Network optimization method and device, electronic equipment and vehicle

Abstract

The invention relates to a network optimization method and device, electronic equipment and a vehicle, relates to the technical field of vehicle communication, and solves the technical problem of how to quickly and accurately detect and optimize a network of a vehicle. The network optimization method comprises the following steps: acquiring position environment data of a detected vehicle; the position environment data comprises a detected vehicle position and environment information of the detected vehicle position; inputting the position environment data into a network optimization model to obtain a network fault type of the detected vehicle and a network optimization strategy corresponding to the network fault type; and optimizing the network for detecting the vehicle according to the network optimization strategy. The present disclosure is used to analyze, diagnose and optimize the network of the vehicle.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle communication technology, and in particular to a network optimization method, device, electronic equipment, and vehicle. Background Art

[0002] With the rapid development of intelligent and connected vehicles, vehicles are becoming increasingly dependent on mobile wireless networks. Whether it's real-time high-precision positioning and navigation, online video entertainment, remote vehicle control, autonomous driving, or wireless parking, these functions all require stable, high-speed mobile networks. However, while vehicles are in motion, the network environment is complex and ever-changing, and signals are easily affected by factors such as terrain, building obstructions, and weather. This can lead to unstable network connections, reduced data rates, and even interruptions.

[0003] Related technologies monitor the network connection between the vehicle and a higher-level server, save network anomaly information to a local database, and periodically upload it to a backend server. Backend R&D personnel then analyze the anomaly information. Subsequently, an update package can be downloaded based on the cause of the network failure, and the updated package can be installed in the vehicle. This technical solution addresses network failures by downloading software updates over the network, but it fails to account for the possibility that software updates cannot be downloaded when the vehicle's network is abnormal, thus failing to resolve the network failure.

[0004] Another related technology provides a method for automatically uploading abnormal data. This method collects vehicle abnormality information, encapsulates the information, and uploads it to the cloud. The cloud classifies the abnormal information and then uses a local abnormality detection module to perform abnormality detection. The abnormality detection module analyzes the abnormal information based on preset abnormal conditions. This technical solution provides a method for classifying uploaded vehicle abnormality information through the cloud and then performing abnormality detection based on the vehicle's local abnormality detection module. When the abnormality detection module is activated, that is, when a vehicle experiences an abnormal fault, the vehicle may no longer be able to communicate with the backend, and the cloud will not be able to obtain abnormal information, making it impossible to promptly address the vehicle abnormality.

[0005] In summary, how to quickly and accurately detect and optimize the vehicle network is a technical problem that needs to be solved urgently. Summary of the Invention

[0006] The present disclosure provides a network optimization method, device, electronic device and vehicle. The purpose of the present disclosure is to solve the technical problem of how to quickly and accurately detect and optimize the vehicle network.

[0007] In order to achieve the above objectives, the technical solutions adopted in this disclosure are as follows:

[0008] According to a first aspect provided by the present disclosure, a network optimization method is provided, including: obtaining location environment data of a detection vehicle; the location environment data including: the detection vehicle location and environmental information of the detection vehicle location; inputting the location environment data into a network optimization model to obtain a network fault type of the detection vehicle and a network optimization strategy corresponding to the network fault type; and optimizing the network of the detection vehicle according to the network optimization strategy.

[0009] Based on the above technical means, the present disclosure can input the acquired location and environmental data of the detection vehicle into a network optimization model deployed on the detection vehicle, realize the analysis and diagnosis of the detection vehicle network, and obtain the detection vehicle network fault type and the corresponding network optimization strategy. Then, the network optimization strategy output by the network optimization model can be used to complete the network optimization of the detection vehicle, resolve the detection vehicle network fault, and thus realize the network self-diagnosis function of the detection vehicle. Based on the network optimization model, it is possible to quickly and accurately analyze and diagnose the detection vehicle network.

[0010] In one possible implementation, a network optimization model is trained in the following manner: obtaining a training sample set; the training sample set includes multiple training samples and a label for each training sample; the training samples include sample features of a sample vehicle; the sample features are used to represent environmental information and network status of the sample vehicle; the labels of the training samples include: the network fault type of the sample vehicle and the network optimization strategy of the sample vehicle; and an initial network optimization model is trained based on the training sample set to obtain a network optimization model.

[0011] According to the above technical means, by training the initial network optimization model based on the environmental information and network status data of the sample vehicle's location, the obtained network optimization model can fully combine factors such as the environmental information and network status of the detection vehicle's location when performing network analysis and diagnosis on the detection vehicle in the future, and accurately determine the network fault type of the detection vehicle and the network optimization strategy corresponding to the network fault type.

[0012] In one possible embodiment, sample features are obtained in the following manner: sample data corresponding to the sample features are collected based on a collection frequency; the sample data includes environmental information and network status of the sample vehicle's location; the collection frequency is negatively correlated with the network status; data preprocessing and feature extraction are performed on the sample data to obtain sample features; data preprocessing includes data cleaning and denoising and / or normalization processing.

