CN112767693A - Vehicle driving data processing method and device - Google Patents
Vehicle driving data processing method and device Download PDFInfo
- Publication number
- CN112767693A CN112767693A CN202011639277.0A CN202011639277A CN112767693A CN 112767693 A CN112767693 A CN 112767693A CN 202011639277 A CN202011639277 A CN 202011639277A CN 112767693 A CN112767693 A CN 112767693A
- Authority
- CN
- China
- Prior art keywords
- target
- position information
- vehicle
- request
- information
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/02—Protecting privacy or anonymity, e.g. protecting personally identifiable information [PII]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/023—Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/025—Services making use of location information using location based information parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/44—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Traffic Control Systems (AREA)
Abstract
The application discloses a vehicle driving data processing method and device, relates to the technical field of electronics, and can solve the problem that vehicle owner privacy data such as vehicle position information in the prior art are leaked. The vehicle driving data processing method comprises the following steps: under the condition of receiving a target request, acquiring identification information of a target vehicle carried in the target request; the target request is used for acquiring the running data of the target vehicle; acquiring at least two pieces of key position information of the running of the target vehicle according to the identification information of the target vehicle; generating target position information according to the distribution probability density information of the at least two pieces of key position information; returning the target location information and the at least two key location information based on the target request. The vehicle driving data processing method is applied to the electronic equipment.
Description
Technical Field
The present disclosure relates to the field of electronic technologies, and in particular, to a method and an apparatus for processing vehicle driving data.
Background
The intelligent network automobile is an important field of 'internet plus' strategy landing, and has important significance for promoting transformation and upgrading of automobile, traffic and information communication industries. The intelligent internet automobile is based on the LTE-V2X modern communication technology and comprises a vehicle-mounted sensor, a controller, an actuator, a vehicle-mounted intelligent terminal, a data service platform and the like, so that intelligent information exchange and sharing of communication between the inside of the automobile and external facilities such as the automobile, roads, people and clouds can be realized, the surrounding environment can be sensed to make an instant decision, a driver is assisted to achieve control over the intelligent internet automobile, and the intelligent internet automobile finally replaces the driver to realize a safe, efficient, comfortable and energy-saving travel demand.
Under the background of the multi-mode development and industrial intelligence trend of the internet, the automobile industry is increasingly applied to the development of intellectualization and networking under the promotion of technologies such as mobile interconnection, big data and cloud computing. As a new direction of innovation and development, the intelligent internet automobile brings the automobile industry into a high-speed development period of multi-field and large-system integration, and relevant technology research and development and industrial layout are actively developed by whole automobile factories, component manufacturers, internet companies and the like, and concepts and technologies such as internet intelligent automobiles, automatic driving automobiles, shared automobiles, car networking and the like are continuously pushed out.
At present, the overall development of the Internet of vehicles in China is still in a starting stage. The potential safety hazard brought by the Internet of vehicles is increasingly obvious. Especially, when the vehicle is developed to be unmanned from the current single vehicle, various entrances of the intelligent internet vehicle-mounted terminal are more easily attacked. Meanwhile, data are stored in a data service platform in a centralized manner, and once illegal invasion and data stealing are caused, personal information can be leaked, and even a driving is threatened. Due to the continuous appearance of network security events, the security of the lives and properties of users is seriously threatened. The Internet of vehicles industry is long in chain, numerous in protection environment and complex in network safety problem, meanwhile, the Internet of vehicles is complex in network safety requirement, the network safety protection means is lack of pertinence and systematicness in construction, and the strengthening of Internet of vehicles network safety guarantee is urgent in cooperation with the whole situation of international network safety.
With the continuous improvement of automobile intellectualization, networking and electromotion degrees, the problem of intelligent networking automobile information safety becomes more serious, means such as information tampering and virus intrusion are successfully applied to automobile attack by hackers, and particularly, automobile information safety recall events which are frequently generated in recent years are more highly concerned by the industry. The information security crisis of the intelligent networked automobile can not only cause personal privacy and enterprise economic loss, but also cause serious consequences of automobile damage and personal death, and even rise to be a national public security problem.
With the gradual application of the intelligent networking automobile, a large amount of vehicle running information and vehicle position information are stored in a cloud system of an Internet of vehicles service provider and are used by other Internet of vehicles service providers. However, when the cloud system opens the data to the car networking service provider, the problem of leakage of car owner privacy data such as vehicle position information also becomes a problem which needs to be solved urgently in the car networking industry.
Content of application
The application provides a vehicle driving data processing method and device, which are used for solving the problem that privacy data of vehicle owners such as vehicle position information and the like in the prior art are leaked.
In order to solve the above problem, an embodiment of the present application provides a vehicle driving data processing method, including:
under the condition of receiving a target request, acquiring identification information of a target vehicle carried in the target request; the target request is used for acquiring the running data of the target vehicle;
acquiring at least two pieces of key position information of the running of the target vehicle according to the identification information of the target vehicle;
generating target position information according to the distribution probability density information of the at least two pieces of key position information;
returning the target location information and the at least two key location information based on the target request.
Optionally, the generating target location information according to the distribution probability density information of the at least two pieces of key location information includes:
generating target position information in different sub-area ranges according to the distribution probability density degree of the key position information of each sub-area range in the area range where the at least two key position information are located;
for any sub-region range, the degree of the distribution probability density of the key position information is in direct proportion to the number of the generated target position information.
Optionally, in the case that the target request is received, the method further includes:
acquiring a target time interval carried in the target request;
the acquiring at least two pieces of key position information of the target vehicle according to the identification information of the target vehicle comprises:
acquiring position information of the target vehicle in the target time period according to the identification information of the target vehicle and the target time period;
and acquiring at least two pieces of key position information from the position information of the running in the target time period.
