Big data analysis system and method based on cloud computing

Abstract

The invention relates to the technical field of intelligent driving, in particular to a big data analysis system and method based on cloud computing, and the system comprises a collection layer, an analysis layer and a control layer. The system integrated by the acquisition layer, the analysis layer and the control layer is applied to a highway driving scene in which a vehicle with an automatic driving function is switched from autonomous driving to automatic driving; according to the invention, the historical driving state parameters of the vehicle are uploaded through the acquisition layer, and the data cleaning and storage are executed in the acquisition layer, and through the uploading of the historical driving state parameters of the vehicle and the acquisition of the current driving environment state parameters of the vehicle, the response time efficiency of a vehicle driving user and the optimal driving position of the vehicle are analyzed; in the high-speed driving process of the vehicle, an automatic vehicle driving system is assisted on the basis of the optimal driving position and the driving user response time as the logic basis, so that the vehicle which starts automatic driving can automatically drive at the position which is safer relative to surrounding vehicle obstacles.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to a big data analysis system and method based on cloud computing. Background Art

[0002] Autonomous driving is the use of advanced sensors, computer technology and artificial intelligence to enable vehicles to drive automatically without human intervention. It can sense the surrounding environment, make decisions and control vehicle movements to improve driving safety and efficiency. Currently, it is divided into different levels and is gradually maturing, changing the way of travel in the future.

[0003] The invention patent with application number 202410514054.3 discloses a data analysis method for autonomous driving, which is characterized by including: receiving multiple compiled video files generated by the autonomous driving end by encoding frame by frame the multiple original video data respectively shot by multiple cameras during the autonomous driving process using the GPU; determining the target decoding method according to the obtained decoding configuration file corresponding to the user data analysis requirements; decoding the multiple compiled video files in the target decoding method to obtain multiple decoded video data; performing data analysis based on the multiple decoded video data to generate data analysis results of the autonomous driving process.

[0004] The application aims to solve the problem that: "In the traditional data analysis process, since the input of the model training and online perception modules are all frames of image information, and a single image is also the data that is easiest to display on various platforms, the original image output by the camera is usually compressed into a Jpeg image for storage. However, this will cause certain problems. First, we need to use a separate process to use the GPU to compress the camera's raw video data into image data and then store it, which will cause a certain amount of resource loss. At the same time, since an autonomous driving vehicle platform generally has 8 to 12 cameras and the jpeg data volume is large, this will result in a huge volume of data after compression. Generally speaking, all cameras on a vehicle will generate about 2GB of image data within two minutes, which will not only consume a large amount of I0 resources on the autonomous driving end, but also cause greater pressure on cloud data storage."

[0005] However, although the current autonomous driving technology of automobiles is gradually maturing, it does not mean that the driver can completely entrust the car to the autonomous driving system when using the autonomous driving function. Especially when the driver is tired, completely entrusting the car to the autonomous driving system will increase the risk of using the car's autonomous driving function to a certain extent.

[0006] To this end, we proposed a big data analysis system and method based on cloud computing. Summary of the invention

[0007] In view of the above-mentioned shortcomings of the prior art, the present invention provides a big data analysis system and method based on cloud computing, which solves the technical problems raised in the above-mentioned background technology.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: In a first aspect, a big data analysis system based on cloud computing includes: a collection layer, an analysis layer, and a control layer; The system integrated by the acquisition layer, analysis layer and control layer is applied to the highway driving scenario where a vehicle with an automatic driving function switches from autonomous driving to automatic driving; The historical driving state parameters of the vehicle are uploaded through the collection layer, and data cleaning and storage are performed in the collection layer. The analysis layer synchronously receives the cleaned and stored vehicle driving state parameters in the collection layer, analyzes the driving user response time based on the vehicle driving state parameters, synchronously obtains the current vehicle driving environment parameters, and uses the current vehicle driving environment parameters to analyze the vehicle's optimal driving position. The control layer operates to receive the vehicle driving user response time and the vehicle's optimal driving position analyzed in the analysis layer, coordinates the vehicle's driving position based on the vehicle's optimal driving position, and performs attenuation control on the vehicle's current driving speed based on the vehicle driving user response time. The analysis layer includes a receiving module, a retrieving module and an analyzing module. The receiving module is used to receive the vehicle historical driving state parameters stored in the collection layer and synchronously collect the driving environment parameters of the current vehicle. The retrieving module is used to sequentially retrieve the vehicle historical driving state parameters received by it and the collected driving environment parameters of the current vehicle in the receiving module, and transmit them to the analysis module in the retrieval order. The analysis module is used to analyze the vehicle driving user response time efficiency and the vehicle's optimal driving position. When the retrieval module retrieves the historical driving state parameters of the vehicle and transmits them to the analysis module, the analysis module performs an analysis operation of the vehicle driving user response time efficiency: ; Where: Response time for vehicle driving users; It is the base time of response for vehicle driving users; is the set of remaining vehicle driving trajectories that are cut off by the curve part of the vehicle driving trajectory; is the set of coordinates on the i-th vehicle trajectory; is the length of the i-th vehicle trajectory; is the average speed of the vehicle’s driving trajectory in the i-th segment; is the jth coordinate on the i-th vehicle trajectory; is the minimum offset of adjacent coordinates; is the maximum value of adjacent coordinate offset; in, Representing coordinates With coordinates The vertical deviation relative to the vehicle's forward direction, Express The average of the vehicle driving user response time base The value range is 0.5~3 and is customized by the system end user. The vehicle driving user response time It is used to reflect the fatigue level of vehicle driving users and is a design reference for vehicle speed attenuation control.

