CN112164224A - Traffic information processing system, method, device and storage medium for information security - Google Patents
Traffic information processing system, method, device and storage medium for information security Download PDFInfo
- Publication number
- CN112164224A CN112164224A CN202011052789.7A CN202011052789A CN112164224A CN 112164224 A CN112164224 A CN 112164224A CN 202011052789 A CN202011052789 A CN 202011052789A CN 112164224 A CN112164224 A CN 112164224A
- Authority
- CN
- China
- Prior art keywords
- module
- data
- traffic information
- user
- federal learning
- 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.)
- Withdrawn
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
-
- 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
- G06F21/602—Providing cryptographic facilities or services
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
- G08G1/096708—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control
- G08G1/096725—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control where the received information generates an automatic action on the vehicle control
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Atmospheric Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
Abstract
A traffic information processing system, device and storage medium for information security, the system includes vehicle end and central end; the vehicle end comprises a data acquisition module, a local processing module, a local storage module, a federal learning module, a judger, a communication module and a human-computer interaction module; the central end comprises a federal learning center module and a communication module. The system adopts a federal learning mode, better processes traffic information collected by the sensor, enriches the quantity of data, protects the privacy of users, improves the overall model recognition level and vehicle control level, and improves the information safety level. According to the invention, safe federal learning of privacy is adopted, and privacy is protected by encryption operation, so that images acquired by an intelligent automobile are not transmitted to a central end, and the privacy of users is protected. According to the invention, a user participates in confirming and labeling data arrangement and analysis results, the improved model is detected, the detection result requires the user to confirm, and the recognition level and the vehicle control level of the model are increased.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to a traffic information processing system, a method, equipment and a storage medium for information safety.
Background
Automatic driving or assisted driving (hereinafter referred to as intelligent automobile) requires continuous improvement of algorithm to improve recognition accuracy and steering accuracy. The information transmitted from each sensor needs to be processed continuously, the images collected by the camera are collected into the cloud picture from the LIDAR, and position information, weather, temperature and humidity, driving control signals are also collected, key information such as road condition information, traffic signals, traffic signs, road signs, pedestrians, vehicles, obstacles and the like is identified, and the automobile action is controlled according to the key information.
At present, more and more intelligent automobiles provided with automatic driving facilities have stronger and stronger requirements on data, and the privacy safety problem is also more and more serious.
The market needs a system which can protect privacy and can fully utilize user data to improve a recognition model algorithm so as to improve the automatic driving control capability to be assembled in an intelligent automobile.
In addition, in order to achieve the purpose of improving the model algorithm, different data are collected and processed in the operation process of automobiles produced by each automobile factory, and part of processing is used for executing a driving task, and part of information is collected and uploaded to a central server, and then algorithm optimization processing is performed. According to the published documents, a plurality of manufacturers upload data collected by automobiles to a central server for subsequent model optimization processing. At this time, many data related to personal privacy or other sensitive data can be transmitted to a manufacturer server, and information leakage is hidden.
Sometimes, the user person cannot identify whether the privacy of the user person is related to sensitive data, and a single user protocol actually substantially infringes the authority of the user. Secondly, when a certain manufacturer grasps a large amount of extra hand data, the whole social security is threatened.
Disclosure of Invention
The invention aims to provide a traffic information processing system, a traffic information processing method, traffic information processing equipment and a storage medium for information safety.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a traffic information processing system with information safety, which comprises a vehicle end and a center end, wherein the vehicle end is connected with the center end;
the vehicle end comprises a data acquisition module, a local processing module, a local storage module, a federal learning module, a judger, a communication module and a man-machine interaction module;
the data acquisition module acquires various data;
the local processing module is used for analyzing the acquired data to obtain an analysis result so as to generate a control signal;
the local storage module is used for storing data needing to be subjected to federal learning;
the federal learning module is used for performing federal learning to obtain an improved model;
the judger judges to take corresponding operation according to the condition preset by the system;
the human-computer interaction module is used for interaction between a user and a vehicle end;
the central end comprises a federal learning center module and a communication module;
and the federal learning center module is used for coordinating each user to carry out a federal learning improvement model.
Further, the data acquisition module includes a plurality of sensors for acquiring environmental data and vehicle data.
Furthermore, the local processing module preprocesses the acquired data, and performs data analysis and recognition calculation.
Furthermore, the central end also comprises a central end local processing module and a central end local storage module;
the central end local processing module is used for preprocessing the acquired data;
the central end local storage module is used for storing the acquired original data, the preprocessed data and/or the result data.
