Vehicle network switching method and device, equipment, storage medium and program product

By using the random forest classifier model in the vehicle network to predict network path quality and determine vulnerability locations, the application flow is migrated in advance, and the problem of unstable vehicle network connection is solved, and the network stability and data transmission efficiency of mobile vehicles are improved.

CN118984269APending Publication Date: 2024-11-19CHINA MOBILE ZIJIN INNOVATION INST CO LTD +2
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411156111.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-21
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

In the prior art, the vehicle network connection is unstable and a single network cannot provide complete geographical coverage, resulting in network vulnerabilities and failure recovery time being too long, affecting the service continuity of the vehicle network system.

Method used

By entering map information and network information into the trained random forest classifier model, predict network path quality, determine network vulnerability location, and calculate flow switching time based on vehicle location and speed, migrate application flow to redundant network paths in advance , ensure the stability of network connection.

Benefits of technology

It realizes maintaining stable network connections during vehicle movement, foreseeing and responding to potential network vulnerabilities, improving network availability and data transmission efficiency, and ensuring uninterrupted service.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118984269A_ABST
    Figure CN118984269A_ABST
Patent Text Reader

Abstract

The invention discloses a vehicle network switching method, a vehicle network switching device, vehicle network switching equipment, a storage medium and a computer program product, and relates to the technical field of communication, and the method comprises the steps: firstly, inputting collected map information and network information into a trained random forest classifier model, predicting the quality of a network path, and then, carrying out the prediction of the quality of the network path; the method comprises the steps of determining the position of a network vulnerability, the current position of a vehicle and the vehicle speed according to the quality of a network path, calculating to obtain the flow switching time for migrating an application program flow to a redundant network path, and finally migrating the application program flow to the redundant network path before the flow switching time is reached. Therefore, the network vulnerabilities on the path of the moving vehicle are calculated in real time, the future network availability is intelligently predicted, and the application data flow is automatically switched, so that the uninterrupted network service and the optimal data transmission efficiency are ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a vehicle network switching method, a vehicle network switching apparatus, a vehicle network switching device, a storage medium, and a computer program product. Background Art

[0002] At present, firstly, most mobile vehicles rely on a single communication provider. Usually, the availability and performance provided by the network service meet the requirements of various in-vehicle applications, but its performance indicators are rarely better than 99%, and there is still the possibility of downtime. At the critical moment of vehicle driving, network failure is very dangerous. Secondly, a single network operates as an independent routing domain and is an independent autonomous system. Due to various reasons such as network congestion that varies with time and location, each individual wireless network service cannot provide highly complete geographic coverage, which will cause network loopholes in the geographic coverage of the service provider, resulting in unstable services in the Internet of Vehicles system. Finally, the long convergence time of traditional routing protocols will destroy the continuity of application use, resulting in untimely information interaction in the Internet of Vehicles, which will have an adverse impact on user use.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present application is to provide a vehicle network switching method, a vehicle network switching device, a vehicle network switching equipment, a storage medium and a computer program product, aiming to solve the technical problem of unstable network connection of the Internet of Vehicles.

[0005] To achieve the above objectives, the present application proposes a vehicle network switching method, the vehicle network switching method comprising:

[0006] The collected map information and network information are input into the trained random forest classifier model to predict the quality of the network path;

[0007] Determine the location of network vulnerabilities based on the quality of network paths;

[0008] According to the current position of the vehicle, the position of the network vulnerability and the vehicle speed, the flow switching time for migrating the application flow to the redundant network path is calculated, and the application flow is migrated to the redundant network path before the flow switching time is reached.

[0009] In one embodiment, the step of inputting the collected map information and network information into the trained random forest classifier model to predict the quality of the network path includes:

[0010] Collecting time information, location information and weather information associated with a geographic location as map information;

[0011] Perform self-started connection measurement on each network service provider to obtain network information.

[0012] In one embodiment, the step of calculating the flow switching time for migrating the application flow to the redundant network path according to the current position of the vehicle, the position of the network vulnerability and the vehicle speed includes:

[0013] Obtain a flow table record storing an application sensitivity threshold, wherein the flow table record includes all relevant protocol information of a data link layer, a network layer, a transport layer, a session layer, a presentation layer, and an application layer;

[0014] The location of the network vulnerability is determined by the real-time measurement value of the network connection performance indicator in the flow table record and the preset sensitivity threshold of the application flow.

[0015] In one embodiment, the network vulnerability is the loss or degradation of network connection performance, and the location of the network vulnerability includes a temporary location and a permanent location.

[0016] In one embodiment, the step of migrating the application flow to the redundant network path includes:

[0017] Determine the preferred network path at the current time or when the flow switching time is reached, and use the preferred network path as a redundant network path to migrate the application flow to the redundant network path.

[0018] In one embodiment, the vehicle network switching method further includes:

[0019] The actual traffic life span of the application flow is determined based on the survival probability of the application flow under different traffic life spans and the error probability allowed in the actual switching of the network path.

[0020] In addition, to achieve the above-mentioned purpose, the present application also proposes a vehicle network switching device, the vehicle network switching device comprising:

[0021] The prediction module is used to input the collected map information and network information into the trained random forest classifier model to predict the quality of the network path;

[0022] A determination module, used to determine the location of network vulnerabilities based on the quality of network paths;

[0023] The migration module is used to calculate the flow switching time for migrating the application flow to the redundant network path according to the current position of the vehicle, the location of the network vulnerability and the vehicle speed, and migrate the application flow to the redundant network path before the flow switching time is reached.

[0024] In addition, to achieve the above-mentioned purpose, the present application also proposes a vehicle network switching device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the vehicle network switching method described above.

[0025] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the vehicle network switching method described above are implemented.

[0026] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the vehicle network switching method described above are implemented.

