Network optimization method, vehicle, storage medium, and computer program product

Abstract

The present application relates to the technical field of vehicles, and discloses a network optimization method, a vehicle, a storage medium, and a computer program product. The network optimization method of the present application is applied to a vehicle, wherein the vehicle comprises an on-board communication module and an on-board computing module. The method specifically comprises: monitoring a module state of the on-board computing module, wherein the module state is an in-use state or an idle state; when it is detected that the module state is the in-use state, reading an interaction log of the on-board computing module; and when it is determined, on the basis of the interaction log, that the on-board computing module is experiencing network latency, performing a network optimization operation according to a target network optimization policy, wherein the target network optimization policy is a first network optimization policy or a second network optimization policy. By using the present application, the technical effect of improving the operation efficiency of network optimization is achieved.

Description

Network optimization methods, vehicles, storage media, and computer program products

[0001] Related applications

[0002] This application claims priority to Chinese patent application No. 202510473294.8, filed on April 16, 2025, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the field of vehicle technology, and more particularly to a network optimization method, a vehicle, a storage medium, and a computer program product. Background Technology

[0004] With the continuous development of the automotive industry, vehicles have increasingly higher demands for the real-time performance and stability of network connectivity, especially for in-vehicle communication modules and in-vehicle computing modules, which heavily rely on a low-latency, reliable network environment. In related technologies, vehicles periodically upload network status parameters to the base station. The base station then filters all available base stations based on these parameters to determine the target base station / cell that best matches the vehicle's network status parameters. Finally, it issues a handover command to the target base station / cell to complete the vehicle's network optimization operation. Summary of the Invention

[0005] This application proposes a network optimization method applied to a vehicle, the vehicle including an on-board communication module and an on-board computing module, the network optimization method comprising:

[0006] The module status of the vehicle computing module is detected, wherein the module status is either in use or idle.

[0007] If the module status is detected to be in the usage state, the interaction log of the vehicle computing module is read.

[0008] If the interaction log determines that the vehicle computing module is experiencing network lag, a network optimization operation is performed according to the target network optimization strategy, wherein the target network optimization strategy is either a first network optimization strategy or a second network optimization strategy.

[0009] In one embodiment, after the step of reading the interaction log of the in-vehicle computing module, the method further includes:

[0010] The number of screen clicks and the screen click time contained in the interaction log are determined, and the user operation frequency is determined based on the number of screen clicks and the screen click time.

[0011] If the frequency of user operation is detected to reach a preset click frequency threshold, it is determined that the vehicle computing module has a network lag phenomenon, and the step of performing network optimization operation according to the target network optimization strategy is executed.

[0012] In one embodiment, the vehicle and a cloud server are communicatively connected. After the step of detecting the module status of the on-board computing module, the method further includes:

[0013] When the module is detected to be in the usage state, multiple first network state parameters corresponding to the vehicle computing module are determined.

[0014] Multiple first network state parameters are sent to the cloud server, and network environment detection results are received from the cloud server. The network environment detection results are generated by a lightweight time series prediction model deployed in the cloud server based on multiple first network state parameters.

[0015] Based on the network environment detection results, a target network optimization strategy is determined, and network optimization operations are performed according to the target network optimization strategy.

[0016] In one embodiment, the step of determining the target network optimization strategy based on the network environment detection results includes:

[0017] If the network environment detection result indicates that the vehicle computing module is in a weak network environment, the preset first network optimization strategy is determined as the target network optimization strategy, wherein the first network optimization strategy is a network optimization strategy for switching the communication cell corresponding to the vehicle.

[0018] If the network environment detection result indicates that the vehicle computing module is in a network change environment, the preset second network optimization strategy is determined as the target network optimization strategy, wherein the second network optimization strategy is a network optimization strategy that switches the network connection mode corresponding to the vehicle.

[0019] In one embodiment, the vehicle and the target mobile terminal are communicatively connected, and the step of performing network optimization operations according to the target network optimization strategy includes:

[0020] If the target network optimization strategy is detected to be the first network optimization strategy, the cell feature database sent by the target mobile terminal is received.

[0021] The target cell is determined by querying the cell feature database based on multiple first network state parameters, and the vehicle is connected to the target cell via the vehicle communication module.

[0022] In one embodiment, the step of performing network optimization operations according to the target network optimization strategy further includes:

[0023] If the target network optimization strategy is detected to be the second network optimization strategy, a preset target network connection type is determined;

[0024] The vehicle communication module switches the current network connection mode of the vehicle to the target network connection mode.

[0025] In one embodiment, after the step of detecting the module state of the on-board computing module, the method further includes:

[0026] When the module is detected to be in the idle state, multiple second network status parameters corresponding to the vehicle communication module are determined.

[0027] Determine a preset global network environment judgment rule, and determine the threshold values ​​of the state parameters corresponding to each of the multiple second network state parameters included in the global network environment judgment rule;

[0028] Multiple second network state parameters are compared with their respective state parameter thresholds to obtain multiple first comparison results, and a target network state parameter is determined based on the multiple first comparison results, wherein the target network state parameter is a second network state parameter that reaches the state parameter threshold.

[0029] If the number of the target network state parameters is detected to reach a first quantity threshold, the network environment corresponding to the vehicle communication module is determined to be a weak network environment.

[0030] The first network optimization strategy is determined as the target network optimization strategy, and network optimization operations are performed according to the target network optimization strategy.

[0031] In one embodiment, after the step of determining the target network state parameters based on a plurality of first comparison results, the method further includes:

[0032] If the number of the target network state parameters is detected to reach a second quantity threshold, the network environment corresponding to the vehicle communication module is determined to be a network change environment, wherein the second quantity threshold is greater than the first quantity threshold;

[0033] The second network optimization strategy is determined as the target network optimization strategy, and network optimization operations are performed according to the target network optimization strategy.

[0034] Furthermore, this application also proposes a vehicle comprising: an on-board communication module, an on-board computing module, a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the network optimization method described above.

[0035] Furthermore, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps of the network optimization method described above.

[0036] In addition, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the network optimization method described above.

[0037] The network optimization method provided in this application embodiment is applied to a vehicle, which includes an in-vehicle communication module and an in-vehicle computing module. The method detects the module status of the in-vehicle computing module, wherein the module status is either in use or idle. If the module status is detected as being in use, the interaction log of the in-vehicle computing module is read. If the interaction log determines that the in-vehicle computing module is experiencing network lag, a network optimization operation is performed according to a target network optimization strategy, wherein the target network optimization strategy is either a first network optimization strategy or a second network optimization strategy.

