CN114861220A - Automatic driving data processing method and system conforming to data privacy security - Google Patents
Automatic driving data processing method and system conforming to data privacy security Download PDFInfo
- Publication number
- CN114861220A CN114861220A CN202210444802.6A CN202210444802A CN114861220A CN 114861220 A CN114861220 A CN 114861220A CN 202210444802 A CN202210444802 A CN 202210444802A CN 114861220 A CN114861220 A CN 114861220A
- Authority
- CN
- China
- Prior art keywords
- data
- automatic driving
- vehicle
- processing method
- metadata
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/258—Data format conversion from or to a database
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/28—Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0841—Registering performance data
- G07C5/085—Registering performance data using electronic data carriers
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an automatic driving data processing method and system according with data privacy safety, wherein the processing method comprises the following steps: step 1, collecting automatic driving data of a vehicle; step 2, preprocessing the data; step 3, extracting the characteristics of the data; step 4, calculating a control instruction of automatic driving; step 5, data classification and labeling are carried out; and 6, obtaining data scores of automatic driving of the vehicle, if the data scores reach a preset threshold value of a user, generating metadata, initiating a request for packaging the metadata into blocks by the vehicle, completing data authority after the metadata pass through confirmation of all nodes, and storing automatic driving data corresponding to the metadata. On the basis of guaranteeing privacy and rights and interests of automatic driving data owners, the method and the system can be used for exploring and classifying difficult data and can also prompt intelligent automobile users to actively contribute to automatic driving data.
Description
Technical Field
The invention relates to the technical field of automobile automatic driving data processing, in particular to an automatic driving data processing method and system in accordance with data privacy safety.
Background
Currently, there are published patent techniques to collect massive data using large fleets of vehicles under flags, thereby retrospectively iterating their autonomous driving system performance. Various sensors such as cameras, laser radars, millimeter wave radars, speed measuring instruments and navigators and various APPs integrated on the intelligent automobile constantly collect environmental information, vehicle driving information and personal information of the vehicle. Therefore, in the past, the safety problem of the intelligent mobile terminal is also transferred to the intelligent automobile, and the problems of data safety, personal information, personal safety and public safety are also regarded as the road barricades for the commercial use of the intelligent automobile. In recent years, with the accelerated development of intelligent networked automobiles, the data security problem of the intelligent automobiles becomes a key point of industrial attention.
Although technologies for guaranteeing privacy and data security of intelligent automobile users by adopting federal learning or block chaining exist at present, the existing technologies are not specially designed for data collection in the field of automatic driving, do not have capacity of exploring and classifying difficult data, and lack an incentive mechanism for agreeing to contribute data to users, so that the final data collection efficiency is low, and the initiatives of data sharing are lacked among organizations and enterprises, so that the technologies are more difficult to be used for improving the performance of automatic driving vehicles. Therefore, a new big data acquisition system of an automatic driving vehicle is required to be provided on the premise of meeting the data security law and the user privacy protection.
Disclosure of Invention
The invention aims to provide an automatic driving data processing method and system which are in accordance with data privacy safety. On the basis of guaranteeing privacy and rights and interests of automatic driving data owners, the method and the system can be used for exploring and classifying difficult data and can also prompt intelligent automobile users to actively contribute to automatic driving data.
The technical scheme of the invention is as follows: an automatic driving data processing method conforming to data privacy safety comprises the following steps:
step 1, collecting vehicle automatic driving data consisting of external sensing data measured by a vehicle sensor and behavior state data of a vehicle;
step 2, preprocessing the collected automatic driving data of the vehicle, and converting the data into a structured standard format;
step 3, extracting the characteristics of the preprocessed data to obtain a characteristic matrix F of the collected external perception data sensor And high-dimensional state features F of the vehicle behavior state data state ；
Step 4, data F obtained after characteristic extraction sensor And F state Calculating the control instruction of automatic driving to obtain a decision control signal sequence U model ；
Step 5, data F obtained after feature extraction sensor And F state Carrying out data classification and labeling to form a first data packet;
step 6, collecting the action signal sequence U actually executed by the vehicle real Will U is real And U model Comparing to obtain basic score E base And then an extra score E is given according to the data scarcity of the first data packet bonus The basic score E base And an additional score E benus Integrating to obtain the data score E of the automatic driving of the vehicle adjust Updating the first data packet to include a data score E adjust The second data packet of (1);
if the data score is E adjust When the preset threshold value of the user is reached, generating metadata containing all data in the second data packet, initiating a request for packaging the metadata into a block by the vehicle, completing data right confirmation after the confirmation of all nodes is passed, and simultaneously enabling the metadata to be matched with the blockStoring the automatic driving data corresponding to the data.