[0027] One or more technical solutions proposed in this application have at least the following technical effects:

[0028] In this application, a method for optimizing mobile vehicle network switching is proposed, aiming to ensure that the vehicle maintains a stable network connection during movement, and to foresee and respond to potential network vulnerabilities in the geographical coverage area before they occur by dynamically allocating the data flow of the application to other paths, thereby improving the network stability of the vehicle during movement. First, the collected map information and network information are input into the trained random forest classifier model to predict the quality of the network path. Then, the location of the network vulnerability, the current location of the vehicle, and the speed are determined based on the quality of the network path. The flow switching time for migrating the application flow to the redundant network path is calculated, and finally, the application flow is migrated to the redundant network path before the flow switching time is reached. In this way, by calculating the network vulnerabilities on the mobile vehicle path in real time, the future network availability is intelligently predicted, and the application data flow is automatically switched to ensure uninterrupted network services and optimal data transmission efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0030] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0031] Figure 1 A schematic diagram of a flow chart provided for the first embodiment of the vehicle network switching method of the present application;

[0032] Figure 2 A schematic diagram of mobile vehicle data information recorded in a database provided in Embodiment 1 of the vehicle network switching method of the present application;

[0033] Figure 3 A schematic diagram of calculating the latest switching time provided in Embodiment 1 of the vehicle network switching method of the present application;

[0034] Figure 4 A schematic diagram of providing continuous application connection for an intelligent vehicle gateway equipped with a mobile prediction multi-guide system provided in Embodiment 1 of the vehicle network switching method of the present application;

[0035] Figure 5 A schematic diagram of predictive switching of MPMS provided for the first application scenario of the vehicle network switching method of the present application;

[0036] Figure 6 A schematic diagram of establishing a global geographic connection database for a gateway provided for the first application scenario of the vehicle network switching method of this application;

[0037] Figure 7 A schematic diagram of a network connection environment of a mobile vehicle provided for the first application scenario of the vehicle network switching method of the present application;

[0038] Figure 8 This is a schematic diagram of the module structure of the vehicle network switching device according to an embodiment of the present application;

[0039] Fig. 9 Schematic diagram of the device structure of the hardware operating environment involved in the vehicle network switching method in the embodiment of the present application.

[0040] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0041] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0042] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0043] At present, among the conventional technical means, 1. A single communication provider. An important feature of the vehicle communication system is that multiple wireless networks coexist and complement each other to provide end users with a transparent, universal and optimal service experience. Different wireless networks vary greatly in terms of speed, service type, coverage, user experience, etc., and most mobile vehicles rely on a single communication provider. Usually, the availability and performance provided by the network service must meet the network requirements of various vehicle-mounted applications, but its index performance is rarely better than 99%, and there is still a possibility of downtime. At the critical moment of vehicle driving, network failure is very dangerous. In addition, under the vehicle-mounted LAN, the network ownership problem when the vehicle is moving has not been solved. According to SLA (service level agreement, service level agreement), that is, the service level agreement between the service provider and the customer, it defines the service quality that the service provider should guarantee, as well as the service compensation in the event of non-compliance with the service standard, where service availability = system normal operation time / total time within the statistical period, in one embodiment, as shown in the following table.

[0044] SLA Commitment Abnormal downtime in 1 year (minutes) Applicable scenarios 99.9% <526 minutes (8.8 hours) General Internet Services 99.5% <210 minutes (3.5 hours) Enterprise-level services 99.99% <52 minutes Enterprise-level services 99.999% <5 minutes Carrier-grade services

[0045] 2. Incomplete geographical coverage of a single network service. The efficient operation of the Internet of Vehicles system depends on a strong and stable network support, but any single network service lacks complete geographical coverage, which will have a series of impacts on the Internet of Vehicles system, not only limiting its functions, but also bringing potential safety hazards. Single networks operate as independent routing domains. They are independent autonomous systems. Due to various reasons such as network congestion that varies with time and location, each individual wireless network service cannot provide highly complete geographical coverage, which will cause network vulnerabilities in the geographical coverage of service providers, resulting in unstable services in the Internet of Vehicles system. During the driving process of the vehicle, if the network signal is frequently interrupted, it will directly affect the vehicle's real-time positioning, navigation, traffic information update and other functions. This not only reduces the driving experience, but may also cause traffic accidents due to information lag. In addition, incomplete network coverage will also affect certain functional services in the Internet of Vehicles system, such as emergency rescue functions, remote control functions, etc. The instability of the network makes these functions unable to be used normally.

[0046] 3. Fault recovery time is too long. When there are two or more networks, and each network comes from an independent service provider, in this case, there will be two or more wireless-based network autonomous systems running. When a specific network path to a destination fails in one of the autonomous networks, the application traffic to the destination needs to be automatically rerouted through another autonomous network. The time between detecting a fault on the first autonomous network and rerouting to the second autonomous network is called the routing convergence time. In some autonomous network routing protocols, such as the BGP protocol, the convergence time is usually 5 minutes or longer. During this convergence period, many applications will lose network connectivity and will not set a waiting time of 5 minutes or more for recovery. Therefore, the long convergence time of traditional routing protocols will disrupt the continuity of application use, resulting in untimely information interaction in the Internet of Vehicles, which will have an adverse impact on user use.

[0047] Based on this, the embodiment of the present application provides a vehicle network switching method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the vehicle network switching method of the present application.

[0048] It should be noted that the Internet of Vehicles uses the moving vehicles as the information perception object, and uses the new generation of information and communication technology to realize the network connection between the vehicle and X (i.e., vehicles, people, roads, cloud platforms, etc.). Among them, the communication between the vehicle and the cloud platform refers to the information transmission between the vehicle and the Internet of Vehicles service platform through wireless communication technologies such as satellite wireless communication or mobile cellular, receiving control instructions issued by the platform, and sharing vehicle data in real time. Communication between vehicles refers to the information exchange and information sharing between vehicles, including vehicle status information such as vehicle position and driving speed, which can be used to judge the traffic conditions on the road. Communication between vehicles and roads is the information exchange between vehicles and roads with the help of fixed communication facilities on the ground road, which is used to monitor the road surface conditions and guide vehicles to choose the best driving path. Communication between vehicles and people means that users can communicate with vehicles through wireless communication means such as Bluetooth, Wi-Fi, cellular, etc., so that users can monitor and control vehicles through corresponding mobile terminal devices. Communication between in-vehicle devices refers to the information data transmission between various devices inside the vehicle, which is used for real-time detection and operation control of device status and establishment of a digital in-vehicle control system.

[0049] In addition, it should be noted that the vehicle gateway is a core component in the electronic and electrical architecture of the vehicle, responsible for data transmission and protocol conversion between multiple networks inside the vehicle. The vehicle gateway can perform protocol conversion between networks with different structures and characteristics, such as CAN bus, LIN, MOST, FlexRay, etc., to ensure that data can be transmitted in different network systems. As a hub for data interaction, it manages and monitors the flow of data to ensure that data is transmitted safely and reliably in multiple networks inside the vehicle. By using a gateway, the confidentiality of the vehicle network can be improved and the safety of the vehicle can be enhanced. The use of a gateway allows the electronic and electrical architecture of the vehicle to be more optimized and improves the scalability of the vehicle network.

