CN109443301B - Vehicle loss assessment method, computer readable storage medium and server - Google Patents
Vehicle loss assessment method, computer readable storage medium and server Download PDFInfo
- Publication number
- CN109443301B CN109443301B CN201811115698.6A CN201811115698A CN109443301B CN 109443301 B CN109443301 B CN 109443301B CN 201811115698 A CN201811115698 A CN 201811115698A CN 109443301 B CN109443301 B CN 109443301B
- Authority
- CN
- China
- Prior art keywords
- deformation
- damage
- damage assessment
- vector
- vehicle
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000006378 damage Effects 0.000 claims abstract description 240
- 239000013598 vector Substances 0.000 claims abstract description 159
- 239000011159 matrix material Substances 0.000 claims description 45
- 230000006870 function Effects 0.000 claims description 16
- 238000007405 data analysis Methods 0.000 abstract 1
- 238000012545 processing Methods 0.000 description 6
- 230000006735 deficit Effects 0.000 description 5
- 238000010276 construction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001125 extrusion Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008832 photodamage Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
- G01B21/32—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring the deformation in a solid
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B5/00—Measuring arrangements characterised by the use of mechanical techniques
- G01B5/0025—Measuring of vehicle parts
-
- 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
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- 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)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention belongs to the technical field of computers, and particularly relates to a vehicle damage assessment method based on big data analysis, a computer-readable storage medium and a server. The method comprises the steps that a vehicle loss assessment request sent by a terminal device is received, and a vehicle identifier is extracted from the vehicle loss assessment request; issuing a sensor data acquisition instruction to a sensor control device of a target vehicle, wherein the target vehicle is a vehicle corresponding to the vehicle identifier; receiving a sensor data packet fed back by the sensor control device, wherein the sensor data packet comprises deformation data of each part of the target vehicle, which is acquired by a sensor group in the target vehicle; and constructing a damage assessment deformation vector of the target vehicle according to the deformation data of each part of the target vehicle, and performing damage assessment on the target vehicle according to the damage assessment deformation vector. The whole damage assessment process is completed automatically, data collected by the sensors provide assessment basis, and the accuracy of the damage assessment result is greatly improved.
Description
Technical Field
The invention belongs to the technical field of computers, and particularly relates to a vehicle damage assessment method, a computer-readable storage medium and a server.
Background
With the development of vehicle technology and the sharp increase of the number of vehicles, the probability of accidents such as scratch and rear-end collision between vehicles is greatly increased. When these accidents occur, vehicle damage is usually done by a traffic police or insurance company.
In the prior art, when vehicle damage assessment is carried out, damage assessment personnel usually carry out manual assessment aiming at specific scenes according to own past experience, the personal judgment of the damage assessment personnel is mainly relied on, the subjectivity is strong, and the final obtained damage assessment result is often low in accuracy.
Disclosure of Invention
In view of this, embodiments of the present invention provide a vehicle loss assessment method, a computer-readable storage medium, and a server, so as to solve the problems of strong subjectivity and low accuracy when manually performing vehicle loss assessment.
A first aspect of an embodiment of the present invention provides a vehicle damage assessment method, which may include:
receiving a vehicle loss assessment request sent by a terminal device, and extracting a vehicle identifier from the vehicle loss assessment request;
issuing a sensor data acquisition instruction to a sensor control device of a target vehicle, wherein the target vehicle is a vehicle corresponding to the vehicle identifier;
receiving a sensor data packet fed back by the sensor control device, wherein the sensor data packet comprises deformation data of each part of the target vehicle, which is acquired by a sensor group in the target vehicle;
and constructing a damage assessment deformation vector of the target vehicle according to the deformation data of each part of the target vehicle, and performing damage assessment on the target vehicle according to the damage assessment deformation vector.
A second aspect of embodiments of the present invention provides a computer-readable storage medium storing computer-readable instructions, which when executed by a processor implement the steps of:
receiving a vehicle loss assessment request sent by a terminal device, and extracting a vehicle identifier from the vehicle loss assessment request;
issuing a sensor data acquisition instruction to a sensor control device of a target vehicle, wherein the target vehicle is a vehicle corresponding to the vehicle identifier;
receiving a sensor data packet fed back by the sensor control device, wherein the sensor data packet comprises deformation data of each part of the target vehicle, which is acquired by a sensor group in the target vehicle;
and constructing a damage assessment deformation vector of the target vehicle according to the deformation data of each part of the target vehicle, and performing damage assessment on the target vehicle according to the damage assessment deformation vector.
A third aspect of the embodiments of the present invention provides a server, including a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, where the processor implements the following steps when executing the computer readable instructions:
receiving a vehicle loss assessment request sent by a terminal device, and extracting a vehicle identifier from the vehicle loss assessment request;
issuing a sensor data acquisition instruction to a sensor control device of a target vehicle, wherein the target vehicle is a vehicle corresponding to the vehicle identifier;
receiving a sensor data packet fed back by the sensor control device, wherein the sensor data packet comprises deformation data of each part of the target vehicle, which is acquired by a sensor group in the target vehicle;
and constructing a damage assessment deformation vector of the target vehicle according to the deformation data of each part of the target vehicle, and performing damage assessment on the target vehicle according to the damage assessment deformation vector.