[0013] The above-mentioned technical means collect sample data corresponding to sample features based on the collection frequency, enabling the collection of sample data based on the network status of the sample vehicle. When the network status is poor, a higher collection frequency can be used to ensure the continuity of data collection and ensure that key data information is not missed. When the network status is relatively stable, a lower collection frequency can be used, effectively reducing unnecessary data and alleviating pressure on network transmission and data storage. Data preprocessing ensures the reliability of the sample data and improves the quality and efficiency of network optimization model training. Feature extraction can reduce data dimensionality and discover key data features in the data. Subsequent network optimization model training can be based on key data features, improving the training effect of the network optimization model.

[0014] In one possible implementation, the network optimization strategy includes: switching the network access base station of the detection vehicle to the first base station, raising the network signal receiving and transmitting position of the network antenna of the detection vehicle, adjusting the network standard of the detection vehicle, and adjusting the network bandwidth resource allocation ratio of the application of the detection vehicle; wherein, the first base station satisfies at least one of the following conditions: the detection vehicle detects that the signal strength of the first base station is greater than the preset strength, the detection vehicle is in the coverage range of the first base station, and the network load of the first base station is lower than the preset load.

[0015] According to the above technical means, the network optimization strategy provided by the network optimization model can be used to optimize the network failure of the detection vehicle. When the detection vehicle frequently experiences network connection interruptions during driving, or cannot be registered normally to the network base station, the network of the detection vehicle is connected to the first base station (that is, during the driving process of the vehicle, the signal strength of all base stations around the detection vehicle meets the connection conditions and the network load is low) by switching the base station. The network optimization strategy solves the problem that the network signal of the base station currently connected to the detection vehicle is unstable, which leads to the unstable network connection of the detection vehicle. When the network signal reception of the detection vehicle fluctuates and the signal strength continues to decrease, the network signal receiving and transmitting position of the network antenna of the detection vehicle can be raised or the network standard of the detection vehicle can be adjusted (from 5G network to 4G network) to enhance the network signal strength of the detection vehicle. When the network of the detection vehicle is stuck or delayed, the bandwidth allocation of the detection vehicle can be optimized, and the problem of network stuck and delay of the detection vehicle can be solved by reasonably adjusting the proportion of network bandwidth resource allocation of the application program of the detection vehicle.

[0016] In one possible implementation, after optimizing the network of the detection vehicle according to the network optimization strategy, it also includes: obtaining a network optimization result after optimizing the network of the detection vehicle; the network optimization result is used to represent the difference between the network performance after optimizing the network of the detection vehicle and the preset network performance; when the network optimization result is used to represent that the difference between the network performance after optimizing the network of the detection vehicle and the preset network performance is greater than the preset difference, obtaining network optimization analysis data; and determining the network problem location result of the detection vehicle based on the network optimization analysis data.

[0017] Using the aforementioned technical means, the network optimization results obtained after optimizing the test vehicle's network can be used to determine whether the optimized vehicle's network performance meets the expected performance. If the optimized test vehicle's network does not meet the expected performance, network optimization analysis data from the test vehicle's network optimization process is obtained and, based on this network optimization analysis data, the specific cause of the test vehicle's network problem is located (i.e., the network problem location result for the test vehicle is determined).

[0018] In one possible implementation, obtaining a network optimization result after optimizing the network of the detection vehicle includes: obtaining network performance parameters after optimizing the network of the detection vehicle; network performance parameters include: network signal strength, RSSI, RSRP, RSRQ, SINR, data transmission rate, delay, packet loss rate, TCP retransmission rate and at least one of network connection status; determining the network optimization result based on the network performance parameters and the difference between the network performance indicators.

[0019] According to the above technical means, the network optimization result after optimizing the network of the detection vehicle can be determined by obtaining the network performance parameters of the detection vehicle and comparing the difference between the network performance parameters of the detection vehicle and the network performance indicators, so as to analyze the network situation of the optimized detection vehicle and subsequently optimize the network through the network optimization result.

[0020] In a possible implementation, the network optimization analysis data includes: location environment data during the process of optimizing and detecting the network of the vehicle, optimization logs during the process of optimizing and detecting the network of the vehicle, and network optimization strategies.

[0021] According to the above technical means, after the network of the detection vehicle is optimized, when the network performance of the optimized detection vehicle still does not meet the preset network performance, the network optimization model analyzes the location environment data obtained in real time during the optimization process of the detection vehicle, as well as the optimization log during the optimization process of the detection vehicle and the network optimization strategy for optimizing the detection vehicle network, so as to obtain detailed error information during the optimization process and the network fault type of the optimized detection vehicle.

[0022] In a possible implementation, after determining the network problem locating result of the detection vehicle based on the network optimization analysis data, it also includes: when the network problem locating result is that the number of network connection interruptions of the detection vehicle within a preset time period is greater than the preset number of network connection interruptions and registration with the base station fails, the base station of the network access of the detection vehicle is switched to a second base station; the detection vehicle is in the coverage range of the second base station.