[0050] In this embodiment, the vehicle network switching method includes steps S10 to S30:

[0051] Step S10, inputting the collected map information and network information into the trained random forest classifier model to predict the quality of the network path;

[0052] In one embodiment, a predictive flow switching process is implemented based on a random forest classifier. The power of machine learning models can be used to predict network conditions and perform switching in advance when necessary, thereby reducing service interruptions and improving user experience. This predictive switching process can significantly improve flow switching efficiency and reliability. (1) Data collection and preprocessing: Collect application flow measurement data and local network measurement data. Clean the data and handle missing values ​​and outliers. (2) Feature engineering: Extract useful features from the original data, such as signal strength, latency, bandwidth, vehicle speed, location, etc. Create new features, such as moving averages or other statistical indicators based on historical data. (3) Select an unconventional model: Consider using an ensemble learning model (such as random forests, gradient boosting trees, etc.) or a deep learning model (such as convolutional neural networks, recurrent neural networks, etc.), which performs well in processing complex data and discovering nonlinear relationships. (4) Train the model: Use the data prepared in steps (1) and (2) to train the model. Split the data set into a training set and a test set to evaluate the performance of the model. (5) Model evaluation: Use indicators such as accuracy, recall, F1 score, ROC curve, etc. to evaluate the performance of the model. Adjust model parameters and perform cross-validation to optimize the model. (6) Predictive switching decision: Use the trained model to predict the quality of network paths and identify paths that may be affected by network vulnerabilities. Calculate the flow switching time T based on the output of the model. (7) Implement switching strategy: When the predicted flow switching time T is reached, automatically migrate the application flow to the redundant path. Continuously monitor the network status to ensure a smooth transition of the application flow. (8) Feedback loop: Collect actual application performance data after switching for further training and optimization of the model. Implement a continuous learning and adaptation mechanism to cope with changes in the network environment.

[0053] It should be noted that the random forest classifier is an ensemble learning algorithm that improves classification performance by building multiple decision trees and voting. This model has significant advantages in the predictive switching process: (1) Reducing the risk of overfitting: Random forests train each decision tree by randomly selecting features and samples. This randomness helps reduce the model's dependence on specific features or samples, thereby reducing the risk of overfitting. (2) Handling high-dimensional data: Random forests can effectively handle high-dimensional data without the need for complex feature selection processes. This is because when training each tree, it randomly selects a subset from all features, which helps capture important information in the data. (3) Dealing with incomplete data: Random forests can handle data containing missing values ​​and outliers. When building a decision tree, it tries to use different feature subsets to find the best split point, thereby being able to tolerate data incompleteness. (4) Evaluating feature importance: Random forests can evaluate the importance of each feature to the model, which is very helpful for feature selection and model interpretation. By analyzing the importance of features, we can better understand the decision-making process of the model. (5) Easy to implement and optimize: The implementation of the random forest algorithm is relatively simple, and there are many open source libraries (such as scikit-learn) that provide random forest implementations, which facilitates the rapid construction and optimization of models. In summary, the random forest classifier has significant advantages in the predictive switching process, including reducing the risk of overfitting, handling high-dimensional data, coping with incomplete data, evaluating feature importance, and easy implementation and optimization. These advantages make the random forest classifier an ideal choice for dealing with such problems.

[0054] It should be noted that, similar to the geographic database used for road navigation or maritime navigation, in the present application, a geographic connection database is proposed to collect the exact time and location of temporary or permanent network vulnerabilities. The database has the original data of network metrics collected from the perspective of mobile vehicles, including GPS or other equivalent coordinates (for example: timestamp information with date and time accurate to milliseconds), each instantaneous detailed two-way network indicator set of multiple wireless network services accessing the cloud, etc.

[0055] In one embodiment, the geographic connection database has the following properties:

[0056] (1) Describe network vulnerabilities in different geographical locations (such as land, sea, and air), which will adversely affect the performance of computer network applications in mobile vehicles; (2) Network vulnerabilities can be temporary, such as severe weather such as fog and lightning that cause temporary packet loss or flow jitter, or permanent, such as in highway tunnels or obstruction by trees and tall buildings; (3) In the case of temporary network vulnerabilities, automatic and real-time network measurements are required from the perspective of mobile vehicles to calculate and discover network vulnerabilities and further communicate the existence, location, and timestamp of network vulnerabilities; (4) These network vulnerability events can be communicated to another mobile vehicle or some smart roadside infrastructure; (5) Network vulnerabilities include degradation in measurement indicators based on application sensitivity thresholds, which affect different applications to different degrees. These application sensitivity thresholds will be used as part of active flow placement or migration, specifically bit rate, latency, jitter, etc.

[0057] In a feasible implementation manner, the step S10 includes:

[0058] Collecting time information, location information and weather information associated with a geographic location as map information;

[0059] Perform self-started connection measurement on each network service provider to obtain network information.

[0060] When the vehicle passes through various wireless network coverage areas, the intelligent vehicle gateway will measure the network input, calculate and form a geographic connection database. Its main function is to record network measurement data within a specific time period, such as the most recent period, and summarize the measurement data in the same area or adjacent areas.

[0061] The vehicle's network input data may include one or more of the following: (1) Global Positioning System (GPS) or equivalent geographic location coordinates of the measurement location; (2) the measurement time; (3) weather data provided from sensors or cloud services; and (4) measurement data received and analyzed by the gateway.

