CN116029326A - Method for establishing vehicle risk assessment code convenient for AI image identification - Google Patents
Method for establishing vehicle risk assessment code convenient for AI image identification Download PDFInfo
- Publication number
- CN116029326A CN116029326A CN202310014542.3A CN202310014542A CN116029326A CN 116029326 A CN116029326 A CN 116029326A CN 202310014542 A CN202310014542 A CN 202310014542A CN 116029326 A CN116029326 A CN 116029326A
- Authority
- CN
- China
- Prior art keywords
- data
- damage
- vehicle
- assessment
- item
- 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.)
- Granted
Links
Images
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention relates to the technical field of insurance finance, in particular to a method for establishing a vehicle insurance loss code convenient for AI image identification. The method comprises the steps of simplifying vehicle insurance claim data, then carrying out n-n square project distribution on the processed data, obtaining the collision position and damage degree value of a vehicle damage accident, obtaining a vehicle insurance damage assessment code which is convenient for AI image identification after the position and damage degree value are converted and encrypted, and obtaining the vehicle insurance damage assessment code which has the advantages of avoiding data leakage, protecting personal privacy and carrying out data sharing on restored data in a picture mode. The invention simplifies the vehicle risk assessment data, uses a small picture to contain key information, and can simply and clearly judge the collision position and damage degree value of the vehicle assessment accident. In the aspect of data security, only the accessory corresponding to each pixel point, namely the password template, is protected, the picture cannot be restored to case data, and case data leakage is effectively prevented.
Description
Technical Field
The invention relates to the technical field of insurance finance, in particular to a method for establishing a vehicle insurance loss code convenient for AI image identification.
Background
With the rapid development of AI intelligence, AI intelligence technology has been gradually applied in various large fields, especially in pictures, texts, voices and video related modules AI intelligence has been a great number of successful cases, neural networks brought by deep learning are also in continuous optimization, but damage data of the car insurance industry is really unstructured data, including texts, amounts and dates, and has a highly complex hierarchical structure, if data processing, data conversion, neural network structure construction, model parameter adjustment and the like are carried out from 0, a great deal of effort and time are undoubtedly spent, and whether replicability is to be referred to or not is required, and meanwhile, leakage of data and personal privacy is easily caused when car insurance data is shared.
Disclosure of Invention
The invention discloses a method for establishing a vehicle risk assessment loss code convenient for AI image identification, which aims to solve any one of the above and other potential problems in the prior art.
In order to solve the technical problems, the technical scheme of the invention is as follows: a vehicle risk assessment code establishment method convenient for AI image identification is characterized in that vehicle risk settlement data are simplified, a collision part and a damage degree value of a vehicle assessment accident are obtained after analysis, the obtained damage degree value is converted and encrypted to obtain the vehicle risk assessment code convenient for AI image identification, the obtained vehicle risk assessment code has the advantages of avoiding data leakage, protecting personal privacy, and carrying out data sharing on restored data in a picture mode.
Further, the establishment method specifically includes the following steps:
s1) acquiring vehicle insurance claim data of an insurance company;
s2) preprocessing the acquired vehicle insurance claim data to obtain a azimuth chart of the damage assessment project;
s3) extracting the item type, the item name, the maintenance type and the item remarks from the acquired vehicle insurance claim data, and determining the damage degree value of the damage assessment item;
s4) converting the confirmed damage degree value obtained in the step S3), obtaining picture pixel matrix data through a square item distribution map of n x n, and regenerating picture information to obtain the vehicle risk damage assessment code convenient for AI image identification.
Further, the vehicle insurance claim data in the step S1) is an assessment list with cases, wherein the assessment list comprises an accessory list, a working hour list, an accessory list and an external repair list;
wherein, contain accessory name field in the accessory list, contain man-hour name field and maintenance type field in the man-hour list, the auxiliary material list contains auxiliary material name field, and the external repair list contains external repair name field.
Further, the specific steps of the pretreatment in S2) are as follows:
s2.1) converting the acquired vehicle risk assessment data into specified format data;
s2.2) extracting project information from the specified format data obtained in the step S2.1);
s2.3) carrying out standardization processing on the project information in a mode of combining the extracted project information with an alias library, and obtaining a azimuth chart of the damaged project.