[0038] In this embodiment, during vehicle operation, the vehicle first detects its own onboard computing module to determine whether the module is in use or idle. Then, if the vehicle detects that the onboard computing module is in use, it further reads the interaction log contained in the onboard computing module. Finally, the vehicle identifies whether there is network lag in the onboard computing module based on the interaction log. If network lag is detected, the vehicle determines a preset first network optimization strategy or a second network optimization strategy as the target network execution strategy and actively performs network optimization operations based on the target network execution strategy to change the connected base station or network connection mode.

[0039] Thus, this application solves the technical problem of low network optimization operation efficiency in related technologies. Specifically, this application determines whether there is network lag in the vehicle computing module based on the interaction log of the vehicle computing module when the vehicle computing module is detected to be in use. If network lag is detected, the application actively performs network optimization operation according to the target network optimization strategy. This enables the vehicle to actively initiate network optimization requests to the base station, so that the base station does not need to further select a suitable target base station / target cell after collecting network status parameters, thereby reducing the latency in the network optimization operation process and greatly improving the efficiency of the network optimization operation. Attached Figure Description

[0040] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0041] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 is a schematic diagram of an existing network optimization operation scenario involving an embodiment of the network optimization method of this application;

[0043] Figure 2 is a flowchart of the network optimization method provided in Embodiment 1 of this application;

[0044] Figure 3 is a schematic diagram of a multi-terminal interaction scenario involved in an embodiment of the network optimization method of this application;

[0045] Figure 4 is a schematic diagram of the module structure of the network optimization device according to an embodiment of this application;

[0046] Figure 5 is a schematic diagram of the device structure of the hardware operating environment involved in the network optimization method in this application embodiment.

[0047] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0048] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0049] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0050] In this embodiment, for ease of description, the following description will focus on vehicles equipped with in-vehicle computing modules and in-vehicle communication modules, or mobile terminals, data storage control terminals, PCs, and other terminals connected to the vehicle's electronic control unit.

[0051] The in-vehicle computing module is a device with strong computing power installed in the vehicle, specifically a hardware device such as a smart cockpit controller or intelligent driving controller. In addition, the in-vehicle communication device is a communication device with weaker computing power installed in the vehicle, capable of switching network connection standards and base stations.

[0052] Based on the aforementioned vehicles, the overall concept of the network optimization method of this application is proposed.

[0053] With the continuous development of the automotive industry, vehicles have increasingly higher demands for the real-time performance and stability of network connectivity, especially for in-vehicle communication modules and in-vehicle computing modules, which heavily rely on a low-latency, reliable network environment. Referring to Figure 1, which illustrates an embodiment of the network optimization method of this application, the vehicle periodically uploads network status parameters to the base station. The base station then filters all available base stations based on these parameters to determine the target base station / cell that best matches the vehicle's network status parameters. Finally, it issues a handover command to the target base station / cell to complete the vehicle's network optimization operation. However, base stations typically need to process massive amounts of network status data uploaded by vehicles, resulting in significant time delays in the process from collecting network status parameters to specifying a handover strategy, thus greatly reducing the efficiency of network optimization operations.

[0054] To address the above issues, this application provides a network optimization method applied to a vehicle. The vehicle includes an in-vehicle communication module and an in-vehicle computing module. The network optimization method includes: detecting the module status of the in-vehicle computing module, wherein the module status is either in use or idle; when the module status is detected to be in use, reading the interaction log of the in-vehicle computing module; and when it is determined from the interaction log that the in-vehicle computing module is experiencing network lag, performing network optimization operations according to a target network optimization strategy, wherein the target network optimization strategy is either a first network optimization strategy or a second network optimization strategy.

[0055] Thus, this application solves the technical problem of low network optimization operation efficiency in related technologies. Specifically, this application determines whether there is network lag in the vehicle computing module based on the interaction log of the vehicle computing module when the vehicle computing module is detected to be in use. If network lag is detected, the application actively performs network optimization operation according to the target network optimization strategy. This enables the vehicle to actively initiate network optimization requests to the base station, so that the base station does not need to further select a suitable target base station / target cell after collecting network status parameters, thereby reducing the latency in the network optimization operation process and greatly improving the efficiency of the network optimization operation.

[0056] Based on the overall concept of the network optimization method of this application, this application provides a network optimization method. Referring to Figure 2, which is a flowchart of the first embodiment of the network optimization method of this application, in this embodiment, the network optimization method is applied to a vehicle, the vehicle including an on-board communication module and an on-board computing module, and the network optimization method includes steps S10 to S30:

[0057] Step S10: Detect the module status of the vehicle computing module, wherein the module status is either in use or idle.

[0058] This module status indicates the network resource occupancy status of the in-vehicle computing module, including: in use or idle. When the in-vehicle computing module is in use, it means that the user has launched network-related applications (such as music apps, navigation apps, etc.) through the in-vehicle computing module, and the network-related applications are occupying network resources. Similarly, when the in-vehicle computing module is in idle, it means that all network-related applications are not running, or the running network-related applications are not actively occupying network resources (such as an app that is performing a local update in the background).

[0059] In this embodiment, during vehicle operation, the vehicle-mounted control system integrated within the vehicle first accesses the system process management interface of the vehicle-mounted computing module configured in the vehicle to obtain the application running list of the vehicle-mounted computing module through the system process management interface. Based on the application running list, it determines the network occupancy parameters corresponding to each of the currently running network-related applications. Then, based on the obtained application running list and each network occupancy parameter, when it detects that the network occupancy parameter of at least one network-related application has reached a preset occupancy parameter threshold, it determines that the module status of the vehicle-mounted computing module is in use. Similarly, when it detects that all network-related applications are in a closed state or that the network occupancy parameters of all network-related applications have not reached the occupancy parameter threshold, it determines that the module status is in idle state.

[0060] For example, while the vehicle is in motion, if a user launches a music app through the smart cockpit controller configured in the smart cockpit and controls the music app to play online music in real time, the vehicle control system integrated in the vehicle accesses the system process management interface in the smart cockpit controller to obtain a list of launched apps. Based on the list of launched apps, the system control system determines that the launched app is the music app. At the same time, the system control system determines the network usage parameters corresponding to the music app based on the list of launched apps. If the system control system detects that the network usage parameters have reached a preset threshold, it determines that the music app is in an active state. At this time, the system control system determines that the module status of the smart cockpit controller is in a usage state.

