CN115170248A - Automobile leasing credit information analysis management method based on big data - Google Patents
Automobile leasing credit information analysis management method based on big data Download PDFInfo
- Publication number
- CN115170248A CN115170248A CN202210933986.2A CN202210933986A CN115170248A CN 115170248 A CN115170248 A CN 115170248A CN 202210933986 A CN202210933986 A CN 202210933986A CN 115170248 A CN115170248 A CN 115170248A
- Authority
- CN
- China
- Prior art keywords
- target user
- rental
- rental car
- historical
- coefficient
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 32
- 238000007726 management method Methods 0.000 title claims abstract description 23
- 238000001514 detection method Methods 0.000 claims abstract description 4
- 230000007547 defect Effects 0.000 claims description 82
- 230000006399 behavior Effects 0.000 claims description 76
- 238000004364 calculation method Methods 0.000 claims description 30
- SAZUGELZHZOXHB-UHFFFAOYSA-N acecarbromal Chemical compound CCC(Br)(CC)C(=O)NC(=O)NC(C)=O SAZUGELZHZOXHB-UHFFFAOYSA-N 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 6
- 238000012423 maintenance Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 238000003915 air pollution Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000003973 paint Substances 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0645—Rental transactions; Leasing transactions
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/174—Segmentation; Edge detection involving the use of two or more images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Finance (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a big data-based automobile leasing credit information analysis and management method, which comprises the following steps: the method comprises the steps of extracting historical rental car orders of a target user in a detection period from a car rental platform, extracting rental parameters corresponding to the historical rental car orders of the target user, analyzing the integrity coefficient of a rental car, analyzing a driving behavior comprehensive specification coefficient, a driving specification coefficient and a rental payment time reasonable coefficient corresponding to the target user, and analyzing a rental car credit coefficient corresponding to the user according to the parameters.
Description
Technical Field
The invention relates to the technical field of automobile leasing, in particular to an automobile leasing credit information analysis management method based on big data.
Background
With the rapid development of economy, the shared economy is developed more and more rapidly, and common shared economy projects are as follows: shared bicycle, shared treasured that charges, shared umbrella and shared car etc. in numerous shared economic projects, the shared car has huge development potential, the shared car helps alleviating traffic jam and road wear, reduce air pollution, just need the lease car when people's car that possess at present can't satisfy current demand, need pay certain deposit when the lease car, and user's credit has very big influence to the payment deposit of lease car, consequently, need carry out the analysis to user's lease car credit.
Most of the existing analysis on the rental car credit of the user is carried out according to whether the user pays the fee on time on the platform, the behavior of the user when the user rents the car, traffic violation conditions and the influence of car damage degree on the rental car credit of the user are ignored, the analysis dimensionality is single, further the analysis on the rental car credit of the user is inaccurate, on one hand, a reliable reference value cannot be provided for subsequent deposit assessment, the credit coefficient of the subsequent user is not matched with the deposit to be paid, on the other hand, the behavior of the user during the rental period cannot be well restrained, further the safety of the user in the rental car storage is reduced, and therefore the maintenance cost of the rental car platform on the rental car is increased.
Disclosure of Invention
In order to overcome the defects in the background art, the embodiment of the invention provides a car rental credit information analysis management method based on big data, which can effectively solve the problems in the background art.
The purpose of the invention can be realized by the following technical scheme:
a car rental credit information analysis and management method based on big data comprises the following steps:
step 1, extracting historical rental car orders of target users: extracting historical rental car orders of a target user in a detection period from the car rental platform, and numbering each historical rental car order as 1,2,. Multidot.i,. Multidot.n;
step 2, extracting lease parameters in historical lease automobile orders of target users: extracting lease parameters corresponding to each historical lease car order from the historical lease car orders of the target user;
step 3, analyzing the integrity of the rental car: analyzing the rental car integrity coefficient according to the rental parameters corresponding to the target user in each historical rental car order;
step 4, analyzing the driving behavior specification of the target user: analyzing a driving behavior comprehensive standard coefficient corresponding to a target user according to lease parameters corresponding to orders of the target user in each historical lease car;
and 5, analyzing the driving normative of the target user: analyzing a driving standard coefficient corresponding to a target user according to the leasing parameters of the target user corresponding to each historical leasing automobile order;
step 6, analyzing the rationality of the lease payment time of the target user: analyzing a lease payment time reasonable coefficient corresponding to the target user according to lease parameters corresponding to the target user in each historical lease car order;
step 7, analyzing the credit of the rented automobile of the target user: and analyzing the credit coefficient of the rental car corresponding to the target user according to the integrity coefficient of the rental car, the driving behavior comprehensive specification coefficient corresponding to the target user, the driving specification coefficient and the rental payment time reasonable coefficient.
Further, the rental parameters comprise rental car information and target user information.
Further, the rental car information comprises an external image and an internal image of the rental car, a driving operation behavior recording video and a rental car surface area, and the target user information comprises a violation record, a rental return time point and a rental fee payment time point of the target user during the rental car.
