CN113329021A - Automobile depreciation model parameter privacy protection system and method based on industrial Internet - Google Patents

Automobile depreciation model parameter privacy protection system and method based on industrial Internet Download PDF

Info

Publication number
CN113329021A
CN113329021A CN202110597639.2A CN202110597639A CN113329021A CN 113329021 A CN113329021 A CN 113329021A CN 202110597639 A CN202110597639 A CN 202110597639A CN 113329021 A CN113329021 A CN 113329021A
Authority
CN
China
Prior art keywords
automobile
owner
depreciation
cloud
store
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
Application number
CN202110597639.2A
Other languages
Chinese (zh)
Other versions
CN113329021B (en
Inventor
张明武
周冰若兰
翟亦文
张语荻
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hubei University of Technology
Original Assignee
Hubei University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hubei University of Technology filed Critical Hubei University of Technology
Priority to CN202110597639.2A priority Critical patent/CN113329021B/en
Publication of CN113329021A publication Critical patent/CN113329021A/en
Application granted granted Critical
Publication of CN113329021B publication Critical patent/CN113329021B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/04—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks
    • H04L63/0428—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the data content is protected, e.g. by encrypting or encapsulating the payload
    • 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
    • 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
    • G06Q10/067—Enterprise or organisation modelling
    • 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
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0283—Price estimation or determination
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Educational Administration (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Operations Research (AREA)
  • Signal Processing (AREA)
  • Finance (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Computer Security & Cryptography (AREA)
  • Computing Systems (AREA)
  • Accounting & Taxation (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Storage Device Security (AREA)

Abstract

The invention discloses an automobile depreciation model parameter privacy protection system and method based on an industrial internet, wherein M automobile owners, automobile clouds and 4S stores are arranged in the system; firstly, generating and distributing a secret key and system parameters; then, the vehicle acquires vehicle condition data and depreciation evaluation levels of all parts of the vehicle in real time by using a sensing and monitoring technology of the industrial Internet of things and stores the data and depreciation evaluation levels into a local place for a vehicle owner to process; the automobile owner encrypts the automobile condition data and sends the automobile condition data to the automobile cloud; performing depreciation model parameter fitting on the automobile cloud and the 4S store, and calculating the received ciphertext to obtain privacy protection depreciation model parameters
Figure DDA0003091766170000012
And returning the result to the car owner; finally, the automobile owner obtains depreciation model parameters under the assistance of a 4S store
Figure DDA0003091766170000011
Due to the homomorphism of the algorithm, the automobile owner can not acquire the automobile condition data of other automobile owners after decryption, so the method has high privacy protection safety.

