CN113255833B - Vehicle damage assessment method, device, equipment and storage medium - Google Patents
Vehicle damage assessment method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113255833B CN113255833B CN202110701943.7A CN202110701943A CN113255833B CN 113255833 B CN113255833 B CN 113255833B CN 202110701943 A CN202110701943 A CN 202110701943A CN 113255833 B CN113255833 B CN 113255833B
- Authority
- CN
- China
- Prior art keywords
- risk
- target
- factor data
- initial
- vehicle damage
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, and discloses a vehicle loss assessment method, device, equipment and storage medium, which are used for improving the accuracy of vehicle loss assessment. The vehicle damage assessment method comprises the following steps: receiving a vehicle damage assessment request, and acquiring a target factor data set according to the vehicle damage assessment request, wherein the target factor data set comprises driver factor data, vehicle factor data, risk factor data and driving behavior factor data; carrying out risk prediction on the target factor data set through a preset actuarial model to obtain an initial compensation risk prediction result; carrying out risk identification processing on the driving behavior factor data through the trained residual error network model to obtain an initial compensation risk residual value; and calculating a target compensation risk actual result according to the initial compensation risk prediction result and the initial compensation risk residual value, and determining the vehicle damage compensation amount based on the target compensation risk actual result. In addition, the invention also relates to a block chain technology, and the target factor data set can be stored in the block chain node.
Description
Technical Field
The invention relates to the technical field of artificial intelligence neural networks, in particular to a vehicle loss assessment method, device, equipment and storage medium.
Background
With the development and popularization of big data, more and more data can be collected in a big data portrait of a user, and the data is more and more comprehensive. How to apply user data to the traditional car insurance actuarial model is always a key point of industry attention.
According to the traditional vehicle insurance actuarial model, if a user risk factor is added, the user risk factor is required to have clear risk correlation, and the data saturation is required to be high during synchronization. In the face of the characteristics of large data dimension and strong data sparsity, unsaturated factors (namely sparse factors) cannot be added into a traditional model.
Wherein unsaturated data refers to data of this type, which is owned only by a part of users, for example: the driving behavior data is used by only a portion of the vehicle and user authorization models. And if the unsaturated data is added into the traditional model according to the traditional method, the data of the type is lost by most users, so that the whole model cannot have a strong effect, and the accuracy of predicting the vehicle damage compensation amount is low.
Disclosure of Invention
The invention provides a vehicle damage assessment method, a vehicle damage assessment device, vehicle damage assessment equipment and a storage medium, which are used for determining vehicle damage compensation amount through a preset actuarial model and a trained residual error network model, and improving the accuracy of vehicle damage compensation prediction.
To achieve the above object, a first aspect of the present invention provides a vehicle damage assessment method, including: receiving a vehicle damage assessment request, and acquiring a target factor data set according to the vehicle damage assessment request, wherein the target factor data set comprises driver factor data, vehicle factor data, risk factor data and driving behavior factor data; performing risk prediction on the target factor data set through a preset actuarial model to obtain an initial compensation risk prediction result; carrying out risk identification processing on the driving behavior factor data through a trained residual error network model to obtain an initial compensation risk residual value; and calculating a target compensation risk actual result according to the initial compensation risk prediction result and the initial compensation risk residual value, and determining the vehicle damage compensation amount based on the target compensation risk actual result.
Optionally, in a first implementation manner of the first aspect of the present invention, the performing risk identification processing on the driving behavior factor data through the trained residual network model to obtain an initial reimbursement risk residual value includes: performing feature extraction and feature vector normalization processing on the driving behavior factor data through a trained residual error network model to obtain a plurality of normalized feature vectors, wherein the trained residual error network model comprises a plurality of decision trees; and performing identification and classification processing on the plurality of normalized feature vectors based on the plurality of decision trees to obtain a prediction result corresponding to each decision tree, and accumulating the prediction results corresponding to each decision tree to obtain an initial reimbursement risk residual value.
Optionally, in a second implementation manner of the first aspect of the present invention, the calculating a target risk actual result according to the initial risk prediction result and the initial risk residual value, and determining a vehicle damage compensation amount based on the target risk actual result includes: judging whether the initial reimbursement risk prediction result belongs to a preset numerical range or not; if the initial claim risk prediction result belongs to a preset numerical range, performing multiplication operation on the initial claim risk prediction result and the initial claim risk residual value to obtain a target claim risk actual result; and inquiring target business risk compensation rate from a preset risk compensation configuration table based on the target compensation risk actual result, and determining the vehicle damage compensation amount according to the target business risk compensation rate and a preset compensation benchmark limit.
Optionally, in a third implementation manner of the first aspect of the present invention, after the target business risk compensation rate is queried from a preset risk compensation configuration table based on the target compensation risk actual result, and the vehicle damage compensation amount is determined according to the target business risk compensation rate and a preset compensation benchmark limit, the vehicle damage assessment method further includes: if the initial reimbursement risk prediction result does not belong to the preset numerical range, performing addition calculation on the initial reimbursement risk prediction result and the initial reimbursement risk residual value to obtain a target reimbursement risk actual result; and inquiring a target service risk grade from a preset risk grade configuration table based on the target reimbursement risk actual result, and setting the target reimbursement risk actual result as the vehicle damage reimbursement amount when the target service risk grade is not null.
Optionally, in a fourth implementation manner of the first aspect of the present invention, in the receiving a vehicle damage assessment request, a target factor data set is obtained according to the vehicle damage assessment request, where the target factor data set includes driver factor data, vehicle factor data, risk factor data, and driving behavior factor data, and the vehicle damage assessment method further includes: acquiring a historical driving risk data set, and performing feature cleaning on the historical driving risk data set to obtain a driving behavior sample data set, wherein each driving behavior sample data has a corresponding sample identification; carrying out numerical characteristic normalization, data binning and discrete characteristic digitization processing on the driving behavior sample data set in sequence to obtain a target sample data set; predicting and identifying the target sample data set through a preset actuarial model to obtain a plurality of sample prediction results; obtaining a real result corresponding to each sample prediction result, dividing each sample prediction result by the real result corresponding to each sample prediction result to obtain a plurality of prediction ratios, and setting the prediction ratios as output variables; setting the target sample data set as an input variable, generating a decision tree model according to the input variable and the output variable through a gradient lifting decision tree algorithm, and performing pruning training on the decision tree model according to a loss function of a minimized decision tree to obtain the trained residual error network model, wherein the decision tree model comprises a plurality of decision trees.
