CN112419072A - Automobile insurance anti-leakage calculation method based on automobile physical attributes - Google Patents
Automobile insurance anti-leakage calculation method based on automobile physical attributes Download PDFInfo
- Publication number
- CN112419072A CN112419072A CN202011193920.1A CN202011193920A CN112419072A CN 112419072 A CN112419072 A CN 112419072A CN 202011193920 A CN202011193920 A CN 202011193920A CN 112419072 A CN112419072 A CN 112419072A
- Authority
- CN
- China
- Prior art keywords
- parts
- automobile
- leakage
- data
- algorithm based
- 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
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
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Technology Law (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides an automobile insurance anti-leakage algorithm based on automobile physical attributes, which is used for counting a part damage list of an automobile type and extracting point cloud data of parts according to insurance risk data and automobile type geometric data; calculating a minimum distance matrix between each part according to the point cloud data, determining the sum of the distances between each damaged part and the N parts closest to the damaged part in each case according to the distance matrix, and sequencing the damaged parts from small to large; and judging whether the parts have leakage parts according to the sequencing result. The algorithm provided by the invention judges the leakage part according to the distance between the parts by utilizing the spatial position relationship of the automobile parts, and corrects the distance between the parts by considering the material property and the connection relationship of the parts, so that more accurate part loss condition is obtained, the leakage part is rapidly and accurately detected, and the loss of insurance company reimbursement is reduced.
Description
Technical Field
The invention belongs to the technical field of automobile insurance anti-leakage, and particularly relates to an automobile insurance anti-leakage algorithm based on automobile physical attributes.
Background
In automobile insurance claims, cases of fraud guarantee often occur, wherein the fraud guarantee is most common when automobile parts are artificially damaged by expansion and are damaged by accidents other than the accident. At present, leakage pieces are determined mainly by judging and checking one by means of experienced loss assessment personnel, the method has long time period and low efficiency for mass automobile insurance cases, so that the economic loss of an insurance company is large, the problem of fraud cheating and protection in the insurance industry is urgently solved by means of an emerging technology, the screening of the leakage pieces can be completed quickly and efficiently by an anti-leakage early warning model based on vehicle attributes, the fraud cheating and protection cases are reduced, and the economic loss of the insurance company is further reduced.
Disclosure of Invention
In view of the above, the invention aims to provide an automobile insurance anti-leakage algorithm based on automobile physical attributes to solve the problem that the economic loss of an insurance company is large due to long time period and low efficiency of a loss assessment worker for judging and checking a large number of automobile insurance cases one by one.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
the automobile insurance anti-leakage algorithm based on the automobile physical attributes comprises the following steps:
s1, counting and manufacturing a part damage list of a certain vehicle type according to the vehicle insurance risk data;
s2, according to the part damage list and the vehicle type geometric data, finding out the geometric data of the damaged parts in the step S1, extracting point cloud data, and meanwhile, making a part material attribute information table and a part connection relation table;
s3, calculating a minimum distance matrix of each part and the rest parts according to the point cloud data of the parts, and correcting the distance matrix according to the part connection relation table;
s4, determining the sum of the distances between each damaged part and the N parts with the shortest distance in each case according to the corrected minimum distance matrix in the step S3, and correcting the sum of the distances according to the material attribute information table of the parts;
s5, sorting and comparing the sum of the distances corresponding to each part corrected in the step S4;
and S6, judging whether the corresponding parts are leakage parts from head to head one by one according to the ratio in the step 5.
Further, the geometric data in step S2 includes positions of the components on the entire vehicle, shapes of the components, sizes of the components, and connection manners of the components and the entire vehicle.
Further, the part material attribute information table in step S2 includes material attributes of each damaged part, where the material attributes are divided into four damage levels: such as soft plastic, hard plastic, aluminum alloy, and sheet metal.
Further, in the point cloud data in step S2, points with a distance of 5mm are generated from the outer surface of the geometric data of the component, and X, Y, Z coordinates of the points are extracted to create point cloud data of the component.
