Method and system for intelligent guided network selection

Abstract

A method for intelligently guiding network selection includes detecting a wireless connection problem between networks. The vehicle-mounted network device is located inside the vehicle, and the network access device can be located inside or outside the vehicle. The method also includes receiving network data. The network data includes a list of available networks and network performance characteristics for each of the available networks. The method includes using machine learning to predict quality of service (QoS) indicators for available networks along the trip of the vehicle, and solving based on the predicted QoS indicators for the available networks and a constraint of QoS constraints to select one or more networks from the list of available networks for one or more in-vehicle network devices.

Description

Technical Field

[0001] The present invention relates to a system and method for intelligently guiding network selection. Background Art

[0002] This section generally presents the background of the invention. To the extent described in this section, the work of the presently named inventors and aspects of the description that may not constitute prior art at the time of filing are neither expressly nor impliedly admitted to be prior art to the present invention.

[0003] In some cases, vehicle features, vehicle applications, network devices (e.g., mobile phones) require certain throughput and latency constraints. To address these quality of service (QoS) constraints, network devices can switch from one network to another. In other words, network devices can disconnect from one network and connect to another network. However, such network switching may cause reconnection delays. Therefore, it is desirable to predict the connection quality to allow seamless switching from one network to another even before the current connection quality degrades. Summary of the invention

[0004] The present invention describes a method for intelligently guiding network selection. In some aspects of the present invention, the method includes detecting the best available wireless connectivity and enabling the vehicle to select an appropriate NAD from a list of NADs to establish a connection. The method also includes receiving network data in response to maintaining good QoS and throughput of network access devices. The network data includes a list of available networks and network performance characteristics of each of the available networks. The network performance characteristics include network throughput offerings and network latency offerings. The method includes using machine learning to predict and constrain solving QoS indicators of available networks in a vehicle journey. The method also includes selecting one or more from a list of available networks and network technologies based on the predicted QoS indicators and QoS constraints of the available networks to determine a selected network list for one or more on-board network devices. Then, the method includes connecting one or more on-board network devices to the selected network list.

[0005] Implementations may include one or more of the following features. The vehicle network device is one of a plurality of vehicle network devices. Each of the plurality of vehicle network devices runs an application. Each of the plurality of vehicle network devices has an independent throughput requirement and an independent delay requirement. The method includes receiving network demand data. The network demand data includes the number of a plurality of vehicle network devices, the independent throughput requirement of each of the plurality of vehicle network devices, and the independent delay requirement of each of the plurality of vehicle network devices. The network performance characteristics of each of the available networks also include the supported bandwidth of each of the available networks. The plurality of vehicle network devices are associated with users. The method may also include detecting the number of users. The method also includes determining network demand and receiving the priority and constraints (e.g., no public Wi-Fi, low cost, etc.) of each user in the entire journey of the vehicle. The method may include receiving external factor data for each of the plurality of route segments of the navigation route of the entire journey. The external factor data includes the network traffic volume of each of the plurality of route segments, the vehicle location of each of the plurality of route segments, the seasonality of each of the plurality of route segments, the time of day of each of the plurality of route segments, and the vehicle speed of each of the plurality of route segments. The external factor data is used to predict the QoS indicators of the available networks. QoS indicators of available networks are predicted using external factor data and network performance characteristics of each of the available networks. Network performance characteristics and number of users of each of the available networks. Traffic volume of each of multiple route segments is determined by crowdsourcing or sensors or a combination. Machine learning can be a recurrent neural network. Machine learning can include fully connected deep neural networks and convolutional neural networks. Machine learning can be supervised or unsupervised or reinforcement learning. Multiple deep neural networks are used to predict QoS indicators of available networks throughout the vehicle's journey. Machine learning includes convolutional neural networks. Convolutional neural networks are used to determine crowds and traffic patterns using a vehicle's camera. Implementations of the technology may include hardware, methods, or computer software on a computer-accessible medium.

[0006] The present invention also describes a system for intelligently guiding network selection. The system includes an on-board network device and a controller communicating with the on-board network device. The controller is programmed to execute the above method.

[0007] The present invention also describes a tangible, non-transitory machine-readable medium comprising machine-readable instructions which, when executed by a processor, cause the processor to perform the above method.

[0008] Further areas of applicability will become apparent from the description provided herein.It should be understood that the description and specific examples are intended for purposes of illustration only and are not intended to limit the scope of the present invention.