Optionally, the returning the target location information and the at least two pieces of key location information based on the target request includes:
acquiring a total privacy budget value of the target vehicle; the total privacy budget value is inversely proportional to a privacy level of the target vehicle;
aiming at a target terminal corresponding to the target request, acquiring the target times of the request of the target terminal for acquiring the running data of the target vehicle;
determining a residual privacy budget value corresponding to the target request according to the total privacy budget value and the target times; the target number of times is inversely proportional to the remaining privacy budget value;
returning the target location information and the at least two key location information if the remaining privacy budget value is greater than zero.
Optionally, in the case that the target request is received, the method further includes:
acquiring identification information of the target terminal carried in the target request;
the returning the target location information and the at least two key location information based on the target request includes:
and returning the target position information and the at least two pieces of key position information to the target terminal according to the identification information of the target terminal.
In order to solve the above technical problem, an embodiment of the present application further provides a vehicle driving data processing apparatus, including:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring identification information of a target vehicle carried in a target request under the condition of receiving the target request; the target request is used for acquiring the running data of the target vehicle;
the second acquisition module is used for acquiring at least two pieces of key position information of the running of the target vehicle according to the identification information of the target vehicle;
the generating module is used for generating target position information according to the distribution probability density information of the at least two pieces of key position information;
and the return module is used for returning the target position information and the at least two pieces of key position information based on the target request.
Optionally, the generating module includes:
the position generating unit is used for generating target position information in different sub-area ranges according to the distribution probability density degree of the key position information in each sub-area range in the area range where the at least two pieces of key position information are located;
for any sub-region range, the degree of the distribution probability density of the key position information is in direct proportion to the number of the generated target position information.
Optionally, the apparatus further comprises:
a third obtaining module, configured to obtain a target time period carried in the target request;
the second obtaining module includes:
a first position acquisition unit configured to acquire position information of the target vehicle traveling in the target time period, based on the identification information of the target vehicle and the target time period;
and the second position acquisition unit is used for acquiring at least two pieces of key position information in the position information of the running in the target time interval.
Optionally, the return module includes:
a privacy acquisition unit configured to acquire a total privacy budget value of the target vehicle; the total privacy budget value is inversely proportional to a privacy level of the target vehicle;
a number obtaining unit, configured to obtain, for a target terminal corresponding to the target request, a target number of times that the target terminal sends a request for obtaining the travel data of the target vehicle;
the determining unit is used for determining a residual privacy budget value corresponding to the target request according to the total privacy budget value and the target times; the target number of times is inversely proportional to the remaining privacy budget value;
a first data returning unit, configured to return the target location information and the at least two pieces of key location information when the remaining privacy budget value is greater than zero.
Optionally, the apparatus further comprises:
a fourth obtaining module, configured to obtain identification information of the target terminal carried in the target request;
the return module includes:
and the second data returning unit is used for returning the target position information and the at least two pieces of key position information to the target terminal according to the identification information of the target terminal.
Compared with the prior art, the method has the following advantages:
when a target request for acquiring running data of a target vehicle is received, at least two pieces of key position information of the target vehicle, which is run by the target vehicle, are acquired according to identification information of the target vehicle, such as a license plate number, carried in the target request. Secondly, random target position information is added into the obtained at least two pieces of key position information, so that the at least two pieces of key position information and the added target position information are returned. In this way, in the returned data, a plurality of types of travel trajectories can be generated based on the key position information of the target vehicle and the target position information. Therefore, on the premise that a large amount of vehicle running information and vehicle position information are stored in a cloud system of the internet of vehicles service provider and used by other internet of vehicles service providers, based on the vehicle running data processing method of the embodiment of the application, the cloud system opens the data to the internet of vehicles service provider and returns the data to the internet of vehicles service provider, not only can approximate running data of a target vehicle be embodied through key position information, but also the internet of vehicles service provider can be interfered to acquire real running data through added target position information, and therefore the problem that privacy data of a vehicle owner such as the vehicle position information are leaked is solved.
Drawings
Fig. 1 is a flowchart illustrating steps of a method for processing vehicle driving data according to an embodiment of the present application;
fig. 2 is a system architecture diagram of a cloud server according to an embodiment of the present disclosure;
FIG. 3 is a schematic view of a vehicle networking system provided in an embodiment of the present application;
fig. 4 is a schematic diagram of a data desensitization process according to an embodiment of the present application;
FIG. 5 is a schematic diagram of vehicle driving data provided by an embodiment of the present application;
FIG. 6 is a schematic view of another vehicle driving data provided by an embodiment of the present application;
FIG. 7 is a schematic diagram of a differential attack provided by an embodiment of the present application;
fig. 8 is a system architecture diagram of another cloud server according to an embodiment of the present disclosure;
fig. 9 is a block diagram of a vehicle travel data processing device according to an embodiment of the present application.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, the present application is described in further detail with reference to the accompanying drawings and the detailed description.
Referring to fig. 1, a flowchart illustrating steps of a vehicle driving data processing method according to an embodiment of the present application is shown, and as shown in fig. 1, the vehicle driving data processing specifically may include the following steps:
step 101: and acquiring the identification information of the target vehicle carried in the target request under the condition of receiving the target request.
Wherein the target request is used to obtain the travel data of the target vehicle.
The method and the device for acquiring the driving data of the vehicle to be inquired can be applied to a scene that the terminal sends a request to the server so as to acquire the driving data of the vehicle to be inquired.
Optionally, the embodiment of the application is applied to a cloud server. The vehicle position information is stored in a cloud system of the internet of vehicles service provider, and is used by terminals of other internet of vehicles service providers.