In the automatic driving data processing method conforming to data privacy security, the external sensing data in the step 1 includes laser radar data, camera data, millimeter wave radar data, and ultrasonic radar data; the external sensing data, namely the external environment image and the point cloud data from the sensor can support a sensing algorithm based on deep learning to perform model training.
In the foregoing automatic driving data processing method according with data privacy security, the behavior state data of the vehicle in step 1 includes map data, combined navigation data, wheel speed pulse data, V2X data, vehicle execution motion data, vehicle body electronic stability system data, and battery level SOC; the vehicle behavior state data can be used for model training and iteration based on a decision planning algorithm of reinforcement learning.
In the foregoing automatic driving data processing method according to data privacy security, the data preprocessing in step 2 includes image distortion removal, time synchronization, and signal filtering.
In the automatic driving data processing method conforming to the data privacy security, in the step 3, the general neural network model is used for performing feature extraction and data fusion on the external perception data to obtain the feature matrix F sensor The characteristic matrixes are used for inputting neural network models which are subsequently responsible for different detection tasks, and finally making decisions and control on the vehicle; at the same time, these feature matrices are also used for classification, scoring, and metadata generation of the autonomous driving data.
In the automatic driving data processing method conforming to data privacy security, in the step 3, the vehicle behavior state data is subjected to feature extraction by using a rule judgment mode to form a high-dimensional state feature F representing the current driving behavior, the overall operation state and the position of the vehicle state ，F state Current position coordinates, navigation destination coordinates, navigation planning path points, current road area, current vehicle control actions, current vehicle state, external traffic conditions, external weatherSituation, time of day]。
In the automatic driving data processing method meeting the data privacy safety, in the step 5, a supervised learning algorithm is used for performing multi-stage classification on data scenes, and a semi-supervised learning method is used for performing semi-automatic labeling on data.
In the foregoing automatic driving data processing method according to data privacy security, in step 6, U is added real And U model The absolute value of the difference between the two is used as a basic score E base The larger the difference between the action actually performed by the vehicle and the action output by the model is, the base score E base The higher the number of the channels to be used,
E adjust ＝A*E base +B*E bonus
wherein T is the total frame number of the data packets collected each time, A, B represents the weight of two scores respectively, can be freely adjusted, and E is shown adjust Measured by the subsequent use heat, scarcity of the data.
The evaluation of the data for the subsequent screening of the data by the data consumer and the evaluation of the data usage costs also correspond to the gains that the data holder can obtain based on the data, and therefore, E adjust The scoring mechanism can better send out difficult scenes and high-value data.
In the foregoing automatic driving data processing method according with data privacy security, in step 6, when the vehicle initiates a request for packaging metadata into a block, all nodes compete for metadata packaging right through a POW mechanism; the vehicle side acquiring the metadata packaging right shares subsequent data rights and interests with the data owner; when each node authenticates the data in the block chain, the information provided by the metadata synchronously searches whether the similar data exist.
When a data demand party wants to update the algorithm model of the data demand party based on high-value data of a user, metadata and corresponding automatic driving data which are wanted to be used can be searched and locked through a block chain network, then the algorithm model which needs to be iterated per se is uploaded to a corresponding supervised data storage center, and the model is downloaded back to the local after being trained remotely. The revenue generated by this process will be shared by the data center, the data owner, and the data packager.
All information stored on the block chain is metadata, and all information of node accounts, data owners and the like is subjected to hash encryption through the block chain, so that the risk of privacy disclosure does not exist on the chain. And the automatic driving original data is only related to the metadata and is stored in a data center under supervision, so that the requirements of laws and regulations are met.
The system for realizing the automatic driving data processing method according with the data privacy safety comprises a communication module, a sensor module, a calculation module and a metadata storage module.