[0023] According to the above technical means, the network analysis of the detection vehicle is performed based on the network optimization model, and the network of the detection vehicle is optimized through the network optimization strategy output by the network optimization model. When the network access base station of the detection vehicle is switched last time, the network of the detection vehicle still frequently experiences network connection interruptions or cannot be normally registered to the network base station, the network of the detection vehicle is connected to other network base stations within the connection range of the detection vehicle.

[0024] In a possible implementation, the network optimization method further includes:

[0025] Synchronously detect the policy version information of the vehicle and the cloud server; the policy version information includes at least one of the vehicle version information of the detected vehicle, the version information of the network optimization model and the network optimization policy.

[0026] According to the above technical means, the network optimization method provided by the present disclosure can also synchronously detect the policy versions of the vehicle and the cloud server to avoid the problem of the vehicle's local policy being lost due to network problems or other problems.

[0027] According to a second aspect provided by the present disclosure, a network optimization device is provided. The network optimization device is applied to a vehicle, and the network optimization device includes: a communication unit and a processing unit.

[0028] The communication unit is used to obtain the position environment data of the detection vehicle; the position environment data includes: the detection vehicle position and the environment information of the detection vehicle position.

[0029] The processing unit is used to input the location environment data into the network optimization model to obtain the network fault type of the detection vehicle and the network optimization strategy corresponding to the network fault type.

[0030] The processing unit is further used to optimize the network for detecting vehicles according to a network optimization strategy.

[0031] According to a third aspect provided by the present disclosure, an electronic device is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement the method of the above-mentioned first aspect and any possible implementation method thereof.

[0032] According to a fourth aspect provided by the present disclosure, a vehicle is provided, which is used to implement the method of the above-mentioned first aspect and any possible implementation manner thereof.

[0033] It should be noted that the technical effects brought about by any implementation method in the second to fourth aspects can refer to the technical effects brought about by the corresponding implementation method in the first aspect, and will not be repeated here.

[0034] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute an improper limitation of the present disclosure.

[0036] Figure 1 is a structural diagram of a network optimization system according to an exemplary embodiment;

[0037] Figure 2 is a flow chart showing a network optimization method according to an exemplary embodiment;

[0038] Figure 3 is a training flow chart of a network optimization model according to an exemplary embodiment;

[0039] Figure 4 is a training flowchart of another network optimization model according to an exemplary embodiment;

[0040] Figure 5 is a flow chart showing another network optimization method according to an exemplary embodiment;

[0041] Figure 6 is a flow chart showing another network optimization method according to an exemplary embodiment;

[0042] Figure 7 is a flow chart showing another network optimization method according to an exemplary embodiment;

[0043] Figure 8 is a block diagram of a network optimization device according to an exemplary embodiment;

[0044] Figure 9 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0045] In order to enable ordinary people in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0046] It should be noted that the terms "first," "second," and the like in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the numbers used in this manner are interchangeable where appropriate so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure as detailed in the appended claims.

[0047] like Figure 1 As shown, an embodiment of the present disclosure provides a network optimization system, which can be deployed on a vehicle (i.e., the detection vehicle provided by the embodiment of the present disclosure) 101, and a data acquisition device 102 can also be deployed on the vehicle.

[0048] In the embodiment of the present disclosure, the data acquisition device 102 is used to obtain the vehicle's location environment data and the vehicle's network status information, and provide it to the vehicle 101, so that the vehicle 101 can diagnose, analyze and optimize the vehicle's network based on the vehicle's location environment data and network status information.

[0049] Optionally, the data acquisition device 102 can be a Global Navigation Satellite System (GNSS) module deployed on the vehicle 101, which is used to obtain the vehicle's geographic location information, or it can be a built-in vehicle antenna, an external 4G / 5G antenna and an external positioning antenna, which are used to obtain the vehicle's network signal strength and network quality information, or it can be a millimeter-wave lidar and visual sensor installed on the vehicle, which are used to collect environmental information near the vehicle.

[0050] Optionally, the execution entity of the network optimization method provided in the embodiment of the present disclosure may be a processing module deployed on the vehicle (such as a central control device), which is used to detect, analyze and optimize the vehicle network based on the vehicle's location environment data provided by the data acquisition device 102.

[0051] The network optimization method provided by the embodiment of the present disclosure is described in detail below with reference to the accompanying drawings.

[0052] The network optimization method provided by the embodiment of the present disclosure is applied to Figure 1 The vehicle 101 in the network optimization system shown (ie, the detection vehicle provided by the embodiment of the present disclosure) is as follows: Figure 2 As shown, the network optimization method provided by the embodiment of the present disclosure includes:

[0053] S201: Acquire location and environment data of a detection vehicle.

[0054] The location environment data includes: the detected vehicle location and the environment information of the detected vehicle location.

[0055] Specifically, the network optimization model in the detection vehicle needs to analyze and diagnose the network of the detection vehicle based on the location environment data of the detection vehicle, so the location environment data of the detection vehicle needs to be obtained.