Further, the specific implementation manner of analyzing the rental car health factor in the step 3 includes the following steps:
step 31: extracting external images and internal images of the rental cars from rental car information in rental parameters in each historical rental car order of the target user, and comparing the external images and the internal images with the external images and the internal images of the rental cars before rental, so as to identify external defect parameters and internal defect parameters of the rental cars, wherein the external defect parameters comprise external defect types and external defect areas, and the internal defect parameters comprise internal defect types and internal defect areas;
step 32: extracting external defect types from external defect parameters of the rental car, and matching the external defect types with the proportion coefficients corresponding to various external defect types stored in the database so as to match the proportion coefficients corresponding to the external defect types of the rental car;
step 33: extracting internal defect types from internal defect parameters of the rental car, matching the internal defect types with the proportionality coefficients corresponding to various internal defect types stored in the database, and further matching the proportionality coefficients corresponding to the internal defect types of the rental car;
step 34: extracting the surface area of the rental car from the information of the rental car in the rental parameters in each historical rental car order of the target user;
step 35: analyzing the external sound coefficient of the rental car according to the area and the surface area of the external defect corresponding to the rental car in each historical rental car order of the target user and the proportion coefficient corresponding to the type of the external defect, wherein the calculation formula is as follows:
wherein
Representing the external sound factor, s, of the rental car i And s' respectively represent the corresponding external defect area and surface area of the rental car in the ith historical rental car order of the target user, and lambda i Representing the proportion coefficient of the external defect types corresponding to the rental cars in the ith historical rental car order;
and step 36: analyzing the internal sound coefficient of the rental car according to the internal defect area, the surface area and the proportion coefficient corresponding to the internal defect type of the rental car in each historical rental car order of the target user, wherein the calculation formula is as follows:
wherein
Representing the internal health factor, s, of the rental car i "and s' respectively represent the internal defect area and the surface area, lambda, of the rental car corresponding to the ith historical rental car order of the target user i "a scaling factor representing the internal defect type corresponding to the rental car in the ith historical rental car order;
step 37: analyzing the good coefficient of the rental car based on the external good coefficient and the internal good coefficient of the rental car, wherein the calculation formula is as follows:
wherein
Indicating rental car health factor.
Further, the specific implementation manner of analyzing the driving behavior comprehensive specification coefficient corresponding to the target user in step 4 includes the following steps:
step 41: extracting driving operation behavior recording videos from rental car information in rental parameters in each historical rental car order of a target user;
step 42: dividing the driving operation behavior recording video into a plurality of behavior pictures according to a preset frame number, and numbering the behavior pictures as 1,2,. Eta., m,. Eta., l respectively;
step 43: acquiring the skin bare parts of the target user in each behavior picture, counting the number of the skin bare parts, further matching the skin bare parts of the target user in each behavior picture with the skin allowable bare parts stored in the database one by one, and counting the number of the skin bare parts which are successfully matched according to the number;
step 44: analyzing the corresponding dressing risk coefficient of the target user in each historical rental car order according to the number of the skin exposed parts of the target user successfully matched and the number of the skin exposed parts in each action picture, wherein the calculation formula is as follows:
wherein eta i Representing the corresponding dressing risk coefficient, alpha, of the target user in the ith historical rental car order im The number alpha representing the successful matching of the skin bare parts of the target user in the mth behavior picture in the ith historical rental car order im ' indicating the number of skin bare parts of a target user in the mth behavior picture in the ith historical rental car order;
step 45: identifying hand action characteristics corresponding to each historical rental car order of a target user based on each action picture, comparing the hand action characteristics with hand characteristics corresponding to throwing behaviors stored in a database, further judging whether the target user has the throwing behavior in the action picture, and if the throwing behavior exists, extracting throwing object parameters from the action picture, wherein the throwing object parameters comprise throwing object types and throwing object volumes;
step 46: extracting a throwing object type from throwing object parameters corresponding to each historical rental car order of the target user, matching the throwing object type with weight factors corresponding to unit volumes of various throwing object types stored in a database, and further matching the weight factors corresponding to the unit volumes of the throwing object types of each historical rental car order of the target user;
step 47: analyzing the throwing danger coefficient corresponding to each historical rental car order by the target user according to the weight factor corresponding to the unit volume of the thrown object and the thrown object type of each historical rental car order by the target user, wherein the calculation formula is as follows: mu.s i ＝v i *γ i In which μ i Showing the throwing risk coefficient, v, corresponding to the ith historical rental car order of the target user i Volume of toss, γ, representing target user's order at ith historical rental car i Representing a weight factor corresponding to the unit volume of the throwing object type of the ith historical rental car order of the target user;
and 48: analyzing a driving behavior specification coefficient corresponding to each historical rental car order of the target user based on the dressing risk coefficient and the throw object risk coefficient corresponding to each historical rental car order of the target user, wherein the calculation formula is as follows:
wherein κ i ' represents a driving behavior specification coefficient corresponding to the ith historical rental car order of the target user;
step 49: analyzing a driving behavior comprehensive specification coefficient corresponding to the target user according to the driving behavior specification coefficient and the standard driving behavior specification coefficient corresponding to each historical rental car order of the target user, wherein the calculation formula is
Wherein, k represents the driving behavior comprehensive specification coefficient corresponding to the target user, and k' represents the standard driving behavior specification coefficient.