Compared with the prior art, the embodiment of the invention has the following beneficial effects: the method comprises the steps of issuing a sensor data acquisition command to a sensor control device of a target vehicle after receiving a vehicle loss assessment request, thereby acquiring a sensor data packet fed back by the sensor control device, wherein the sensor data packet comprises deformation data of each part of the target vehicle acquired by a sensor group in the target vehicle, constructing a loss assessment deformation vector of the target vehicle according to the deformation data, and assessing the loss of the target vehicle according to the loss assessment deformation vector. The whole damage assessment process is completed automatically without any manual intervention of damage assessment personnel, dependence on personal experience of the damage assessment personnel is eliminated, data collected by the sensor provides a basis for objectively and accurately evaluating vehicles, and accuracy of damage assessment results is greatly improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a flow chart of one embodiment of a method for vehicle damage assessment in accordance with embodiments of the present invention;
FIG. 2 is a schematic flow chart of constructing a damage assessment deformation vector of a target vehicle based on deformation data of various portions of the target vehicle;
FIG. 3 is a schematic flow chart of damage assessment of a target vehicle based on a damage assessment deformation vector;
FIG. 4 is a schematic flow chart of a process of calculating weight coefficients;
fig. 5 is a structural view of an embodiment of a vehicle damage assessment apparatus according to an embodiment of the present invention;
fig. 6 is a schematic block diagram of a server according to an embodiment of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, an embodiment of a method for determining damage to a vehicle according to an embodiment of the present invention may include:
and step S101, obtaining a vehicle damage assessment request sent by a receiving terminal device, and extracting a vehicle identifier from the vehicle damage assessment request.
After a vehicle accident occurs, a vehicle owner can send a vehicle damage assessment request to a server through a specified application program (APP) installed on a terminal device such as a mobile phone and a tablet personal computer. The Vehicle damage assessment request carries a Vehicle identifier, which may be a license plate Number, a Vehicle Identification Number (VIN), an engine Number, or other identifier. And after receiving the vehicle loss assessment request, the server can extract the vehicle identification from the vehicle loss assessment request.
And S102, issuing a sensor data acquisition command to a sensor control device of the target vehicle.
The target vehicle is a vehicle corresponding to the vehicle identification. The target vehicle is provided with deformation sensors at various parts such as a bumper, a vehicle door, wheels, a suspension, a chassis, an engine, a cylinder and the like, so that a sensor group is formed. When a vehicle accident happens, the vehicle can deform due to collision, bump and extrusion, each deformation sensor can acquire deformation data of the position where the deformation sensor is located, and a sensor control device is further installed in the target vehicle and used for controlling each deformation sensor and acquiring the deformation data acquired by each deformation sensor.
The importance of each part of the vehicle is different, for example, the engine is the most important part in the vehicle, therefore, each different part can be installed with different quantity of deformation sensors, and the core parts such as the engine are installed with a larger quantity of deformation sensors, so that more sufficient engine deformation data can be acquired, and other non-core parts can be installed with a smaller quantity of deformation sensors.
The number of the vehicle parts needing to be detected is recorded as P, the vehicle parts are respectively marked by serial numbers 1, 2, 3, …, P, … and P, P is more than or equal to 1 and less than or equal to P, and the number of the deformation sensors arranged at each part is recorded as sensorpThen, the total number of deformation data that can be collected is:
and after receiving the sensor data acquisition instruction, the sensor control device acquires deformation data acquired by each deformation sensor in the sensor group, packages the deformation data into a sensor data packet, and feeds the sensor data packet back to the server for processing.
And step S103, receiving a sensor data packet fed back by the sensor control device.
And after receiving the sensor data packet, the server analyzes the deformation data of each part of the target vehicle from the sensor data packet.
And step S104, constructing a damage assessment deformation vector of the target vehicle according to the deformation data of each part of the target vehicle.
As shown in fig. 2, step S104 may specifically include the following processes:
step S1041, configuring deformation data of each part of the target vehicle as a first deformation vector.
For example, the deformation data of the respective portions of the target vehicle may be constructed as a first deformation vector as follows:
DeformVec1=(DfData11,DfData12,...,DfData1d,...,DfData1Dim)
wherein, DfData1dD is more than or equal to 1 and less than or equal to Dim, Dim is the total number of the deformation sensors in the sensor group, and DeformVec1 is the first deformation vector of the target vehicle.
Step S1042, inquiring a second deformation vector of the target vehicle in a preset database according to the vehicle identification.
The second deformation vector is the deformation vector of the target vehicle collected at a preset initial moment, the initial moment is earlier than the sending moment of the vehicle damage assessment request, for example, the initial moment can be the moment when a vehicle owner makes a guarantee for the vehicle, when the vehicle owner makes a guarantee for the vehicle, the server issues a sensor data collection instruction to a sensor control device of the vehicle, receives a sensor data packet fed back by the sensor control device, and constructs the deformation data therein into the second deformation vector. After the server obtains the second deformation vector of the insurance vehicle, the vehicle identification and the second deformation vector of the vehicle are stored in a preset database for subsequent query.