Description

Automobile depreciation model parameter privacy protection system and method based on industrial Internet
Technical Field
The invention belongs to the technical field of linear regression models and the technical field of privacy protection regression evaluation of automobile depreciation model parameters of industrial internet; an industrial internet-based regression evaluation system-level method for privacy protection of automobile depreciation model parameters relates to a linear regression model providing interactive services for automobile owners and automobile clouds; in particular to a regression evaluation system and method for privacy protection of automobile depreciation model parameters based on industrial internet, which is designed based on the requirement of the regression evaluation of automobile conditions of the industrial internet on the privacy protection of the automobile.
Background
With the rapid development of industrial internet technology, the automobile inventory in China is gradually increased. The market for used cars is an indispensable part of the automobile market, and the scale of the market is continuously expanding. Vehicle depreciation assessment is an indispensable step in the used-vehicle market and has wide application in the fields of used-vehicle buying and selling and the like. The existing vehicle depreciation evaluation method is usually carried out by methods such as test driving and the like, is greatly influenced by personal subjectivity, and the evaluation result is different from person to person and lacks of a uniform standard. By utilizing massive vehicle data in the industrial internet, a linear regression curve of the vehicle condition of each part of the automobile on the influence of vehicle depreciation can be fitted through a regression model, and the obtained depreciation model parameters can be used for comprehensively judging the degree of goodness and badness of the vehicle condition and serve as important references in a vehicle depreciation evaluation model. But in the linear regression fitting process, the automobile condition data are leaked. Therefore, how to protect the car condition privacy of the car owner while providing the car owner with the vehicle depreciation evaluation service by using the industrial big data is an important issue.
Disclosure of Invention
The invention provides an automobile depreciation model parameter privacy protection evaluation system and method based on an industrial internet, aiming at realizing the privacy protection evaluation of automobile depreciation model parameters under the condition that the automobile condition privacy of an automobile owner is not disclosed.
The technical scheme adopted by the system of the invention is as follows: an automobile depreciation model parameter privacy protection system based on industrial Internet comprises M automobile owners uiCar cloud and 4S store, i ═ 1, …, M; the car owner uiThe vehicle condition data is the user who owns the vehicle condition data; the automobile cloud is a cloud server capable of providing secure storage and computing functions; the 4S store is a physical store which performs system initialization and provides assistance calculation;
the 4S shop is provided with a system initialization module for generating and distributing a secret key and system parameters;
the car owner uiThe system is provided with an automobile Internet of things acquisition and evaluation module, an automobile data encryption module and an automobile owner decryption module; the automobile internet of things acquisition and evaluation module is used for acquiring automobile condition data and depreciation evaluation levels of all parts of an automobile in real time by using the sensing and monitoring technology of the industrial internet of things and storing the data and depreciation evaluation levels into a local place for an automobile owner to process; the automobile data encryption module is used for encrypting automobile condition data by an automobile owner and sending the automobile condition data to the automobile cloud; the automobile owner decryption module is used for obtaining depreciation model parameters under the assistance of a 4S store
Figure BDA0003091766150000021
The automobile cloud is provided with a depreciation model parameter training module and a termination judging module; the depreciation model parameter training module is used for performing depreciation model parameter fitting on the automobile cloud, calculating the received ciphertext and obtaining privacy protection depreciation model parameters
Figure BDA0003091766150000022
And returning the result to the car owner; and the termination judging module is used for judging whether the automobile cloud finishes training.
The method adopts the technical scheme that: an automobile depreciation model parameter privacy protection method based on industrial Internet comprises the following steps:
step 1: initializing a system;
step 1.1: 4S shop according to selected safety parameters
Figure BDA0003091766150000023
Generating a car owner uiAnd session keys (pk, sk) between the car cloud, (pk, sk) is a public-private key pair based on BGN, i ═ 1, …, M;
Figure BDA0003091766150000024
wherein n is q1q2，q1、q2Is a two-large prime number that is,
Figure BDA0003091766150000025
is of order n ═ q1q2The cyclic group of (3);
Figure BDA0003091766150000026
is a bilinear map; k is
Figure BDA0003091766150000027
H ═ u, is generated randomlyq2Is a group
Figure BDA0003091766150000028
Q of (a) to (b)1Randomly generating elements of the order subgroup; sk ═ q1；i＝1，…，M；u＝(u1，u2，…，uM)；
Step 1.2: publishing a public key pk;
step 1.3: automobile owner negotiates regularization coefficient lambda and depreciation model parameter
Figure BDA0003091766150000029
Initial value of (2)
Figure BDA00030917661500000210
Learning step length alpha and precision E by a gradient descent algorithm;
step 1.4: automobile owner uiSending the accuracy E to the automobile cloud;
step 2: vehicle real-time acquisition of vehicle condition data of each part of automobile
Figure BDA00030917661500000211
And depreciation rating yiAutomobile owner uiCalculating and encrypting automobile condition data
Figure BDA00030917661500000212
And depreciation rating yi(ii) a Sending the encrypted information to the automobile cloud;
and step 3: the automobile cloud carries out privacy protection depreciation model parameter fitting, and returns the result to the automobile owner u as a service responsei；
And 4, step 4: automobile owner uiDecrypting with the help of a 4S store to obtain depreciated model parameters
Figure BDA00030917661500000213
Compared with the prior art, the method of the invention has the following advantages and beneficial effects:
the invention realizes the privacy protection evaluation system of the automobile depreciation model parameters under the condition of ensuring that the automobile condition data of the automobile owner is not leaked, and the obtained depreciation model parameters
Figure BDA0003091766150000031
