Vehicle-mounted heterogeneous network switching method, frame, electronic equipment and storage medium

Abstract

The invention provides a vehicle-mounted heterogeneous network switching method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining vehicle-related information and / or environment-related information of an environment where a vehicle is located, and determining a target business demand of the vehicle according to the vehicle-related information and / or environment-related information; determining a target vehicle-mounted network matched with the target service requirement from a plurality of vehicle-mounted heterogeneous networks supported by the vehicle; if the current vehicle-mounted network is not the target vehicle-mounted network, determining a switching strategy according to the quality of the current vehicle-mounted network and a target service demand; and switching the current vehicle-mounted network to the target vehicle-mounted network according to the switching strategy. Therefore, by obtaining the vehicle information and / or the environment information, the system can accurately evaluate the service requirements of the vehicle, such as low time delay and high bandwidth, so that the most suitable vehicle-mounted network is selected, the communication requirements of the intelligent vehicle in diversified scenes are met, and the driving experience of a user is improved.

Description

Technical Field

[0001] One or more embodiments of the present disclosure relate to the technical field of network switching, and in particular, to a method, framework, electronic device, and storage medium for switching heterogeneous vehicle-mounted networks. Background Art

[0002] For intelligent vehicles, the vehicle-mounted network system only supports a single type of network connection, such as a cellular network, Wi-Fi, or Bluetooth. The vehicle-mounted network system usually relies on preset network selection rules or manual selection to determine which network to use for data transmission. For example, in some cases, the vehicle-mounted network system may first attempt to connect to the Wi-Fi network. If the Wi-Fi is unavailable, it will switch to the cellular network.

[0003] However, different types of vehicle-mounted networks have their own advantages and limitations in terms of data transmission rate, latency, coverage, power consumption, etc. Relying on preset network selection rules or manual selection to determine the network for data transmission may not be able to make an optimal choice based on real-time changing vehicle-related information and environment-related information. Moreover, manual switching will cause an additional operation burden on the driver and may also lead to delays in information transmission. Summary of the Invention

[0004] To solve the technical problem that the vehicle-mounted network of an intelligent vehicle cannot make an optimal decision according to the actual situation due to relying on preset network selection rules or manual selection to determine the network for data transmission, in a first aspect, the present disclosure provides a method for switching heterogeneous vehicle-mounted networks, the method comprising:

[0005] Obtaining vehicle-related information and / or environment-related information of the environment where the vehicle is located, and determining the target service requirements of the vehicle according to the vehicle-related information and / or environment-related information;

[0006] Determining a target vehicle-mounted network that matches the target service requirements from multiple heterogeneous vehicle-mounted networks supported by the vehicle;

[0007] If the current vehicle-mounted network is not the target vehicle-mounted network, determining a switching strategy according to the current vehicle-mounted network quality and the target service requirements; and switching the current vehicle-mounted network to the target vehicle-mounted network according to the switching strategy.

[0008] In a second aspect, the present disclosure further provides a system for switching heterogeneous vehicle-mounted networks, the system comprising:

[0009] An environment perception layer for obtaining vehicle-related information and / or environment-related information of the environment where the vehicle is located, and determining the target service requirements of the vehicle according to the vehicle-related information and / or environment-related information;

[0010] A fusion engine layer for determining a target vehicle network that matches the target service requirement from multiple heterogeneous vehicle-mounted networks supported by the vehicle;

[0011] An application service layer for determining a handover strategy according to the current vehicle network quality and the target service requirement if the current vehicle network is not the target vehicle network; and switching the current vehicle network to the target vehicle network according to the handover strategy.

[0012] The present disclosure also provides an electronic device, including a communication interface, a processor, a memory, and a bus, where the communication interface, the processor, and the memory are interconnected through the bus;

[0013] Machine-readable instructions are stored in the memory, and the processor executes the above method by calling the machine-readable instructions.

[0014] The present disclosure also provides a machine-readable storage medium storing machine-readable instructions, and the machine-readable instructions implement the above method when being called and executed by a processor.

[0015] Through the embodiments of the present disclosure, first, vehicle-related information and / or environment-related information of the vehicle is obtained, and the target service requirement of the vehicle is determined according to the vehicle-related information and / or the environment-related information; further, a target vehicle network that matches the target service requirement is determined from multiple heterogeneous vehicle-mounted networks supported by the vehicle; finally, if the current vehicle network is not the target vehicle network, a handover strategy is determined according to the current vehicle network quality and the target service requirement; and the current vehicle network is switched to the target vehicle network according to the handover strategy.