Further, the specific implementation manner of analyzing the driving norm coefficient corresponding to the target user in step 5 includes the following steps:
step 51: extracting violation records of the target user in the automobile rental period from target user information in rental parameters in each historical automobile rental order of the target user, wherein the violation records comprise violation types and violation times;
step 52: extracting violation types from violation records of a target user during automobile rental, counting the types of the violation types corresponding to the target user, and numbering the types as 1,2, a.
Step 53: matching the type of the violation type corresponding to the target user with the violation value corresponding to the single violation of each violation type stored in the database, and further matching the violation value corresponding to the single violation of each violation type of the target user;
step 54: analyzing a driving standard coefficient corresponding to the target user according to violation values corresponding to single violations of all violation type types of the target user and the occurrence times of all violation type types, wherein the calculation formula is as follows:
where phi denotes a driving specification coefficient corresponding to the target user, sigma j Violation values corresponding to single violations of the jth violation type category representing the target user,
Indicating the number of occurrences of the jth violation type category for the target user.
Further, the specific implementation manner of analyzing the reasonable coefficient of the rental payment time corresponding to the target user in the step 6 includes the following steps:
step 61: extracting a lease returning time point and a lease fee payment time point from target user information in lease parameters in each historical lease car order of a target user;
step 62: analyzing a reasonable coefficient of lease payment time corresponding to a target user according to lease return time points, lease fee payment time points and allowable fee payment time lengths of various historical lease car orders of the target user, wherein the calculation formula is as follows:
where θ represents the targetReasonable coefficient of lease payment time, t, corresponding to the user i ′、t i Respectively representing the lease return time point and the lease fee payment time point corresponding to the ith historical lease car order of the target user, wherein t' represents the time length of allowing the payment fee.
Further, the specific calculation formula for analyzing the credit coefficient of the rental car corresponding to the target user in the step 7 is as follows:
where ψ represents the rental car credit factor for the target user.
Compared with the prior art, the embodiment of the invention has at least the following advantages or beneficial effects:
when the method analyzes the rental car credit of the user, the method analyzes whether the user pays the fee on time on the platform, analyzes the behavior, traffic violation and rental car damage degree of the user when renting the car, solves the problem of single analysis dimension, further solves the problem of inaccurate analysis of the rental car credit of the user, can provide a reliable reference value for subsequent deposit evaluation on one hand, improves the matching degree of the credit coefficient of the subsequent user and the deposit to be paid on the other hand, can well restrict the behavior of the user during the rental period on the other hand, further improves the safety of the user in keeping the rental car during the rental period, and further reduces the maintenance cost of the rental car platform on the rental car.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
Fig. 1 is a schematic diagram of a car rental credit information analysis management method based on big data according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Referring to fig. 1, the invention provides a big data-based analysis and management method for automobile rental credit information, which comprises the following steps:
step 1, extracting historical rental car orders of target users: historical rental car orders of the target user in the detection period are extracted from the car rental platform, and the historical rental car orders are respectively numbered as 1, 2.
Step 2, extracting leasing parameters in the historical lease car order of the target user: and extracting the leasing parameters corresponding to the historical leasing automobile orders from the historical leasing automobile orders of the target user.
In a specific embodiment, the rental parameters include rental car information and target user information.
In a specific embodiment, the rental car information includes rental car exterior and interior images, driving operation behavior recording video, and rental car surface area, and the target user information includes violation records, rental return time points, and rental fee payment time points of the target user during the rental car.
Step 3, analyzing the integrity of the rental car: and analyzing the good coefficient of the rental car according to the rental parameters corresponding to the target user in each historical rental car order.
In a specific embodiment, the specific implementation manner of analyzing the rental car health factor in step 3 includes the following steps:
step 31: extracting external images and internal images of the rental cars from rental car information in rental parameters in each historical rental car order of the target user, and comparing the external images and the internal images with the external images and the internal images of the rental cars before rental respectively, thereby identifying external defect parameters and internal defect parameters of the rental cars, wherein the external defect parameters comprise external defect types and external defect areas, and the internal defect parameters comprise internal defect types and internal defect areas.
Note that the external defect types include scratches, dirt, paint drops, and the like, and the internal defect types include scratches, peeling, cracking, and the like.
It should be noted that the invention analyzes the integrity factor of the rental car from both the external and internal defects of the rental car, and the analysis is relatively comprehensive.
Step 32: and extracting the external defect type from the external defect parameters of the rental car, matching the external defect type with the proportion coefficient corresponding to each external defect type stored in the database, and further matching the proportion coefficient corresponding to the external defect type of the rental car.
