CN110363670A - Vehicle collision damage identification method and system based on history case - Google Patents
Vehicle collision damage identification method and system based on history case Download PDFInfo
- Publication number
- CN110363670A CN110363670A CN201810250609.2A CN201810250609A CN110363670A CN 110363670 A CN110363670 A CN 110363670A CN 201810250609 A CN201810250609 A CN 201810250609A CN 110363670 A CN110363670 A CN 110363670A
- Authority
- CN
- China
- Prior art keywords
- setting loss
- damage identification
- history case
- vehicle
- case
- 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
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
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
The present invention provides the damage identification method after a kind of vehicle collision, comprising: (a) obtains car damage identification history case, establishes car damage identification history case database；(b) it receives to setting loss information of vehicles；(c) it based on setting loss history case data, according to setting loss information of vehicles, calculates and determines the setting loss volume to setting loss vehicle.This damage identification method utilizes big data and machine learning techniques, can provide setting loss volume quick, accurate and personalizedly, is applicable not only to each insurance company and is used alone, is readily applicable to third party's setting loss platform.
Description
Technical field
The present invention relates to car insurance fields, and in particular to damage identification method and system after vehicle collision.
Background technique
Estimated amount of damage (abbreviation setting loss) process after vehicle collision will usually consider multiple technologies factor, including part valence
Lattice, hours to repair and local man-rating etc..It is needed after determining damaged parts and the extent of damage based on the setting loss of technical factor,
According to aforementioned multiple technologies because usually determining, this need insurance company or third party constantly safeguard various vehicle brands, the time,
The database of model, part type, part price, maintenance man-hours, man-rating, corresponding maintenance logic etc..But to reach guarantor
There are lot of challenges for all acceptable setting loss volume of dangerous company and repairing side.For example, insurance company and setting loss tool provider are often
It is difficult to obtain the database of accurate and high coverage as setting loss basis, third-party data source cannot often be approved
Deng.These data scale of constructions big (such as various vehicle brands, time, model, part type, part price, maintenance man-hours, labour cost
Rate etc.), broad covered area, updating decision and being difficult to reach an agreement (for example, on maintenance man-hours) be accurate setting loss challenge.Again
Person, such as in China, insurance company actually still takes macroscopical claim administration mode, and it is not based on the microcosmic accurate fixed of case
Damage mode, the former can consider many non-technique factors.For example, if maintenance can band to the dealer (such as shop 4S) of setting loss vehicle
Carry out a large amount of car insurance business, insurance company may change parameter or manual adjustment setting loss result accordingly.For another example if
The annual KPI(KPI Key Performance Indicator of insurance company) it is up to standard, setting loss may loosen height-regulating.This macroscopic view pipe of insurance company
Reason mode may result in the precision management for ignoring case level.
As can be seen that existing damage identification method dependent on based on technical factor setting loss tool and subsequent macroscopic view it is artificial
The combination of adjustment is realized.Therefore, in many cases, existing damage identification method and system are for reference only, without adapting to
The dynamic change in market, and may cause the price negotiation of multiple circulations.For example, using existing loss assessment system sometimes for
Spend several days, time in even a few weeks reach an agreement, therefore there are problems that inefficient, high cost of labor and high fault rate, reduce
Customer satisfaction.
Therefore, it is necessary to a kind of improved damage identification method and system be provided, to overcome above-mentioned existing in the prior art one
A or multiple problems.
Summary of the invention
One aspect of the present invention provides a kind of car damage identification method, suitable for executing on computers, which comprises
(a) car damage identification history case is obtained, car damage identification history case database is established；(b) it receives to setting loss information of vehicles；With
(c) based on setting loss history case data, according to setting loss information of vehicles, the setting loss volume to setting loss vehicle is calculated.
In some embodiments, the method is after step (c) further include: (d) will be described to setting loss information of vehicles
And its setting loss volume is added in the car damage identification history case database.
In some embodiments, the layer for the car damage identification history case database that the method is established in step (a)
Secondary includes case level, setting loss element level and setting loss factor level.