Optionally, in a fifth implementation manner of the first aspect of the present invention, before the receiving a vehicle damage assessment request and obtaining a target factor data set according to the vehicle damage assessment request, where the target factor data set includes driver factor data, vehicle factor data, risk factor data, and driving behavior factor data, the vehicle damage assessment method further includes: acquiring initial vehicle claim payment sample data, and performing claim payment data labeling processing on the initial vehicle claim payment sample data to obtain target vehicle claim payment sample data; and constructing the preset actuarial model based on the target vehicle claim sample data, wherein the preset actuarial model is a trained linear regression model or a trained polynomial regression model.
Optionally, in a sixth implementation manner of the first aspect of the present invention, in the calculating a target risk actual result according to the initial risk prediction result and the initial risk residual value, and determining a vehicle damage compensation amount based on the target risk actual result, the vehicle damage compensation method further includes: generating an order to be checked according to the vehicle damage claim payment amount, and sending the order to be checked to a target terminal through a preset message queue; and receiving an audit notification message sent by the target terminal, and triggering a corresponding service process according to the audit notification message.
A second aspect of the present invention provides a vehicle damage assessment device, comprising: the system comprises an acquisition module, a judgment module and a processing module, wherein the acquisition module is used for receiving a vehicle damage assessment request and acquiring a target factor data set according to the vehicle damage assessment request, and the target factor data set comprises driver factor data, vehicle factor data, risk factor data and driving behavior factor data; the prediction module is used for carrying out risk prediction on the target factor data set through a preset actuarial model to obtain an initial reimbursement risk prediction result; the recognition module is used for carrying out risk recognition processing on the driving behavior factor data through a trained residual error network model to obtain an initial compensation risk residual value; and the calculation module is used for calculating a target compensation risk actual result according to the initial compensation risk prediction result and the initial compensation risk residual value, and determining the vehicle damage compensation amount based on the target compensation risk actual result.
Optionally, in a first implementation manner of the second aspect of the present invention, the identification module is specifically configured to: performing feature extraction and feature vector normalization processing on the driving behavior factor data through a trained residual error network model to obtain a plurality of normalized feature vectors, wherein the trained residual error network model comprises a plurality of decision trees; and performing identification and classification processing on the plurality of normalized feature vectors based on the plurality of decision trees to obtain a prediction result corresponding to each decision tree, and accumulating the prediction results corresponding to each decision tree to obtain an initial reimbursement risk residual value.
Optionally, in a second implementation manner of the second aspect of the present invention, the calculation module includes: the judging unit is used for judging whether the initial reimbursement risk prediction result belongs to a preset numerical range or not; the first operation unit is used for multiplying the initial claim risk prediction result and the initial claim risk residual value to obtain a target claim risk actual result if the initial claim risk prediction result belongs to a preset numerical range; and the determining unit is used for inquiring the target service risk compensation rate from a preset risk compensation configuration table based on the target compensation risk actual result and determining the vehicle damage compensation amount according to the target service risk compensation rate and a preset compensation benchmark limit.
Optionally, in a third implementation manner of the second aspect of the present invention, the calculation module further includes: the second operation unit is used for performing addition calculation on the initial claim payment risk prediction result and the initial claim payment risk residual value to obtain a target claim payment risk actual result if the initial claim payment risk prediction result does not belong to a preset numerical range; and the setting unit is used for inquiring a target service risk level from a preset risk level configuration table based on the target reimbursement risk actual result, and setting the target reimbursement risk actual result as the vehicle damage reimbursement amount when the target service risk level is not null.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the vehicle damage assessment device further includes: the cleaning module is used for acquiring a historical driving risk data set and performing characteristic cleaning on the historical driving risk data set to obtain a driving behavior sample data set, wherein each driving behavior sample data set has a corresponding sample identification; the processing module is used for sequentially carrying out numerical characteristic normalization, data binning and discrete characteristic digitization processing on the driving behavior sample data set to obtain a target sample data set; the prediction identification module is used for performing prediction identification on the target sample data set through a preset actuarial model to obtain a plurality of sample prediction results; the division module is used for acquiring a real result corresponding to each sample prediction result, dividing each sample prediction result by the real result corresponding to each sample prediction result to obtain a plurality of prediction ratios, and setting the prediction ratios as output variables; and the pruning training module is used for setting the target sample data set as an input variable, generating a decision tree model according to the input variable and the output variable through a gradient lifting decision tree algorithm, and carrying out pruning training on the decision tree model according to a loss function of a minimized decision tree to obtain the trained residual error network model, wherein the decision tree model comprises a plurality of decision trees.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the vehicle damage assessment apparatus further includes: the marking module is used for acquiring initial vehicle claim payment sample data, and performing claim payment data marking processing on the initial vehicle claim payment sample data to obtain target vehicle claim payment sample data; and the construction module is used for constructing the preset actuarial model based on the target vehicle claims sample data, wherein the preset actuarial model is a trained linear regression model or a trained polynomial regression model.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the vehicle damage assessment apparatus further includes: the generating module is used for generating an order to be checked according to the vehicle damage claim payment amount and sending the order to be checked to a target terminal through a preset message queue; and the triggering module is used for receiving the audit notification message sent by the target terminal and triggering the corresponding business process according to the audit notification message.
A third aspect of the present invention provides a vehicle damage assessment apparatus comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the vehicle damage assessment apparatus to perform the vehicle damage assessment method described above.
