Intelligent interconnection platform navigation system based on Android vehicle machine

Abstract

The invention discloses an intelligent interconnection platform navigation system based on an Android vehicle machine, and relates to the technical field of navigation analysis, and the system comprises a navigation path planning module which is used for generating an optimal navigation path based on an Android vehicle machine system corresponding to a target vehicle; the data acquisition module is used for acquiring environment data and driving behavior data; the path analysis module is used for analyzing and processing the optimal navigation path, determining a dangerous road section corresponding to the optimal navigation path, and determining a path danger score in combination with the dangerous road section and the environment data; the driving analysis module is used for analyzing the corresponding driving behavior data when the driver drives on each dangerous road section, and determining a driving behavior danger score; and the safety risk assessment module is used for confirming a driving risk score corresponding to the driver and providing corresponding alarm information for the driver according to the driving risk score. The method and the device have the effect of improving driving safety.

Description

Technical Field

[0001] The present application relates to the field of navigation analysis technology, and in particular to an intelligent interconnected platform navigation system based on Android vehicle machines. Background Art

[0002] With the development of intelligent transportation technology, more and more vehicles are equipped with Android-based car platforms. These platforms provide drivers with a convenient driving experience by integrating navigation, communication and entertainment functions. Modern navigation systems not only rely on high-precision maps and real-time traffic information, but also combine driving behavior analysis and environmental perception technology to improve navigation safety and efficiency.

[0003] In the related technologies, the existing Internet platform navigation system is unable to dynamically adjust the navigation strategy in real time to cope with sudden traffic conditions or improper driver behavior. At the same time, the lack of a comprehensive assessment and early warning mechanism for driving risks may lead to the failure to provide effective safety tips in a timely manner on dangerous roads, affecting driving safety and user experience. There is room for improvement. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present application provides an intelligent interconnected platform navigation system based on Android car machine.

[0005] In the first aspect, the present application provides an intelligent interconnected platform navigation system based on Android vehicle machine, including:

[0006] The navigation path planning module is used to generate the optimal navigation path based on the Android vehicle system corresponding to the target vehicle and the destination information corresponding to the driver;

[0007] A data collection module, used to collect environmental data and driving behavior data corresponding to the target vehicle when it travels along the optimal navigation path;

[0008] A path analysis module, used to analyze and process the optimal navigation path, identify the corresponding dangerous section on the optimal navigation path, and identify the path danger score in combination with the dangerous section and the environmental data;

[0009] A driving analysis module is used to analyze the driving behavior data corresponding to the driver when driving on each dangerous road section, and then determine the driving behavior risk score based on the analysis results;

[0010] The safety risk assessment module is used to comprehensively analyze the path risk score and the driving behavior risk score, thereby confirming the driving risk score corresponding to the driver, and providing corresponding warning information to the driver based on the driving risk score.

[0011] Preferably, the optimal navigation path is generated based on the Android vehicle system corresponding to the target vehicle and in combination with the destination information corresponding to the driver, specifically including:

[0012] Confirming the initial position information corresponding to the target vehicle, and constructing a road network topology map based on the initial position information corresponding to the target vehicle and the destination information corresponding to the driver, wherein the road network topology map is set as a node-edge weighted graph structure;

[0013] Obtaining weight coefficients corresponding to each edge in the road network topology graph, and then generating an optimal navigation path based on the weight coefficients corresponding to each edge in the road network topology graph;

[0014] The process of obtaining the weight coefficient corresponding to each edge in the road network topology graph specifically includes:

[0015] By formula C i =T i *a1+D i *a2+R i *a3, confirm the weight coefficient C corresponding to each edge i , where i represents the number corresponding to each edge, i=1,2,3.......j, T i Denotes the travel time corresponding to the ith edge, D i Represented as the length of the road segment corresponding to the i-th edge, R i It is expressed as the difficulty coefficient corresponding to the i-th edge.