[0016] In the above manner, the vehicle system of the present disclosure obtains vehicle-related information and / or environment-related information, evaluates the vehicle service requirement and determines a matching network, and formulates a seamless handover strategy according to the network quality and the vehicle service requirement, smoothly transitioning the vehicle from the current vehicle network to the target vehicle network, meeting the communication requirements of intelligent vehicles in diverse scenarios, and improving driving safety and user experience. Description of the Drawings

[0017] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for description in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments recorded in the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1It is a flowchart of a vehicle-mounted heterogeneous network handover method shown in an exemplary embodiment;

[0019] Figure 2 It is a schematic diagram of data flow of a vehicle-mounted heterogeneous network handover method shown in an exemplary embodiment;

[0020] Figure 3 It is a schematic diagram of data flow of a network fusion engine shown in an exemplary embodiment;

[0021] Figure 4 It is a hardware structure diagram of an electronic device shown in an exemplary embodiment;

[0022] Figure 5 It is a schematic diagram of a vehicle-mounted heterogeneous network handover system shown in an exemplary embodiment. Detailed implementation manners

[0023] In order to enable those skilled in the art of the present technology to better understand the technical solutions in the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present disclosure.

[0024] It should be noted that: in other embodiments, the steps of the corresponding methods are not necessarily executed in the order shown and described in the present disclosure. In some other embodiments, the steps included in the method may be more or less than those described in the present disclosure. In addition, a single step described in the present disclosure may be decomposed into multiple steps for description in other embodiments; and multiple steps described in the present disclosure may also be combined into a single step for description in other embodiments.

[0025] For intelligent vehicles, the in-vehicle network system only supports a single type of network connection, such as cellular network, Wi-Fi or Bluetooth, etc. The in-vehicle network system usually depends on preset network selection rules or manual selection to decide which network to use for data transmission. For example, in some cases, the in-vehicle network system may preferentially attempt to connect to the Wi-Fi network. If the Wi-Fi is unavailable, it will switch to the cellular network.

[0026] However, different types of in-vehicle networks have their own advantages and limitations in terms of data transmission rate, latency, coverage, power consumption, etc. Relying on preset network selection rules or manual selection to determine the network for data transmission may not be able to make the optimal choice according to the vehicle-related information and environment-related information that change in real time. Moreover, manual switching will impose an additional operation burden on the driver and may also lead to delays in information transmission.

[0027] How to effectively integrate these in-vehicle networks so that intelligent vehicles can automatically select the most suitable network connection in different scenarios, improving the overall performance of network services and user experience, has become a key issue in the field of intelligent vehicle network communication.

[0028] In view of this, the present disclosure aims to propose a technical solution for selecting the most suitable in-vehicle network according to the real-time information of the vehicle and the environment and performing network switching.

[0029] This technical solution first obtains vehicle-related information and / or environment-related information of the environment where the vehicle is located, and determines the target service requirements of the vehicle according to the vehicle-related information and / or environment-related information; further, from multiple heterogeneous in-vehicle networks supported by the vehicle, determines the target in-vehicle network that matches the target service requirements; finally, if the current in-vehicle network is not the target in-vehicle network, determines a switching strategy according to the current in-vehicle network quality and the target service requirements; and switches the current in-vehicle network to the target in-vehicle network according to the switching strategy.

[0030] For example, an intelligent vehicle is driving on a highway. The vehicle system first collects environmental data such as the current driving speed, location information of the vehicle, and surrounding traffic conditions, and takes low-latency real-time traffic updates and high-precision navigation services as the target service requirements based on this information. Based on these target service requirements, the vehicle system analyzes and determines that the existing Wi-Fi connection of the vehicle cannot provide the stability and coverage required for the target service, so it is necessary to switch to a V2X (Vehicle to Everything) communication network that matches the target service requirements to obtain lower-latency data transmission, and at the same time combines the global positioning system and the cellular network to ensure the accuracy of navigation.

[0031] After confirming that the current Wi-Fi network does not meet the requirements of real-time traffic updates and high-precision navigation, the vehicle system first conducts a detailed assessment of the quality of the existing network, including key parameters such as signal strength, transmission rate, and latency. Based on the confirmed target service requirements, the vehicle system activates an intelligent network selection algorithm to determine the appropriate handover strategy. Considering that the vehicle is moving at high speed and requires continuous data streams to ensure safe driving, the system selects the pre-handover strategy as the initial step. The pre-handover strategy allows the system to establish a connection with the target network (V2X and cellular networks) in advance, but temporarily maintains the connection status with the original Wi-Fi network until it is confirmed that the new network can stably provide services. Once the new network connection is verified as reliable, the system will perform a soft handover, that is, wait until the current data transmission or service processing via Wi-Fi is completed, and then fully transfer to the new network configuration. This method avoids the risk of data loss and service interruption. However, extreme situations also need to be considered. If an emergency is detected at any time, such as approaching a Wi-Fi coverage area and immediate access to the latest traffic information is required, the vehicle system will adopt a hard handover strategy, directly disconnect the Wi-Fi connection and quickly switch to the V2X and cellular networks. Although this may result in temporary data loss, in this case, the security of obtaining real-time traffic information takes precedence over data integrity.

[0032] In the above manner, the vehicle system of the present disclosure obtains vehicle-related information and / or environment-related information, evaluates the vehicle's service requirements and determines the matching network, and formulates a seamless handover strategy based on the network quality and vehicle service requirements, smoothly transitioning the vehicle from the current in-vehicle network to the target in-vehicle network, meeting the communication requirements of intelligent vehicles in diverse scenarios, and enhancing driving safety and user experience.