Further, the center terminal further comprises a model evaluation module for evaluating the effectiveness of the improved model.
Furthermore, the center end further comprises a man-machine interaction module used for interaction between the user and the center end.
The second aspect of the present invention provides a traffic information processing method for information security, which uses the system as described above to process, and includes the following steps:
preprocessing the data acquired by the data acquisition module;
preprocessing the preprocessed data by machine learning data;
analyzing the graphic image and identifying and calculating to obtain an analysis and calculation result, and transmitting the analysis and calculation result to a judger;
the judger judges the analysis and calculation result according to the preset conditions and gives out corresponding operation instructions;
according to preset conditions, federal learning is started after the conditions are met;
and communicating with the central terminal to complete federal learning to obtain an improved model.
Further, the method also comprises the steps of carrying out local verification on the improved model, and reading data of a local storage module for verification.
And further, the method also comprises the step of sending the result obtained by the improved model calculation to a user for result confirmation through a human-computer interaction module at the vehicle end.
Further, the method also comprises submitting the verified model to the central terminal.
The method further comprises the steps that the judger carries out calculation according to the improved model to obtain a calculation result, data needing to be judged by a user are selected, and the user is requested to judge and/or mark through the human-computer interaction module at the vehicle end when appropriate, so that the model is further improved.
Further, the method also comprises the following steps: prompting the user whether the data and/or the calculation result can be uploaded to the central terminal, and/or prompting the user to label the data, and/or giving the user a corresponding reward.
Further, the preset conditions include: the vehicle is in a charging state and has a network connection.
A third aspect of the present invention provides an information-safe traffic information processing apparatus, including:
a memory and one or more processors;
wherein the memory is communicatively coupled to the one or more processors and has stored therein instructions executable by the one or more processors to cause the one or more processors to perform the method as previously described.
A fourth aspect of the invention provides a computer-readable storage medium having stored thereon computer-executable instructions operable, when executed by a computing device, to perform a method as previously described.
In summary, the present invention provides a traffic information processing system, a device and a storage medium for information security, the system includes a vehicle end and a center end; the vehicle end comprises a data acquisition module, a local processing module, a local storage module, a federal learning module, a judger, a communication module and a human-computer interaction module; the central end comprises a federal learning center module and a communication module. The system is arranged between traffic information vehicles, the vehicles and the center are mutually cooperated, a federal learning mode is adopted, the traffic information collected by the sensor is better processed, the number of data is enriched, the privacy of a user is protected, the overall model recognition level and the vehicle control level are improved, and the information safety level is improved.
The invention has the beneficial technical effects that:
1. by adopting the federal study with safe privacy and the encryption operation to protect the privacy, the image collected by the intelligent automobile can not be sent to the central end, the privacy of the user is protected, and the overall safety level of the system is improved.
2. And the user participates in confirming and labeling data sorting and analyzing results, the improved model is detected, the detection result is confirmed by the user, and the recognition level and the vehicle control level of the model are increased.
3. Meanwhile, users are involved in a model improvement link, accuracy is improved, the problem of calculation result deviation possibly existing in federal learning is avoided, and users are involved to ensure the right of awareness of the users.
Drawings
FIG. 1 is a schematic diagram of a vehicle-side structure of a traffic information processing system for information security according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a central end of a traffic information processing system for information security according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a central end of a traffic information processing system for information security according to another embodiment of the present invention;
FIG. 4 is a schematic diagram of a central end of a traffic information processing system for information security according to another embodiment of the present invention;
FIG. 5 is a flow chart illustrating a traffic information processing method for information security according to an embodiment of the present invention;
FIG. 6 is a flow chart illustrating a traffic information processing method for information security according to an embodiment of the present invention;
fig. 7 is a flowchart illustrating a traffic information processing method for information security according to another embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings in conjunction with the following detailed description. It should be understood that the description is intended to be exemplary only, and is not intended to limit the scope of the present invention. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present invention.
A first aspect of the present invention provides an information-safe traffic information processing system, as shown in fig. 1, including a vehicle end and a center end; the vehicle end comprises a data acquisition module, a local processing module, a local storage module, a federal learning module, a judger, a communication module and a human-computer interaction module.
