CN112085610A - Target damage assessment method and device, electronic equipment and computer-readable storage medium - Google Patents
Target damage assessment method and device, electronic equipment and computer-readable storage medium Download PDFInfo
- Publication number
- CN112085610A CN112085610A CN202010927116.5A CN202010927116A CN112085610A CN 112085610 A CN112085610 A CN 112085610A CN 202010927116 A CN202010927116 A CN 202010927116A CN 112085610 A CN112085610 A CN 112085610A
- Authority
- CN
- China
- Prior art keywords
- accessory
- damage
- core
- original
- damage assessment
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012423 maintenance Methods 0.000 claims abstract description 84
- 231100000809 Damage Assessment Model Toxicity 0.000 claims abstract description 67
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000000605 extraction Methods 0.000 claims abstract description 17
- 238000004140 cleaning Methods 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 claims description 53
- 238000013528 artificial neural network Methods 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 16
- 230000006735 deficit Effects 0.000 claims description 13
- 239000008358 core component Substances 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 239000000306 component Substances 0.000 description 8
- 230000011218 segmentation Effects 0.000 description 6
- 238000007726 management method Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000007635 classification algorithm Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 239000010705 motor oil Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003921 oil Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention relates to an artificial intelligence technology, and discloses a target damage assessment method, which comprises the following steps: the method comprises the steps of carrying out feature extraction on an original damage accessory set to obtain an accessory feature set, cleaning the original damage accessory set based on similarity among accessory features in the accessory feature set to obtain a standard damage accessory set, dividing the standard damage accessory set into a core accessory damage set and a non-core accessory damage set, training an original damage assessment model by utilizing the core accessory damage set, the non-core accessory damage set and a maintenance duration set to obtain a standard damage assessment model, and carrying out damage assessment on a damage accessory of a target object to be subjected to damage assessment by utilizing the standard damage assessment model to obtain maintenance duration of the damage accessory. The invention also provides a target damage assessment device, electronic equipment and a computer readable storage medium. The invention can improve the accuracy of damage assessment of the target object by combining the relation between the accessories of the target object.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a target damage assessment method and device, electronic equipment and a computer readable storage medium.
Background
With the rapid development of science and technology, the damage assessment of a target object gradually changes from manual damage assessment to automatic damage assessment, for example, in a vehicle insurance claim settlement service, the conventional damage assessment method depends on personal experience to perform manual damage assessment on the damage degree of a vehicle, or uses a classification algorithm to predict the maintenance time spent on damaged accessories of the vehicle, and evaluates the damage assessment result of the vehicle according to the predicted time.
However, the manual loss assessment occupies too much time of workers, and has low efficiency and high error rate, and the automatic loss assessment by using a classification algorithm cannot effectively divide the relation between different accessories in the target object, so that the loss assessment result sometimes differs from the actual result when the target object is determined.
Disclosure of Invention
The invention provides a method and a device for determining damage of a target object, electronic equipment and a computer readable storage medium, and aims to improve the accuracy of determining damage of the target object by combining the relation between accessories of the target object.
In order to achieve the above object, the present invention provides a method for determining damage of a target object, comprising:
acquiring a historical maintenance data set of a target object, and extracting an original damage accessory set and a maintenance duration set from the historical maintenance data set;
performing feature extraction on the original damage accessory set to obtain an accessory feature set;
according to the maintenance duration set, calculating similarity among the accessory features in the accessory feature set, and cleaning the original damaged accessory set based on the similarity to obtain a standard damaged accessory set;
dividing the standard damage accessory set into a core accessory damage set and a non-core accessory damage set;
constructing an original damage assessment model based on a forward feedback neural network, and training the original damage assessment model by using the core accessory damage set, the non-core accessory damage set and the maintenance duration set to obtain a standard damage assessment model;
and performing damage assessment on the damaged accessory of the target object to be subjected to damage assessment by using the standard damage assessment model to obtain the maintenance duration of the damaged accessory.
Optionally, the constructing the original impairment model based on the feedforward neural network includes:
integrating a preset first classification function and a preset second classification function to obtain an output layer, wherein the first classification function and the second classification function are probability functions;
and connecting the output layer to the tail end of the feedforward neural network to obtain the original damage assessment model.
