Multi-type data labeling system based on block chain

Abstract

The invention discloses a block chain-based multi-type data labeling system, which relates to the field of intelligent safe driving and comprises a block chain input module, a permission setting module, a real-time monitoring module, an interactive analysis module, an output comparison module and an intelligent labeling module. The block chain input module is used for establishing a relation between vehicle data, driver information and road information on a highway and a block chain system to facilitate intelligent and safe driving, and the permission setting module opens the access permission of the vehicle and user information to enter the block chain system when the vehicle enters a highway section, so that the intelligent and safe driving is facilitated. The real-time monitoring module is used for carrying out information acquisition and data interaction on all vehicles in a highway section, the real-time monitoring module comprises a road monitoring unit and a vehicle monitoring unit, the road monitoring unit is in signal connection with a road camera, and the vehicle monitoring unit is in signal connection with monitoring devices of the vehicles. According to the system, the safety of a user during vehicle driving is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent safe driving technology, and in particular to a multi-type data labeling system based on blockchain. Background Art

[0002] In recent years, artificial intelligence has developed rapidly, and intelligent driving, as an important part of strategic emerging industries, has attracted more and more attention. Intelligence will be an important trend in the automotive industry in the future. With the development of technologies such as artificial intelligence and machine learning, intelligent equipment will be combined with automobiles to realize the popularization of automotive intelligence, which will also be inseparable from the cooperation of high-tech.

[0003] Blockchain is currently an important development project. Blockchain is a chain composed of blocks. It has two core characteristics: one is that the data is difficult to tamper with, and the other is decentralization, which ensures the authenticity and reliability of the data. When it is put into use in vehicles, a blockchain can be established in batches of vehicle-mounted data to achieve data interoperability. Data labeling is also a common labeling technology in vehicle-mounted technology. It can label voice, images, text, etc. It mainly labels data sets by marking, highlighting, labeling, framing objects, and making annotations, and then these data sets are given to machine training and learning, and then put into use.

[0004] When driving on the highway, the driver may feel drowsy due to lack of rest or long driving time, which can easily cause traffic accidents. In addition to the driver's own attention, how to use other technologies to help the driver stay awake is an urgent problem to be solved by people in this field. Summary of the invention

[0005] The purpose of the present invention is to provide a multi-type data annotation system based on blockchain to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a multi-type data annotation system based on blockchain, including a blockchain input module, which is used to establish a connection between vehicle data, driver information, and road information on the highway and the blockchain system to facilitate intelligent and safe driving;

[0007] The permission setting module opens the access rights of the vehicle and user information when the vehicle enters the expressway, enters the blockchain system, and collects information and interacts with data of all vehicles on the expressway;

[0008] A real-time monitoring module, including a road monitoring unit and a vehicle monitoring unit, wherein the road monitoring unit is connected to a road camera signal, and the vehicle monitoring unit is connected to a vehicle monitoring device identification signal, thereby performing real-time monitoring of road driving safety;

[0009] An interactive analysis module, which is connected to the real-time monitoring module and the blockchain input module signal, is used to receive and analyze vehicle driving data and monitoring parameters, and provide the best driving plan for the vehicle;

[0010] The output comparison module is connected to the real-time monitoring module signal to verify whether the vehicle is driving safely;

[0011] The intelligent labeling module can perform multi-type labeling of the front and rear driving conditions according to the real-time driving status of the vehicle, and provide reports and prompts to improve driving safety.

[0012] The present invention further illustrates that it also includes an evaluation management module, which is connected to the permission setting module by signal. When the user leaves the high-speed driving section, the mobile terminal notifies the user to exit the high-speed blockchain system, and the user will make a subjective score based on the experience.

[0013] The present invention further illustrates that the blockchain input module includes:

[0014] The data annotation platform is used to store a large number of identification data types of vehicle driving status and driver status, and store multiple types of data annotation methods to adapt to different vehicle driving conditions and play a role in differentiation and warning;

[0015] The input storage module is used to input the driver information and verify it with the vehicle user information.

[0016] A method for using a multi-type data annotation system based on blockchain, characterized in that it includes the following steps:

[0017] S1: When the driver drives on the expressway, he joins the blockchain system of the expressway through permission setting. After applying to enter the driver's information, a high-speed vehicle information database is built based on blockchain technology, and on this basis, a blockchain input network is added to facilitate information exchange between vehicles on the expressway;

[0018] S2: When the vehicle is driving on the highway, the access rights in the blockchain are enabled, and the authorized mobile terminal can access the vehicle data and road data in the blockchain system, thereby obtaining real-time monitoring data;

[0019] S3: The vehicle in motion exchanges data through monitoring parameters and driving data, and analyzes the best driving plan based on the interactive data to ensure safe driving of the vehicle;

[0020] S4: Verify whether the vehicle is driving safely through the real-time monitoring module;

[0021] S5: When the user leaves the highway section, the mobile terminal notifies the user to exit the highway blockchain system. At the same time, the user will give a subjective rating based on the experience. The rating result will be fed back to the display terminal of the multi-type data annotation system, and then exit the system;

[0022] S6: The terminal collects scoring data and provides improvement directions during subsequent system testing and tuning to improve the quality of annotation.