In some embodiments, in step (c), described calculate carries out in case level, obtains not less than predetermined phase
Like at least one setting loss history case of degree.It is in this case, described that at least one complete setting loss history case is calculated,
The complete setting loss history case includes the value of multiple setting loss factors.
Alternatively, in some embodiments, in step (c), described calculate carries out in setting loss factor level, with
To the different historical datas of at least one setting loss factor.In this case, described calculate with one or more setting loss factors is
Basis obtains each setting loss factor corresponding multiple historical datas in different history cases.
Alternatively, in some embodiments, in step (c), it is described calculate simultaneously case level and setting loss because
Sublayer face carries out, i.e., the described calculating is not related to the use of single complete history case data.For example, described calculate based on from not
The setting loss volume is determined with the setting loss factor data of different classes of/attribute of history case.
In some embodiments, the car damage identification history case database includes vehicle brand, vehicle system, vehicle, vehicle
Productive year, damaged vehicle photo, damaged parts title and number, damaged parts picture, damaged parts quantity, damaged parts
The extent of damage, renewal part price, hours to repair, local man-rating and setting loss volume etc..In some embodiments, the vehicle
Setting loss history case database further includes collision time of origin, place where the collision occurred point, repairer title, colliding part and volume
Outer expense expenditure.
In some embodiments, the data in car damage identification history case database are located in advance in step (a)
Reason.The pretreatment, which can be, offline to be carried out.Pretreated mode includes but is not limited to be classified to data, clustered, gathered
It closes, sort, summarize, clear up, such as classified according to colliding part to history case.
In some embodiments, described to setting loss information of vehicles includes vehicle brand, vehicle system, vehicle, vehicle production year
Part, accident photograph and damaged parts title and quantity and degree of injury.In some embodiments, described to believe to setting loss vehicle
Breath further includes version, body color, body-finishing, colliding part, crash site and repair shop's information of vehicle etc..
In some embodiments, described calculate includes traversal car damage identification history case database, by predetermined computation mould
Formula, it is received to setting loss information of vehicles based on institute, it calculates described in setting loss vehicle and car damage identification history case database
The case similarity of case and/or the factor similarity of the setting loss factor.In some embodiments, the history case and the factor
It is sorted from high to low with similarity.In some embodiments, the predetermined similarity is artificial settings and can be according to reality
The variation of border situation.
In some embodiments, when the setting loss history case and/or the setting loss factor that are not less than predetermined similarity are more than one
When a, by setting loss history case with time-sequencing, by the setting loss volume of nearest one or more setting loss history cases and/or the factor
It averages.In other embodiments, when the setting loss history case and/or the factor that are not less than predetermined similarity are more than one
When, the setting loss volume is determined by other algorithms.
In other embodiments, the determination of the setting loss volume can be related to making for related data in other history cases
With.For example, if lacking in the high history case of one or more similarities to the corresponding one or more damages of setting loss vehicle
Hurt the historical claim data of part, then it can be from other history cases (such as similarity is lower than history case of predetermined similarity)
The historical claim data for finding one or more identical parts, for the setting loss of the part, and then determination is determined to setting loss vehicle
Damage volume.
In some embodiments, the method the step of in (c), with the number of at least one setting loss history case
Apply one or more adjustment, based on to determine the setting loss volume to setting loss vehicle.In some embodiments, described
One or more adjustment is according to part price change rate, man-rating's change rate, KPI(Key PerformanceINdicator, KPI Key Performance Indicator) compliance rate, insurance business contribution rate etc. be one or more because usually applying.In some realities
It applies in mode, one or more of adjustment include manually adjusting.
In some embodiments, using setting loss volume obtained by conventional damage identification method as the inspection of setting loss volume obtained by step (c)
It puts to verify the accuracy of the method for the present invention.
In some embodiments, the present invention provides a kind of vehicle loss assessment system comprising processor；And memory, it uses
In storage car damage identification instruction, described instruction is suitable for being loaded by processor to execute above-mentioned any car damage identification method.
In some embodiments, the present invention provides a kind of computer-readable medium, is stored with computer-readable instruction,
Described instruction is suitable for being loaded by processor to execute above-mentioned any car damage identification method.