Optionally, the training the original damage assessment model by using the core component damage set, the non-core component damage set, and the maintenance duration set to obtain a standard damage assessment model includes:
performing calculation on a non-core accessory damage set by using the first classification function to obtain a core accessory prediction set;
calculating a fitting error value between the core fitting prediction set and the core fitting damage set;
judging the size relation between the accessory error value and a preset accessory error threshold value;
if the accessory error value is larger than or equal to the accessory error threshold value, adjusting the internal parameter value of the original damage assessment model, and predicting a core accessory prediction set again;
if the accessory error value is smaller than the accessory error threshold value, calculating a duration prediction set of the non-core accessory damage set by using the second classification function;
calculating a maintenance duration error value of the duration prediction set and the maintenance duration set;
judging the size relation between the maintenance duration error value and a preset maintenance duration threshold value;
if the maintenance duration error value is larger than or equal to the maintenance duration threshold value, continuously adjusting the internal parameter value of the original damage assessment model, and recalculating a core component prediction set;
and if the maintenance duration error value is smaller than the maintenance duration threshold value, obtaining the standard damage assessment model.
Optionally, the performing, by using the first classification function, a calculation on a non-core accessory damage set to obtain a core accessory prediction set includes:
extracting a feature set of the non-core accessory damage set by using the feedforward neural network;
and calculating a probability value set corresponding to the feature set by using the first classification function, and predicting by using the probability value set to obtain a core accessory prediction set.
Optionally, the adjusting internal parameter values of the original impairment model comprises:
modifying the weight value and the bias value of the original damage assessment model;
and modifying the step length and the training batch number of the training of the original damage assessment model.
Optionally, the performing feature extraction on the original damaged accessory set to obtain an accessory feature set includes:
carrying out preprocessing operations including analysis and abnormal word removal on the original damage accessory set to obtain a primary damage accessory set;
and performing word vector conversion on each damage accessory in the primary damage accessory set to obtain the accessory feature set.
Optionally, the calculating similarity between the accessory features in the accessory feature set includes:
calculating the similarity between the accessory features in the accessory feature set by adopting a similarity calculation method as follows:
the method comprises the following steps of obtaining a plurality of accessory features, wherein sim (d, T) represents the similarity between the accessory feature d and the accessory feature T in the accessory feature set, w represents the weighting coefficients of d, T and other accessory features k in the accessory feature set, n is the total data number in the accessory feature set, alpha and beta are offset coefficients, and T is the maintenance duration corresponding to the accessory features.
In order to solve the above problems, the present invention also provides a target damage assessment apparatus, comprising:
the accessory feature calculation module is used for acquiring a historical maintenance data set of a target object, extracting an original damaged accessory set and a maintenance duration set from the historical maintenance data set, and performing feature extraction on the original damaged accessory set to obtain an accessory feature set;
the accessory dividing module is used for calculating the similarity among the accessory features in the accessory feature set according to the maintenance duration set, cleaning the original damage accessory set based on the similarity to obtain a standard damage accessory set, and dividing the standard damage accessory set into a core accessory damage set and a non-core accessory damage set;
the model training module is used for constructing an original damage assessment model based on a forward feedback neural network, and training the original damage assessment model by using the core accessory damage set, the non-core accessory damage set and the maintenance duration set to obtain a standard damage assessment model;
and the target object damage assessment module is used for performing damage assessment on a damaged accessory of the target object to be damaged by the standard damage assessment model to obtain the maintenance duration of the damaged accessory.
In order to solve the above problem, the present invention also provides an electronic device, including:
a memory storing at least one instruction; and
a processor executing instructions stored in the memory to implement the target damage assessment method of any of the above.
In order to solve the above problem, the present invention further provides a computer-readable storage medium including a storage data area and a storage program area, the storage data area storing created data, the storage program area storing a computer program; wherein the computer program when executed by a processor implements the object impairment method of any one of the above.
According to the method, an original damage accessory set is extracted according to a historical maintenance data set of a target object, feature extraction and similarity calculation are carried out on the original damage accessory set to obtain a standard damage accessory set, the feature extraction can effectively extract the feature of damage of each accessory, interference of non-accessory damage features is reduced, and meanwhile, part of similar accessory features are removed by using a similarity calculation method, so that interference of data volume, non-accessory features and similar features on subsequent target object loss assessment can be effectively reduced, and the loss assessment accuracy is improved; meanwhile, in the embodiment of the invention, the standard damage accessory set is divided into the core accessory damage set and the non-core accessory damage set, the damage assessment model is trained through the relevance between the non-core accessory and the core accessory, the accessory is effectively divided into the core accessory and the non-core accessory, and the damage assessment model is trained according to the relevance between the core accessory and the non-core accessory, so that the interference on the whole damage assessment process caused by the unclear relation between the accessories is avoided, and the accuracy of damage assessment can be further improved. Therefore, the method, the device and the computer readable storage medium for determining the damage of the target object provided by the invention can be combined with the relation between the accessories of the target object, so that the accuracy rate of determining the damage of the target object is improved.