[0016] Preferably, the environmental data includes traffic flow data and weather data, and the driving behavior data includes emergency braking data, emergency acceleration data and speeding data.

[0017] Preferably, analyzing and processing the optimal navigation path to identify the corresponding dangerous road section on the optimal navigation path, and identifying the path danger score in combination with the dangerous road section information and the environmental data, specifically includes:

[0018] Confirming an optimal navigation path, and inputting the optimal navigation path into a preset road segment identification model, thereby identifying corresponding dangerous road segments on the optimal navigation path, wherein the dangerous road segments include the number of dangerous road segments and basic danger scores corresponding to each dangerous road segment, wherein the basic danger scores corresponding to each dangerous road segment are set by road segment characteristics corresponding to each dangerous road segment;

[0019] Collecting in real time the environmental data corresponding to when the target vehicle passes through each of the dangerous sections, and extracting from the environmental data the traffic flow data and weather data corresponding to when the target vehicle passes through each of the dangerous sections, and then confirming the real-time traffic correction coefficient and the real-time weather correction coefficient based on the traffic flow data and weather data;

[0020] By formula Determine the path hazard score S corresponding to each dangerous section when the target vehicle passes through i , where i represents the number corresponding to each dangerous road section, i=1,2,3......j, They are respectively represented as the basic danger score, real-time traffic correction coefficient, and real-time weather correction coefficient corresponding to the dangerous road section numbered i.

[0021] Preferably, the driving behavior data corresponding to the driver when driving on each dangerous road section is analyzed, and then the driving behavior risk score is determined based on the analysis results, specifically including:

[0022] Acquire driving behavior data corresponding to the driver when driving on each dangerous road section, and extract emergency braking data, emergency acceleration data and speeding data from the driving behavior data, and then confirm the emergency braking risk value, emergency acceleration risk value and speeding risk value corresponding to the driver when driving on each dangerous road section based on the emergency braking data, emergency acceleration data and speeding data;

[0023] By formula P i =Jsc i *ω1+Jjs i *ω2+Cs i *ω3, confirm the driving behavior risk score P corresponding to the driver when driving on each dangerous road section i , where Jsc i 、Jjs i , Cs i They respectively represent the emergency braking risk value, sudden acceleration risk value, and speeding risk value corresponding to the driver when driving on the dangerous road section numbered i, and ω1, ω2, and ω3 are represented as weight coefficients.

[0024] Preferably, a comprehensive analysis is performed on the path risk score and the driving behavior risk score to determine the driving risk score corresponding to the driver, and corresponding warning information is provided to the driver according to the driving risk score, specifically including:

[0025] The path hazard score S corresponding to the target vehicle passing through each dangerous section i and the driving behavior risk score P corresponding to the driver when driving on each dangerous road section i Substitute into formula K i =S i *ψ1+P i *ψ2, confirm the driving risk score K corresponding to the driver at each dangerous road section i , where ψ1 and ψ2 represent the weight coefficients corresponding to the path risk score and driving behavior risk score respectively;

[0026] Compare the driving risk score K corresponding to the driver on each dangerous section i with the preset driving risk threshold range [K′, K″];

[0027] If there is a driving risk score K corresponding to a dangerous section i < K′, then output the first warning message;

[0028] If there is a driving risk score K corresponding to a dangerous section i between [K′, K″], then output the second warning message;

[0029] If there is a driving risk score K corresponding to a dangerous section i > K″, then output the third warning message.

[0030] Preferably, after confirming the driving risk score corresponding to the driver on each dangerous section, it further includes:

[0031] During the preset time period, collect in real time the driving risk scores corresponding to the driver on each dangerous section, and construct a curve K i (t) of the driving risk scores corresponding to the driver on each dangerous section changing with time,

[0032] Through the formula confirm the change coefficient r of the driving risk scores corresponding to the driver on each dangerous section i , where [t1, t2] represents the preset time period;

[0033] Compare the change coefficient r of the driving risk scores corresponding to the driver on each dangerous section i with the preset change threshold r′;

[0034] If there is a change coefficient r of the driving risk scores corresponding to a dangerous section i > r′, it is determined that the driving risk of the driver on the dangerous section increases, and a warning signal needs to be output to the driver.