[0009] The above features and advantages and other features and advantages of the presently disclosed systems and methods are apparent from the detailed description, including the claims and exemplary embodiments, when taken in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The present invention will be more fully understood from the detailed description and accompanying drawings, in which:

[0011] Figure 1 is a schematic diagram of a system for intelligently guiding network selection;

[0012] Figure 2 is a method for intelligently guiding network selection;

[0013] Figure 3 is the method used to collect data about available networks;

[0014] Figure 4 Is a feedback method used to identify connection problems. DETAILED DESCRIPTION

[0015] Reference will now be made in detail to several examples of the present invention as illustrated in the accompanying drawings. Whenever possible, the same or similar reference numerals are used in the drawings and the description to refer to the same or similar components or steps.

[0016] like Figure 1 As shown, the vehicle 10 generally includes a body 12 and a plurality of wheels 14 coupled to the body 12. The vehicle 10 may be an autonomous vehicle. In the illustrated embodiment, the vehicle 10 is depicted as a sedan in the illustrated embodiment, but it should be understood that other vehicles may also be used, such as trucks, coupes, sport utility vehicles (SUVs), recreational vehicles (RVs), airplanes, helicopters, etc.

[0017] The vehicle 10 also includes one or more sensors 24 connected to the vehicle body 12. The sensors 24 sense observable conditions of the external environment and / or the internal environment of the vehicle 10. As non-limiting examples, the sensors 24 may include one or more cameras, one or more light detection and ranging (L IDAR) sensors, one or more proximity sensors, one or more cameras, one or more ultrasonic sensors, one or more thermal imaging sensors, and / or other sensors. Each sensor 24 is configured to generate a signal indicative of a sensed observable condition (i.e., sensor data) of the external environment and / or the internal environment of the vehicle 10.

[0018] The vehicle 10 includes one or more in-vehicle network devices 16. In the present invention, the term "network device" refers to electronic hardware that is configured to wirelessly connect to the network 30 and is programmed to run other software applications. As non-limiting examples, the in-vehicle network device 16 can be a mobile phone, a computer, a tablet computer, an internal integrated component of the vehicle 10 (e.g., a vehicle feature such as GPS navigation), or any other electronic hardware that is configured to send and receive data over a network. Each in-vehicle network 16 is disposed inside the vehicle 10, includes a transceiver 18, and is capable of running applications (e.g., video games).

[0019] The vehicle 10 includes a controller 34 that communicates with the sensor 24 and the onboard remote network device 16. The controller 34 includes at least one processor 44 and a non-transitory computer-readable storage device or medium 46. The processor 44 can be a custom or commercially available processor, a central processing unit (CPU), a graphics processing unit (GPU), an auxiliary processor in several processors associated with the vehicle controller 34, a semiconductor-based microprocessor (in the form of a microchip or chipset), a macroprocessor, a combination thereof, or generally a device for executing instructions. The computer-readable storage device or medium 46 can include volatile and non-volatile memory such as read-only memory (ROM), random access memory (RAM), and keep-alive memory (KAM). KAM is a persistent or non-volatile memory that can be used to store various operating variables when the processor 44 is powered off. The computer readable storage device or medium 46 may be implemented using a variety of storage devices, such as PROM (Programmable Read Only Memory), EPROM (Electrical PROM), EEPROM (Electrically Erasable PROM), flash memory, or any other electrical, magnetic, optical, or combination storage device capable of storing data used by the vehicle controller 34 in controlling the vehicle 10, some of which represents executable instructions. The controller 34 of the vehicle 10 may be referred to as a vehicle controller and may be programmed to perform the methods 100, 200, and 300 described in detail below. Figure 3-4 ).

[0020] The instructions may include one or more separate programs, each of which includes an ordered list of executable instructions for implementing logical functions. When executed by the processor 44, the instructions receive and process signals from sensors, execute logic, calculations, methods and / or algorithms for automatically controlling components of the vehicle 10, and generate control signals based on the logic, calculations, methods and / or algorithms to automatically control components of the vehicle 10. Although Figure 11 , a single controller 34 is shown, but embodiments of the vehicle 10 may include multiple controllers 34 that communicate via a suitable communication medium or combination of communication mediums and cooperate to process sensor signals, perform logic, calculations, methods and / or algorithms, and generate control signals to automatically control features of the vehicle 10. The controller 34 is part of the system 20 for intelligent guidance network 30 selection.