A fourth aspect of the present invention provides a computer-readable storage medium having stored therein instructions, which, when run on a computer, cause the computer to execute the above-mentioned vehicle damage assessment method.
According to the technical scheme, a vehicle damage assessment request is received, and a target factor data set is obtained according to the vehicle damage assessment request, wherein the target factor data set comprises driver factor data, vehicle factor data, risk factor data and driving behavior factor data; performing risk prediction on the target factor data set through a preset actuarial model to obtain an initial compensation risk prediction result; carrying out risk identification processing on the driving behavior factor data through a trained residual error network model to obtain an initial compensation risk residual value; and calculating a target compensation risk actual result according to the initial compensation risk prediction result and the initial compensation risk residual value, and determining the vehicle damage compensation amount based on the target compensation risk actual result. In the embodiment of the invention, a target factor data set is obtained according to a vehicle damage assessment request, wherein the target factor data set comprises driver factor data; carrying out risk prediction on the target factor data set through a preset actuarial model to obtain an initial compensation risk prediction result; carrying out risk identification processing on the driving behavior factor data through the trained residual error network model to obtain an initial compensation risk residual value; and determining the damage compensation amount of the vehicle according to the initial compensation risk prediction result and the initial compensation risk residual value. The vehicle damage compensation amount is determined through the preset actuarial model and the trained residual error network model, and the accuracy of vehicle damage compensation prediction and the accuracy of risk prediction are improved.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a vehicle damage assessment method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of another embodiment of a vehicle damage assessment method according to an embodiment of the present invention;
FIG. 3 is a schematic view of an embodiment of a vehicle damage assessment apparatus according to an embodiment of the present invention;
fig. 4 is a schematic view of another embodiment of the vehicle damage assessment apparatus according to the embodiment of the present invention;
fig. 5 is a schematic diagram of an embodiment of the vehicle damage assessment device in the embodiment of the invention.
Detailed Description
The embodiment of the invention provides a vehicle damage assessment method, a vehicle damage assessment device, vehicle damage assessment equipment and a storage medium, which are used for determining vehicle damage claim payment amount through a preset actuarial model and a trained residual error network model, and improving the accuracy of risk prediction.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For ease of understanding, a detailed flow of an embodiment of the present invention is described below, with reference to fig. 1, where an embodiment of a method for determining damage to a vehicle according to an embodiment of the present invention includes:
101. the method comprises the steps of receiving a vehicle damage assessment request, and obtaining a target factor data set according to the vehicle damage assessment request, wherein the target factor data set comprises driver factor data, vehicle factor data, risk factor data and driving behavior factor data.
The target factor data set is used for indicating factor data related to driving risks of a user, and comprises driver factor data, vehicle factor data, risk factor data and driving behavior factor data, wherein the driver factor data comprises factor data such as age, sex and driving age; the vehicle factor data comprises the vehicle model, the vehicle condition and the like, wherein the vehicle condition refers to the technical condition of the vehicle and is used for indicating multiple indexes of the safety performance, the power performance, the operation performance, the exhaust emission, the vehicle appearance and the like of the vehicle; the risk factor data comprises historical risk times and historical risk types, for example, the historical risk times is 1, and the historical risk types are that claim settlement information fails to be audited; the driving behavior factor data may include rapid acceleration data, rapid deceleration data, and rapid turning data, the driving behavior factor data may further include driving duration data, driving mileage, and driving speed, and the driving behavior factor data may also include other data, which is not limited herein.
Specifically, the server receives a vehicle loss assessment request, and the server analyzes the vehicle loss assessment request to obtain a risk user identity and a risk user license plate number; the server inquires a preset database according to the identity identification of the risk user and the license plate number of the risk user to obtain a target factor data set, wherein the target factor data set comprises driver factor data, vehicle factor data, risk factor data and driving behavior factor data. The predetermined database is a database (e.g., neo4 j), a data warehouse hive, an in-memory database (e.g., SQLite or remote service dictionary redis), or a relational database (e.g., mysql), which is not limited herein. Further, the server stores the target factor data set in a blockchain database, which is not limited herein.
It is to be understood that the executing subject of the present invention may be a vehicle damage assessment device, and may also be a terminal or a server, which is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject.
102. And performing risk prediction on the target factor data set through a preset actuarial model to obtain an initial reimbursement risk prediction result.
It should be noted that the preset actuarial model is used for indicating that an initial reimbursement risk prediction result is determined according to the target factor data set, a value range of the initial reimbursement risk prediction result is greater than or equal to 0, and the initial reimbursement risk prediction result may be a reference reimbursement rate (that is, a probability value conforming to a normal standard distribution table) or reference reimbursement amount data (greater than 0) according to an actual application scenario, which is not limited herein. Further, before step 101, the server acquires initial vehicle claim payment sample data, and the server performs claim payment data labeling processing on the initial vehicle claim payment sample data to obtain target vehicle claim payment sample data; the server constructs a preset actuarial model based on the target vehicle claim payment sample data. The preset actuarial model may be a pre-trained linear regression model, a pre-trained polynomial regression model, or other pre-trained predictive user risk claim model, and is not limited herein.
Specifically, the server performs feature screening on a target factor data set through a preset actuarial model to obtain a plurality of actuarial index feature data, and the server determines a weight value corresponding to each actuarial index feature data; and the server performs mean value calculation according to the weight value corresponding to each actuarial index characteristic data to obtain an initial compensation risk prediction result. For example, when the initial reimbursement risk prediction result is the benchmark reimbursement rate, the initial reimbursement risk prediction result may be 0.9. When the initial reimbursement risk prediction result is the benchmark reimbursement amount data, the initial reimbursement risk prediction result may be 800.
103. And carrying out risk identification processing on the driving behavior factor data through the trained residual error network model to obtain an initial compensation risk residual value.