Step 33: and extracting the internal defect type from the internal defect parameters of the rental car, matching the internal defect type with the proportionality coefficient corresponding to each internal defect type stored in the database, and further matching the proportionality coefficient corresponding to the internal defect type of the rental car.
Step 34: and extracting the surface area of the rental car from the rental car information in the rental parameters in each historical rental car order of the target user.
Step 35: analyzing the external sound coefficient of the rental car according to the area and the surface area of the external defect corresponding to the rental car in each historical rental car order of the target user and the proportion coefficient corresponding to the type of the external defect, wherein the calculation formula is as follows:
wherein
Representing the external sound factor, s, of the rental car i And s' respectively represent the external defect area and the surface area, lambda, corresponding to the rental car in the ith historical rental car order of the target user i And the proportion coefficient represents the external defect type corresponding to the rental car in the ith historical rental car order.
Step 36:analyzing the internal sound coefficient of the rental car according to the internal defect area, the surface area and the proportion coefficient corresponding to the internal defect type of the rental car in each historical rental car order of the target user, wherein the calculation formula is as follows:
wherein
Indicating the internal health factor, s, of the rental car i "and s' respectively represent the internal defect area and the surface area, lambda, of the rental car corresponding to the ith historical rental car order of the target user i "represents the scaling factor for the internal defect type corresponding to the rental car in the ith historical rental car order.
Step 37: analyzing the good coefficient of the rental car based on the external good coefficient and the internal good coefficient of the rental car, wherein the calculation formula is as follows:
wherein
Indicating rental car health factor.
If the rental car health factor is not qualified, it indicates that the target user does not have a good idea of the rental car during the rental car, and further affects the appearance and the service time of the rental car.
Step 4, analyzing the driving behavior specification of the target user: and analyzing the driving behavior comprehensive specification coefficient corresponding to the target user according to the leasing parameters corresponding to the historical leasing automobile orders of the target user.
In a specific embodiment, the specific implementation manner for analyzing the driving behavior comprehensive specification coefficient corresponding to the target user in step 4 includes the following steps:
step 41: and extracting a driving operation behavior recording video from the rental car information in the rental parameters in each historical rental car order of the target user.
Step 42: dividing the driving operation behavior recording video into a plurality of behavior pictures according to a preset frame number, and numbering each behavior picture as 1, 2.
Step 43: the method comprises the steps of obtaining the skin bare parts of a target user in each action picture, counting the number of the skin bare parts, further matching the skin bare parts of the target user in each action picture with the skin allowed bare parts stored in a database one by one, and counting the number of the skin bare parts successfully matched according to the number.
And step 44: analyzing the corresponding dressing risk coefficient of the target user in each historical rental car order according to the number of the skin exposed parts of the target user successfully matched and the number of the skin exposed parts in each action picture, wherein the calculation formula is as follows:
wherein eta i Representing the corresponding dressing risk coefficient, alpha, of the target user in the ith historical rental car order im The number alpha representing the successful matching of the skin bare parts of the target user in the mth behavior picture in the ith historical rental car order im ' indicates the number of the skin bare parts of the target user in the mth action picture in the ith historical rental car order.
Step 45: identifying hand action characteristics corresponding to each historical rental car order of the target user based on each action picture, comparing the hand action characteristics with hand characteristics corresponding to the throwing behavior stored in the database, further judging whether the target user has the throwing behavior in the action picture, and if the throwing behavior exists, extracting throwing object parameters from the action picture, wherein the throwing object parameters comprise throwing object types and throwing object volumes.
Step 46: and extracting the type of the throwing object from the throwing object parameters corresponding to each historical rental car order of the target user, matching the type of the throwing object with the weight factors corresponding to the unit volumes of various types of the throwing objects stored in the database, and further matching the weight factors corresponding to the unit volumes of the type of the throwing object of each historical rental car order of the target user.
Step 47: analyzing the throwing danger coefficient corresponding to each historical rental car order of the target user according to the weight factor corresponding to the unit volume of the thrown object volume and the thrown object type of each historical rental car order of the target user, wherein the calculation formula is as follows: mu.s i ＝v i *γ i In which μ i Showing the throwing risk coefficient, v, corresponding to the ith historical rental car order of the target user i Volume of throw, gamma, representing the target user's order for the ith historical rental car i And the weight factor represents the corresponding unit volume of the throwing object type of the ith historical rental car order of the target user.
And 48: analyzing a driving behavior specification coefficient corresponding to each historical rental car order by the target user based on the dressing risk coefficient and the throwing object risk coefficient corresponding to each historical rental car order by the target user, wherein the calculation formula is as follows:
wherein κ i ' represents a driving behavior specification coefficient corresponding to the ith historical rental car order of the target user.
Step 49: analyzing a driving behavior comprehensive specification coefficient corresponding to the target user according to the driving behavior specification coefficient and the standard driving behavior specification coefficient corresponding to each historical rental car order of the target user, wherein the calculation formula is
And k represents a driving behavior comprehensive standard coefficient corresponding to the target user, and k' represents a standard driving behavior standard coefficient.