[0033] The following describes the present disclosure through specific embodiments in combination with specific application scenarios.

[0034] Please refer to Figure 1 , Figure 1 which is a flowchart of a method for switching in-vehicle heterogeneous networks shown in an exemplary embodiment. The method may perform the following steps:

[0035] Step 102: Obtain vehicle-related information and / or environment-related information of the environment where the vehicle is located, and determine the target service requirements of the vehicle according to the vehicle-related information and / or environment-related information.

[0036] For example, an intelligent vehicle is driving on a highway. The vehicle system first collects environmental data such as the current driving speed, location information, and surrounding traffic conditions of the vehicle, and takes low-latency real-time traffic updates and high-precision navigation services as the target service requirements based on this information.

[0037] Among them, the current driving speed and location information of the vehicle can be obtained through the Global Positioning System (GPS) and the Inertial Measurement Unit (IMU), while the surrounding traffic conditions can be perceived and analyzed by devices such as in-vehicle cameras and radar sensors. These technical means ensure that the vehicle can accurately understand its own state and the environmental changes around it, providing a key basis for subsequent network selection.

[0038] Step 104: Determine a target in-vehicle network that matches the target service requirements from the multiple heterogeneous in-vehicle networks supported by the vehicle.

[0039] For example, based on the target service requirements of real-time traffic condition updates with low latency and high-precision navigation services, the vehicle system analyzes and determines that the existing Wi-Fi connection of the vehicle cannot provide the stability and coverage required by the target service. Therefore, it is necessary to switch to a Vehicle-to-Everything (V2X) communication network that matches the target service requirements to obtain lower-latency data transmission, and at the same time combine GPS (Global Positioning System) and cellular networks to ensure the accuracy of navigation.

[0040] Among them, the V2X communication network can achieve fast and reliable information exchange between vehicles and other vehicles as well as infrastructure. In addition, cellular networks (such as 4G / 5G) can provide wide geographical coverage and high data transmission rates, which are suitable for application scenarios with large amounts of data. By comprehensively applying these different network technologies, the vehicle can select the most suitable network configuration for specific application requirements.

[0041] Step 106: If the current in-vehicle network is not the target in-vehicle network, determine a handover strategy based on the current in-vehicle network quality and the target service requirements; and switch the current in-vehicle network to the target in-vehicle network according to the handover strategy.

[0042] For example, after confirming that the current Wi-Fi network does not meet the requirements of real-time traffic condition updates and high-precision navigation, the vehicle system first conducts a detailed assessment of the quality of the existing network, including key parameters such as signal strength, transmission rate, and latency. Based on the confirmed target service requirements, the vehicle system activates an intelligent network selection algorithm to determine an appropriate handover strategy. Considering that the vehicle is traveling at high speed and requires continuous data streams to ensure safe driving, the system selects the pre-handover strategy as an initial step. The pre-handover strategy allows the system to pre-establish connections with the target networks (V2X and cellular networks), but temporarily maintains the connection status with the original Wi-Fi network until it is confirmed that the new network can stably provide services. Once the new network connection is verified as reliable, the system will perform a soft handover, that is, wait until the current data transmission or service processing via Wi-Fi is completed, and then fully switch to the new network configuration. This method avoids the risks of data loss and service interruption. However, extreme cases also need to be considered. If an emergency is detected at any time, such as approaching a Wi-Fi coverage-free area and immediate access to the latest traffic information is required, the vehicle system will adopt a hard handover strategy, directly disconnect the Wi-Fi connection and quickly switch to the V2X and cellular networks. Although this may result in short-term data loss, in this case, the security of obtaining real-time traffic information takes precedence over data integrity.

[0043] Among them, hard handover refers to the method of directly cutting off the existing connection and accessing the new network regardless of whether the current data transmission task is completed, which is suitable for rapid response in emergency situations; soft handover refers to the method of performing network handover only after ensuring the completion of the current task, which can effectively prevent data loss and service interruption; pre-handover is a strategy of preparing in advance but not performing the final handover immediately. Only when all conditions are ripe will the network be officially switched. This method can improve the success rate and efficiency of network handover without affecting the user experience. The intelligent network selection algorithm automatically determines the most suitable handover strategy for the current situation by comprehensively considering factors such as network status and service requirements, ensuring the continuity and efficiency of network services.

[0044] In one illustrated embodiment, determining the target service requirements of the vehicle according to the vehicle-related information and / or environment-related information includes: predicting the geographical scenario where the vehicle will be located within a preset time period after the current moment based on the obtained vehicle-related information and / or environment-related information, and determining the target service requirements matching the geographical scenario.

[0045] For example, the vehicle system determines the current location, speed, and information of the vehicle based on the in-vehicle Global Positioning System (GPS), and predicts that the vehicle will be in the road scenario of a highway from the current moment to the next ten minutes. Considering the high requirements for real-time traffic condition updates and navigation accuracy on the highway, and the need for safe communication with surrounding vehicles, the system determines the low-latency real-time traffic condition updates and high-precision navigation services as the target business requirements.