It should be noted that the initial reimbursement risk residual value is used to indicate a relative error value between the initial reimbursement risk prediction result and the target reimbursement risk actual result. The initial reimbursement risk residual value can be the corrected reimbursement rate and also can be the corrected reimbursement amount data. The value range of the correction claim rate is larger than 0, and the correction claim amount data can be positive numbers, negative numbers or 0. The initial reimbursement risk residual value is used for correcting the initial reimbursement risk prediction result, so that the initial reimbursement risk residual value and the initial reimbursement risk prediction result have consistency. For example, when the initial payout risk prediction result is the reference payout rate, the initial payout risk residual value is the corrected payout rate, the initial payout risk residual value may be 1.125, and when the initial payout risk prediction result is the reference payout amount data, the initial payout risk residual value is the corrected payout amount data, the initial payout risk residual value may be +20, may also be-20, and may also be 0, which is not limited herein. Specifically, the server inputs driving behavior factor data into a trained residual error network model; the server converts the driving behavior factor data into a plurality of initial characteristic vectors through a trained residual error network model; the server performs numerical value normalization processing on the plurality of initial feature vectors to obtain a plurality of normalized feature vectors; and the server performs recognition and classification processing based on the plurality of normalized feature vectors to obtain an initial compensation risk residual value.
104. And calculating a target compensation risk actual result according to the initial compensation risk prediction result and the initial compensation risk residual value, and determining the vehicle damage compensation amount based on the target compensation risk actual result.
If the initial claim risk prediction result can be a value range between 0 and 1, that is, the initial claim risk prediction result is a risk prediction probability value, the server performs multiplication operation on the initial claim risk prediction result and the initial claim risk residual value to obtain a target claim risk actual result, and the value range of the target claim risk actual result is between 0 and 1; and the server determines the vehicle damage compensation amount according to the target compensation risk actual result. For example, the initial reimbursement risk prediction result is a basic reimbursement amount, the initial reimbursement risk residual value is a positive or negative reimbursement difference, and the server adds the initial reimbursement risk prediction result and the initial reimbursement risk residual value to obtain a vehicle damage reimbursement amount.
In the embodiment of the invention, a target factor data set is obtained according to a vehicle damage assessment request, wherein the target factor data set comprises driver factor data; carrying out risk prediction on the target factor data set through a preset actuarial model to obtain an initial compensation risk prediction result; carrying out risk identification processing on the driving behavior factor data through the trained residual error network model to obtain an initial compensation risk residual value; and determining the damage compensation amount of the vehicle according to the initial compensation risk prediction result and the initial compensation risk residual value. The vehicle damage compensation amount is determined through the preset actuarial model and the trained residual error network model, and the accuracy of vehicle damage compensation prediction and the accuracy of risk prediction are improved.
Referring to fig. 2, another embodiment of the method for determining damage to a vehicle according to the embodiment of the present invention includes:
201. the method comprises the steps of receiving a vehicle damage assessment request, and obtaining a target factor data set according to the vehicle damage assessment request, wherein the target factor data set comprises driver factor data, vehicle factor data, risk factor data and driving behavior factor data.
The execution process of step 201 is similar to the execution process of step 101, and detailed description thereof is omitted here.
Further, before step 201, the server obtains a historical driving risk data set, and performs feature cleaning on the historical driving risk data set to obtain a driving behavior sample data set, wherein each driving behavior sample data set has a corresponding sample identifier; that is, the server performs feature selection on the historical driving risk data set (that is, all underlying factors for modeling or factors for primary processing), performs screening mainly based on saturation and correlation, and deletes features with low saturation; the server removes features that are too highly correlated with the Y-tag (features that may present data leaks). The server sequentially performs numerical characteristic normalization, data binning and discrete characteristic digitization processing on the driving behavior sample data set to obtain a target sample data set; the numerical characteristic normalization improves the stability of the model; data binning can avoid model overfitting; the server realizes discrete feature numeralization through one-hot coding or target coding. The server carries out prediction identification on the target sample data set through a preset actuarial model to obtain a plurality of sample prediction results; the server obtains a real result corresponding to each sample prediction result, divides each sample prediction result by the real result corresponding to each sample prediction result to obtain a plurality of ratios, and sets the ratios as output variables; the server sets the target sample data set as input variables, generates a decision tree model according to the input variables and the output variables through a gradient lifting decision tree algorithm, and performs pruning training on the decision tree model according to a loss function of a minimized decision tree to obtain a trained residual network model, wherein the decision tree model comprises a plurality of decision trees. After pruning training, the energy consumption can be reduced and the risk prediction speed can be increased by applying the trained residual error model.
202. And performing risk prediction on the target factor data set through a preset actuarial model to obtain an initial reimbursement risk prediction result.
The execution process of step 202 is similar to the execution process of step 102, and detailed description thereof is omitted here.
203. And carrying out risk identification processing on the driving behavior factor data through the trained residual error network model to obtain an initial compensation risk residual value.
And the initial reimbursement risk residual value is used for indicating a relative error value between the initial reimbursement risk prediction result and the target reimbursement risk actual result. Optionally, the server performs feature extraction and feature vector normalization processing on the driving behavior factor data through the trained residual error network model to obtain a plurality of normalized feature vectors, wherein the trained residual error network model comprises a plurality of decision trees; and the server identifies and classifies the plurality of normalized feature vectors based on the plurality of decision trees to obtain a prediction result corresponding to each decision tree, and accumulates the prediction results corresponding to each decision tree to obtain an initial reimbursement risk residual value.
Wherein each normalized feature vector belongs to the [0,1] interval. And optimizing an initial compensation risk prediction result of the actuarial model through a preset actuarial model and the trained residual error network model. The accuracy of the actuarial model prediction can be improved, and the prediction result of the actuarial model can not be influenced. And aiming at users with driving behavior factor data, the risk is adjusted by using a residual error network model, and the prediction result is more accurate by using the model. The universality of the actuarial model is enhanced, and the accuracy of risk prediction can be improved by using a residual error network model aiming at other unsaturated data, such as user position service data and new energy vehicle data.