Further, the S2.3) is specifically:
s2.31) coding according to standard names in an alias library, and determining the azimuth according to industry standards;
s2.32) establishing a direction diagram of nine directions according to the extracted project information;
s2.32) corresponding the azimuth of the item to the azimuth map to obtain an azimuth map of the n-by-n loss assessment item.
Further, the specific steps of S3) are as follows:
s3.1) extracting the item type, the item name, the maintenance type and the item remark from the car insurance claim data obtained in the S1),
s3.2) determining the damage degree value of the damage-assessment item according to the item type, the item name, the maintenance type and damage-assessment data contained in the item remarks extracted in the S3.1).
Further, the specific steps of S4) are as follows:
s4.1), converting the damage degree value obtained in the step S3.2) into a binary value, and then converting the binary value into a hexadecimal value;
s4.2) carrying out one-to-one correspondence on the hexadecimal numerical value obtained in the step S4.1) and the azimuth map of the n-by-n loss assessment item obtained in the step S2.32), so as to obtain picture pixel matrix data;
s4.3) converting the picture pixel matrix data obtained in the step 4.2) into a picture, namely the vehicle risk loss assessment code which is convenient for AI image identification.
The vehicle loss identification system comprises an identification model, wherein the identification model is obtained by training the vehicle risk assessment loss code obtained by the building method.
The processor is used for running a program, wherein the program executes the vehicle risk assessment code establishment method which is convenient for AI image identification.
A readable storage medium comprising a memory, the memory storing a program, and a processor, the processor executing the vehicle risk assessment code establishment method for facilitating AI image recognition.
The vehicle risk loss assessment code convenient for AI image identification has the following beneficial effects:
1. the vehicle risk assessment data is simplified, and key information can be contained by a small picture.
2. The damage degree is in the form of a picture, the existing image recognition neural network structure can be directly used for model training, and a model is quickly generated.
3. The method can abstract the vehicle model structure through nine azimuth forms by establishing the azimuth map of the n-by-n damage assessment item, and can simply and clearly judge the collision position of the vehicle damage assessment accident.
4. In the aspect of data security, only the accessory corresponding to each pixel point, namely the password template, is protected, the picture cannot be restored to case data, and the case data is effectively prevented from being leaked.
Drawings
The above and other objects, features and advantages of the present disclosure will become more apparent from the following description of the embodiments of the present disclosure with reference to the accompanying drawings. The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
It is evident that the drawings in the following description are only some embodiments of the present invention and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art. In the drawings:
fig. 1 is a flowchart of a method for establishing a risk assessment loss code for facilitating AI image recognition according to the present invention.
Fig. 2 is a schematic diagram of an original 32×32 pixel in an embodiment of the method of the present invention.
Fig. 3 is a schematic diagram of an original 32×32 pixel point segmentation nine-palace chart in an embodiment of the present invention.
FIG. 4 is a diagram of pixel values converted from the degree of accessory loss in an embodiment of the present invention.
Fig. 5 is a schematic diagram of 32×32 pixels after filling the fitting in an embodiment of the present invention.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the invention. However, it will be appreciated by those skilled in the art that the inventive aspects may be practiced without one or more of the specific details, or that other methods may be employed. In other instances, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the invention.
The invention relates to a vehicle risk damage assessment code establishment method convenient for AI image identification, which simplifies vehicle risk claim data, obtains the collision part and damage degree value of a vehicle damage assessment accident after analysis, converts and encrypts the obtained damage degree value to obtain the vehicle risk damage assessment code convenient for AI image identification, and obtains the vehicle risk damage assessment code to avoid data leakage, protect personal privacy and share data in a picture mode.
As shown in fig. 1, the establishment method specifically includes the following steps:
s1) acquiring vehicle insurance claim data of an insurance company;
s2) preprocessing the acquired vehicle insurance claim data to obtain a azimuth chart of the damage assessment project;
s3) extracting the item type, the item name, the maintenance type and the item remarks from the acquired vehicle insurance claim data, and determining the damage degree value of the damage assessment item;
s4) converting the confirmed damage degree value obtained in the step S3), obtaining picture pixel matrix data through a square item distribution map of n x n, and regenerating picture information to obtain the vehicle risk damage assessment code convenient for AI image identification.
The vehicle insurance claim data in the S1) is an assessment list with cases, wherein the assessment list comprises an accessory list, a working hour list, an accessory list and an external repair list;
wherein, contain accessory name field in the accessory list, contain man-hour name field and maintenance type field in the man-hour list, the auxiliary material list contains auxiliary material name field, and the external repair list contains external repair name field.