Method provided by the invention, according to the record in setting loss information of vehicles and history case database, with history case
Based on number of cases evidence and/or factor data, the setting loss volume determined to setting loss vehicle is calculated.This damage identification method using big data and
Machine learning techniques can provide setting loss volume quick, accurate and personalizedly, be applicable not only to each insurance company and be used alone,
It is readily applicable to third party's setting loss platform.
Detailed description of the invention
Fig. 1 is the flow chart of the illustrative methods for setting loss according to one embodiment.
Fig. 2 is the process of the illustrative methods for establishing car damage identification history case database according to one embodiment
Figure.
Fig. 3 is the flow chart of the illustrative methods for setting loss according to another embodiment.
Fig. 4 is the table for showing setting loss element Yu setting loss factor exemplary relation.
Fig. 5 is the block diagram of exemplary loss assessment system according to one embodiment.
Specific embodiment
Referring now to illustrative embodiment the present invention is described in detail, some embodiments are illustrated in the drawings.It is described below
It is carried out with reference to attached drawing, unless otherwise indicated, otherwise same numbers in different figures represent same or similar element.Below
Scheme described in illustrative embodiments does not represent all schemes of the invention.On the contrary, these schemes are only that appended right is wanted
The example of the system and method for various aspects of the invention involved in asking.
Fig. 1 shows the illustrative methods 100 for car damage identification according to embodiment of the present invention.Method
100 start from step 110, establish car damage identification history case database.The implementation of the illustrative methods 100 is with car damage identification
Based on the foundation of history case database.Each insurance company forms a large amount of history case in long-term vehicle damage claim business
Data, setting loss mode routinely, the setting loss volume of these history cases are by the conventional setting loss tool based on technical factor
Calculating and combine manually adjusting based on non-technique factors.Therefore, the setting loss volume of these history cases is market feelings
The most true reflection of condition, has been precipitated the experience and knowledge of setting loss person and core damage person, has been determined based on the setting loss volume of history case
Setting loss volume to setting loss vehicle, it can be ensured that the accuracy of setting loss volume.
The method for establishing history case database is known in the art, and can use database generally in the art
Establishing techniques are implemented.Method 200 schematically illustrates the method for building up of history case database.Method 200 starts from fixed
The setting loss factor 210 of adopted car damage identification history case.The setting loss factor may include vehicle brand, vehicle system, vehicle, colliding part,
Part name, part price, hours to repair, local man-rating, collision time of origin, place where the collision occurred point, is repaired at number of parts
Manage trade name, extra charge expenditure, vehicle production time, the version of vehicle, body color, the part extent of damage and vehicle body dress
One or more of decorations.In a step 220, the setting loss element of car damage identification history case is defined.Setting loss element may include
Crash type, including but not limited to, front case, dead astern case, left front case, right front case, left side case, the right side
Side case, left back case, right back case, slight case, serious case or its various combination case.Step 210 and 220
It can be implemented with reverse sequence.Finally, in step 230, by one or more setting loss elements respectively with one or more
The setting loss factor is associated.For example, a setting loss factor is associated with multiple setting loss elements.For another example between each setting loss element
Shared one or more identical setting loss factors.The setting loss factor and setting loss element are illustratively shown in table 400 shown in Fig. 4
Between relationship.
These setting loss factors or setting loss element can update, such as increase newly, are deleted or modified, so as to from more, more
New dimension safeguards database.When method of the invention is implemented on third party's setting loss platform, can will insure from more
The history case of company summarizes and establishes history case database by above-mentioned example method.
In the step 120, method receives the relevant information to setting loss vehicle.These relevant informations may include such as license plate
Number, vehicle brand, vehicle system, vehicle, colliding part, crash site, damaged parts title and quantity, vehicle production time, vehicle
Version, body color, the part extent of damage and body-finishing.Such as those skilled in the art it can be anticipated that arriving, believe to setting loss vehicle
Breath provides more abundant, then it is easier with history case database in record matching, thus retrieve more matched claim/
Setting loss record provides basis for the high case of output similarity.Certainly, on the other hand, the matching of case also relies on database
The popularity and integrality of middle record.In actual operation, the input to the relevant information of setting loss vehicle can be independent of data
Input one by one.For example, in some cases, when input is when the license plate number of setting loss vehicle, method 100 can from official's platform or
Other platform automatically retrievals go out corresponding vehicle brand, vehicle system, vehicle, the vehicle production time, the version of vehicle, body color,
The information such as body-finishing.