Drawings
Fig. 1 is a schematic flow chart of a method for determining damage to a target object according to an embodiment of the present invention;
fig. 2 is a detailed flowchart of S2 in the method for determining damage to a target object according to an embodiment of the present invention;
fig. 3 is a detailed flowchart illustrating the training of the original damage assessment model in the target damage assessment method according to an embodiment of the present invention;
fig. 4 is a block diagram of a target damage assessment apparatus according to an embodiment of the present invention;
fig. 5 is a schematic internal structural diagram of an electronic device for implementing a target damage assessment method according to an embodiment of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The execution subject of the target damage assessment method provided by the embodiment of the present application includes, but is not limited to, at least one of electronic devices, such as a server and a terminal, which can be configured to execute the method provided by the embodiment of the present application. In other words, the target damage assessment method may be performed by software or hardware installed in a terminal device or a server device, and the software may be a block chain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
The invention provides a method for determining damage of a target object. Fig. 1 is a schematic flow chart of a target damage assessment method according to an embodiment of the present invention. The method may be performed by an apparatus, which may be implemented by software and/or hardware.
In this embodiment, the target damage assessment method includes:
s1, obtaining a historical maintenance data set of the target object, and extracting an original damage accessory set and a maintenance duration set from the historical maintenance data set.
In a preferred embodiment of the present invention, the target object may be an object that is often damaged, such as an automobile. Further, maintenance data of the target objects arranged in advance by the user in the historical time can be obtained, so that a historical maintenance data set is obtained, for example, a plurality of pieces of vehicle insurance claim data accepted in a specified time period are obtained from an automobile insurance company, damaged accessories of each vehicle are extracted from the vehicle insurance claim data, an original damaged accessory set is obtained, maintenance time corresponding to the damaged accessories is extracted, and a maintenance time set is obtained. For example, the original damaged parts set corresponding to the automobile insurance field comprises the steps of replacing a headlamp, repairing engine oil leakage, replacing automobile tires and the like, wherein the repairing time is concentrated and the headlamp replacing time is recorded for 2 hours, the engine oil leakage repairing time is recorded for 5 hours, the automobile tires are replaced for 0.6 hour and the like.
And S2, performing feature extraction on the original damage accessory set to obtain an accessory feature set.
In the preferred embodiment of the invention, because the original damaged parts set has the condition that words of a plurality of damaged parts are similar, such as replacing automobile tires, replacing front tires of automobiles and the like, the features of the damaged parts need to be extracted from the original damaged parts set by using a feature extraction method, and the part feature set is obtained.
In detail, as shown in fig. 2, the S2 includes:
s21, carrying out preprocessing operation including word segmentation and abnormal word removal on the original damage accessory set to obtain a primary damage accessory set;
because there is no definite separation mark between words in the chinese expression, if no preprocessing of word segmentation and heteromorphic word is performed before the word vector conversion, the phenomenon of redundant accessory features corresponding to each damaged accessory occurs, and the subsequent similarity calculation is directly affected, so that word segmentation and heteromorphic word removal are performed on the original damaged accessory set.
In a preferred embodiment of the present invention, the word segmentation process may use a jieba word segmentation program based on programming languages such as Python and JAVA, and if the original damaged parts are concentrated with damaged parts: 'air leakage of rear wheel tyre of automobile, replacement of rear wheel tyre'. The method is obtained by processing based on the jieba participle as follows: [ automobile ] [ rear wheel ] [ tire ] [ blow-by ] [ exchange ] [ rear wheel ] [ tire ].
Therefore, after word segmentation, a plurality of repeated words, punctuation marks, stop words and other special words can be found, so that the special words need to be removed to achieve the purpose of simplification, and the special words are changed into the rear wheel tire.
And S22, performing word vector transformation on each damage accessory in the primary damage accessory set to obtain an accessory feature set.
Preferably, the word vector conversion can adopt a one-hot model, a word2vec model and the like which are currently disclosed, for example, the word2vec model can be used for changing the [ replacement ] [ rear wheel ] [ tire ] into a matrix type accessory feature.
S3, calculating the similarity among the accessory features in the accessory feature set, and cleaning the original damage accessory set based on the similarity to obtain a standard damage accessory set.