[0061] Similarly, in this embodiment and another embodiment, if the vehicle control system reads the list of launched apps and determines that none of the system apps are running, it directly determines that the module status of the cockpit controller is idle; or, if the vehicle control system reads the list of launched apps and determines that the music app is running, but the network usage parameter of the music app has not reached the above-mentioned usage parameter threshold, the vehicle control system determines that the music app is inactive and determines that the module status of the cockpit controller is idle.

[0062] Step S20: If the module status is detected as being in use, read the interaction log of the vehicle computing module;

[0063] This interaction log contains various operational behaviors generated when users control the in-vehicle computing module through the human-machine interface. It can be understood that these operational behaviors include direct interactive behaviors such as touch clicks, voice commands, and gesture operations, as well as indirect interactive behaviors such as sound quality adjustment, playback rate switching, and application window scaling.

[0064] In this embodiment, when the vehicle control system detects that the vehicle computing module is in use, it further accesses the vehicle computing module to obtain the interaction log and reads the direct and / or indirect interaction behaviors contained in the interaction log, thereby determining whether there is a network lag phenomenon in the vehicle computing module during use based on the direct and / or indirect interaction behaviors.

[0065] For example, if the vehicle management system determines that the module status of the intelligent cockpit controller is in use, it will further access the intelligent cockpit controller to obtain the interaction log stored in the intelligent cockpit controller. The vehicle management system reads the touch click events contained in the interaction log and determines the number of clicks and the click time when the user performs interactive operations through the HMI (Human-Machine Interface) based on the touch click events. Then, based on the number of clicks and the click time, it can identify that the user is continuously clicking pause in the music APP, and determine that there is a network lag phenomenon in the intelligent cockpit controller.

[0066] In this embodiment and another embodiment, after obtaining the interaction log, the vehicle management system can also read the sound quality adjustment event contained in the interaction log, and when it is determined that the user has performed a sound quality downgrade operation in the music APP based on the sound quality adjustment event, it can directly determine that there is a network lag phenomenon in the smart cockpit controller.

[0067] In this embodiment and another embodiment, if the vehicle management system determines, after obtaining the interaction log, that the user has not continuously clicked pause or performed sound quality degradation operations in the music APP, then it can be determined that there is no network lag in the smart cockpit controller.

[0068] In this way, the vehicle can recognize the interactive behavior triggered by the user on the in-vehicle computing module, and identify whether there is network lag in the in-vehicle computing module based on the interactive behavior.

[0069] In one embodiment, after step S20 described above, the network optimization method of this application may further include steps S201 to S202:

[0070] Step S201: Determine the number of screen clicks and the screen click time contained in the interaction log, and determine the user operation frequency based on the number of screen clicks and the screen click time;

[0071] Step S202: If the frequency of user operation is detected to reach a preset click frequency threshold, it is determined that the vehicle computing module has a network lag phenomenon, and the step of performing network optimization operation according to the target network optimization strategy is executed.

[0072] In this embodiment, after acquiring the interaction log, the vehicle control system reads the number of screen clicks and the screen click time contained in the interaction log, and determines the frequency of user operations on the vehicle computing module within a certain period of time based on the number of screen clicks and the screen click time. Then, the vehicle control system acquires a preset click frequency threshold and compares the user operation frequency with the click frequency threshold. If the vehicle control system detects that the user operation frequency has reached the click frequency threshold, it determines that there is a network lag phenomenon in the vehicle computing module.

[0073] For example, after acquiring the interaction log, the vehicle control system reads the interaction log to determine the number of times the user performs screen click operations on the HMI when controlling the smart cockpit controller through the HMI. Based on the interaction log, it determines the operation time corresponding to each click operation on the HMI. The vehicle control system then calculates the user operation frequency of the HMI within a certain time period based on the number of clicks and the click time. Afterward, the vehicle control system acquires a preset click frequency threshold and compares the user operation frequency with the click frequency threshold. If the vehicle control system detects that the user operation frequency has reached the click frequency threshold, it determines that the smart cockpit controller is unable to respond to the user's click operations. At this point, the vehicle control system determines that the smart cockpit controller is experiencing network lag.

[0074] In this embodiment and another embodiment, after obtaining the interaction log, the vehicle management system can also read the sound quality adjustment event contained in the interaction log, and when it is determined from the sound quality adjustment event that the user performs a sound quality downgrade operation in the music APP, it can directly determine that there is a network lag phenomenon in the smart cockpit controller.

[0075] In this way, the vehicle can recognize the interactive behavior triggered by the user on the in-vehicle computing module, and identify whether there is network lag in the in-vehicle computing module based on the interactive behavior.

[0076] Step S30: If it is determined from the interaction log that there is a network lag in the vehicle computing module, perform network optimization operation according to the target network optimization strategy, wherein the target network optimization strategy is either the first network optimization strategy or the second network optimization strategy.

[0077] The target network optimization strategy is a network adjustment scheme dynamically selected based on the current network environment, including a first network optimization strategy or a second network optimization strategy. The first network optimization strategy is a network optimization strategy that switches the communication cell corresponding to the vehicle, and the second network optimization strategy is a network optimization strategy that adjusts the network connection mode corresponding to the vehicle.

[0078] In this embodiment, when the vehicle management system determines that there is a network lag in the vehicle computing module based on the interaction log, it determines a preset first network optimization strategy or a second network optimization strategy as the target network optimization strategy, and performs operations such as switching cells / adjusting network connection standards according to the target network optimization strategy to complete the network optimization operation.

[0079] For example, if the vehicle management system determines, based on the aforementioned interaction logs, that a music app running within the smart cockpit controller is experiencing network lag, it first determines the target network optimization strategy for improving the network environment of the smart cockpit controller as a preset first network optimization strategy or a second network optimization strategy. The vehicle management system then controls the vehicle communication device according to the target network optimization strategy, causing the vehicle communication device to perform operations such as switching cells or switching the network connection mode from 5G mode to 4G mode, thereby optimizing the network environment of the smart cockpit controller.