In step 130, it will be calculated to setting loss vehicle and history case database, and find similar history case.
Described calculate includes traversal car damage identification history case database, received to setting loss vehicle based on institute by predetermined computation mode
Information calculates described to the similarity of each case or/and the factor in setting loss vehicle and car damage identification history case database.
The predetermined computation mode can be machine learning algorithm, can also be determined as needed by those skilled in the art.One exemplary
Calculating mode be to calculate the weighted sum of the similarity of value of each setting loss factor.Another illustrative calculating mode is to calculate respectively
The weighted average of the similarity of the value of the setting loss factor.In the illustrative calculating mode, those skilled in the art need
Determine the weight of each setting loss factor, for example, vehicle brand, vehicle system, vehicle weight could possibly be higher than vehicle production time, vehicle
The weight of version, the weight of body color or colliding part, the part extent of damage could possibly be higher than the weight of crash site.Power
The determination of weight can be determined by the test of those skilled in the art's limited times.
In some cases, obtained history case is sorted from high to low with similarity.Alternatively, being with predetermined similarity
Threshold value only exports the history case of the threshold value or more.It, will when the setting loss history case not less than predetermined similarity is more than one
Setting loss history case is with time-sequencing.The predetermined similarity can be set according to actual conditions and be adjusted by those skilled in the art
It is whole.In some cases, similarity can adjust in real time, and the similar case exported correspondingly increases and decreases in real time, to make user
The number of similar history case can be determined by practical merit.
In step 140, setting loss volume is calculated based on the data of the history case of acquisition.One illustrative algorithm is with institute
The setting loss volume to setting loss vehicle is determined based on the setting loss volume or its average value of obtained one or more setting loss history cases.
When the similar setting loss history case that there are multiple higher than similarity threshold, can choose nearest one or more cases come it is true
The fixed setting loss volume (such as averaging) to setting loss vehicle.Alternatively, when there are multiple similar setting loss higher than the threshold value
When history case, it can be subject to the setting loss volume of one of history case.For example, if a certain history case with to setting loss vehicle
Information exact matching, it may not be necessary to average as described above.
Another illustrative determining method to the setting loss volume of setting loss vehicle is related to related data in other history cases
Use.For example, if lacking to setting loss vehicle corresponding one or more in the high history case of one or more similarities
The historical claim data of a injuring part, the then history that one or more identical parts can be found from other history cases are compensated
Data for the setting loss of the part, and then determine the setting loss volume to setting loss vehicle.
Another illustrative determining method to the setting loss volume of setting loss vehicle is not related to single complete history case data
Use.In this case, method 100 is based on the data of different classes of/attribute from different history cases to determine
State setting loss volume.
In step 140, one or more adjustment can be applied on identified setting loss volume, described in finally determining
Setting loss volume to setting loss vehicle.These adjustment be, for example, according to part price change rate, man-rating's change rate, KPI compliance rate,
Insurance business contribution rate etc. is one or more because usually applying.These adjustment can be computer execution, alternatively, these are adjusted
Whole is to manually adjust.
Method 300 shows another illustrative damage identification method.Method 300 starts from establishing car damage identification history case
Database (step 310) is substantially identical to step 110, but in establishment process, method 300 further to database into
Line number Data preprocess.Pretreatment usually can under line/offline carry out.Data prediction can be based on big data analysis aggregating algorithm,
It can also be carried out according to different purposes.Classify for example, crash type can be based on to history case, therefore can match
When history case database, matching record more rapidly and is accurately filtered out according to crash type, without traversing all numbers
According to record.Step 320 is identical to step 140 substance as the step 120 in method 100 to step 340.In step 350, side
History case database is added in setting loss information of vehicles and its setting loss volume by method 300, so that abundant and more new database record, is
The setting loss offer of new case is more acurrate and timely matches record.(the step when carrying out data update to history case database
352) it, needs to carry out data prediction step therein again.Therefore, data prediction is actually what dynamic carried out.When this
When invention is implemented in the form of artificial intelligence and machine learning, the addition of new data records may make machine dynamically adjust its calculation
Method, to constantly improve accuracy.