Compared with the prior art, the invention has the beneficial effects that: the method ensures the privacy and the rights of the owner of the automatic driving data, and the storage safety and the use safety of other sensitive data (geographic data, security data, social and economic data and the like), and ensures the safety and the legality of the collected automatic driving data in the use process; meanwhile, classification of data scenes, identification of difficult cases/boundary working conditions, screening of high-value data and labeling of the data can be automatically carried out; in addition, the invention can also promote intelligent automobile users to actively contribute to automatic driving data, and make it possible for different enterprise organizations to share and share the automatic driving data, finally realize continuous data supply, and can bring continuous improvement to the performance of the automatic driving vehicle.
Drawings
FIG. 1 is a flow chart of a data processing method of the present invention;
FIG. 2 is a block diagram of a data processing system in accordance with the present invention.
Detailed Description
The invention is further illustrated by the following figures and examples, which are not to be construed as limiting the invention.
Example (b): an automatic driving data processing system conforming to data privacy security, system modules refer to fig. 1 and comprise a communication module, a sensor module, a calculation module and a metadata storage module, and an automatic driving data processing method conforming to data privacy security based on the above modules comprises the following steps, and a flow chart of the steps refers to fig. 2:
step 1, collecting vehicle automatic driving data consisting of external sensing data measured by a vehicle sensor and behavior state data of a vehicle;
a driver drives a vehicle in an urban area that carries the system of the present invention, which continuously collects information about sensors on the vehicle and the vehicle itself. The method comprises the following steps: external sensing data (lidar data, camera data, millimeter wave radar data, ultrasonic radar data) and vehicle behavior state data (map data, integrated navigation data, wheel speed pulse data, V2X data, vehicle execution motion data, vehicle body electronic stability system data, battery level SOC, etc.).
And 2, preprocessing the collected automatic driving data of the vehicle, converting the automatic driving data into a structured standard format, and reserving the data which can be triggered subsequently for the step of uploading the data to a data center.
Step 3, extracting the characteristics of the preprocessed data to obtain a characteristic matrix F of the collected external perception data sensor And high-dimensional state features F of the vehicle behavior state data state ；
F is obtained by performing feature extraction and data fusion on external perception data by using mainstream universal neural network models such as darknet53 and resnet50 sensor 。
Using a rule judgment mode to perform feature extraction on the vehicle behavior state data to form high-dimensional state features F representing the current driving behavior, the overall running state and the position of the vehicle state 。
F state Current position coordinates, navigation destination coordinates, navigation planning path points, current road area, current vehicle control actions, current vehicleState, external traffic conditions, external weather conditions, time]。
For example, the current driver drives a vehicle, runs on a road near a cell A, keeps going straight, and a navigation target is arranged in a mall B:
then F state Current coordinates of vehicle, coordinates of entrance of parking lot in market B, planned route from A to B, and non-express way u in urban area real [ vehicle speed, remaining amount of electricity, heading angle, etc. ]]Road smoothness, rainy day, night 19: 00]。
Step 4, data F obtained after characteristic extraction sensor And F state Calculating the control instruction of automatic driving to obtain a decision control signal sequence U model The command does not actually act on the vehicle (whether the actual vehicle is driven by the driver or not);
there are many ways to calculate the automatic driving control instruction, and the data demander can select the data result output by using the corresponding calculation way according to the situation, for example, three more mainstream flows are as follows:
scheme 1: extracting external perception data to obtain characteristic F sensor Binding F state Corresponding dimension conversion and state splicing are carried out to obtain similar [ F ] sensor ，F state ]In the form of (1). Will [ F ] sensor ，F state ]Inputting into a designed reinforcement learning neural network model, and directly outputting corresponding control action u model Instructions;
and (2) a flow scheme: f can also be replaced by sensor Input into the normal autodrive algorithm workflow, namely: sensing module pair F sensor Analyzing and extracting a perception target result O res The decision-making module extracts information F according to the perception target result and the behavior state data from the vehicle state Starting behavior decision A (high-dimensional instructions such as lane change, straight driving, parking, turning, avoidance and the like), planning the trajectory of the decision instruction by the planning module, outputting a series of position points which are expected to be reached by the vehicle in the next period of time, finally tracking and controlling the position trajectory points by the control module, and calculating the corresponding control action u at the current moment model ；
And (3) a flow path: can convert O in scheme 2 res And F state Performing state splicing to obtain [ O ] res ，F state ]Will be [ O ] res ，F state ]Inputting the decision behavior instruction A into the reinforcement learning neural network model, and outputting a corresponding decision behavior instruction A, wherein the subsequent method is consistent with the process 2.