[0046] Among them, the Global Positioning System (GPS) is a satellite navigation system that can provide accurate position information and time data. In this embodiment, the Global Positioning System (GPS) is used to determine the current location and speed of the vehicle, providing basic data support for subsequent geographical scenario prediction. The specific method for predicting the geographical scenario where the vehicle is located is not limited in this disclosure.

[0047] In an illustrated embodiment, the predicting the geographical scenario where the vehicle will be in a preset time period after the current moment based on the acquired vehicle-related information and / or environment-related information includes: constructing a three-dimensional map of the environment where the vehicle is located based on the acquired vehicle-related information and / or environment-related information, and recording the position, attitude, and speed of the vehicle; determining the geographical scenario where the vehicle will be in a preset time period after the current moment based on the three-dimensional map and the position, attitude, and speed of the vehicle.

[0048] For example, an intelligent vehicle is driving on a busy highway. The vehicle system first collects information on the current location, attitude, speed, and surrounding environment of the vehicle through its sensors (such as GPS signal receivers, IMUs (Inertial Measurement Units), cameras, and radars). These data are used to construct a detailed three-dimensional map that not only includes the current position and attitude information of the vehicle but also depicts environmental features such as the surrounding road structure, buildings, other vehicles, and obstacles. Based on this three-dimensional map, the system predicts that the vehicle will be in a specific road scenario of a highway within ten minutes after the current moment.

[0049] Among them, constructing a 3D map is a crucial step for intelligent vehicles to achieve environmental perception and precise navigation, involving data collection, processing, and fusion of multiple sensors. First, the vehicle collects information about its current position, attitude, speed, and the surrounding environment through sensors such as GPS signal receivers, IMUs, cameras, and radars. The GPS provides initial position information, and the IMU monitors the vehicle's attitude changes to ensure continuous position estimation even when GPS signals are weak. The camera captures visual images of the environment to identify road signs, lane lines, and other static features. The radar captures the distance, speed, and movement direction of the vehicle and obstacles. Especially in adverse weather or low visibility conditions, the radar can provide reliable dynamic environment information to complement the deficiencies of the camera. Then, using simultaneous localization and mapping technology, these multi-source data are fused and processed. The front end is responsible for data association and feature extraction, and the back end optimizes the results to minimize errors and improve the consistency and accuracy of the map. Finally, through dynamic object filtering technology, the influence of moving objects is removed, and static background information is retained to form an accurate and detailed 3D map for subsequent navigation and decision support. The 3D map constructed in this way not only provides a detailed description of the vehicle's surrounding environment but also supports real-time updates to adapt to changing road conditions. The present disclosure does not limit the specific construction process of the 3D map.

[0050] In an illustrated embodiment, the determining of the target service requirement that matches the geographical scenario includes: when the geographical scenario is a road scenario, determining the low-latency service communication requirement as the target service requirement; when the geographical scenario is a non-road scenario, determining the high-traffic service communication requirement as the target service requirement.

[0051] For example, an intelligent vehicle is driving from the suburban area of a city towards its destination and will pass through a large parking lot (off-road scenario) and a section of highway (road scenario) on the way. When the vehicle enters a large parking lot, the driver hopes to use this time to perform some high-traffic data transmission tasks, such as downloading the latest software or watching high-definition videos. A parking lot is usually an enclosed space. Although there may be Wi-Fi coverage, the signal strength and stability may not be consistent. Therefore, in this off-road scenario, the main communication requirement changes to high-traffic service communication. In this case, since the requirement for latency is not high but a large amount of data transmission tasks need to be processed, the system will give priority to using a network connection that can provide a large bandwidth. When the vehicle enters the highway, the driver's needs shift to real-time traffic condition updates and navigation assistance. The driving speed on the highway is fast, and the driver needs to timely understand key information such as the road conditions ahead and accident alerts to ensure safe driving. In addition, accurate location information is also crucial for avoiding missing exits or making quick responses. In this road scenario, the focus of the system is to provide low-latency data transmission services to support real-time traffic condition updates and high-precision navigation.

[0052] Among them, in the off-road scenario such as a parking lot, the system gives priority to using a network connection that can provide a large bandwidth, such as a Wi-Fi hotspot or a cellular network. If the Wi-Fi signal in the parking lot is strong and stable, the system will select Wi-Fi as the main network for high-traffic tasks. If there is no reliable Wi-Fi available, the system will switch to a cellular network (4G / 5G). Although the cost may be higher, it can still meet the high-traffic demand when there are no other options. In the road scenario such as a highway, the focus of the system is to provide low-latency data transmission services. To achieve this, the system selects to use a combination of V2X communication technology and a cellular network (4G / 5G). V2X allows vehicles to exchange real-time information with other vehicles and infrastructure, reducing the occurrence of traffic accidents and improving the overall traffic efficiency. The cellular network is used to receive the latest traffic information and send V2X communication data packets to ensure low-latency data transmission.

[0053] In an illustrated embodiment, the obtaining of vehicle-related information and / or environment-related information of the environment where the vehicle is located, and determining the target service requirement of the vehicle according to the vehicle-related information and / or environment-related information includes: obtaining the information ciphertext of the encrypted vehicle-related information and / or environment-related information of the environment where the vehicle is located; when the service provider or user using the vehicle passes the authorization verification, decrypting the information ciphertext, and determining the target service requirement of the vehicle according to the decrypted information plaintext.