[0009] Furthermore, the acquisition layer includes an upload module, a cleaning module and a management module, the upload module is used to upload the historical driving state parameters of the vehicle, the cleaning module is used to receive the historical driving state parameters of the vehicle uploaded in the upload module, and clean the historical driving state parameters of the vehicle, and the management module is used to receive the historical driving state parameters of the vehicle that have been cleaned in the cleaning module, and store the historical driving state parameters of the vehicle; Among them, the vehicle's historical driving state parameters include: vehicle driving trajectory, vehicle real-time speed. When the cleaning module runs to clean the vehicle's historical driving state parameters, the vehicle's driving trajectory is traversed, and the curved part of the vehicle's driving trajectory and its corresponding vehicle real-time speed parameters are determined as discarded targets. The cleaning operation is performed, and the vehicle's historical driving state parameters that have not been determined as discarded targets are retained.

[0010] Furthermore, the vehicle historical driving state parameters uploaded in the uploading module are: the vehicle driving trajectory and the vehicle real-time speed within a time threshold defined after the vehicle is started or the last automatic driving mode ends and before the next automatic driving mode of the vehicle is started; After storing the vehicle's historical driving status parameters, the management module synchronously monitors the vehicle's driving mode. When the vehicle's driving mode is autonomous driving or parking, the vehicle's historical driving status parameters stored in the management module are cleared, and after the clearing operation is completed, the system synchronization is reset.

[0011] Furthermore, the vehicle driving trajectory in the vehicle historical driving state parameters uploaded in the upload module is expressed in the form of a polyline, and each group of line segments in the polyline is a ratio line segment, and the time span corresponding to each group of line segments is one second. After uploading, the vehicle driving trajectory is placed in a Cartesian coordinate system; During the operation phase of the cleaning module, in the process of traversing the vehicle's driving trajectory, the determination of the curved part of the vehicle's driving trajectory is as follows: ; Where: is the curve indicator; , are the polar diameter and polar angle after normalization; , , The time corresponding to the polar diameter or polar angle in its parameter; is the curve index determination value; Before determining the curved part of the vehicle's driving trajectory, the coordinates on the vehicle's driving trajectory placed in the Cartesian coordinate system are converted into coordinates in the polar coordinate system. Based on the above, the three sets of coordinates corresponding to each two adjacent sets of line segments on the multi-segment line corresponding to the vehicle's driving trajectory are calculated to obtain the curve index. , Curve Index Judgment Value Customized by the system user. Representation calculation The line segment used is the curved part of the vehicle's driving trajectory, otherwise, it is the non-curved part of the trajectory; The coordinates (x, y) on the vehicle's driving trajectory placed in the Cartesian coordinate system correspond to the coordinates in the polar coordinate system: , ,but , is the maximum polar diameter, is the maximum polar angle.

[0012] Furthermore, the current vehicle driving environment parameters include: position information of obstacles around the vehicle relative to the vehicle, and position information of the vehicle itself relative to the surrounding obstacles. When the retrieval module retrieves the current vehicle driving environment parameters and transmits them to the analysis module, the analysis module performs an analysis operation of the optimal driving position of the vehicle: A set of closed figures are constructed based on the position information of obstacles around the vehicle, and the length and width of the vehicle are used to draw a rectangle in the closed figure, so that the two long sides of the rectangle are parallel to the two lane lines of the lane where the vehicle is located in the closed image, and the center point of the closed figure is further obtained. The closest point on the parallel midline between the two lane lines of the lane where the vehicle is located is used to obtain the point as the moving target of the rectangle representing the vehicle, and the rectangle is moved horizontally and vertically to the position where the center point of the rectangle coincides with the obtained point; Among them, based on the position represented by the rectangle after the acquisition point moves, that is, the optimal driving position of the vehicle, the position information of obstacles around the vehicle is acquired based on the sensing device installed on the vehicle.

[0013] Furthermore, in the stage of analyzing the optimal driving position of the vehicle, after obtaining the driving environment parameters of the current vehicle, the state risk of the obstacles around each vehicle is first analyzed, and the 10% and no less than one group of obstacles around the vehicle with the highest state risk are selected as high-risk obstacles. The current position information of the high-risk obstacles is moved based on the forward direction of the vehicle driving section to a position that exceeds the vehicle position information and is a distance of the vehicle length from the vehicle position information. The original position information of the high-risk obstacles is iterated with the moved position, and then the closed graph construction operation is performed; Among them, the state risk analysis logic of obstacles around the vehicle is: ; Where: is the state risk index of obstacles around the vehicle; is the distance between the vehicle and the obstacle; is the relative speed between the vehicle and the obstacle; is the vehicle's own weight; is the weight of the obstacle; , is the weight; is the vehicle's own acceleration; is the obstacle acceleration; Among them, the weight , The sum is 1, which is defined by the system user. For the coordination function: The vehicle is in front of the obstacle, and > hour: = ; The vehicle is in front of the obstacle, and < hour: = ; The vehicle is behind the obstacle, and > hour: = ; The vehicle is behind the obstacle, and < hour: = ; = hour, =1.