204. And calculating a target compensation risk actual result according to the initial compensation risk prediction result and the initial compensation risk residual value, and determining the vehicle damage compensation amount based on the target compensation risk actual result.
Specifically, the server judges whether the initial reimbursement risk prediction result belongs to a preset numerical range; wherein the predetermined range is greater than or equal to 0 and less than or equal to 1. Further, the server determines whether the initial reimbursement risk prediction result is greater than or equal to 0 and less than or equal to 1, for example, if the initial reimbursement risk prediction result is 0.75, the server determines that the initial reimbursement risk prediction result belongs to a preset value range, that is, the initial reimbursement risk prediction result is the reference reimbursement rate; if the initial reimbursement risk prediction result is 4000, the server determines that the initial reimbursement risk prediction result does not belong to the preset numerical range. If the initial claim risk prediction result belongs to the preset numerical range, the server performs multiplication operation on the initial claim risk prediction result and the initial claim risk residual value to obtain a target claim risk actual result; for example, the initial claim risk prediction result is 0.780, the initial claim risk residual value is 0.975, and the initial claim risk prediction result is multiplied by the initial claim risk residual value, i.e., 0.78 × 0.975, resulting in a target claim risk actual result of 0.800. The server inquires the target service risk compensation rate from a preset risk compensation configuration table based on the target compensation risk actual result, and determines the vehicle damage compensation amount according to the target service risk compensation rate and a preset compensation benchmark limit.
Further, if the initial reimbursement risk prediction result does not belong to the preset numerical range, the server performs addition calculation on the initial reimbursement risk prediction result and the initial reimbursement risk residual value to obtain a target reimbursement risk actual result; for example, the initial claim risk prediction result is 1250, the initial claim risk residual value is-105, and the initial claim risk prediction result and the initial claim risk residual value are added, i.e., 1250+ (-105), to obtain the target claim risk actual result of 1145. And the server inquires the target service risk level from a preset risk level configuration table based on the target claims risk actual result, and when the target service risk level is not null, the server sets the target claims risk actual result as the vehicle damage claims amount.
205. And generating an order to be checked according to the vehicle damage claim payment amount, and sending the order to be checked to the target terminal through a preset message queue.
Specifically, the server obtains a request for generating an audit order; the server analyzes the audit order generation request to obtain the service type, the target auditor identification and the user claim information, wherein the user claim information comprises the vehicle damage claim amount; the server acquires order template information according to the service type; the server performs order filling processing according to the user payment information based on the template information to obtain order content information; the server acquires the reviewer information according to the target reviewer identifier, and converts the reviewer information and the order content information into an order to be reviewed, wherein the order to be reviewed has a unique order identifier; and the server writes the order to be audited into a preset message queue and sends the order to be audited to the target terminal according to the information of the auditor through the preset message queue.
206. And receiving an audit notification message sent by the target terminal, and triggering the corresponding service flow according to the audit notification message.
Specifically, the server receives an audit notification message sent by the target terminal, extracts an order identifier, an audit result and audit opinion information from the audit notification message, and updates an order state corresponding to the order to be audited according to the order identifier and the audit result, wherein the order state comprises a state to be audited, a state in audit, a state that the audit is passed and a state that the audit is not passed; sending the audit result and the audit opinion information to the target user through a preset notification mode, wherein the preset notification mode comprises a short message mode and a message notification mode, and is not limited in detail here; and when the verification result is that the verification is passed, the server acquires the service type according to the order mark and calls a corresponding service flow (for example, a vehicle compensation service flow) according to the service type.
In the embodiment of the invention, a target factor data set is obtained according to a vehicle damage assessment request, wherein the target factor data set comprises driver factor data; carrying out risk prediction on the target factor data set through a preset actuarial model to obtain an initial compensation risk prediction result; carrying out risk identification processing on the driving behavior factor data through the trained residual error network model to obtain an initial compensation risk residual value; and determining the damage compensation amount of the vehicle according to the initial compensation risk prediction result and the initial compensation risk residual value. The vehicle damage compensation amount is determined through the preset actuarial model and the trained residual error network model, and the accuracy of vehicle damage compensation prediction and the accuracy of risk prediction are improved.
With reference to fig. 3, the vehicle damage assessment method in the embodiment of the present invention is described above, and a vehicle damage assessment device in the embodiment of the present invention is described below, where an embodiment of the vehicle damage assessment device in the embodiment of the present invention includes:
the obtaining module 301 is configured to receive a vehicle damage assessment request, and obtain a target factor data set according to the vehicle damage assessment request, where the target factor data set includes driver factor data, vehicle factor data, risk factor data, and driving behavior factor data;
the prediction module 302 is configured to perform risk prediction on the target factor data set through a preset actuarial model to obtain an initial reimbursement risk prediction result;
the identification module 303 is configured to perform risk identification processing on the driving behavior factor data through the trained residual network model to obtain an initial reimbursement risk residual value;
the calculating module 304 is configured to calculate a target reimbursement risk actual result according to the initial reimbursement risk prediction result and the initial reimbursement risk residual value, and determine a vehicle damage reimbursement amount based on the target reimbursement risk actual result.
Further, the target factor data set is stored in the block chain database, which is not limited herein.
In the embodiment of the invention, a target factor data set is obtained according to a vehicle damage assessment request, wherein the target factor data set comprises driver factor data; carrying out risk prediction on the target factor data set through a preset actuarial model to obtain an initial compensation risk prediction result; carrying out risk identification processing on the driving behavior factor data through the trained residual error network model to obtain an initial compensation risk residual value; and determining the damage compensation amount of the vehicle according to the initial compensation risk prediction result and the initial compensation risk residual value. The vehicle damage compensation amount is determined through the preset actuarial model and the trained residual error network model, and the accuracy of vehicle damage compensation prediction and the accuracy of risk prediction are improved.