The pretreatment in S2) comprises the following specific steps:
s2.1) converting the acquired vehicle risk assessment data into specified format data;
s2.2) extracting project information from the specified format data obtained in the step S2.1);
s2.3) carrying out standardization processing on the project information in a mode of combining the extracted project information with an alias library, and obtaining a azimuth chart of the damaged project.
The S2.3) is specifically as follows:
s2.31) coding according to standard names in an alias library, and determining the azimuth according to industry standards;
s2.32) establishing a direction diagram of nine directions according to the extracted project information;
s2.32) corresponding the azimuth of the item to the azimuth map to obtain an azimuth map of the n-by-n loss assessment item.
The specific steps of the S3) are as follows:
s3.1) extracting the item type, the item name, the maintenance type and the item remark from the car insurance claim data obtained in the S1),
s3.2) determining the damage degree value of the damage-assessment item according to the item type, the item name, the maintenance type and damage-assessment data contained in the item remarks extracted in the S3.1).
The specific steps of the S4) are as follows:
s4.1), converting the damage degree value obtained in the step S3.2) into a binary value, and then converting the binary value into a hexadecimal value;
s4.2) carrying out one-to-one correspondence on the hexadecimal numerical value obtained in the S4.1) and the azimuth map of the n x n loss assessment item obtained in the S2.32), so as to obtain picture pixel matrix data;
s4.3) converting the picture pixel matrix data obtained in the step 4.2) into a picture, namely the vehicle risk loss assessment code which is convenient for AI image identification.
The alias library and the industry standard are EPC (electronic catalog) databases of various large automobile manufacturers in the automobile industry.
The vehicle loss identification system comprises an identification model, wherein the identification model is obtained by training the vehicle risk assessment loss code obtained by the building method.
The processor is used for running a program, wherein the program executes the vehicle risk assessment code establishment method which is convenient for AI image identification.
A readable storage medium comprising a memory, the memory storing a program, and a processor, the processor executing the vehicle risk assessment code establishment method for facilitating AI image recognition.
The insurance company vehicle insurance claim data needs specific format data for transmission, and the transmission method is not limited to JSON, EXCEL, TXT, but the transmission method must meet the requirement of an assessment list with a case, wherein the assessment list comprises an accessory list, a working hour list, an auxiliary material list and an external repair list. The accessory list is required to be provided with an accessory name field, the man-hour list is required to be provided with a man-hour name field, a maintenance type field, the accessory list is required to be provided with an accessory name field, and the external repair list is required to be provided with an external repair name field;
and the pretreatment can sort the characters of the project names, reject the characters and convert the characters, thereby achieving the effect of unifying the description of the names.
The alias library is provided with a standard name of a vehicle common item defined by the user, a standard name code, a direction to which the standard name belongs, an upper left, a middle upper right, a middle left, a middle right, a lower left, a middle lower middle right and nine directions to which the standard name belongs, and various kinds of calling of the standard name in the industry are called aliases.
The preprocessing includes extracting azimuth characters in project names, for example: in the front, back, left and right, sorting is performed after extraction, special characters, spaces, tab, numbers and the like contained in the names are removed, then standard names and standard aliases in an aliases library are matched, and the items are matched to corresponding standard name codes.
And judging the damage degree. The method comprises the steps of extracting a project type, a project name, a maintenance type and a project remark, judging the damage degree of the project, and judging from the project type, the project name, the maintenance type, the project remark and the four dimensions, wherein the judging mode is divided into a specified project type, a specified project name, a specified maintenance type and a specified keyword. The damage degree of the item is classified, the damage program expresses the characteristic that each item has unique damage degree, so that each item meeting the judgment condition can obtain unique damage degree results no matter how many times, and finally the damage degree of the item is 0-8.
The azimuth map of the n×n impairment term may select x×x standard names from a standard name library, which may be 4*4, 16×16, 32×32, etc. The method is characterized in that the method is required to meet square distribution, according to nine directions of directions to which standard names belong, the standard names are sequentially arranged in a mode of cutting the square into nine-grid squares, so that an item distribution diagram is formed, namely a password template is formed, and encryption is required after a picture is generated.