[0056] Optionally, the location environment data can be the original data such as the detection vehicle position, the detection vehicle position environmental information, etc. obtained in real time by the data acquisition equipment during the driving process of the detection vehicle. Then, after data preprocessing and feature extraction, the location environment data is obtained to facilitate the subsequent network optimization model to analyze, diagnose and optimize the detection vehicle network based on the location environment data.

[0057] Optionally, detecting the vehicle's location may include detecting the vehicle's Global Positioning System (GPS) location information and detecting the vehicle's speed and other data. Detecting the vehicle's location environment information may include detecting the vehicle's surrounding environment information (such as detecting whether the vehicle is in a tunnel, a city area with dense high-rise buildings, etc.).

[0058] S202: Input the location environment data into a network optimization model to obtain a network fault type of the detection vehicle and a network optimization strategy corresponding to the network fault type.

[0059] Specifically, the detection vehicle analyzes the input location environment data through the network optimization model, can determine whether there is a network failure in the detection vehicle's network, and output the network failure type of the detection vehicle and the network optimization strategy corresponding to the network failure type.

[0060] Optionally, the network fault type is the type of vehicle network fault detected (such as weak signal, severe packet loss, network interruption, etc.), and the network optimization strategy can also be the corresponding solution given by the network optimization model according to the network fault type (such as switching network mode, adjusting signal reception parameters, etc.).

[0061] For example, the network optimization model rapidly analyzes the input location environment data and, based on the characteristic patterns and regularities learned from the location environment data, determines whether the network currently being tested is faulty. If so, it outputs the network fault type and network optimization strategy, and generates a specific optimization plan based on the network optimization strategy. For example, if the network optimization model determines that the network fault type is weak network signal and the cause of the network fault is excessively loaded at the current base station, the network optimization model outputs an optimization plan to switch to a nearby base station with lower load.

[0062] It's understandable that using the network optimization model to diagnose network faults on the test vehicle and output network optimization strategies enables self-diagnosis of the test vehicle. This is because the network optimization model continuously learns and updates based on a large amount of historical vehicle location and environmental data, improving its diagnostic capabilities and accuracy. It can adapt to different locations and environments, enabling rapid and accurate diagnosis of the test vehicle's network status and subsequent network optimization. Compared to conventional techniques where back-office personnel analyze network fault causes, this model provides a comprehensive and in-depth understanding of the test vehicle's network issues.

[0063] S203: Optimize the network for detecting vehicles according to the network optimization strategy.

[0064] Specifically, the detection vehicle automatically adjusts the network of the detection vehicle according to the network optimization strategy to achieve network optimization of the detection vehicle.

[0065] Exemplarily, the inspection vehicle automatically adjusts the network configuration parameters of the inspection vehicle according to the network optimization strategy, such as restarting the on-network module to switch to a base station with more stable signal strength, increasing the frequency of concurrent links, changing the network protocol, etc., thereby optimizing the network performance of the inspection vehicle.

[0066] It can be seen that the network optimization strategy output by the network optimization model of the detection vehicle can complete the self-optimization of the detection vehicle network, which can improve the speed and stability of the detection vehicle network optimization.

[0067] In some embodiments, as Figure 3 As shown in Figure 2, the network optimization model is trained in the following way:

[0068] S301: Obtain a training sample set.

[0069] The training sample set includes multiple training samples and labels for each training sample. The training samples include sample features of the sample vehicle. The sample features represent the environmental information and network status of the sample vehicle's location. The labels for the training samples include the network fault type of the sample vehicle and the network optimization strategy for the sample vehicle.

[0070] S302: Train the initial network optimization model based on the training sample set to obtain a network optimization model.

[0071] It should be noted that the construction and training of the network optimization model can be carried out in the cloud server, and the obtained network optimization model will be deployed locally on the detection vehicle.

[0072] Specifically, in the process of training the initial network optimization model based on the training sample set, the training samples in the training sample set can be input into the initial network optimization model to obtain a prediction result.

[0073] Then, the loss value between the prediction result of the initial network optimization model and the training sample label can be calculated based on the loss function (that is, the difference between the network fault type and the network optimization strategy corresponding to the network fault type output by the initial network optimization model, and the network fault type and the network optimization strategy of the sample vehicle in the training sample label).

[0074] When the loss value converges and the performance of the initial network optimization model reaches stability, the training is stopped to obtain the trained network optimization model.

[0075] Subsequently, the disclosed embodiment may further optimize the performance of the trained network optimization model to obtain a network optimization model.

[0076] For example, combined Figure 3 ,like Figure 4 As shown, in the above S302, the training process of the network optimization model is as follows:

[0077] S401: Determine the model architecture of the initial network optimization model.

[0078] For example, an initial network optimization model can be designed based on the Transformer model architecture. Subsequently, a module specifically for processing vehicle location features and the environmental information features of the vehicle location can be embedded in the initial network optimization model to further process the feature data of the vehicle location features and the environmental features of the vehicle location, so that the initial network optimization model can better integrate the feature data of the vehicle location features and the environmental features of the vehicle location. Subsequently, the number of layers and neurons in the initial network optimization model can be adjusted to improve the learning ability and generalization performance of the initial network optimization model while ensuring computational efficiency.