The data acquisition module acquires various data, and comprises a plurality of sensors for acquiring environmental data and vehicle data. For example, a camera sensor for acquiring image video data; the LIDAR laser scanning sensor is used for acquiring cloud picture data; the position sensor is used for acquiring the coordinates, the direction, the acceleration, the altitude and the like of the current position; the temperature and humidity sensor is used for acquiring the current temperature and humidity; the sensors of the power system in the vehicle are various sensor resources provided by a control bus, OBD CBUS, in the vehicle; and other in-vehicle configured sensors: the load capacity of the vehicle is the number of people, the load capacity, the wind direction, the wind power, the time, the weather and the like.
The local processing module is used for analyzing the acquired data to obtain an analysis result so as to generate a control signal. Specifically, the local processing module is used for processing signals of the sensors to analyze, and obtaining an analysis result, so that the local processing module is used for controlling driving of the intelligent automobile. The local processing module adopts a deep learning model algorithm to analyze and recognize; the system also comprises a data preprocessing function, which is mainly used for preprocessing the data of each sensor and further processing the data so as to facilitate identification and calculation.
And the judger takes action according to the conditions preset by the system and judges the current graphic label and the recognition confidence coefficient. The judger mainly obtains the data outside and inside the vehicle, obtains the value from the sensor, judges whether the collision happens, whether overtaking and combining, whether raining, fogging, driving time length and the like.
The local storage module is used for storing data required to be subjected to federal learning. The relevant data is saved locally without uploading and is preprocessed to prepare for subsequent federal learning data analysis. The federal learning module is used for federal learning to obtain an improved model, and the improved model comprises an encrypted mode and a non-encrypted mode. The communication module is used for communicating with the outside, including communicating with a central terminal, communicating with a mobile terminal and the like. The man-machine interaction module is used for interaction between a user and a vehicle end, and prompts the user to select and confirm the marked original graph, video, image, mark, model operation result, possible privacy prompt and processing mode result, so that the user privacy is protected, and the user is encouraged to participate in model training and improvement.
Specifically, a camera acquires a front image, a sensor acquires the current illumination intensity and the current rain state, and a local calculation module is used for preprocessing, preprocessing machine learning data and using a current pattern recognition algorithm. A recognition result is obtained, which includes the recognized target information, confidence, location, and various tag information, such as whether the tag information is currently raining. The GPS information is used as a sensor, and a traffic light is arranged at the position of 100 meters of the target obtained by the basic map information. For example, the current position is Hangzhou, which corresponds to the basic shape of the signal lamp. The judger is internally provided with a current rule, for example, the current rule is used for identifying signal lamps, the brightness is lower than 100 lumens in rainy days, and if the confidence coefficient is lower than 80%, the data needs to be collected to update the model. And the local storage module obtains various data, original data, preprocessed data and label data (raining) corresponding to the recognition result from the local calculation module under the instruction of the judger, and processes the data and the label data to prepare for federal learning. And when the federal learning condition is prepared, connecting the central system and starting to perform federal learning. After learning is completed, an improved algorithm model is obtained. The improved algorithmic model will be validated locally. And during verification, data is extracted from the local storage module for verification. The result of the verification is displayed on the man-machine interaction interface and confirmed by the user. After the model is confirmed to have the effect, the preprocessing of machine learning data, an image recognition algorithm and a judger in the local calculation module can be improved. To improve the accuracy of the calculation.
As shown in fig. 2, the central end includes a federal learning center module and a communication module; the federal learning center module is used for coordinating each user to carry out a federal learning improvement model; the communication module is used for communicating with the outside.
Further, as shown in fig. 3, in a specific embodiment, the vehicle end is unchanged, and the center end is added with a center-end local processing module and a center-end local storage module. The central end local processing module is used for preprocessing the data acquired by the central end; the central end local storage module is used for storing the acquired original data, the preprocessed data and/or the result data. The effect of adding these components at the center end is to simulate the vehicle end to provide more effective data to facilitate model refinement updates. Because the federal learning needs the participation of the vehicle terminals participating in the learning, but the vehicles can not participate in many cases, the federal learning effect is influenced, the problem can be solved to a great extent by providing a function of the vehicle terminals by the central terminal, and the function of the central terminal is always on line and can participate in the federal learning.
Further, as shown in fig. 3, the central end further includes a human-computer interaction module, which is used for interaction between a user and the central end.