[0023] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention establishes a high-speed vehicle information database and simultaneously forms a virtual imaging dynamic video to verify the vehicle model, license plate number, driver's name, and contact information. The data annotation platform identifies and monitors the real-time vehicle speed and the driver's driving status and updates the data to obtain the fatigue status level. According to the driver's fatigue status level, multiple types of data annotation methods are performed to remind the driver to drive the vehicle safely.

[0024] In addition, the system also calculates the danger factor of the vehicle based on the fatigue level and vehicle speed, and then determines the degree of danger and gives the best driving plan to ensure the safety of itself and others. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0026] Figure 1 It is a module schematic diagram of a multi-type data annotation system according to an embodiment disclosed in the present invention;

[0027] Figure 2 It is a flowchart of a multi-type data labeling method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The following is a further non-limiting detailed description of the technical solution of the present invention in conjunction with the preferred embodiments and the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] See also Figure 1 The present invention provides a multi-type data annotation system based on blockchain, including:

[0030] The blockchain input module is used to connect vehicle data, driver information, and road information on the highway with the blockchain system to facilitate intelligent and safe driving;

[0031] The permission setting module opens the access rights of the vehicle and user information when the vehicle enters the expressway, enters the blockchain system, and collects information and interacts with data of all vehicles on the expressway;

[0032] The real-time monitoring module includes a road monitoring unit and a vehicle monitoring unit. The road monitoring unit is connected to the road camera signal, and the vehicle monitoring unit is connected to the vehicle's monitoring device signal, thereby performing real-time monitoring of road driving safety;

[0033] The interactive analysis module is connected to the real-time monitoring module and the blockchain input module by signal, and is used to receive and analyze vehicle driving data and monitoring parameters, and at the same time provide the best driving plan for the vehicle, and upload it to the mobile terminal in the form of voice, picture or video annotation. For example, the mobile terminal can be an electronic device such as a car audio system, a mobile phone terminal or a vehicle display terminal; the electronic device in this embodiment is a mobile phone terminal;

[0034] The output comparison module is connected to the real-time monitoring module signal to verify whether the vehicle is driving safely;

[0035] The intelligent labeling module can perform multi-type labeling of the front and rear driving conditions according to the real-time driving status of the vehicle, and provide broadcast and prompt functions to improve driving safety.

[0036] The evaluation management module is connected to the permission setting module by signal. When the user leaves the high-speed driving section, the mobile terminal notifies the user to exit the high-speed blockchain system. At the same time, the user will make a subjective score based on the experience. The score can be scored on a five-point scale, and the score results will be fed back to the display terminal of the multi-type data annotation system.

[0037] The blockchain input module includes a data annotation platform and an input storage module;

[0038] The data annotation platform is used to store a large number of identification data types of vehicle driving status and driver status, and store multiple types of data annotation methods to adapt to different vehicle driving conditions and play a role in differentiation and warning. Data annotation methods include but are not limited to video annotation, image annotation, text annotation, voice annotation, etc.;

[0039] The input storage module is used to input the driver information and verify it with the vehicle user information. If the driver information is consistent with the vehicle user information, the driver information in the blockchain system is directly entered. If the driver information is inconsistent with the vehicle user information, the driver's user information is obtained from all the driving license holders nationwide through facial recognition technology to determine the driver's identity information.

[0040] Through the setting of the above system, a blockchain system for highway sections is established, and various types of data annotation methods are used to prompt users to adopt the best driving plan, thereby improving the safety of users when driving.