The picture pixel matrix data is whether 0-8 damage degrees of the items in the case exist or not, 8-bit continuous 0/1 data is generated, binary data can be converted into hexadecimal data well known, and the pixel value of the picture can be represented by hexadecimal data. And then carrying out one-to-one correspondence on the project and the project distribution map, so as to produce pixel matrix data of a picture. And performing data conversion picture operation by a known method to generate a vehicle loss assessment loss code.
The insurance company vehicle insurance claim data is transmitted in a specific format, and the transmission method is not limited to JSON, EXCEL, TXT, but the method is required to meet the requirement of an assessment list with a case, wherein the assessment list comprises an accessory list, a working hour list, an auxiliary material list and an external repair list. The accessory list is required to have an accessory name field, the man-hour list is required to have a man-hour name field, a maintenance type field, the accessory list is required to have an accessory name field, and the external repair list is required to have an external repair name field.
The judgment is carried out from four dimensions of item type, item name, maintenance type, item remark, the judgment mode is divided into whether the specified item type, the specified item name, the specified maintenance type and the specified keyword.
Examples:
the risk assessment code may be applied in AI model training.
1, counting the occurrence times of accessories or working hours in the existing industry data, sorting the occurrence times in a descending order, and selecting 1024 items which occur most in the existing industry data.
And 2, marking the fittings according to the positions of the fittings, namely, upper left, upper middle, upper right, middle left, middle right, lower left, lower middle and lower right, and the upper structure of the vehicle tail, namely, a front fender (L) -lower left, a trunk cover-upper middle, a front headlight (R) -lower right, a roof-middle and middle according to the top view of the vehicle.
The 32 x 32 pixel points are expressed in the form of (x, y) coordinates, and the actual ranges are the upper left corner (1, 1), the upper right corner (32, 1), the lower left corner (1, 32) and the lower right corner (32, 32) as shown in fig. 2.
4, cutting 32 x 32 pixels into nine squares, as shown in figure 3, respectively corresponding to the upper left positions
(1, 1) (11, 11), (12, 1) (21, 1) (12, 11) (21, 11), (upper right) and lower right)
(22, 1) (32, 1) (22, 11) (32, 11), [ 1, 12) (11, 12) (1, 21) (11, 21) ] in the left middle (1, 12) (11, 12) (1, 21) ], in the middle
(12, 12) (21,12) (12, 21) (21, 21), [ 22, 12) (32,12) (22, 21) (32,21) ] in the right middle and lower left
(1, 22) (11, 22) (1, 32) (11, 32), [ 12, 22) (21, 22) (12, 32) (21,32) ] lower middle and right lower
【(22,22)(32,22)(22,32)(32,32)】。
And 5, placing 1024 accessories on each pixel point according to the pixel azimuth area to form a password template, such as a front lappet (L) -lower left- (4, 26), a trunk cover-upper right- (14, 8), a headlight (R) -lower right- (27, 30) and a roof-middle- (16, 16).
And 6, each accessory in the damage assessment list has 0-8 damage degrees. The presence or absence of 0 to 8 lesion levels is respectively designated as 0 and 1. The 8-bit 0/1 data can be obtained, and converted into 0-255 data in a binary mode, for example, the binary data obtained by front lappet (large sheet metal, full spray, disassembly) is 01001010, as shown in fig. 4, the binary data is 74 when converted into 10, and the RGB data is # 4A.4A.4A.
The method needs specific format data for transmission, and the transmission method is not limited to JSON, EXCEL, TXT, but the method must meet the requirement of an assessment list with a case, wherein the assessment list comprises an accessory list, a working hour list, an auxiliary material list and an external repair list. The accessory list is required to have an accessory name field, the man-hour list is required to have a man-hour name field, a maintenance type field, the accessory list is required to have an accessory name field, and the external repair list is required to have an external repair name field.
8, after transmitting the format data according to the step 7, extracting the corresponding fields under the corresponding list to form a table as shown below
| Case(s) | Item type | Project name | Maintenance type |
| Case A | Fitting parts | Left anterior lappet | |
| Case A | Man-hour(s) | Left front headlight | Scratch paint |
| Case A | Man-hour(s) | Anterior left lappet | Plastic repair |
| Case B | Auxiliary materials | Condensing agent |
And 9, preprocessing the project names, namely, as shown in step 8, the front left lappet expresses an actual position, and the method needs to establish a project name alias library in advance, wherein the front lappet (L) is taken as an example, the front lappet (L) is a standard name, the front left lappet is the alias of the front lappet (L), and the project names can be subjected to standardization processing through the alias relation.