Further, as shown in fig. 4, in a specific embodiment, the center further includes a model evaluation module for evaluating the effectiveness of the improved model. The center end is provided with a central local storage module, a man-machine interaction module, a federal learning center module, a model evaluation module and a communication module for better improving the model algorithm. Because the mobility of the vehicle and the data amount required by calculation may influence, a memory is also deployed at the central end, labeled and processed data obtained from other channels are stored, federal learning is carried out by matching with a vehicle client, meanwhile, an obtained model is also evaluated at the central end, personnel evaluate the model through a human-computer interaction module to confirm the effect of the model, and the verified and improved model algorithm is downloaded to the intelligent vehicle through an OTA (over the air) mode to carry out algorithm upgrading. The central human-machine interface can review that the central system receives data actively submitted by the user for improving the model, and can give rewards to the user.
A second aspect of the present invention provides a traffic information processing method for information security, which uses the system as described above to perform processing, as shown in fig. 5, and includes the following steps:
and S100, preprocessing the data acquired by the data acquisition module.
And step S200, performing machine learning data preprocessing on the preprocessed data.
And step S300, analyzing the graphic image, identifying and calculating to obtain an analysis calculation result, and transmitting the analysis calculation result to a judger.
And step S400, the judger judges the analysis and calculation result according to the preset conditions and gives a corresponding operation instruction.
And step S500, according to preset conditions, after the conditions are met, federal learning is started.
And S600, communicating with the central terminal to complete federal learning to obtain an improved model.
The method is further illustrated with a specific example. As shown in fig. 6, a traffic information processing method for information security includes the steps of:
1. the first step is as follows: and preprocessing the data acquired by each sensor, and removing the operations such as interference, signal filtering and the like according to the characteristics of the sensors.
2. The second step is that: and preprocessing machine learning data, wherein preprocessing comprises unifying and standardizing the image data and the cloud picture, secondarily reducing noise, reducing dimensionality, enhancing data and the like so as to facilitate machine learning.
3. The third step: and analyzing the graphic images, and performing identification calculation by adopting a basic identification algorithm.
4. The fourth step: and obtaining the identification result, transmitting the identification result to a judger and an execution mechanism of the intelligent automobile, executing actions according to the execution result, for example, identifying obstacles in the middle of the road, prompting to give an alarm, and taking measures such as steering, deceleration and the like according to other information.
The first four steps are functions of the common intelligent automobile.
5. The fifth step: and the judger confirms whether the local storage module reserves the original data corresponding to the judgment result or not according to the identification result, namely the data obtained by the machine learning data preprocessing. If the predefined condition is met, saving is performed.
6. And 6, step 6: the judger tells the local storage module to save the data according to the judgment result.
7. And 7, step 7: the local storage module stores data from the related module according to the instruction of the judger and preprocesses the data so as to facilitate the subsequent federal study under the confidential condition.
8. And 8, step 8: and starting to carry out federal learning according to preset conditions when the conditions are met.
9. Step 9: and communicate with a central system to accomplish federal learning.
10. Step 10: and completing federal learning to obtain an improved algorithm model.
11. And 11, step 11: and the algorithm model starts to verify locally, and the data of the local storage module is read to start to verify.
12. Step 12 is optional. And the model effect requests the user to confirm through a human-computer interface.
13. And step 13, the verified model is used for improving a data preprocessing module of machine learning, a graph and image recognition algorithm and a judger.
14. Step 14 is optional. And submitting the verified model to a central system.
15. Step 15, optional (not shown), the judger selects pictures to be judged by the user according to the model calculation result, and requests the user to judge and mark when appropriate. (either before or after federal learning) and further based on user judgment and labeling, for improving the model algorithm.
16. Step 16 is optional (not shown), and prompts the user whether the user can upload to the central system. If so, the system gives the user a corresponding reward.
Wherein the condition for starting the federal learning is preset. For example: the vehicle is in a charging state, has enough energy supply and network connection, and is in a safe state.
And starting the state judged by the user, wherein the vehicle is in a safe stop state. Such as: and in a charging state, the vehicle is in a safe parking lot.
The method is further illustrated with another specific example. As shown in fig. 7, a traffic information processing method for information security includes the steps of:
the first step is as follows: the car sensor detects that charging is started/refueling is started/the vehicle is in a safe state.
The second step is that: and the system judger judges whether the user participates in the annotation verification, the user data sharing, the federal learning model improvement and the working condition is met. For example, depending on the length of the charging time, or user intent; according to the current network connection state with the central system; depending on how much data is currently available for calculation in the local data store, or other predetermined conditions.
The third step: the human-computer interaction interface prompts a user whether to start to participate in annotation verification or not, the user starts to annotate, the system extracts pictures from the local storage module according to the rule of the judger, asks the user to annotate and records an annotation result, the system extracts the pictures from the local storage module according to the rule of the judger, calculates the result by using a model algorithm, asks the user to confirm and records a confirmation result.