It should be noted that the purpose of analyzing the driving behavior of the target user is to: whether the target user has the non-civilized behaviors such as exposing the upper body, taking off shoes and throwing articles outside the window during the driving of the rental car is detected, and the driving behavior normalization of the target user is further ensured, so that the behavior constraint force on a driver can be improved.
And 5, analyzing the driving normative of the target user: and analyzing the driving standard coefficient corresponding to the target user according to the leasing parameters corresponding to the historical leasing automobile orders of the target user.
In a specific embodiment, the specific implementation manner for analyzing the driving norm coefficient corresponding to the target user in step 5 includes the following steps:
step 51: and extracting violation records of the target user during the automobile rental period from target user information in the rental parameters of each historical rental automobile order of the target user, wherein the violation records comprise violation types and violation times.
Step 52: and extracting violation types from violation records of the target user during automobile rental, counting the types of the violation types corresponding to the target user, and numbering the types as 1, 2.
Step 53: and matching the type of the violation type corresponding to the target user with the violation value corresponding to the single violation of each violation type stored in the database, and further matching the violation value corresponding to the single violation type of the target user.
Step 54: analyzing a driving standard coefficient corresponding to the target user according to violation values corresponding to the violation types of the target user in a single violation mode and the occurrence times of the violation types, wherein the calculation formula is as follows:
where phi denotes a driving specification coefficient corresponding to the target user, sigma j Violation values corresponding to single violation of the jth violation type category representing the target user,
Indicating the number of occurrences of the jth violation type category for the target user.
If a traffic violation occurs during the driving of the rental car by the target user, not only is the safety of the target user threatened, but also the rental platform needs to bear certain responsibility, and meanwhile, the rental car may also become an accident car, which affects the further use of the rental car and increases the cost of the rental platform for releasing the rental car.
Step 6, analyzing the rationality of the lease payment time of the target user: and analyzing the lease payment time reasonable coefficient corresponding to the target user according to the lease parameters corresponding to the target user in each historical lease automobile order.
In a specific embodiment, the specific implementation manner of analyzing the reasonable coefficient of the rental payment time corresponding to the target user in step 6 includes the following steps:
step 61: and extracting the lease return time point and the lease fee payment time point from the target user information in the lease parameters in each historical lease automobile order of the target user.
Step 62: analyzing a lease payment time reasonable coefficient corresponding to the target user according to the lease return time point, the lease fee payment time point and the allowable payment time length of each historical lease automobile order of the target user, wherein the calculation formula is as follows:
wherein theta represents a reasonable coefficient of lease payment time corresponding to the target user, t i ′、t i Respectively representing the lease return time point and the lease fee payment time point corresponding to the ith historical lease car order of the target user, wherein t' represents the time length of allowing the payment fee.
It should be noted that the sign of θ may be positive or negative, when the sign of θ is positive, it indicates that the rental payment time corresponding to the target user is reasonable, and the larger the value of θ is, the more reasonable the rental payment time corresponding to the target user is, when the sign of θ is negative, it indicates that the rental payment time corresponding to the target user is unreasonable, and the smaller the value of θ is, the more unreasonable the rental payment time corresponding to the target user is.
If the lease payment time of the target user is long, the target user is not in high time keeping degree, and the credibility of the target user is reflected to be low from the side face, so that the reasonable coefficient of the lease payment time corresponding to the target user needs to be analyzed.
Step 7, analyzing the credit of the rented automobile of the target user: and analyzing the credit coefficient of the rental car corresponding to the target user according to the integrity coefficient of the rental car, the driving behavior comprehensive specification coefficient corresponding to the target user, the driving specification coefficient and the rental payment time reasonable coefficient.
In a specific embodiment, the specific calculation formula for analyzing the rental car credit coefficient corresponding to the target user in step 7 is as follows:
where ψ represents the rental car credit factor for the target user.
When the method analyzes the rental car credit of the user, the method analyzes whether the user pays the fee on time on the platform, analyzes the behavior, traffic violation and rental car damage degree of the user when renting the car, solves the problem of single analysis dimension, further solves the problem of inaccurate analysis of the rental car credit of the user, can provide a reliable reference value for subsequent deposit evaluation on one hand, improves the matching degree of the credit coefficient of the subsequent user and the deposit to be paid on the other hand, can well restrict the behavior of the user during the rental period on the other hand, further improves the safety of the user in keeping the rental car during the rental period, and further reduces the maintenance cost of the rental car platform on the rental car.
The foregoing is merely exemplary and illustrative of the present invention and various modifications, additions and substitutions may be made by those skilled in the art to the specific embodiments described without departing from the scope of the invention as defined in the following claims.