As can be seen from the feature extraction in S2, if the original damaged part set includes replacing an automobile tire and replacing an automobile front tire, two similar part features can be obtained by using the feature extraction method in S2, but since the subsequent damage assessment results of the similar part features are approximately the same, the similar part features need to be further cleaned by calculating the similarity between the part features in the part feature set, so as to obtain the standard damaged part set.
In the preferred embodiment of the present invention, the following similarity calculation method can be used to calculate the similarity between the accessory features:
the method comprises the following steps that sim (d, T) represents the similarity between an accessory feature d and an accessory feature T in an accessory feature set, w represents weight coefficients of d, T and other accessory features k in the accessory feature set, n is the total number of data in the accessory feature set, alpha and beta are offset coefficients, wherein alpha + beta is 1, T is maintenance duration corresponding to the accessory feature, and the maintenance duration can be searched from the maintenance duration set.
Preferably, there are multiple cleaning methods for cleaning the original damaged part set, for example, each similarity obtained by sorting according to a sorting method of similarity from large to small, whether a difference value between every two adjacent groups of similarities is smaller than a specified threshold is judged, and if the difference value is smaller than the specified threshold, a damaged part corresponding to one of the similarities is removed until the standard damaged part set is obtained.
S4, dividing the standard damage assembly set into a core assembly damage set and a non-core assembly damage set.
According to the principle that the parts and other parts are generally associated with each other, a standard damaged part set can be divided into a core part damaged set and a non-core part damaged set, for example, when a part A is damaged, a part B and a part C are damaged at the same time, but when a part B is damaged, other parts are not affected in general, the part A is divided into the non-core part, and the part B is divided into the core part, for example, in the automobile insurance field, the fault of the steering wheel of an automobile generally has a problem along with the bearing of the steering wheel, so that the steering wheel of the automobile is the non-core part, and the bearing of the steering wheel is the core part.
S5, constructing an original damage assessment model based on a forward feedback neural network, and training the original damage assessment model by utilizing the core accessory damage set, the non-core accessory damage set and the maintenance duration set to obtain a standard damage assessment model.
Since the conventional machine learning algorithm is relatively simple to process the accessory damage assessment, in a preferred embodiment of the present invention, the damage assessment model is constructed by combining with a neural network, wherein the constructing the original damage assessment model based on the feedforward neural network includes:
integrating a preset first classification function and a preset second classification function to obtain an output layer, wherein the first classification function and the second classification function are probability functions;
and connecting the output layer to the tail end of the feedforward neural network to obtain the original damage assessment model.
The first classification function is used for predicting the core accessories related to the non-core accessory damage set to obtain a core accessory prediction set. Preferably, the first classification function may employ a probability function such as a softmax function. And the second classification function is used for predicting the maintenance time corresponding to each non-core accessory in the non-core accessory damage set to obtain a time prediction set. Similarly, the second classification function may be the same classification function as the first classification function, or may be a different classification function. For example, when a different classification function is employed, the second classification function may be a sigmoid function.
In a preferred embodiment of the present invention, the first classification function and the second classification function are used to form an output layer, and replace the original output layer of the feedforward neural network, so as to obtain the original damage assessment model.
Further, after the original damage assessment model is constructed, internal parameters of the original damage assessment model need to be trained further. Therefore, the embodiment of the invention also comprises the step of training the original damage assessment model. Preferably, in the embodiment of the present invention, the original damage assessment model is trained by using the core component damage set, the non-core component damage set, and the maintenance duration set, so as to obtain a standard damage assessment model.
In detail, referring to fig. 3, the training of the original impairment model comprises:
s511, calculating a non-core accessory damage set by using the first classification function to obtain a core accessory prediction set;
in detail, the S511 includes: and extracting a feature set of the non-core accessory damage set by using the forward feedback neural network, calculating a probability value set corresponding to the feature set by using the first classification function, and predicting by using the probability value set to obtain a core accessory prediction set. In a preferred embodiment of the invention, because the feedforward neural network is a multilayer feedforward neural network trained according to an error reverse propagation algorithm, the characteristic sets of a non-core accessory damage set can be effectively extracted by using the feedforward neural network, and meanwhile, the probability values corresponding to each characteristic set are respectively calculated by using a first classification function, such as damage of a pull rod accessory in the non-core accessory damage set, the characteristic values of the pull rod accessory are obtained by calculation, and when the pull rod accessory is damaged according to the first classification function, the damage probability of a corresponding tie rod is 78%, the damage probability of a steering driven arm is 17%, and the damage probability of a power steering oil tank is 31%, when the pull rod accessory is damaged, the tie rod can be correspondingly damaged by prediction, so that a core accessory prediction set is obtained by summarizing.