[0079] It is important to know that the Transformer model architecture mainly consists of two parts: encoder and decoder.

[0080] The encoder consists of multiple identical encoder layers stacked together. Its primary function is to extract features and encode the input sequence data. Each encoder layer contains components such as a multi-head self-attention mechanism, a feed-forward neural network, and some normalization and residual connections. These components work together to gradually process the input and capture long-range dependencies and other semantic features in the sequence.

[0081] The decoder is also composed of multiple stacked decoder layers. Building on the encoder, it further converts the encoded information into the desired output sequence. In addition to a multi-head self-attention mechanism, a feedforward neural network, normalization, and residual connections, the decoder layer also incorporates a multi-head attention mechanism focused on the encoder output. This incorporates information passed by the encoder, ensuring that the generated output sequence meets the requirements and is semantically related to the input sequence.

[0082] Components such as the multi-head attention mechanism in the Transformer model architecture can be computed in parallel, significantly improving training and inference speed. They can also capture long-range dependencies in input sequences. For example, when understanding the semantics of complex, long sentences, they can accurately grasp the logical relationships between different parts, helping to identify and output network fault types and network optimization strategies.

[0083] It is important to know that the input layer of the initial network optimization model is used to receive the preprocessed sample data features, the middle layer performs in-depth feature extraction and analysis on the sample data through a multi-layer neural network, and the output layer outputs the network diagnosis results of the sample vehicle (such as network fault type and cause) and network optimization strategies (such as switching network modes and adjusting signal reception parameters, etc.).

[0084] S402: Obtain a training sample set.

[0085] Optionally, a large amount of historical network data from sample vehicles is collected from cloud servers and / or onboard storage units, including data under normal network conditions and data under different network failure scenarios. The collected historical data is then annotated to clearly identify the network failure type (e.g., weak signal, severe packet loss, network interruption, etc.) and network optimization strategy (e.g., switching to a more stable base station, re-logging in, changing network protocols, etc.) corresponding to each data sample. This annotated data becomes the training sample set.

[0086] Optionally, the labeled data can be divided into a training sample set (also called a training set), a validation set, and a test set (used for training, validation, and evaluation of the initial network optimization model).

[0087] S403: Train an initial network optimization model.

[0088] Optionally, the initial network optimization model can be trained based on the training sample set. During the training process, the error (i.e., loss value) between the predicted results of the initial network optimization model and the labeled true results is calculated based on the loss function (also known as the stochastic gradient descent optimization algorithm), and the parameters of the initial network optimization model are adjusted. In addition, during the training process, the initial network optimization model is regularly evaluated using the validation set to monitor the performance indicators of the initial network optimization model (such as diagnostic accuracy, optimization effect improvement rate, etc.). Based on the evaluation results, the training parameters (such as learning rate, regularization coefficient, etc.) are adjusted to prevent the initial network optimization model from overfitting or underfitting.

[0089] When the loss value of the initial network optimization model tends to converge and the performance detected on the validation set reaches stability, training is stopped.

[0090] S404: Evaluate and optimize the initial network optimization model to determine the network optimization model.

[0091] Optionally, various performance indicators (such as diagnostic accuracy, recall rate, and F1-score) of the initial network optimization model can be calculated based on the test set data. The diagnostic and optimization effects of the initial network optimization model in different network scenarios can be analyzed to identify any deficiencies in the initial network optimization model. To address these deficiencies, the initial network optimization model architecture and training parameters can be further adjusted to optimize the initial network optimization model, thereby improving its performance and reliability and ultimately obtaining a network optimization model.

[0092] In some embodiments, combined Figure 3 ,like Figure 5 As shown, the sample features in the above S301 are obtained in the following way:

[0093] S501: Collect sample data corresponding to sample features based on collection frequency.

[0094] The sample data includes the environmental information and network status of the sample vehicle's location. The collection frequency is negatively correlated with the network status.

[0095] Specifically, since the data change rates are different under different network states, sample data corresponding to the sample characteristics may be collected based on the collection frequency.

[0096] Optionally, when the location environment of the sample vehicle is complex or there are many environmental signal sources at the location, the network environment may become complex and the network status may be unstable. The relevant data of the sample vehicle may change frequently in a short period of time, so the data collection frequency can be increased to capture these complex and rapidly changing data details as comprehensively and timely as possible. When the location environment of the sample vehicle is relatively simple, that is, the network status is relatively stable, the relevant data of the sample vehicle changes relatively slowly and will not change frequently in a short period of time, so the data collection frequency can be reduced to reduce the amount of unnecessary data. Therefore, different collection frequencies can be set according to the network status of the sample vehicle.