[0080] In this embodiment and another embodiment, before controlling the vehicle communication equipment to perform operations such as cell handover / network connection mode switching from 5G mode to 4G mode, the vehicle management system can first determine the application priority of each running APP, and determine the non-critical APPs running according to the application priority. Then, it compresses the bandwidth corresponding to each non-critical APP according to a preset compression ratio. After that, the vehicle management system re-detects whether there is any lag in the vehicle computing module. If it is determined that there is still lag in the vehicle computing module, it performs operations such as cell handover / network connection mode switching from 5G mode to 4G mode according to the target network optimization strategy. It is understood that in addition to compressing the bandwidth of non-critical APPs, the vehicle management system can also perform other parameter adjustment operations such as adjusting real-time traffic and optimizing TCP operations. This application does not limit the specific content of the parameter adjustment operations.

[0081] In this way, vehicles can proactively initiate network optimization requests to base stations, eliminating the need for base stations to further screen suitable target cells after collecting network status parameters. This reduces latency during network optimization operations and greatly improves the efficiency of network optimization.

[0082] In one embodiment, the vehicle and the target mobile terminal are communicatively connected, and the step of "performing network optimization operation according to the target network optimization strategy" in step S30 above may specifically include steps S301 to S302:

[0083] Step S301: If the target network optimization strategy is detected to be the first network optimization strategy, receive the cell feature database sent by the target mobile terminal;

[0084] Step S302: Query the cell feature database based on multiple first network status parameters to determine the target cell, and connect the vehicle to the target cell through the vehicle communication module.

[0085] The cell feature database is a dynamic dataset generated by unsupervised contrastive learning of the target mobile terminal that communicates with the vehicle. The cell feature database contains multi-dimensional vector features (such as signal strength, load rate, geographical location, historical performance, etc.) of multiple cells contained by multiple base stations. It is understood that the feature types and number of features contained in the cell feature database can be set by the technicians according to actual needs, and this application does not impose any restrictions on this.

[0086] In this embodiment, when the vehicle control system determines that the vehicle computing module is experiencing network lag, if the target network optimization strategy to be executed is the aforementioned first network optimization strategy, it first receives the cell feature database sent by the target mobile terminal with which it is communicating. Then, the vehicle control system detects the vehicle computing module to obtain multiple first network status parameters corresponding to the vehicle computing module, and filters each preset cell contained in the cell feature database according to the multiple first network status parameters to determine the cells to be screened that meet the multiple first network status parameters. Based on the stability score of each cell to be screened in the cell feature database, the system determines the target cell that best matches the vehicle computing module. The vehicle control system sends the target cell to the vehicle communication module, and the vehicle communication module sends a handover request to the target cell to switch the vehicle's current connection to the target cell.

[0087] For example, please refer to Figure 3, which is a schematic diagram of a multi-terminal interaction scenario involving an embodiment of the network optimization method of this application. As shown in Figure 3, when the vehicle control system determines that there is a network lag in the intelligent cockpit controller, if it determines that the target network optimization strategy to be executed is the first network optimization strategy mentioned above, it first receives the cell feature database sent by the target mobile terminal communicating with the vehicle. Then, the vehicle control system detects the intelligent cockpit controller to determine the RSSI (Received Signal Strength Index) contained in the intelligent cockpit controller. The vehicle control system uses multiple first network status parameters, such as signal strength (RSSI) and latency, to query the cell feature database. Based on these parameters, it identifies cells with signal strength greater than RSSI and load rate less than a certain threshold. The system then prioritizes these cells according to their stability scores, geographical location, and other factors to determine the highest-priority target cell. Finally, the system sends the target cell to the vehicle communication module Tx, which in turn sends a handover request carrying vehicle identification information to the target cell to switch connections.

[0088] In this way, vehicles can proactively initiate network optimization requests to base stations, eliminating the need for base stations to further screen suitable target cells after collecting network status parameters. This reduces latency during network optimization operations and greatly improves the efficiency of network optimization.

[0089] In one embodiment, the vehicle and the target mobile terminal are communicatively connected, and the step of "performing network optimization operation according to the target network optimization strategy" in step S30 may further include steps S303 to S304:

[0090] Step S303: If the target network optimization strategy is detected to be the second network optimization strategy, a preset target network connection mode is determined; Step S304: The vehicle communication module switches the current network connection mode corresponding to the vehicle to the target network connection mode.

[0091] In this embodiment, when the vehicle control system determines that there is a network lag in the vehicle computing module, if the target network optimization strategy to be executed is the second network optimization strategy mentioned above, the vehicle control system first determines the target network connection mode to be switched. Then, the vehicle control system sends the target network connection mode to the vehicle communication module, and the vehicle communication module switches the vehicle's current network connection mode to the target network connection mode.

[0092] For example, if the vehicle control system determines that there is a network lag in the intelligent cockpit controller, and determines that the target network optimization strategy to be executed is the second network optimization strategy mentioned above, then it first determines the 4G low-frequency band standard as the target network connection standard based on the first network status parameters such as RSSI and latency. Then, the vehicle control system sends the target network connection standard to the vehicle communication module Tx, and the vehicle communication module Tx sends a standard switching request to the base station, thereby turning off the 5G radio frequency module configured in the vehicle, activating the 4G module and connecting it to the specified frequency band, so that the vehicle's connection standard is switched from 5G mode to 4G low-frequency band standard.

[0093] In this embodiment, during vehicle operation, the integrated vehicle control system first accesses the system process management interface of the vehicle's onboard computing module to obtain the application running list of the onboard computing module. Based on the application running list, it determines the network usage parameters corresponding to each running network-related application. Then, based on the obtained application running list and network usage parameters, when it detects that the network usage parameter of at least one network-related application reaches a preset usage parameter threshold, it determines the module status of the onboard computing module as "in use." Similarly, when it detects that all network-related applications are in a closed state / all network-related applications are in a closed state, the system determines the module status as "in use." If none of the program's network usage parameters reach the threshold, the module is determined to be in an idle state. Then, the vehicle control system accesses the vehicle computing module to obtain the interaction logs and reads the direct and / or indirect interaction behaviors contained in the logs. Based on these direct and / or indirect interaction behaviors, the system determines whether the vehicle computing module experiences network lag during use. Finally, if the vehicle management system determines from the interaction logs that the vehicle computing module is experiencing network lag, it determines either a preset first or second network optimization strategy as the target network optimization strategy and performs operations such as cell switching / network connection type adjustment according to the target network optimization strategy to complete the network optimization operation.