Further, the component connection relation table in step S2 includes a connection mode between each damaged component and the entire vehicle, where the connection mode is: no connection, buckle connection, gluing and rigid connection; wherein the rigid connection is a bolt, a welding spot and a riveting.
Further, the process of calculating the minimum distance between each part according to the point cloud data of the part in step S3 is as follows: by assigning M, N point cloud data of any two parts, respectively, the euclidean distance D between any one point in M and any one point in N is calculated, and the minimum D is the minimum distance between the two parts.
Further, in step S4, the sum of the distances between each damaged part and the nearest N parts in each emergency case is calculated, and the calculation process is as follows:
and finding a distance matrix of the corresponding parts through the fixed-loss part name of each case, sequencing the numerical values of the distance matrix from small to large, and finding the first N data for summation.
Further, in the step S5, the modified numerical values of the sum of the distances corresponding to each component are sorted and compared, and the implementation process is as follows:
sorting the numerical values of the sum of the distances corresponding to each part from small to large, carrying out ratio between the next numerical value and the previous numerical value, and forming a row vector by the numerical values of the ratio according to the sequence;
further, the step S6 of judging whether the part is a leakage part is implemented as follows:
and judging the size of the intermediate data and 2 one by one according to the ratio, stopping judging and outputting the name of the current corresponding part and the name of the subsequent part as the leakage part when the judged data is more than or equal to 2, and outputting the no-leakage part of the damage assessment list if all the judged data are less than 2.
Compared with the prior art, the automobile insurance anti-leakage algorithm based on the automobile physical attributes has the following advantages:
the algorithm of the invention judges the leakage part according to the distance between the parts by utilizing the spatial position relationship of the automobile parts, and corrects the distance between the parts by considering the material property and the connection relationship of the parts, so as to obtain more accurate loss condition of the parts and further find out the leakage part. According to the test result, the vehicle type leakage detection method can quickly and accurately detect the vehicle type leakage part and reduce the insurance company compensation loss.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate an embodiment of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
fig. 1 is a flowchart of an automobile insurance back-leakage calculation method based on automobile physical attributes according to an embodiment of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used only for convenience in describing the present invention and for simplicity in description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention. Furthermore, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first," "second," etc. may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art through specific situations.
The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
As shown in fig. 1, the automobile insurance anti-leakage algorithm based on the physical attributes of the automobile comprises the following steps:
s1, counting and manufacturing a part damage list of a certain vehicle type according to the vehicle insurance risk data;
s2, according to the part damage list and the vehicle type geometric data, finding out the geometric data of the damaged parts in the step S1, extracting point cloud data, and meanwhile, making a part material attribute information table and a part connection relation table;
s3, calculating a minimum distance matrix of each part and the rest parts according to the point cloud data of the parts, and correcting the distance matrix according to the part connection relation table;
s4, determining the sum of the distances between each damaged part and the N parts with the shortest distance in each case according to the corrected minimum distance matrix in the step S3, and correcting the sum of the distances according to the material attribute information table of the parts;
s5, sorting and comparing the sum of the distances corresponding to each part corrected in the step S4;
and S6, judging whether the corresponding parts are leakage parts from head to head one by one according to the ratio in the step 5.
The geometric data in step S2 includes positions of the components on the entire vehicle, shapes of the components, sizes of the components, and connection modes of the components and the entire vehicle.
The part material attribute information table in step S2 includes material attributes of each damaged part, where the material attributes are divided into four damage levels: such as soft plastic, hard plastic, aluminum alloy and sheet metal, the corresponding correction coefficients are [ k1, k2, k3 and k4], and as the rigidity of the material is higher, the probability of injury after collision is lower, the material is reflected to a spatial position, the distance between parts is farther, and the parts are less prone to damage;
the part material attribute information table is 'part material attribute information, xlsx'.
The point cloud data in the step S2 is generated into points with a distance of 5mm from the outer surface of the geometric data of the component, and X, Y, Z coordinates of the points are extracted to produce point cloud data of the component.