Referring to fig. 4, another embodiment of the vehicle damage assessment apparatus according to the embodiment of the present invention includes:
the obtaining module 301 is configured to receive a vehicle damage assessment request, and obtain a target factor data set according to the vehicle damage assessment request, where the target factor data set includes driver factor data, vehicle factor data, risk factor data, and driving behavior factor data;
the prediction module 302 is configured to perform risk prediction on the target factor data set through a preset actuarial model to obtain an initial reimbursement risk prediction result;
the identification module 303 is configured to perform risk identification processing on the driving behavior factor data through the trained residual network model to obtain an initial reimbursement risk residual value;
the calculating module 304 is configured to calculate a target reimbursement risk actual result according to the initial reimbursement risk prediction result and the initial reimbursement risk residual value, and determine a vehicle damage reimbursement amount based on the target reimbursement risk actual result.
Optionally, the identifying module 303 may be further specifically configured to:
performing feature extraction and feature vector normalization processing on the driving behavior factor data through a trained residual error network model to obtain a plurality of normalized feature vectors, wherein the trained residual error network model comprises a plurality of decision trees;
and performing identification and classification processing on the plurality of normalized feature vectors based on a plurality of decision trees to obtain a prediction result corresponding to each decision tree, and accumulating the prediction results corresponding to each decision tree to obtain an initial reimbursement risk residual value.
Optionally, the calculation module 304 may further include:
a determining unit 3041, configured to determine whether the initial risk prediction result belongs to a preset value range;
the first arithmetic unit 3042, configured to perform a multiplication operation on the initial claim risk prediction result and the initial claim risk residual value if the initial claim risk prediction result belongs to a preset numerical range, to obtain an actual target claim risk result;
the determining unit 3043 is configured to query the target business risk compensation rate from the preset risk compensation configuration table based on the target compensation risk actual result, and determine the vehicle damage compensation amount according to the target business risk compensation rate and the preset compensation benchmark amount.
Optionally, the calculation module 304 may further include:
the second arithmetic unit 3044 is configured to, if the initial reimbursement risk prediction result does not belong to the preset numerical range, perform addition calculation on the initial reimbursement risk prediction result and the initial reimbursement risk residual value to obtain an actual target reimbursement risk result;
the setting unit 3045 is configured to query the target business risk level from the preset risk level configuration table based on the target reimbursement risk actual result, and set the target reimbursement risk actual result as the vehicle damage reimbursement amount when the target business risk level is not null.
Optionally, the vehicle damage assessment device may further include:
a cleaning module 305, configured to obtain a historical driving risk data set, and perform feature cleaning on the historical driving risk data set to obtain a driving behavior sample data set, where each driving behavior sample data set has a corresponding sample identifier;
the processing module 306 is used for sequentially carrying out numerical characteristic normalization, data binning and discrete characteristic digitization processing on the driving behavior sample data set to obtain a target sample data set;
the prediction identification module 307 is configured to perform prediction identification on the target sample data set through a preset actuarial model to obtain a plurality of sample prediction results;
a division module 308, configured to obtain a real result corresponding to each sample prediction result, divide each sample prediction result by the real result corresponding to each sample prediction result, respectively, to obtain multiple prediction ratios, and set the multiple prediction ratios as output variables;
the pruning training module 309 is configured to set the target sample data set as an input variable, generate a decision tree model according to the input variable and the output variable through a gradient lifting decision tree algorithm, and perform pruning training on the decision tree model according to a loss function of the minimized decision tree to obtain a trained residual network model, where the decision tree model includes multiple decision trees.
Optionally, the vehicle damage assessment device may further include:
the labeling module 310 is configured to obtain initial vehicle claim payment sample data, perform claim payment data labeling processing on the initial vehicle claim payment sample data, and obtain target vehicle claim payment sample data;
the building module 311 is configured to build a preset actuarial model based on the target vehicle claims sample data, where the preset actuarial model is a trained linear regression model or a trained polynomial regression model.
Optionally, the vehicle damage assessment device may further include:
the generating module 312 is configured to generate an order to be checked according to the vehicle damage claim payment amount, and send the order to be checked to the target terminal through a preset message queue;
and the triggering module 313 is configured to receive an audit notification message sent by the target terminal, and trigger a corresponding service flow according to the audit notification message.
In the embodiment of the invention, a target factor data set is obtained according to a vehicle damage assessment request, wherein the target factor data set comprises driver factor data; carrying out risk prediction on the target factor data set through a preset actuarial model to obtain an initial compensation risk prediction result; carrying out risk identification processing on the driving behavior factor data through the trained residual error network model to obtain an initial compensation risk residual value; and determining the damage compensation amount of the vehicle according to the initial compensation risk prediction result and the initial compensation risk residual value. The vehicle damage compensation amount is determined through the preset actuarial model and the trained residual error network model, and the accuracy of vehicle damage compensation prediction and the accuracy of risk prediction are improved.
The vehicle damage assessment device in the embodiment of the present invention is described in detail in terms of modularization in fig. 3 and 4 above, and the vehicle damage assessment apparatus in the embodiment of the present invention is described in detail in terms of hardware processing below.
Fig. 5 is a schematic structural diagram of a vehicle damage-assessment device 500 according to an embodiment of the present invention, where the vehicle damage-assessment device 500 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and a memory 520, and one or more storage media 530 (e.g., one or more mass storage devices) storing applications 533 or data 532. Memory 520 and storage media 530 may be, among other things, transient or persistent storage. The program stored on the storage medium 530 may include one or more modules (not shown), each of which may include a series of instructions operating on the vehicle damage assessment apparatus 500. Still further, the processor 510 may be configured to communicate with the storage medium 530 to execute a series of instruction operations in the storage medium 530 on the vehicle damage assessment apparatus 500.
The vehicle damage assessment apparatus 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, and the like. Those skilled in the art will appreciate that the vehicle damage assessment apparatus configuration shown in fig. 5 does not constitute a limitation of vehicle damage assessment apparatus and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, which may also be a volatile computer readable storage medium, having stored therein instructions, which, when run on a computer, cause the computer to perform the steps of the vehicle damage assessment method.