[0035] In a second aspect, the present application provides an intelligent interconnection platform navigation method based on an Android vehicle head unit, including the following steps:

[0036] Based on the Android vehicle head unit system corresponding to the target vehicle, and combined with the destination information corresponding to the driver, generate the optimal navigation path;

[0037] Collect the environmental data and driving behavior data corresponding to the target vehicle when driving along the optimal navigation path;

[0038] Analyzing and processing the optimal navigation path, identifying a corresponding dangerous section on the optimal navigation path, and identifying a path danger score in combination with the dangerous section and the environmental data;

[0039] Analyze the driving behavior data corresponding to the driver when driving on each dangerous road section, and then determine the driving behavior risk score based on the analysis results;

[0040] A comprehensive analysis is performed on the path hazard score and the driving behavior hazard score to determine the driver's corresponding driving risk score, and corresponding warning information is provided to the driver based on the driving risk score.

[0041] In a third aspect, the present application provides a computer-readable storage medium storing instructions, which, when executed on a computer, enables the computer to execute any one of the above-mentioned smart interconnected platform navigation systems based on an Android vehicle machine.

[0042] In summary, this application includes the following beneficial technical effects:

[0043] The present invention provides an intelligent interconnected platform navigation system based on an Android vehicle machine, which generates an optimal navigation path and collects and analyzes the corresponding environmental data and driving behavior data when a target vehicle travels along the optimal navigation path, thereby confirming a path hazard score and a driving behavior hazard score, and comprehensively analyzing the path hazard score and the driving behavior hazard score, thereby confirming a driving risk score corresponding to a driver, and providing corresponding warning information to the driver according to the driving risk score, thereby effectively reducing the occurrence of situations that affect driving safety due to sudden traffic conditions or improper behavior of the driver, and at the same time, effectively performing a comprehensive assessment and early warning mechanism for driving risks, thereby timely providing effective safety prompts on dangerous sections, and effectively ensuring driving safety and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0045] Figure 1 It is a system diagram of the smart interconnected platform navigation based on Android car machine in the embodiment of the present application.

[0046] Figure 2 It is a flow chart of the method for navigation based on the smart interconnected platform of the Android car machine in the embodiment of the present application. DETAILED DESCRIPTION

[0047] The following is combined with Figure 1-2 This application is described in further detail.

[0048] Example 1

[0049] The embodiment of the present application discloses an intelligent interconnected platform navigation system based on Android vehicle machine.

[0050] Reference Figure 1 , an intelligent interconnected platform navigation system based on Android car machine, including:

[0051] The navigation path planning module is used to generate the optimal navigation path based on the Android vehicle system corresponding to the target vehicle and the destination information corresponding to the driver;

[0052] A data collection module, used to collect environmental data and driving behavior data corresponding to the target vehicle when it travels along the optimal navigation path;

[0053] A path analysis module, used to analyze and process the optimal navigation path, identify the corresponding dangerous section on the optimal navigation path, and identify the path danger score in combination with the dangerous section and the environmental data;

[0054] A driving analysis module is used to analyze the driving behavior data corresponding to the driver when driving on each dangerous road section, and then determine the driving behavior risk score based on the analysis results;

[0055] The safety risk assessment module is used to comprehensively analyze the path risk score and the driving behavior risk score, thereby confirming the driving risk score corresponding to the driver, and providing corresponding warning information to the driver based on the driving risk score.