[0062] The intelligent vehicle gateway uses all or part of the collected measurement data, including GPS, network service provider paths, weather, etc., to calculate a composite, multi-layered geographic database and related connection maps. This process not only needs to process data from various sensors, but also takes into account the real-time and accuracy of the data. The following is a detailed description of this process:

[0063] (1) Data collection. Multi-source data collection: The smart vehicle gateway first collects data from multiple data sources, including GPS, network service provider routes, weather information, etc. Communication protocol analysis: The gateway needs to have the ability to parse multiple communication protocols in order to communicate with various smart meters and extract useful data. Data security: During the data collection process, encrypted communication, access control and other measures are used to protect data security. (2) Data processing. Edge computing technology: In order to improve the efficiency and accuracy of data processing, the smart vehicle gateway can use edge computing technology to pre-process and filter data, perform real-time data processing and analysis near the data source, and promptly discover and solve potential problems. Data fusion: Fusion of data from different sensors to obtain more comprehensive environmental information and vehicle status information. (3) Database construction. SQL database application: The smart vehicle gateway stores the processed data in the SQL database, which facilitates data storage and management and provides a basis for subsequent data analysis and mining. Data integrity: In the process of building the database, the integrity and accuracy of the data must be ensured. Abnormal data must be screened and processed to avoid affecting subsequent data analysis. (4) Database and geographic connection map construction. Multi-layer geographic database: Based on the collected data, a composite, multi-layer geographic database is calculated. This database contains rich geographic information, such as road conditions, traffic signs, real-time network status, etc., providing detailed environmental information for the vehicle driving system. Connection map: Using the geographic database, a related connection map is constructed. This map not only shows the road connection, but also adjusts the route according to real-time data to cope with various situations in actual driving.

[0064] In addition, the smart vehicle gateway also has the following features: 1. Scalability: With the change of business needs and the increase of equipment, the system should have good scalability. 2. Remote maintenance and upgrade: Considering the long-term stable operation of the system, the system should be maintained and upgraded regularly (remotely), and system vulnerabilities should be repaired and software versions updated in time to ensure the normal operation of the system.

[0065] In summary, the intelligent vehicle gateway realizes a composite, multi-layered geographic database and related connection maps through a series of processes such as collecting multi-source data, using edge computing technology for data processing, building an SQL database, and building a geographic connection map based on data. Various types of data collected by multiple vehicles in the same area at the same time will make the geographic connectivity dataset very large in a short period of time, so that highly accurate and statistically significant inferences can be drawn about many indicators, including but not limited to application flows and data on their expected duration.

[0066] It should be noted that by combining geographic connectivity map data with data such as the vehicle's speed and driving route, various connection events that may be detrimental to the normal operation of the application are predicted, and then predictive application flow placement is performed by selecting the best available path from a set of redundant paths before the vehicle encounters any network vulnerabilities. Through the above method, the continuity of the application is maximized, and if there are always redundant wireless paths available when the vehicle moves, it can theoretically reach 100%.

[0067] For the gateway, 1. The CPU in the gateway is used to process real-time communication and network measurement data from multiple mobile vehicles, and manage and update the geographic connection database based on the received measurement data. The CPU can complete the above functions under the control of the operating system and other application software. The CPU can include one or more processors, such as ARM microprocessors, MIPS microprocessors, etc. The memory is also part of the CPU, and the memory can be coupled to the system.

[0068] 2. The interface can be an interface card or a wireless interface, for example, which is configured to provide wireless network access using one or more RF transceivers. The interface controls the sending and receiving of data packets over the network, and sometimes supports other peripheral devices connected to the router. Interfaces that can be provided include, but are not limited to, Gigabit Ethernet interfaces, frame relay interfaces, cable interfaces, digital subscriber line (DSL) interfaces, token ring interfaces, WiFi IEEE802.1la / b / g / n wireless interfaces, DSRC IEEE 802.11p wireless interfaces, geostationary satellite (GSO) interfaces, low earth orbit (LEO) satellite interfaces, etc. Typically, these interfaces may include appropriate ports for communicating with appropriate media. In some cases, they may also include an independent processor that can control such communications. Independent processors can control communication-intensive tasks such as packet switching, media control and management. By providing separate processors for communication-intensive tasks, these interfaces allow the main microprocessor to efficiently perform routing calculations, network diagnostics, security functions, etc.

[0069] 3. Regardless of the configuration of the network device, it can use one or more memories or memory modules that are configured to store program instructions for general network operations and mechanisms for roaming, route optimization, and routing functions described herein. For example, the program instructions can control the operation of the operating system, the operations required by the network control plane processor, the operations required by the network forward plane processor, and / or one or more applications. One or more memories can also be configured to store tables, such as application microflow tables, flow lifetime tables, application sensitivity refresh tables, mobility binding, registration, and association tables, and other data related to the detection and prediction of network vulnerabilities.

[0070] 4. To enable user interaction with a computing device, an interface may represent any number of input mechanisms, such as a microphone for voice, a touch-sensitive screen for gesture or graphic input, a keyboard, a mouse, motion input, speech, etc. An interface may also represent one or more output devices or mechanisms. In some cases, a multimodal system enables a user to provide multiple types of input to communicate with the gateway.

[0071] Step S20, determining the location of the network vulnerability according to the quality of the network path;

[0072] In one embodiment, referring to Figure 2 , Figure 2 It shows how to build a data center-based geographic connectivity database for each mobile vehicle, which works in conjunction with an intelligent vehicle gateway connected to the global Internet. The geographic connectivity database and the geographic connectivity map are synonymous in this application. The geographic connectivity map is a visual representation of the geographic connectivity database, which is a geographic information database. The gateway stores the data sets obtained from the mobile vehicles, and the MPMS (Mobile Prediction Multihoming System) system of all mobile vehicles can work in conjunction with the intelligent vehicle gateway to perform measurements.

[0073] Figure 2 Also shown is local database record information that a mobile vehicle may provide, which may include location, such as GPS coordinates, timestamp, local weather data, etc., and a set of related local measurement data, ISP 1 to ISP N, where ISP 1,…,N are the wireless or other network service providers encountered by the mobile vehicle at a particular location and moment. Figure 2 Also shown are examples of network measurements for a moving vehicle at moments and locations, such as round-trip delay, inbound packet loss rate, inbound throughput, inbound available bit rate, outbound packet loss rate, outbound throughput, outbound available bit rate, inbound jitter, and outbound jitter.

[0074] During initialization or installation, each vehicle's MPMS unit is associated with a gateway, and redundant gateways are allowed for fault tolerance. The measured data includes, but is not limited to, throughput, packet loss, round-trip time, jitter, each traffic direction and each available access cloud path. MPMS can quickly and reliably detect network-related problems. The measurement server in the smart vehicle gateway collects large data sets, and combined with the data collected by the gateways of other mobile vehicles, various summary statistics and analysis conclusions associated with the geographic location can be obtained, as well as other data such as weather forecasts and line of sight loss calculated in the background. Based on the above large amount of data, MPMS can reliably detect failures of various components connected to the vehicle LAN, such as TCU or ADAS, or individual LAN components within microseconds.