The second deformation vector is as follows:
DeformVec2=(DfData21,DfData22,...,DfData2d,...,DfData2Dim)
wherein, DfData2dFor the deformation data collected by the d-th deformation sensor in the sensor group at the initial time, the DeformVec2 is a second deformation vector of the target vehicle.
And S1043, constructing a damage-assessment deformation vector according to the first deformation vector and the second deformation vector.
For example, a damage set deformation vector can be constructed as follows:
DeformVec=(DfData1,DfData2,...,DfDatad,...,DfDataDim)
wherein, DfDatad=DfData1d-DfData2dAnd DeformVec is a damage assessment deformation vector of the target vehicle.
And S105, carrying out damage assessment on the target vehicle according to the damage assessment deformation vector.
In this embodiment, the processing data in the history cases may be used as the basis for the subsequent data processing, where the history cases refer to cases that have undergone damage assessment processing, the history cases are divided into ClassNum damage levels according to the finally determined damage degree, and the ClassNum damage levels are respectively marked with serial numbers 1, 2, 3, …, c, …, and ClassNum, where c is greater than or equal to 1 and less than or equal to ClassNum, and may be divided into 4 levels, for example, light damage, general damage, medium damage, and heavy damage.
As shown in fig. 3, step S105 may specifically include the following processes:
step S1051, extracting sample vectors of each damage level from a preset damage sample set.
Any one of the sample vectors is as follows:
Samplec,s=(SpDfDtc,s,1,SpDfDtc,s,2,...,SpDfDtc,s,d,...,SpDfDtc,s,Dim)
wherein c is the serial number of the damage level, c is more than or equal to 1 and less than or equal to ClassNum, ClassNum is the total number of the damage level, s is the serial number of the sample vector, s is more than or equal to 1 and less than or equal to SampleNumc,SampleNumcThe total number of sample vectors for the c-th impairment level, SpDfDtc,s,dD deformation data of s Sample vector of c damage level, Samplec,sThe s-th sample vector for the c-th impairment level.
And step 1052, respectively calculating the matching degree between the damage assessment deformation vector and the sample vector of each damage assessment level.
For example, the matching degree between the impairment shape vector and the sample vector of each impairment level can be calculated according to the following formula:
among them, WeightdMatchDeg as a weight coefficient for the d-th deformation datacAnd the matching degree between the damage set deformation vector and the sample vector of the c-th damage level is obtained.
And step S1053, determining the damage assessment grade of the target vehicle.
For example, the damage rating of the target vehicle may be determined according to the following equation:
DmgClass=argmax(MatchDeg1,MatchDeg2,...,MatchDegc,...,MatchDegClassNum)
wherein argmax is a maximum independent variable function, and DmgClass is a serial number of the damage rating of the target vehicle.
Further, as shown in fig. 4, the calculating process of the weight coefficient may include:
step S401 constructs each sample vector as a sample matrix.
For example, each sample vector may be constructed as a sample matrix as shown below:
wherein,n is the row number of the sample matrix, N is more than or equal to 1 and less than or equal to N,Sn,dis the element of the n-th row and d-th column in the sample matrix, Sf(c,s),d=SpDfDtc,s,d,In particular, SampleNum0=0;
And step S402, calculating a covariance matrix of the sample matrix.
For example, the covariance matrix of the sample matrix may be calculated according to the following equation:
wherein,uais the average value of the a column of the sample matrix, namely:ubis the average of the b-th column of the sample matrix, i.e.:
and S403, solving a characteristic equation to obtain each characteristic value of the sample matrix.
The characteristic equation is | λ I-CovMatrix | ═ 0, where I is the identity matrix.
And S404, respectively calculating the weight coefficient of each deformation data.
For example, the weight coefficients of the respective deformation data may be calculated respectively according to the following equation:
wherein λ isdFor the d-th eigenvalue, Weight, of the sample matrixdIs the weight coefficient of the d-th deformation data.
Further, the setting process of the loss sample set may include the following processes:
firstly, a damage assessment deformation vector of each historical damage assessment vehicle with the damage assessment result of the c-th damage assessment level is extracted from a preset historical damage assessment database.
The damage assessment deformation vector of any historical damage assessment vehicle is as follows:
HsVecc,hn=(HsDfDtc,hn,1,HsDfDtc,hn,2,...,HsDfDtc,hn,d,...,HsDfDtc,hn,Dim)
wherein HN is the serial number of the historical damage assessment vehicle, and HN is more than or equal to 1 and less than or equal to HNc,HNcThe total number of historical damage-rated vehicles, HsDfDt, with the damage-rating result being the c-th damage-rating levelc,hn,dThe value HsVec of the d deformation data of the hn-th historical damage assessment vehicle with the damage assessment result of the c-th damage assessment grade isc,hnAnd the damage assessment result is the damage assessment deformation vector of the hn-th historical damage assessment vehicle of the c-th damage assessment level.
And then, respectively calculating the priority indexes of the damage assessment deformation vectors of the historical damage assessment vehicles with the damage assessment results of the c-th damage assessment level.