[0054] For example, an intelligent vehicle is traveling on a busy highway. The vehicle collects information about its current position, attitude, speed, and the surrounding environment through sensors such as GPS signal receivers, IMUs, cameras, and radars. These data are encrypted and transmitted to a cloud server to ensure data security and privacy protection. Specifically, the system uses an asymmetric encryption algorithm to encrypt these data. Each vehicle has a public key and a private key pair, where the public key is used to encrypt the data, and the private key is securely stored locally in the vehicle or in a secure device trusted by the vehicle owner. The encrypted information ciphertext is sent to the cloud server. When the vehicle owner or service provider needs to access these data, a secure USB key containing the private key can be used for authentication. After inserting the USB key, the system reads the private key and uses it to decrypt the encrypted data downloaded from the cloud. Once the verification is successful and the decryption process is completed, the system will obtain the original vehicle position, attitude, speed, and surrounding environment information, and build a detailed 3D map based on this information. Based on this 3D map, the system predicts that the vehicle will be in a specific road scenario of the highway within ten minutes after the current moment, and takes low-latency real-time traffic updates and high-precision navigation services as the target business requirements of the vehicle.

[0055] Among them, in order to protect the security and privacy of vehicle and environmental related data, all collected data will be encrypted before transmission. Common encryption methods include symmetric encryption and asymmetric encryption. Symmetric encryption uses the same key for encryption and decryption, while asymmetric encryption uses a pair of public and private keys to perform encryption and decryption operations respectively. This ensures that even if the data is intercepted during transmission, unauthorized third parties cannot interpret its content, guaranteeing security.

[0056] In one shown implementation manner, determining a target vehicle-mounted network that matches the target business requirements from multiple vehicle-mounted heterogeneous networks supported by the vehicle includes: determining a candidate vehicle-mounted network that matches the target business requirements from multiple vehicle-mounted heterogeneous networks supported by the vehicle; if the number of candidate vehicle-mounted networks is one, determining this candidate vehicle-mounted network as the target vehicle-mounted network; if the number of candidate vehicle-mounted networks is multiple, determining the candidate vehicle-mounted network with the highest network quality as the target vehicle-mounted network, where the network quality of the candidate vehicle-mounted network is determined by at least one of the following network quality information: network bandwidth, network latency, network reliability, network cost.

[0057] For example, an intelligent vehicle is traveling on a busy highway. The system predicts that the vehicle will be in the specific road scenario of the highway within ten minutes after the current moment, and takes low-latency real-time traffic updates and high-precision navigation services as the target service requirements of the vehicle. The system needs to select a suitable in-vehicle heterogeneous network to meet the requirements. First, the system identifies multiple in-vehicle heterogeneous networks supported by the current vehicle, including Wi-Fi, 4G cellular network, 5G cellular network, and V2X communication network. Among these networks, only the 4G / 5G cellular network and the V2X communication network can provide the required low-latency communication services, so they are selected as candidate in-vehicle networks. If only the 5G cellular network is available in the area where the vehicle is located, and the V2X communication network cannot be used due to infrastructure limitations. In this case, the system will directly determine the 5G cellular network as the target in-vehicle network because it is the only candidate network that can meet the low-latency service requirements. If the area where the vehicle is located supports both the 4G / 5G cellular network and the V2X communication network. To decide which network is most suitable for the current target service requirements, the system will evaluate the quality of each candidate network. Considering that network stability is particularly important when driving on a highway. Although V2X communication performs well in areas with good network coverage, in some remote or underdeveloped infrastructure areas, its reliability and coverage may be inferior to those of mature cellular networks. Compared with the 4G cellular network, the 5G cellular network usually has higher bandwidth and can support more efficient data transmission. The 5G cellular network not only provides low-latency communication capabilities, but also has a wide coverage range and high reliability. Even without extensive V2X infrastructure support, the 5G cellular network can ensure stable connections and high-quality services. Therefore, the 5G cellular network is selected as the target in-vehicle network.

[0058] Among them, the V2X communication network is a technology specifically designed for low-latency communication and is suitable for information exchange between vehicles and between vehicles and infrastructure. It is very useful under specific conditions, such as urban traffic management and autonomous driving assistance, but its effectiveness is limited by the degree of support from the surrounding environment. The 5G cellular network provides lower latency, higher bandwidth, and stronger reliability than the previous generation of cellular technologies (such as the 4G cellular network). It is not only suitable for low-latency application scenarios, but also can support large data volume transmission. Even in areas with underdeveloped infrastructure, the 5G cellular network can provide more stable and reliable connections.

[0059] In an illustrated embodiment, determining the target service requirements of the vehicle based on the vehicle-related information and / or environment-related information includes: performing data cleaning on the acquired vehicle-related information and / or environment-related information to remove data noise and / or outliers; performing data association on the cleaned vehicle-related information and / or environment-related information to obtain the corresponding relationship between data, and performing data fusion on the associated data to obtain a fused data set; and determining the target service requirements of the vehicle according to the data features extracted from the fused data set.