And 10, judging the damage degree of the project according to the project type, the project name and the maintenance type.
The following are examples of damage levels for several damage assessment items:
example 1: the damage degree A, B, C, D, E and five damage degrees are defined. The method comprises the steps of defining the project type equal to man-hour as damage degree A, defining the project type equal to accessories as damage degree B, defining four-wheel positioning contained in the project name as damage degree C, defining maintenance type disassembly as damage degree D and defining other parts as damage degree E.
Example 2: the degree of damage 1,2,3,4 is defined. The item type is equal to the accessory and is defined as damage degree 1, the item type is equal to the working hour and is defined as damage degree 2, the item type is equal to the auxiliary material and is defined as damage degree 3, and the item type is equal to the external repair and is defined as damage degree 4.
Example 3: the degree of damage 1,2,3,4 is defined. Defining the term name including the "front" keyword as the damage degree
1, the keyword "after" included in the item name is defined as a damage degree 2, the keyword "left" included in the item name is defined as a damage degree 3, and the keyword "right" included in the item name is defined as a damage degree 4.
Example 4 the defined degree of damage can be 1-8 on the basis of example 3. The key words are ' front ', ' rear ', '
"left" and "right" may be any keywords.
According to the industrial situation, each case averagely contains 6-10 accessories and 5-20 working hours, each password template can select different 1024 items and different damage degrees in 8, the password templates are multiple sets, and the formed damage assessment code has a strong encryption means and cannot be analyzed on the premise that the password templates cannot be obtained because of uncertainty of the password templates. And selecting any one set of password templates, and performing data conversion in a step 6 mode.
12: filling the data according to the above method will generate a damage-assessment code by assessing all damage-assessment items of the list, as shown in fig. 5.
13: the impairment codes generated by a large number of impairment sheets are used for training an image recognition model.
Any vehicle risk assessment code convenient for AI image identification provided by the embodiment of the application is based on the same design conception, and the technical means in any embodiment of the application can be freely combined, and the combined technical means are still within the protection scope of the application.
Those skilled in the art will appreciate that the features recited in the various embodiments of the disclosure and/or in the claims may be combined in various combinations and/or combinations, even if such combinations or combinations are not explicitly recited in the disclosure. These examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the embodiments cannot be used advantageously in combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be made by those skilled in the art without departing from the scope of the disclosure, and such alternatives and modifications are intended to fall within the scope of the disclosure.
Claims (10)
1. A method for establishing a vehicle risk assessment code convenient for AI image identification is characterized in that the method simplifies vehicle risk claim data, obtains a collision part and a damage degree value of a vehicle assessment accident after analysis, converts and encrypts the obtained damage degree value to obtain the vehicle risk assessment code convenient for AI image identification, obtains the vehicle risk assessment code, and shares data with restored data in a picture mode.
2. The method according to claim 1, characterized in that it comprises in particular the following steps:
s1) acquiring vehicle insurance claim data of an insurance company;
s2) preprocessing the acquired vehicle insurance claim data to obtain a azimuth chart of the damage assessment project;
s3) extracting the item type, the item name, the maintenance type and the item remarks from the acquired vehicle insurance claim data, and determining the damage degree value of the damage assessment item;
s4) converting the confirmed damage degree value obtained in the step S3), obtaining picture pixel matrix data through a square item distribution map of n x n, and regenerating picture information to obtain the vehicle risk damage assessment code convenient for AI image identification.
3. The method according to claim 2, wherein the vehicle insurance claim data in S1) is an impairment list with cases, and the impairment list includes an accessory list, a man-hour list, an accessory list and an external repair list;
wherein, contain accessory name field in the accessory list, contain man-hour name field and maintenance type field in the man-hour list, the auxiliary material list contains auxiliary material name field, and the external repair list contains external repair name field.
4. The method according to claim 3, wherein the preprocessing in S2) specifically comprises the following steps:
s2.1) converting the acquired vehicle risk assessment data into specified format data;
s2.2) extracting project information from the specified format data obtained in the step S2.1);
s2.3) carrying out standardization processing on the project information in a mode of combining the extracted project information with an alias library, and obtaining a azimuth chart of the damaged project.