S512, calculating accessory error values of the core accessory prediction set and the core accessory damage set;
s513, judging the size relation between the accessory error value and a preset accessory error threshold value;
s514, if the accessory error value is larger than or equal to the accessory error threshold value, adjusting an internal parameter value of the original damage assessment model, and returning to S511;
in detail, the internal parameter values of the original impairment model include weight values, bias values, training step lengths, batch times, iteration cycles and the like of a feedforward neural network.
S515, if the accessory error value is smaller than the accessory error threshold value, calculating a duration prediction set of the non-core accessory damage set by using the second classification function;
in a preferred embodiment of the present invention, the second classification function has the same function as the first classification function, and as described above, when the pull rod fitting is damaged, the tie rod is also damaged correspondingly, so that the second classification function is used to calculate that when the pull rod fitting is damaged, the corresponding maintenance time is 3 hours.
S516, calculating a maintenance duration error value of the duration prediction set and the maintenance duration set;
s517, judging the size relation between the maintenance time length error value and a preset maintenance time length threshold value;
s518, if the maintenance duration error value is larger than or equal to the maintenance duration threshold value, continuously adjusting the internal parameter value of the original damage assessment model, and returning to S511;
and S519, if the maintenance duration error value is smaller than the maintenance duration threshold value, obtaining the standard damage assessment model.
In detail, the adjusting the internal parameter values of the original impairment model comprises: modifying the weight value and the bias value of the original damage assessment model; and modifying the step length and the batch number of the original damage assessment model training.
In the preferred embodiment of the present invention, the weight value and the bias value are internal parameter values of the feedforward neural network.
S6, obtaining the damaged accessory to be damaged, and obtaining the maintenance duration of the damaged accessory by damage assessment by utilizing the standard damage assessment model.
If an automobile with a car accident needs to be damaged and the engine hood of the automobile is folded in a large area, the standard damage assessment model predicts that if the engine hood of the automobile is folded in a large area, the corresponding bumper is damaged, and therefore compared with the traditional damage assessment, the damage assessment method can obtain a damage assessment result with longer maintenance time.
According to the method, an original damage accessory set is extracted according to a historical maintenance data set of a target object, feature extraction and similarity calculation are carried out on the original damage accessory set to obtain a standard damage accessory set, the feature extraction can effectively extract the feature of damage of each accessory, interference of non-accessory damage features is reduced, and meanwhile, part of similar accessory features are removed by using a similarity calculation method, so that interference of data volume, non-accessory features and similar features on subsequent target object loss assessment can be effectively reduced, and the loss assessment accuracy is improved; meanwhile, in the embodiment of the invention, the standard damage accessory set is divided into the core accessory damage set and the non-core accessory damage set, the damage assessment model is trained through the relevance between the non-core accessory and the core accessory, the accessory is effectively divided into the core accessory and the non-core accessory, and the damage assessment model is trained according to the relevance between the core accessory and the non-core accessory, so that the interference on the whole damage assessment process caused by the unclear relation between the accessories is avoided, and the accuracy of damage assessment can be further improved. Therefore, the method, the device and the computer readable storage medium for determining the damage of the target object provided by the invention can be combined with the relation between the accessories of the target object, so that the accuracy rate of determining the damage of the target object is improved.
Fig. 4 is a block diagram of the damage assessment device according to the present invention.
The object damage assessment apparatus 100 according to the present invention may be installed in an electronic device. According to the realized functions, the target damage assessment device can comprise an accessory feature calculation module 101, an accessory division module 102, a model training module 103 and a target damage assessment module 104. A module according to the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the accessory feature calculation module 101 is configured to obtain a historical maintenance data set of a target object, extract an original damaged accessory set and a maintenance duration set from the historical maintenance data set, and perform feature extraction on the original damaged accessory set to obtain an accessory feature set;
the accessory dividing module 102 is configured to calculate similarity between accessory features in the accessory feature set according to the maintenance duration set, clean the original damaged accessory set based on the similarity to obtain a standard damaged accessory set, and divide the standard damaged accessory set into a core accessory damaged set and a non-core accessory damaged set;
the model training module 103 is configured to construct an original damage assessment model based on a feedforward neural network, and train the original damage assessment model by using the core accessory damage set, the non-core accessory damage set, and the maintenance duration set to obtain a standard damage assessment model;
the target damage assessment module 104 is configured to perform damage assessment on a damaged accessory of the target object to be damaged by the standard damage assessment model, and obtain a maintenance duration of the damaged accessory.