The part connection relation table in step S2 includes a connection mode between each damaged part and the entire vehicle, where the connection mode is: no connection, buckle connection, gluing and rigid connection; the rigid connection is bolts, welding points and riveting, the corresponding correction coefficients are [ t1, t2, t3 and t4], the real distance is obtained when the parts are not connected, when the connection strength is higher, the corresponding linkage damage is lighter, the parts are reflected to a spatial position, the distance between the parts is farther, and the parts are less prone to damage;
the connection relation table of the parts is ' connection relation table of parts ' xlsx '.
The process of calculating the minimum distance between each part according to the point cloud data of the part in the step S3 is as follows: by assigning M, N point cloud data of any two parts, respectively, the euclidean distance D between any one point in M and any one point in N is calculated, and the minimum D is the minimum distance between the two parts.
In step S4, the sum of the distances between each damaged part and the nearest N parts in each case is calculated, and the calculation process is as follows:
finding a distance matrix of corresponding parts through the fixed-loss part name of each case, sequencing the numerical values of the distance matrix from small to large, and finding the first N data for summation;
wherein N is 1/3 rounded of the total number of damaged parts in each case, N is too large in value and cannot display the deviation condition of the parts, and N is too small in value and too large in error;
the summation aims to calculate the distance of each part deviating from the N similar parts, so as to determine the relative position distribution of all parts in the three-dimensional space, and provide a basis for the judgment of subsequent leakage parts (parts deviating from farther parts in the spatial position).
In step S5, the modified numerical values of the sum of the distances corresponding to each component are sorted and compared, and the implementation process is as follows:
sorting the numerical values of the sum of the distances corresponding to each part from small to large, carrying out ratio between the next numerical value and the previous numerical value, and forming a row vector by the numerical values of the ratio according to the sequence;
the implementation process of judging whether the part is a leakage part in the step S6 is as follows:
and (3) judging the size of the intermediate data (rounding except 2) with 2 one by one, stopping judging and outputting the name of the current corresponding part and the name of the subsequent part as leakage parts when the judged data is more than or equal to 2 (the part and the subsequent part are far away from other parts), and outputting the loss assessment list without leakage parts if all the judged data is less than 2.
The specific technical scheme is as follows:
(1) selecting a certain type of vehicle, and making a damaged part list corresponding to the vehicle according to the historical insurance data in a statistical manner;
(2) extracting point cloud data of the parts from the geometric data of the vehicle type according to the part list;
(3) four damage grades are divided according to the material properties of the parts: soft plastics, hard plastics, aluminum alloys, metal plates;
(4) the connection mode of the parts is divided into four grades: no connection, snap connection, gluing, rigid connection (bolts, welding points, riveting);
(5) calculating the distance between every two parts according to the point cloud data, and correcting the distance according to the connection relation between every two parts;
(6) calculating the sum of the distances between each damaged part and N parts closest to each damaged part in each emergency case (the distance is taken as a whole according to the number of the fixed-loss parts divided by 3), and correcting the sum of the distances according to the material properties of the parts;
(7) sorting the values of the sum of the distances corrected in the step 6 from small to large, and performing two adjacent back-to-front ratios;
(8) selecting the second half-section data of the ratio, judging with 2 one by one from front to back, and outputting the part name corresponding to the ratio and all parts behind the part sequenced according to the step 6 as leakage parts when the ratio is more than 2; if the ratio is not larger than 2, the leakage-free part is output.
The correction coefficients corresponding to the four grades of the material properties in the step (3) are [ k1, k2, k3 and k4], and as the rigidity of the material is higher, the probability of injury after collision is lower, the material reflects to a space position, the distance between parts is farther, and the parts are less prone to damage.
The correction coefficients corresponding to the four levels of the connection mode in the step (4) are [ t1, t2, t3 and t4], the real distance is obtained when the parts are not connected, when the connection strength is higher, the corresponding associated damage is lighter, the parts are reflected to the space position, the distance between the parts is farther, and the parts are less prone to damage.