[0060] For example, an intelligent vehicle is driving on a highway. The vehicle collects information about its current position, attitude, speed, and the surrounding environment through its equipped sensors such as GPS signal receivers, IMUs, cameras, and radars. These raw data may contain noise and outliers, such as drifts in GPS signals or blurred areas in camera images. To ensure the accuracy of subsequent analysis, the system first cleans the data to remove noise and outliers. Specifically, the system can use Kalman filtering to smooth the GPS data and reduce the impact of signal drift; at the same time, image processing techniques are applied to clean the noise and blurred parts in the camera images, making the data more accurate and reliable after cleaning. Next, the system performs data association on the cleaned data. For example, the current vehicle position information provided by GPS is associated with the vehicle attitude data of the IMU to form a complete vehicle state description; at the same time, the road signs captured by the camera are combined with the point cloud data generated by the radar to identify and label the road structure. Then, the system can adopt multi-sensor fusion techniques, such as extended Kalman filtering or particle filtering, to merge the data of multiple associated sensors into a unified representation form, and then generate a fused data set. Finally, based on the fused data set, the system extracts key data features, such as the current driving speed of the vehicle, the road conditions ahead, and the traffic flow, and determines the target service requirements accordingly.

[0061] Among them, Kalman filtering is a commonly used recursive filter for estimating the state of a system and can effectively remove noise in sensor data. Some image processing techniques, such as Gaussian blur and edge detection, can remove noise and blurred parts in camera images and improve image quality. Data association may involve timestamp synchronization of data to ensure that data collected by different sensors can be compared and associated at the same time point, and feature matching algorithms are used to align data from different sensors to establish the corresponding relationship between data. This step ensures that data from different sources can complement each other and provide a more comprehensive environmental description.

[0062] To help those skilled in the art better understand the above embodiments, the following combines Figure 2 and Figure 3The above embodiments will be described.

[0063] Please refer to Figure 2 , Figure 2 which is a schematic diagram of data flow of a vehicle-mounted heterogeneous network handover method shown in an exemplary embodiment. As Figure 2 shown, the vehicle is equipped with a variety of sensors, including cameras, lidar, etc., for omnidirectionally perceiving vehicle-related information and / or surrounding environment-related information. These sensors collect road conditions, obstacle positions, traffic flow, and vehicle data in real time, and transmit this raw data to the network fusion engine. At the same time, the multi-network interface unit provides multiple data transmission interfaces, supporting multiple network connection methods such as Wi-Fi, 4G / 5G cellular networks, V2X communication, etc., to transmit internal and external data. Through these interfaces, the multi-network interface unit can not only ensure smooth communication between various sensors and computing units in the vehicle, but also establish a stable connection with external cloud servers or roadside infrastructure, ensuring that the vehicle can obtain the required information in a timely manner and make corresponding adjustments. After receiving the data from the environmental perception module and the multi-network interface unit, the network fusion engine first cleans and preprocesses this data, removes noise and outliers, and performs data association and fusion. Then, based on the processed environmental information, vehicle state, and network state, the network fusion engine selects the optimal network strategy through an internal intelligent algorithm, and sends the optimized information to the application service to execute corresponding tasks or decisions.

[0064] Please refer to Figure 3 , Figure 3 which is a schematic diagram of data flow of a network fusion engine shown in an exemplary embodiment. As Figure 3 shown, the data analysis and fusion module performs data fusion on the environmental information, data from the multi-network interface unit, and data obtained from network state detection, then extracts data features from the fused data, and finally feeds back the extracted data features to the intelligent network selection module. The intelligent network selection module formulates the optimal network strategy and specific network handover decisions based on the data features extracted and fed back by the data analysis and fusion module. The network handover management module executes network handover actions according to the decisions of the intelligent network selection module. The protocol conversion module performs protocol conversion according to the network handover actions executed by the network handover management module, and feeds back to the data analysis and fusion module. The output of the data analysis and fusion module will be fed back to the intelligent network selection module again, forming a closed-loop feedback system, continuously optimizing network selection according to real-time data.

[0065] Corresponding to the above embodiments of the vehicle-mounted heterogeneous network handover method, the present disclosure also provides an embodiment of a vehicle-mounted heterogeneous network handover system.

[0066] Please refer to Figure 4 , Figure 4It is a hardware structure diagram of an electronic device shown in an exemplary embodiment. At the hardware level, the device includes a processor 402, an internal bus 404, a network interface 406, a memory 408, and a non-volatile memory 410. Of course, it may also include other required hardware. One or more embodiments of the present disclosure can be implemented in a software manner. For example, the processor 402 reads the corresponding computer program from the non-volatile memory 410 into the memory 408 and then runs it. Of course, in addition to the software implementation manner, one or more embodiments of the present disclosure do not exclude other implementation manners, such as logic devices or a combination of software and hardware, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, and can also be hardware or a logic device.