[0056] It should be noted that the optimal navigation path is generated based on the Android vehicle system corresponding to the target vehicle and the destination information corresponding to the driver, including:

[0057] Confirming the initial position information corresponding to the target vehicle, and constructing a road network topology map based on the initial position information corresponding to the target vehicle and the destination information corresponding to the driver, wherein the road network topology map is set as a node-edge weighted graph structure;

[0058] Obtaining weight coefficients corresponding to each edge in the road network topology graph, and then generating an optimal navigation path based on the weight coefficients corresponding to each edge in the road network topology graph;

[0059] The process of obtaining the weight coefficient corresponding to each edge in the road network topology graph specifically includes:

[0060] By formula Ci =T i *a1+D i *a2+R i *a3, confirm the weight coefficient C corresponding to each edge i , where i represents the number corresponding to each edge, i=1,2,3.......j, T i Denotes the travel time corresponding to the ith edge, D i Represented as the length of the road segment corresponding to the i-th edge, R i It is expressed as the difficulty coefficient corresponding to the i-th edge.

[0061] Specifically, in the embodiment of the present application, the nodes in the road network topology graph are represented as key points such as road intersections, initial positions, and destinations, and the edges in the road network topology graph are represented as road segments. The weight coefficients corresponding to the edges are the weight coefficients corresponding to the road segments, where T i It is represented as the travel time corresponding to the ith edge. The travel time is obtained from the real-time traffic flow corresponding to each road segment. That is, the greater the real-time traffic flow, the longer the travel time, and the greater the weight coefficient corresponding to the road segment. i It is expressed as the length of the road segment corresponding to the i-th edge. That is, the longer the road segment length, the greater the weight coefficient corresponding to the road segment. i It is expressed as the difficulty coefficient corresponding to the i-th edge, and the difficulty coefficient is obtained by fitting factors such as sharp turns and steep slopes contained in the road segment, that is, the greater the difficulty coefficient, the greater the weight coefficient corresponding to the road segment; then the corresponding weight coefficient corresponding to each edge is obtained, and the road segment with a smaller weight coefficient is selected as the optimal navigation path. For long-distance driving, the path can be divided into multiple sub-paths (such as highway sections and urban sections) to optimize each path separately, and then merge them into a global path.

[0062] Furthermore, the environmental data includes traffic flow data and weather data, and the driving behavior data includes emergency braking data, emergency acceleration data and speeding data.

[0063] It should be noted that the analysis and processing of the optimal navigation path to identify the corresponding dangerous road section on the optimal navigation path and the determination of the path danger score in combination with the dangerous road section information and the environmental data specifically includes:

[0064] Confirming an optimal navigation path, and inputting the optimal navigation path into a preset road segment identification model, thereby identifying corresponding dangerous road segments on the optimal navigation path, wherein the dangerous road segments include the number of dangerous road segments and basic danger scores corresponding to each dangerous road segment, wherein the basic danger scores corresponding to each dangerous road segment are set by road segment characteristics corresponding to each dangerous road segment;

[0065] Collecting in real time the environmental data corresponding to when the target vehicle passes through each of the dangerous sections, and extracting from the environmental data the traffic flow data and weather data corresponding to when the target vehicle passes through each of the dangerous sections, and then confirming the real-time traffic correction coefficient and the real-time weather correction coefficient based on the traffic flow data and weather data;

[0066] By formula Confirm the path hazard score S route , where i represents the number corresponding to each dangerous road section, i=1,2,3......j, F i weather They are respectively represented as the basic danger score, real-time traffic correction coefficient, and real-time weather correction coefficient corresponding to the dangerous road section numbered i.