[0041] See also Figure 2 , Figure 2 A multi-type data annotation method based on blockchain is provided in an embodiment of the present invention. The method is executed using the multi-type data annotation system based on blockchain. The method specifically includes the following steps:

[0042] S1: When the driver drives on the expressway, he joins the blockchain system of the expressway through permission setting. After applying to enter the driver's information, a high-speed vehicle information database is built based on blockchain technology, and on this basis, a blockchain input network is added to facilitate information exchange between vehicles on the expressway;

[0043] S2: When the vehicle is driving on the highway, the access rights in the blockchain are enabled, and the authorized mobile terminal can access the vehicle data and road data in the blockchain system, thereby obtaining real-time monitoring data;

[0044] S3: The vehicle in motion exchanges data through monitoring parameters and driving data, and analyzes the best driving plan based on the interactive data to ensure safe driving of the vehicle;

[0045] S4: Verify whether the vehicle is driving safely through the real-time monitoring module;

[0046] S5: When the user leaves the highway section, the mobile terminal notifies the user to exit the highway blockchain system. At the same time, the user will give a subjective rating based on the experience. The rating result will be fed back to the display terminal of the multi-type data annotation system, and then exit the system;

[0047] S6: The terminal collects scoring data and provides improvement directions during subsequent system testing and tuning to improve the quality of annotation.

[0048] In the embodiment, fatigue driving judgment is performed. In S1, the high-speed vehicle information database is set inside the blockchain input module. The high-speed vehicle information database is composed of each vehicle information block. Each vehicle information block is a dynamic database. The internal data will be adjusted in real time. Each vehicle information block includes the vehicle model, license plate number, driver's name, contact information, real-time vehicle speed, and driver's driving status. At the same time, virtual imaging is performed on the display terminal to form a dynamic video, which includes the vehicle model, speed, position of adjacent vehicles, road dividing line and driving status. The vehicle can retrieve the virtual imaging dynamic video through permission setting;

[0049] In the dynamic video, the driver's vehicle will obtain information about vehicles within 100 to 500 meters in front and 100 to 500 meters behind. This range can be manually selected and defined as the adjacent driving range area. The speed and driving status are displayed above the corresponding vehicle in the form of text annotations;

[0050] The input storage module verifies the vehicle model, license plate number, driver's name, and contact information. The data annotation platform identifies and monitors the real-time vehicle speed and the driver's driving status and updates the data. The real-time vehicle speed is recorded as V s The driver’s driving state is recorded as T, which is the fatigue state. The fatigue state is divided into level one, level two and level three. The higher the level, the more serious it is.

[0051] The vehicle monitoring unit in the real-time monitoring module obtains vehicle speed and face data through the monitoring equipment installed in the vehicle;

[0052] The road monitoring unit in the real-time monitoring module obtains road deviation data through a road camera;

[0053] In S2, the permission setting module controls the opening of access rights, and the vehicle mobile terminal in the blockchain system of the highway section will grant access rights, which can be one-to-one or one-to-many access;

[0054] The specific methods in S3 are as follows:

[0055] S31: monitoring parameters include the opening and closing state of human eyes and road deviation data, and driving data include driving speed;

[0056] S32: The fatigue status is judged based on the eye opening and closing status and the road deviation data, and corresponding annotation methods are used to prompt, specifically:

[0057] When it is monitored that the eyes are closed for more than 2 seconds, the real-time monitoring module receives this data and further monitors this state. When it is monitored that the closed state continues for 3 times, it is identified as the first level of fatigue state, and the text is marked as T1. The real-time monitoring module is connected with the interactive analysis module signal. The interactive analysis module controls the intelligent marking module to use voice marking to give voice prompts to the driver through the mobile terminal, that is, the first type of data marking method, to remind the driver to stay awake, and at the same time suggest common ways to refresh the driver;

[0058] In the case of fatigue state level 1, if the vehicle is detected to have road deviation, that is, lane change occurs but the turn signal is not turned on, it is identified as fatigue state level 2, and the text is marked as T2. The interactive analysis module controls the intelligent marking module to intercept the image of road deviation in the virtual imaging dynamic video, mark the deviation position and fatigue state level in the image, and send it to the mobile terminal to warn the driver, which is the second type of data marking method;

[0059] The real-time monitoring module continuously monitors the opening and closing status of the human eyes and the road deviation data. If the second-level fatigue state appears again, the real-time monitoring module will upgrade the level and identify it as the third-level fatigue state, with the text annotation as T3. At this time, the interactive analysis module obtains the information of the vehicle closest to the driver in the driving range, and transmits the virtual imaging dynamic signal to the mobile terminal of the closest vehicle behind through the enabled access rights. If there are vehicles at the same distance, the signal is transmitted to the mobile terminals of multiple vehicles, indicating that the vehicle in front is in the third-level fatigue state. The intelligent annotation module informs the current driver to honk the horn to signal the vehicle in front through pictures with text and voice annotation, that is, the third type of data annotation method, to remind the vehicle in front to drive safely.