Fig. 5 shows the block diagram of the loss assessment system 500 according to some disclosed embodiments.The system may include place
Manage device 521, input/output (I/O) equipment 522, memory 523, storage device 526, database 527 and display device 528.
Processor 521 can be processing unit known to one or more, such as the Pentium system manufactured by Intel
Column microprocessor, or the Turion series microprocessor manufactured by AMD.Processor 521 may include single core processor system
Or it is able to carry out the multi-core processor system of parallel processing.For example, processor 521 can be at the monokaryon with virtual processing technique
Manage device.In some embodiments, processor 521 can be performed simultaneously and control multiple processes using logic processor.Processing
Virtual machine technique or other similar known technology can be performed in device 521, more so as to execute, control, allow, manipulate, store
A software process, application, program etc..In another embodiment, processor 521 includes that multi-core processor configuration is (such as double
Core or four cores), it is configurable to provide parallel processing function, so that loss assessment system 500 be allowed to be performed simultaneously multiple processes.Ability
Field technique personnel are it will be appreciated that the configuration of other kinds of processor can also be performed to provide function as described herein.
Memory 523 may include one or more storage devices, these storage devices are configured to store the use of processor 521
Instruction, thereby executing the function in disclosed embodiment.For example, memory 523 can be configured with one or more softwares
Instruction, such as instruction 524 can carry out one or more operations when being executed by processor 521.Disclosed embodiment
It is not limited to be configured to perform the single program of special duty or computer.For example, memory 523 may include executing loss assessment system
The single instruction 524 of 500 function, or instruction 524 may include multiple instruction.
Memory 523 can also storing data 525, data 525, which can reflect, executes appointing for the function in disclosed embodiment
Any kind of information of what form.For example, data 525 may include the first number for calculating relevant history case database to setting loss
According to, and other data of the function that is able to carry out processor 521 in disclosed embodiment.
I/O equipment 522 can be configured to allow data to be received and/or transmit.I/O equipment 522 may include one or more
A number and/or artificial traffic equipment, allow loss assessment system 500 to communicate with other machines and equipment.Loss assessment system 500 may be used also
It is communicated to connect including one or more databases 527, or by network and one or more databases 527.For example, database
527 may include Oracle database, Sybase database or other relational databases or non-relational database, such as
Hadoop sequential file, HBase or Cassandra.In the exemplary embodiment, database 527 can be stored for setting loss
History case data.For example, the metadata can be created by user, and it is stored in database 527.
Of the invention also provides a kind of computer-readable medium, is stored with computer-readable instruction, and described instruction is suitable for
It is loaded by processor to execute any one car damage identification method shown in the present invention.The computer-readable medium may include making
Being includes disk (including floppy disk), CD (including CD-ROM(compact disc read-only memory) and DVD(digital versatile disc)), magneto-optic
Disk (including MD(mini disk)) or semiconductor memory encapsulation medium removable media.In some embodiments, the meter
Calculation machine readable medium is present in such as application shop, to provide any one car damage identification method shown in the coding present invention
Application program, such as mobile terminal application.
To those skilled in the art, after considering specification disclosed herein and specific embodiment, this
The other embodiments of invention will become obvious.The scope of the present invention is intended to follow having for general principle of the present invention
Any version, purposes or application of the invention are closed, also includes all compared with disclosure deviating from but belonging to this field
Known or known practice content.What description and embodiments were merely exemplary, claims define model of the invention
It encloses and substantive.
It will be appreciated that the present invention is not limited to precision architectures that is described above and illustrating in the accompanying drawings, and can be
Without departing from making various modifications and variations in the scope of the present invention.The scope of the present invention is only defined in the claims.