The method reflects the weight of the influence of each part of automobile conditions on the vehicle depreciation evaluation, can be used for comprehensively evaluating the quality degree of the automobile conditions, is used as an important reference in the vehicle depreciation evaluation model, and has high practicability. The automobile owner encrypts and sends own automobile condition information and depreciation grade to the automobile cloud, and the automobile cloud cannot recover the private data of the automobile. And (4) carrying out privacy protection regression model fitting calculation on the ciphertext by the automobile cloud with the help of a 4S shop by using a machine learning algorithm, solving depreciation model parameters, and returning the result to the automobile owner. The automobile owner obtains depreciation model parameters through decryption with the help of a 4S store
Figure BDA0003091766150000032
Namely the weight of the influence of the vehicle conditions of all parts of the automobile on the vehicle depreciation evaluation. Due to the homomorphism of the algorithm, the automobile owner can not acquire the automobile condition data of other automobile owners after decryption. Therefore, the invention has high privacy protection safety.
Drawings
FIG. 1: the system architecture diagram of the embodiment of the invention;
FIG. 2: the method of the embodiment of the invention is a flow chart, wherein (a) is a flow chart from step 1 to step 3.1, (b) is a flow chart from step 3.2 to step 3.10, and (c) is a flow chart from step 3.11 to step 4.
Detailed Description
In order to facilitate the understanding and implementation of the present invention for those of ordinary skill in the art, the present invention is further described in detail with reference to the accompanying drawings and examples, it is to be understood that the embodiments described herein are merely illustrative and explanatory of the present invention and are not restrictive thereof.
The evaluation of the parameters of the automobile depreciation model is a service based on a privacy protection regression model. The depreciation model parameters are obtained under the condition that the participatory automobile owner does not want to reveal own automobile condition data to any participator
Figure BDA0003091766150000033
Namely, the weight of the influence of the vehicle conditions of all parts of the automobile on the automobile depreciation evaluation is convenient for the automobile depreciation grade evaluation. Therefore, the safety privacy protection evaluation system for the automobile depreciation model parameters has strong practical significance.
Referring to fig. 1, the system for privacy protection and evaluation of the parameters of the automobile depreciation model based on the industrial internet specifically comprises M automobile owners ui(i ═ 1, …, M), car cloud, and 4S store.
The 4S store of this embodiment is configured with a system initialization module, configured to generate and distribute a key and system parameters;
automobile owner u of the embodimentiThe system is provided with an automobile Internet of things acquisition and evaluation module, an automobile data encryption module and an automobile owner decryption module;the automobile internet of things acquisition and evaluation module is used for acquiring automobile condition data and depreciation evaluation levels of all parts of an automobile in real time by using the sensing and monitoring technology of the industrial internet of things and storing the data and depreciation evaluation levels into a local place for an automobile owner to process; the automobile data encryption module is used for encrypting automobile condition data by an automobile owner and sending the automobile condition data to the automobile cloud; the automobile owner decryption module is used for obtaining depreciation model parameters under the assistance of a 4S store
Figure BDA0003091766150000041
The automobile cloud of the embodiment is provided with a depreciation model parameter training module and a depreciation model parameter training module of a termination judgment module, and is used for performing depreciation model parameter fitting on the automobile cloud (the automobile cloud finishes the training module, the automobile cloud sends a query request to a 4S shop in the training process, and the 4S shop returns a query response, namely the automobile cloud calculates and the 4S shop provides a small amount of assistance calculation), and calculating a received ciphertext to obtain privacy protection depreciation model parameters
Figure BDA0003091766150000042
And returning the result to the car owner; and the termination judgment module is used for judging whether the training is finished or not (the judgment module is finished by the automobile cloud, the automobile cloud sends a query request to the 4S shop and the 4S shop returns a query response in the judgment process, namely the automobile cloud calculates and the 4S shop provides a small amount of assistance calculation).
In this embodiment, the car owner holds the car condition data and makes a safe car depreciation model parameter privacy protection evaluation service request to the car cloud, the car cloud and the 4S store generate a response (i.e., determine depreciation model parameters) without knowing any car owner specific car condition data, the car cloud returns the result to the car owner, and the car owner recovers the depreciation model parameters with the assistance of the 4S store
Figure BDA0003091766150000043
The car cloud interacts with the car owner, and the 4S store is responsible for system initialization and assisted computing.
M car owners u according to the embodimenti(i-1, …, M) providing respective vehicle condition data
Figure BDA0003091766150000044
(mileage, age, scene of use, safety performance, power performance, operability, exhaust emission, vehicle appearance, brand impact) and depreciation level yiFitting a privacy protection regression model by using a machine learning algorithm to obtain depreciation model parameters
Figure BDA0003091766150000045
Namely the weight of the influence of the vehicle conditions of all parts of the automobile on the vehicle depreciation evaluation.
Referring to fig. 2, the privacy protection evaluation method for the parameters of the automobile depreciation model based on the industrial internet safely calculates the parameters of the depreciation model according to the vehicle condition data of each part of the automobile provided by M automobile owners
Figure BDA0003091766150000046
Namely the weight of the influence of the vehicle conditions of all parts of the automobile on the vehicle depreciation evaluation. The concrete implementation comprises four steps: system initialization and vehicle real-time acquisition of vehicle condition data of each part of automobile
Figure BDA0003091766150000047
And depreciation rating yiVehicle condition data calculated and encrypted by the vehicle owner
Figure BDA0003091766150000048
And depreciation rating yiThe automobile cloud and the 4S store perform privacy protection depreciation model parameter fitting, the result is returned to the automobile owner as a service response, and the automobile owner decrypts the data with the help of the 4S store to obtain depreciation model parameters
Figure BDA0003091766150000049
The method specifically comprises the following steps:
step 1: initializing a system;
step 1.1: the 4S store selects 160bit security parameters according to the security parameters (the 4S store selects the security parameters of the security of the store of the security of the security of the security of the