[0014] Furthermore, it is characterized in that the control layer includes a coordination module, a logic module and a control module. The coordination module is used to receive the optimal driving position of the vehicle analyzed in the analysis layer, and drive to the optimal driving position of the vehicle based on the vehicle automatic driving mode control. The logic module is used to receive the vehicle driving user response time efficiency analyzed in the analysis layer, and feed back the vehicle driving user response time efficiency to the control module, and synchronously design the vehicle's current driving speed attenuation logic. The control module is used to receive the vehicle driving user response time efficiency and the vehicle's current driving speed attenuation logic, and control the vehicle's driving speed attenuation based on the vehicle driving user response time efficiency and the vehicle's current driving speed attenuation logic. During the operation phase of the control module, the operation status of the coordination module is monitored synchronously. When the coordination module controls the vehicle based on the automatic driving mode and drives the vehicle to the optimal driving position, the control module is triggered to run after reaching the optimal driving position.

[0015] Furthermore, the design of the vehicle's current speed decay logic in the logic module complies with: ; Where: is the decay rate of the vehicle’s current speed; is the current speed of the vehicle; The minimum speed limit on the far right side of the road where the vehicle is currently located; is the number of obstacles around the vehicle; Response time for vehicle driving users; Among them, the decay rate of the vehicle's current speed is The unit is km / s, which is the attenuation frequency of the vehicle speed after the vehicle reaches the optimal driving position. In the process of executing speed attenuation based on the attenuation logic, the vehicle is synchronously controlled based on the vehicle's automatic driving mode to drive to the rightmost lane of the vehicle's driving road. After the vehicle reaches the rightmost lane, it is refreshed based on the analysis layer to obtain the optimal driving position again, and based on the control layer operation and the vehicle's automatic driving mode control, it drives to the vehicle's optimal driving position.

[0016] Furthermore, the receiving module is interactively connected to the management module via a wireless network, the management module is interactively connected to the cleaning module and the uploading module via a wireless network, the receiving module is interactively connected to the retrieval module and the analysis module via a wireless network, the analysis module is interactively connected to the coordination module via a wireless network, and the coordination module is interactively connected to the logic module and the control module via a wireless network.

[0017] In a second aspect, a big data analysis method based on cloud computing includes: Step 1: Collect historical vehicle driving state parameters, set data cleaning logic, and clean and store the historical vehicle driving state parameters based on the data cleaning logic; Step 2: Obtain the stored historical vehicle driving state parameters and collect the current vehicle driving environment state parameters; Step 3: Set the vehicle's optimal driving position analysis logic, and analyze the vehicle's optimal driving position in combination with the current vehicle driving environment state parameters; Step 4: Set the vehicle speed attenuation control logic, and design the attenuation speed of the vehicle's current speed in combination with the vehicle driving user's response time; Step 5: Based on the analyzed optimal position of the vehicle and the designed decay speed, the vehicle's driving position and speed are coordinated in combination with the vehicle's automatic driving mode control; Step 6: In the process of coordinating the driving position and speed of the vehicle, the vehicle is synchronously controlled based on the vehicle automatic driving mode to drive the vehicle to the rightmost lane of the vehicle driving road, and the optimal driving position of the vehicle is analyzed again; Step 7: Based on the latest analyzed optimal driving position of the vehicle, the driving position of the vehicle in the rightmost lane is re-coordinated.

[0018] Compared with the known public technology, the technical solution provided by the present invention has the following beneficial effects: The present invention provides a big data analysis system and method based on cloud computing. The system is applied to a high-speed driving scenario in which a vehicle with an automatic driving function switches from autonomous driving to automatic driving. During operation, the system analyzes the vehicle driving user response time efficiency and the vehicle's optimal driving position by uploading the vehicle's historical driving state parameters and collecting the vehicle's current driving environment state parameters. During the operation, it is also possible to evaluate whether the driving user is in a fatigue state based on the vehicle driving user response time efficiency. In this way, during the high-speed driving process of the vehicle, the vehicle automatic driving system is assisted based on the optimal driving position and the driving user response time efficiency as a logical basis, so that the vehicle with automatic driving turned on can automatically drive in a safer position relative to surrounding vehicle obstacles. At the same time, the vehicle speed decay logic and lane change assistance of the automatic driving system are configured, so that the vehicle can drive more safely after the automatic driving function is turned on, which can offset the additional risks caused by turning on the automatic driving function in the fatigue driving state to a certain extent, and provide safer protection for the actual application of automatic driving technology; In addition, a cloud computing-based big data analysis method provides further operational logic support for the above system, ensuring that the technical solution composed of the system and method is combined with the car's automatic driving system to serve the car owner and bring the car owner a better intelligent driving experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work: Figure 1 It is a structural diagram of a big data analysis system based on cloud computing; Figure 2 A flowchart of a big data analysis method based on cloud computing is shown in FIG. Figure 3 This is a schematic diagram of an example of a vehicle driving trajectory in the present invention; Figure 4 A logical schematic diagram for determining the optimal driving position of the vehicle in the present invention; The numbers in the figures indicate: 1. Obstacle; 2. Vehicle; 3. Center of closed figure; 4. Center point of optimal driving position of vehicle; 5. Parallel center line between two sets of lane lines of the lane where the vehicle is located; 6. Lane; 7. Closed figure. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0021] The present invention will be further described below in conjunction with the embodiments.