[0067] Specifically, in the embodiment of the present application, the dangerous road section includes a sharp bend, a steep slope and a congested area, wherein the basic danger score corresponding to each dangerous road section is set by the road section characteristics corresponding to each dangerous road section. For example, when the dangerous road section is a sharp bend, the basic danger score corresponding to the sharp bend is set according to the curvature radius corresponding to the sharp bend, that is, the smaller the curvature radius, the higher the basic danger score; when the dangerous road section is a steep slope, the basic danger score corresponding to the steep slope is set according to the slope corresponding to the steep slope, that is, the greater the slope, the higher the basic danger score; if the dangerous road section is a congested area, the basic danger score corresponding to the congested area is set according to the congestion degree corresponding to the congested area, that is, the more serious the congestion, the higher the basic danger score;

[0068] The real-time traffic correction coefficient is expressed as the impact of the traffic flow data of each dangerous road section on the basic risk score. In the embodiment of the present application, when the traffic flow data is unblocked, the real-time traffic correction coefficient is 1.0; when the traffic flow data is congested, the real-time traffic correction coefficient is 1.2; when the traffic flow data is severely congested, the real-time traffic correction coefficient is 1.5;

[0069] The real-time weather correction coefficient represents the impact of the weather data of each dangerous road section on the basic risk score. In the embodiment of the present application, when the weather data is sunny, the real-time weather correction coefficient is 1.0; when the weather data is rainy, the real-time weather correction coefficient is 1.3; when the weather data is snowy or foggy, the real-time weather correction coefficient is 1.5.

[0070] Specifically, by combining the basic hazard score of each dangerous section, the real-time traffic correction factor and the real-time weather correction factor to confirm the path hazard score, the actual risk of the road can be dynamically assessed, and the current road conditions and weather changes can be reflected in a timely manner, thereby improving the accuracy and safety of the navigation system, helping drivers make more informed driving decisions, and effectively reducing the risk of accidents.

[0071] It should be noted that the driving behavior data corresponding to the driver when driving on each dangerous road section is analyzed, and then the driving behavior risk score is determined based on the analysis results, specifically including:

[0072] Acquire driving behavior data corresponding to the driver when driving on each dangerous road section, and extract emergency braking data, emergency acceleration data and speeding data from the driving behavior data, and then confirm the emergency braking risk value, emergency acceleration risk value and speeding risk value corresponding to the driver when driving on each dangerous road section based on the emergency braking data, emergency acceleration data and speeding data;

[0073] By formula P i =Jsc i *ω1+Jjs i *ω2+Cs i *ω3, confirm the driving behavior risk score P corresponding to the driver when driving on each dangerous road section i , where Jsc i 、Jjs i , Cs i They respectively represent the emergency braking risk value, sudden acceleration risk value, and speeding risk value corresponding to the driver when driving on the dangerous road section numbered i, and ω1, ω2, and ω3 are represented as weight coefficients.

[0074] Specifically, in the embodiment of the present application, the emergency braking risk value can be calculated by the braking force and frequency, and the formula Confirm the emergency braking risk value, where F brake 、F max Respectively represent the current braking force and the maximum vehicle-involved force threshold, N brake 、N total They are respectively expressed as the number of emergency brakes and the total number of brakes, and a1 and a2 are expressed as weight coefficients;

[0075] The risk value of sudden acceleration can be calculated by the acceleration and frequency, using the formula Confirm the risk value of sudden acceleration, where A accel , A max Respectively represent the current acceleration, the maximum acceleration threshold, H accel , H total They are respectively represented as the number of rapid accelerations and the total number of accelerations, and b1 and b2 are represented as weight coefficients;

[0076] The speeding risk value can be calculated by the speeding degree and speeding duration, using the formula Confirm the speeding risk value, where V actual 、V lim Respectively represent the actual vehicle speed and speed limit value, T speed , Ttotal They are respectively represented as the overspeed duration and the total driving time, and c1 and c2 are represented as weight coefficients;