Step 5, data F obtained after feature extraction sensor And F state And data classification and labeling are carried out, so that the repeated operation of feature extraction by a module is avoided, and the calculation consumption is reduced. This step forms the data such as the external sensing data, the vehicle behavior state data, and the label]The first data packet of (1);
first F state Some classification labels such as: rainy day-urban road-night-u real Vehicle condition, based on the extracted features F sensor And carrying out data classification and labeling through a mainstream AI classification algorithm and a labeling algorithm.
Step 6, a data scoring link: collecting the action signal sequence U actually executed by the vehicle real Will U is real And U model Comparing to obtain basic score E base And then an additional score E is given according to the data scarcity of the first data packet bonus The basic score E base And an additional score E benus Integrating to obtain the data score E of the automatic driving of the vehicle adjust Updating the first data packet to include a data score E adjust The second data packet of (1);
this step forms a second data packet such as [ external perception data, vehicle behavior state data, tag, score ];
in the data scoring section, the collected action signals u actually executed by the vehicle are taken into account real And calculating the decision control signal sequence u with the current model model And (6) carrying out comparison. And taking the absolute value of the difference value of the two as the base value of the final score. The larger the difference between the action actually performed by the vehicle and the action output by the model is, the larger the basic score E is base The higher. Assuming that the total frame number of the data packets collected each time is T, the actual control signal movesThe sequence is U real ＝[u real1 ，u real2 ，...，u realT ]And the control signal action sequence obtained by the model is U model ＝[u model1 ，u model2 ，...，u modelT ]，
The final data summary consists of two parts:
E adjust ＝A*E base +B*E bonus
E benus an additional score given by the scarcity of data, therefore, see E adjust Measured by the subsequent use heat, scarcity of the data.
A. B represents the weight of the two scores respectively and can be freely adjusted.
The scoring of the data is used for screening the data by a subsequent data demander and evaluating the cost required by the data use, and also corresponds to the income obtained by the data holder based on the data. By E adjust The scoring mechanism can better send out difficult scenes and high-value data.
Metadata composition:
if the score is E adjust If the preset threshold value of the user is reached, the step, the subsequent metadata right confirmation and the uploading and storage of the automatic driving data packet are triggered. The metadata is data describing data attributes, and the metadata in the embodiment mainly describes data packets [ external perception data, vehicle behavior state data, tags, scores ] needing to be uploaded and stored]The data of (1). The metadata content in the invention includes scene type description (such as weather condition, geographical position, time, data rating/value, driving condition, data encryption mode, feature extraction mode and parameter, feature matrix obtained after the data is subjected to the feature extraction step, data quantity, owner, data packet storage address and the like) of the collected automatic driving data, and the metadata in the embodiment is [ tag (including weather, time, geographical position and driving condition)Etc.), data score E adjust Encryption (such as sha256), feature extraction (such as dark net53), and extracted feature data matrix [ F [ sensor ，F state ]Data size (e.g., 3MB), data owner node (e.g., ID304c26b0cb99ce91c6 node user, each node having a unique encrypted ID), data authentication node (e.g., IDafe2cc588d86079f9de8 node user), address index of the corresponding packet (e.g., xxx number of xxx city data center xxx number storage area xxx number location)]。
User node, data right confirmation and packaging:
each vehicle with data storage, computation, and network communication functions can be freely selected by the user whether to become a computing node or a data providing node in the data authentication network. Each new node encrypts the owner information through hash operation to obtain a unique encrypted node ID and a private key for identity verification. When the collected data packet meets the scoring threshold value and the application of metadata uploading block chain authentication is triggered, the application is sent to peripheral computing nodes in a broadcasting mode, and the computing nodes adopt a POW mechanism to compete for metadata authentication. And finally, after metadata authentication is completed, uploading and storing the corresponding automatic driving data packet to a supervised data center. At this time, the metadata stored in the blockchain network also includes information such as a data owner node, a data authentication node, and a data storage address. When each node authenticates the data block chain, the node synchronously searches whether the similar data exist or not through the information provided by the metadata (through the label of data classification, the extracted characteristic and the like), and gives higher E to the rare data bonus And (6) additional scoring.