5. The method according to claim 4, wherein the step S2.3) is specifically:
s2.31) coding according to standard names in an alias library, and determining the azimuth according to industry standards;
s2.32) establishing a direction diagram of nine directions according to the extracted project information;
s2.32) corresponding the azimuth of the item to the azimuth map to obtain an azimuth map of the n-by-n loss assessment item.
6. The method according to claim 4, wherein the specific steps of S3) are:
s3.1) extracting the item type, the item name, the maintenance type and the item remarks from the car insurance claim data acquired in the S1);
s3.2) determining the damage degree value of the damage project according to the project type, the project name, the maintenance type and the damage data contained in the project remarks extracted in the S3.1).
7. The method according to claim 5, wherein the specific steps of S4) are:
s4.1), converting the damage degree value obtained in the step S3.2) into a binary value, and then converting the binary value into a hexadecimal value;
s4.2) carrying out one-to-one correspondence on the hexadecimal numerical value obtained in the S4.1) and the azimuth map of the n x n loss assessment item obtained in the S2.32), so as to obtain picture pixel matrix data;
s4.3) converting the picture pixel matrix data obtained in the step 4.2) into a picture, namely the vehicle risk loss assessment code which is convenient for AI image identification.
8. A vehicle damage recognition system, which comprises a recognition model, and is characterized in that the recognition model is obtained by training a vehicle risk assessment code obtained by the building method according to any one of claims 1-7.
9. A processor, wherein the processor is configured to run a program, and wherein the program is configured to perform the vehicle risk assessment loss code creation method for facilitating AI image recognition of any of claims 1-7 when run.
10. A readable storage medium, comprising:
a memory storing a program;
a processor that performs the vehicle risk assessment loss code establishment method for facilitating AI image recognition of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310014542.3A CN116029326B (en) | 2023-01-05 | 2023-01-05 | Method for establishing vehicle risk assessment code convenient for AI image identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310014542.3A CN116029326B (en) | 2023-01-05 | 2023-01-05 | Method for establishing vehicle risk assessment code convenient for AI image identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116029326A true CN116029326A (en) | 2023-04-28 |
| CN116029326B CN116029326B (en) | 2023-07-18 |
Family
ID=86080835
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310014542.3A Active CN116029326B (en) | 2023-01-05 | 2023-01-05 | Method for establishing vehicle risk assessment code convenient for AI image identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116029326B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116308828A (en) * | 2023-05-10 | 2023-06-23 | 凯泰铭科技（北京）有限公司 | Intelligent damage assessment method and system for vehicle with integrated and fused risk data |
| CN116612475A (en) * | 2023-06-01 | 2023-08-18 | 凯泰铭科技（北京）有限公司 | Intelligent correction method and device for vehicle model names in vehicle insurance data |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104392005A (en) * | 2014-12-18 | 2015-03-04 | 北京精友世纪软件技术有限公司 | Automobile rapid loss setting method |
| CN107133876A (en) * | 2017-05-08 | 2017-09-05 | 明觉科技（北京）有限公司 | Car damage identification method and setting loss client |
| CN107274293A (en) * | 2017-06-05 | 2017-10-20 | 郭雅玲 | A kind of equipment is settled a claim method automatically |
| CN107516278A (en) * | 2016-06-15 | 2017-12-26 | 平安科技（深圳）有限公司 | The treating method and apparatus that vehicle insurance is reported a case to the security authorities |
| WO2020101607A2 (en) * | 2018-10-22 | 2020-05-22 | Sicpa Turkey Ürün Güvenli̇ği̇ Sanayi̇ Ve Ti̇caret Anoni̇m Şi̇rketi̇ | Spare parts tracking system and method |
| CN112651757A (en) * | 2020-12-30 | 2021-04-13 | 邦邦汽车销售服务(北京)有限公司 | Automobile traceability label distribution and management method and application |
| CN115563996A (en) * | 2022-10-27 | 2023-01-03 | 杭州宝策供应链管理有限公司 | Detection method for establishing corresponding relation between EPC and TID |
-
2023
- 2023-01-05 CN CN202310014542.3A patent/CN116029326B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104392005A (en) * | 2014-12-18 | 2015-03-04 | 北京精友世纪软件技术有限公司 | Automobile rapid loss setting method |