[0094] Thus, this application solves the technical problem of low network optimization operation efficiency in related technologies. Specifically, this application determines whether there is network lag in the vehicle computing module based on the interaction log of the vehicle computing module when the vehicle computing module is detected to be in use. If network lag is detected, the application actively performs network optimization operation according to the target network optimization strategy. This enables the vehicle to actively initiate network optimization requests to the base station, so that the base station does not need to further select a suitable target base station / target cell after collecting network status parameters, thereby reducing the latency in the network optimization operation process and greatly improving the efficiency of the network optimization operation.

[0095] Based on the first embodiment of this application, a second embodiment of this application is proposed herein. In this second embodiment, content that is the same as or similar to the above embodiments can be referred to the above description and will not be repeated hereafter. Based on this, the communication connection between the vehicle and the cloud server, after step S10 above, the network optimization method of this application may further include steps A10 to A30:

[0096] Step A10: When the module status is detected to be the usage status, determine multiple first network status parameters corresponding to the vehicle computing module;

[0097] Step A20: Send multiple first network state parameters to the cloud server and receive network environment detection results from the cloud server, wherein the network environment detection results are generated by a lightweight time series prediction model deployed in the cloud server based on multiple first network state parameters;

[0098] Step A30: Determine the target network optimization strategy based on the network environment detection results, and perform network optimization operations according to the target network optimization strategy.

[0099] In this embodiment, when the vehicle control system detects that the vehicle computing module is in use, it further collects multiple first network state parameters generated by the vehicle computing module. Then, the vehicle control system uploads these first network state parameters to a cloud server connected to the vehicle. The cloud server generates input features based on these first network state parameters and inputs these features into a lightweight time-series prediction model configured within the cloud server. The lightweight time-series prediction model generates hidden states corresponding to the input features. The cloud server then determines the network environment of the intelligent cockpit controller based on the hidden states output by the lightweight time-series prediction model and generates a network environment detection result based on this network environment. The cloud server sends the network environment detection result to the vehicle management system. Finally, the vehicle control system reads the network environment detection result to determine the target network optimization strategy as either the first network optimization strategy or the second network optimization strategy. Then, it controls the vehicle communication module according to the target network optimization strategy to perform network optimization operations.

[0100] For example, as shown in Figure 3, when the vehicle control system detects that the above-mentioned vehicle computing module is in use, it detects the intelligent cockpit controller to obtain multiple first network state parameters such as RSSI, latency, packet loss rate, satellite signal strength, and throughput generated by the intelligent cockpit controller. Then, the vehicle control system accesses the cloud server connected to the vehicle communication and uploads the multiple first network state parameters to the cloud server. At this time, the cloud server generates an input feature x containing multiple first network state parameters based on RSSI, latency, packet loss rate, satellite signal strength, and throughput. t The cloud server then processes the input feature x t Input to its own configured lightweight LSTM time series prediction model:

[0101] h t =σ(W xh x t +W hh h t-1 +b h ), where W xh The input weight matrix is ​​used to map the input features to the hidden space d. x ×d h Below, d x =5(RSSI, throughput, latency, packet loss rate, satellite signal strength), d h The value is set according to memory limits (typically 64 or 256), W hh This is a cyclic weight matrix used to model the temporal state transition relationship d. h ×d h To prevent gradient explosion, h t-1 The hidden state output from the previous time step is used to preserve historical network feature memory to initialize the all-zero vector, b. h The bias term is used to improve the model's expressive power, and σ is the activation function, specifically the Hard Sigmoid function. It can be understood that the Hard Sigmoid function has the characteristic of lower computational cost compared to the traditional Sigmoid function.

[0102] LSTM time series prediction model thus uses the input weight matrix W xh For input feature x t Process to output the corresponding hidden state h t The cloud server then reads the hidden state h. tThe system includes network state timing characteristics. Based on these characteristics, it determines that the intelligent cockpit controller is in a weak network environment. It then generates corresponding network environment detection results. The cloud server then sends the network environment detection results to the vehicle control system. Finally, when the vehicle controller system determines that the intelligent cockpit controller is in a weak network environment based on the network environment detection results, it determines the first network optimization strategy mentioned above as the target network optimization strategy and controls the vehicle communication device Tx to perform cell handover operation according to the first network optimization strategy.

[0103] If the cloud server determines that the intelligent cockpit controller is in a changing network environment (e.g., changing from a normal network environment to a parking garage network environment) based on the timing characteristics of the network status, it generates a corresponding network environment detection result. The cloud server then sends the network environment detection result to the vehicle control system. Finally, when the vehicle controller system determines that the intelligent cockpit controller is in a changing network environment based on the network environment detection result, it determines the above-mentioned second network optimization strategy as the target network optimization strategy and controls the vehicle communication device Tx to perform a connection mode switching operation according to the first network optimization strategy.

[0104] The lightweight LSTM time series prediction model fuses the current input features (such as RSSI and time delay) with historical hidden features through cyclic weight matrices, thereby forming a dynamic model of the network state, and allowing the output hidden state h to be determined. t It includes abrupt change patterns in network parameters (such as a sudden drop in RSSI in the underground parking scenario) and periodic fluctuations (such as a periodic increase in packet loss rate in the weak network scenario), thereby accurately identifying whether the network environment in which the vehicle is located is a weak network environment or a network change environment. It can be understood that there are many ways to train a lightweight LSTM time series prediction model, and this application does not limit this.

[0105] In this way, the vehicle can upload the collected network status data to the cloud server, which then processes the network status parameters using a lightweight time-series prediction model to determine the network environment in which the vehicle is located. The vehicle can then select network optimization strategies that match the network environment, further improving the efficiency of network optimization operations.

[0106] In one embodiment, the step of "determining the target network optimization strategy based on the network environment detection results" in step A30 above may specifically include steps A301 to A302:

[0107] Step A301: When the network environment detection result indicates that the vehicle computing module is in a weak network environment, the preset first network optimization strategy is determined as the target network optimization strategy, wherein the first network optimization strategy is the network optimization strategy of switching the communication cell corresponding to the vehicle.

[0108] Step A302: When the network environment detection result indicates that the vehicle computing module is in a network change environment, the preset second network optimization strategy is determined as the target network optimization strategy, wherein the second network optimization strategy is a network optimization strategy that switches the network connection mode corresponding to the vehicle.