Examples of Accord model reverse leakage:
the method comprises the following steps: and according to the insurance risk data of the automobile, counting the damage names and the damage numbers of the parts of the automobile. The number of damaged parts of the vehicle is 982 according to statistics.
Step two: according to a part damage list, point cloud data of each damaged part is extracted from the geometrical data of the Accord vehicle type (the position, the shape, the size and the connection mode of the part in the geometrical data are consistent with those of a whole vehicle), the part name is named and stored into an xlsx format, and meanwhile, part material attribute information xlsx and a part connection relation table xlsx are manufactured according to the material attribute of the part and the connection relation among the parts.
Step three: and (4) calculating the minimum distance between every two parts according to the point cloud data of the parts (the distance calculation adopts Euclidean distance calculation), wherein the distance is obtained through the Euclidean distance of the minimum point cloud data in every two parts.
And correcting the distance matrix of the parts according to a part connection relation table xlsx.
Step four: and D, determining the sum S of the distances between each damaged part and the nearest N (the number of the damaged parts is divided by 3 to be rounded) parts in each case according to the distance matrix between every two parts obtained in the step three, and correcting the sum of the distances according to the material attributes of the parts.
Step five: the sum of the distances between each damaged part and the N parts closest to the damaged part in each case is sorted from small to large.
Step six: and D, according to the sequencing vector of the sum of the distances in the step five from small to large, carrying out ratio between the next numerical value and the previous numerical value, judging the size of the data in the middle of the ratio one by one with 2, stopping judging and outputting the name of the current corresponding part and the name of the next part as a leakage part when the judgment data is more than or equal to 2, and outputting the loss assessment list without the leakage part if all the judgment data is less than 2.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (9)
1. The automobile insurance anti-leakage algorithm based on the automobile physical attributes is characterized by comprising the following steps of:
s1, counting and manufacturing a part damage list of a certain vehicle type according to the vehicle insurance risk data;
s2, according to the part damage list and the vehicle type geometric data, finding out the geometric data of the damaged parts in the step S1, extracting point cloud data, and meanwhile, making a part material attribute information table and a part connection relation table;
s3, calculating a minimum distance matrix of each part and the rest parts according to the point cloud data of the parts, and correcting the distance matrix according to the part connection relation table;
s4, determining the sum of the distances between each damaged part and the N parts with the shortest distance in each case according to the corrected minimum distance matrix in the step S3, and correcting the sum of the distances according to the material attribute information table of the parts;
s5, sorting and comparing the sum of the distances corresponding to each part corrected in the step S4;
and S6, judging whether the corresponding parts are leakage parts from head to head one by one according to the ratio in the step 5.
2. The automobile insurance anti-leakage algorithm based on the automobile physical property according to claim 1, characterized in that: the geometric data in step S2 includes positions of the components on the entire vehicle, shapes of the components, sizes of the components, and connection modes of the components and the entire vehicle.
3. The automobile insurance anti-leakage algorithm based on the automobile physical property according to claim 1, characterized in that: the part material attribute information table in step S2 includes material attributes of each damaged part, where the material attributes are divided into four damage levels: such as soft plastic, hard plastic, aluminum alloy, and sheet metal.
4. The automobile insurance anti-leakage algorithm based on the automobile physical property according to claim 1, characterized in that: the point cloud data in the step S2 is generated into points with a distance of 5mm from the outer surface of the geometric data of the component, and X, Y, Z coordinates of the points are extracted to produce point cloud data of the component.
5. The automobile insurance anti-leakage algorithm based on the automobile physical property according to claim 1, characterized in that: the part connection relation table in step S2 includes a connection mode between each damaged part and the entire vehicle, where the connection mode is: no connection, buckle connection, gluing and rigid connection; wherein the rigid connection is a bolt, a welding spot and a riveting.