Referring to fig. 2, optionally, in the system architecture of the cloud server, a plurality of data query interfaces are included. Therefore, in the application scenario of this embodiment, a terminal of an external entity such as an internet of vehicles service provider calls a data query interface provided by this system through an interface service, and applies for obtaining vehicle travel track data.
Step 102: and acquiring at least two pieces of key position information of the target vehicle in running according to the identification information of the target vehicle.
With continued reference to FIG. 2, in this step, the data query interface sends a target request to the module of the differentiated protection service. And the differential protection service calls a track data clustering model and sends the interface parameter values to the model.
Wherein the interface parameter value includes at least identification information of the target vehicle in this step.
Optionally, the identification information of the target vehicle includes a vehicle identifier such as a license plate number.
In the step, the track data clustering model queries vehicle running track data from the vehicle track data set according to the queried vehicle identification, and obtains key position information by using a clustering algorithm.
The embodiment of the application provides a differential protection service.
Referring to fig. 3, after the vehicle joins the internet of vehicles, the vehicle position information is sent to the internet of vehicles service cloud end for unified storage. Charging pile and other vehicle networking configuration service enterprises obtain vehicle position data from the cloud end, measure and calculate vehicle density and position, and help to determine the position and density of the installed charging pile.
In the prior art, in order to solve the privacy disclosure problem, a data desensitization technology is adopted.
The purpose of data desensitization techniques is to prevent the misuse of sensitive data by hiding such data. A variety of data desensitization techniques currently exist, such as replacing some fields with similar characters, replacing characters with masked characters (e.g., 'x'); replacing the actual surname with the virtual surname, and reorganizing the data in the database array. Data desensitization is also known as data obfuscation, data privacy, data disinfection, data scrambling, data anonymization, and data authentication. The data desensitization process can be seen in fig. 4.
Furthermore, in a data collaborative use scene, a desensitization technology is adopted, and the effect of blurring sensitive data in real time is achieved. Desensitization can realize transparent dynamic desensitization and static desensitization on sensitive data in a service system database. Dynamic desensitization: dynamic desensitization various desensitization strategies such as shielding and hiding can be carried out on data returned in a production database. Static desensitization: for the scenes of development, testing, data outgoing and the like, batch data desensitization capability is provided, a desensitized quasi-real database is generated through sampling, replacing and the like, and original association relation of desensitized data is kept.
While desensitization techniques are not resistant to differential attacks. The attacker can restore the vehicle privacy data by inquiring and comparing for many times or associating the desensitization data result set with other public data sets and adopting a method of continuously enriching background knowledge.
Therefore, based on the data desensitization technology, a charging pile service provider can still obtain the position and track information of part of vehicles through differential attack means such as background information, and privacy of vehicle owners is leaked. The obtained actual track information of the vehicle is shown in fig. 5.
The differential protection service provided by the embodiment of the application is a safe use method of vehicle driving track data based on differential privacy. Referring to fig. 6, after differential protection, trajectory information provided to the internet of vehicles service provider is a point with strong discreteness, and the internet of vehicles service provider can draw various driving trajectories according to the trajectory information, and even if background information exists, accurate trajectory information of a vehicle cannot be obtained. The differential attack results can be seen in fig. 7.
Therefore, the embodiment of the application provides a method and a system for safely using vehicle running track data based on differential privacy, so that differential privacy protection is provided for the open use of vehicle running track information containing cloud, and thus, a vehicle networking service provider can safely use the data and meet the service requirements of the vehicle networking service provider.
Step 103: and generating target position information according to the distribution probability density information of the at least two pieces of key position information.
In this step, noise is generated in the trajectory information acquired in step 102.
Optionally, based on a laplace probability density function, random noise is generated for a key position of the vehicle driving track data, and data disturbance is performed.
The generated noise is the target position information added to the at least two key position information.
As can be seen, the target location information may be virtual location information based on distribution characteristics of the key location information, or the like.
This step, among other things, generates random noise, which is also part of the differential protection service.
Step 104: target location information and at least two key location information are returned based on the target request.
In this step, the target location information and the at least two pieces of key location information may be sequentially returned according to the time sequence corresponding to each piece of location information.
When a target request for acquiring running data of a target vehicle is received, at least two pieces of key position information of the target vehicle, which is run by the target vehicle, are acquired according to identification information of the target vehicle, such as a license plate number, carried in the target request. Secondly, random target position information is added into the obtained at least two pieces of key position information, so that the at least two pieces of key position information and the added target position information are returned. In this way, in the returned data, a plurality of types of travel trajectories can be generated based on the key position information of the target vehicle and the target position information. Therefore, on the premise that a large amount of vehicle running information and vehicle position information are stored in a cloud system of the internet of vehicles service provider and used by other internet of vehicles service providers, based on the vehicle running data processing method of the embodiment of the application, the cloud system opens the data to the internet of vehicles service provider and returns the data to the internet of vehicles service provider, not only can approximate running data of a target vehicle be embodied through key position information, but also the internet of vehicles service provider can be interfered to acquire real running data through added target position information, and therefore the problem that privacy data of a vehicle owner such as the vehicle position information are leaked is solved.
In the step flow of the vehicle driving data processing method according to another embodiment of the present application, step 103 may specifically include the following steps:
substep A1: and generating target position information in different sub-area ranges according to the distribution probability density degree of the key position information in each sub-area range in the area range where at least two pieces of key position information are located.
For any sub-area range, the degree of the distribution probability density of the key position information is in direct proportion to the number of the generated target position information.
Referring to fig. 2, in the present embodiment, random noise may be generated in the noise generation model.