[0022] Embodiment 1: A big data analysis system based on cloud computing in this embodiment, such as Figure 1 As shown, it includes: collection layer, analysis layer and control layer; The system integrated by the collection layer, analysis layer and control layer is applied to the highway driving scenario where vehicles with autonomous driving functions switch from autonomous driving to autonomous driving; The historical driving state parameters of the vehicle are uploaded through the collection layer, and data cleaning and storage are performed in the collection layer. The analysis layer synchronously receives the cleaned and stored vehicle driving state parameters in the collection layer, analyzes the driving user response time based on the vehicle driving state parameters, synchronously obtains the current vehicle driving environment parameters, and uses the current vehicle driving environment parameters to analyze the vehicle's optimal driving position. The control layer operates to receive the vehicle driving user response time and the vehicle's optimal driving position analyzed in the analysis layer, coordinates the vehicle's driving position based on the vehicle's optimal driving position, and performs attenuation control on the vehicle's current driving speed based on the vehicle driving user response time. The collection layer includes an upload module, a cleaning module and a management module. The upload module is used to upload the historical driving state parameters of the vehicle. The cleaning module is used to receive the historical driving state parameters of the vehicle uploaded in the upload module and clean the historical driving state parameters of the vehicle. The management module is used to receive the historical driving state parameters of the vehicle that have been cleaned in the cleaning module and store the historical driving state parameters of the vehicle. The vehicle historical driving state parameters include: vehicle driving trajectory and vehicle real-time speed. When the cleaning module runs to clean the vehicle historical driving state parameters, the vehicle driving trajectory is traversed, and the curved part of the vehicle driving trajectory and its corresponding vehicle real-time speed parameters are determined as discarded targets, and the cleaning operation is performed, and the vehicle historical driving state parameters that are not determined as discarded targets are retained; The vehicle driving trajectory in the vehicle historical driving state parameters uploaded in the upload module is expressed as a multi-segment line, and each group of line segments in the multi-segment line is a ratio line segment, and the time span corresponding to each group of line segments is one second. After uploading, the vehicle driving trajectory is placed in the Cartesian coordinate system; During the operation phase of the cleaning module, when traversing the vehicle's driving trajectory, the determination of the curved part of the vehicle's driving trajectory is as follows: ; Where: is the curve indicator; , are the polar diameter and polar angle after normalization; , , The time corresponding to the polar diameter or polar angle in its parameter; is the curve index determination value; Before determining the curved part of the vehicle's driving trajectory, the coordinates on the vehicle's driving trajectory placed in the Cartesian coordinate system are converted into coordinates in the polar coordinate system. Based on the above, the three sets of coordinates corresponding to each two adjacent sets of line segments on the multi-segment line corresponding to the vehicle's driving trajectory are calculated to obtain the curve index. , Curve Index Judgment Value Customized by the system user. Representation calculation The line segment used is the curved part of the vehicle's driving trajectory, otherwise, it is the non-curved part of the trajectory; The coordinates (x, y) on the vehicle's trajectory placed in the Cartesian coordinate system correspond to the coordinates in the polar coordinate system: , ,but , is the maximum polar diameter, is the maximum polar angle; The analysis layer includes a receiving module, a retrieving module and an analyzing module. The receiving module is used to receive the historical driving state parameters of the vehicle stored in the collecting layer and synchronously collect the driving environment parameters of the current vehicle. The retrieving module is used to sequentially retrieve the historical driving state parameters of the vehicle received and the driving environment parameters of the current vehicle collected in the receiving module, and transmit them to the analyzing module in the retrieving order. The analyzing module is used to analyze the response time of the vehicle driving user and the optimal driving position of the vehicle. When the retrieval module retrieves the historical driving state parameters of the vehicle and transmits them to the analysis module, the analysis module performs an analysis operation of the vehicle driving user response time efficiency: ; Where: Response time for vehicle driving users; It is the base time of response for vehicle driving users; is the set of remaining vehicle driving trajectories that are cut off by the curve part of the vehicle driving trajectory; is the set of coordinates on the i-th vehicle trajectory; is the length of the i-th vehicle trajectory; is the average speed of the vehicle’s driving trajectory in the i-th segment; is the jth coordinate on the i-th vehicle trajectory; is the minimum offset of adjacent coordinates; is the maximum value of adjacent coordinate offset; in, Representing coordinates With coordinates The vertical deviation relative to the vehicle's forward direction, Express The average of the vehicle driving user response time base The value range is 0.5~3 and is customized by the system end user. The vehicle driving user response time Used to reflect the fatigue level of vehicle drivers and as a design reference for vehicle speed attenuation control; The control layer includes a coordination module, a logic module and a control module. The coordination module is used to receive the optimal driving position of the vehicle analyzed in the analysis layer, and drive to the optimal driving position of the vehicle based on the vehicle automatic driving mode control. The logic module is used to receive the vehicle driving user response time efficiency analyzed in the analysis layer, and feed back the vehicle driving user response time efficiency to the control module, and synchronously design the vehicle's current driving speed attenuation logic. The control module is used to receive the vehicle driving user response time efficiency and the vehicle's current driving speed attenuation logic, and control the vehicle's driving speed attenuation based on the vehicle driving user response time efficiency and the vehicle's current driving speed attenuation logic. Among them, during the operation phase of the control module, the operation status of the coordination module is monitored synchronously. When the coordination module drives to the optimal driving position of the vehicle based on the vehicle's automatic driving mode control and reaches it, the control module is triggered to run; The design of the vehicle's current speed attenuation logic in the logic module complies with: ; Where: is the decay rate of the vehicle’s current speed; is the current speed of the vehicle; The minimum speed limit on the far right side of the road where the vehicle is currently located; is the number of obstacles around the vehicle; Response time for vehicle driving users; Among them, the decay rate of the vehicle's current speed is The unit is km / s, which is the attenuation frequency of the vehicle speed after the vehicle reaches the optimal driving position. In the process of executing the vehicle speed attenuation based on the attenuation logic, the vehicle is synchronously controlled based on the vehicle automatic driving mode to drive to the rightmost lane of the vehicle driving road. After the vehicle reaches the rightmost lane, it is refreshed based on the analysis layer to obtain the optimal driving position again, and driven to the optimal driving position of the vehicle based on the control layer operation and the vehicle automatic driving mode control; The receiving module is interactively connected to the management module through a wireless network, the management module is interactively connected to the cleaning module and the uploading module through a wireless network, the receiving module is interactively connected to the retrieval module and the analysis module through a wireless network, the analysis module is interactively connected to the coordination module through a wireless network, and the coordination module is interactively connected to the logic module and the control module through a wireless network.