The system extracts pictures from the local storage module according to the judger's rules, makes appropriate processing annotations for confirmation by the user, and may provide uploads for model improvement. And performing subsequent operation after the user confirms.
The system initiates a federal learning model improvement based on the rules of the judgers.
The fourth step: the system receives the user's contribution content and awards the user, for example: the price charged by the user may be discounted, providing the user with an incentive electronic token.
In the third step, the man-machine interface can be pushed to a terminal such as a user mobile phone through the communication module for operation.
Further, the judger of the system starts the analysis of the driving instruction model when the conditions are proper (when the vehicle is charged and refueled), analyzes and considers the historical data (accelerator and accelerator are added and reduced, and the record of overtaking is combined, the speed smoothness, the position and the road condition) of the driving record (including automatic driving) of the driver after the user agrees, and prompts the user to input the riding feeling. And carrying out federal learning analysis to obtain a better vehicle control instruction set model, so as to provide better driving for a user.
A third aspect of the present invention provides an information-safe traffic information processing apparatus, including:
a memory and one or more processors;
wherein the memory is communicatively coupled to the one or more processors and has stored therein instructions executable by the one or more processors to cause the one or more processors to perform the method as previously described.
A fourth aspect of the invention provides a computer-readable storage medium having stored thereon computer-executable instructions operable, when executed by a computing device, to perform a method as previously described.
In summary, the present invention provides a traffic information processing system, a device and a storage medium for information security, the system includes a vehicle end and a center end; the vehicle end comprises a data acquisition module, a local processing module, a local storage module, a federal learning module, a communication module and a man-machine interaction module; the central end comprises a federal learning center module and a communication module. The system is arranged between traffic information vehicles, the vehicles and the center are mutually cooperated, a federal learning mode is adopted, the traffic information collected by the sensor is better processed, the number of data is enriched, the privacy of a user is protected, the overall model recognition level and the vehicle control level are improved, and the information safety level is improved. According to the invention, by adopting federal learning with safe privacy, protecting the privacy by using an encryption operation means and performing model training by using aggregated data, different types of original data such as images, temperature, speed and the like collected by an intelligent automobile can not be sent to a central end, so that the privacy of a user is protected. According to the invention, a user participates in confirming and labeling data arrangement and analysis results, the improved model is detected, the detection result requires the user to confirm, and the recognition level and the vehicle control level of the model are increased.
It is to be understood that the above-described embodiments of the present invention are merely illustrative of or explaining the principles of the invention and are not to be construed as limiting the invention. Therefore, any modification, equivalent replacement, improvement and the like made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. Further, it is intended that the appended claims cover all such variations and modifications as fall within the scope and boundaries of the appended claims or the equivalents of such scope and boundaries.
Claims (15)
1. The traffic information processing system for information security is characterized by comprising a vehicle end and a center end;
the vehicle end comprises a data acquisition module, a local processing module, a local storage module, a federal learning module, a judger, a communication module and a man-machine interaction module;
the data acquisition module acquires various data;
the local processing module is used for analyzing the acquired data to obtain an analysis result so as to generate a control signal;
the local storage module is used for storing data needing to be subjected to federal learning;
the federal learning module is used for performing federal learning to obtain an improved model;
the judger judges to take corresponding operation according to the condition preset by the system;
the human-computer interaction module is used for interaction between a user and a vehicle end;
the central end comprises a federal learning center module and a communication module;
and the federal learning center module is used for coordinating each user to carry out a federal learning improvement model.
2. The information-safe traffic information handling system of claim 1, wherein the data collection module includes a plurality of sensors for collecting environmental data and vehicle data.
3. The information-safe traffic information processing system according to claim 1 or 2, wherein the local processing module preprocesses the collected data, performs data analysis and recognition calculation.
4. The information-safe traffic information processing system according to any one of claims 1 to 3, wherein the central terminal further includes a central terminal local processing module and a central terminal local storage module;
the central end local processing module is used for preprocessing the acquired data;
the central end local storage module is used for storing the acquired original data, the preprocessed data and/or the result data.
5. The information-safe traffic information processing system of claim 4, wherein the central end further comprises a model evaluation module for evaluating the effectiveness of the improved model.
6. The traffic information processing system for information security according to claim 4 or 5, wherein the central terminal further comprises a human-computer interaction module for interaction between a user and the central terminal.