Specifically, a vehicle track information noise generation model adds random noise complying with Laplace probability density distribution to a vehicle driving track data result set by adopting a Laplace mechanism. Let x be data to be protected, the initial parameter be 0, the Laplace distribution of the scale parameter a be lap (a), and the probability density function be:
setting D as a data set of vehicle driving track key position data, and F (D) as a query result of the data set D;
let D ' be the D neighborhood data set, and F (D ') be the query result of data set D ';
if M (F (D)) ═ M (F (D')), the privacy protection algorithm M provides differential privacy protection for D.
Wherein M (F (D)), (D)) + p (x), and M (F (D ')), (F (D') + p (x).
Based on the noise generation model, the purposes can be achieved: and generating target position information according to the relation between the acquired key position information, such as the distribution probability density degree of all key positions.
For example, in the region where the distribution probability density degree is high, more than several target position information can be generated;
in contrast, in the area where the distribution probability density is low, a few pieces of target position information can be generated.
Therefore, in this step, the acquired key location information may be considered to be located in one region, and further, may be divided into a plurality of sub-regions, and specifically, the dividing method is not limited, and the dividing purpose is only to generate the target location information in different sub-regions.
It should be noted that, in the present embodiment, on the basis of not limiting the method of dividing the sub-area, the default division is a virtual step, and is only used for assisting understanding of generation of the target location information.
In the present embodiment, random noise is generated by a noise generation model. The algorithm in the noise generation model obeys Laplace probability density distribution, so that random noise, namely target position information accords with the real driving rule of a target vehicle, and further, the phenomenon that the track of the target vehicle is greatly influenced by deviation due to the addition of the target position information is avoided. Therefore, the vehicle running data privacy is protected, and the requirement of the vehicle networking service provider on the vehicle running data can be met.
In the step flow of the vehicle travel data processing method according to another embodiment of the present application, in step 101, in the case where the target request is received, the method further includes:
step B1: and acquiring the target time interval carried in the target request.
Wherein the interface parameter values further include at least a target time period in this step.
Optionally, the target period is a period included in a preset cycle. For example, the preset period is 30 seconds, and a period within every 30 seconds is taken as a target period.
Alternatively, the target period is a set certain period. For example, a target period of time is set from 6 am to 9 pm per day.
substep B2: and acquiring the position information of the target vehicle in the target period according to the identification information of the target vehicle and the target time period.
Referring to fig. 5, the position information acquired in this step includes a plurality of pieces of position information having low discreteness.
Substep B3: at least two key position information are acquired from the position information of the running in the target time period.
Referring to fig. 2, in the present embodiment, at least two pieces of key location information are acquired from the acquired location information through a vehicle travel track clustering model.
Wherein a k-means clustering algorithm is used.
Wherein w and c are scalar, after clustering, each value in w is assigned a cluster index, and c can be used as index1×kThe cluster centers form a codebook.
In reference, a K value (K is a positive integer, K >1) is determined, that is, we want to cluster the vehicle driving track data sets into K sets; randomly selecting K data points from a vehicle driving track data set as a mass center; calculating the distance between each point in the vehicle driving track data set and each centroid, and dividing the set to which the centroid belongs when the point is close to which centroid; after all data are grouped together, K groups are provided. And then calculating the mass center of each set to obtain K key position data in the vehicle driving track.
In this embodiment, at least two pieces of key position information are acquired through the vehicle driving track clustering model, so that the acquired key position information can embody the driving habits of the target vehicle. Therefore, on the basis of returning the running data of the target vehicle to the internet of vehicles service provider, only a few pieces of key position information are returned, so that differential protection is performed on the running data of the vehicle, and privacy disclosure is avoided.
In the flow of steps of the vehicle travel data processing method according to another embodiment of the present application, step 104 includes:
substep C1: and acquiring a total privacy budget value of the target vehicle.
Wherein the total privacy budget value is inversely proportional to the privacy level of the target vehicle.
In this step, the corresponding total privacy budget values are different based on different privacy levels of different vehicles.
The higher the privacy level of the vehicle is, the lower the total privacy budget value is, and the fewer times the car networking service provider can inquire. Conversely, the lower the privacy level of the vehicle, the higher the total privacy budget value, and the more times the car networking service provider can query.
Substep C2: and aiming at the target terminal corresponding to the target request, acquiring the target times of the requests for acquiring the running data of the target vehicle sent by the target terminal.
For a request, the target terminal in the request, i.e., the terminal that issued the request, will use an opportunity to query the target vehicle.
In this step, the number of used targets may be obtained for the current target request.
Substep C3: and determining a residual privacy budget value corresponding to the target request according to the total privacy budget value and the target times.
Wherein the target number is inversely proportional to the remaining privacy budget value.
In this step, the remaining privacy budget value is obtained by subtracting the target number of times from the total privacy budget value.
Thus, it can be understood that: the total privacy budget value is the total number of times of use, the target number of times is the number of times of use of the target terminal, and the remaining privacy budget value is the remaining number of times of use.
Substep C4: and returning the target position information and at least two pieces of key position information under the condition that the residual privacy budget value is larger than zero.
In this step, query data is returned only if the remaining privacy budget value is greater than zero.
Referring to fig. 2, in the present embodiment, the residual privacy budget value is obtained by the privacy budget module.
And if the residual privacy budget value is greater than zero, random noise is added into a key information result set of the queried vehicle. If the privacy budget value is less than or equal to zero, the user is informed that the data cannot be queried, and the result set is emptied.
In the privacy budget model of the present embodiment, the queries are classified into two categories, i.e., high budget queries and low budget queries. High budget queries are used for general civilian vehicles and low budget queries are used for high security class vehicles.