[0109] In this embodiment, after receiving the network environment detection result from the cloud server, if the vehicle control system determines that the vehicle computing module is in a weak network environment based on the network environment detection result, then the first network optimization strategy mentioned above is determined as the target network optimization strategy to be executed. Similarly, if the vehicle control system determines that the vehicle computing module is in a network change environment based on the network environment detection result, then the second network optimization strategy mentioned above for controlling the vehicle communication module to switch network connection modes is determined as the target network optimization strategy.

[0110] For example, when the cloud server determines that the intelligent cockpit controller is in a weak network environment, it generates a corresponding network environment detection result. The cloud server then sends the network environment detection result to the vehicle control system. At this time, the vehicle control system receives the network environment detection result and reads the network environment contained in the network environment detection result. The vehicle control system determines that the network environment is a weak network environment and determines the preset first network optimization strategy for controlling the vehicle communication device Tx to switch communication cells as the target network optimization strategy.

[0111] When the cloud server determines that the intelligent cockpit controller is in a network change environment, it generates a corresponding network environment detection result. The cloud server then sends the network environment detection result to the vehicle control system. At this time, the vehicle control system receives the network environment detection result and reads the network environment contained in the network environment detection result. If the vehicle control system determines that the network environment is a network change environment, it determines the preset second network optimization strategy used to control the switching of communication mode of the vehicle communication device Tx as the target network optimization strategy.

[0112] In this way, vehicles can select network optimization strategies that match the network environment, further improving the efficiency of network optimization operations.

[0113] Based on the first and / or second embodiments of this application, a third embodiment of this application is proposed herein. In this third embodiment, content that is the same as or similar to the above embodiments can be referred to the above description and will not be repeated hereafter. Furthermore, after step S10 above, the network optimization method of this application may further include steps B10 to B50:

[0114] Step B10: If the module status is detected to be the idle state, determine multiple second network status parameters corresponding to the vehicle communication module;

[0115] Step B20: Determine the preset global network environment judgment rule, and determine the state parameter threshold corresponding to each of the multiple second network state parameters included in the global network environment judgment rule;

[0116] Step B30: Compare multiple second network state parameters with their respective corresponding state parameter thresholds to obtain multiple first comparison results, and determine the target network state parameter based on the multiple first comparison results, wherein the target network state parameter is a second network state parameter that has reached the state parameter threshold; Step B40: If the number of the target network state parameters is detected to reach a first quantity threshold, determine that the network environment corresponding to the vehicle communication module is a weak network environment;

[0117] Step B50: Determine the first network optimization strategy as the target network optimization strategy, and perform network optimization operations according to the target network optimization strategy.

[0118] This global network judgment rule is a dynamic threshold setting rule generated by the cloud server based on massive amounts of data. It is used to dynamically adjust the parameter judgment criteria according to different scenarios (such as cities, suburbs, and underground parking lots). In addition, the first quantity threshold is the minimum number of parameters exceeding the standard to trigger the weak network environment judgment (for example, if ≥3 parameters exceed the threshold, it is determined that the vehicle communication module is in a weak network environment), which is used to comprehensively evaluate the network environment.

[0119] In this embodiment, when the vehicle control system detects that the vehicle computing module is in an idle state, it further collects multiple second network status parameters generated by the vehicle communication module. Then, the vehicle control system obtains a preset global network judgment rule and reads the status parameter thresholds corresponding to the multiple second network status parameters contained in the global network judgment rule. Next, the vehicle control system compares the multiple second network status parameters with their respective status parameter thresholds to obtain multiple first comparison results. Based on the multiple first comparison results, it filters the target second network status parameters that reach the status parameter thresholds. Then, the vehicle control system reads the global network environment judgment rule to obtain a first quantity threshold. When it detects that the number of target second network status parameters reaches the first quantity threshold, it determines that the network environment where the vehicle communication module is located is a weak network environment. Finally, the vehicle control system determines the above-mentioned first network optimization strategy as the target network optimization strategy to be executed and controls the vehicle communication device Tx to perform a cell handover operation according to the first network optimization strategy.

[0120] For example, when the vehicle control system detects that the vehicle computing module is in an idle state, it detects the vehicle communication device Tx to obtain multiple second network status parameters such as RSSI, latency, and packet loss rate generated by the vehicle communication device Tx. Then, the vehicle control system obtains the global network environment judgment rules issued by the cloud server and reads the global network environment judgment rules to determine the network status parameter thresholds corresponding to each of the multiple second network status parameters. Then, the vehicle control system compares the multiple second network status parameters with their respective network status parameter thresholds to obtain multiple first comparison results, and determines the target second network status parameters that reach the network status parameter thresholds based on the multiple first comparison results. Then, the vehicle control system determines the first quantity threshold through the global network environment judgment rules, and when the number of target second network status parameters reaches the first quantity threshold (e.g., 3 sets), it determines that the vehicle communication device Tx is in a weak network environment. Finally, the vehicle control system determines the above-mentioned first network optimization strategy as the target network optimization strategy, and controls the vehicle communication device Tx to perform cell handover operation according to the first network optimization strategy.

[0121] The deep residual network configured within the cloud server can be trained based on massive amounts of network state parameters and network environment data uploaded from vehicles to obtain initial network environment judgment rules. The cloud server then uses knowledge distillation technology to process these initial rules to generate lightweight global network environment judgment rules, which are then distributed to the vehicles. Understandably, the global network environment judgment rules generated through knowledge distillation are relatively small in size, thus ensuring that the distribution of these rules does not place significant pressure on bandwidth, further improving the efficiency of network optimization operations.

[0122] In this way, the vehicle can more accurately determine the network environment it is in based on the collected network status data, thereby selecting a network optimization strategy that matches the network environment and further improving the efficiency of network optimization operations.

[0123] Based on the embodiments of this application, a fourth embodiment of this application is proposed herein. In this fourth embodiment, content that is the same as or similar to the embodiments described above can be referred to the above description and will not be repeated hereafter. Furthermore, after step B30 above, the network optimization method of this application may further include steps B60 to B70:

[0124] Step B60: When the number of the target network state parameters is detected to reach the second quantity threshold, the network environment corresponding to the vehicle communication module is determined to be a network change environment, wherein the second quantity threshold is greater than the first quantity threshold;

[0125] Step B70: Determine the second network optimization strategy as the target network optimization strategy, and perform network optimization operations according to the target network optimization strategy.

[0126] The second quantity threshold is the minimum number of parameters exceeding the standard required to determine the network change environment. Its value is greater than the first quantity threshold mentioned above (for example, if ≥4 parameters exceed the threshold, it is determined that the vehicle communication module is in a network change environment).