[0067] Please refer to Figure 5 , Figure 5 It is a schematic diagram of a vehicle heterogeneous network switching system shown in an exemplary embodiment. The vehicle heterogeneous network switching system 500 can be applied to an electronic device as shown in Figure 4 to implement the technical solution of the present disclosure.

[0068] The system includes:

[0069] An environment perception layer 502, configured to obtain vehicle-related information and / or environment-related information of the environment where the vehicle is located, and determine the target service requirements of the vehicle according to the vehicle-related information and / or environment-related information;

[0070] A fusion engine layer 504, configured to determine a target vehicle-mounted network that matches the target service requirements from multiple vehicle heterogeneous networks supported by the vehicle;

[0071] An application service layer 506, configured to determine a switching strategy according to the current vehicle-mounted network quality and the target service requirements if the current vehicle-mounted network is not the target vehicle-mounted network; and switch the current vehicle-mounted network to the target vehicle-mounted network according to the switching strategy.

[0072] In some embodiments, the environment perception layer includes:

[0073] A requirement determination layer, configured to predict the geographical scenario where the vehicle will be located within a preset time period after the current moment according to the obtained vehicle-related information and / or environment-related information, and determine the target service requirements that match the geographical scenario.

[0074] In some embodiments, the requirement determination layer includes:

[0075] A scenario construction layer, configured to construct a three-dimensional map of the environment where the vehicle is located according to the obtained vehicle-related information and / or environment-related information, and record the position, attitude, and speed of the vehicle.

[0076] A scene judgment layer, configured to determine a geographical scene where the vehicle is located within a preset time period after the current moment based on the three-dimensional map and the position, attitude, and speed of the vehicle.

[0077] In some embodiments, the requirement determination layer is specifically configured to:

[0078] When the geographical scene is a road scene, determine the low-latency service communication requirement as the target service requirement;

[0079] When the geographical scene is a non-road scene, determine the high-traffic service communication requirement as the target service requirement.

[0080] In some embodiments, the environment perception layer includes:

[0081] A data acquisition layer, configured to acquire ciphertexts of encrypted vehicle-related information and / or environment-related information of the environment where the vehicle is located;

[0082] A data decryption layer, configured to decrypt the ciphertext when the service provider or user of the vehicle passes the authorization verification, and determine the target service requirement of the vehicle according to the decrypted plaintext information.

[0083] In some embodiments, the fusion engine layer includes:

[0084] A network candidate layer, configured to determine a candidate vehicle-mounted network that matches the target service requirement from multiple heterogeneous vehicle-mounted networks supported by the vehicle;

[0085] A network target layer, configured to, if the number of candidate vehicle-mounted networks is one, determine this candidate vehicle-mounted network as the target vehicle-mounted network;

[0086] The network target layer is further configured to, if the number of candidate vehicle-mounted networks is multiple, determine the candidate vehicle-mounted network with the highest network quality as the target vehicle-mounted network, where the network quality of the candidate vehicle-mounted network is determined by at least one of the following network quality information: network bandwidth, network latency, network reliability, network cost.

[0087] In some embodiments, the environment perception layer includes:

[0088] A data cleaning layer, configured to clean the acquired vehicle-related information and / or environment-related information to remove data noise and / or outliers;

[0089] A data fusion layer for associating the cleaned vehicle-related information and / or environment-related information to obtain the corresponding relationships between the data, and fusing the associated data to obtain a fused data set;

[0090] A feature extraction layer for determining the target business requirements of the vehicle according to the data features extracted from the fused data set.

[0091] The implementation processes of the functions and roles of each unit in the above device are specifically described in the implementation processes of the corresponding steps in the above method, and will not be elaborated here.

[0092] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial descriptions of the method embodiments. The device embodiments described above are only illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present disclosure solution. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0093] The system, device, module or unit described in the above embodiments can be specifically implemented by a computer chip or entity, or by a product with certain functions. A typical implementation device is a computer, and the specific form of the computer can be a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email transceiver device, a game console, a tablet computer, a wearable device, or a combination of any several of these devices.

[0094] In a typical configuration, a computer includes one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0095] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM), and / or non-volatile memory in the form of, for example, read-only memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

[0096] A computer-readable medium includes permanent and non-permanent, removable and non-removable media that can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices, or any other non-transitory media that can be used to store information accessible by a computing device. As defined herein, a computer-readable medium does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0097] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data that have been authorized by the user or fully authorized by all parties. And the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or reject.

[0098] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of additional identical elements in the process, method, commodity or device comprising the said element.

[0099] The above describes specific embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the particular order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0100] The terms used in one or more embodiments of the present disclosure are for the purpose of describing particular embodiments only and are not intended to limit one or more embodiments of the present disclosure. The singular forms "a", "the", and "said" used in one or more embodiments of the present disclosure and the appended claims are also intended to include the plural forms unless the context clearly dictates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0101] It should be understood that although the terms first, second, third, etc. may be used in one or more embodiments of the present disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of one or more embodiments of the present disclosure, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining".

[0102] The above description is only a preferred embodiment of one or more embodiments of the present disclosure and is not intended to limit one or more embodiments of the present disclosure. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of one or more embodiments of the present disclosure shall be included within the scope of protection of one or more embodiments of the present disclosure.