The high-budget inquiry of the civil vehicle adopts a PMW (private Multiplicated weights) mechanism, and the PMW constructs a composite algorithm through a voting mechanism to perform privacy budget consumption. PWM takes the distribution of the query structure over the value domain as a histogram, sets the corresponding frequency for each queried value and adds noise. If the difference between the two queries is smaller than a preset acceptable difference value, outputting the result of the last query without consuming the privacy budget, if the difference value is too large, issuing a new query result, consuming a higher privacy budget, and having query result accuracy to satisfy k queries with an error of
And the low budget query of the high-security-level vehicle adopts a median mechanism, and the median is used as the privacy budget for a query algorithm. M when the query result is odd0.5X (n + 1)/2; m when query is even0.5＝(x(n/2)+x(n/2+1))/2. The query process gradually deviates from the median outwards, and when the deviation value exceeds 2 standard deviations, random noise is regenerated, and the probability density distribution of output results is adjusted. Wherein x is the query result, and m is the median value of the formula operation output.
In this embodiment, a remaining privacy budget value corresponding to the current request is calculated through a privacy budget model, and valid data or null data is returned according to different remaining privacy budget values. Therefore, according to the embodiment, random noise is generated on the basis of differential protection, privacy budget is further provided, privacy of users is protected in multiple ways, and the problem of privacy disclosure is effectively solved.
In the step flow of the vehicle travel data processing method according to another embodiment of the present application, in step 101, in the case where the target request is received, the method further includes:
step D1: and acquiring the identification information of the target terminal carried in the target request.
Wherein, the interface parameter value at least also includes the identification information of the target terminal in the step.
Optionally, the identification information of the target terminal includes an identification code, a communication number bound to the target terminal, an account bound to the target terminal, and the like.
substep D2: and returning the target position information and the at least two pieces of key position information to the target terminal according to the identification information of the target terminal.
In this step, based on the identification information of the target terminal in this embodiment, the differential protection service monitors the query result set, and when the monitored result set has a value, obtains the result set data according to the vehicle identification parameter and the query interface identification parameter, and returns the result set data to the query interface. The query interface identification parameter includes identification information of the target terminal.
Alternatively, the target number of times the target terminal transmits the request for acquiring the travel data of the target vehicle is acquired according to the identification information of the target terminal.
In the embodiment, the final result is returned to the target terminal by acquiring the identification information of the target terminal in the target request; in addition, the target number of times requested by the target terminal is acquired according to the identification information of the target terminal. Therefore, the data can be pertinently returned to the terminal sending the request, so that the number of vehicles is prevented from being leaked to other terminals, and the problem of privacy data leakage is solved.
In a vehicle driving data processing method according to another embodiment of the present application, an application scenario according to an embodiment of the present application is described.
In reference, a certain vehicle enterprise accumulates a large amount of vehicle driving track information in a cloud vehicle remote service Provider (TSP), and the data are particularly important for a vehicle networking supporting enterprise engaged in charging pile service. However, how to safely provide the vehicle driving track data to the charging pile company is a problem that needs to be solved for data sharing. For many years, because data security problem can not effectively be solved, so fill electric pile enterprise and can only take modes such as spot-check survey to decide the position of installing the electric pile of filling, lead to filling electric pile to use very not abundant unbalance from this, fill electric pile to use for a few months in succession, fill electric pile to queue up the phenomenon seriously for a few.
By the vehicle track data safe use method and system based on the differential privacy, the safety problem that vehicle track data are used by a charging pile enterprise through a vehicle networking cloud can be solved.
See the system architecture shown in fig. 8. The system consists of 4 key parts of a service queue, a data queue, service management and differential privacy protection.
The service queue part is used for serving the external query request;
the data queue part is used for caching the returned data set for obtaining an external request;
and the service management part is used for setting service priority, calling external services, monitoring service execution conditions, monitoring machine load conditions and the like.
Wherein, the service management part comprises: the system comprises four modules of service priority setting, load setting and monitoring, service monitoring and service scheduling.
And the service priority setting module is used for setting service priority. The service priority is divided into 3 grades of general, priority and suspension, the priority service is executed preferentially, and the suspension service is not executed any more.
And the service scheduling module is used for scheduling the service according to the service priority, forwarding the service to the database interface and inquiring data.
And the service monitoring module is used for monitoring the service execution quantity, stopping service scheduling when the load of the machine exceeds a threshold value, recovering the load of the standby machine and restarting scheduling the external service.
The load setting and monitoring module is used for setting a network card Input/Output (IO) load threshold, a Central Processing Unit (CPU) utilization rate load threshold and a memory utilization rate threshold, and the monitoring means that the IO of the network card, the CPU utilization rate and the memory utilization rate are obtained through a server operating system interface.
And the differential privacy protection part is used for extracting key positions from the query result set in a clustering manner, generating random noise, disturbing the data of the key positions by using the random noise, and returning the data added with the noise under the condition that the privacy budget is greater than 0.
The key position data refers to key position data in a vehicle running track generated through a K-means clustering algorithm.
For example, a vehicle travel data set is shown in Table 1 below, with the data desensitized. The data acquisition frequency was 10 seconds/sample.
TABLE 1
The vehicle driving track clustering algorithm is as follows:
wherein w and c are scalar, after clustering, each value in w is assigned a cluster index, and c can be used as index1×kThe cluster centers form a codebook.
Specifically, a K value is determined every 30 seconds by taking 30 seconds as a period, and K sets are obtained by clustering the vehicle driving track data sets. And randomly selecting K data points from the vehicle driving track data set as the centroid. Taking the above table as an example, 9 centroids will be determined. And calculating the distance between each point in the vehicle driving track data set and each centroid, and dividing the point to which the centroid belongs to the set when the point is close to which centroid. After all data are grouped together, K is 9 groups. And then calculating the mass center of each set to obtain the data of K-9 key positions in the vehicle driving track. As in table 2 below.