6. The automobile insurance anti-leakage algorithm based on the automobile physical property according to claim 1, characterized in that: the process of calculating the minimum distance between each part according to the point cloud data of the part in the step S3 is as follows: by assigning M, N point cloud data of any two parts, respectively, the euclidean distance D between any one point in M and any one point in N is calculated, and the minimum D is the minimum distance between the two parts.
7. The automobile insurance anti-leakage algorithm based on the automobile physical property according to claim 1, characterized in that: in step S4, the sum of the distances between each damaged part and the nearest N parts in each case is calculated, and the calculation process is as follows:
and finding a distance matrix of the corresponding parts through the fixed-loss part name of each case, sequencing the numerical values of the distance matrix from small to large, and finding the first N data for summation.
8. The automobile insurance anti-leakage algorithm based on the automobile physical property according to claim 1, characterized in that: in step S5, the modified numerical values of the sum of the distances corresponding to each component are sorted and compared, and the implementation process is as follows:
and sorting the numerical values of the sum of the distances corresponding to each part from small to large, carrying out ratio of the next numerical value to the previous numerical value, and forming a row vector by the numerical values of the ratio according to the sequence.
9. The automobile insurance anti-leakage algorithm based on the automobile physical property according to claim 1, characterized in that: the implementation process of judging whether the part is a leakage part in the step S6 is as follows:
and judging the size of the intermediate data and 2 one by one according to the ratio, stopping judging and outputting the name of the current corresponding part and the name of the subsequent part as the leakage part when the judged data is more than or equal to 2, and outputting the no-leakage part of the damage assessment list if all the judged data are less than 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011193920.1A CN112419072B (en) | 2020-10-30 | 2020-10-30 | Automobile insurance anti-leakage method based on automobile physical attributes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011193920.1A CN112419072B (en) | 2020-10-30 | 2020-10-30 | Automobile insurance anti-leakage method based on automobile physical attributes |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112419072A true CN112419072A (en) | 2021-02-26 |
| CN112419072B CN112419072B (en) | 2022-10-14 |
Family
ID=74827116
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011193920.1A Active CN112419072B (en) | 2020-10-30 | 2020-10-30 | Automobile insurance anti-leakage method based on automobile physical attributes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112419072B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN106709808A (en) * | 2016-11-22 | 2017-05-24 | 中国平安财产保险股份有限公司 | Automatic filtering method and system of unique fitting based on intelligent auto insurance loss assessment platform |
| CN107798618A (en) * | 2017-04-11 | 2018-03-13 | 平安科技（深圳）有限公司 | A kind of intelligent Claims Resolution treating method and apparatus |
| CN108346036A (en) * | 2018-03-06 | 2018-07-31 | 平安科技（深圳）有限公司 | Insurance policy concentrates vouching method, electronic device and readable storage medium storing program for executing |
| CN108845210A (en) * | 2018-07-04 | 2018-11-20 | 中国汽车技术研究中心有限公司 | A kind of automobile fuse circuit electric performance test apparatus and system |
| CN109345395A (en) * | 2018-09-12 | 2019-02-15 | 医倍思特（北京）医疗信息技术有限公司 | A kind of anti-fake system and method for settlement of insurance claim |
| CN109635824A (en) * | 2018-12-14 | 2019-04-16 | 深源恒际科技有限公司 | A kind of images match deep learning method and system |
| CN110298125A (en) * | 2019-07-03 | 2019-10-01 | 中汽研（天津）汽车工程研究院有限公司 | A kind of fatigue analysis method based on virtual test field technology |
| CN110689443A (en) * | 2019-09-02 | 2020-01-14 | 中国平安财产保险股份有限公司 | Insurance data processing method and device, storage medium and server |
| CN210804454U (en) * | 2019-10-09 | 2020-06-19 | 阳光财产保险股份有限公司 | Monitoring device for vehicle insurance claims settlement and replacement |