[0021] In addition to the controller 34, the system 20 also includes a vehicle, an onboard network device 16, and one or more network access devices (NADs) 28. In the present invention, the term "network access device" refers to a hardware device that allows a computer or other network device 16 to connect to a network 30. The NAD 28 is typically located at the edge of the network 30 and provides an interface between the network 30 and the onboard network devices 16 connected to the NAD 28. As non-limiting examples, the NAD 28 can be a router, a switch, a wireless access point, and a modem. The NAD 28 can be inside the vehicle 10 (and part of the vehicle 10) or outside the vehicle 10. Regardless of its location, each NAD 28 is wirelessly connected to one or more networks 30 and serves as an interface between the onboard network devices 16 and the network 30. As non-limiting examples, the network 30 can be a cellular network, a local area network (LAN), a wide area network (WAN), a Wi-Fi network, the Internet, etc. Cellular networks may include 3G, 4G, 5G, LTE, WiMAX, etc.

[0022] The system 20 uses a wireless network device optimization model and distributes data across multiple NADs 28. Specifically, the system 20 considers factors such as location, route, trajectory, time of day, repetitive patterns, etc. to determine the best NAD data distribution. Before selecting the best NAD 28 for the application, the machine learning predictor dynamically optimizes QoS indicators for each NAD 28. The system 20 applies periodic mitigation based on vehicle experience data and other NAD factors.

[0023] Figure 21 is a flow chart of a method 100 for intelligently guiding network 30 selection. The method 100 begins at box 102. At box 102, the controller 34 detects whether there is a wireless connection problem between one or more vehicle network devices 16 and one or more network access devices 28. To this end, the controller 34 can determine the quality of service (QoS) indicator of the network service and compare the QoS indicator of the network service with a predetermined threshold. As a non-limiting example, the QoS indicator of the network service may include latency, throughput, availability, jitter, etc. If one or more QoS indicators of the network service are less than the predetermined threshold, a connection problem is detected. If the QoS indicator of the network service is equal to or greater than the predetermined threshold, no connection problem is detected. If no connection problem is detected, the method 100 proceeds to box 104 and the method 100 ends. Alternatively, if no connectivity problem is detected, the method 100 can continuously perform box 102 to monitor the connectivity between the vehicle network device 16 and the network access device 28. If a connection problem is detected, the method 100 continues to box 106.

[0024] At block 106, the controller 34 receives network data. The network data includes a list of available networks 30 and network performance characteristics of each of the available networks 30. The network performance characteristics include network throughput provision, network latency provision, and bandwidth supported by each of the available networks, among other things. Each network 30 may be associated with a NAD 28. The network data may also include NAD internal data sets. The NAD internal data sets may include a readiness index and an activity index for each NAD 28. The network data may also include a dynamic network data set. The method 100 continues to block 108.

[0025] At box 108, the controller 34 uses machine learning to predict QoS metrics for the available network 30 along the entire trip of the vehicle 10. The machine learning algorithm can be, for example, a recurrent neural network (RNN) that processes time series data. Alternatively, if traffic recognition is based on images rather than enumerated inputs, the machine learning can be a combination of a fully connected deep neural network (DNN) and a convolutional neural network (CNN) to analyze the images to understand traffic levels, which can be crowdsourced or rely on information about the number of network devices connected to cell towers.

[0026] At box 108, a machine learning algorithm (e.g., a DNN or RNN) can use different data sets to predict QoS indicators of available networks 30. For example, the machine learning algorithm can use external factor data, static rules, network performance characteristics of each of the available networks, and the number of users to predict the QoS indicators of the available networks 30. The static rule set may include preferences for cost ranges, user priorities, and restrictions such as no public Wi-Fi___33. As described above, the machine learning algorithm can use the navigation route of the vehicle 10 to predict the QoS indicators of the available networks along the entire trip 30 of the vehicle 10. Therefore, the controller 34 can receive navigation data from the vehicle 10, such as the navigation route of the vehicle 10 to reach the desired destination.

[0027] As described above, a machine learning algorithm (e.g., a DNN or RNN) can use dynamic external factors and parameters of each of the multiple route segments of the navigation route of the vehicle 10 for the entire trip to predict the QoS indicators of the available network 30 along the entire trip of the vehicle 10. The dynamic external factors and parameters may include, but are not limited to, the traffic volume of each of the multiple route segments, the vehicle location of each of the multiple route segments, the seasonality of each of the multiple route segments, the time of day of each of the multiple route segments, and the vehicle speed of the vehicle 10 for each of the multiple route segments. The traffic volume of each of the multiple route segments can be determined by crowdsourcing and in combination with sensors. For example, the vehicle 10 can use V2V communication to collect traffic data from other vehicles. Therefore, at box 108, the controller 34 receives the dynamic external factors and parameters of each of the multiple route segments of the navigation route of the entire trip of the vehicle 10.