[0075] In a feasible implementation manner, the step S30 includes:

[0076] Obtain a flow table record storing an application sensitivity threshold, wherein the flow table record includes all relevant protocol information of a data link layer, a network layer, a transport layer, a session layer, a presentation layer, and an application layer;

[0077] The location of the network vulnerability is determined by the real-time measurement value of the network connection performance indicator in the flow table record and the preset sensitivity threshold of the application flow.

[0078] In one embodiment, the vehicle MPMS system can be used to detect or predict reliable network degradation and automatically correct the placement of computer application flows on the alternate ISP path within a sufficiently small time interval (a few milliseconds or less). By computer application flow program, not only user computing devices such as laptops and smartphones are included, but also embedded vehicle computers such as (Advanced Driver Assistance System) ADAS, (Telematic Control Unit) TCU, etc. Application flows can include any network traffic executed by an application or other software process, and application flows can include voice, video, or other media type data.

[0079] MPMS must be consistent with all network traffic during operation. All data and message packets must flow through it or be visible to it, and MPMS will store all flow data in various tables. If a corresponding table or entry is not established for a certain flow data, MPMS will establish a corresponding table or entry when the first data packet of the flow is observed. The flow table records all relevant protocol information including the data link layer, network layer, transport layer, session layer, presentation layer and application layer. In addition, it also includes the current path selection information, as well as assisting NAT (Network Address Translation) and PAT (Port Address Translation) flow placement entries.

[0080] Whenever MPMS decides to switch paths, the sensitivity of the application to network conditions is a decision factor for flow placement, where the application sensitivity threshold is stored in a table or database of MPMS. The following is an example of such information:

[0081]

[0082] In this table, there is no limit on the application flow type, and various types of network measurement thresholds are listed, which, if exceeded, will cause the corresponding application flow to be severely degraded or completely fail. These thresholds can be changed up or down within a reasonable range based on actual conditions. This table is used to predict the geographical areas where adverse conditions may be encountered, because when a vehicle is moving, it may encounter various forms of network vulnerabilities from time to time.

[0083] Taking the jitter of voice applications as an example, if multiple vehicles’ MPMS units are connected with the gateway Figure 2 If the average or 80% of the values ​​for a specific ISP and a specific geographic location are greater than 40 milliseconds, the gateway can map the scope of this network vulnerability and then communicate it to the MPMS of the mobile vehicle in advance. After that, the MPMS can decide whether to make predictive automatic corrections.

[0084] In a feasible implementation manner, the network vulnerability is the loss or degradation of network connection performance, and the location of the network vulnerability includes a temporary location and a permanent location.

[0085] A network vulnerability may refer to a loss or degradation of network connectivity performance at a particular geographic point or geographic area. In some cases, a network vulnerability may refer to a lack of coverage relative to a particular network provider path.

[0086] The following transient phenomena encountered by a moving vehicle may cause network vulnerabilities, such as line of sight problems where network signals may be impaired, local rain, fog and weather conditions, the location and scope of road tunnels, and obstruction by high-rise buildings. Therefore, it is necessary to collect and store database geographic information that affects network connection performance.

[0087] Step S30, calculating the flow switching time for migrating the application flow to the redundant network path according to the current position of the vehicle, the location of the network vulnerability and the vehicle speed, and migrating the application flow to the redundant network path before the flow switching time is reached.

[0088] In one embodiment, referring to Figure 3 Ideally, in order to avoid session interruption due to the proximity of network vulnerabilities on the vehicle's route, predictive flow switching should be performed in a timely manner. Figure 3 inequality in ,calculate the latest time of the mobile application flow.

[0089] The gateway collects information about application flows from all vehicles’ MPMS units and ranks them as percentiles over the lifetime of that flow. This process is done periodically, so the gateway has a statistically large data set covering the traffic lifecycle of multiple vehicles and their users. When a network breach occurs that adversely affects HTTPS flows on a particular network path, it is the job of MPMS to migrate all new HTTPS flows from the original path to a redundant path as early as possible.

[0090] For example, if the MPMS is 15 minutes away from a network hole and the statistics for HTTPS flows are up to date, then 100% of the HTTPS flows for all current sessions will start to degrade before the vehicle reaches the network hole, requiring all new flows to be placed on redundant paths without network holes via proactive migration within these 15 minutes.

[0091] In a feasible implementation manner, the step S30 includes:

[0092] Determine the preferred network path at the current time or when the flow switching time is reached, and use the preferred network path as a redundant network path to migrate the application flow to the redundant network path.

[0093] After quickly detecting a vulnerability, the next step is to perform automatic correction, which involves measuring and calculating how to place application flows on network paths with better performance.

[0094] In one embodiment, Figure 4 It describes the in-vehicle LAN and how MPMS connects these LANs to the WAN through multiple WAN paths (via cellular or satellite modems, etc.). Various network data packets are transmitted and received on these paths. There are also multiple ISP network paths to choose from. When MPMS detects a real-time interruption event in the network and needs to urgently correct the path, it will choose from the backup paths. The specific detection time point can be the current time point or the future time point predicted by the system. This ensures the uninterrupted use of applications and improves user experience. In addition, Figure 4 Various types of network service provider (ISP) paths are described in the , each of which has a non-overlapping IP address space. MPMS provides the choice of at least two wireless network service provider paths, because two network paths rarely experience network failures at the same time, and through their connection with MPMS, reliability is greatly improved, increasing the continuous uptime of applications.

[0095] In a feasible implementation manner, the vehicle network switching method further includes:

[0096] The actual traffic life span of the application flow is determined based on the survival probability of the application flow under different traffic life spans and the error probability allowed in the actual switching of the network path.

[0097] Flows appear and disappear, similar to a user opening a web page with a browser and then closing the page. MPMS uses its flow tables to calculate and perform statistical analysis of flow lifetimes, which can be optimized based on the usage habits of vehicle users. MPMS is able to calculate these flow lifetimes using standard network packet observation and timestamp techniques. The specific process of calculating flow lifetimes involves multiple steps and techniques, including data collection, data processing, statistical analysis, and optimization. The following is a detailed explanation of this process:

[0098] (1) Data collection. Flow table: MPMS uses flow table to record the flow information of each application flow, including flow size, duration, etc. Timestamp technology: MPMS uses timestamp technology to record the start time and end time of each application flow in order to calculate its life cycle.