[0077] Specifically, by calculating the risk values of hard braking, hard acceleration, and overspeed, it is possible to comprehensively evaluate the driving behavior risk score of the driver on dangerous sections, and it helps to identify potential high-risk behaviors of the driver under specific road conditions. The hard braking risk value can reveal the problem of insufficient anticipation ability or overreaction of the driver to the road conditions ahead, while the hard acceleration risk value may reflect improper control or neglect of the road conditions by the driver. The overspeed risk value is directly related to the degree of compliance with traffic regulations. Overspeed driving is particularly dangerous on dangerous sections because it increases the possibility of vehicle out of control and the severity of accidents. By combining the above risk values, the driving behavior risk score provides a comprehensive safety assessment index, which can not only provide immediate safety warnings for drivers, but also provide detailed behavior analysis reports after the driving is over, helping drivers identify and improve bad driving habits, thereby contributing to improving driving safety, reducing the probability of accidents, and protecting the safety of drivers and other road users.

[0078] Furthermore, by comprehensively analyzing the path risk score and the driving behavior risk score, the corresponding driving risk score of the driver is confirmed, and corresponding warning information is provided to the driver according to the driving risk score, specifically including:

[0079] Substitute the path risk score S i corresponding to when the target vehicle passes through each dangerous section and the driving behavior risk score P i corresponding to when the driver drives on each dangerous section into the formula K i = S i *ψ1 + P i *ψ2, and confirm the driving risk score K i corresponding to the driver on each dangerous section. Among them, ψ1 and ψ2 are respectively represented as the weight coefficients corresponding to the path risk score and the driving behavior risk score;

[0080] Compare the driving risk score K i corresponding to the driver on each dangerous section with the preset driving risk threshold interval [K′, K″];

[0081] If there is a driving risk score K i < K′ corresponding to a dangerous section, then output the first warning information;

[0082] If there is a driving risk score K i within [K′, K″] corresponding to a dangerous section, then output the second warning information;

[0083] If there is a driving risk score K corresponding to a dangerous road section i >K″, the third alarm information is output.

[0084] Specifically, in an embodiment of the present application, the first alarm message is set to prompt the driver to continue to maintain the current driving state, the second alarm message is set to remind the driver to pay attention to the road conditions ahead and suggest slowing down, and the third alarm message is set to issue a warning and suggest taking immediate measures (such as slowing down and keeping a safe distance).

[0085] Furthermore, after confirming the driving risk score of the driver on each dangerous road section, it also includes:

[0086] In the preset time period, the driving risk scores of drivers at each dangerous section are collected in real time, and a curve K showing the driving risk scores of drivers at each dangerous section changing with time is constructed. i (t),

[0087] By formula Identify the change coefficient r corresponding to the driver's driving risk score at each dangerous road section i , where [t1, t2] represents the preset time period;

[0088] The coefficient of change r corresponding to the driver's driving risk score at each dangerous road section i Compare with the preset change threshold r′;

[0089] If there is a dangerous road section driving risk score corresponding to the change coefficient r i >r′, it is determined that the driving risk of the driver on the dangerous road section has increased, and a warning signal needs to be output to the driver.

[0090] Specifically, in the embodiment of the present application, the preset change threshold value r′ is a positive number, wherein a warning signal is output to the driver to provide an early warning, thereby helping the driver to adjust his behavior and ensure driving safety.

[0091] Example 2

[0092] The embodiment of the present application also discloses a navigation method for an intelligent interconnected platform based on an Android vehicle machine.

[0093] Reference Figure 2 , the navigation method of the intelligent interconnected platform based on the Android vehicle machine includes the following steps:

[0094] Generate the optimal navigation path based on the Android vehicle system corresponding to the target vehicle and the destination information corresponding to the driver;

[0095] Collecting environmental data and driving behavior data corresponding to the target vehicle when it travels along the optimal navigation path;

[0096] Analyzing and processing the optimal navigation path, identifying a corresponding dangerous section on the optimal navigation path, and identifying a path danger score in combination with the dangerous section and the environmental data;

[0097] Analyze the driving behavior data corresponding to the driver when driving on each dangerous road section, and then determine the driving behavior risk score based on the analysis results;

[0098] A comprehensive analysis is performed on the path hazard score and the driving behavior hazard score to determine the driver's corresponding driving risk score, and corresponding warning information is provided to the driver based on the driving risk score.