7. An information-safe traffic information processing method characterized by being processed by the system according to any one of claims 1 to 6, comprising the steps of:
preprocessing the data acquired by the data acquisition module;
preprocessing the preprocessed data by machine learning data;
analyzing the graphic image and identifying and calculating to obtain an analysis and calculation result, and transmitting the analysis and calculation result to a judger;
the judger judges the analysis and calculation result according to the preset conditions and gives out corresponding operation instructions;
according to preset conditions, federal learning is started after the conditions are met;
and communicating with the central terminal to complete federal learning to obtain an improved model.
8. The information-safe traffic information processing method according to claim 7, further comprising performing local verification on the improved model, and performing verification by reading data of the local storage module.
9. The traffic information processing method for information security according to claim 7 or 8, further comprising sending the result obtained by the improved model calculation to a user for result confirmation through a human-computer interaction module at the vehicle end.
10. The information-safe traffic information processing method according to claim 9, further comprising submitting the verified model to the center.
11. The traffic information processing method for information security according to claim 7, further comprising the steps of calculating by the judger according to the improved model to obtain a calculation result, selecting data to be judged by the user, and requesting the user to make judgment and/or marking for further improving the model through the human-computer interaction module at the vehicle side when appropriate.
12. The information-safe traffic information processing method according to claim 11, further comprising: prompting the user whether the data and/or the calculation result can be uploaded to the central terminal, and/or prompting the user to label the data, and/or giving the user a corresponding reward.
13. The information-safe traffic information processing method according to claim 7, wherein the preset condition includes: the vehicle is in a charging state and has a network connection.
14. An information-secured traffic information processing apparatus, characterized by comprising:
a memory and one or more processors;
wherein the memory is communicatively coupled to the one or more processors and has stored therein instructions executable by the one or more processors to cause the one or more processors to perform the method of any of claims 7-13.
15. A computer-readable storage medium having stored thereon computer-executable instructions operable, when executed by a computing device, to perform the method of any of claims 7-13.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011052789.7A CN112164224A (en) | 2020-09-29 | 2020-09-29 | Traffic information processing system, method, device and storage medium for information security |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011052789.7A CN112164224A (en) | 2020-09-29 | 2020-09-29 | Traffic information processing system, method, device and storage medium for information security |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112164224A true CN112164224A (en) | 2021-01-01 |
Family
ID=73860949
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011052789.7A Withdrawn CN112164224A (en) | 2020-09-29 | 2020-09-29 | Traffic information processing system, method, device and storage medium for information security |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112164224A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113345229A (en) * | 2021-06-01 | 2021-09-03 | 平安科技（深圳）有限公司 | Road early warning method based on federal learning and related equipment thereof |
| CN113448606A (en) * | 2021-06-29 | 2021-09-28 | 重庆长安汽车软件科技有限公司 | Vehicle OTA (over the air) upgrade safety control method, system, terminal equipment and storage medium based on map data |
| CN113973125A (en) * | 2021-10-26 | 2022-01-25 | 杭州博盾习言科技有限公司 | Communication method and device in federal learning, electronic equipment and storage medium |
Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104063713A (en) * | 2014-07-04 | 2014-09-24 | 中国地质大学（武汉） | Semi-autonomous on-line studying method based on random fern classifier |
| CN109389044A (en) * | 2018-09-10 | 2019-02-26 | 中国人民解放军陆军工程大学 | More scene crowd density estimation methods based on convolutional network and multi-task learning |