[0127] In this embodiment, after filtering out the target second network state parameters, the vehicle control system further reads the global network judgment rules to determine a second quantity threshold that is greater than the first quantity threshold. When the vehicle control system detects that the number of target second network state parameters has reached the second quantity threshold, it determines that the network environment in which the vehicle communication module is located is a network change environment. Finally, the vehicle control system determines the second network optimization strategy as the target network optimization strategy to be executed, and controls the vehicle communication device Tx to perform a connection mode switching operation according to the second network optimization strategy.

[0128] For example, after the vehicle control system filters out the target second network state parameters, it further reads the global network judgment rules to determine a second quantity threshold (e.g., 4 sets) that is greater than the first quantity threshold. When the vehicle control system detects that the number of target second network state parameters has reached the second quantity threshold, it determines that the network environment in which the vehicle communication device Tx is located is a network change environment (e.g., the vehicle enters the underground parking garage from a normal driving scenario). Finally, the vehicle control system determines the second network optimization strategy as the target network optimization strategy and controls the vehicle communication device Tx to send a mode switching request to the base station according to the second network optimization strategy, thereby turning off the 5G radio frequency module configured in the vehicle, activating the 4G module and connecting to the specified frequency band, so that the vehicle's connection mode is switched from 5G mode to 4G low frequency band mode.

[0129] In this way, the vehicle can more accurately determine the network environment it is in based on the collected network status data, thereby selecting a network optimization strategy that matches the network environment and further improving the efficiency of network optimization operations.

[0130] This application also provides a network optimization device, as shown in Figure 4. The network optimization device is applied to a vehicle, which includes an in-vehicle communication module and an in-vehicle computing module. The device includes:

[0131] User behavior detection module 10: detects the module status of the vehicle computing module, wherein the module status is either in use or idle.

[0132] Lag detection module 20: When the module is detected to be in the usage state, it reads the interaction log of the vehicle computing module;

[0133] Network optimization execution module 30: If it is determined from the interaction log that there is a network lag in the vehicle computing module, a network optimization operation is performed according to the target network optimization strategy, wherein the target network optimization strategy is a first network optimization strategy or a second network optimization strategy.

[0134] In one embodiment, the above-mentioned stuttering detection module 20 is further used for:

[0135] The number of screen clicks and the screen click time contained in the interaction log are determined, and the user operation frequency is determined based on the number of screen clicks and the screen click time.

[0136] If the frequency of user operation is detected to reach a preset click frequency threshold, it is determined that the vehicle computing module has a network lag phenomenon, and the step of performing network optimization operation according to the target network optimization strategy is executed.

[0137] In one embodiment, the vehicle and the cloud server are communicatively connected, and the aforementioned lag detection module 20 is further used for:

[0138] When the module is detected to be in the usage state, multiple first network state parameters corresponding to the vehicle computing module are determined.

[0139] Multiple first network state parameters are sent to the cloud server, and network environment detection results are received from the cloud server. The network environment detection results are generated by a lightweight time series prediction model deployed in the cloud server based on multiple first network state parameters.

[0140] Based on the network environment detection results, a target network optimization strategy is determined, and network optimization operations are performed according to the target network optimization strategy.

[0141] In one embodiment, the above-mentioned stuttering detection module 20 is further used for:

[0142] If the network environment detection result indicates that the vehicle computing module is in a weak network environment, the preset first network optimization strategy is determined as the target network optimization strategy, wherein the first network optimization strategy is a network optimization strategy for switching the communication cell corresponding to the vehicle.

[0143] If the network environment detection result indicates that the vehicle computing module is in a network change environment, the preset second network optimization strategy is determined as the target network optimization strategy, wherein the second network optimization strategy is a network optimization strategy that switches the network connection mode corresponding to the vehicle.

[0144] In one embodiment, the vehicle and the target mobile terminal are communicatively connected, and the network optimization execution module 30 is further configured to:

[0145] If the target network optimization strategy is detected to be the first network optimization strategy, the system receives the cell feature database sent by the target mobile terminal; queries the cell feature database based on multiple first network status parameters to determine the target cell; and connects the vehicle to the target cell through the vehicle communication module.

[0146] In one embodiment, the network optimization execution module 30 is further configured to:

[0147] If the target network optimization strategy is detected to be the second network optimization strategy, a preset target network connection type is determined;

[0148] The vehicle communication module switches the current network connection mode of the vehicle to the target network connection mode.

[0149] In one embodiment, the above-mentioned stuttering detection module 20 is further used for:

[0150] When the module is detected to be in the idle state, multiple second network status parameters corresponding to the vehicle communication module are determined.

[0151] Determine a preset global network environment judgment rule, and determine the threshold values ​​of the state parameters corresponding to each of the multiple second network state parameters included in the global network environment judgment rule;

[0152] Multiple second network state parameters are compared with their respective state parameter thresholds to obtain multiple first comparison results, and a target network state parameter is determined based on the multiple first comparison results, wherein the target network state parameter is a second network state parameter that reaches the state parameter threshold.

[0153] If the number of the target network state parameters is detected to reach a first quantity threshold, the network environment corresponding to the vehicle communication module is determined to be a weak network environment.

[0154] The first network optimization strategy is determined as the target network optimization strategy, and network optimization operations are performed according to the target network optimization strategy.

[0155] In one embodiment, the above-mentioned stuttering detection module 20 is further used for:

[0156] If the number of the target network state parameters is detected to reach a second quantity threshold, the network environment corresponding to the vehicle communication module is determined to be a network change environment, wherein the second quantity threshold is greater than the first quantity threshold;

[0157] The second network optimization strategy is determined as the target network optimization strategy, and network optimization operations are performed according to the target network optimization strategy.

[0158] The network optimization apparatus provided in this application, employing the network optimization method described in the above embodiments, can solve the technical problem of low efficiency in network optimization operations in related technologies. Compared with the prior art, the beneficial effects of the network optimization apparatus provided in this application are the same as those of the network optimization method described in the above embodiments, and other technical features in the network optimization apparatus are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0159] This application provides a vehicle, the vehicle including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the network optimization method in Embodiment 1 above.

