | Onboard vehicle accident detection and damage estimation system and method of use |
| CN106530095A (en) * | 2016-12-05 | 2017-03-22 | 北京中交兴路信息科技有限公司 | Method and device for analyzing user fraud behavior |
| US9767692B1 (en) * | 2014-06-25 | 2017-09-19 | Louvena Vaudreuil | Vehicle and environmental data acquisition and conditioned response system |
| CN109191312A (en) * | 2018-08-07 | 2019-01-11 | 阳光财产保险股份有限公司 | A kind of anti-fraud air control method and device of Claims Resolution |
| CN110458718A (en) * | 2019-08-09 | 2019-11-15 | 泰康保险集团股份有限公司 | Vehicle insurance cheats recognition methods, device, medium and electronic equipment |
-
2020
- 2020-05-20 CN CN202010431471.3A patent/CN111612638A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080312969A1 (en) * | 2007-04-20 | 2008-12-18 | Richard Raines | System and method for insurance underwriting and rating |
| WO2014207558A2 (en) * | 2013-06-27 | 2014-12-31 | Scope Technologies Holdings Limited | Onboard vehicle accident detection and damage estimation system and method of use |
| US9767692B1 (en) * | 2014-06-25 | 2017-09-19 | Louvena Vaudreuil | Vehicle and environmental data acquisition and conditioned response system |
| CN106530095A (en) * | 2016-12-05 | 2017-03-22 | 北京中交兴路信息科技有限公司 | Method and device for analyzing user fraud behavior |
| CN109191312A (en) * | 2018-08-07 | 2019-01-11 | 阳光财产保险股份有限公司 | A kind of anti-fraud air control method and device of Claims Resolution |
| CN110458718A (en) * | 2019-08-09 | 2019-11-15 | 泰康保险集团股份有限公司 | Vehicle insurance cheats recognition methods, device, medium and electronic equipment |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112288334A (en) * | 2020-11-27 | 2021-01-29 | 上海评驾科技有限公司 | Lightgbm-based car networking risk factor extraction method |
| CN112288334B (en) * | 2020-11-27 | 2024-04-16 | 上海评驾科技有限公司 | Method for extracting Internet of vehicles risk factors based on lightgbm |
| CN113077179A (en) * | 2021-04-21 | 2021-07-06 | 中国第一汽车股份有限公司 | Vehicle false claim identification method, system, equipment and storage medium |
| CN113657476A (en) * | 2021-08-09 | 2021-11-16 | 湖北亿咖通科技有限公司 | Method for identifying driving risk, electronic equipment and computer storage medium |
| CN113657476B (en) * | 2021-08-09 | 2023-10-31 | 亿咖通(湖北)技术有限公司 | Method for identifying driving risk, electronic equipment and computer storage medium |
| CN116934350A (en) * | 2023-06-25 | 2023-10-24 | 深圳民太安智能科技有限公司 | Vehicle insurance fraud risk control method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111612638A (en) | Method for identifying insurance fraud risk based on big data of Internet of vehicles | |
| CN110866677B (en) | Driver relative risk evaluation method based on benchmark analysis | |
| CN106022296B (en) | A kind of fake-licensed car detection method of the probability polymerization based on vehicle hot spot region | |
| CN111914687B (en) | Method for actively identifying accidents based on Internet of vehicles | |
| CN108427757A (en) | Emphasis vehicle pass-through method for early warning based on correlation rule and supervisory systems | |
| CN111476177B (en) | Method and device for detecting suspects | |
| CN109615853A (en) | Identify the method and apparatus of the doubtful illegal operation vehicle of highway | |
| CN109767618B (en) | Comprehensive study and judgment method and system for abnormal data of public security traffic management service | |
| CN111806516A (en) | Health management device and method for intelligent train monitoring and operation and maintenance | |
| CN109448372A (en) | A kind of safety monitoring and alarm method of riding | |
| CN112989069B (en) | Traffic violation analysis method based on knowledge graph and block chain | |
| CN114331181A (en) | Vehicle driving behavior risk analysis method based on big data | |
| CN111861765B (en) | Intelligent anti-fraud method for vehicle insurance claim settlement | |
| CN117391894A (en) | Patrol robot collaborative violation evidence obtaining method, system and medium | |
| CN102157061A (en) | Keyword-statistic-based traffic event identifying method | |
| CN114780591B (en) | Calculation method and system for detecting travel license plate recognition errors | |
| CN114201530B (en) | Early screening and preventive supervision method for suspected abnormal operation passenger car | |
| CN116153063A (en) | Traffic safety hidden danger early warning method and system | |
| CN112906518B (en) | Riding abnormal person identification method and system based on SVM model | |
| CN116061953A (en) | Truck dangerous driving behavior discrimination evaluation method based on driving track data | |
| CN114446031A (en) | Multi-device and multi-dimensional data fusion analysis-based inspection station management method and system | |
| Yokoyama et al. | Do drivers' behaviors reflect their past driving histories?-large scale examination of vehicle recorder data | |
| CN111861762B (en) | Data processing method and system for identifying anti-fraud safety of vehicle | |
| CN112722007B (en) | Deep learning-based train operation comprehensive early warning method | |
| CN112308699B (en) | Method, system, equipment and storage medium for auditing warranty business data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200901 |