Claims (11)
1. a kind of car damage identification method, suitable for executing on computers, which comprises
(a) car damage identification history case is obtained, car damage identification history case database is established；
(b) it receives to setting loss information of vehicles；With
(c) it based on setting loss history case data, according to setting loss information of vehicles, calculates and determines described in determining to setting loss vehicle
Damage volume.
2. according to the method described in claim 1, wherein the method is after step (c) further include: (d) will be described to setting loss
Information of vehicles and its setting loss volume are added in the car damage identification history case database.
3. according to the method described in claim 1, wherein in step (a) to the data in car damage identification history case database
It is pre-processed.
4. according to the method described in claim 1, the level for the car damage identification history case database wherein established in step (a)
Including case level, setting loss element level and setting loss factor level.
5. being obtained not low according to the method described in claim 4, described calculate carries out in case level wherein in step (c)
In at least one setting loss history case of predetermined similarity.
6. according to the method described in claim 4, described calculate carries out in setting loss factor level wherein in step (c), to obtain
To the different historical datas of at least one setting loss factor.
7. according to the method described in claim 4, wherein in step (c), it is described calculate simultaneously case level and setting loss because
Sublayer face carries out.
8. according to the method described in claim 1, the one or more adjustment of the application involved in step (c), with determine it is described to
The final setting loss volume of setting loss vehicle.
9. according to the method described in claim 8, wherein it is one or more of adjustment include but according to part price change rate,
The one or more such as man-rating's change rate, KPI compliance rate, insurance business contribution rate is because usually applying or one
Or multiple adjustment include manually adjusting.
10. a kind of vehicle loss assessment system comprising:
Processor；With
Memory, for storing car damage identification instruction, described instruction, which is suitable for being loaded by processor, requires 1 to 9 with perform claim
Method described in any one.
11. a kind of computer-readable medium, is stored with computer-readable instruction, described instruction is suitable for being loaded by processor to hold
Method described in any one of row claim 1 to 9.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810250609.2A CN110363670A (en) | 2018-03-26 | 2018-03-26 | Vehicle collision damage identification method and system based on history case |
| PCT/CN2019/079629 WO2019184899A1 (en) | 2018-03-26 | 2019-03-26 | Vehicle collision damage assessment method and system based on historical cases |
| CN201980021736.8A CN111886619B (en) | 2018-03-26 | 2019-03-26 | Vehicle collision damage assessment method and system based on historical cases |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810250609.2A CN110363670A (en) | 2018-03-26 | 2018-03-26 | Vehicle collision damage identification method and system based on history case |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110363670A true CN110363670A (en) | 2019-10-22 |
Family
ID=68211934
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810250609.2A Pending CN110363670A (en) | 2018-03-26 | 2018-03-26 | Vehicle collision damage identification method and system based on history case |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110363670A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111461906A (en) * | 2020-05-28 | 2020-07-28 | 深圳麦亚信科技股份有限公司 | Fast vehicle insurance claim settlement method and device, computer equipment and storage medium |
| CN111507854A (en) * | 2020-06-29 | 2020-08-07 | 爱保科技有限公司 | Vehicle damage assessment method, device, medium and electronic equipment based on historical claims |
| CN113362189A (en) * | 2021-06-11 | 2021-09-07 | 爱保科技有限公司 | Vehicle claim processing method and device, medium and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080255887A1 (en) * | 2007-04-10 | 2008-10-16 | Autoonline Gmbh Informationssysteme | Method and system for processing an insurance claim for a damaged vehicle |
| CN105550756A (en) * | 2015-12-08 | 2016-05-04 | 优易商业管理成都有限公司 | Vehicle rapid damage determination method based on simulation of vehicle damages |
| CN106021548A (en) * | 2016-05-27 | 2016-10-12 | 大连楼兰科技股份有限公司 | Remote damage assessment method and system based on distributed artificial intelligent image recognition |