Data usage:
when a data demand party wants to update the algorithm model of the data demand party based on high-value data of a user, metadata and corresponding automatic driving data which are wanted to be used are locked through a block chain network browser through a screening method such as a mode of retrieving metadata labels, scores and model feature extraction, then the algorithm model which needs to be iterated per se is uploaded to a corresponding supervised data storage center according to the address of a corresponding automatic driving data packet in the metadata, and the algorithm model is downloaded back to the local after remote model training. The revenue generated by this process will be shared by the data center, the data owner node, and the data authentication node.
The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above-mentioned examples, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention. It should be noted that modifications and embellishments within the scope of the invention may occur to those skilled in the art without departing from the principle of the invention, and are considered to be within the scope of the invention.
Claims (10)
1. An automatic driving data processing method conforming to data privacy safety is characterized by comprising the following steps:
step 1, collecting vehicle automatic driving data consisting of external sensing data measured by a vehicle sensor and behavior state data of a vehicle;
step 2, preprocessing the collected automatic driving data of the vehicle, and converting the data into a structured standard format;
step 3, extracting the characteristics of the preprocessed data to obtain a characteristic matrix F of the collected external perception data sensor And a high-dimensional state feature F of the vehicle behavior state data state ；
Step 4, data F obtained after characteristic extraction sensor And F state Calculating the control instruction of automatic driving to obtain a decision control signal sequence U model ；
Step 5, data F obtained after feature extraction sensor And F state Carrying out data classification and labeling to form a first data packet;
step 6, collecting the action signal sequence U actually executed by the vehicle real Will U is real And U model Comparing to obtain basic score E base An extra is given according to the data scarcity of the first data packetScore E bonus The basic score E base And an additional score E bonus Integrating to obtain the data score E of the automatic driving of the vehicle adjust Updating the first data packet to include a data score E adjust The second data packet of (1);
if the data score is E adjust And when the threshold value is preset by the user, generating metadata containing all data in the second data packet, initiating a request for packaging the metadata into a block by the vehicle, completing data authority confirmation after the metadata passes through all nodes, and storing the automatic driving data corresponding to the metadata.
2. The automatic driving data processing method according to claim 1, wherein the automatic driving data processing method comprises the following steps: the external perception data in the step 1 comprise laser radar data, camera data, millimeter wave radar data and ultrasonic radar data.
3. The automatic driving data processing method according to claim 1, wherein the automatic driving data processing method comprises the following steps: the behavior state data of the vehicle in the step 1 comprises map data, combined navigation data, wheel speed pulse data, V2X data, vehicle execution action data, vehicle body electronic stability system data and battery power SOC level.
4. The automatic driving data processing method according to claim 1, wherein the automatic driving data processing method comprises the following steps: the data preprocessing in the step 2 comprises image distortion removal, time synchronization and signal filtering.
5. The automatic driving data processing method according to claim 1, wherein the automatic driving data processing method comprises the following steps: in the step 3, a general neural network model is used for carrying out feature extraction and data fusion on external perception data to obtain a feature matrix F sensor 。
6. According to claim 1The automatic driving data processing method conforming to the data privacy safety is characterized by comprising the following steps of: in the step 3, the vehicle behavior state data is subjected to feature extraction by using a rule judgment mode to form high-dimensional state features F representing the current driving behavior, the overall running state and the position of the vehicle state ，F state The current position coordinate, the navigation destination coordinate, the navigation planning path point, the current road area, the current vehicle control action, the current vehicle state, the external traffic condition, the external weather condition and the time]。
7. The automatic driving data processing method according to claim 1, wherein the automatic driving data processing method comprises the following steps: in the step 5, a supervised learning algorithm is used for carrying out multi-stage classification on the data scene, and a semi-supervised learning method is used for carrying out semi-automatic labeling on the data.