Figure BDA0003091766150000051
) Generating a car owner ui(i ═ 1, …, M) and the session key (pk, sk) between the car clouds, (pk, sk) is a BGN-based public and private key pair;
Figure BDA0003091766150000052
wherein n is q1q2，q1、q2Is a two-large prime number that is,
Figure BDA0003091766150000053
is of order n ═ q1q2The cyclic group of (2). e:
Figure BDA0003091766150000054
is a bilinear map. k is
Figure BDA00030917661500000522
H ═ u, is generated randomlyq2Is a group
Figure BDA0003091766150000055
Q of (a) to (b)1Randomly generating elements of the order subgroup; sk ═ q1And kept secret by the 4S store. u ═ ui(i-1, …, M) } denotes that there are M car owners, each being u1，u2，…，uM；
Step 1.2: publishing a public key pk;
step 1.3: automobile owner ui(i 1, …, M) negotiating the regularization coefficients λ, fitting function parameters
Figure BDA0003091766150000056
Initial value of (2)
Figure BDA0003091766150000057
The gradient descent algorithm learns the step length alpha and the precision e.
Step 1.4: the car owner u1 sends the precision e to the car cloud.
Step 2: vehicle real-time acquisition of vehicle condition data of each part of automobile
Figure BDA0003091766150000058
And depreciation rating yiAnd stored locally. Automobile owner calculates and encrypts automobile condition data
Figure BDA0003091766150000059
And depreciation rating yi；
Step 2.1: the method comprises the steps that the automobile utilizes the sensing and monitoring technology of the industrial Internet of things to collect automobile condition data of all parts of the automobile in real time, the maintenance information and depreciation evaluation grade of the automobile in entity stores such as a 4S store and a maintenance store are collected, and the automobile condition data are processed
Figure BDA00030917661500000510
And depreciation rating yiAnd storing the data into the local.
Step 2.2: automobile owner ui(i-1, …, M) calculation
Figure BDA00030917661500000511
And
Figure BDA00030917661500000512
and selects a random number
Figure BDA00030917661500000513
Using algorithmic public key pairs
Figure BDA00030917661500000514
And
Figure BDA00030917661500000515
and (3) encryption:
Figure BDA00030917661500000516
Figure BDA00030917661500000517
wherein the content of the first and second substances,
Figure BDA00030917661500000518
representing a set of integers from 0 to n-1, and R represents a random choice.
Figure BDA00030917661500000519
Represents randomly selecting an integer from 0 to n-1;
step 2.3: automobile owner ui(i-1, …, M) information to be encrypted
Figure BDA00030917661500000520
And
Figure BDA00030917661500000521
sending the data to the automobile cloud;
step 2.4: automobile owner u1Selecting random numbers
Figure BDA0003091766150000061
The ai is encrypted using the algorithm public key,
Figure BDA0003091766150000062
and
Figure BDA0003091766150000063
Figure BDA0003091766150000064
Figure BDA0003091766150000065
Figure BDA0003091766150000066
wherein I represents an identity matrix, and m represents the number of vehicle condition data owned by the vehicle owner;
step 2.5: automobile owner u1Information to be encrypted [ lambda I [ [ lambda ] I ]]]、
Figure BDA0003091766150000067
And
Figure BDA0003091766150000068
and sending the data to the automobile cloud.
And step 3: the automobile cloud carries out privacy protection depreciation model parameter fitting, and returns the result to the automobile owner as a service response;
step 3.1: automobile cloud computing
Figure BDA0003091766150000069
And
Figure BDA00030917661500000610
Figure BDA00030917661500000611
Figure BDA00030917661500000612
wherein o represents a matrix-corresponding position element multiplication;
step 3.2: automobile cloud computing safety vector inner product
Figure BDA00030917661500000613
Figure BDA00030917661500000614
Figure BDA00030917661500000615
Then
Figure BDA0003091766150000071
Where Δ represents a safety vector inner product calculation, k1＝e(k，k)，h1＝e(k，h)。
Step 3.3: information to be encrypted by automobile cloud
Figure BDA0003091766150000072
Sending to a 4S store;
step 3.4: private key sk q for 4S store1Decrypting the received message:
private key sk q for 4S store1Decrypting the received message to obtain:
Figure BDA0003091766150000073
the 4S store decrypts with Pollard' S lambda algorithm to
Figure BDA0003091766150000074
Recovering the message plaintext by using the discrete logarithm of the base
Figure BDA0003091766150000075
4S store random number selection
Figure BDA0003091766150000076
Encryption using algorithmic public keys
Figure BDA0003091766150000077
Obtaining:
Figure BDA0003091766150000078
step 3.5: 4S store encrypted information
Figure BDA0003091766150000079
Sending the data to the automobile cloud;
step 3.6:automobile cloud computing
Figure BDA00030917661500000710
Figure BDA0003091766150000081
Step 3.7: automobile cloud computing
Figure BDA0003091766150000082
Figure BDA0003091766150000083
Using the multiplicative homomorphism to obtain:
Figure BDA0003091766150000084
step 3.8: automobile cloud ciphertext
Figure BDA0003091766150000085
Sending to a 4S store;
step 3.9: private key sk q for 4S store1Decrypting the received message:
private key sk q for 4S store1Decrypting the received message to obtain:
Figure BDA0003091766150000086
the 4S store decrypts with Pollard' S lambda algorithm to
Figure BDA0003091766150000087
Recovering the message plaintext by using the discrete logarithm of the base
Figure BDA0003091766150000088
And sending to the automobile cloud;
step 3.10: cloud basis of automobile
Figure BDA0003091766150000089
And judging whether the iteration is ended or not. If it is
Figure BDA00030917661500000810
Stopping the iteration and returning
Figure BDA00030917661500000811
Otherwise, go to step 3.11;
step 3.11: automobile cloud selection random number
Figure BDA00030917661500000812
Encryption using algorithmic public keys
Figure BDA00030917661500000813
Figure BDA0003091766150000091
Figure BDA0003091766150000092
Figure BDA0003091766150000093
Step 3.12: automobile cloud computing
Figure BDA0003091766150000094
Figure BDA0003091766150000095
And repeating step 3 until
Figure BDA0003091766150000096
Satisfy precision, stop iteration, return
Figure BDA0003091766150000097
And 4, step 4: the car owner decrypts to obtain depreciation model parameters with the help of 4S store
Figure BDA0003091766150000098
Step 4.1: automobile owner ui(i-1, …, M) choosing random vectors
Figure BDA0003091766150000099
For received cipher text
Figure BDA00030917661500000910
Randomizing;
Figure BDA00030917661500000911
and (3) calculating:
Figure BDA00030917661500000912
step 4.2: the car owner randomizes the ciphertext
Figure BDA00030917661500000913
Sending to a 4S store;
step 4.3: private key sk q for 4S store1Decrypting the received message to obtain:
Figure BDA00030917661500000914
4S store decrypts with k using Pollard' lambda algorithmq1Recovering the message plaintext by using the discrete logarithm of the base
Figure BDA0003091766150000101
And returned to the car owner;
step 4.4: the owner of the automobile randomizes the message to obtain depreciation model parameters
Figure BDA0003091766150000102
Figure BDA0003091766150000103
It should be understood that the above description of the preferred embodiments is given for clarity and not for any purpose of limitation, and that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (7)