[0099] (2) Data processing. Data cleaning: Before processing data, it is necessary to clean the data to remove outliers and erroneous data to ensure data quality and accuracy. Data conversion: Convert raw data into a format suitable for analysis, such as converting timestamps into readable time intervals.

[0100] (3) Statistical analysis. Percentile calculation: Based on the data in the flow table, calculate the flow lifetime of different percentiles. For example, 95% of email flows have a flow lifetime of 30 minutes. Error analysis: Based on the degree of statistical reliability, calculate the error range for allowing flow switching. For example, if the email flow requires a 0% error rate, the value of the flow lifetime is increased to 80 minutes.

[0101] (4) Optimization. Threshold setting: According to the results of statistical analysis, set the corresponding threshold times for different application flow types. For example, setting the threshold for 95% of http flows to 10 minutes means that a 5% error is allowed in traffic switching. Traffic switching strategy: According to the set threshold, formulate a traffic switching strategy to achieve reasonable allocation and optimization of network resources.

[0102] Through the above steps, MPMS can calculate the traffic life of various application flow types and optimize them according to the usage habits of vehicle users. This helps to improve network resource utilization, reduce network congestion and latency, and provide more stable and efficient network services.

[0103] Without restrictions, the flow lifetime table calculated by a single MPMS in a single vehicle is a table of application flow types categorized by percentiles of flow lifetime. In large datasets, one or more mobile vehicles provide configurable data for these percentiles, resulting in relevant threshold times with corresponding degrees of statistical reliability. For example: 95% of email flows only survive for 30 minutes, which means that a 5% error is allowed for flow switching. If a 0% error rate is enforced for email flows, the value of flow lifetime is increased to 80 minutes.

[0104]

[0105] In addition, the mobile prediction multi-channel system also has the following functions, which are crucial for the prediction of mobile vehicles, such as (a) global positioning: assisting mobile vehicles to obtain accurate data of real-time geographic positioning; (b) vehicle speed measurement: measuring or reading the speed of the moving vehicle (through the on-board tachometer); (c) emergency / fault call: the telecommunications control unit TCU is used for emergency calls or fault calls. The mobile prediction multi-channel system can use multiple redundant paths to provide continuity for voice calls initiated or received by the TCU; (d) integrated car phone: connecting to the MPMS through wired or wireless connections and providing network services through various ISP paths.

[0106] In one application scenario, most vehicles will be parked or stationary for a long period of time when not in use. During this period, the gateway will communicate with MPMS and load or update the static connection map data of a reasonably sized geographic area into MPMS. After the vehicle is started again, it has stored all the static data and is relatively independent in making switching decisions for various application flows. MPMS can calculate the distance from the current location to any network holes based on data such as GPS coordinates and the expected speed of the vehicle, as well as the estimated time of arrival at the network hole. Then, if any set of flows needs to be migrated to a different network, MPMS has enough time to apply the flow before migrating to the network hole.

[0107] Changes in dynamic connectivity metrics may be related to line-of-sight obstructions (appearance or removal), weather, or other network congestion that causes packet loss. The gateway can pre-configure event-driven intervals to update each vehicle's MPMS with changes in the dynamic connectivity map. Communication is only required when the gateway detects significant changes. The gateway, with its large data sets collected from many vehicles and access to geographic databases, can control dynamic map connectivity updates for vehicles in areas that are close or expected to be close.

[0108] Sort all known network holes by their distance from the vehicle and eliminate holes that are too far away. When the vehicle reaches a specific hole, all flows are degraded, based on Figure 3The constraint equations in are used to estimate the maximum time L within which the flow switching needs to be completed, otherwise the integrity of the flow will be affected. If there are still loopholes after elimination, MPMS forms a connection graph update message (as an update to the previous static connection graph) and transmits the update message to the vehicle using one of the available network paths.

[0109] The steps and procedures implemented by MPMS to achieve predictive switching minimize the possibility of session interruption or application disruption, such as Figure 5 As shown:

[0110] (1) MPMS sends a data collection request to obtain application flow measurement data (local network measurement data, without sending a request to the gateway (online measurement);

[0111] (2) MPMS responds after receiving the request and uses the received measurement data to update the local geo-connectivity database;

[0112] (3) MPMS sends a request to the remote gateway to obtain the geographic connection data of the gateway's relevant area;

[0113] (4) When receiving a response from the gateway, MPMS updates the local geographic connection database;

[0114] (5) MPMS sends network measurements to the gateway: For each service provider, if requested, collect the metrics ( Figure 2 ) and append the vehicle’s identifier, location and timestamp to the request, then perform the measurement and store it in the MPMS and IVCA gateways;

[0115] (6) MPMS calculates the degree to which each network path among multiple service providers is close to a network vulnerability by analyzing data in a geographic connectivity database;

[0116] (7) MPMS calculates the set of application flows on the network path that will be adversely affected by the network vulnerability;

[0117] (8) MPMS calculates the flow switching time T based on the vehicle speed and the distance to the network vulnerability. After that, the new type of flow found in the above set will be migrated to a redundant path, taking into account the speed and direction of the vehicle;

[0118] (9) When the flow switching time T is reached, any application flow detected by MPMS will be placed on the backup path. Even application flows that are not affected by network vulnerabilities on the original path will be transferred to the backup path to ensure that the subsequent flows will not be affected by network vulnerabilities.

[0119] Reference Figure 6 , Figure 6 An example of how the gateway starts with a geographic information system (GIS) database and uses various network metrics obtained from moving vehicles to calculate a geographic connectivity database, and then collaborates with the vehicle upon request to perform a predictive flow switch. The steps taken by the gateway to achieve predictive flow switching are summarized below:

[0120] (1) The gateway initializes the GIS database to build global maps and navigation routes for various vehicles;

[0121] (2) The gateway waits for requests or updates from various geographic information services from mobile vehicles. Updates mainly refer to information that affects network connectivity, such as network measurement data, related to tunnels, weather, etc.