The invention also provides a vehicle damage assessment device, which comprises a memory and a processor, wherein the memory stores instructions, and the instructions are executed by the processor, so that the processor executes the steps of the vehicle damage assessment method in the embodiments.
Further, the computer-readable 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.
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.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
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 instructions for causing 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: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
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 (9)
1. A vehicle damage assessment method, characterized by comprising:
receiving a vehicle damage assessment request, and acquiring a target factor data set according to the vehicle damage assessment request, wherein the target factor data set comprises driver factor data, vehicle factor data, risk factor data and driving behavior factor data;
performing risk prediction on the target factor data set through a preset actuarial model to obtain an initial compensation risk prediction result;
carrying out risk identification processing on the driving behavior factor data through a trained residual error network model to obtain an initial compensation risk residual value;
judging whether the initial reimbursement risk prediction result belongs to a preset numerical range or not;
if the initial claim risk prediction result belongs to a preset numerical range, performing multiplication operation on the initial claim risk prediction result and the initial claim risk residual value to obtain a target claim risk actual result;
and inquiring target business risk compensation rate from a preset risk compensation configuration table based on the target compensation risk actual result, and determining the vehicle damage compensation amount according to the target business risk compensation rate and a preset compensation benchmark limit.
2. The vehicle damage assessment method according to claim 1, wherein the performing risk identification processing on the driving behavior factor data through the trained residual network model to obtain an initial reimbursement risk residual value comprises:
performing feature extraction and feature vector normalization processing on the driving behavior factor data through a trained residual error network model to obtain a plurality of normalized feature vectors, wherein the trained residual error network model comprises a plurality of decision trees;
and performing identification and classification processing on the plurality of normalized feature vectors based on the plurality of decision trees to obtain a prediction result corresponding to each decision tree, and accumulating the prediction results corresponding to each decision tree to obtain an initial reimbursement risk residual value.
3. The vehicle damage assessment method according to claim 1, wherein after querying a preset risk compensation configuration table for target business risk compensation rate based on the target compensation risk actual result and determining a vehicle damage compensation amount according to the target business risk compensation rate and a preset compensation benchmark limit, the vehicle damage assessment method further comprises:
if the initial reimbursement risk prediction result does not belong to the preset numerical range, performing addition calculation on the initial reimbursement risk prediction result and the initial reimbursement risk residual value to obtain a target reimbursement risk actual result;
and inquiring a target service risk grade from a preset risk grade configuration table based on the target reimbursement risk actual result, and setting the target reimbursement risk actual result as the vehicle damage reimbursement amount when the target service risk grade is not null.
4. The vehicle damage assessment method according to any one of claims 1-3, wherein before said receiving a vehicle damage assessment request, obtaining a target factor data set according to said vehicle damage assessment request, said target factor data set comprising driver factor data, vehicle factor data, risk factor data and driving behavior factor data, said vehicle damage assessment method further comprises:
acquiring a historical driving risk data set, and performing feature cleaning on the historical driving risk data set to obtain a driving behavior sample data set, wherein each driving behavior sample data has a corresponding sample identification;
carrying out numerical characteristic normalization, data binning and discrete characteristic digitization processing on the driving behavior sample data set in sequence to obtain a target sample data set;
predicting and identifying the target sample data set through a preset actuarial model to obtain a plurality of sample prediction results;
obtaining a real result corresponding to each sample prediction result, dividing each sample prediction result by the real result corresponding to each sample prediction result to obtain a plurality of prediction ratios, and setting the prediction ratios as output variables;
setting the target sample data set as an input variable, generating a decision tree model according to the input variable and the output variable through a gradient lifting decision tree algorithm, and performing pruning training on the decision tree model according to a loss function of a minimized decision tree to obtain the trained residual error network model, wherein the decision tree model comprises a plurality of decision trees.
5. The vehicle damage assessment method according to any one of claims 1-3, wherein before said receiving a vehicle damage assessment request, obtaining a target factor data set according to said vehicle damage assessment request, said target factor data set comprising driver factor data, vehicle factor data, risk factor data and driving behavior factor data, said vehicle damage assessment method further comprises:
acquiring initial vehicle claim payment sample data, and performing claim payment data labeling processing on the initial vehicle claim payment sample data to obtain target vehicle claim payment sample data;
and constructing the preset actuarial model based on the target vehicle claim sample data, wherein the preset actuarial model is a trained linear regression model or a trained polynomial regression model.
6. The vehicle damage assessment method according to any one of claims 1 to 3, wherein after said calculating a target damage risk actual result from said initial damage risk prediction result and said initial damage risk residual value, and determining a vehicle damage claim amount based on said target damage risk actual result, said vehicle damage assessment method further comprises:
generating an order to be checked according to the vehicle damage claim payment amount, and sending the order to be checked to a target terminal through a preset message queue;
and receiving an audit notification message sent by the target terminal, and triggering a corresponding service process according to the audit notification message.
7. A vehicle damage assessment device, characterized by comprising:
the system comprises an acquisition module, a judgment module and a processing module, wherein the acquisition module is used for receiving a vehicle damage assessment request and acquiring a target factor data set according to the vehicle damage assessment request, and the target factor data set comprises driver factor data, vehicle factor data, risk factor data and driving behavior factor data;
the prediction module is used for carrying out risk prediction on the target factor data set through a preset actuarial model to obtain an initial reimbursement risk prediction result;
the recognition module is used for carrying out risk recognition processing on the driving behavior factor data through a trained residual error network model to obtain an initial compensation risk residual value;
the calculation module is used for judging whether the initial compensation risk prediction result belongs to a preset numerical range or not; if the initial claim risk prediction result belongs to a preset numerical range, performing multiplication operation on the initial claim risk prediction result and the initial claim risk residual value to obtain a target claim risk actual result; and inquiring target business risk compensation rate from a preset risk compensation configuration table based on the target compensation risk actual result, and determining the vehicle damage compensation amount according to the target business risk compensation rate and a preset compensation benchmark limit.