1. The utility model provides a car depreciation model parameter privacy protection system based on industry internet which characterized in that: comprising M car owners uiCar cloud and 4S store, i ═ 1, …, M; the car owner uiThe vehicle condition data is the user who owns the vehicle condition data; the automobile cloud is a cloud server capable of providing secure storage and computing functions; the 4S store is a physical store which performs system initialization and provides assistance calculation;
the 4S shop is provided with a system initialization module for generating and distributing a secret key and system parameters;
the car owner uiThe system is provided with an automobile Internet of things acquisition and evaluation module, an automobile data encryption module and an automobile owner decryption module; the automobile internet of things acquisition and evaluation module is used for acquiring automobile condition data and depreciation evaluation levels of all parts of an automobile in real time by using the sensing and monitoring technology of the industrial internet of things and storing the data and depreciation evaluation levels into a local place for an automobile owner to process; the automobile data encryption module is used for encrypting automobile condition data by an automobile owner and sending the automobile condition data to the automobile cloud; the car ownerA decryption module for obtaining depreciation model parameters under the assistance of a 4S store by an automobile owner
Figure FDA0003091766140000011
The automobile cloud is provided with a depreciation model parameter training module and a termination judging module; the depreciation model parameter training module is used for performing depreciation model parameter fitting on the automobile cloud, calculating the received ciphertext and obtaining privacy protection depreciation model parameters
Figure FDA0003091766140000012
And returning the result to the car owner; and the termination judging module is used for judging whether the automobile cloud finishes training.
2. An automobile depreciation model parameter privacy protection method based on an industrial internet is characterized by comprising the following steps:
step 1: initializing a system;
step 1.1: 4S shop according to selected safety parameters
Figure FDA0003091766140000013
Generating a car owner uiAnd session keys (pk, sk) between the car cloud, (pk, sk) is a public-private key pair based on BGN, i ═ 1, …, M;
Figure FDA0003091766140000014
wherein n is q1q2，q1、q2Is a two-large prime number that is,
Figure FDA0003091766140000015
is of order n ═ q1q2The cyclic group of (3); e:
Figure FDA0003091766140000016
is a bilinear map; k is
Figure FDA0003091766140000017
The random generator of (a) is generated,
Figure FDA00030917661400000112
is a group
Figure FDA0003091766140000018
Q of (a) to (b)1Randomly generating elements of the order subgroup; sk ═ q1；i＝1，…，M；u＝(u1，u2，...，uM)；
Step 1.2: publishing a public key pk;
step 1.3: automobile owner negotiates regularization coefficient lambda and depreciation model parameter
Figure FDA0003091766140000019
Initial value of (2)
Figure FDA00030917661400000110
Learning step length alpha and precision E by a gradient descent algorithm;
step 1.4: automobile owner uiSending the accuracy E to the automobile cloud;
step 2: vehicle real-time collecting vehicle condition number of each part of vehicle
Figure FDA00030917661400000111
And depreciation rating yiAutomobile owner uiCalculating and encrypting automobile condition data
Figure FDA0003091766140000021
And depreciation rating yi(ii) a Sending the encrypted information to the automobile cloud;
and step 3: the automobile cloud carries out privacy protection depreciation model parameter fitting, and returns the result to the automobile owner u as a service responsei；
And 4, step 4: automobile owner uiDecrypting with the help of a 4S store to obtain depreciated model parameters
Figure FDA0003091766140000022
3. The privacy protection method for the parameters of the industrial internet-based automobile depreciation model according to claim 2, characterized in that: the specific implementation of the step 2 comprises the following substeps:
step 2.1: the method comprises the steps of collecting vehicle condition data of each part of the vehicle in real time, collecting vehicle maintenance information and depreciation evaluation grade, and collecting the vehicle condition data
Figure FDA0003091766140000023
And depreciation rating yiStoring the data into the local;
step 2.2: automobile owner uiComputing
Figure FDA0003091766140000024
And
Figure FDA0003091766140000025
and selects a random number
Figure FDA0003091766140000026
Public key pair
Figure FDA0003091766140000027
And
Figure FDA0003091766140000028
carrying out encryption; wherein the content of the first and second substances,
Figure FDA0003091766140000029
represents a set of integers from 0 to n-1, R represents a random choice;
Figure FDA00030917661400000210
represents randomly selecting an integer from 0 to n-1;
step 2.3: automobile owner uiInformation to be encrypted
Figure FDA00030917661400000211
And
Figure FDA00030917661400000212
sending the data to the automobile cloud;
step 2.4: automobile owner u1Selecting random numbers
Figure FDA00030917661400000213
The key is used to encrypt the ai,
Figure FDA00030917661400000214
and
Figure FDA00030917661400000215