[0097] For example, in areas with good network environment, such as highways and uninhabited areas, a low-frequency collection strategy can be used; in areas with complex and changeable network environment, such as city center or areas with many surrounding signal sources, the collection frequency needs to be increased to ensure the collection quantity under high load and high interference.

[0098] It is important to know that the collected data can also be transmitted to the storage unit in the vehicle communication controller through the in-vehicle network for local storage in the vehicle. At the same time, the original data after the report can be uploaded to the cloud server through the wireless network. The cloud server can perform more in-depth analysis and model training based on the collected data.

[0099] S502: Perform data preprocessing and feature extraction on the sample data to obtain sample features.

[0100] Among them, data preprocessing includes data cleaning and denoising and / or normalization processing.

[0101] Specifically, the sample data is first preprocessed to improve its quality and consistency, generating preprocessed data. Feature extraction is then performed on the preprocessed data to extract sample features that are useful for training the network optimization model.

[0102] Optionally, by extracting sample features from the data (such as the changing trend of network signals, the peak and valley values of data transmission rates, the relationship between vehicle driving direction and network signal changes, etc.), the expressive power of sample data can be enhanced, thereby improving the diagnosis of network optimization models and network optimization results.

[0103] Exemplarily, during the data preprocessing process, data cleaning and denoising can include employing a data cleaning algorithm to remove duplicate data, erroneous data, and outliers from the collected data. For example, sudden maxima and minima in network signal strength can be identified and corrected using statistical analysis methods. Data algorithms can also be used to denoise data with large fluctuations, such as network transmission rates, to smooth the data and improve data usability.

[0104] For example, during the data preprocessing process, normalization (also known as regularization) can include normalizing different types of data to convert them to the same numerical range and establish a unified standard. For example, signal strength can be converted from its original decibel relative to one milliwatt (dBm) value to a range of 0 to 1, data delay can be converted from milliseconds (ms) to a relative value of 0 to 1, and data signal-to-noise ratio can be converted from its original decibel (dB) value to a relative value of 0 to 1. This ensures that data with different sample characteristics have the same weight and influence in network optimization model training.

[0105] It's understandable that preprocessing sample data can ensure its reliability and improve the quality and efficiency of network optimization model training. Feature extraction can reduce data dimensionality and uncover key data features within the data. Subsequent network optimization model training can be based on these key data features, improving training effectiveness.

[0106] In some embodiments, the network optimization strategy includes:

[0107] Switch the network access base station of the detection vehicle to the first base station, raise the network signal receiving and transmitting position of the network antenna of the detection vehicle, adjust the network standard of the detection vehicle, and adjust the network bandwidth resource allocation ratio of the application of the detection vehicle.

[0108] Among them, the first base station meets at least one of the following conditions: the signal strength of the first base station detected by the detection vehicle is greater than the preset strength, the detection vehicle is in the coverage range of the first base station, and the network load of the first base station is lower than the preset load.

[0109] Optionally, the network standard may include: any one of: 2G network standard, 3G network standard, 4G network standard and 5G network standard.

[0110] For example, while the detection vehicle is driving, the detection vehicle's network is detected and analyzed based on the network optimization model. When it is detected that the detection vehicle's network frequently experiences network connection interruptions or is unable to properly register with a network base station, the network optimization model outputs a network optimization strategy that can be to switch the detection vehicle's network access base station to a first base station, that is, by connecting the detection vehicle's network to a base station with higher network signal strength and lower network load among all base stations that can be connected around the detection vehicle, thereby resolving the network failure problem of the detection vehicle frequently experiencing network interruptions and being unable to properly register with a network base station.

[0111] When it is detected that the network signal reception of the detection vehicle fluctuates and the signal strength continues to decrease (for example, parameter indicators such as the received signal strength indication (RSSI) or the reference signal received power (RSRP) are low, indicating that the received network signal strength is insufficient), the network optimization strategy output by the network optimization model can be to increase the network signal receiving and transmitting position of the network antenna of the detection vehicle or adjust the network format of the detection vehicle, that is, by changing or increasing the receiving position of the network antenna of the detection vehicle, the network antenna can better receive the network signal sent by the base station, thereby enhancing the network signal strength of the detection vehicle. Or by automatically adjusting the network format of the detection vehicle (for example, switching from a 4G network to a 5G network) to solve the problem of continuously decreasing network signal strength.

[0112] When it is detected that the network of the inspection vehicle is stuck or delayed (for example, the packet loss rate rises to 15%, the delay increases to 500ms, etc.), the proportion of the bandwidth occupied by the inspection vehicle's application is analyzed according to the network load of the inspection vehicle, the bandwidth of the inspection vehicle is reasonably allocated, and the bandwidth proportion of key applications is increased (for example, during the driving process of the vehicle, a higher bandwidth is allocated to obtain real-time road conditions), thereby improving the overall bandwidth utilization of the inspection vehicle and solving network failure problems such as network stuck and delay.

[0113] In some embodiments, combined Figure 2 ,like Figure 6 As shown, in the above S203, after optimizing the network for detecting vehicles according to the network optimization strategy, the process further includes:

[0114] S601: Obtain a network optimization result after optimizing the network of the detection vehicle.