| CN106600422A (en) * | 2016-11-24 | 2017-04-26 | 中国平安财产保险股份有限公司 | Car insurance intelligent loss assessment method and system |
| CN106779799A (en) * | 2016-11-17 | 2017-05-31 | 中国平安财产保险股份有限公司 | Local setting loss price processing method and system based on vehicle insurance intelligence setting loss platform |
| US20180082379A1 (en) * | 2016-09-21 | 2018-03-22 | Allstate Insurance Company | Enhanced Image Capture and Analysis of Damaged Tangible Objects |
-
2018
- 2018-03-26 CN CN201810250609.2A patent/CN110363670A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080255887A1 (en) * | 2007-04-10 | 2008-10-16 | Autoonline Gmbh Informationssysteme | Method and system for processing an insurance claim for a damaged vehicle |
| CN105550756A (en) * | 2015-12-08 | 2016-05-04 | 优易商业管理成都有限公司 | Vehicle rapid damage determination method based on simulation of vehicle damages |
| CN106021548A (en) * | 2016-05-27 | 2016-10-12 | 大连楼兰科技股份有限公司 | Remote damage assessment method and system based on distributed artificial intelligent image recognition |
| US20180082379A1 (en) * | 2016-09-21 | 2018-03-22 | Allstate Insurance Company | Enhanced Image Capture and Analysis of Damaged Tangible Objects |
| CN106779799A (en) * | 2016-11-17 | 2017-05-31 | 中国平安财产保险股份有限公司 | Local setting loss price processing method and system based on vehicle insurance intelligence setting loss platform |
| CN106600422A (en) * | 2016-11-24 | 2017-04-26 | 中国平安财产保险股份有限公司 | Car insurance intelligent loss assessment method and system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111461906A (en) * | 2020-05-28 | 2020-07-28 | 深圳麦亚信科技股份有限公司 | Fast vehicle insurance claim settlement method and device, computer equipment and storage medium |
| CN111507854A (en) * | 2020-06-29 | 2020-08-07 | 爱保科技有限公司 | Vehicle damage assessment method, device, medium and electronic equipment based on historical claims |
| CN113362189A (en) * | 2021-06-11 | 2021-09-07 | 爱保科技有限公司 | Vehicle claim processing method and device, medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110363670A (en) | Vehicle collision damage identification method and system based on history case | |
| CN111886619B (en) | Vehicle collision damage assessment method and system based on historical cases | |
| WO2019205020A1 (en) | Road condition recognition method, apparatus and device | |
| CN105678457A (en) | Method for evaluating user behavior on the basis of position mining | |
| CN107180367A (en) | A kind of method, storage medium and the device of the vehicle appraisal based on machine learning | |
| WO2021047211A1 (en) | Neural network-based data verification method and apparatus, device, and storage medium | |
| CN110147926A (en) | A kind of risk class calculation method, storage medium and the terminal device of type of service | |
| CN114393520A (en) | Robot intelligent punching process monitoring method and system | |
| CN108537243A (en) | A kind of violation alarm method and device | |
| CN114140009A (en) | Power grid distribution network engineering technology evaluation method and device, terminal and storage medium | |
| CN112164144B (en) | Casting three-dimensional model classification method combining D2 operator and normal operator | |
| CN110363669A (en) | The automatic damage identification method of vehicle collision and system based on non-technique factors | |
| CN107885781A (en) | A kind of method for edition management and system | |
| CN111915368A (en) | Automobile industry customer ID identification system, method and medium | |
| CN115577983B (en) | Enterprise task matching method based on block chain, server and storage medium | |
| WO2021232595A1 (en) | Enterprise state supervision method, apparatus, and device, and computer readable storage medium | |
| CN115271565B (en) | DEA-based method, device and equipment for evaluating highway pavement maintenance measures | |
| CN114986956A (en) | Tire dynamic balance management system and method | |
| CN115564276A (en) | Project statistics reserve management system, method and storage medium | |
| CN114998022A (en) | Compliance wind control method and system | |
| CN115564554A (en) | Multi-technology stack parameter management method, device, equipment and medium | |
| CN113672952A (en) | Data authority configuration and control method and system based on automatic classification | |
| CN113779391A (en) | Intelligent lock unlocking recommendation method, system and device based on modeling and storage medium | |
| CN112633736A (en) | Risk monitoring method, system and device based on block chain system | |
| CN111898879A (en) | AI intelligent wind control modeling method |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191022 |
|
| WD01 | Invention patent application deemed withdrawn after publication |