[0122] (3) The gateway processes network measurement requests from the mobile vehicle MPMS. For each network provider, it works with the MPMS to collect Figure 2 Indicators in the , attach vehicle identifiers, location and time stamps, and create a global geographical information connection database;

[0123] (4) The gateway collects data from multiple vehicles and performs statistical analysis, and the statistically analyzed data is updated to the global geographic information connection database;

[0124] (5) The gateway calculates network vulnerabilities and organizes them according to the local area of ​​any vehicle and updates them into a global geographic information connection database;

[0125] (6) The gateway uses the online network path measurement of MPMS to process the update data packets from the mobile vehicles. The data packets detect new network vulnerability issues on the route and are updated by the gateway to the global geographic information connection database.

[0126] Take a mobile vehicle entering a tunnel as an example: before the vehicle arrives at the tunnel, there is a network connection on Network Service Provider Path 1, and the gateway knows that Network Service Provider Path 2 is enabled inside the tunnel (through communication with other on-board gateways or the global geographic connection database). MPMS obtains this information from the gateway in advance, and the predictive flow switching of MPMS automatically transfers the network connection from Network Service Provider Path 1 to Network Service Provider Path 2 before entering the tunnel to ensure the continuity of the application and no disconnection.

[0127] In one embodiment, a mobile prediction multi-path system is proposed to ensure that the vehicle maintains a stable network connection during movement and solve various problems related to network stability. The data flow of the application is dynamically allocated to other paths, so as to foresee and respond to potential network vulnerabilities in the geographical coverage area before they occur. In addition, the system is also equipped with a predictive flow switching function, which can calculate the network vulnerabilities on the path of the moving vehicle in real time, intelligently predict the future network availability, and automatically switch the application data flow as needed to ensure uninterrupted network service and optimal data transmission efficiency.

[0128] Reference Figure 7 , Figure 7 The network connection environment of a mobile vehicle is described. Two mobile vehicles (Vehicle-1 and Vehicle-2 in the figure) are in two large areas covered by two wireless network service providers. The areas with sufficient wireless signal coverage in Wireless Network-1 and Wireless Network-2 have been marked (two trapezoids in the figure). The wireless network coverage area represents the coverage of any type of data network maintained or managed by any network provider. For example, Wireless Network Coverage Area-1 can be a cellular LTE provider, and Wireless Network Coverage Area-2 can be a low-orbit satellite service provider. In addition, wireless networks can also provide various services including smart navigation, high-definition maps, and other smart driving supporting services. If the mobile vehicle is equipped with MPMS, it has the ability to automatically detect local network defects in the area under the jurisdiction of the network service provider. After the network vulnerability is detected in advance, MPMS will quickly initiate preparatory measures and seamlessly switch the network connection from the main network to the backup network to ensure that the vehicle enjoys continuous and stable network quality during travel. This intelligent network management mechanism greatly improves the reliability and efficiency of vehicle network services, avoids the problem of data connection interruption or quality degradation, and provides users with a worry-free network usage environment.

[0129] MPMS performs self-initiated connection measurements for each network service provider and is executed in conjunction with measurement software running on an intelligent vehicle gateway, which can act as a measurement server with sufficient computing power to continuously and simultaneously perform various connection measurements on a large number of moving vehicles. The types of measurement data received and analyzed by the gateway include, but are not limited to: bit rate throughput, packet loss rate, latency, jitter, out-of-order events in each traffic direction, and network provider paths that the vehicle may be connected to. These paths include DSRC (dedicated short-range communication technology), Wi-Fi, 5G, LTE, and other types of networks.

[0130] In summary, 1. Collaboration of multiple network service providers to expand the geographical coverage of the network. Unlike traditional single network service providers, MPMS works in conjunction with the geographic connection database to coordinate the resources of multiple network service providers near the mobile vehicle to expand the geographical coverage of the network. During operation, MPMS uses real-time measurement data in the geographic connection database to continuously compare and analyze the performance indicators of all available network service providers. Based on this comprehensive data, MPMS can intelligently judge and select the best redundant path for instant migration of application data flows, ensuring that data transmission is always in the best state.

[0131] 2. Ensure application continuity. Application flows cover network transmission content generated by various applications or software processes, including but not limited to voice, video, and other multimedia types of data. MPMS has the ability to monitor and predict network quality degradation, and can automatically redirect computer application data flows to backup network paths in a very short time (milliseconds or even shorter) to ensure the continuity and stability of data transmission. By collecting detailed information about application flows and combining it with a geographic connection database, MPMS can quickly transfer new data flows from the original path to the backup redundant path before network vulnerabilities interfere with the data flow, ensuring that users experience uninterrupted continuity during use.

[0132] 3. Track the life cycle of computing application flows. MPMS uses standardized network packet monitoring and timestamp technology to accurately calculate the life cycle of data flows. The appearance and disappearance of data flows are similar to the behavior pattern of users opening and closing web pages through browsers. Based on the traffic record table, MPMS performs statistical analysis of the duration of data flows and optimizes the network usage habits of vehicle users accordingly. For example, after computational analysis, MPMS will conclude that 95% of all HTTPS data flows will be completed within 10 minutes, and 100% completion rate will be achieved within 15 minutes. This analysis process is repeated regularly, accumulating a large data set covering the communication traffic life cycle of multiple vehicles and their users. Therefore, once a network vulnerability that may negatively affect HTTPS data flows on a specific network path is detected, MPMS will quickly migrate all new HTTPS data flows to alternative redundant paths to minimize the impact on the user experience.

[0133] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the vehicle network switching method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0134] This application also provides a vehicle network switching device, please refer to Figure 8, the vehicle network switching device comprises:

[0135] The prediction module is used to input the collected map information and network information into the trained random forest classifier model to predict the quality of the network path;

[0136] A determination module, used to determine the location of network vulnerabilities based on the quality of network paths;

[0137] The migration module is used to calculate the flow switching time for migrating the application flow to the redundant network path according to the current position of the vehicle, the location of the network vulnerability and the vehicle speed, and migrate the application flow to the redundant network path before the flow switching time is reached.

[0138] In one embodiment, the vehicle network switching device further includes a collection module, which is used to:

[0139] Before the step of inputting the collected map information and network information into the trained random forest classifier model to predict the quality of the network path,

[0140] Collecting time information, location information and weather information associated with a geographic location as map information;

[0141] Perform self-started connection measurement on each network service provider to obtain network information.