[0023] In this embodiment, the upload module runs to upload the historical driving state parameters of the vehicle, the cleaning module synchronously receives the historical driving state parameters of the vehicle uploaded in the upload module, and cleans the historical driving state parameters of the vehicle. The management module further receives the historical driving state parameters of the vehicle that have been cleaned in the cleaning module, and stores the historical driving state parameters of the vehicle. The receiving module runs to receive the historical driving state parameters of the vehicle stored in the collection layer and synchronously collects the driving environment parameters of the current vehicle. The retrieval module then sequentially retrieves the received historical driving state parameters of the vehicle and the collected driving environment parameters of the current vehicle in the receiving module, and sends them to the analysis module in the retrieval order. Block transmission, the analysis module synchronously analyzes the vehicle driving user response time and the vehicle's optimal driving position, the coordination module post-operates to receive the vehicle's optimal driving position analyzed in the analysis layer, and drives to the vehicle's optimal driving position based on the vehicle's automatic driving mode control. The logic module receives the vehicle driving user response time analyzed in the analysis layer in real time, and feeds back the vehicle driving user response time to the control module, and synchronously designs the vehicle's current driving speed attenuation logic. Finally, the control module receives the vehicle driving user response time and the vehicle's current driving speed attenuation logic, and controls the vehicle's driving speed attenuation based on the vehicle driving user response time and the vehicle's current driving speed attenuation logic.

[0024] Through the operation of the system in the above embodiment, the current automobile automatic driving system is assisted to provide automatic driving services for the car owner, so that the automobile automatic driving system is safer, more reliable and less risky when being used; See also Figure 3 As shown, the figure further shows the vehicle's driving trajectory, and based on the angular symbol indication in the figure, the direction of the vehicle's driving trajectory is marked; See also Figure 4 As shown, based on the number markings in the figure, it is further demonstrated how the closed figure 7 is determined by the obstacle 1, how the closed figure center 3 is determined by the closed figure 7, how the parallel center line 5 between the two sets of lane lines in the lane where the vehicle is located is determined by the lane 6, and how to combine the closed figure center 3 and the parallel center line 5 between the two sets of lane lines in the lane where the vehicle is located to determine the center point 4 of the vehicle's optimal driving position.

[0025] Embodiment 2: In terms of specific implementation, based on Example 1, this example refers to Figure 1 The cloud computing-based big data analysis system in Example 1 is further described in detail: The vehicle historical driving state parameters uploaded in the upload module are: the vehicle driving trajectory and the vehicle real-time speed within the time threshold defined after the vehicle is started or the last automatic driving mode ends and before the next automatic driving mode of the vehicle is started; After storing the vehicle's historical driving status parameters, the management module synchronously monitors the vehicle's driving mode. When the vehicle's driving mode is autonomous driving or parking, the vehicle's historical driving status parameters stored in the management module are cleared, and after the clearing operation is completed, the system synchronization is reset.

[0026] Through the above settings, further continuous operation logic is provided for the system operation in Example 1, ensuring that the system continuously operates to assist the vehicle's automatic driving system and achieve safe and stable automobile automatic driving control.

[0027] like Figure 1 As shown, the current vehicle driving environment parameters include: the position information of the obstacles around the vehicle relative to the vehicle, and the position information of the vehicle itself relative to the surrounding obstacles. When the retrieving module retrieves the current vehicle driving environment parameters and transmits them to the analysis module, the analysis module performs the analysis operation of the vehicle's optimal driving position: A set of closed figures are constructed based on the position information of obstacles around the vehicle, and the length and width of the vehicle are used to draw a rectangle in the closed figure, so that the two long sides of the rectangle are parallel to the two lane lines of the lane where the vehicle is located in the closed image, and the center point of the closed figure is further obtained. The closest point on the parallel midline between the two lane lines of the lane where the vehicle is located is used to obtain the point as the moving target of the rectangle representing the vehicle, and the rectangle is moved horizontally and vertically to the position where the center point of the rectangle coincides with the obtained point; Wherein, based on the position represented by the rectangle after the acquisition point moves, that is, the optimal driving position of the vehicle, the position information of obstacles around the vehicle is acquired based on the sensing device installed on the vehicle; In the stage of analyzing the optimal driving position of the vehicle, after obtaining the driving environment parameters of the current vehicle, the state risk of the obstacles around each vehicle is first analyzed, and the 10% and no less than one group of obstacles around the vehicle with the highest state risk are selected as high-risk obstacles. The current position information of the high-risk obstacles is moved based on the forward direction of the vehicle driving section to a position that exceeds the vehicle position information and is the vehicle length away from the vehicle position information. The original position information of the high-risk obstacles is iterated with the moved position, and then the closed graph construction operation is performed; Among them, the state risk analysis logic of obstacles around the vehicle is: ; Where: is the state risk index of obstacles around the vehicle; is the distance between the vehicle and the obstacle; is the relative speed between the vehicle and the obstacle; is the vehicle's own weight; is the weight of the obstacle; , is the weight; is the vehicle's own acceleration; is the obstacle acceleration; Among them, the weight , The sum is 1, which is defined by the system user. For the coordination function: The vehicle is in front of the obstacle, and > hour: = ; The vehicle is in front of the obstacle, and < hour: = ; The vehicle is behind the obstacle, and > hour: = ; The vehicle is behind the obstacle, and < hour: = ; = hour, =1.

[0028] In this embodiment, the state risk analysis logic of the obstacles around the vehicle is further limited through the above-mentioned logical formula, so that based on the setting of the state risk analysis logic of the obstacles around the vehicle, the construction logic of the closed figure 7 is further provided, so as to provide support for the determination of the optimal driving position of the vehicle based on the further limitation of the closed figure 7.

[0029] Embodiment three: In terms of specific implementation, based on Example 1, this example refers to Figure 2 The cloud computing-based big data analysis system in Example 1 is further described in detail: A big data analysis method based on cloud computing, comprising: Step 1: Collect historical vehicle driving state parameters, set data cleaning logic, and clean and store the historical vehicle driving state parameters based on the data cleaning logic; Step 2: Obtain the stored historical vehicle driving state parameters and collect the current vehicle driving environment state parameters; Step 3: Set the vehicle's optimal driving position analysis logic, and analyze the vehicle's optimal driving position in combination with the current vehicle driving environment state parameters; Step 4: Set the vehicle speed attenuation control logic, and design the attenuation speed of the vehicle's current speed in combination with the vehicle driving user's response time; Step 5: Based on the analyzed optimal position of the vehicle and the designed decay speed, the vehicle's driving position and speed are coordinated in combination with the vehicle's automatic driving mode control; Step 6: In the process of coordinating the driving position and speed of the vehicle, the vehicle is synchronously controlled based on the vehicle automatic driving mode to drive the vehicle to the rightmost lane of the vehicle driving road, and the optimal driving position of the vehicle is analyzed again; Step 7: Based on the latest analyzed optimal driving position of the vehicle, the driving position of the vehicle in the rightmost lane is re-coordinated.

[0030] In summary, in the above-mentioned embodiment, during operation, the system analyzes the vehicle driving user response time and the vehicle's optimal driving position by uploading the vehicle's historical driving state parameters and collecting the vehicle's current driving environment state parameters. During this period, it can also evaluate whether the driving user is in a fatigue state based on the vehicle driving user response time. Therefore, during high-speed driving of the vehicle, the optimal driving position and the driving user response time are used as the logical basis to assist the vehicle's automatic driving system, so that the vehicle with automatic driving turned on can automatically drive in a safer position relative to surrounding vehicle obstacles; at the same time, it is configured with vehicle speed attenuation logic and lane change assistance of the automatic driving system, so that the vehicle after the automatic driving is turned on can automatically drive more safely, which to a certain extent offsets the additional risks caused by turning on the automatic driving function in a fatigued driving state, provides safer protection for the actual application of automatic driving technology, and brings a better intelligent driving experience to car owners.