For example, the priority index of the damage assessment deformation vector of each historical damage assessment vehicle with the damage assessment result being the c-th damage level can be respectively calculated according to the following formula:
wherein abs is an absolute value function, exp is a natural index function, PriIdxc,hnAnd the preferential index of the damage assessment deformation vector of the hn-th historical damage assessment vehicle with the damage assessment result being the c-th damage assessment level is obtained.
Finally, selecting the front SampleNum with the highest priority index from the damage assessment deformation vectors of the historical damage assessment vehicles with the damage assessment result being the c-th damage assessment gradecAnd taking the individual damage assessment deformation vector as a sample vector of the c-th damage assessment level, and adding the sample vector into the damage assessment sample set.
Wherein, SampleNumc=min(max(μ×HNcMinNum), MaxNum), μ is a preset proportionality coefficient, whose value can be set according to practical situations, for example, it can be set to 0.1, 0.2, 0.5 or other values, MinNum is a preset minimum number of samples, whose value can be set according to practical situations, for example, it can be set to 100, 200, 500 or other valuesThe MaxNum is a preset minimum number of samples, and the value thereof can be set according to actual conditions, for example, it can be set to 1000, 2000, 5000 or other values, min is a minimum function, and max is a maximum function.
In summary, in the embodiments of the present invention, after receiving a vehicle damage assessment request, a sensor data acquisition instruction is issued to a sensor control device of a target vehicle, so as to obtain a sensor data packet fed back by the sensor control device, where the sensor data packet includes deformation data of each part of the target vehicle acquired by a sensor group in the target vehicle, and then a damage assessment deformation vector of the target vehicle is constructed according to the deformation data, and the target vehicle is damaged according to the damage assessment deformation vector. The whole damage assessment process is completed automatically without any manual intervention of damage assessment personnel, dependence on personal experience of the damage assessment personnel is eliminated, data collected by the sensor provides a basis for objectively and accurately evaluating vehicles, and accuracy of damage assessment results is greatly improved.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Fig. 5 is a structural diagram of an embodiment of a vehicle damage assessment apparatus according to an embodiment of the present invention, which corresponds to the vehicle damage assessment method described in the foregoing embodiment.
In this embodiment, a vehicle damage assessment apparatus may include:
the vehicle damage assessment request module 501 is configured to receive a vehicle damage assessment request sent by a terminal device, and extract a vehicle identifier from the vehicle damage assessment request;
an acquisition instruction sending module 502, configured to issue a sensor data acquisition instruction to a sensor control device of a target vehicle, where the target vehicle is a vehicle corresponding to the vehicle identifier;
a sensor data packet receiving module 503, configured to receive a sensor data packet fed back by the sensor control device, where the sensor data packet includes deformation data of each part of the target vehicle, which is acquired by a sensor group in the target vehicle;
a damage assessment deformation vector construction module 504, configured to construct a damage assessment deformation vector of the target vehicle according to deformation data of each part of the target vehicle;
and a damage assessment module 505, configured to assess the damage of the target vehicle according to the damage assessment deformation vector.
Further, the damage assessment deformation vector construction module may include:
the first deformation vector unit is used for constructing deformation data of each part of the target vehicle into a first deformation vector as follows:
DeformVec1=(DfData11,DfData12,...,DfData1d,...,DfData1Dim)
wherein, DfData1dD is more than or equal to 1 and less than or equal to Dim, Dim is the total number of the deformation sensors in the sensor group, and DeformVec1 is a first deformation vector of the target vehicle;
a second deformation vector unit, configured to query, in a preset database according to the vehicle identifier, a second deformation vector of the target vehicle, where the second deformation vector is a deformation vector of the target vehicle collected at a preset initial time, the initial time is earlier than a sending time of the vehicle damage assessment request, and the second deformation vector is as follows:
DeformVec2=(DfData21,DfData22,...,DfData2d,...,DfData2Dim)
wherein, DfData2dFor deformation data acquired by the d-th deformation sensor in the sensor group at the initial moment, the DeformVec2 is a second deformation vector of the target vehicle;
a damage assessment deformation vector construction unit, configured to construct a damage assessment deformation vector according to the first deformation vector and the second deformation vector, as shown below:
DeformVec=(DfData1,DfData2,...,DfDatad,...,DfDataDim)
wherein, DfDatad=DfData1d-DfData2dAnd DeformVec is a damage assessment deformation vector of the target vehicle.
Further, the damage assessment module may include:
a sample vector extraction unit, configured to extract sample vectors of respective damage levels from a preset damage sample set, where any sample vector is as follows:
Samplec,s=(SpDfDtc,s,1,SpDfDtc,s,2,...,SpDfDtc,s,d,...,SpDfDtc,s,Dim)
wherein c is the serial number of the damage level, c is more than or equal to 1 and less than or equal to ClassNum, ClassNum is the total number of the damage level, s is the serial number of the sample vector, s is more than or equal to 1 and less than or equal to SampleNumc,SampleNumcThe total number of sample vectors for the c-th impairment level, SpDfDtc,s,dD deformation data of s Sample vector of c damage level, Samplec,sThe s sample vector of the c damage assessment level;
a matching degree calculation unit, configured to calculate matching degrees between the loss assessment deformation vector and sample vectors of each loss assessment level according to the following formula:
among them, WeightdMatchDeg as a weight coefficient for the d-th deformation datacMatching degree between the damage assessment deformation vector and a sample vector of a c-th damage level;
a damage rating determination unit for determining a damage rating of the target vehicle according to the following formula:
DmgClass=argmax(MatchDeg1,MatchDeg2,...,MatchDegc,...,MatchDegClassNum)
wherein argmax is a maximum independent variable function, and DmgClass is a serial number of the damage rating of the target vehicle.