8. A vehicle damage assessment device, characterized by comprising: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause the vehicle impairment device to perform the vehicle impairment method of any one of claims 1 to 6.
9. A computer readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement the vehicle damage assessment method according to any one of claims 1-6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110701943.7A CN113255833B (en) | 2021-06-24 | 2021-06-24 | Vehicle damage assessment method, device, equipment and storage medium |
| PCT/CN2022/071483 WO2022267456A1 (en) | 2021-06-24 | 2022-01-12 | Vehicle damage assessment method, apparatus and device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110701943.7A CN113255833B (en) | 2021-06-24 | 2021-06-24 | Vehicle damage assessment method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113255833A CN113255833A (en) | 2021-08-13 |
| CN113255833B true CN113255833B (en) | 2021-10-12 |
Family
ID=77189430
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110701943.7A Active CN113255833B (en) | 2021-06-24 | 2021-06-24 | Vehicle damage assessment method, device, equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113255833B (en) |
| WO (1) | WO2022267456A1 (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113255833B (en) * | 2021-06-24 | 2021-10-12 | 平安科技（深圳）有限公司 | Vehicle damage assessment method, device, equipment and storage medium |
| CN114493903B (en) * | 2022-02-17 | 2024-04-09 | 平安科技（深圳）有限公司 | Loss model optimization method in human cold risk assessment and related equipment |
| CN116452007B (en) * | 2023-06-15 | 2023-09-19 | 深圳市迪博企业风险管理技术有限公司 | Enterprise tax compliance risk assessment method based on capsule network |
| CN116452008B (en) * | 2023-06-16 | 2023-08-29 | 山东四季车网络科技有限公司 | Second-hand vehicle risk prediction method and system based on polynomial modeling |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8489433B2 (en) * | 2010-07-29 | 2013-07-16 | Insurance Services Office, Inc. | System and method for estimating loss propensity of an insured vehicle and providing driving information |
| CN108960431A (en) * | 2017-05-25 | 2018-12-07 | 北京嘀嘀无限科技发展有限公司 | The prediction of index, the training method of model and device |
| CN110599353A (en) * | 2018-06-13 | 2019-12-20 | 百度在线网络技术（北京）有限公司 | Vehicle insurance and claims rate prediction method, device, equipment and medium |
| CN108986249B (en) * | 2018-06-26 | 2021-08-03 | 杭州车厘子智能科技有限公司 | Vehicle remote damage assessment method and system based on panoramic all-around image |
| CN110103822A (en) * | 2019-05-17 | 2019-08-09 | 深圳市尼欧科技有限公司 | A kind of device and method that intelligent measurement and safe driving scoring are accustomed in driving behavior |
| CN111127228A (en) * | 2019-12-30 | 2020-05-08 | 山东坤达诚经济咨询有限公司 | Risk factor identification method, system and terminal |
| CN111260487A (en) * | 2020-01-20 | 2020-06-09 | 北京中科泽达科技有限公司 | Risk control method and device for vehicle insurance claim settlement |
| CN113255833B (en) * | 2021-06-24 | 2021-10-12 | 平安科技（深圳）有限公司 | Vehicle damage assessment method, device, equipment and storage medium |
-
2021
- 2021-06-24 CN CN202110701943.7A patent/CN113255833B/en active Active
-
2022
- 2022-01-12 WO PCT/CN2022/071483 patent/WO2022267456A1/en unknown
Non-Patent Citations (1)
| Title |
|---|
| 一种基于图像识别的车辆智能定损系统;施海;《科学技术创新》;20201031(第10期);第48-50页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113255833A (en) | 2021-08-13 |
| WO2022267456A1 (en) | 2022-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113255833B (en) | Vehicle damage assessment method, device, equipment and storage medium | |
| CN112381428B (en) | Service distribution method, device, equipment and storage medium based on reinforcement learning | |
| CN111507470A (en) | Abnormal account identification method and device | |
| CN113221960B (en) | Construction method and collection method of high-quality vulnerability data collection model | |
| CN112116225A (en) | Fighting efficiency evaluation method and device for equipment system, and storage medium | |
| CN111275485A (en) | Power grid customer grade division method and system based on big data analysis, computer equipment and storage medium | |
| CN114139931A (en) | Enterprise data evaluation method and device, computer equipment and storage medium | |
| CN110489142A (en) | Appraisal procedure and device, storage medium, the terminal of equipment software upgrading | |
| CN114187125A (en) | Claims case distribution method, device, equipment and storage medium | |
| CN112966965A (en) | Import and export big data analysis and decision method, device, equipment and storage medium | |
| CN113962160A (en) | Internet card user loss prediction method and system based on user portrait | |
| CN115168509A (en) | Processing method and device of wind control data, storage medium and computer equipment | |
| CN114896955A (en) | Data report processing method and device, computer equipment and storage medium | |
| CN113850483A (en) | Enterprise credit risk rating system | |
| CN109308565B (en) | Crowd performance grade identification method and device, storage medium and computer equipment | |
| CN113487109A (en) | Group identification method and device, electronic equipment and storage medium | |
| CN111008078A (en) | Batch processing method, device and equipment of data and computer storage medium | |
| CN113742495B (en) | Rating feature weight determining method and device based on prediction model and electronic equipment | |
| CN113657488B (en) | User grading method, device, equipment and storage medium based on driving behaviors | |
| CN117194020B (en) | Cloud computing original big data processing method, system and storage medium | |
| CN114936851B (en) | IDC data cooperation method and system based on block chain | |
| CN114358659B (en) | Document verification information processing method and system | |
| CN113689301B (en) | Method, device, equipment and storage medium for constructing pay strategy | |
| CN111369352B (en) | Joint modeling method, apparatus, and medium | |
| CN114255125A (en) | Transaction risk judgment method and device, storage medium and electronic device |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40056719 Country of ref document: HK |