The module in the device provided by the application can improve the accuracy of damage assessment on the target object by combining the relationship between the accessory and the accessory of the target object based on the target object damage assessment method.
Fig. 5 is a schematic structural diagram of an electronic device for implementing the method for determining damage to an object according to the present invention.
The electronic device 1 may comprise a processor 10, a memory 11 and a bus, and may further comprise a computer program, such as an object impairment program 12, stored in the memory 11 and executable on the processor 10.
The memory 11 includes at least one type of readable storage medium, which includes flash memory, removable hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only to store application software installed in the electronic device 1 and various types of data, such as codes of the object damage program 12, but also to temporarily store data that has been output or is to be output.
The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device 1 by running or executing programs or modules (for example, executing a target damage program) stored in the memory 11 and calling data stored in the memory 11.
The bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
Fig. 5 only shows an electronic device with components, and it will be understood by a person skilled in the art that the structure shown in fig. 5 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or a combination of certain components, or a different arrangement of components.
For example, although not shown, the electronic device 1 may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so as to implement functions of charge management, discharge management, power consumption management, and the like through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 1 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
Further, the electronic device 1 may further include a network interface, and optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a bluetooth interface, etc.), which are generally used for establishing a communication connection between the electronic device 1 and other electronic devices.
Optionally, the electronic device 1 may further comprise a user interface, which may be a Display (Display), an input unit (such as a Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the electronic device 1 and for displaying a visualized user interface, among other things.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The object impairment program 12 stored in the memory 11 of the electronic device 1 is a combination of instructions that, when executed in the processor 10, enable:
acquiring a historical maintenance data set of a target object, and extracting an original damage accessory set and a maintenance duration set from the historical maintenance data set;
performing feature extraction on the original damage accessory set to obtain an accessory feature set;
according to the maintenance duration set, calculating similarity among the accessory features in the accessory feature set, and cleaning the original damaged accessory set based on the similarity to obtain a standard damaged accessory set;
dividing the standard damage accessory set into a core accessory damage set and a non-core accessory damage set;
constructing an original damage assessment model based on a forward feedback neural network, and training the original damage assessment model by using the core accessory damage set, the non-core accessory damage set and the maintenance duration set to obtain a standard damage assessment model;
and performing damage assessment on the damaged accessory of the target object to be subjected to damage assessment by using the standard damage assessment model to obtain the maintenance duration of the damaged accessory.
Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. The computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
Further, the computer usable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules 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, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any accompanying claims should not be construed as limiting the claim concerned.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A method of damage assessment of a target, the method comprising:
acquiring a historical maintenance data set of a target object, and extracting an original damage accessory set and a maintenance duration set from the historical maintenance data set;
performing feature extraction on the original damage accessory set to obtain an accessory feature set;
according to the maintenance duration set, calculating similarity among the accessory features in the accessory feature set, and cleaning the original damaged accessory set based on the similarity to obtain a standard damaged accessory set;
dividing the standard damage accessory set into a core accessory damage set and a non-core accessory damage set;
constructing an original damage assessment model based on a forward feedback neural network, and training the original damage assessment model by using the core accessory damage set, the non-core accessory damage set and the maintenance duration set to obtain a standard damage assessment model;
and performing damage assessment on the damaged accessory of the target object to be subjected to damage assessment by using the standard damage assessment model to obtain the maintenance duration of the damaged accessory.
2. The method of claim 1, wherein constructing the original impairment model based on the feedforward neural network comprises:
integrating a preset first classification function and a preset second classification function to obtain an output layer, wherein the first classification function and the second classification function are probability functions;
and connecting the output layer to the tail end of the feedforward neural network to obtain the original damage assessment model.
3. The method of claim 2, wherein training the original damage assessment model using the set of core component damage, the set of non-core component damage, and the set of repair durations to obtain a standard damage assessment model comprises:
performing calculation on a non-core accessory damage set by using the first classification function to obtain a core accessory prediction set;
calculating a fitting error value between the core fitting prediction set and the core fitting damage set;
judging the size relation between the accessory error value and a preset accessory error threshold value;
if the accessory error value is larger than or equal to the accessory error threshold value, adjusting the internal parameter value of the original damage assessment model, and predicting a core accessory prediction set again;
if the accessory error value is smaller than the accessory error threshold value, calculating a duration prediction set of the non-core accessory damage set by using the second classification function;
calculating a maintenance duration error value of the duration prediction set and the maintenance duration set;
judging the size relation between the maintenance duration error value and a preset maintenance duration threshold value;
if the maintenance duration error value is larger than or equal to the maintenance duration threshold value, continuously adjusting the internal parameter value of the original damage assessment model, and recalculating a core component prediction set;
and if the maintenance duration error value is smaller than the maintenance duration threshold value, obtaining the standard damage assessment model.