8. The automatic driving data processing method according to claim 1, wherein the automatic driving data processing method comprises the following steps: in the step 6, U is added real And U model The absolute value of the difference between the two is used as a basic score E base ，
E adjust ＝A*E base +B*E bonus
Wherein, T is the total frame number of the data packets collected each time, A, B represents the weight of two scores respectively, and can be freely adjusted.
9. The automatic driving data processing method according to claim 1, wherein the automatic driving data processing method comprises the following steps: in the step 6, when the vehicle initiates a request for packaging the metadata into the block, all nodes compete for the metadata packaging right through a POW mechanism; the vehicle side acquiring the metadata packaging right shares subsequent data rights and interests with the data owner; when each node authenticates the data in the block chain, the information provided by the metadata synchronously searches whether the similar data exist.
10. A system for implementing a method of automated driving data processing in accordance with data privacy security as claimed in any one of claims 1 to 9, characterized by: the system comprises a communication module, a sensor module, a calculation module and a metadata storage module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210444802.6A CN114861220A (en) | 2022-04-24 | 2022-04-24 | Automatic driving data processing method and system conforming to data privacy security |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210444802.6A CN114861220A (en) | 2022-04-24 | 2022-04-24 | Automatic driving data processing method and system conforming to data privacy security |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114861220A true CN114861220A (en) | 2022-08-05 |
Family
ID=82634344
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210444802.6A Pending CN114861220A (en) | 2022-04-24 | 2022-04-24 | Automatic driving data processing method and system conforming to data privacy security |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114861220A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116664964A (en) * | 2023-07-31 | 2023-08-29 | 福思(杭州)智能科技有限公司 | Data screening method, device, vehicle-mounted equipment and storage medium |
-
2022
- 2022-04-24 CN CN202210444802.6A patent/CN114861220A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116664964A (en) * | 2023-07-31 | 2023-08-29 | 福思(杭州)智能科技有限公司 | Data screening method, device, vehicle-mounted equipment and storage medium |
| CN116664964B (en) * | 2023-07-31 | 2023-10-20 | 福思(杭州)智能科技有限公司 | Data screening method, device, vehicle-mounted equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10817731B2 (en) | Image-based pedestrian detection | |
| US11537127B2 (en) | Systems and methods for vehicle motion planning based on uncertainty | |
| Jiménez | Intelligent Vehicles: Enabling technologies and future developments | |
| JP7420734B2 (en) | Data distribution systems, sensor devices and servers | |
| CN108073170A (en) | For the automation collaborative Driving control of autonomous vehicle | |
| CN110376594A (en) | A kind of method and system of the intelligent navigation based on topological diagram | |
| CN109510851A (en) | The construction method and equipment of map datum | |
| Suryadithia et al. | Technological developments in the intelligent transportation system (ITS) | |
| Wei et al. | Survey of connected automated vehicle perception mode: from autonomy to interaction | |
| CN107316457B (en) | Method for judging whether road traffic condition accords with automatic driving of automobile | |
| CN109552211A (en) | System and method for the radar fix in autonomous vehicle | |
| Lee et al. | Building a V2X simulation framework for future autonomous driving | |
| CN114485700A (en) | High-precision dynamic map generation method and device | |
| CN107395757B (en) | Parallel vehicle networking system based on ACP method and social physical information system | |
| Yuan et al. | Harnessing machine learning for next-generation intelligent transportation systems: a survey | |
| CN114861220A (en) | Automatic driving data processing method and system conforming to data privacy security | |
| CN116457800A (en) | Architecture for map change detection in an autonomous vehicle | |
| Lee et al. | Augmenting car surrounding information by inter-vehicle data fusion | |
| EP4257443A1 (en) | Method and system for automatic driving data collection and closed-loop management | |
| Lodhia et al. | An Investigation into the Recent Developments in Intelligent Transport System | |
| CN110446106B (en) | Method for identifying front camera file, electronic equipment and storage medium | |
| CN117854284B (en) | Vehicle-road cooperative monitoring method and vehicle detector device for complex road environment | |
| Kasetti et al. | Deep Vision Net: An AI-Based System for Dynamic Traffic Scene Reconstruction and Safety Prediction with Explainable AI | |
| CN117612140B (en) | Road scene identification method and device, storage medium and electronic equipment | |
| Du | Autonomous Vehicle Technology: Global Exploration and Chinese Practice |
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 |