wherein I represents an identity matrix, and m represents the number of vehicle condition data owned by the vehicle owner;
step 2.5: automobile owner u1And sending the encrypted information to the automobile cloud.
4. The privacy protection method for the parameters of the industrial internet-based automobile depreciation model according to claim 3, characterized in that: in the step 2.2, the first step,
Figure FDA00030917661400000216
Figure FDA00030917661400000217
5. the privacy protection method for the parameters of the industrial internet-based automobile depreciation model according to claim 3, characterized in that: in the step 2.4, the first step,
Figure FDA00030917661400000221
Figure FDA00030917661400000218
Figure FDA00030917661400000219
6. the privacy protection method for the parameters of the industrial internet-based automobile depreciation model according to claim 3, characterized in that: the specific implementation of the step 3 comprises the following substeps:
step 3.1: automobile cloud computing
Figure FDA00030917661400000222
And
Figure FDA00030917661400000220
Figure FDA0003091766140000031
Figure FDA0003091766140000032
wherein the content of the first and second substances,
Figure FDA0003091766140000039
representing multiplication of corresponding position elements of the matrix;
step 3.2: automobile cloud computing safety vector inner product
Figure FDA0003091766140000033
Figure FDA0003091766140000034
Note the book
Figure FDA0003091766140000035
Then
Figure FDA0003091766140000036
Where Δ represents a safety vector inner product calculation, k1＝e(k，k)，h1＝e(k，h)；
Step 3.3: information to be encrypted by automobile cloud
Figure FDA0003091766140000037
Sending to a 4S store;
step 3.4: the 4S store decrypts the received message and then encrypts the message again
Figure FDA0003091766140000038
Private key sk q for 4S store1Decrypting the received message to obtain:
Figure FDA0003091766140000041
4S store random number selection
Figure FDA0003091766140000042
Encryption using algorithmic public keys
Figure FDA0003091766140000043
Obtaining:
Figure FDA0003091766140000044
step 3.5: 4S store encrypted information
Figure FDA0003091766140000045
Sending the data to the automobile cloud;
step 3.6: automobile cloud computing
Figure FDA0003091766140000046
Figure FDA0003091766140000047
Step 3.7: automobile cloud computing
Figure FDA0003091766140000048
Note the book
Figure FDA0003091766140000049
Using the multiplicative homomorphism to obtain:
Figure FDA0003091766140000051
step 3.8: automobile cloud ciphertext
Figure FDA0003091766140000052
Sending to a 4S store;
step 3.9: decrypted by the 4S store
Figure FDA0003091766140000053
And sending to the automobile cloud;
private key sk q for 4S store1Decrypting the received message to obtain:
Figure FDA0003091766140000054
the 4S store decrypts with Pollard' S lambda algorithm to
Figure FDA0003091766140000055
Recovering the message plaintext by using discrete logarithm of base
Figure FDA0003091766140000056
And sending to the automobile cloud;
step 3.10: cloud basis of automobile
Figure FDA0003091766140000057
Judging whether the iteration is finished; if it is
Figure FDA0003091766140000058
Stopping the iteration and returning
Figure FDA0003091766140000059
Otherwise, go to step 3.11;
step 3.11: automobile cloud selection random number
Figure FDA00030917661400000510
Encryption using algorithmic public keys
Figure FDA00030917661400000511
Figure FDA00030917661400000512
Note the book
Figure FDA00030917661400000513
Figure FDA00030917661400000514
Step 3.12: automobile cloud computing
Figure FDA00030917661400000515
And repeating step 3 until
Figure FDA00030917661400000516
Satisfy precision, stop iteration, return
Figure FDA00030917661400000517
Figure FDA0003091766140000061
7. The privacy protection method for the parameters of the industrial internet-based automobile depreciation model according to any one of claims 2-6, characterized in that: the specific implementation of the step 4 comprises the following substeps:
step 4.1: automobile owner selects random vector
Figure FDA0003091766140000062
For received cipher text
Figure FDA0003091766140000063
Randomizing;
automobile owner uiPicking random vectors
Figure FDA0003091766140000064
For received cipher text
Figure FDA0003091766140000065
Randomizing;
note the book
Figure FDA0003091766140000066
And (3) calculating:
Figure FDA0003091766140000067
step 4.2: the car owner randomizes the ciphertext
Figure FDA0003091766140000068
Sending to a 4S store;
step 4.3: the 4S store decrypts the received ciphertext and returns the ciphertext to the automobile owner;
private key sk q for 4S store1Decrypting the received message to obtain:
Figure FDA0003091766140000069
the 4S store decrypts with Pollard' S lambda algorithm to
Figure FDA00030917661400000612
And recovering the message plaintext by taking the discrete logarithm as a base:
Figure FDA00030917661400000610
and returned to the car owner;
step 4.4: the owner of the automobile randomizes the message to obtain depreciation model parameters
Figure FDA00030917661400000611
Figure FDA0003091766140000071
CN202110597639.2A 2021-05-31 2021-05-31 Automobile depreciation model parameter privacy protection system and method based on industrial Internet Active CN113329021B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110597639.2A CN113329021B (en) 2021-05-31 2021-05-31 Automobile depreciation model parameter privacy protection system and method based on industrial Internet