| US20200027019A1 (en) * | 2019-08-15 | 2020-01-23 | Lg Electronics Inc. | Method and apparatus for learning a model to generate poi data using federated learning |
| CN110765960A (en) * | 2019-10-29 | 2020-02-07 | 黄山学院 | Pedestrian re-identification method for adaptive multi-task deep learning |
| CN110796266A (en) * | 2019-10-30 | 2020-02-14 | 深圳前海微众银行股份有限公司 | Method, device and storage medium for implementing reinforcement learning based on public information |
| CN111008704A (en) * | 2019-11-29 | 2020-04-14 | 上海能塔智能科技有限公司 | Processing method, device, equipment and storage medium for federal learning of electric vehicle |
| CN111126609A (en) * | 2019-12-20 | 2020-05-08 | 深圳前海微众银行股份有限公司 | Knowledge migration method, device, equipment and medium based on federal learning |
| CN111290381A (en) * | 2020-02-10 | 2020-06-16 | 深圳前海微众银行股份有限公司 | Federal learning experiment system based on unmanned vehicle |
| CN111401563A (en) * | 2018-12-28 | 2020-07-10 | 杭州海康威视数字技术股份有限公司 | Machine learning model updating method and device |
| CN111428881A (en) * | 2020-03-20 | 2020-07-17 | 深圳前海微众银行股份有限公司 | Recognition model training method, device, equipment and readable storage medium |
| CN111459787A (en) * | 2019-01-18 | 2020-07-28 | 南京大学 | Test plagiarism detection method based on machine learning |
| CN111476139A (en) * | 2020-04-01 | 2020-07-31 | 同济大学 | Driver behavior cloud-side collaborative learning system based on federal transfer learning |
| CN111477290A (en) * | 2020-03-05 | 2020-07-31 | 上海交通大学 | Federal learning and image classification method, system and terminal for protecting user privacy |
| CN111539469A (en) * | 2020-04-20 | 2020-08-14 | 东南大学 | Weak supervision fine-grained image identification method based on vision self-attention mechanism |
| CN111538598A (en) * | 2020-04-29 | 2020-08-14 | 深圳前海微众银行股份有限公司 | Federal learning modeling method, device, equipment and readable storage medium |
| CN111598098A (en) * | 2020-05-09 | 2020-08-28 | 河海大学 | Water gauge water line detection and effectiveness identification method based on full convolution neural network |
| CN111597420A (en) * | 2020-04-29 | 2020-08-28 | 西安理工大学 | Deep learning-based rail transit standard relation extraction method |
| CN111611610A (en) * | 2020-04-12 | 2020-09-01 | 西安电子科技大学 | Federal learning information processing method, system, storage medium, program, and terminal |
| CN111612168A (en) * | 2020-06-30 | 2020-09-01 | 腾讯科技（深圳）有限公司 | Management method and related device for machine learning task |
| CN111680708A (en) * | 2019-03-18 | 2020-09-18 | 上海铼锶信息技术有限公司 | Method and system for tagging pictures |
| CN111695696A (en) * | 2020-06-12 | 2020-09-22 | 深圳前海微众银行股份有限公司 | Method and device for model training based on federal learning |
-
2020
- 2020-09-29 CN CN202011052789.7A patent/CN112164224A/en not_active Withdrawn
Patent Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104063713A (en) * | 2014-07-04 | 2014-09-24 | 中国地质大学（武汉） | Semi-autonomous on-line studying method based on random fern classifier |
| CN109389044A (en) * | 2018-09-10 | 2019-02-26 | 中国人民解放军陆军工程大学 | More scene crowd density estimation methods based on convolutional network and multi-task learning |
| CN111401563A (en) * | 2018-12-28 | 2020-07-10 | 杭州海康威视数字技术股份有限公司 | Machine learning model updating method and device |
| CN111459787A (en) * | 2019-01-18 | 2020-07-28 | 南京大学 | Test plagiarism detection method based on machine learning |
| CN111680708A (en) * | 2019-03-18 | 2020-09-18 | 上海铼锶信息技术有限公司 | Method and system for tagging pictures |
| US20200027019A1 (en) * | 2019-08-15 | 2020-01-23 | Lg Electronics Inc. | Method and apparatus for learning a model to generate poi data using federated learning |
| CN110765960A (en) * | 2019-10-29 | 2020-02-07 | 黄山学院 | Pedestrian re-identification method for adaptive multi-task deep learning |
| CN110796266A (en) * | 2019-10-30 | 2020-02-14 | 深圳前海微众银行股份有限公司 | Method, device and storage medium for implementing reinforcement learning based on public information |
| CN111008704A (en) * | 2019-11-29 | 2020-04-14 | 上海能塔智能科技有限公司 | Processing method, device, equipment and storage medium for federal learning of electric vehicle |
| CN111126609A (en) * | 2019-12-20 | 2020-05-08 | 深圳前海微众银行股份有限公司 | Knowledge migration method, device, equipment and medium based on federal learning |
| CN111290381A (en) * | 2020-02-10 | 2020-06-16 | 深圳前海微众银行股份有限公司 | Federal learning experiment system based on unmanned vehicle |
| CN111477290A (en) * | 2020-03-05 | 2020-07-31 | 上海交通大学 | Federal learning and image classification method, system and terminal for protecting user privacy |