[0028] At box 108, as described above, a machine learning algorithm (e.g., a RNN or DNN) can use the network demand to predict QoS indicators of available networks 30 along the entire journey of the vehicle 10. To this end, the controller 34 can receive network demand data. The network demand data may include determining the network demand of each user throughout the journey of the vehicle 10. The network demand of each user may depend on the applications running on each in-vehicle network device 16. The applications may include, but are not limited to, GPS navigation, online meeting applications with video, email applications, social media applications, music applications, etc. Each in-vehicle network device 16 has independent throughput requirements and independent latency requirements. After predicting the QoS indicators of available networks 30 along the entire journey of the vehicle 10, the machine learning algorithm ranks the top available networks based on all of the different factors discussed, and the method 100 continues to box 110.

[0029] At box 110, the controller 34 selects one or more networks 30 (i.e., selected networks) from the list of available networks 30 for the vehicle network device 16 based on the QoS indicators of the available networks along the entire journey of the vehicle 10 predicted and ranked by the machine learning algorithm (e.g., RNN or DNN). The selection of the network 30 may also depend on the QoS rule set. The QoS rule set is a list of rules based on the network service requirements (QoS requirements) of each application running on the vehicle network device 16. The selection of the network 30 may also depend on the NAD performance rule set. The NAD performance rule set includes rules based on whether the NAD performance characteristics will enable the application running on the vehicle network device 16 to run normally. NAD performance characteristics may include availability, delay, loss, and utilization. The availability of NAD 28 may depend on connectivity and functionality. The delay characteristics of NAD 28 may include round-trip delay and delay variance. The loss characteristics of NAD 28 may include one-way loss and round-trip loss. The utilization characteristics of NAD 28 may include bandwidth, capacity, and throughput. Once the network 30 is selected, the vehicle network device is connected to the selected network 30. Specifically, seamless switching occurs to switch the connection from the current network 30 to the newly selected network 30. The mapping of the sorted network (NAD) to the set of network devices can be done by constraint solving. QoS rules and requirements are converted into constraints, and the constraint solver can solve all subsets of network devices into one of the sorted NADs. The best feasible mapping will be selected to achieve seamless network switching. For example, all network devices can be mapped to network 1, or a subset of network devices can be mapped to network 1, and another subset of network devices can be connected to network 2. The scheduling predictor will switch wireless technologies based on application requirements and predicted functional requirements to ensure bit rate (GBR), delay critical tasks and non-GBR best efforts. The controller 34 can generate a list of the best set of networks 30 and prioritize the networks based on QoS thresholds (e.g., throughput thresholds and delay thresholds). Some applications can use one network 30, while another application can use another network 30 based on QoS thresholds and cost constraints. Then the method 100 returns to box 102.

[0030] Figure 3 is a method 200 for collecting data about available networks, as described above with respect to Figure 2The method 200 starts at block 202. The method 200 then continues to block 204. At block 204, the controller 34 collects a list of available networks 30 for the current navigation segment and network performance characteristics of each of the available networks 30. The network performance characteristics include network throughput provision, network latency provision, supported bandwidth, connectivity, and throughput supported by each of the available networks. The available networks 30 may include a home Wi-Fi network, a public Wi-Fi network, a 5G network, a 4G network, etc. The method 200 then continues to block 206.

[0031] At box 206, the controller 34 retrieves a navigation route for the vehicle 10. Alternatively, the controller 34 selects a regular route based on time (e.g., a route to the office, a route to school, etc.). The navigation route can be retrieved from a navigation application. The navigation route can be determined based on an appointment or a regular route based on time. Once the vehicle arrives at the destination, the vehicle Wi-Fi will be predicted to be disconnected, which can trigger a switch to a different NAD. The method 200 then continues to box 208.

[0032] At block 208, the controller 34 selects the available networks 30 for the next navigation segment and the network performance characteristics of each of the available networks 30. The network performance characteristics include network throughput provision, network latency provision, supported bandwidth, connectivity, and throughput supported by each of the available networks. The available networks 30 may include a home Wi-Fi network, a public Wi-Fi network, a 5G network, a 4G network, etc. The method 200 then proceeds to block 210.