Further, the loss assessment module may further include:
a sample matrix constructing unit, configured to construct each sample vector into a sample matrix as shown below:
wherein,n is the row number of the sample matrix, N is more than or equal to 1 and less than or equal to N,Sn,dis the element of the n-th row and d-th column in the sample matrix, Sf(c,s),d=SpDfDtc,s,d,In particular, SampleNum0=0;
A covariance matrix calculation unit for calculating a covariance matrix of the sample matrix according to the following formula:
wherein,uais the average value of the a column of the sample matrix, namely:ubis the average of the b-th column of the sample matrix, i.e.:
the characteristic value calculating unit is used for solving a characteristic equation of lambda I-CovMatrix 0 and solving each characteristic value of the sample matrix, wherein I is a unit matrix;
a weight coefficient calculation unit, configured to calculate a weight coefficient of each deformation data according to the following formula:
wherein λ isdFor the d-th eigenvalue, Weight, of the sample matrixdIs the weight coefficient of the d-th deformation data.
Further, the loss assessment module may further include:
and the historical damage assessment vector extraction unit is used for extracting damage assessment deformation vectors of the historical damage assessment vehicles with damage assessment results of the c-th damage assessment level from a preset historical damage assessment database, wherein the damage assessment deformation vectors of any historical damage assessment vehicle are as follows:
HsVecc,hn=(HsDfDtc,hn,1,HsDfDtc,hn,2,...,HsDfDtc,hn,d,...,HsDfDtc,hn,Dim)
wherein HN is the serial number of the historical damage assessment vehicle, and HN is more than or equal to 1 and less than or equal to HNc,HNcThe total number of historical damage-rated vehicles, HsDfDt, with the damage-rating result being the c-th damage-rating levelc,hn,dThe value HsVec of the d deformation data of the hn-th historical damage assessment vehicle with the damage assessment result of the c-th damage assessment grade isc,hnSetting a damage assessment deformation vector of an hn-th historical damage assessment vehicle with a damage assessment result of a c-th damage assessment level;
a priority index calculation unit, configured to calculate priority indexes of the damage assessment deformation vectors of the historical damage assessment vehicles with the damage assessment result being the c-th damage assessment level according to the following formula:
wherein abs is an absolute value function, exp is a natural index function, PriIdxc,hnThe hn-th historical damage assessment vehicle with the damage assessment result of the c-th damage assessment gradeThe priority index of the damage-assessment deformation vector;
a damage assessment sample set constructing unit for selecting the front SampleNum with the highest priority index from the damage assessment deformation vectors of each historical damage assessment vehicle with the damage assessment result being the c-th damage assessment gradecAnd taking the individual damage assessment deformation vector as a sample vector of the c-th damage assessment level, and adding the sample vector into the damage assessment sample set.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses, modules and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Fig. 6 shows a schematic block diagram of a server provided in an embodiment of the present invention, and for convenience of explanation, only the parts related to the embodiment of the present invention are shown.
In this embodiment, the server 6 may include: a processor 60, a memory 61, and computer readable instructions 62 stored in the memory 61 and executable on the processor 60, such as computer readable instructions to perform the vehicle damage assessment method described above. The processor 60, when executing the computer readable instructions 62, implements the steps in the various vehicle damage assessment method embodiments described above, such as steps S101-S105 shown in fig. 1. Alternatively, the processor 60, when executing the computer readable instructions 62, implements the functions of the modules/units in the above-mentioned device embodiments, such as the functions of the modules 501 to 505 shown in fig. 5.
Illustratively, the computer readable instructions 62 may be partitioned into one or more modules/units that are stored in the memory 61 and executed by the processor 60 to implement the present invention. The one or more modules/units may be a series of computer-readable instruction segments capable of performing specific functions, which are used to describe the execution of the computer-readable instructions 62 in the server 6.
The Processor 60 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 61 may be an internal storage unit of the server 6, such as a hard disk or a memory of the server 6. The memory 61 may also be an external storage device of the server 6, such as a plug-in hard disk, a smart memory Card (SDC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the server 6. Further, the memory 61 may also include both an internal storage unit of the server 6 and an external storage device. The memory 61 is used to store the computer readable instructions and other instructions and data required by the server 6. The memory 61 may also be used to temporarily store data that has been output or is to be output.