4. The method of claim 2, wherein the performing a computation on a set of non-core accessory impairments using the first classification function to obtain a set of core accessory predictions comprises:
extracting a feature set of the non-core accessory damage set by using the feedforward neural network;
and calculating a probability value set corresponding to the feature set by using the first classification function, and predicting by using the probability value set to obtain a core accessory prediction set.
5. The method of claim 3, wherein said adjusting internal parameter values of said original impairment model comprises:
modifying the weight value and the bias value of the original damage assessment model;
and modifying the step length and the training batch number of the training of the original damage assessment model.
6. The method for object damage assessment according to claim 1, wherein said feature extraction of said original damage accessory set to obtain an accessory feature set comprises:
carrying out preprocessing operations including analysis and abnormal word removal on the original damage accessory set to obtain a primary damage accessory set;
and performing word vector conversion on each damage accessory in the primary damage accessory set to obtain the accessory feature set.
7. The method of any one of claims 1 to 6, wherein the calculating the similarity between the accessory features within the accessory feature set comprises:
calculating the similarity between the accessory features in the accessory feature set by adopting a similarity calculation method as follows:
the method comprises the following steps of obtaining a plurality of accessory features, wherein sim (d, T) represents the similarity between the accessory feature d and the accessory feature T in the accessory feature set, w represents the weighting coefficients of d, T and other accessory features k in the accessory feature set, n is the total data number in the accessory feature set, alpha and beta are offset coefficients, and T is the maintenance duration corresponding to the accessory features.
8. A target damage assessment apparatus, said apparatus comprising:
the accessory feature calculation module is used for acquiring a historical maintenance data set of a target object, extracting an original damaged accessory set and a maintenance duration set from the historical maintenance data set, and performing feature extraction on the original damaged accessory set to obtain an accessory feature set;
the accessory dividing module is used for calculating the similarity among the accessory features in the accessory feature set according to the maintenance duration set, cleaning the original damage accessory set based on the similarity to obtain a standard damage accessory set, and dividing the standard damage accessory set into a core accessory damage set and a non-core accessory damage set;
the model training module is used for constructing an original damage assessment model based on a forward feedback neural network, and training the original damage assessment model by using the core accessory damage set, the non-core accessory damage set and the maintenance duration set to obtain a standard damage assessment model;
and the target object damage assessment module is used for performing damage assessment on a damaged accessory of the target object to be damaged by the standard damage assessment model to obtain the maintenance duration of the damaged accessory.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the object impairment method of any one of claims 1 to 7.
10. A computer-readable storage medium comprising a storage data area and a storage program area, wherein the storage data area stores created data, and the storage program area stores a computer program; wherein the computer program, when executed by a processor, implements the object impairment method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010927116.5A CN112085610B (en) | 2020-09-07 | 2020-09-07 | Target damage assessment method, target damage assessment device, electronic equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010927116.5A CN112085610B (en) | 2020-09-07 | 2020-09-07 | Target damage assessment method, target damage assessment device, electronic equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112085610A true CN112085610A (en) | 2020-12-15 |
| CN112085610B CN112085610B (en) | 2023-08-22 |
Family
ID=73732441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010927116.5A Active CN112085610B (en) | 2020-09-07 | 2020-09-07 | Target damage assessment method, target damage assessment device, electronic equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112085610B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113628055A (en) * | 2021-07-23 | 2021-11-09 | 明觉科技（北京）有限公司 | Vehicle accident loss evaluation method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107180389A (en) * | 2017-05-10 | 2017-09-19 | 平安科技（深圳）有限公司 | People's wound Claims Resolution setting loss fee calculating method, device, server and medium |
| CN109215027A (en) * | 2018-10-11 | 2019-01-15 | 平安科技（深圳）有限公司 | A kind of car damage identification method neural network based, server and medium |