[0033] At box 210 , the controller 34 detects the number of users. To this end, the controller 34 may receive user data from, for example, a body control module (BCM) of the vehicle 10 . The user data may include the number of doors opened, images captured by the vehicle, data from seat pressure sensors, seat belt usage, vehicle Bluetooth access information and / or Wi-Fi access information, or use of an interior camera, etc. The method 200 then continues to box 212 .

[0034] At box 212, the controller 34 determines the network requirements of each user throughout the journey of the vehicle 10. To this end, the controller 34 may first collect the individual network requirements of each user and then estimate the overall network requirements of all users in the vehicle 10. The individual network requirements of each user may depend on the applications that the user will use throughout the journey of the vehicle 10. Specifically, the individual network requirements of each user may be determined by accessing each user's electronic calendar and the applications running on each user's in-vehicle network device 16. For example, the user's electronic calendar may indicate that he or she has an online video conference that requires specific network requirements during the journey of the vehicle 10. The user may also run music or video applications on their in-vehicle network device 16. In addition, the controller 34 may use a conventional use learner application to determine the network requirements of each user. Each user may run different applications in their in-vehicle network device 16, such as online video conferencing applications, email, GPS navigation applications, music applications, etc. The set of available networks 30 may be limited by constraints implemented by the user. For example, the user may not allow the online video conferencing application to use a public Wi-Fi network. Then, the method 200 continues at box 214. At box 214, the method 200 ends.

[0035] Figure 4 is used to determine the above Figure 1 The method 300 for feedback on connectivity issues discussed in block 102 of FIG. 300 begins at block 302. Then, the method 300 proceeds to block 304. At block 304, the controller 34 detects a QoS issue for an application running on the vehicle network device 16. Then, the method 300 proceeds to block 306. At block 306, the controller 34 generates a feedback trigger in response to detecting a QoS issue for an application running on the vehicle network device 16. Then, the method 300 proceeds to block 308. At block 308, the controller 34 identifies the correct feedback question and then asks the user the feedback question through, for example, a user interface of the vehicle 10. The feedback question may be: "Do you find any connectivity issues with the network?", and then the user answers the feedback question. The method 300 proceeds to block 310. At block 310, the controller 34 collects answers to the feedback question and triggers related and subordinate questions (if necessary). Then, the method 300 proceeds to block 312. At block 312, the controller 34 analyzes the answers to the feedback question and changes the constraints and QoS thresholds if necessary. The controller 34 may also recommend alternative networks 30 based on the conditions. For example, the network 30 may be filtered out based on a rule set, profile settings, etc. As a non-limiting example, the QoS thresholds may include a throughput threshold and a delay threshold. The current throughput and delay thresholds may be changed to more appropriate values ​​to accommodate network uncertainties.

[0036] Although exemplary embodiments are described above, it is not intended that these embodiments describe all possible forms included in the claims. The words used in the specification are descriptive rather than restrictive, and it is understood that various changes can be made without departing from the spirit and scope of the present invention. As previously mentioned, the features of the various embodiments can be combined to form further embodiments of the currently disclosed system and method that may not be explicitly described or illustrated. Although various embodiments can be described as having advantages or advantages over other embodiments or prior art embodiments relative to one or more desired features, it is recognized by those of ordinary skill in the art that one or more features or characteristics can be compromised to achieve the desired overall system properties, depending on the specific application and implementation. These properties may include, but are not limited to, cost, strength, durability, life cycle cost, marketability, appearance, packaging, size, applicability, weight, manufacturability, ease of assembly, etc. Therefore, embodiments described as less ideal than other embodiments or prior art implementations relative to one or more features are not outside the scope of the present invention and may be ideal for specific applications.

[0037] The drawings are in simplified form and are not drawn to exact scale. Directional terms such as top, bottom, left, right, up, above, above, below, below, rear, and front may be used with respect to the drawings for convenience and clarity of description only. These directional terms and similar directional terms should not be construed as limiting the scope of the present invention in any way.

[0038] Embodiments of the present invention are described herein. However, it should be understood that the disclosed embodiments are merely examples, and other embodiments in various alternative forms may be employed. The drawings are not necessarily drawn to scale; certain features may be magnified or minimized to show the details of a particular component. Therefore, the specific structural and functional details disclosed herein should not be interpreted as limiting, but only as a representative basis for teaching those skilled in the art to adopt the systems and methods of the present invention in different ways. As will be understood by those of ordinary skill in the art, the various features illustrated and described with reference to any one of the figures may be combined with the features shown in one or more other figures to produce embodiments that are not explicitly shown or described. The combination of features shown provides representative embodiments of typical applications. However, various combinations and modifications of features consistent with the teachings of the present invention may be required for specific applications or implementations.