Each functional unit in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of computer readable instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only memory (ROD), a random Access memory (RAD), a magnetic disk or an optical disk, and other various media capable of storing computer-readable instructions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. A method of vehicle damage assessment, comprising:
receiving a vehicle loss assessment request sent by a terminal device, and extracting a vehicle identifier from the vehicle loss assessment request;
issuing a sensor data acquisition instruction to a sensor control device of a target vehicle, wherein the target vehicle is a vehicle corresponding to the vehicle identifier;
receiving a sensor data packet fed back by the sensor control device, wherein the sensor data packet comprises deformation data of each part of the target vehicle, which is acquired by a sensor group in the target vehicle;
constructing a damage assessment deformation vector of the target vehicle according to the deformation data of each part of the target vehicle, and performing damage assessment on the target vehicle according to the damage assessment deformation vector;
the damage assessment of the target vehicle according to the damage assessment deformation vector comprises the following steps:
extracting sample vectors of each damage level from a preset damage sample set, wherein any sample vector is as follows:
Samplec,s=(SpDfDtc,s,1,SpDfDtc,s,2,...,SpDfDtc,s,d,...,SpDfDtc,s,Dim)
wherein c is the serial number of the damage level, c is more than or equal to 1 and less than or equal to ClassNum, ClassNum is the total number of the damage level, s is the serial number of the sample vector, s is more than or equal to 1 and less than or equal to SampleNumc,SampleNumcThe total number of sample vectors of the c-th damage assessment level, d is the serial number of the deformation sensor, d is more than or equal to 1 and less than or equal to Dim, Dim is the total number of the deformation sensors in the sensor group, SpDfDtc,s,dD deformation data of s Sample vector of c damage level, Samplec,sThe s sample vector of the c damage assessment level;
respectively calculating the matching degree between the damage assessment deformation vector and the sample vector of each damage assessment grade according to the following formula:
among them, WeightdIs the weight coefficient of the d-th deformation data, DfDatadThe d-th deformation data of the damage-assessment deformation vector, MatchDegcMatching degree between the damage assessment deformation vector and a sample vector of a c-th damage level;
determining the damage rating of the target vehicle according to the following formula:
DmgClass=argmax(MatchDeg1,MatchDeg2,...,MatchDegc,...,MatchDegClassNum)
wherein argmax is a maximum independent variable function, and DmgClass is a serial number of the damage rating of the target vehicle.
2. The vehicle damage assessment method according to claim 1, wherein said constructing a damage assessment deformation vector of said target vehicle based on deformation data of various parts of said target vehicle comprises:
constructing deformation data of each part of the target vehicle into a first deformation vector as follows:
DeformVec1=(DfData11,DfData12,...,DfData1d,...,DfData1Dim)
wherein, DfData1dFor deformation data acquired by the d-th deformation sensor in the sensor group, the DeformVec1 is a first deformation vector of the target vehicle;
inquiring a second deformation vector of the target vehicle in a preset database according to the vehicle identification, wherein the second deformation vector is a deformation vector of the target vehicle collected at a preset initial time, the initial time is earlier than the sending time of the vehicle damage assessment request, and the second deformation vector is as follows:
DeformVec2=(DfData21,DfData22,...,DfData2d,...,DfData2Dim)
wherein, DfData2dFor deformation data acquired by the d-th deformation sensor in the sensor group at the initial moment, the DeformVec2 is a second deformation vector of the target vehicle;
constructing a damage-assessment deformation vector according to the first deformation vector and the second deformation vector as follows:
DeformVec=(DfData1,DfData2,...,DfDatad,...,DfDataDim)
wherein, DfDatad=DfData1d-DfData2dAnd DeformVec is a damage assessment deformation vector of the target vehicle.
3. The vehicle damage assessment method according to claim 1, wherein the calculation of the weighting factor comprises:
each sample vector is constructed as a sample matrix as follows:
wherein,n is the row number of the sample matrix, N is more than or equal to 1 and less than or equal to N,Sn,dis the element of the n-th row and d-th column in the sample matrix, Sf(c,s),d=SpDfDtc,s,d,In particular, SampleNum0=0;
Calculating a covariance matrix of the sample matrix according to:
wherein,uais the average value of the a column of the sample matrix, namely:ubis the average of the b-th column of the sample matrix, i.e.:
solving a characteristic equation of lambda I-CovMatrix 0 to obtain each characteristic value of the sample matrix, wherein I is a unit matrix;
the weight coefficient of each deformation data is respectively calculated according to the following formula:
wherein λ isdFor the d-th eigenvalue, Weight, of the sample matrixdIs the weight coefficient of the d-th deformation data.
4. The vehicle damage assessment method according to claim 1, wherein said process of setting said set of damage samples comprises:
extracting the damage assessment deformation vectors of the historical damage assessment vehicles with the damage assessment results of the c-th damage assessment level from a preset historical damage assessment database, wherein the damage assessment deformation vectors of any historical damage assessment vehicle are as follows:
HsVecc,hn=(HsDfDtc,hn,1,HsDfDtc,hn,2,...,HsDfDtc,hn,d,...,HsDfDtc,hn,Dim)
wherein HN is the serial number of the historical damage assessment vehicle, and HN is more than or equal to 1 and less than or equal to HNc,HNcThe total number of historical damage-rated vehicles, HsDfDt, with the damage-rating result being the c-th damage-rating levelc,hn,dThe value HsVec of the d deformation data of the hn-th historical damage assessment vehicle with the damage assessment result of the c-th damage assessment grade isc,hnSetting a damage assessment deformation vector of an hn-th historical damage assessment vehicle with a damage assessment result of a c-th damage assessment level;
and respectively calculating the priority indexes of the damage assessment deformation vectors of the historical damage assessment vehicles with the damage assessment results being the c-th damage assessment level according to the following formula:
wherein abs is an absolute value function, exp is a natural index function, PriIdxc,hnThe preferential index of the damage assessment deformation vector of the hn-th historical damage assessment vehicle with the damage assessment result being the c-th damage assessment level;
selecting front SampleNum with highest priority index from the damage assessment deformation vectors of all historical damage assessment vehicles with the damage assessment result being the c-th damage assessment gradecAnd taking the individual damage assessment deformation vector as a sample vector of the c-th damage assessment level, and adding the sample vector into the damage assessment sample set.