[0115] The network optimization result is used to indicate the difference between the network performance after optimizing the detection vehicle's network and the preset network performance.

[0116] Specifically, after the test vehicle's network is optimized, the test vehicle obtains the network optimization results after the optimization of the test vehicle's network to determine whether the optimized test vehicle's network will still experience network failures. If the network performance after the optimization of the test vehicle's network does not meet the preset network performance, the network optimization model will need to be further optimized.

[0117] For example, after optimizing the network of the detection vehicle, the network performance indicators such as signal strength, data transmission rate, signal-to-noise ratio, etc. are continuously monitored to calculate whether the effect after optimization has achieved the expected effect through the indicators.

[0118] S602: When the network optimization result indicates that the difference between the network performance after the network of the detection vehicle is optimized and the preset network performance is greater than the preset difference, obtain network optimization analysis data.

[0119] Specifically, when the network performance after optimizing the detection vehicle network does not reach the preset network performance, network optimization analysis data is obtained so that the subsequent network optimization model can analyze the optimized detection vehicle network based on the network optimization analysis data.

[0120] In some embodiments, the network optimization analysis data includes: location environment data during the process of optimizing the network of the detection vehicle, optimization logs during the process of optimizing the network of the detection vehicle, and network optimization strategies.

[0121] Optionally, the optimization log during the process of optimizing and detecting the network of the vehicle may include the network connection status and the error code of abnormal conditions that occur during the network analysis process.

[0122] Exemplarily, the optimization log in the process of optimizing the network of the detection vehicle can be log information recorded by the built-in modem of the detection vehicle during the network analysis and optimization process of the detection vehicle, including: network connection, communication interaction and other related status, detailed information after network optimization through network optimization strategy, and radio resource control (RCC) signaling related error codes.

[0123] S603: Determine the network problem location result of the detection vehicle based on the network optimization analysis data.

[0124] Specifically, the network of the optimized detection vehicle is analyzed based on the network optimization model according to the network optimization analysis data. The model can determine the specific cause of the network optimization failure based on the network optimization analysis data (such as through error message prompts in the log and other information), thereby locating the specific cause of the network optimization failure and determining the network problem locating result of the detection vehicle.

[0125] Optionally, the positioning result is a specific cause of the network optimization failure located by the network optimization model analysis.

[0126] For example, after the network optimization model obtains the network optimization analysis data, it conducts a more in-depth analysis of the optimized detection vehicle network, including locating the cause of the failure, analyzing whether the failure is caused by the superposition of multiple concurrent problems, or whether unavoidable factors such as external factors lead to the failure of network optimization.

[0127] In some embodiments, combined Figure 6 ,like Figure 7 As shown, in the above S601, obtaining the network optimization result after optimizing the network of the detection vehicle specifically includes:

[0128] S701: Obtain network performance parameters after optimizing the network for detecting the vehicle.

[0129] Among them, the network performance parameters include: network signal strength, RSSI, RSRP, Reference Signal Received Quality (RSRQ), Signal to Interference plus Noise Ratio (SINR), data transmission rate, delay, packet loss rate, Transmission Control Protocol (TCP) retransmission rate and network connection status.

[0130] Specifically, the network optimization result after optimizing the network of the detection vehicle needs to be obtained by comparing and analyzing the network performance parameters of the detection vehicle with the preset network performance parameters. Therefore, it is necessary to obtain the network performance parameters after optimizing the network of the detection vehicle.

[0131] S702: Determine a network optimization result based on the network performance parameters and the difference between the network performance indicators.

[0132] Specifically, by comparing and analyzing the network performance parameters of the vehicle with the preset network performance parameters, the network performance parameters and the difference in network performance indicators are obtained, thereby determining the network optimization result.

[0133] For example, assuming that the preset network performance parameters are signal strength improvement greater than 5dBm, packet loss rate less than 2%, etc., the network optimization result is determined by comparing the difference between the network performance parameter value after optimizing the network of the detection vehicle and the above-mentioned preset network performance parameters.

[0134] In some embodiments, combined Figure 6 In the above S603, after determining the network problem location result of the detection vehicle based on the network optimization analysis data, the following steps are also included:

[0135] When the network problem location result is that the number of network connection interruptions of the detection vehicle within a preset time period is greater than the preset number of network connection interruptions and registration with the base station fails, the base station of the network access of the detection vehicle is switched to a second base station; the detection vehicle is in the coverage range of the second base station.

[0136] Specifically, after switching the base station for network access of the detection vehicle, a network failure problem still occurs in which the number of network connection interruptions of the detection vehicle within the preset time period is greater than the preset number of network connection interruptions and registration with the base station fails, indicating that the previous network optimization did not completely solve the network failure problem. The base station for network access of the detection vehicle can be switched to other base stations around the detection vehicle to which the detection vehicle can connect.