[0160] Referring to Figure 5 below, a structural schematic diagram of a vehicle suitable for implementing embodiments of this application is shown. The vehicle in the embodiments of this application may include, but is not limited to, vehicles internally equipped with an onboard computing module and an onboard communication module, or terminals such as mobile terminals, data storage control terminals, and PCs connected to the vehicle's electronic control unit. The vehicle shown in Figure 5 is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0161] As shown in Figure 5, the vehicle may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for vehicle operation. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. The communication device 1009 allows the vehicle to exchange data with other devices wirelessly or via wired communication. Although the diagram shows vehicles with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented alternatively.

[0162] According to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0163] The vehicle provided in this application, employing the network optimization method described in the above embodiments, can solve the technical problem of low efficiency in network optimization operations in related technologies. Compared with the prior art, the beneficial effects of the vehicle provided in this application are the same as those of the network optimization method provided in the above embodiments, and other technical features of the vehicle are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0164] The various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0165] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0166] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the network optimization method described in the above embodiments.

[0167] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0168] The aforementioned computer-readable storage medium may be included in the vehicle or may exist independently and not installed in the vehicle.

[0169] The aforementioned computer-readable storage medium carries one or more programs. When the one or more programs are executed by a vehicle, the vehicle causes the vehicle to: detect the module status of the on-board computing module, wherein the module status is either in use or idle; if the module status is detected to be in use, read the interaction log of the on-board computing module; and if the interaction log determines that the on-board computing module is experiencing network lag, perform network optimization operations according to a target network optimization strategy, wherein the target network optimization strategy is either a first network optimization strategy or a second network optimization strategy.

[0170] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0171] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0172] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0173] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described network optimization method, thereby solving the technical problem of low efficiency in network optimization operations in related technologies. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the network optimization method provided in the above embodiments, and will not be repeated here.

[0174] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the network optimization method described above.

[0175] The computer program product provided in this application can solve the technical problem of low efficiency in network optimization operations in related technologies. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the network optimization method provided in the above embodiments, and will not be repeated here.

[0176] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A network optimization method, wherein, The network optimization method is applied to a vehicle, which includes an onboard communication module and an onboard computing module. The network optimization method includes: The module status of the vehicle computing module is detected, wherein the module status is either in use or idle. If the module status is detected to be in the usage state, the interaction log of the vehicle computing module is read. If the interaction log determines that the vehicle computing module is experiencing network lag, a network optimization operation is performed according to the target network optimization strategy, wherein the target network optimization strategy is either a first network optimization strategy or a second network optimization strategy.

2. The network optimization method as described in claim 1, wherein, After the step of reading the interaction log of the in-vehicle computing module, the method further includes: The number of screen clicks and the screen click time contained in the interaction log are determined, and the user operation frequency is determined based on the number of screen clicks and the screen click time. If the frequency of user operation is detected to reach a preset click frequency threshold, it is determined that the vehicle computing module has a network lag phenomenon, and the step of performing network optimization operation according to the target network optimization strategy is executed.

3. The network optimization method as described in claim 1 or 2, wherein, The vehicle and the cloud server are connected in communication. After the step of detecting the module status of the on-board computing module, the method further includes: When the module is detected to be in the usage state, multiple first network state parameters corresponding to the vehicle computing module are determined. Multiple first network state parameters are sent to the cloud server, and network environment detection results are received from the cloud server. The network environment detection results are generated by a lightweight time series prediction model deployed in the cloud server based on multiple first network state parameters. Based on the network environment detection results, a target network optimization strategy is determined, and network optimization operations are performed according to the target network optimization strategy.

4. The network optimization method as described in claim 3, wherein, The step of determining the target network optimization strategy based on the network environment detection results includes: If the network environment detection result indicates that the vehicle computing module is in a weak network environment, the preset first network optimization strategy is determined as the target network optimization strategy, wherein the first network optimization strategy is a network optimization strategy for switching the communication cell corresponding to the vehicle. If the network environment detection result indicates that the vehicle computing module is in a network change environment, the preset second network optimization strategy is determined as the target network optimization strategy, wherein the second network optimization strategy is a network optimization strategy that switches the network connection mode corresponding to the vehicle.

5. The network optimization method according to any one of claims 1 to 4, wherein, The vehicle and the target mobile terminal are communicatively connected. The step of performing network optimization operations according to the target network optimization strategy includes: If the target network optimization strategy is detected to be the first network optimization strategy, the cell feature database sent by the target mobile terminal is received. The target cell is determined by querying the cell feature database based on multiple first network state parameters, and the vehicle is connected to the target cell via the vehicle communication module.

6. The network optimization method as described in claim 5, wherein, The step of performing network optimization operations according to the target network optimization strategy further includes: If the target network optimization strategy is detected to be the second network optimization strategy, a preset target network connection type is determined; The vehicle communication module switches the current network connection mode of the vehicle to the target network connection mode.

7. The network optimization method according to any one of claims 1 to 6, wherein, After the step of detecting the module status of the on-board computing module, the method further includes: When the module is detected to be in the idle state, multiple second network status parameters corresponding to the vehicle communication module are determined. Determine a preset global network environment judgment rule, and determine the threshold values ​​of the state parameters corresponding to each of the multiple second network state parameters included in the global network environment judgment rule; Multiple second network state parameters are compared with their respective state parameter thresholds to obtain multiple first comparison results, and a target network state parameter is determined based on the multiple first comparison results, wherein the target network state parameter is a second network state parameter that reaches the state parameter threshold. If the number of the target network state parameters is detected to reach a first quantity threshold, the network environment corresponding to the vehicle communication module is determined to be a weak network environment. The first network optimization strategy is determined as the target network optimization strategy, and network optimization operations are performed according to the target network optimization strategy.

8. The network optimization method as described in claim 7, wherein, After the step of determining the target network state parameters based on multiple first comparison results, the method further includes: If the number of the target network state parameters is detected to reach a second quantity threshold, the network environment corresponding to the vehicle communication module is determined to be a network change environment, wherein the second quantity threshold is greater than the first quantity threshold; The second network optimization strategy is determined as the target network optimization strategy, and network optimization operations are performed according to the target network optimization strategy.

9. A vehicle, wherein, The vehicle includes: an on-board communication module, an on-board computing module, a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the network optimization method as described in any one of claims 1 to 8.

10. A storage medium, wherein, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the network optimization method as described in any one of claims 1 to 8.

11. A computer program product, wherein, The computer program product includes a computer program that, when executed by a processor, implements the steps of the network optimization method as described in any one of claims 1 to 8.

Images