TABLE 2
And disturbing the K value set data of the key position by adopting a Laplacp probability density distribution function.
Setting the k value set as x, the notation parameter as 0, the Laplace distribution of the scale parameter a as Lap (a), and the probability density function as:
setting D as desensitization data set, and F (D) as query result of data set D;
let D ' be the D neighborhood data set, and F (D ') be the query result of data set D ';
if M (F (D)) ═ M (F (D')), the privacy protection algorithm M provides differential privacy protection for D.
Wherein M (F (D)), (D)) + p (x), and M (F (D ')), (F (D') + p (x).
The perturbed set of key position k values is shown in table 3 below.
TABLE 3
Optionally, the present embodiment is applied to civil vehicle projects, employing a high budget query employing a PMW mechanism, PMWAnd constructing a composite algorithm through a voting mechanism to perform privacy budget consumption. The PMW takes the distribution of the query structure over the value range as a histogram, sets the corresponding frequency for each queried value and adds noise. If the difference between the two queries is smaller than a preset acceptable difference value, outputting the result of the last query without consuming the privacy budget, if the difference value is too large, issuing a new query result, consuming a higher privacy budget, and having query result accuracy meeting k queries with an error of
And after the privacy budget assessment, sending the data set to a data queue for external application to obtain.
In summary, the embodiment of the application aims to solve the problem of vehicle position data leakage, and realizes safe use of vehicle privacy data by taking a differential privacy protection technology as a means. The embodiment of the application mainly solves the following two key problems:
and one, the sensitive data guarantee capability in the car networking environment is greatly improved. The safe use method and the safe use system of the vehicle driving track data based on the differential privacy adopt a laplace-based differential privacy algorithm, a K-means clustering algorithm, a PWM privacy budget mechanism and a middle data privacy budget mechanism to provide reliable sensitive data protection for the data service of the Internet of vehicles cloud end, and realize the safe use of the sensitive data among different organizations.
And secondly, the use efficiency of the data of the Internet of vehicles is obviously improved. The safe use method and the safe use system of the vehicle driving track data based on the differential privacy adopt a differential privacy algorithm, a K-means clustering algorithm, a PWM privacy budget mechanism and a middle data privacy budget mechanism based on the laplace, effectively protect the safety of the vehicle sensitive data, enable the sensitive data which cannot be used by an external mechanism originally to be safely used under the protection of the differential privacy, help a vehicle networking service provider to exert data value, promote business development by using the data and improve the data application capability of a vehicle networking enterprise.
Referring to fig. 9, a block diagram of a vehicle travel data processing apparatus according to another embodiment of the present application is shown, and as shown in fig. 9, the vehicle travel data processing apparatus may specifically include:
a first obtaining module 10, configured to, in a case where a target request is received, obtain identification information of a target vehicle carried in the target request; the target request is used for acquiring the running data of the target vehicle;
the second obtaining module 20 is configured to obtain at least two pieces of key position information of the target vehicle according to the identification information of the target vehicle;
a generating module 30, configured to generate target location information according to distribution probability density information of at least two pieces of key location information;
and a returning module 40, configured to return the target location information and the at least two key location information based on the target request.
When a target request for acquiring running data of a target vehicle is received, at least two pieces of key position information of the target vehicle, which is run by the target vehicle, are acquired according to identification information of the target vehicle, such as a license plate number, carried in the target request. Secondly, random target position information is added into the obtained at least two pieces of key position information, so that the at least two pieces of key position information and the added target position information are returned. In this way, in the returned data, a plurality of types of travel trajectories can be generated based on the key position information of the target vehicle and the target position information. Therefore, on the premise that a large amount of vehicle running information and vehicle position information are stored in a cloud system of the internet of vehicles service provider and used by other internet of vehicles service providers, based on the vehicle running data processing method of the embodiment of the application, the cloud system opens the data to the internet of vehicles service provider and returns the data to the internet of vehicles service provider, not only can approximate running data of a target vehicle be embodied through key position information, but also the internet of vehicles service provider can be interfered to acquire real running data through added target position information, and therefore the problem that privacy data of a vehicle owner such as the vehicle position information are leaked is solved.
Optionally, the generating module 30 includes:
the position generating unit is used for generating target position information in different sub-area ranges according to the distribution probability density degree of the key position information of each sub-area range in the area range where at least two pieces of key position information are located;
for any sub-area range, the degree of the distribution probability density of the key position information is in direct proportion to the number of the generated target position information.
Optionally, the apparatus further comprises:
the third acquisition module is used for acquiring the target time interval carried in the target request;
a second acquisition module 20 comprising:
the first position acquisition unit is used for acquiring the position information of the target vehicle in the target time period according to the identification information of the target vehicle and the target time period;
and the second position acquisition unit is used for acquiring at least two pieces of key position information in the position information of the running in the target time period.
Optionally, the return module 40 includes:
a privacy acquisition unit for acquiring a total privacy budget value of the target vehicle; the total privacy budget value is inversely proportional to the privacy level of the target vehicle;
the number obtaining unit is used for obtaining the target number of times that the target terminal sends the request for obtaining the running data of the target vehicle aiming at the target terminal corresponding to the target request;
the determining unit is used for determining a residual privacy budget value corresponding to the target request according to the total privacy budget value and the target times; the target times are inversely proportional to the remaining privacy budget value;
and the first data returning unit is used for returning the target position information and the at least two pieces of key position information under the condition that the residual privacy budget value is larger than zero.