Claims (8)
1. A car rental credit information analysis and management method based on big data is characterized by comprising the following steps:
step 1, extracting historical rental car orders of target users: extracting historical rental car orders of a target user in a detection period from a car rental platform, and numbering the historical rental car orders as 1,2, 1, i, n;
step 2, extracting leasing parameters in the historical lease car order of the target user: extracting leasing parameters corresponding to each historical leasing automobile order from the historical leasing automobile orders of the target user;
step 3, analyzing the integrity of the rental car: analyzing the good coefficients of the rental cars according to the rental parameters corresponding to the target user in each historical rental car order;
step 4, analyzing the driving behavior specification of the target user: analyzing a driving behavior comprehensive standard coefficient corresponding to a target user according to lease parameters corresponding to orders of the target user in each historical lease car;
and 5, analyzing the driving normative of the target user: analyzing a driving standard coefficient corresponding to a target user according to the leasing parameters of the target user corresponding to each historical leasing automobile order;
step 6, analyzing the rationality of the lease payment time of the target user: analyzing a lease payment time reasonable coefficient corresponding to the target user according to lease parameters corresponding to each historical lease automobile order of the target user;
step 7, analyzing the credit of the rented automobile of the target user: and analyzing the credit coefficient of the rental car corresponding to the target user according to the integrity coefficient of the rental car, the driving behavior comprehensive specification coefficient corresponding to the target user, the driving specification coefficient and the rental payment time reasonable coefficient.
2. The big-data-based analysis and management method for the car rental credit information according to claim 1, wherein the big-data-based analysis and management method comprises the following steps: the rental parameters comprise rental car information and target user information.
3. The big-data-based analysis and management method for the car rental credit information according to claim 2, wherein the big-data-based analysis and management method comprises the following steps: the rental car information comprises an external image and an internal image of the rental car, a driving operation behavior recording video and the surface area of the rental car, and the target user information comprises violation records, rental return time points and rental fee payment time points of target users during the rental car.
4. The big-data-based analysis and management method for the car rental credit information according to claim 3, wherein the big-data-based analysis and management method comprises the following steps: the specific execution mode for analyzing the good coefficient of the rental car in the step 3 comprises the following steps:
step 31: extracting external images and internal images of the rental cars from rental car information in rental parameters in each historical rental car order of a target user, and comparing the external images and the internal images with the external images and the internal images of the rental cars before rental, so as to identify external defect parameters and internal defect parameters of the rental cars, wherein the external defect parameters comprise external defect types and external defect areas, and the internal defect parameters comprise internal defect types and internal defect areas;
step 32: extracting external defect types from external defect parameters of the rental car, and matching the external defect types with the proportion coefficients corresponding to various external defect types stored in the database so as to match the proportion coefficients corresponding to the external defect types of the rental car;
step 33: extracting internal defect types from the internal defect parameters of the rental car, matching the internal defect types with the proportionality coefficients corresponding to various internal defect types stored in the database, and further matching the proportionality coefficients corresponding to the internal defect types of the rental car;
step 34: extracting the surface area of the rental car from the information of the rental car in the rental parameters in each historical rental car order of the target user;
step 35: analyzing the external sound coefficient of the rental car according to the area and the surface area of the external defect corresponding to the rental car in each historical rental car order of the target user and the proportion coefficient corresponding to the external defect type, wherein the calculation formula is as follows:
wherein
Representing the external sound factor, s, of the rental car i And s' respectively represent the corresponding external defect area and surface area of the rental car in the ith historical rental car order of the target user, and lambda i Representing the proportion coefficient of the external defect type corresponding to the rental car in the ith historical rental car order;
step 36: analyzing the internal sound coefficient of the rental car according to the internal defect area, the surface area and the proportion coefficient corresponding to the internal defect type of the rental car in each historical rental car order of the target user, wherein the calculation formula is as follows:
wherein
Indicating the internal health factor, s, of the rental car i "and s' respectively represent the internal defect area and the surface area, lambda, of the rental car corresponding to the ith historical rental car order of the target user i "a scaling factor indicating the type of internal defect corresponding to the rental car in the ith historical rental car order;
step 37: analyzing the good coefficient of the rental car based on the external good coefficient and the internal good coefficient of the rental car, wherein the calculation formula is as follows:
wherein
Indicating rental car health factor.