Claims

1. A vehicle-mounted heterogeneous network handover method, characterized in that, The method includes: Obtaining vehicle-related information and / or environment-related information of the environment where the vehicle is located, and determining a target service requirement of the vehicle according to the vehicle-related information and / or the environment-related information; Determining a target vehicle-mounted network that matches the target service requirement from multiple heterogeneous vehicle-mounted networks supported by the vehicle; If the current vehicle-mounted network is not the target vehicle-mounted network, determining a handover strategy according to the current vehicle-mounted network quality and the target service requirement; and switching the current vehicle-mounted network to the target vehicle-mounted network according to the handover strategy.

2. The method according to claim 1, wherein The determining the target service requirement of the vehicle according to the vehicle-related information and / or the environment-related information includes: Predicting a geographical scenario where the vehicle will be located within a preset time period after the current moment according to the obtained vehicle-related information and / or environment-related information, and determining a target service requirement that matches the geographical scenario.

3. The method according to claim 2, wherein The predicting the geographical scenario where the vehicle will be located within a preset time period after the current moment according to the obtained vehicle-related information and / or environment-related information includes: Constructing a three-dimensional map of the environment where the vehicle is located according to the obtained vehicle-related information and / or environment-related information, and recording the position, attitude and speed of the vehicle; Based on the three-dimensional map and the position, attitude and speed of the vehicle, determining the geographical scenario where the vehicle will be located within a preset time period after the current moment.

4. The method according to claim 2, wherein The determining the target service requirement that matches the geographical scenario includes: In the case where the geographical scenario is a road scenario, determining a low-latency service communication requirement as the target service requirement; In the case where the geographical scenario is a non-road scenario, determining a high-traffic service communication requirement as the target service requirement.

5. The method according to claim 1, wherein The obtaining vehicle-related information and / or environment-related information of the environment where the vehicle is located, and determining the target service requirement of the vehicle according to the vehicle-related information and / or the environment-related information includes: Obtaining an information ciphertext of the encrypted vehicle-related information and / or environment-related information of the environment where the vehicle is located; When the service provider or user using the vehicle passes the authorization verification, decrypting the information ciphertext, and determining the target service requirement of the vehicle according to the decrypted information plaintext.

6. The method according to claim 1, wherein The determining a target vehicle-mounted network that matches the target service requirement from multiple heterogeneous vehicle-mounted networks supported by the vehicle includes: Determining candidate vehicle-mounted networks that match the target service requirement from multiple heterogeneous vehicle-mounted networks supported by the vehicle; If the number of the candidate vehicle-mounted networks is one, determining the candidate vehicle-mounted network as the target vehicle-mounted network; If the number of the candidate vehicle-mounted networks is multiple, determining the candidate vehicle-mounted network with the highest network quality as the target vehicle-mounted network, where the network quality of the candidate vehicle-mounted network is determined by at least one of the following network quality information: network bandwidth, network latency, network reliability, network cost.

7. The method according to claim 1, characterized in that, The determining the target service requirement of the vehicle according to the vehicle-related information and / or the environment-related information includes: Perform data cleaning on the obtained vehicle-related information and / or the environment-related information to remove data noise and / or outliers; Perform data association on the cleaned vehicle-related information and / or environment-related information to obtain the corresponding relationship between data, and perform data fusion on the associated data to obtain a fused dataset; Determine the target business requirements of the vehicle according to the data features extracted from the fused dataset.

8. A vehicle-mounted heterogeneous network handover system, characterized in that, The system includes: An environment perception layer for obtaining vehicle-related information and / or environment-related information of the environment where the vehicle is located, and determining the target business requirements of the vehicle according to the vehicle-related information and / or environment-related information; A fusion engine layer for determining a target vehicle-mounted network that matches the target business requirements from multiple heterogeneous vehicle-mounted networks supported by the vehicle; An application service layer for determining a handover strategy according to the current vehicle-mounted network quality and the target business requirements if the current vehicle-mounted network is not the target vehicle-mounted network; and switching the current vehicle-mounted network to the target vehicle-mounted network according to the handover strategy.

9. The system according to claim 8, wherein The environment perception layer includes: A data cleaning layer for performing data cleaning on the obtained vehicle-related information and / or the environment-related information to remove data noise and / or outliers; A data fusion layer for performing data association on the cleaned vehicle-related information and / or environment-related information to obtain the corresponding relationship between data, and performing data fusion on the associated data to obtain a fused dataset; A feature extraction layer for determining the target business requirements of the vehicle according to the data features extracted from the fused dataset.

10. An electronic device, characterized in that, It includes a communication interface, a processor, a memory, and a bus, and the communication interface, the processor, and the memory are interconnected through the bus; Machine-readable instructions are stored in the memory, and the processor executes the method according to any one of claims 1 to 7 by calling the machine-readable instructions.

11. A machine-readable storage medium, characterized in that, The machine-readable storage medium stores machine-readable instructions, and when the machine-readable instructions are called and executed by the processor, the method according to any one of claims 1 to 7 is implemented.

Images