| CN111428881A (en) * | 2020-03-20 | 2020-07-17 | 深圳前海微众银行股份有限公司 | Recognition model training method, device, equipment and readable storage medium |
| CN111476139A (en) * | 2020-04-01 | 2020-07-31 | 同济大学 | Driver behavior cloud-side collaborative learning system based on federal transfer learning |
| CN111611610A (en) * | 2020-04-12 | 2020-09-01 | 西安电子科技大学 | Federal learning information processing method, system, storage medium, program, and terminal |
| CN111539469A (en) * | 2020-04-20 | 2020-08-14 | 东南大学 | Weak supervision fine-grained image identification method based on vision self-attention mechanism |
| CN111538598A (en) * | 2020-04-29 | 2020-08-14 | 深圳前海微众银行股份有限公司 | Federal learning modeling method, device, equipment and readable storage medium |
| CN111597420A (en) * | 2020-04-29 | 2020-08-28 | 西安理工大学 | Deep learning-based rail transit standard relation extraction method |
| CN111598098A (en) * | 2020-05-09 | 2020-08-28 | 河海大学 | Water gauge water line detection and effectiveness identification method based on full convolution neural network |
| CN111695696A (en) * | 2020-06-12 | 2020-09-22 | 深圳前海微众银行股份有限公司 | Method and device for model training based on federal learning |
| CN111612168A (en) * | 2020-06-30 | 2020-09-01 | 腾讯科技（深圳）有限公司 | Management method and related device for machine learning task |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113345229A (en) * | 2021-06-01 | 2021-09-03 | 平安科技（深圳）有限公司 | Road early warning method based on federal learning and related equipment thereof |
| CN113345229B (en) * | 2021-06-01 | 2022-04-19 | 平安科技（深圳）有限公司 | Road early warning method based on federal learning and related equipment thereof |
| CN113448606A (en) * | 2021-06-29 | 2021-09-28 | 重庆长安汽车软件科技有限公司 | Vehicle OTA (over the air) upgrade safety control method, system, terminal equipment and storage medium based on map data |
| CN113448606B (en) * | 2021-06-29 | 2022-11-18 | 重庆长安汽车软件科技有限公司 | Vehicle OTA (over the air) upgrade safety control method, system, terminal equipment and storage medium based on map data |
| CN113973125A (en) * | 2021-10-26 | 2022-01-25 | 杭州博盾习言科技有限公司 | Communication method and device in federal learning, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112164224A (en) | Traffic information processing system, method, device and storage medium for information security | |
| US20170248441A1 (en) | Assistance When Driving a Vehicle | |
| JP7420734B2 (en) | Data distribution systems, sensor devices and servers | |
| KR102037459B1 (en) | Vehicle monitoring system using sumulator | |
| CN104494534A (en) | Vehicle transportation management system and method | |
| CN111127282B (en) | System and method for determining recommended locations | |
| CN110531752A (en) | Crowdsourcing construction area detection for the maintenance of autonomous vehicle map | |
| CN116391161A (en) | In-vehicle operation simulating a scenario during autonomous vehicle operation | |
| CN114935334B (en) | Construction method and device of lane topological relation, vehicle, medium and chip | |
| CN112509321A (en) | Unmanned aerial vehicle-based driving control method and system for urban complex traffic situation and readable storage medium | |
| CN113611007B (en) | Data processing method and data acquisition system | |
| CN111433779A (en) | System and method for identifying road characteristics | |
| CN114331490A (en) | Price estimation server, price estimation system, and recording medium | |
| CN114639260A (en) | Intelligent interaction method, interaction system and computer readable medium for vehicles | |
| CN113591744A (en) | Generation method of labeled data for dangerous driving behaviors and data acquisition system | |
| CN113099385A (en) | Parking monitoring method, system and equipment | |
| CN113574529A (en) | Shielding method and device | |
| CN106710270A (en) | Processing method and device for vehicle driving data | |
| EP3425607A1 (en) | Mobile body management device, mobile body management method and storage medium | |
| CN113628360B (en) | Data acquisition method and system | |
| TWI831336B (en) | Driving record authentication method, electronic device, storage medium, vehicle | |
| US11625767B2 (en) | Information processing apparatus, information processing method and non-transitory recording medium | |
| CN114842653B (en) | Highway violation auxiliary determination method and system, storage medium and monitoring system | |
| US20240061917A1 (en) | Driving record authentication method, electronic device, storage medium | |
| CN114331489A (en) | Portable terminal, price estimation system, and recording medium |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210101 |
|
| WW01 | Invention patent application withdrawn after publication |