5. The big-data-based analysis and management method for the car rental credit information according to claim 4, wherein the big-data-based analysis and management method comprises the following steps: the specific execution mode for analyzing the driving behavior comprehensive specification coefficient corresponding to the target user in the step 4 comprises the following steps:
step 41: extracting driving operation behavior recording videos from rental car information in rental parameters in each historical rental car order of a target user;
step 42: dividing the driving operation behavior recording video into a plurality of behavior pictures according to a preset frame number, and numbering the behavior pictures as 1,2,. Eta., m,. Eta., l respectively;
step 43: acquiring the skin bare parts of the target user in each behavior picture, counting the number of the skin bare parts, further matching the skin bare parts of the target user in each behavior picture with the skin allowable bare parts stored in the database one by one, and counting the number of the skin bare parts which are successfully matched according to the number;
and step 44: analyzing the corresponding dressing risk coefficient of the target user in each historical rental car order according to the number of the skin exposed parts of the target user successfully matched and the number of the skin exposed parts in each action picture, wherein the calculation formula is as follows:
wherein eta i Represents the corresponding dressing risk coefficient, alpha, of the target user in the ith historical rental car order im The number alpha representing the successful matching of the skin bare parts of the target user in the mth behavior picture in the ith historical rental car order im ' indicating the number of skin bare parts of a target user in the mth behavior picture in the ith historical rental car order;
step 45: identifying hand action characteristics corresponding to each historical rental car order of a target user based on each action picture, comparing the hand action characteristics with hand characteristics corresponding to throwing behaviors stored in a database, further judging whether the target user has the throwing behavior in the action picture, and if the throwing behavior exists, extracting throwing object parameters from the action picture, wherein the throwing object parameters comprise throwing object types and throwing object volumes;
step 46: extracting a tossing object type from corresponding tossing object parameters in each historical rental car order of the target user, matching the tossing object type with weight factors corresponding to unit volumes of various tossing object types stored in a database, and further matching the weight factors corresponding to the unit volumes of the tossing object types of each historical rental car order of the target user;
step 47: analyzing the throwing danger coefficient corresponding to each historical rental car order of the target user according to the weight factor corresponding to the unit volume of the thrown object volume and the thrown object type of each historical rental car order of the target user, wherein the calculation formula is as follows: mu.s i ＝v i *γ i In which μ i Showing the throwing risk coefficient, v, corresponding to the ith historical rental car order of the target user i Volume of throw, gamma, representing the target user's order for the ith historical rental car i Representing a weight factor corresponding to the unit volume of the throwing object type of the ith historical rental car order of the target user;
and step 48: analyzing a driving behavior specification coefficient corresponding to each historical rental car order of the target user based on the dressing risk coefficient and the throw object risk coefficient corresponding to each historical rental car order of the target user, wherein the calculation formula is as follows:
wherein κ i ' represents a driving behavior specification coefficient corresponding to the ith historical rental car order of the target user;
step 49: analyzing a driving behavior comprehensive specification coefficient corresponding to the target user according to the driving behavior specification coefficient and the standard driving behavior specification coefficient corresponding to each historical rental car order of the target user, wherein the calculation formula is
Wherein, k represents the driving behavior comprehensive specification coefficient corresponding to the target user, and k' represents the standard driving behavior specification coefficient.
6. The big-data-based analysis and management method for the car rental credit information according to claim 5, wherein the big-data-based analysis and management method comprises the following steps: the specific implementation manner for analyzing the driving norm coefficient corresponding to the target user in the step 5 includes the following steps:
step 51: extracting violation records of the target user in the automobile rental period from target user information in rental parameters in each historical automobile rental order of the target user, wherein the violation records comprise violation types and violation times;
step 52: extracting violation types from violation records of a target user during automobile rental, counting the types of the violation types corresponding to the target user, and numbering the types as 1,2, a.
Step 53: matching the type of the violation type corresponding to the target user with the violation value corresponding to the single violation of each violation type stored in the database, and further matching the violation value corresponding to the single violation of each violation type of the target user;
step 54: analyzing a driving standard coefficient corresponding to the target user according to violation values corresponding to the violation types of the target user in a single violation mode and the occurrence times of the violation types, wherein the calculation formula is as follows:
where phi denotes a driving specification coefficient corresponding to the target user, sigma j Violation values corresponding to single violation of the jth violation type category representing the target user,
Indicating the number of occurrences of the jth violation type category for the target user.
7. The big-data-based analysis and management method for the car rental credit information according to claim 6, wherein the big-data-based analysis and management method comprises the following steps: the specific execution mode for analyzing the reasonable coefficient of the lease payment time corresponding to the target user in the step 6 comprises the following steps:
step 61: extracting lease return time points and lease fee payment time points from target user information in lease parameters in each historical lease automobile order of a target user;
step 62: analyzing a lease payment time reasonable coefficient corresponding to the target user according to the lease return time point, the lease fee payment time point and the allowable payment time length of each historical lease automobile order of the target user, wherein the calculation formula is as follows:
wherein theta represents a reasonable coefficient of lease payment time corresponding to the target user, t i ′、t i Respectively representing the lease return time point and the lease fee payment time point corresponding to the ith historical lease car order of the target user, wherein t' represents the time length of allowing the payment fee.