| WO2019169688A1 (en) * | 2018-03-09 | 2019-09-12 | 平安科技（深圳）有限公司 | Vehicle loss assessment method and apparatus, electronic device, and storage medium |
| CN110458301A (en) * | 2019-07-11 | 2019-11-15 | 深圳壹账通智能科技有限公司 | A kind of damage identification method of vehicle part, device, computer equipment and storage medium |
| CN110705361A (en) * | 2019-09-06 | 2020-01-17 | 中国平安财产保险股份有限公司 | Intelligent damage assessment method and device for vehicle, computer system and readable storage medium |
| CN111488875A (en) * | 2020-06-24 | 2020-08-04 | 爱保科技有限公司 | Vehicle insurance claim settlement loss checking method and device based on image recognition and electronic equipment |
| US10762385B1 (en) * | 2017-06-29 | 2020-09-01 | State Farm Mutual Automobile Insurance Company | Deep learning image processing method for determining vehicle damage |
-
2020
- 2020-09-07 CN CN202010927116.5A patent/CN112085610B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107180389A (en) * | 2017-05-10 | 2017-09-19 | 平安科技（深圳）有限公司 | People's wound Claims Resolution setting loss fee calculating method, device, server and medium |
| US10762385B1 (en) * | 2017-06-29 | 2020-09-01 | State Farm Mutual Automobile Insurance Company | Deep learning image processing method for determining vehicle damage |
| WO2019169688A1 (en) * | 2018-03-09 | 2019-09-12 | 平安科技（深圳）有限公司 | Vehicle loss assessment method and apparatus, electronic device, and storage medium |
| CN109215027A (en) * | 2018-10-11 | 2019-01-15 | 平安科技（深圳）有限公司 | A kind of car damage identification method neural network based, server and medium |
| CN110458301A (en) * | 2019-07-11 | 2019-11-15 | 深圳壹账通智能科技有限公司 | A kind of damage identification method of vehicle part, device, computer equipment and storage medium |
| CN110705361A (en) * | 2019-09-06 | 2020-01-17 | 中国平安财产保险股份有限公司 | Intelligent damage assessment method and device for vehicle, computer system and readable storage medium |
| CN111488875A (en) * | 2020-06-24 | 2020-08-04 | 爱保科技有限公司 | Vehicle insurance claim settlement loss checking method and device based on image recognition and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113628055A (en) * | 2021-07-23 | 2021-11-09 | 明觉科技（北京）有限公司 | Vehicle accident loss evaluation method and device |
| WO2023000737A1 (en) * | 2021-07-23 | 2023-01-26 | 明觉科技（北京）有限公司 | Vehicle accident loss assessment method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112085610B (en) | 2023-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111814962A (en) | Method and device for acquiring parameters of recognition model, electronic equipment and storage medium | |
| CN111652278B (en) | User behavior detection method, device, electronic equipment and medium | |
| CN111783982A (en) | Attack sample acquisition method, device, equipment and medium | |
| CN114519524A (en) | Enterprise risk early warning method and device based on knowledge graph and storage medium | |
| CN112528013A (en) | Text abstract extraction method and device, electronic equipment and storage medium | |
| CN112749653A (en) | Pedestrian detection method, device, electronic equipment and storage medium | |
| CN111339072B (en) | User behavior-based change value analysis method and device, electronic equipment and medium | |
| CN111985449A (en) | Rescue scene image identification method, device, equipment and computer medium | |
| CN112579621A (en) | Data display method and device, electronic equipment and computer storage medium | |
| CN111461266A (en) | Vehicle damage assessment abnormity identification method, device, server and storage medium | |
| CN114187489B (en) | Method and device for detecting abnormal driving risk of vehicle, electronic equipment and storage medium | |
| CN112085610B (en) | Target damage assessment method, target damage assessment device, electronic equipment and computer readable storage medium | |
| CN112101481B (en) | Method, device, equipment and storage medium for screening influence factors of target object | |
| CN112816898B (en) | Battery failure prediction method and device, electronic equipment and storage medium | |
| CN115049836B (en) | Image segmentation method, device, equipment and storage medium | |
| CN111460293A (en) | Information pushing method and device and computer readable storage medium | |
| CN114708073B (en) | Intelligent detection method and device for surrounding mark and serial mark, electronic equipment and storage medium | |
| CN113822379B (en) | Process process anomaly analysis method and device, electronic equipment and storage medium | |
| CN113705201B (en) | Text-based event probability prediction evaluation algorithm, electronic device and storage medium | |
| CN115146064A (en) | Intention recognition model optimization method, device, equipment and storage medium | |
| CN115034812A (en) | Steel industry sales prediction method and device based on big data | |
| CN113515591A (en) | Text bad information identification method and device, electronic equipment and storage medium | |
| CN112215336A (en) | Data labeling method, device, equipment and storage medium based on user behavior | |
| CN113343882A (en) | Crowd counting method and device, electronic equipment and storage medium | |
| CN112685536B (en) | Text dialogue method, text dialogue device, electronic equipment and storage medium |
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 |