5. A computer readable storage medium storing computer readable instructions, wherein the computer readable instructions, when executed by a processor, implement the steps of the vehicle damage assessment method according to any one of claims 1 to 4.
6. A server comprising a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, wherein the processor when executing the computer readable instructions performs the steps of:
receiving a vehicle loss assessment request sent by a terminal device, and extracting a vehicle identifier from the vehicle loss assessment request;
issuing a sensor data acquisition instruction to a sensor control device of a target vehicle, wherein the target vehicle is a vehicle corresponding to the vehicle identifier;
receiving a sensor data packet fed back by the sensor control device, wherein the sensor data packet comprises deformation data of each part of the target vehicle, which is acquired by a sensor group in the target vehicle;
constructing a damage assessment deformation vector of the target vehicle according to the deformation data of each part of the target vehicle, and performing damage assessment on the target vehicle according to the damage assessment deformation vector;
the damage assessment of the target vehicle according to the damage assessment deformation vector comprises the following steps:
extracting sample vectors of each damage level from a preset damage sample set, wherein any sample vector is as follows:
Samplec,s=(SpDfDtc,s,1,SpDfDtc,s,2,...,SpDfDtc,s,d,...,SpDfDtc,s,Dim)
wherein c is the serial number of the damage level, c is more than or equal to 1 and less than or equal to ClassNum, ClassNum is the total number of the damage level, s is the serial number of the sample vector, s is more than or equal to 1 and less than or equal to SampleNumc,SampleNumcThe total number of sample vectors of the c-th damage assessment level, d is the serial number of the deformation sensor, d is more than or equal to 1 and less than or equal to Dim, Dim is the total number of the deformation sensors in the sensor group, SpDfDtc,s,dD deformation data of s Sample vector of c damage level, Samplec,sThe s sample vector of the c damage assessment level;
respectively calculating the matching degree between the damage assessment deformation vector and the sample vector of each damage assessment grade according to the following formula:
among them, WeightdIs the weight coefficient of the d-th deformation data, DfDatadThe d-th deformation data of the damage-assessment deformation vector, MatchDegcMatching degree between the damage assessment deformation vector and a sample vector of a c-th damage level;
determining the damage rating of the target vehicle according to the following formula:
DmgClass=argmax(MatchDeg1,MatchDeg2,...,MatchDegc,...,MatchDegClassNum)
wherein argmax is a maximum independent variable function, and DmgClass is a serial number of the damage rating of the target vehicle.
7. The server according to claim 6, wherein the constructing the damage-assessment deformation vector of the target vehicle according to the deformation data of the target vehicle comprises:
constructing deformation data of each part of the target vehicle into a first deformation vector as follows:
DeformVec1=(DfData11,DfData12,...,DfData1d,...,DfData1Dim)
wherein, DfData1dFor deformation data acquired by the d-th deformation sensor in the sensor group, the DeformVec1 is a first deformation vector of the target vehicle;
inquiring a second deformation vector of the target vehicle in a preset database according to the vehicle identification, wherein the second deformation vector is a deformation vector of the target vehicle collected at a preset initial time, the initial time is earlier than the sending time of the vehicle damage assessment request, and the second deformation vector is as follows:
DeformVec2=(DfData21,DfData22,...,DfData2d,...,DfData2Dim)
wherein, DfData2dFor deformation data acquired by the d-th deformation sensor in the sensor group at the initial moment, the DeformVec2 is a second deformation vector of the target vehicle;
constructing a damage-assessment deformation vector according to the first deformation vector and the second deformation vector as follows:
DeformVec=(DfData1,DfData2,...,DfDatad,...,DfDataDim)
wherein, DfDatad=DfData1d-DfData2dAnd DeformVec is a damage assessment deformation vector of the target vehicle.