[0099] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention, they should all fall within the protection scope of the present invention.

[0100] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0101] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well.

Claims

1. The intelligent interconnected platform navigation system based on Android car machine is characterized by: include: The navigation path planning module is used to generate the optimal navigation path based on the Android vehicle system corresponding to the target vehicle and the destination information corresponding to the driver; A data collection module, used to collect environmental data and driving behavior data corresponding to the target vehicle when it travels along the optimal navigation path; A path analysis module, used to analyze and process the optimal navigation path, identify the corresponding dangerous section on the optimal navigation path, and identify the path danger score in combination with the dangerous section and the environmental data; A driving analysis module is used to analyze the driving behavior data corresponding to the driver when driving on each dangerous road section, and then determine the driving behavior risk score based on the analysis results; The safety risk assessment module is used to comprehensively analyze the path risk score and the driving behavior risk score, thereby confirming the driving risk score corresponding to the driver, and providing corresponding warning information to the driver based on the driving risk score.

2. The Android-based vehicle-mounted intelligent interconnected platform navigation system according to claim 1, characterized in that: Based on the Android vehicle system corresponding to the target vehicle and the destination information corresponding to the driver, the optimal navigation path is generated, including: Confirming the initial position information corresponding to the target vehicle, and constructing a road network topology map based on the initial position information corresponding to the target vehicle and the destination information corresponding to the driver, wherein the road network topology map is set as a node-edge weighted graph structure; Obtaining weight coefficients corresponding to each edge in the road network topology graph, and then generating an optimal navigation path based on the weight coefficients corresponding to each edge in the road network topology graph; The process of obtaining the weight coefficient corresponding to each edge in the road network topology graph specifically includes: The weight coefficient Ci corresponding to each edge is determined by the formula Ci=Ti*a1+Di*a2+Ri*a3, where i represents the number corresponding to each edge, i=1,2,3.......j, Ti represents the travel time corresponding to the i-th edge, Di represents the length of the road section corresponding to the i-th edge, and Ri represents the travel difficulty coefficient corresponding to the i-th edge.

3. The Android-based vehicle-mounted intelligent interconnected platform navigation system according to claim 1, characterized in that: The environmental data includes traffic flow data and weather data, and the driving behavior data includes emergency braking data, emergency acceleration data and speeding data.

4. The Android-based vehicle-mounted intelligent interconnected platform navigation system according to claim 3 is characterized in that: Analyzing and processing the optimal navigation path, identifying the corresponding dangerous road section on the optimal navigation path, and identifying the path danger score in combination with the dangerous road section information and the environmental data, specifically includes: Confirming an optimal navigation path, and inputting the optimal navigation path into a preset road segment identification model, thereby identifying corresponding dangerous road segments on the optimal navigation path, wherein the dangerous road segments include the number of dangerous road segments and basic danger scores corresponding to each dangerous road segment, wherein the basic danger scores corresponding to each dangerous road segment are set by road segment characteristics corresponding to each dangerous road segment; Collecting in real time the environmental data corresponding to when the target vehicle passes through each of the dangerous sections, and extracting from the environmental data the traffic flow data and weather data corresponding to when the target vehicle passes through each of the dangerous sections, and then confirming the real-time traffic correction coefficient and the real-time weather correction coefficient based on the traffic flow data and weather data; By formula Confirm the path danger score Si corresponding to each dangerous section when the target vehicle passes through it, where i represents the number corresponding to each dangerous section, i=1,2,3...j, They are respectively represented as the basic danger score, real-time traffic correction coefficient, and real-time weather correction coefficient corresponding to the dangerous road section numbered i.