[0039] Embodiments of the present invention may be described herein according to functions and / or logic block components and various processing steps. It should be understood that such block components may be implemented by being configured to perform a plurality of hardware, software and / or firmware components of a specified function. For example, embodiments of the present invention may employ various integrated circuit components, such as memory elements, digital signal processing elements, logic elements, look-up tables, etc., which may perform a variety of functions under the control of one or more microprocessors or other control devices. In addition, those skilled in the art will appreciate that embodiments of the present invention may be practiced in conjunction with a variety of systems, and the system described herein is merely an exemplary embodiment of the present invention.

[0040] For the sake of brevity, technologies related to signal processing, data fusion, signaling, control and other functional aspects of the system (as well as the various operating components of the system) may not be described in detail herein. In addition, the connecting lines shown in the various figures contained herein are intended to represent example functional relationships and / or physical couplings between the various elements. It should be noted that alternative or additional functional relationships or physical connections may exist in embodiments of the present invention.

[0041] This description is merely illustrative in nature and is in no way intended to limit the invention, its application or use. The broad teachings of the invention can be implemented in many forms. Therefore, although the invention includes specific examples, the true scope of the invention should not be so limited, as other modifications will become apparent after studying the drawings, description and appended claims.

Claims

1. A method for selecting a network access device, comprising: receiving network data, wherein the network data comprises a list of available networks and network performance characteristics of each of the available networks, and the network performance characteristics comprises a network throughput provision and a network latency provision; Using machine learning, rule sets to predict quality of service (QoS) metrics for available networks along a vehicle’s journey; and selecting one or more networks from the list of available networks based on the predicted QoS indicators and QoS constraints of the available networks to determine a selected network list of one or more in-vehicle network devices from the list of available networks; and The one or more vehicle network devices are connected to the selected network.

2. The method according to claim 1, further comprising: The list of available networks is prioritized based on the QoS indicator, wherein the in-vehicle network device is one of a plurality of in-vehicle network devices, each of the plurality of in-vehicle network devices runs an application, each of the plurality of in-vehicle network devices has an independent throughput requirement and an independent delay requirement, and the method includes receiving network demand data, and the network demand data includes the number of the plurality of in-vehicle network devices, the independent throughput requirement for each of the plurality of in-vehicle network devices, and the independent delay requirement for each of the plurality of in-vehicle network devices.

3. The method according to claim 2, further comprising receiving a navigation route of the vehicle, wherein: The network performance characteristics of each of the available networks also include a supported bandwidth of each of the available networks.

4. The method according to claim 3, wherein: The plurality of in-vehicle network devices are associated with users, and the method further comprises detecting a number of the users, and receiving the network demand data comprises determining a network demand of each user throughout a journey of the vehicle.

5. The method according to claim 4 further includes receiving external factor data for each of a plurality of route segments of the navigation route of the entire trip, and the external factor data includes traffic volume for each of the plurality of route segments, vehicle location for each of the plurality of route segments, seasonality for each of the plurality of route segments, time of day for each of the plurality of route segments, and vehicle speed for each of the plurality of route segments, and the QoS indicator of the available network is predicted using the external factor data.

6. The method according to claim 5, wherein: QoS indicators of the available networks are predicted using the external factor data and the network performance characteristics of each of the available networks.

7. The method according to claim 6, wherein: The QoS indicators of the available networks are predicted using the external factor data, network performance characteristics of each of the available networks, and the number of users and associated preference rules.

8. The method according to claim 7, wherein: The traffic volume of each of the plurality of road segments is determined by crowdsourcing, and the machine learning is a recurrent neural network.

9. The method according to claim 7, wherein the machine learning includes a recurrent neural network and a fully connected deep neural network and a convolutional neural network, the machine learning can be supervised or unsupervised or reinforcement learning, and the deep neural network is used to predict and rank the QoS indicators of the available networks guided by the constraints of a rule set along the entire journey of the vehicle.

10. The method of claim 9, wherein the machine learning comprises a convolutional neural network, wherein: The convolutional neural network is used to determine traffic patterns using the vehicle's camera.

Images