[0060] S33: Calculate the risk factor of the vehicle based on the fatigue state level and the vehicle driving speed, and then determine the degree of risk;

[0061] The risk factor is denoted as δ. i is the number corresponding to the fatigue state level. When the fatigue state is level 1, i is 1, and so on. When there is no fatigue state, i is 0. V s is the real-time speed in kilometers per hour, V s ≤120;

[0062] When δ = 0, it means that the driver is awake and the danger level is low;

[0063] When 0<δ≤0.165, it means that the driver is fatigued and driving at a low speed, the danger level is moderate, and it is easy to have a rear-end collision or cause traffic congestion of the rear vehicles;

[0064] When 0.165<δ≤0.44, it means that the driver is fatigued and the danger level is high;

[0065] When 0.44<δ≤1, it means that the driver is at a high level of fatigue or driving too fast, and the danger is serious;

[0066] S34: According to the degree of danger of the vehicle driving, the interactive analysis module will give the best driving plan and transmit it to the mobile terminal through voice annotation;

[0067] When the danger level is low, the interaction analysis module does not perform speech annotation;

[0068] When the danger level is moderate, in addition to reminding the driver to stay awake, the interactive analysis module prompts the driver to increase speed through voice annotation to prevent safety accidents;

[0069] When the danger level is high, the interactive analysis module transmits a signal to the terminal, which gives a voice prompt on the one hand, and on the other hand, the supervisor at the blockchain system terminal retrieves the vehicle's driving data and interacts with the vehicle's mobile terminal to conduct real-time voice dialogue;

[0070] When the danger level is serious, on the one hand, corresponding voice prompts are given, and on the other hand, the interactive analysis module provides the location information of the nearest service area to remind the driver to take a rest in time.

[0071] The real-time monitoring module in S4 verifies whether the vehicle is driven safely within a set period of time, that is, to ensure that the driver is not fatigued. If the driver is still fatigued, the terminal directly opens the call permission, and the supervisor communicates with the driver to ensure the safety of vehicle driving.

[0072] A scoring system is adopted in S5-S6, and the scoring items include but are not limited to satisfaction with the first type of data labeling method, satisfaction with the second type of data labeling method, satisfaction with the third type of data labeling method, satisfaction with virtual imaging dynamic video, satisfaction with fatigue monitoring method, and satisfaction with permission access, and a comprehensive score is given.

[0073] In the description of the present invention, it is necessary to understand that the terms "up", "down", "front", "back", "left", "right", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as a limitation on the present invention.

[0074] Finally, it should be pointed out that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the above embodiments, a person skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features can be replaced by equivalents, and these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-type data annotation system based on blockchain, characterized by: include: The blockchain input module is used to connect vehicle data, driver information, and road information on the highway with the blockchain system to facilitate intelligent and safe driving; The permission setting module opens the access rights of the vehicle and user information when the vehicle enters the expressway, enters the blockchain system, and collects information and interacts with data of all vehicles on the expressway; A real-time monitoring module, including a road monitoring unit and a vehicle monitoring unit, wherein the road monitoring unit is connected to a road camera signal, and the vehicle monitoring unit is connected to a vehicle monitoring device identification signal, thereby performing real-time monitoring of road driving safety; An interactive analysis module, which is connected to the real-time monitoring module and the blockchain input module signal, is used to receive and analyze vehicle driving data and monitoring parameters, and provide the best driving plan for the vehicle; The output comparison module is connected to the real-time monitoring module signal to verify whether the vehicle is driving safely; The intelligent labeling module can perform multi-type labeling of the front and rear driving conditions according to the real-time driving status of the vehicle, and provide reports and prompts to improve driving safety.

2. According to claim 1, a multi-type data annotation system based on blockchain is characterized in that: Also includes: The evaluation management module is connected to the permission setting module by signal. When the user leaves the high-speed driving section, the mobile terminal notifies the user to exit the high-speed blockchain system. At the same time, the user will make a subjective rating based on the experience.

3. According to claim 2, a multi-type data annotation system based on blockchain is characterized in that: The blockchain input module includes: The data annotation platform is used to store a large number of identification data types of vehicle driving status and driver status, and store multiple types of data annotation methods to adapt to different vehicle driving conditions and play a role in differentiation and warning; The input storage module is used to input the driver information and verify it with the vehicle user information.