8. The server according to claim 6, wherein the calculation of the weighting factor comprises:
each sample vector is constructed as a sample matrix as follows:
wherein,n is the row number of the sample matrix, N is more than or equal to 1 and less than or equal to N,Sn,dis the element of the n-th row and d-th column in the sample matrix, Sf(c,s),d=SpDfDtc,s,d,In particular, SampleNum0=0;
Calculating a covariance matrix of the sample matrix according to:
wherein,uais the average value of the a column of the sample matrix, namely:ubis the average of the b-th column of the sample matrix, i.e.:
solving a characteristic equation of lambda I-CovMatrix 0 to obtain each characteristic value of the sample matrix, wherein I is a unit matrix;
the weight coefficient of each deformation data is respectively calculated according to the following formula:
wherein λ isdFor the d-th eigenvalue, Weight, of the sample matrixdIs the weight coefficient of the d-th deformation data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811115698.6A CN109443301B (en) | 2018-09-25 | 2018-09-25 | Vehicle loss assessment method, computer readable storage medium and server |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811115698.6A CN109443301B (en) | 2018-09-25 | 2018-09-25 | Vehicle loss assessment method, computer readable storage medium and server |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109443301A CN109443301A (en) | 2019-03-08 |
CN109443301B true CN109443301B (en) | 2021-09-10 |
Family
ID=65530631
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811115698.6A Active CN109443301B (en) | 2018-09-25 | 2018-09-25 | Vehicle loss assessment method, computer readable storage medium and server |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109443301B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111572474A (en) * | 2020-05-09 | 2020-08-25 | 麦特汽车服务股份有限公司 | Distributed automobile collision detection method and device |
CN112085612B (en) * | 2020-11-13 | 2021-03-16 | 深圳壹账通智能科技有限公司 | Vehicle total loss detection method and device, terminal equipment and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105469312A (en) * | 2015-11-24 | 2016-04-06 | 大连楼兰科技股份有限公司 | Vehicle appearance clearance change-based laser scanning automatic loss assessment method and system |
CN105931007A (en) * | 2016-01-13 | 2016-09-07 | 平安科技(深圳)有限公司 | Damage assessment checking method, server, and terminal |
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 |
CN106600421A (en) * | 2016-11-21 | 2017-04-26 | 中国平安财产保险股份有限公司 | Intelligent car insurance loss assessment method and system based on image recognition |
CN108415973A (en) * | 2018-02-08 | 2018-08-17 | 泰康保险集团股份有限公司 | Car damage identification method, device, server and storage medium |
WO2018191435A1 (en) * | 2017-04-11 | 2018-10-18 | Alibaba Group Holding Limited | Picture-based vehicle loss assessment method and apparatus, and electronic device |
-
2018
- 2018-09-25 CN CN201811115698.6A patent/CN109443301B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105469312A (en) * | 2015-11-24 | 2016-04-06 | 大连楼兰科技股份有限公司 | Vehicle appearance clearance change-based laser scanning automatic loss assessment method and system |
CN105931007A (en) * | 2016-01-13 | 2016-09-07 | 平安科技(深圳)有限公司 | Damage assessment checking method, server, and terminal |
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 |
CN106600421A (en) * | 2016-11-21 | 2017-04-26 | 中国平安财产保险股份有限公司 | Intelligent car insurance loss assessment method and system based on 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 |
WO2018191435A1 (en) * | 2017-04-11 | 2018-10-18 | Alibaba Group Holding Limited | Picture-based vehicle loss assessment method and apparatus, and electronic device |
CN108415973A (en) * | 2018-02-08 | 2018-08-17 | 泰康保险集团股份有限公司 | Car damage identification method, device, server and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109443301A (en) | 2019-03-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109087510B (en) | Traffic monitoring method and device | |
CN109389135B (en) | Image screening method and device | |
EP3843036B1 (en) | Sample labeling method and device, and damage category identification method and device | |
CN109443301B (en) | Vehicle loss assessment method, computer readable storage medium and server | |
CN117351448B (en) | Improved polarized image road target detection method based on YOLOv8 | |
CN104484658A (en) | Face gender recognition method and device based on multi-channel convolution neural network | |
CN101794345B (en) | Data processing method and device | |
CN103729629A (en) | Method and device for recognizing vehicle type in ETC lane | |
CN106295351B (en) | A kind of Risk Identification Method and device | |
CN109767346B (en) | Vehicle service processing method, device, computer equipment and storage medium | |
CN108052929A (en) | Parking space state detection method, system, readable storage medium storing program for executing and computer equipment | |
CN109784171A (en) | Car damage identification method for screening images, device, readable storage medium storing program for executing and server | |
CN112597995B (en) | License plate detection model training method, device, equipment and medium | |
DE102022128437A1 (en) | Aggregation-based LIDAR data alignment | |
CN114661702A (en) | Target data duplication eliminating method and device, storage medium and electronic device | |
CN102254185A (en) | Background clutter quantizing method based on contrast ratio function | |
DE112022000915T5 (en) | CREATE A STATISTICAL MODEL AND EVALUATE MODEL PERFORMANCE | |
CN112446428B (en) | Image data processing method and device | |
CN116596428B (en) | Rural logistics intelligent distribution system based on unmanned aerial vehicle | |
CN116977834A (en) | Method for identifying internal and external images distributed under open condition | |
CN109635651B (en) | Vehicle damage assessment method based on image recognition, storage medium and server | |
CN113947154B (en) | Target detection method, target detection system, electronic equipment and storage medium | |
CN115049996B (en) | Double-sensor target detection fusion method and system based on evidence reasoning rule | |
CN115239947A (en) | Wheat stripe rust severity evaluation method and device based on unsupervised learning | |
CN107330105B (en) | Robustness evaluation method and device for similar image retrieval algorithm |
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 |