| CN107516278A (en) * | 2016-06-15 | 2017-12-26 | 平安科技（深圳）有限公司 | The treating method and apparatus that vehicle insurance is reported a case to the security authorities |
| CN107133876A (en) * | 2017-05-08 | 2017-09-05 | 明觉科技（北京）有限公司 | Car damage identification method and setting loss client |
| CN107274293A (en) * | 2017-06-05 | 2017-10-20 | 郭雅玲 | A kind of equipment is settled a claim method automatically |
| WO2020101607A2 (en) * | 2018-10-22 | 2020-05-22 | Sicpa Turkey Ürün Güvenli̇ği̇ Sanayi̇ Ve Ti̇caret Anoni̇m Şi̇rketi̇ | Spare parts tracking system and method |
| CN112651757A (en) * | 2020-12-30 | 2021-04-13 | 邦邦汽车销售服务(北京)有限公司 | Automobile traceability label distribution and management method and application |
| CN115563996A (en) * | 2022-10-27 | 2023-01-03 | 杭州宝策供应链管理有限公司 | Detection method for establishing corresponding relation between EPC and TID |
Non-Patent Citations (2)
| Title |
|---|
| B. SIVASANKARI ET AL.: "Auto Detection Of Joints And Axle Failure In Heavy Load Vehicles Using Artificial Intelligence", IEEE * |
| 殷秀凯;: "全球统一编码与标识助力汽车维修行业健康发展――访中国物品编码中心党委书记 中国自动识别技术协会常务副理事长张琳", 中国自动识别技术, no. 06 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116308828A (en) * | 2023-05-10 | 2023-06-23 | 凯泰铭科技（北京）有限公司 | Intelligent damage assessment method and system for vehicle with integrated and fused risk data |
| CN116308828B (en) * | 2023-05-10 | 2023-08-11 | 凯泰铭科技（北京）有限公司 | Intelligent damage assessment method and system for vehicle with integrated and fused risk data |
| CN116612475A (en) * | 2023-06-01 | 2023-08-18 | 凯泰铭科技（北京）有限公司 | Intelligent correction method and device for vehicle model names in vehicle insurance data |
| CN116612475B (en) * | 2023-06-01 | 2024-01-23 | 凯泰铭科技（北京）有限公司 | Intelligent correction method and device for vehicle model names in vehicle insurance data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116029326B (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116029326B (en) | Method for establishing vehicle risk assessment code convenient for AI image identification | |
| US10546206B2 (en) | Methods for mobile image capture of vehicle identification numbers in a non-document | |
| CN107835496B (en) | Spam short message identification method and device and server | |
| CN107862340A (en) | A kind of model recognizing method and device | |
| Kalist et al. | Possiblistic-fuzzy C-means clustering approach for the segmentation of satellite images in HSL color space | |
| US8320665B2 (en) | Document image segmentation system | |
| CN109410215A (en) | Image processing method, device, electronic equipment and computer-readable medium | |
| CN109344258B (en) | Intelligent self-adaptive sensitive data identification system and method | |
| AU2005201257A1 (en) | Model of documents and method for automatically classifying a document | |
| CN108154160A (en) | Color recognizing for vehicle id method and system | |
| CN110175248B (en) | Face image retrieval method and device based on deep learning and Hash coding | |
| CN105631486A (en) | image character recognition method and device | |
| CN103093238B (en) | based on the visual dictionary construction method of D-S evidence theory | |
| CN115348080B (en) | Comprehensive analysis system and method for vulnerability of network equipment based on big data | |
| CN104915664A (en) | Contact object identification acquisition method and device | |
| CN114896594B (en) | Malicious code detection device and method based on image feature multi-attention learning | |
| CN116502726B (en) | Quantum chip-based data storage system and method | |
| CN113591849A (en) | File review method, device, equipment and storage medium based on signature identification | |
| CN111291712B (en) | Forest fire recognition method and device based on interpolation CN and capsule network | |
| CN101894277A (en) | Container number identification method based on multi-category support vector machines | |
| CN116415180A (en) | Automatic data classification and classification method and device based on identification | |
| CN116108464A (en) | Image processing method, device, electronic equipment and readable storage medium | |
| CN109740369B (en) | Information steganography detection method and device | |
| CN109726625B (en) | Face recognition method, device, terminal equipment and storage medium | |
| CN113190858A (en) | Image processing method, system, medium and device based on privacy protection |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |