Intelligent network connection automobile safety enhancement method and system based on artificial intelligence

Abstract

The invention relates to the technical field of intelligent network connection automobile data security, in particular to an intelligent network connection automobile security enhancement method and system based on artificial intelligence, and the method comprises the steps: obtaining external environment image data and vehicle operation data, dividing security enhancement tendency categories, randomly selecting a plurality of clusters, adding a layer, obtaining a contour position, and carrying out the safety enhancement of an intelligent network connection automobile. Adjusting the size of the remaining clustering clusters, obtaining disguised vehicle exterior environment image data, encrypting all the data, obtaining encrypted ciphertexts and then sending all the encrypted ciphertexts to a data receiving end, obtaining the encrypted ciphertexts by the data receiving end, decrypting the encrypted ciphertexts, and restoring the disguised vehicle exterior environment image data into vehicle exterior environment image data. According to the method, the vehicle exterior environment image data containing more information is screened out for processing, so that the security of important data can be ensured while the computing power is reduced and the data processing efficiency is improved, and the security of all the data is further improved by encrypting all the data.

Description

Technical Field

[0001] The present invention relates to the field of intelligent networked vehicle data security technology, and in particular to an intelligent networked vehicle security enhancement method and system based on artificial intelligence. Background Art

[0002] With the rapid development of intelligent connected vehicle technology, these vehicles contain a lot of important information, such as vehicle status, driving behavior, environmental perception data, etc. This information is crucial for the development of intelligent driving systems for vehicles. However, the sensitivity and value of this data also make it a potential security risk point. Therefore, it is particularly important to protect the security of this information.

[0003] The prior art discloses a method for enhancing the channel of intelligent connected vehicles based on spatial scanning technology, including: configuring a spatial beam scanning system on intelligent connected vehicles and infrastructure equipment, and the intelligent connected vehicles transmit data information to the spatial beam scanning system; the beam scanning system performs weight calculation on beam forming, and uses the obtained channel estimation to calculate the phase and amplitude weights of each antenna element in the beam forming network; the calculated weights are used to control the shape and direction of the beam; the spatial beam scanning system is a Butler spatial beam scanning system, which is obtained by connecting the Butler matrix and the antenna array, and is verified, analyzed and adjusted in HFSS and CST simulation software. The present invention ensures that only legitimate recipients receive data information, and eavesdroppers cannot intercept valid transmission data, and can be applied to intelligent transportation systems, autonomous driving vehicles and other fields.

[0004] However, the prior art still has the following problems:

[0005] Information is not screened based on its importance. Important information is processed before all other information is encrypted, which results in low security for important information and consumes a lot of computing power and resources, resulting in low data processing efficiency. Summary of the invention

[0006] To this end, the present invention provides an artificial intelligence-based intelligent connected vehicle security enhancement method and system to overcome the problem in the prior art that information is not screened according to its importance, and all information is encrypted after important information is processed, resulting in a low level of security for important information, as well as consuming a large amount of computing power and resources, resulting in low data processing efficiency.

[0007] To achieve the above objectives, on the one hand, the present invention provides a method for enhancing the safety of an intelligent connected vehicle based on artificial intelligence, comprising:

[0008] Step S1, acquiring vehicle exterior environment image data and vehicle operation data, wherein the vehicle operation data includes vehicle speed, engine speed, vehicle acceleration and vehicle steering angle;

[0009] Step S2, automatically extracting image features of the vehicle exterior environment image data through a convolutional neural network, performing cluster analysis on the image features based on shape and size, and obtaining the number of clusters;

[0010] Step S3, dividing the number of clusters into safety enhancement tendency categories in combination with the change value of vehicle operation data;

[0011] Step S4, in response to the preset category, select a number of clusters, add a layer on the cluster, obtain the outline position of the cluster, and adjust the size of the remaining clusters in the vehicle exterior environment image data to obtain the camouflaged vehicle exterior environment image data;

[0012] Step S5, encrypting the disguised vehicle exterior environment image data, the contour positions of the clusters, and the undisguised vehicle exterior environment image data, and sending all of them to the data receiving end after obtaining the encrypted ciphertext;

[0013] Step S6, the data receiving end obtains the encrypted ciphertext, the encrypted disguised vehicle exterior environment image data, the outline position of the cluster, and the undisguised vehicle exterior environment image data, decrypts the encrypted ciphertext, and obtains the undisguised vehicle exterior environment image data;

[0014] And, for the disguised vehicle exterior environment image data, the layers of the disguised vehicle exterior environment image data are removed according to the contour positions of the clusters, and the sizes of the remaining clusters in the disguised vehicle exterior environment image data are adjusted to obtain the entire vehicle exterior environment image data.

[0015] As a preferred technical solution of the safety enhancement method for intelligent connected vehicles based on artificial intelligence, the step S3 further includes calculating a safety enhancement tendency representation value according to the number of clusters and the change value of vehicle operation data.

[0016] The ratio of the number of clusters to the preset threshold number of clusters is recorded as the first weighted influence amount;

[0017] Obtaining a sum of a ratio of a vehicle speed change value to a preset vehicle speed change value threshold, a ratio of an engine speed change value to a preset engine speed change value threshold, a ratio of a vehicle acceleration change value to a preset vehicle acceleration change value threshold, and a ratio of a vehicle steering angle change value to a preset vehicle steering angle change value threshold, and recording the sum as a second weighted influence amount;

[0018] The first weighted influence amount and the second weighted influence amount are weightedly summed to obtain a safety enhancement tendency representation value.

[0019] As a preferred technical solution of the safety enhancement method for intelligent connected vehicles based on artificial intelligence, the step S3 further includes dividing the safety enhancement tendency categories according to the safety enhancement tendency characterization value, and the process of dividing the safety enhancement tendency categories includes:

[0020] The safety enhancement tendency characterization value is compared with the preset safety enhancement tendency characterization value comparison threshold.

[0021] If the security enhancement tendency representation value is greater than the preset security enhancement tendency representation value comparison threshold, the security enhancement tendency category is classified as a strong security enhancement tendency category;

[0022] If the security enhancement tendency characterization value is less than or equal to the preset security enhancement tendency characterization value comparison threshold, the security enhancement tendency category is classified as a weak security enhancement tendency category.

[0023] As a preferred technical solution for the safety enhancement method of intelligent connected vehicles based on artificial intelligence, in step S4, a preset category is responded to, wherein the preset category is a category with a strong safety enhancement tendency.

[0024] As a preferred technical solution for the safety enhancement method of intelligent connected vehicles based on artificial intelligence, in step S4, several clusters are optionally selected, wherein the number of selected clusters is positively correlated with the number of clusters in the external vehicle environment image data.

[0025] As a preferred technical solution of the safety enhancement method for intelligent connected vehicles based on artificial intelligence, in step S4, the size of the remaining clusters in the external vehicle environment image data is adjusted, wherein there is an adjustment ratio corresponding to the number of remaining clusters.

[0026] As a preferred technical solution for the safety enhancement method of intelligent connected vehicles based on artificial intelligence, in step S5, the uncamouflaged exterior environment image data is exterior environment image data of a weak safety enhancement tendency category.

[0027] As a preferred technical solution of the intelligent networked vehicle safety enhancement method based on artificial intelligence, in step S6, the process of adjusting the size of the remaining clusters in the disguised vehicle external environment image data includes:

[0028] Determine the number of remaining clusters;

[0029] Determine the adjustment ratio based on the number of remaining clusters;

[0030] The sizes of the remaining clusters in the disguised vehicle exterior environment image data are adjusted according to the adjustment ratio.

[0031] On the other hand, the present invention also provides an artificial intelligence-based intelligent networked vehicle safety enhancement system, comprising:

[0032] A data acquisition module is used to obtain image data of the vehicle's external environment and vehicle operation data, wherein the vehicle operation data includes vehicle speed, engine speed, vehicle acceleration and vehicle steering angle;

[0033] An image analysis module, connected to the data acquisition module, for automatically extracting image features of the vehicle exterior environment image data through a convolutional neural network, performing cluster analysis on the image features based on shape and size, and obtaining the number of clusters;

[0034] The data processing module is connected to each of the data acquisition modules and the image analysis module, and includes an image classification unit, an image encryption unit and a data sending unit.

[0035] The image classification unit is used to classify the number of clusters into safety enhancement tendency categories in combination with the vehicle operation data change value;

[0036] The image encryption unit is used to select a plurality of clusters in response to a preset category, add a layer on the cluster, obtain the contour position of the cluster, and adjust the size of the remaining clusters in the vehicle exterior environment image data to obtain the disguised vehicle exterior environment image data;

[0037] The data sending unit is used to encrypt the disguised vehicle exterior environment image data, the outline position of the cluster and the undisguised vehicle exterior environment image data, and send all of them to the data receiving end after obtaining the encrypted ciphertext;

[0038] An image decryption module is connected to the data processing module and is used for the data receiving end to obtain the encrypted ciphertext, the encrypted disguised vehicle exterior environment image data, the outline position of the cluster and the undisguised vehicle exterior environment image data, decrypt the encrypted ciphertext and obtain the undisguised vehicle exterior environment image data;

[0039] And, for the disguised vehicle exterior environment image data, the layers of the disguised vehicle exterior environment image data are removed according to the contour positions of the clusters, and the sizes of the remaining clusters in the disguised vehicle exterior environment image data are adjusted to obtain the entire vehicle exterior environment image data.

[0040] As the preferred technical solution for the intelligent connected vehicle safety enhancement system based on artificial intelligence, it also includes a display module for displaying image data of the external environment of the vehicle.

[0041] Compared with the prior art, the present invention obtains the vehicle exterior environment image data and vehicle operation data, obtains the number of clusters and divides the security enhancement tendency category in combination with the change value of the vehicle operation data, responds to the preset category, selects several clusters to add layers, obtains the contour position, and adjusts the size of the remaining clusters to obtain the disguised vehicle exterior environment image data, encrypts the disguised vehicle exterior environment image data, the contour position of the cluster and the undisguised vehicle exterior environment image data, obtains the encrypted ciphertext and sends all of them to the data receiving end, the data receiving end obtains the encrypted ciphertext, the encrypted disguised vehicle exterior environment image data, the contour position of the cluster and the undisguised vehicle exterior environment image data, decrypts the encrypted ciphertext, obtains the undisguised vehicle exterior environment image data, and restores the disguised vehicle exterior environment image data to the vehicle exterior environment image data. The present invention selects the vehicle exterior environment image data containing more information for processing, so that the security of important data can be guaranteed while reducing computing power and improving data processing efficiency. The present invention encrypts all data to further improve the security of all data.

[0042] In particular, the present invention divides the safety enhancement tendency category by combining the number of clusters with the change value of vehicle operation data. In actual situations, the vehicle exterior environment image data contains information such as road infrastructure, road condition information, and traffic congestion. This information is crucial for the research and development of vehicle intelligent driving systems, etc., and can be used to achieve intelligent navigation and path planning, and improve driving safety and traffic efficiency. Therefore, during the upload process, these vehicle exterior environment image data should be processed to ensure the security and compliance of the data and prevent data leakage. However, processing all vehicle exterior environment image data will cause the problem of excessive computing power, so that the vehicle exterior environment image data containing more information is screened out for processing, so that the security of important data can be guaranteed while reducing computing power. The number of clusters and the change value of vehicle operation data are important influencing parameters for judging whether the vehicle exterior environment image data includes more information. According to these parameters, the amount of information contained in the vehicle exterior environment image data can be characterized, so that the vehicle exterior environment image data can be screened, effectively protecting the security of the data and significantly improving the efficiency of data processing.

[0043] In particular, the present invention obtains camouflaged exterior vehicle environment image data by adding layers to any number of clusters, obtaining the contour positions of the clusters, and adjusting the sizes of the remaining clusters in the exterior vehicle environment image data. By processing the exterior vehicle environment image data containing a large amount of information by blocking any clusters in the image and adjusting the sizes of the remaining clusters in the image, the difficulty of obtaining the original exterior vehicle environment image data will be increased, thereby improving the security of the data.

[0044] In particular, the present invention encrypts the camouflaged exterior vehicle environment image data, the contour position of the clusters, and the uncamouflaged exterior vehicle environment image data. By processing the exterior vehicle environment image data containing more information and encrypting it together with the unprocessed exterior vehicle environment image data, the security of all data can be further improved after the security of important data is improved in advance. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a step diagram of a method for enhancing safety of an intelligent connected vehicle based on artificial intelligence according to an embodiment of the present invention;

[0046] Figure 2 A logic decision diagram for classifying security enhancement tendency categories for an embodiment of the present invention;

[0047] Figure 3 This is a structural block diagram of an intelligent networked vehicle safety enhancement system based on artificial intelligence according to an embodiment of the present invention;

[0048] Figure 4 It is a structural block diagram of a data processing module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0050] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0051] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0052] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0053] See also Figure 1-2 As shown, the present invention provides an artificial intelligence intelligent networked vehicle safety enhancement method, comprising:

[0054] Step S1, acquiring vehicle exterior environment image data and vehicle operation data, wherein the vehicle operation data includes vehicle speed, engine speed, vehicle acceleration and vehicle steering angle;

[0055] Step S2, automatically extracting image features of the vehicle exterior environment image data through a convolutional neural network, performing cluster analysis on the image features based on shape and size, and obtaining the number of clusters;

[0056] Step S3, dividing the number of clusters into safety enhancement tendency categories in combination with the change value of vehicle operation data;

[0057] Step S4, in response to the preset category, select a number of clusters, add a layer on the cluster, obtain the outline position of the cluster, and adjust the size of the remaining clusters in the vehicle exterior environment image data to obtain the camouflaged vehicle exterior environment image data;

[0058] Step S5, encrypting the disguised vehicle exterior environment image data, the contour positions of the clusters, and the undisguised vehicle exterior environment image data, and sending all of them to the data receiving end after obtaining the encrypted ciphertext;

[0059] Step S6, the data receiving end obtains the encrypted ciphertext, the encrypted disguised vehicle exterior environment image data, the outline position of the cluster, and the undisguised vehicle exterior environment image data, decrypts the encrypted ciphertext, and obtains the undisguised vehicle exterior environment image data;

[0060] And, for the disguised vehicle exterior environment image data, the layers of the disguised vehicle exterior environment image data are removed according to the contour positions of the clusters, and the sizes of the remaining clusters in the disguised vehicle exterior environment image data are adjusted to obtain the entire vehicle exterior environment image data.

[0061] Specifically, the present invention divides the safety enhancement tendency category by combining the number of clusters with the change value of vehicle operation data. In actual situations, the vehicle exterior environment image data contains information such as road infrastructure, road conditions, and traffic congestion. This information is crucial for the research and development of vehicle intelligent driving systems, etc., and can be used to achieve intelligent navigation and path planning, and improve driving safety and traffic efficiency. Therefore, during the upload process, these vehicle exterior environment image data should be processed to ensure the security and compliance of the data and prevent data leakage. However, processing all vehicle exterior environment image data will cause the problem of excessive computing power, so that the vehicle exterior environment image data containing more information is screened out for processing, so that the security of important data can be guaranteed while reducing computing power. The number of clusters and the change value of vehicle operation data are important influencing parameters for judging whether the vehicle exterior environment image data includes more information. According to these parameters, the amount of information contained in the vehicle exterior environment image data can be characterized, so that the vehicle exterior environment image data can be screened, effectively protecting the security of the data and significantly improving the efficiency of data processing.

[0062] In this embodiment, the image data of the external environment of the vehicle is obtained through the on-board camera equipped with the intelligent connected car, and the vehicle operation data is obtained through on-board sensors, including wheel speed sensors, rotation speed sensors, acceleration sensors, and steering wheel angle sensors.

[0063] In this embodiment, a convolutional neural network is used to automatically extract image features. The convolutional neural network can automatically extract local features in the image and combine low-level features into high-level feature representations by layer-by-layer transmission. Optionally, a pre-trained model VGG16 is used to extract features. The extracted features are clustered using the K-means clustering algorithm. The number of clusters is determined using the elbow method.

[0064] Specifically, the step S3 further includes calculating a safety enhancement tendency characterization value according to the number of clusters and the change value of the vehicle operation data.

[0065] The ratio of the number of clusters to the preset threshold number of clusters is recorded as the first weighted influence amount;

[0066] Obtaining a sum of a ratio of a vehicle speed change value to a preset vehicle speed change value threshold, a ratio of an engine speed change value to a preset engine speed change value threshold, a ratio of a vehicle acceleration change value to a preset vehicle acceleration change value threshold, and a ratio of a vehicle steering angle change value to a preset vehicle steering angle change value threshold, and recording the sum as a second weighted influence amount;

[0067] The first weighted influence amount and the second weighted influence amount are weightedly summed to obtain a safety enhancement tendency representation value.

[0068] In this embodiment, the preset cluster number threshold C0, the preset vehicle speed change value threshold v0, the preset ratio of the engine speed change value threshold r0, the preset vehicle acceleration change value threshold a0, and the preset vehicle steering angle change value threshold θ0 are all obtained in advance through experiments. By calling historical data, the number of clusters of several vehicle exterior environment image data is obtained, and the average number of clusters Ce is calculated. Let C0 = k × Ce, k is the cluster number coefficient, 0.9 < k < 1.1, obtain vehicle operation data in several time periods, and calculate the vehicle speed. The average value of the speed change value ve, the average value of the engine speed change value re, the average value of the vehicle acceleration change value ae, the average value of the vehicle steering angle change value θe, let v0 = g × ve, g is the vehicle speed change value coefficient, 0.9 < g < 1.1, let r0 = m × re, m is the engine speed change value coefficient, 0.9 < m < 1.1, let a0 = n × ae, n is the vehicle acceleration change value coefficient, 0.9 < n < 1.1, let θ0 = j × θe, j is the vehicle steering angle change value coefficient, 0.9 < j < 1.1.

[0069] In this embodiment, the weight coefficient of the first weighted influence is 0.7, and the weight coefficient of the second weighted influence is 0.3.

[0070] Specifically, the step S3 further includes dividing the security enhancement tendency into categories according to the security enhancement tendency characterization value, and the process of dividing the security enhancement tendency into categories includes:

[0071] The safety enhancement tendency characterization value is compared with the preset safety enhancement tendency characterization value comparison threshold.

[0072] If the security enhancement tendency representation value is greater than the preset security enhancement tendency representation value comparison threshold, the security enhancement tendency category is classified as a strong security enhancement tendency category;

[0073] If the security enhancement tendency characterization value is less than or equal to the preset security enhancement tendency characterization value comparison threshold, the security enhancement tendency category is classified as a weak security enhancement tendency category.

[0074] In this embodiment, the preset security enhancement tendency characterization value comparison threshold is selected within the range of [1.8, 2.0].

[0075] Specifically, in step S4, in response to a preset category, the preset category is a strong security enhancement tendency category.

[0076] Specifically, in step S4, a number of clusters are selected, wherein the number of the selected clusters is positively correlated with the number of clusters in the vehicle exterior environment image data.

[0077] It can be understood that the more clusters there are in the vehicle exterior environment image data, the more clusters there are selected.

[0078] Specifically, in the step S4, the size of the remaining clusters in the vehicle exterior environment image data is adjusted, wherein there is an adjustment ratio corresponding to the number of the remaining clusters.

[0079] In this embodiment,

[0080] 1≤The number of remaining clusters is less than 3, and the adjustment ratio is reduced by 0.8 times;

[0081] 3≤The number of remaining clusters is less than 5, and the adjustment ratio is reduced by 0.6 times;

[0082] 5≤the number of remaining clusters, and the adjustment ratio is 1.2 times.

[0083] In this embodiment, adding a layer to the cluster can programmatically add a layer to the vehicle exterior environment image data through Python's PIL.

[0084] In this embodiment, the findContours function in OpenCV is used to obtain the contour position.

[0085] Specifically, the present invention obtains camouflaged exterior vehicle environment image data by adding layers to any number of clusters, obtaining the contour positions of the clusters, and adjusting the sizes of the remaining clusters in the exterior vehicle environment image data. By processing the exterior vehicle environment image data containing a large amount of information by blocking any clusters in the image and adjusting the sizes of the remaining clusters in the image, the difficulty of obtaining the original exterior vehicle environment image data will be increased, thereby improving the security of the data.

[0086] Specifically, in step S5, the undisguised vehicle exterior environment image data is vehicle exterior environment image data of a weak security enhancement tendency category.

[0087] Specifically, in step S6, the process of adjusting the size of the remaining clusters in the camouflaged vehicle exterior environment image data includes:

[0088] Determine the number of remaining clusters;

[0089] Determine the adjustment ratio based on the number of remaining clusters;

[0090] The sizes of the remaining clusters in the disguised vehicle exterior environment image data are adjusted according to the adjustment ratio.

[0091] For example, in this embodiment, the number of weak residual clusters is 3, and it is determined that the disguised vehicle exterior environment image data is obtained by reducing the vehicle exterior environment image data by 0.8 times, and the disguised vehicle exterior environment image data needs to be restored according to the proportion.

[0092] Specifically, the present invention encrypts the camouflaged exterior vehicle environment image data, the contour position of the clusters, and the uncamouflaged exterior vehicle environment image data. By processing the exterior vehicle environment image data containing more information and encrypting it together with the unprocessed exterior vehicle environment image data, the security of all data can be improved again after the security of important data is improved in advance.

[0093] See also Figure 3-4 As shown, the present invention also provides an intelligent networked vehicle safety enhancement system based on artificial intelligence, comprising:

[0094] A data acquisition module is used to obtain image data of the vehicle's external environment and vehicle operation data, wherein the vehicle operation data includes vehicle speed, engine speed, vehicle acceleration and vehicle steering angle;

[0095] An image analysis module, connected to the data acquisition module, for automatically extracting image features of the vehicle exterior environment image data through a convolutional neural network, performing cluster analysis on the image features based on shape and size, and obtaining the number of clusters;

[0096] The data processing module is connected to each of the data acquisition modules and the image analysis module, and includes an image classification unit, an image encryption unit and a data sending unit.

[0097] The image classification unit is used to classify the number of clusters into safety enhancement tendency categories in combination with the vehicle operation data change value;

[0098] The image encryption unit is used to select a plurality of clusters in response to a preset category, add a layer on the cluster, obtain the contour position of the cluster, and adjust the size of the remaining clusters in the vehicle exterior environment image data to obtain the disguised vehicle exterior environment image data;

[0099] The data sending unit is used to encrypt the disguised vehicle exterior environment image data, the outline position of the cluster and the undisguised vehicle exterior environment image data, and send all of them to the data receiving end after obtaining the encrypted ciphertext;

[0100] An image decryption module is connected to the data processing module and is used for the data receiving end to obtain the encrypted ciphertext, the encrypted disguised vehicle exterior environment image data, the outline position of the cluster and the undisguised vehicle exterior environment image data, decrypt the encrypted ciphertext and obtain the undisguised vehicle exterior environment image data;

[0101] And, for the disguised vehicle exterior environment image data, the layers of the disguised vehicle exterior environment image data are removed according to the contour positions of the clusters, and the sizes of the remaining clusters in the disguised vehicle exterior environment image data are adjusted to obtain the entire vehicle exterior environment image data.

[0102] Specifically, it also includes a display module for displaying image data of the vehicle's exterior environment.

[0103] The modules involved in the embodiments described in the present application may be implemented by software or hardware. The modules described may also be arranged in a processor, wherein the names of these modules do not constitute a limitation on the modules themselves in some cases.

[0104] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the device, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based device that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0105] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0106] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A safety enhancement method for intelligent connected vehicles based on artificial intelligence, characterized in that: include: Step S1, acquiring vehicle exterior environment image data and vehicle operation data, wherein the vehicle operation data includes vehicle speed, engine speed, vehicle acceleration and vehicle steering angle; Step S2, automatically extracting image features of the vehicle exterior environment image data through a convolutional neural network, performing cluster analysis on the image features based on shape and size, and obtaining the number of clusters; Step S3, dividing the number of clusters into safety enhancement tendency categories in combination with the change value of vehicle operation data; Step S4, in response to the preset category, select a number of clusters, add a layer on the cluster, obtain the outline position of the cluster, and adjust the size of the remaining clusters in the vehicle exterior environment image data to obtain the camouflaged vehicle exterior environment image data; Step S5, encrypting the disguised vehicle exterior environment image data, the contour positions of the clusters, and the undisguised vehicle exterior environment image data, and sending all of them to the data receiving end after obtaining the encrypted ciphertext; Step S6, the data receiving end obtains the encrypted ciphertext, the encrypted disguised vehicle exterior environment image data, the outline position of the cluster, and the undisguised vehicle exterior environment image data, decrypts the encrypted ciphertext, and obtains the undisguised vehicle exterior environment image data; And, for the disguised vehicle exterior environment image data, the layers of the disguised vehicle exterior environment image data are removed according to the contour positions of the clusters, and the sizes of the remaining clusters in the disguised vehicle exterior environment image data are adjusted to obtain the entire vehicle exterior environment image data.

2. The method for enhancing safety of intelligent connected vehicles based on artificial intelligence according to claim 1, characterized in that: The step S3 also includes calculating a safety enhancement tendency characterization value according to the number of clusters and the change value of the vehicle operation data, The ratio of the number of clusters to the preset threshold number of clusters is recorded as the first weighted influence amount; Obtaining a sum of a ratio of a vehicle speed change value to a preset vehicle speed change value threshold, a ratio of an engine speed change value to a preset engine speed change value threshold, a ratio of a vehicle acceleration change value to a preset vehicle acceleration change value threshold, and a ratio of a vehicle steering angle change value to a preset vehicle steering angle change value threshold, and recording the sum as a second weighted influence amount; The first weighted influence amount and the second weighted influence amount are weightedly summed to obtain a safety enhancement tendency representation value.