Optionally, the apparatus further comprises:
the fourth acquisition module is used for acquiring the identification information of the target terminal carried in the target request;
a return module 40 comprising:
and the second data returning unit is used for returning the target position information and the at least two pieces of key position information to the target terminal according to the identification information of the target terminal.
While, for purposes of simplicity of explanation, the foregoing method embodiments have been described as a series of acts or combination of acts, it will be appreciated by those skilled in the art that the present application is not limited by the illustrated ordering of acts, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.
Additionally, an embodiment of the present application further provides an electronic device, including: a processor, a memory, and a computer program stored on the memory and executable on the processor, the processor implementing the vehicle travel data processing method of any one of the above when executing the program.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The vehicle driving data processing method and the vehicle driving data processing device provided by the present application are introduced in detail, and specific examples are applied herein to explain the principle and the implementation of the present application, and the description of the above embodiments is only used to help understand the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (10)
1. A vehicle travel data processing method characterized by comprising:
under the condition of receiving a target request, acquiring identification information of a target vehicle carried in the target request; the target request is used for acquiring the running data of the target vehicle;
acquiring at least two pieces of key position information of the running of the target vehicle according to the identification information of the target vehicle;
generating target position information according to the distribution probability density information of the at least two pieces of key position information;
returning the target location information and the at least two key location information based on the target request.
2. The method of claim 1, wherein generating target location information based on the distributed probability density information of the at least two key location information comprises:
generating target position information in different sub-area ranges according to the distribution probability density degree of the key position information in each sub-area range in the area range where the at least two pieces of key position information are located;
for any sub-region range, the degree of the distribution probability density of the key position information is in direct proportion to the number of the generated target position information.
3. The method of claim 1, wherein in case of receiving a target request, further comprising:
acquiring a target time interval carried in the target request;
the acquiring at least two pieces of key position information of the target vehicle according to the identification information of the target vehicle comprises:
acquiring position information of the target vehicle in the target time period according to the identification information of the target vehicle and the target time period;
and acquiring at least two pieces of key position information from the position information of the running in the target time period.
4. The method of claim 1, wherein returning the target location information and the at least two key location information based on the target request comprises:
acquiring a total privacy budget value of the target vehicle; the total privacy budget value is inversely proportional to a privacy level of the target vehicle;
aiming at a target terminal corresponding to the target request, acquiring the target times of the request of the target terminal for acquiring the running data of the target vehicle;
determining a residual privacy budget value corresponding to the target request according to the total privacy budget value and the target times; the target number of times is inversely proportional to the remaining privacy budget value;
returning the target location information and the at least two key location information if the remaining privacy budget value is greater than zero.
5. The method of claim 4, wherein in case of receiving a target request, further comprising:
acquiring identification information of the target terminal carried in the target request;
the returning the target location information and the at least two key location information based on the target request includes:
and returning the target position information and the at least two pieces of key position information to the target terminal according to the identification information of the target terminal.
6. A vehicle travel data processing device characterized by comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring identification information of a target vehicle carried in a target request under the condition of receiving the target request; the target request is used for acquiring the running data of the target vehicle;
the second acquisition module is used for acquiring at least two pieces of key position information of the running of the target vehicle according to the identification information of the target vehicle;
the generating module is used for generating target position information according to the distribution probability density information of the at least two pieces of key position information;
and the return module is used for returning the target position information and the at least two pieces of key position information based on the target request.
7. The apparatus of claim 6, wherein the generating module comprises:
the position generating unit is used for generating target position information in different sub-area ranges according to the distribution probability density degree of the key position information in each sub-area range in the area range where the at least two pieces of key position information are located;
for any sub-region range, the degree of the distribution probability density of the key position information is in direct proportion to the number of the generated target position information.
8. The apparatus of claim 6, further comprising:
a third obtaining module, configured to obtain a target time period carried in the target request;
the second obtaining module includes:
a first position acquisition unit configured to acquire position information of the target vehicle traveling in the target time period, based on the identification information of the target vehicle and the target time period;
and the second position acquisition unit is used for acquiring at least two pieces of key position information in the position information of the running in the target time interval.
9. The apparatus of claim 6, wherein the return module comprises:
a privacy acquisition unit configured to acquire a total privacy budget value of the target vehicle; the total privacy budget value is inversely proportional to a privacy level of the target vehicle;
a number obtaining unit, configured to obtain, for a target terminal corresponding to the target request, a target number of times that the target terminal sends a request for obtaining the travel data of the target vehicle;
the determining unit is used for determining a residual privacy budget value corresponding to the target request according to the total privacy budget value and the target times; the target number of times is inversely proportional to the remaining privacy budget value;
a first data returning unit, configured to return the target location information and the at least two pieces of key location information when the remaining privacy budget value is greater than zero.