| CN211597934U (en) * | 2019-12-02 | 2020-09-29 | 中国汽车技术研究中心有限公司 | Electric automobile strorage device |
-
2020
- 2020-10-30 CN CN202011193920.1A patent/CN112419072B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709808A (en) * | 2016-11-22 | 2017-05-24 | 中国平安财产保险股份有限公司 | Automatic filtering method and system of unique fitting based on intelligent auto insurance loss assessment 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 |
| CN107798618A (en) * | 2017-04-11 | 2018-03-13 | 平安科技（深圳）有限公司 | A kind of intelligent Claims Resolution treating method and apparatus |
| CN108346036A (en) * | 2018-03-06 | 2018-07-31 | 平安科技（深圳）有限公司 | Insurance policy concentrates vouching method, electronic device and readable storage medium storing program for executing |
| CN108845210A (en) * | 2018-07-04 | 2018-11-20 | 中国汽车技术研究中心有限公司 | A kind of automobile fuse circuit electric performance test apparatus and system |
| CN109345395A (en) * | 2018-09-12 | 2019-02-15 | 医倍思特（北京）医疗信息技术有限公司 | A kind of anti-fake system and method for settlement of insurance claim |
| CN109635824A (en) * | 2018-12-14 | 2019-04-16 | 深源恒际科技有限公司 | A kind of images match deep learning method and system |
| CN110298125A (en) * | 2019-07-03 | 2019-10-01 | 中汽研（天津）汽车工程研究院有限公司 | A kind of fatigue analysis method based on virtual test field technology |
| CN110689443A (en) * | 2019-09-02 | 2020-01-14 | 中国平安财产保险股份有限公司 | Insurance data processing method and device, storage medium and server |
| CN210804454U (en) * | 2019-10-09 | 2020-06-19 | 阳光财产保险股份有限公司 | Monitoring device for vehicle insurance claims settlement and replacement |
| CN211597934U (en) * | 2019-12-02 | 2020-09-29 | 中国汽车技术研究中心有限公司 | Electric automobile strorage device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112419072B (en) | 2022-10-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6683985B1 (en) | Method of discriminating shape of free-form curved surface | |
| CN112200225B (en) | Steel rail damage B display image identification method based on deep convolution neural network | |
| CA2561939A1 (en) | Method and system for forecasting events and results based on geospatial modeling | |
| CN111299318B (en) | Automatic determination method for surface quality of hot-rolled plate strip product | |
| CN104899892B (en) | A kind of quickly star map image asterism extracting method | |
| CN112906547A (en) | Railway train windshield breakage fault detection method based on E-YOLO | |
| CN112419072B (en) | Automobile insurance anti-leakage method based on automobile physical attributes | |
| Behera et al. | Advanced feature detection algorithms for incrementally formed sheet metal parts | |
| JP5123244B2 (en) | Shape defect inspection device, shape modeling device, and shape defect inspection program | |
| CN116500048B (en) | Cable clamp defect detection method, device, equipment and medium | |
| CN107941812A (en) | Information processing method and electronic equipment | |
| CN110335242A (en) | A kind of tire X-ray defect detection method based on multi-model fusion | |
| CN1971619A (en) | Testing algorithm of image border based on cellular automata | |
| JP4956207B2 (en) | Rear shape classification judgment device | |
| CN114396892B (en) | Track curvature measuring method for track traffic curve | |
| CN101995213B (en) | Detection method of double-curvature plate after cold forming | |
| CN113159230A (en) | Metallographic grade classification method based on deep learning | |
| CN117390762B (en) | Full-flow ship safety design analysis method | |
| CN114972739B (en) | Image target detection method based on target centroid relation | |
| CN110288047A (en) | A kind of big data feature dimension reduction method and tool for abnormality detection | |
| JP4971811B2 (en) | Function database generation method and function database generation device | |
| US20240221147A1 (en) | Quality inspection method and apparatus and production method and device for connecting piece, and medium | |
| CN115271616B (en) | Inland river harbor navigation smart item type list system and method based on big data | |
| Li et al. | Head Shape Design Of Chinese 400 Km/H High-Speed Trains Based on Pedigree Feature Parameterization | |
| CN113837879B (en) | Abnormality detection method for index quotation |
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 |