3. The method for enhancing safety of intelligent connected vehicles based on artificial intelligence according to claim 2, characterized in that: The step S3 further includes dividing the security enhancement tendency into categories according to the security enhancement tendency characterization value, and the process of dividing the security enhancement tendency into categories includes: The safety enhancement tendency characterization value is compared with the preset safety enhancement tendency characterization value comparison threshold. If the security enhancement tendency representation value is greater than the preset security enhancement tendency representation value comparison threshold, the security enhancement tendency category is classified as a strong security enhancement tendency category; If the security enhancement tendency characterization value is less than or equal to the preset security enhancement tendency characterization value comparison threshold, the security enhancement tendency category is classified as a weak security enhancement tendency category.

4. The method for enhancing safety of intelligent connected vehicles based on artificial intelligence according to claim 1, characterized in that: In the step S4, a preset category is responded to, wherein the preset category is a strong security enhancement tendency category.

5. The method for enhancing safety of intelligent connected vehicles based on artificial intelligence according to claim 1, characterized in that: In the step S4, a number of clusters are selected, wherein the number of the selected clusters is positively correlated with the number of clusters in the vehicle exterior environment image data.

6. The method for enhancing safety of intelligent connected vehicles based on artificial intelligence according to claim 1, characterized in that: In the step S4, the size of the remaining clusters in the vehicle exterior environment image data is adjusted, wherein there is an adjustment ratio corresponding to the number of the remaining clusters.

7. The method for enhancing safety of intelligent connected vehicles based on artificial intelligence according to claim 1, characterized in that: In the step S5, the undisguised vehicle exterior environment image data is vehicle exterior environment image data of a weak security enhancement tendency category.

8. The method for enhancing safety of intelligent connected vehicles based on artificial intelligence according to claim 1, characterized in that: In step S6, the process of adjusting the size of the remaining clusters in the disguised vehicle exterior environment image data includes: Determine the number of remaining clusters; Determine the adjustment ratio based on the number of remaining clusters; The sizes of the remaining clusters in the disguised vehicle exterior environment image data are adjusted according to the adjustment ratio.

9. The safety enhancement system of intelligent connected vehicles based on artificial intelligence is characterized by: The artificial intelligence-based intelligent connected vehicle safety enhancement method according to any one of claims 1 to 8 is applied, and the artificial intelligence-based intelligent connected vehicle safety enhancement system comprises: A data acquisition module is used to obtain image data of the vehicle's external environment and vehicle operation data, wherein the vehicle operation data includes vehicle speed, engine speed, vehicle acceleration and vehicle steering angle; An image analysis module, connected to the data acquisition module, for automatically extracting image features of the vehicle exterior environment image data through a convolutional neural network, performing cluster analysis on the image features based on shape and size, and obtaining the number of clusters; The data processing module is connected to each of the data acquisition modules and the image analysis module, and includes an image classification unit, an image encryption unit and a data sending unit. The image classification unit is used to classify the number of clusters into safety enhancement tendency categories in combination with the vehicle operation data change value; The image encryption unit is used to select a plurality of clusters in response to a preset category, add a layer on the cluster, obtain the contour position of the cluster, and adjust the size of the remaining clusters in the vehicle exterior environment image data to obtain the disguised vehicle exterior environment image data; The data sending unit is used to encrypt the disguised vehicle exterior environment image data, the outline position of the cluster and the undisguised vehicle exterior environment image data, and send all of them to the data receiving end after obtaining the encrypted ciphertext; An image decryption module is connected to the data processing module and is used for the data receiving end to obtain the encrypted ciphertext, the encrypted disguised vehicle exterior environment image data, the outline position of the cluster and the undisguised vehicle exterior environment image data, decrypt the encrypted ciphertext and obtain the undisguised vehicle exterior environment image data; And, for the disguised vehicle exterior environment image data, the layers of the disguised vehicle exterior environment image data are removed according to the contour positions of the clusters, and the sizes of the remaining clusters in the disguised vehicle exterior environment image data are adjusted to obtain the entire vehicle exterior environment image data.

10. The artificial intelligence-based intelligent connected vehicle safety enhancement system according to claim 9, characterized in that: It also includes a display module for displaying image data of the vehicle's exterior environment.

Images