[0142] In one embodiment, the determining module is further configured to:

[0143] Before the step of calculating the flow switching time for migrating the application flow to the redundant network path according to the current position of the vehicle, the position of the network vulnerability and the speed of the vehicle,

[0144] Obtain a flow table record storing an application sensitivity threshold, wherein the flow table record includes all relevant protocol information of a data link layer, a network layer, a transport layer, a session layer, a presentation layer, and an application layer;

[0145] The location of the network vulnerability is determined by the real-time measurement value of the network connection performance indicator in the flow table record and the preset sensitivity threshold of the application flow.

[0146] In one embodiment, the network vulnerability is the loss or degradation of network connection performance, and the location of the network vulnerability includes a temporary location and a permanent location.

[0147] In one embodiment, the migration module is further configured to:

[0148] Determine the preferred network path at the current time or when the flow switching time is reached, and use the preferred network path as a redundant network path to migrate the application flow to the redundant network path.

[0149] In one embodiment, the vehicle network switching device further includes a survival module, which is used to:

[0150] The actual traffic life span of the application flow is determined based on the survival probability of the application flow under different traffic life spans and the error probability allowed in the actual switching of the network path.

[0151] The vehicle network switching device provided by the present application adopts the vehicle network switching method in the above embodiment, which can solve the technical problem of unstable network connection of the Internet of Vehicles. Compared with the prior art, the beneficial effects of the vehicle network switching device provided by the present application are the same as the beneficial effects of the vehicle network switching method provided by the above embodiment, and the other technical features in the vehicle network switching device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0152] The present application provides a vehicle network switching device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the vehicle network switching method in the above-mentioned embodiment 1.

[0153] Reference below Fig. 9 , which shows a schematic diagram of the structure of a vehicle network switching device suitable for implementing an embodiment of the present application. The vehicle network switching device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig. 9 The vehicle network switching device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0154] like Fig. 9As shown, the vehicle network switching device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the vehicle network switching device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the vehicle network switching device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a vehicle network switching device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0155] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0156] The vehicle network switching device provided by the present application adopts the vehicle network switching method in the above embodiment, which can solve the technical problem of unstable network connection of the Internet of Vehicles. Compared with the prior art, the beneficial effects of the vehicle network switching device provided by the present application are the same as the beneficial effects of the vehicle network switching method provided by the above embodiment, and the other technical features in the vehicle network switching device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0157] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0158] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0159] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the vehicle network switching method in the above-mentioned embodiment.

[0160] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0161] The computer-readable storage medium may be included in the vehicle network switching device; or may exist independently without being assembled into the vehicle network switching device.

[0162] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the vehicle network switching device, the vehicle network switching device: inputs the collected map information and network information into the trained random forest classifier model to predict the quality of the network path; determines the location of the network vulnerability based on the quality of the network path; calculates the flow switching time for migrating the application flow to the redundant network path based on the current position of the vehicle, the location of the network vulnerability and the vehicle speed, and migrates the application flow to the redundant network path before the flow switching time is reached.

[0163] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0164] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square 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 square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square 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 square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0165] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0166] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned vehicle network switching method, and can solve the technical problem of unstable network connection of the Internet of Vehicles. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the vehicle network switching method provided by the above-mentioned embodiment, and will not be repeated here.

[0167] The present application also provides a computer program product, including a computer program, which implements the steps of the vehicle network switching method as described above when executed by a processor.

[0168] The computer program product provided by this application can solve the technical problem of unstable network connection of the Internet of Vehicles. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the vehicle network switching method provided by the above embodiment, which will not be repeated here.

[0169] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A vehicle network switching method, characterized in that: The vehicle network switching method comprises: The collected map information and network information are input into the trained random forest classifier model to predict the quality of the network path; Determine the location of network vulnerabilities based on the quality of network paths; According to the current position of the vehicle, the position of the network vulnerability and the vehicle speed, the flow switching time for migrating the application flow to the redundant network path is calculated, and the application flow is migrated to the redundant network path before the flow switching time is reached.

2. The vehicle network switching method according to claim 1, characterized in that: The step of inputting the collected map information and network information into the trained random forest classifier model to predict the quality of the network path includes: Collecting time information, location information and weather information associated with a geographic location as map information; Perform self-started connection measurement on each network service provider to obtain network information.

3. The vehicle network switching method according to claim 1, characterized in that: The step of calculating the flow switching time for migrating the application flow to the redundant network path according to the current position of the vehicle, the position of the network vulnerability and the speed of the vehicle includes: Obtain a flow table record storing an application sensitivity threshold, wherein the flow table record includes all relevant protocol information of a data link layer, a network layer, a transport layer, a session layer, a presentation layer, and an application layer; The location of the network vulnerability is determined by the real-time measurement value of the network connection performance indicator in the flow table record and the preset sensitivity threshold of the application flow.

4. The vehicle network switching method according to claim 1, characterized in that: The network vulnerability is the loss or degradation of network connection performance, and the location of the network vulnerability includes a temporary location and a permanent location.

5. The vehicle network switching method according to claim 1, characterized in that: The step of migrating the application flow to the redundant network path comprises: Determine the preferred network path at the current time or when the flow switching time is reached, and use the preferred network path as a redundant network path to migrate the application flow to the redundant network path.

6. The vehicle network switching method according to claim 1, characterized in that: The vehicle network switching method further includes: The actual traffic life span of the application flow is determined based on the survival probability of the application flow under different traffic life spans and the error probability allowed in the actual switching of the network path.

7. A vehicle network switching device, characterized in that: The vehicle network switching device comprises: The prediction module is used to input the collected map information and network information into the trained random forest classifier model to predict the quality of the network path; A determination module, used to determine the location of network vulnerabilities based on the quality of network paths; The migration module is used to calculate the flow switching time for migrating the application flow to the redundant network path according to the current position of the vehicle, the location of the network vulnerability and the vehicle speed, and migrate the application flow to the redundant network path before the flow switching time is reached.

8. A vehicle network switching device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the vehicle network switching method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the vehicle network switching method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the vehicle network switching method according to any one of claims 1 to 6 are implemented.

Citation Information

Patent Citations

  • Automatic driving oriented data communication handover method and system

    CN106921939A

  • Methods, system and user equipment of a wireless communication network for determining transmission conditions for a real-time media flow

    CN108476091A

  • Network switching method, device and equipment

    CN116017598A

  • Network quality regulation and control method and related equipment

    CN116528274A

  • Predictive flow switching and application continuity in connected vehicle networks

    US20180302770A1