4. The method for using a multi-type data annotation system based on blockchain according to claim 3 is characterized in that: The following steps are involved: S1: When the driver drives on the expressway, he joins the blockchain system of the expressway through permission setting. After applying to enter the driver's information, a high-speed vehicle information database is built based on blockchain technology, and on this basis, a blockchain input network is added to facilitate information exchange between vehicles on the expressway; S2: When the vehicle is driving on the highway, the access rights in the blockchain are enabled, and the authorized mobile terminal can access the vehicle data and road data in the blockchain system, thereby obtaining real-time monitoring data; S3: The vehicle in motion exchanges data through monitoring parameters and driving data, and analyzes the best driving plan based on the interactive data to ensure safe driving of the vehicle; S4: Verify whether the vehicle is driving safely through the real-time monitoring module; S5: When the user leaves the highway section, the mobile terminal notifies the user to exit the highway blockchain system. At the same time, the user will give a subjective rating based on the experience. The rating result will be fed back to the display terminal of the multi-type data annotation system, and then exit the system; S6: The terminal collects scoring data and provides improvement directions during subsequent system testing and tuning to improve the quality of annotation.

5. According to claim 4, a multi-type data annotation system based on blockchain is characterized in that: The high-speed vehicle information database is set inside the blockchain input module. The high-speed vehicle information database is composed of each vehicle information block. Each vehicle information block is a dynamic database, and the internal data will be adjusted in real time. Each vehicle information block includes the vehicle model, license plate number, driver's name, contact information, real-time vehicle speed, and driver's driving status. At the same time, virtual imaging is displayed on the display terminal to form a dynamic video, which includes the vehicle model, speed, position of nearby vehicles, road dividing lines and driving status. The vehicle can call up the virtual imaging dynamic video through permission settings; In the dynamic video, the driver's vehicle will obtain vehicle information within a set distance ahead. This range is selected manually and defined as the adjacent driving range area. The vehicle speed and driving status are displayed above the corresponding vehicle in the form of text annotations.

6. According to claim 5, a multi-type data annotation system based on blockchain is characterized in that: The input storage module will verify the vehicle model, license plate number, driver's name and contact information. The data annotation platform will identify and monitor the real-time vehicle speed and the driver's driving status and update the data. The real-time vehicle speed is recorded as V s The driver’s driving state is recorded as T, which is the fatigue state. The fatigue state is divided into level one, level two and level three. The higher the level, the more serious it is.

7. According to claim 6, a multi-type data annotation system based on blockchain is characterized in that: The specific method in S3 is as follows: S31: monitoring parameters include the opening and closing state of human eyes and road deviation data, and driving data include driving speed; S32: The fatigue status is judged based on the eye opening and closing status and the road deviation data, and corresponding annotation methods are used to prompt, specifically: When it is monitored that the eyes are closed for more than 2 seconds, the real-time monitoring module receives this data and further monitors this state. When it is monitored that the closed state continues for 3 times, it is identified as the first level of fatigue state, and the text is marked as T1. The real-time monitoring module is connected with the interactive analysis module signal. The interactive analysis module controls the intelligent marking module to use voice marking to give voice prompts to the driver through the mobile terminal, that is, the first type of data marking method, to remind the driver to stay awake, and at the same time suggest common ways to refresh the driver; In the case of fatigue state level 1, if the vehicle is detected to have road deviation, that is, lane change occurs but the turn signal is not turned on, it is identified as fatigue state level 2, and the text is marked as T2. The interactive analysis module controls the intelligent marking module to intercept the image of road deviation in the virtual imaging dynamic video, mark the deviation position and fatigue state level in the image, and send it to the mobile terminal to warn the driver, which is the second type of data marking method; The real-time monitoring module continuously monitors the opening and closing status of the human eyes and the road deviation data. If the second-level fatigue state appears again, the real-time monitoring module will upgrade the level and identify it as the third-level fatigue state, with the text annotation as T3. At this time, the interactive analysis module obtains the information of the vehicle closest to the driver in the driving range, and transmits the virtual imaging dynamic signal to the mobile terminal of the closest vehicle behind through the enabled access rights. If there are vehicles at the same distance, the signal is transmitted to the mobile terminals of multiple vehicles, indicating that the vehicle in front is in the third-level fatigue state. The intelligent annotation module informs the current driver to honk the horn to signal the vehicle in front through pictures with text and voice annotation, that is, the third type of data annotation method, to remind the vehicle in front to drive safely.

8. According to claim 7, a multi-type data annotation system based on blockchain is characterized in that: The S3 further includes: S33: Calculate the risk factor of the vehicle based on the fatigue state level and the vehicle driving speed, and then determine the degree of risk; The risk factor is denoted as δ. i is the number corresponding to the fatigue state level. When the fatigue state is level 1, i is 1, and so on. When there is no fatigue state, i is 0. V s is the real-time speed in kilometers per hour, V s ≤120; S34: According to the degree of danger of vehicle driving, the interactive analysis module will give the best driving plan and transmit it to the mobile terminal through voice annotation.

Images