5. The Android-based vehicle-mounted intelligent interconnected platform navigation system according to claim 4 is characterized in that: Analyze the driving behavior data corresponding to the driver when driving on each dangerous section, and then confirm the driving behavior danger score based on the analysis results, specifically including: Obtain the driving behavior data corresponding to the driver when driving on each dangerous section, extract the hard braking data, hard acceleration data, and speeding data from the driving behavior data, and then confirm the hard braking risk value, hard acceleration risk value, and speeding risk value corresponding to the driver when driving on each dangerous section based on the hard braking data, hard acceleration data, and speeding data; Confirm the driving behavior danger score Pi corresponding to the driver when driving on each dangerous section through the formula Pi = J sci * ω1 + J jsi * ω2 + C si * ω3, where J sci, J jsi, and C si respectively represent the hard braking risk value, hard acceleration risk value, and speeding risk value corresponding to the driver when driving on the dangerous section numbered i, and ω1, ω2, and ω3 represent the weight coefficients.

6. The Android-based vehicle-mounted intelligent interconnected platform navigation system according to claim 5, characterized in that: Conduct a comprehensive analysis of the path danger score and the driving behavior danger score, and then confirm the driving risk score corresponding to the driver, and provide corresponding warning information to the driver according to the driving risk score, specifically including: Substitute the path danger score Si corresponding to the target vehicle passing through each dangerous section and the driving behavior danger score Pi corresponding to the driver when driving on each dangerous section into the formula Ki = Si * ψ1 + Pi * ψ2 to confirm the driving risk score Ki corresponding to the driver on each dangerous section, where ψ1 and ψ2 respectively represent the weight coefficients corresponding to the path danger score and the driving behavior danger score; Compare the driving risk score Ki corresponding to the driver on each dangerous section with the preset driving risk threshold range [K′, K″]; If there is a driving risk score Ki < K′ corresponding to a dangerous section, then output the first warning information; If there is a driving risk score Ki corresponding to a dangerous section within [K′, K″], then output the second warning information; If there is a driving risk score Ki > K″ corresponding to a dangerous section, then output the third warning information.

7. The Android-based vehicle-mounted intelligent interconnected platform navigation system according to claim 6 is characterized in that: After confirming the driving risk score corresponding to the driver on each dangerous section, it also includes: During the preset time period, collect the driving risk scores corresponding to the driver on each dangerous section in real time, and construct a curve Ki(t) of the driving risk scores corresponding to the driver on each dangerous section changing with time; By formula Determine the change coefficient ri corresponding to the driver's driving risk score at each dangerous road section, where [t1, t2] represents a preset time period; Compare the change coefficient ri of the driving risk score corresponding to the driver on each dangerous section with the preset change threshold r′; If there is a change coefficient ri > r′ of the driving risk score corresponding to a dangerous section, then it is determined that the driving risk of the driver on the dangerous section increases, and a warning signal needs to be output to the driver.

8. An intelligent interconnected platform navigation method based on Android vehicle machine, applied to an intelligent interconnected platform navigation system based on Android vehicle machine as described in any one of claims 1 to 7, characterized in that: It includes the following steps: Generate the optimal navigation path based on the Android in-vehicle system corresponding to the target vehicle and in combination with the destination information corresponding to the driver; Collect the environmental data and driving behavior data corresponding to the target vehicle when driving along the optimal navigation path; Analyzing and processing the optimal navigation path, identifying a corresponding dangerous section on the optimal navigation path, and identifying a path danger score in combination with the dangerous section and the environmental data; Analyze the driving behavior data corresponding to the driver when driving on each dangerous road section, and then determine the driving behavior risk score based on the analysis results; A comprehensive analysis is performed on the path hazard score and the driving behavior hazard score to determine the driver's corresponding driving risk score, and corresponding warning information is provided to the driver based on the driving risk score.

9. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are run on a computer, the computer executes the intelligent interconnected platform navigation system based on the Android vehicle machine as described in any one of claims 1 to 7.

Images