10. The apparatus of claim 6, further comprising:
a fourth obtaining module, configured to obtain identification information of the target terminal carried in the target request;
the return module includes:
and the second data returning unit is used for returning the target position information and the at least two pieces of key position information to the target terminal according to the identification information of the target terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011639277.0A CN112767693A (en) | 2020-12-31 | 2020-12-31 | Vehicle driving data processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011639277.0A CN112767693A (en) | 2020-12-31 | 2020-12-31 | Vehicle driving data processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112767693A true CN112767693A (en) | 2021-05-07 |
Family
ID=75698283
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011639277.0A Pending CN112767693A (en) | 2020-12-31 | 2020-12-31 | Vehicle driving data processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112767693A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115348280A (en) * | 2022-06-27 | 2022-11-15 | 昆明理工大学 | Vehicle networking data sharing method based on trusted block chain |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9494938B1 (en) * | 2014-04-03 | 2016-11-15 | Google Inc. | Unique signaling for autonomous vehicles to preserve user privacy |
| CN108364476A (en) * | 2018-03-26 | 2018-08-03 | 京东方科技集团股份有限公司 | Obtain car networking information approach and its device |
| CN108537055A (en) * | 2018-03-06 | 2018-09-14 | 南京邮电大学 | A kind of privacy budget allocation of data query secret protection and data dissemination method and its system |
| CN108959961A (en) * | 2018-06-26 | 2018-12-07 | 安徽大学 | Privacy protection method and device for inquiring average score, computer equipment and storage medium |
| CN109379718A (en) * | 2018-12-10 | 2019-02-22 | 南京理工大学 | Complete anonymous method for secret protection based on continuous-query location-based service |
| CN110334757A (en) * | 2019-06-27 | 2019-10-15 | 南京邮电大学 | Secret protection clustering method and computer storage medium towards big data analysis |
| CN110972133A (en) * | 2019-11-20 | 2020-04-07 | 安徽师范大学 | Semantic position privacy protection method based on space-time confusion in road network environment |
| CN111460508A (en) * | 2020-04-14 | 2020-07-28 | 苏州科技大学 | Track data protection method based on differential privacy technology |
| CN111614766A (en) * | 2020-05-22 | 2020-09-01 | 知行汽车科技（苏州）有限公司 | Vehicle information display system, method, device and storage medium |
| CN111797433A (en) * | 2020-07-17 | 2020-10-20 | 辽宁工业大学 | LBS service privacy protection method based on differential privacy |
-
2020
- 2020-12-31 CN CN202011639277.0A patent/CN112767693A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9494938B1 (en) * | 2014-04-03 | 2016-11-15 | Google Inc. | Unique signaling for autonomous vehicles to preserve user privacy |
| CN108537055A (en) * | 2018-03-06 | 2018-09-14 | 南京邮电大学 | A kind of privacy budget allocation of data query secret protection and data dissemination method and its system |
| CN108364476A (en) * | 2018-03-26 | 2018-08-03 | 京东方科技集团股份有限公司 | Obtain car networking information approach and its device |
| CN108959961A (en) * | 2018-06-26 | 2018-12-07 | 安徽大学 | Privacy protection method and device for inquiring average score, computer equipment and storage medium |
| CN109379718A (en) * | 2018-12-10 | 2019-02-22 | 南京理工大学 | Complete anonymous method for secret protection based on continuous-query location-based service |
| CN110334757A (en) * | 2019-06-27 | 2019-10-15 | 南京邮电大学 | Secret protection clustering method and computer storage medium towards big data analysis |
| CN110972133A (en) * | 2019-11-20 | 2020-04-07 | 安徽师范大学 | Semantic position privacy protection method based on space-time confusion in road network environment |
| CN111460508A (en) * | 2020-04-14 | 2020-07-28 | 苏州科技大学 | Track data protection method based on differential privacy technology |
| CN111614766A (en) * | 2020-05-22 | 2020-09-01 | 知行汽车科技（苏州）有限公司 | Vehicle information display system, method, device and storage medium |
| CN111797433A (en) * | 2020-07-17 | 2020-10-20 | 辽宁工业大学 | LBS service privacy protection method based on differential privacy |
Non-Patent Citations (1)
| Title |
|---|
| 包先跃: "车联网中轨迹数据发布隐私保护关键技术的研究", 《中国优秀博硕士学位论文全文数据库(硕士) 工程科技Ⅱ辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115348280A (en) * | 2022-06-27 | 2022-11-15 | 昆明理工大学 | Vehicle networking data sharing method based on trusted block chain |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11477212B2 (en) | System and method for connected vehicle cybersecurity | |
| US20200238847A1 (en) | System to prioritize power delivery from a charging station to electric vehicle | |
| US11410472B2 (en) | Comparing vehicle performance | |
| US11685283B2 (en) | Transport-based energy allocation | |
| CN112215621A (en) | Carbon emission reduction data processing method, apparatus, and computer-readable storage medium | |
| CN102624677B (en) | Method and server for monitoring network user behavior | |
| US11840244B2 (en) | System and method for detecting behavioral anomalies among fleets of connected vehicles | |
| CN112241543A (en) | Sensitive data combing method based on data middling stage | |
| CN113111359A (en) | Big data resource sharing method and resource sharing system based on information security | |
| JP2023532179A (en) | Energy sharing based on demand | |
| CN111177480A (en) | Block chain directory file system | |
| CN113400962A (en) | Wirelessly informing a vehicle of providing a portion of energy | |
| Löbner et al. | Comparison of de-identification techniques for privacy preserving data analysis in vehicular data sharing | |
| CN112767693A (en) | Vehicle driving data processing method and device | |
| JP2022159038A (en) | Multi-level access control in sharing vehicle data with device | |
| CN110798353A (en) | Network behavior risk perception and defense method based on behavior characteristic big data analysis | |
| JP2021182853A (en) | Transportation means charge offload management | |
| CN102833107A (en) | Safety access method and system | |
| US20230268739A1 (en) | Providing electricity to a location using an idle transport | |
| CN116159310A (en) | Data processing method, device, electronic equipment and storage medium | |
| CN110503563A (en) | Risk control method and system | |
| US20230226941A1 (en) | Electric transport charging determination | |
| CN115664800A (en) | Big data safety protection system based on cloud computing | |
| Guo et al. | DCA: Delayed Charging Attack on the Electric Shared Mobility System | |
| CN114051220A (en) | Ontology-based dynamic Bayesian attack graph generation method and system for Internet of vehicles |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210507 |
|
| RJ01 | Rejection of invention patent application after publication |