[0031] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A big data analysis system based on cloud computing, characterized in that: include: Collection layer, analysis layer and control layer; The system integrated by the acquisition layer, analysis layer and control layer is applied to the highway driving scenario where a vehicle with an automatic driving function switches from autonomous driving to automatic driving; The historical driving state parameters of the vehicle are uploaded through the collection layer, and data cleaning and storage are performed in the collection layer. The analysis layer synchronously receives the cleaned and stored vehicle driving state parameters in the collection layer, analyzes the driving user response time based on the vehicle driving state parameters, synchronously obtains the current vehicle driving environment parameters, and uses the current vehicle driving environment parameters to analyze the vehicle's optimal driving position. The control layer operates to receive the vehicle driving user response time and the vehicle's optimal driving position analyzed in the analysis layer, coordinates the vehicle's driving position based on the vehicle's optimal driving position, and performs attenuation control on the vehicle's current driving speed based on the vehicle driving user response time. The analysis layer includes a receiving module, a retrieving module and an analyzing module. The receiving module is used to receive the vehicle historical driving state parameters stored in the collection layer and synchronously collect the driving environment parameters of the current vehicle. The retrieving module is used to sequentially retrieve the vehicle historical driving state parameters received by it and the collected driving environment parameters of the current vehicle in the receiving module, and transmit them to the analysis module in the retrieval order. The analysis module is used to analyze the vehicle driving user response time efficiency and the vehicle's optimal driving position. When the retrieval module retrieves the historical driving state parameters of the vehicle and transmits them to the analysis module, the analysis module performs an analysis operation of the vehicle driving user response time efficiency: ； Where: Response time for vehicle driving users; It is the base time of response of vehicle driving users; is the set of remaining vehicle driving trajectories that are cut off by the curve part of the vehicle driving trajectory; is the set of coordinates on the i-th vehicle trajectory; is the length of the i-th vehicle trajectory; is the average speed of the vehicle’s driving trajectory in the i-th segment; is the jth coordinate on the i-th vehicle trajectory; is the minimum offset of adjacent coordinates; is the maximum value of adjacent coordinate offset; in, Representing coordinates With coordinates The vertical deviation relative to the vehicle's forward direction, Express The average of the vehicle driving user response time base The value range is 0.5~3 and is customized by the system end user. The vehicle driving user response time It is used to reflect the fatigue level of vehicle driving users and is a design reference for vehicle speed attenuation control.

2. The big data analysis system based on cloud computing according to claim 1, characterized in that: The acquisition layer includes an upload module, a cleaning module and a management module. The upload module is used to upload the historical driving state parameters of the vehicle. The cleaning module is used to receive the historical driving state parameters of the vehicle uploaded in the upload module and clean the historical driving state parameters of the vehicle. The management module is used to receive the historical driving state parameters of the vehicle that have been cleaned in the cleaning module and store the historical driving state parameters of the vehicle. Among them, the vehicle's historical driving state parameters include: vehicle driving trajectory, vehicle real-time speed. When the cleaning module runs to clean the vehicle's historical driving state parameters, the vehicle's driving trajectory is traversed, and the curved part of the vehicle's driving trajectory and its corresponding vehicle real-time speed parameters are determined as discarded targets. The cleaning operation is performed, and the vehicle's historical driving state parameters that have not been determined as discarded targets are retained.

3. The big data analysis system based on cloud computing according to claim 2, characterized in that: The vehicle historical driving state parameters uploaded in the upload module are: the vehicle driving trajectory and the vehicle real-time speed within the time threshold defined after the vehicle is started or after the last automatic driving mode ends and before the next automatic driving mode of the vehicle is started; After storing the vehicle's historical driving status parameters, the management module synchronously monitors the vehicle's driving mode. When the vehicle's driving mode is autonomous driving or parking, the vehicle's historical driving status parameters stored in the management module are cleared, and after the clearing operation is completed, the system synchronization is reset.

4. The big data analysis system based on cloud computing according to claim 2, characterized in that: The vehicle driving trajectory in the vehicle historical driving state parameters uploaded in the upload module is expressed in the form of a polyline, and each group of line segments in the polyline is a ratio line segment, and the time span corresponding to each group of line segments is one second. After uploading, the vehicle driving trajectory is placed in the Cartesian coordinate system; During the operation phase of the cleaning module, when traversing the vehicle's driving trajectory, the determination of the curved part of the vehicle's driving trajectory is as follows: ； Where: is the curve indicator; , are the polar diameter and polar angle after normalization; , , The time corresponding to the polar diameter or polar angle in its parameter; is the curve index determination value; Before determining the curved part of the vehicle's driving trajectory, the coordinates on the vehicle's driving trajectory placed in the Cartesian coordinate system are converted into coordinates in the polar coordinate system. Based on the above, the three sets of coordinates corresponding to each two adjacent sets of line segments on the multi-segment line corresponding to the vehicle's driving trajectory are calculated to obtain the curve index. , Curve Index Judgment Value Customized by the system user. Representation calculation The line segment used is the curved part of the vehicle's driving trajectory, otherwise, it is the non-curved part of the trajectory; The coordinates (x, y) on the vehicle's driving trajectory placed in the Cartesian coordinate system correspond to the coordinates in the polar coordinate system: , ,but , is the maximum polar diameter, is the maximum polar angle.

5. The big data analysis system based on cloud computing according to claim 1, characterized in that: The current vehicle driving environment parameters include: position information of obstacles around the vehicle relative to the vehicle, and position information of the vehicle itself relative to the surrounding obstacles. When the retrieval module retrieves the current vehicle driving environment parameters and transmits them to the analysis module, the analysis module performs an analysis operation of the vehicle's optimal driving position: A set of closed figures are constructed based on the position information of obstacles around the vehicle, and the length and width of the vehicle are used to draw a rectangle in the closed figure, so that the two long sides of the rectangle are parallel to the two lane lines of the lane where the vehicle is located in the closed image, and the center point of the closed figure is further obtained. The closest point on the parallel midline between the two lane lines of the lane where the vehicle is located is used to obtain the point as the moving target of the rectangle representing the vehicle, and the rectangle is moved horizontally and vertically to the position where the center point of the rectangle coincides with the obtained point; Among them, based on the position represented by the rectangle after the acquisition point moves, that is, the optimal driving position of the vehicle, the position information of obstacles around the vehicle is acquired based on the sensing device installed on the vehicle.