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110597639.2A CN113329021B (en) 2021-05-31 2021-05-31 Automobile depreciation model parameter privacy protection system and method based on industrial Internet

Publications (2)

Publication Number Publication Date
CN113329021A true CN113329021A (en) 2021-08-31
CN113329021B CN113329021B (en) 2022-04-29

Family

ID=77422477

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110597639.2A Active CN113329021B (en) 2021-05-31 2021-05-31 Automobile depreciation model parameter privacy protection system and method based on industrial Internet

Country Status (1)

Country Link
CN (1) CN113329021B (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110208710A1 (en) * 2011-04-29 2011-08-25 Lesavich Zachary C Method and system for creating vertical search engines with cloud computing networks
CN103957109A (en) * 2014-05-22 2014-07-30 武汉大学 Cloud data privacy protection security re-encryption method
CN107070652A (en) * 2017-04-24 2017-08-18 湖南科技学院 A kind of anti-tamper car networking method for secret protection of ciphertext based on CP ABE and system
CN107682337A (en) * 2017-10-11 2018-02-09 深圳市轱辘车联数据技术有限公司 The processing method and system of a kind of vehicle data
CN108154275A (en) * 2017-12-29 2018-06-12 广东数鼎科技有限公司 Automobile residual value prediction model and Forecasting Methodology based on big data
CN108510400A (en) * 2017-09-19 2018-09-07 腾讯科技（深圳）有限公司 Automobile insurance information processing method and processing device, server and readable storage medium storing program for executing
CN108712260A (en) * 2018-05-09 2018-10-26 曲阜师范大学 The multi-party deep learning of privacy is protected to calculate Proxy Method under cloud environment
CN111343273A (en) * 2020-02-27 2020-06-26 电子科技大学 Attribute-based strategy hiding outsourcing signcryption method in Internet of vehicles environment
CN112308240A (en) * 2020-11-02 2021-02-02 清华大学 Edge side machine cooperation and optimization system based on federal learning
CN112769822A (en) * 2020-12-31 2021-05-07 中国科学院上海高等研究院 Data acquisition device, system and method based on edge calculation