8. The big-data-based analysis and management method for the car rental credit information according to claim 7, wherein the big-data-based analysis and management method comprises the following steps: the specific calculation formula for analyzing the rental car credit coefficient corresponding to the target user in the step 7 is as follows:
where ψ represents the rental car credit factor for the target user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210933986.2A CN115170248B (en) | 2022-08-04 | 2022-08-04 | Big data-based analysis and management method for car rental credit information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210933986.2A CN115170248B (en) | 2022-08-04 | 2022-08-04 | Big data-based analysis and management method for car rental credit information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115170248A true CN115170248A (en) | 2022-10-11 |
| CN115170248B CN115170248B (en) | 2024-05-24 |
Family
ID=83479055
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210933986.2A Active CN115170248B (en) | 2022-08-04 | 2022-08-04 | Big data-based analysis and management method for car rental credit information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115170248B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116596643A (en) * | 2023-07-14 | 2023-08-15 | 深圳市古石科技有限公司 | Intelligent management system for charging of shared charger |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20020078978A (en) * | 2001-04-12 | 2002-10-19 | 이원구 | An Integrated Operating System for Rent Car Service Having Function of Searching Credit Information of Client Using Rent Car Service |
| CN106600612A (en) * | 2016-12-27 | 2017-04-26 | 重庆大学 | Damage identification and detection method for electric automobile before and after renting |
| CN107644369A (en) * | 2017-10-19 | 2018-01-30 | 深圳市国电科技通信有限公司 | A kind of credit estimation method and system of automobile leasing user |
| CN112927045A (en) * | 2021-03-03 | 2021-06-08 | 广州力挚网络科技有限公司 | Car rental credit data processing method, device and equipment |
| CN112967497A (en) * | 2021-02-01 | 2021-06-15 | 吉林大学 | Shared automobile supervision system and supervision method |
| CN114511178A (en) * | 2021-12-27 | 2022-05-17 | 环球车享汽车租赁有限公司 | Monitoring method and system for safe driving behaviors of shared trip users |
-
2022
- 2022-08-04 CN CN202210933986.2A patent/CN115170248B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20020078978A (en) * | 2001-04-12 | 2002-10-19 | 이원구 | An Integrated Operating System for Rent Car Service Having Function of Searching Credit Information of Client Using Rent Car Service |
| CN106600612A (en) * | 2016-12-27 | 2017-04-26 | 重庆大学 | Damage identification and detection method for electric automobile before and after renting |
| CN107644369A (en) * | 2017-10-19 | 2018-01-30 | 深圳市国电科技通信有限公司 | A kind of credit estimation method and system of automobile leasing user |
| CN112967497A (en) * | 2021-02-01 | 2021-06-15 | 吉林大学 | Shared automobile supervision system and supervision method |
| CN112927045A (en) * | 2021-03-03 | 2021-06-08 | 广州力挚网络科技有限公司 | Car rental credit data processing method, device and equipment |
| CN114511178A (en) * | 2021-12-27 | 2022-05-17 | 环球车享汽车租赁有限公司 | Monitoring method and system for safe driving behaviors of shared trip users |
Non-Patent Citations (1)
| Title |
|---|
| 曾娟;吴兴华;张洪昌;: "基于因子分析与K-means聚类耦合的分时保费定价方法研究", 武汉理工大学学报(信息与管理工程版), no. 02, 15 April 2018 (2018-04-15) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116596643A (en) * | 2023-07-14 | 2023-08-15 | 深圳市古石科技有限公司 | Intelligent management system for charging of shared charger |
| CN116596643B (en) * | 2023-07-14 | 2023-10-20 | 深圳市古石科技有限公司 | Intelligent management system for charging of shared charger |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115170248B (en) | 2024-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210312567A1 (en) | Automobile Monitoring Systems and Methods for Loss Reserving and Financial Reporting | |
| US8407139B1 (en) | Credit risk evaluation with responsibility factors | |
| US20090132294A1 (en) | Method for ranking driver's relative risk based on reported driving incidents | |
| CN109887283B (en) | Road congestion prediction method, system and device based on checkpoint data | |
| CN106056839A (en) | Security monitoring system and method for internet-based car hailing service | |
| CN108305409B (en) | Follow-up payment method and system for in-road parking arrearage | |
| CN115170248A (en) | Automobile leasing credit information analysis management method based on big data | |
| CN115035491A (en) | Driving behavior road condition early warning method based on federal learning | |
| CN112967497A (en) | Shared automobile supervision system and supervision method | |
| CN116645646A (en) | Method and system for detecting and early warning parking abnormality | |
| CN111695767A (en) | Highway network traffic efficiency evaluation method, electronic device and storage medium | |
| CN114201530B (en) | Early screening and preventive supervision method for suspected abnormal operation passenger car | |
| CN116542466A (en) | Asset full period management system based on data analysis | |
| CN114387816B (en) | Mall traffic guiding system and method based on consumer behavior prediction analysis | |
| CN115630572A (en) | Vehicle maintenance pricing method, equipment and storage medium | |
| CN109849926A (en) | A kind of method and system for distinguishing taxi and whether giving other people drive | |
| CN114331181A (en) | Vehicle driving behavior risk analysis method based on big data | |
| CN117373259B (en) | Expressway vehicle fee evasion behavior identification method, device, equipment and storage medium | |
| CN116129541B (en) | Fee evasion checking method, device and equipment based on generalized additive model | |
| JP2002133043A (en) | System and method for monitoring road | |
| TWM573041U (en) | Decentralized vehicle risk assessment system | |
| CN116630903B (en) | Method and system for detecting behavior fee evasion of highway counterfeit bus | |
| CN2816938Y (en) | Dynamic managing system for charging toll to motor vehicle on road | |
| CN116978136B (en) | ETC-based intelligent charging management system for urban road side parking | |
| US10346786B1 (en) | Method for applying expert usage based data |
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 |