6. The big data analysis system based on cloud computing according to claim 5, characterized in that: In the stage of analyzing the optimal driving position of the vehicle, after obtaining the driving environment parameters of the current vehicle, the state risk of the obstacles around each vehicle is first analyzed, and the 10% and no less than one group of obstacles around the vehicle with the highest state risk are selected as high-risk obstacles. The current position information of the high-risk obstacles is moved based on the forward direction of the vehicle driving section to a position that exceeds the vehicle position information and is the vehicle length away from the vehicle position information. The original position information of the high-risk obstacles is iterated with the moved position, and then the closed graph construction operation is performed; Among them, the state risk analysis logic of obstacles around the vehicle is: ； Where: is the state risk index of obstacles around the vehicle; is the distance between the vehicle and the obstacle; is the relative speed between the vehicle and the obstacle; is the vehicle's own weight; is the weight of the obstacle; , is the weight; is the vehicle's own acceleration; is the obstacle acceleration; Among them, the weight , The sum is 1, which is defined by the system user. is the coordination function: The vehicle is in front of the obstacle, and > hour: = ; The vehicle is in front of the obstacle, and < hour: = ; The vehicle is behind the obstacle, and > hour: = ; The vehicle is behind the obstacle, and < hour: = ; = hour, =1.

7. The big data analysis system based on cloud computing according to claim 1, characterized in that: The control layer includes a coordination module, a logic module and a control module. The coordination module is used to receive the optimal driving position of the vehicle analyzed in the analysis layer, and drive to the optimal driving position of the vehicle based on the vehicle automatic driving mode control. The logic module is used to receive the vehicle driving user response time efficiency analyzed in the analysis layer, and feed back the vehicle driving user response time efficiency to the control module, and synchronously design the vehicle's current driving speed attenuation logic. The control module is used to receive the vehicle driving user response time efficiency and the vehicle's current driving speed attenuation logic, and control the vehicle's driving speed attenuation based on the vehicle driving user response time efficiency and the vehicle's current driving speed attenuation logic. During the operation phase of the control module, the operation status of the coordination module is monitored synchronously. When the coordination module controls the vehicle based on the automatic driving mode and drives the vehicle to the optimal driving position, the control module is triggered to run after reaching the optimal driving position.

8. The big data analysis system based on cloud computing according to claim 7, characterized in that: The design of the vehicle's current speed decay logic in the logic module complies with: ； Where: is the decay rate of the vehicle’s current speed; is the current speed of the vehicle; The minimum speed limit on the far right side of the road where the vehicle is currently located; is the number of obstacles around the vehicle; Response time for vehicle driving users; Among them, the decay rate of the vehicle's current speed is The unit is km / s, which is the attenuation frequency of the vehicle speed after the vehicle reaches the optimal driving position. In the process of executing speed attenuation based on the attenuation logic, the vehicle is synchronously controlled based on the vehicle's automatic driving mode to drive to the rightmost lane of the vehicle's driving road. After the vehicle reaches the rightmost lane, it is refreshed based on the analysis layer to obtain the optimal driving position again, and based on the control layer operation and the vehicle's automatic driving mode control, it drives to the vehicle's optimal driving position.

9. The big data analysis system based on cloud computing according to claim 1, characterized in that: The receiving module is interactively connected to the management module via a wireless network, the management module is interactively connected to the cleaning module and the uploading module via a wireless network, the receiving module is interactively connected to the retrieval module and the analysis module via a wireless network, the analysis module is interactively connected to the coordination module via a wireless network, and the coordination module is interactively connected to the logic module and the control module via a wireless network.

10. A cloud computing-based big data analysis method, the method being an implementation method of a cloud computing-based big data analysis system as claimed in any one of claims 1 to 9, characterized in that: include: Step 1: Collect historical vehicle driving state parameters, set data cleaning logic, and clean and store the historical vehicle driving state parameters based on the data cleaning logic; Step 2: Obtain the stored historical vehicle driving state parameters and collect the current vehicle driving environment state parameters; Step 3: Set the vehicle's optimal driving position analysis logic, and analyze the vehicle's optimal driving position in combination with the current vehicle driving environment state parameters; Step 4: Set the vehicle speed attenuation control logic, and design the attenuation speed of the vehicle's current speed in combination with the vehicle driving user's response time; Step 5: Based on the analyzed optimal position of the vehicle and the designed decay speed, the vehicle's driving position and speed are coordinated in combination with the vehicle's automatic driving mode control; Step 6: In the process of coordinating the driving position and speed of the vehicle, the vehicle is synchronously controlled based on the vehicle automatic driving mode to drive the vehicle to the rightmost lane of the vehicle driving road, and the optimal driving position of the vehicle is analyzed again; Step 7: Based on the latest analyzed optimal driving position of the vehicle, the driving position of the vehicle in the rightmost lane is re-coordinated.

Images