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110208710A1 (en) * 2011-04-29 2011-08-25 Lesavich Zachary C Method and system for creating vertical search engines with cloud computing networks
CN103957109A (en) * 2014-05-22 2014-07-30 武汉大学 Cloud data privacy protection security re-encryption method
CN107070652A (en) * 2017-04-24 2017-08-18 湖南科技学院 A kind of anti-tamper car networking method for secret protection of ciphertext based on CP ABE and system
CN108510400A (en) * 2017-09-19 2018-09-07 腾讯科技（深圳）有限公司 Automobile insurance information processing method and processing device, server and readable storage medium storing program for executing
CN107682337A (en) * 2017-10-11 2018-02-09 深圳市轱辘车联数据技术有限公司 The processing method and system of a kind of vehicle data
CN108154275A (en) * 2017-12-29 2018-06-12 广东数鼎科技有限公司 Automobile residual value prediction model and Forecasting Methodology based on big data
CN108712260A (en) * 2018-05-09 2018-10-26 曲阜师范大学 The multi-party deep learning of privacy is protected to calculate Proxy Method under cloud environment
CN111343273A (en) * 2020-02-27 2020-06-26 电子科技大学 Attribute-based strategy hiding outsourcing signcryption method in Internet of vehicles environment
CN112308240A (en) * 2020-11-02 2021-02-02 清华大学 Edge side machine cooperation and optimization system based on federal learning
CN112769822A (en) * 2020-12-31 2021-05-07 中国科学院上海高等研究院 Data acquisition device, system and method based on edge calculation

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
MINGWU ZHANG: "PPO-CPQ: A Privacy-Preserving Optimization of Clinical Pathway Query for E-Healthcare Systems", 《IEEE INTERNET OF THINGS JOURNAL》 *
佘承其等: "大数据分析技术在新能源汽车行业的应用综述——基于新能源汽车运行大数据", 《机械工程学报》 *
纪守领等: "机器学习模型安全与隐私研究综述", 《软件学报》 *

Also Published As

Publication number Publication date
CN113329021B (en) 2022-04-29

Similar Documents

Publication Publication Date Title
CN110572253A (en) Method and system for enhancing privacy of federated learning training data
Wang et al. Privacy-assured outsourcing of image reconstruction service in cloud
CN106411533B (en) The online fingerprint identification system and method for two-way secret protection
CN107592311B (en) Cloud storage medical treatment big data lightweight batch auditing method towards wireless body area network
CN105049196B (en) The encryption method that multiple keywords of designated position can search in cloud storage
CN106850183A (en) A kind of full homomorphic cryptography ciphertext division implementation method
CN110120873B (en) Frequent item set mining method based on cloud outsourcing transaction data
CN108171066A (en) The cross-domain searching method of keyword and system in a kind of medical treatment cloud under secret protection
CN106096548A (en) A kind of many intelligent terminal based on cloud environment share face secret recognition methods
CN114640444B (en) Privacy protection set intersection acquisition method and device based on domestic cryptographic algorithm
CN110392038A (en) The multi-key cipher that can verify that under a kind of multi-user scene can search for encryption method
CN103684742A (en) Circulant matrix transformation based and ciphertext computation supportive encryption method
Cui et al. Outsourced ciphertext-policy attribute-based encryption with equality test
CN112491529B (en) Data file encryption and integrity verification method and system used in untrusted server environment
CN107248980A (en) Mobile solution commending system and method with privacy protection function under cloud service
CN109120606B (en) Method and device for processing characteristic attribute with privacy protection
CN108805574B (en) Transaction method and system based on privacy protection
CN112906036A (en) Internet of vehicles anonymous security evidence obtaining method and system based on block chain technology
CN114978495A (en) Rapid Paillier encryption method in federated learning system
CN101859306A (en) Method and equipment for generating blind index table, and united keyword search method and equipment
CN113329021B (en) Automobile depreciation model parameter privacy protection system and method based on industrial Internet
CN114021006A (en) Multi-dimensional data security query method and device
CN111159727B (en) Multi-party cooperation oriented Bayes classifier safety generation system and method
CN112787809B (en) Efficient crowd sensing data stream privacy protection truth value discovery method
CN114547684A (en) Method and device for protecting multi-party joint training tree model of private 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
GR01 Patent grant