[0137] For example, the optimized network of the detection vehicle is analyzed based on the network optimization model to determine if the problem after the previous network optimization has not been completely resolved. For example, if the network failure problem determined in the initial analysis of the detection vehicle's network is frequent network connection interruptions or failure to connect to a base station, the detection vehicle's network connection is connected to a base station with higher network signal strength and lower network load around the detection vehicle. Then, the optimized network of the detection vehicle is continuously monitored to determine if the network failure problem after optimization is still frequent network connection interruptions or failure to connect to a base station. The base station connected to the detection vehicle's network is continuously switched until the network problem is completely resolved.

[0138] In some embodiments, the network optimization method provided by the embodiments of the present disclosure further includes:

[0139] Synchronously detect the policy version information of the vehicle and the cloud server.

[0140] The strategy version information includes at least one of the vehicle version information of the detection vehicle, the version information of the network optimization model, and the network optimization strategy.

[0141] Specifically, when the network of the inspection vehicle is effectively improved, the inspection vehicle will synchronously upload the locally packaged logs (including relevant information of the inspection vehicle network analysis process and network optimization status) and the adjusted network optimization strategy to the cloud server, and upload the strategy version information to avoid the problem of local strategy loss or strategy version rollback due to network anomalies or other reasons.

[0142] It is understandable that when the local policy of the detection vehicle is lost or the policy version is rolled back, the present disclosure can actively send the latest network optimization policy to the detection vehicle through the cloud server. The detection vehicle updates and optimizes the network optimization model based on the latest network optimization policy, so that the network optimization model deployed on the detection vehicle can continuously adapt to new network scenarios and problems.

[0143] The above mainly introduces the solution provided by the embodiment of the present disclosure from the perspective of method. In order to realize the above functions, the network optimization device or electronic device includes a hardware structure and / or software module corresponding to the execution of each function. It should be easy for those skilled in the art to realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0144] The embodiments of the present disclosure can exemplarily divide the functional modules of the network optimization device or electronic device according to the above method. For example, the network optimization device or electronic device can include various functional modules corresponding to the various functional divisions, or two or more functions can be integrated into one processing module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiments of the present disclosure is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0145] Figure 8 FIG. 1 is a block diagram of a network optimization device according to an exemplary embodiment. Figure 8 The network optimization device 800 includes: a communication module 801 and a processing module 802; the communication module 801 is used to obtain the location environment data of the detection vehicle; the location environment data includes: the detection vehicle location and the environmental information of the detection vehicle location; the processing module 802 is used to input the location environment data into the network optimization model to obtain the network fault type of the detection vehicle and the network optimization strategy corresponding to the network fault type; the processing module 802 is also used to optimize the network of the detection vehicle according to the network optimization strategy.

[0146] In one possible implementation, the network optimization model is trained in the following manner:

[0147] Processing module 802 is specifically used to obtain a training sample set; the training sample set includes multiple training samples and a label for each training sample; the training sample includes sample features of a sample vehicle; the sample features are used to represent the environmental information and network status of the sample vehicle; the label of the training sample includes: the network fault type of the sample vehicle and the network optimization strategy of the sample vehicle; processing module 802 is specifically used to train an initial network optimization model based on the training sample set to obtain a network optimization model.

[0148] In one possible implementation, the sample features are obtained in the following manner:

[0149] Processing module 802 is specifically used to collect sample data corresponding to sample features based on the collection frequency; the sample data includes environmental information and network status of the sample vehicle's location; the collection frequency is negatively correlated with the network status; the sample data is preprocessed and feature extracted to obtain sample features; data preprocessing includes data cleaning and denoising and / or normalization processing.

[0150] In one possible implementation, the network optimization strategy includes: switching the network access base station of the detection vehicle to the first base station, raising the network signal receiving and transmitting position of the network antenna of the detection vehicle, adjusting the network standard of the detection vehicle, and adjusting the network bandwidth resource allocation ratio of the application of the detection vehicle; wherein, the first base station satisfies at least one of the following conditions: the detection vehicle detects that the signal strength of the first base station is greater than the preset strength, the detection vehicle is in the coverage range of the first base station, and the network load of the first base station is lower than the preset load.

[0151] In one possible implementation, the processing module 802 is specifically used to: obtain a network optimization result after optimizing the network of the detection vehicle; the network optimization result is used to indicate the difference between the network performance after optimizing the network of the detection vehicle and the preset network performance; when the network optimization result is used to indicate that the difference between the network performance after optimizing the network of the detection vehicle and the preset network performance is greater than the preset difference, obtain network optimization analysis data; and determine the network problem location result of the detection vehicle based on the network optimization analysis data.

[0152] In one possible implementation, the processing module 802 is specifically used to: obtain network performance parameters after optimizing the network of the detection vehicle; the network performance parameters include: network signal strength, RSSI, RSRP, RSRQ, SINR, data transmission rate, delay, packet loss rate, TCP retransmission rate and at least one of the network connection status; determine the network optimization result based on the network performance parameters and the difference between the network performance indicators.

[0153] In a possible implementation, the network optimization analysis data includes: location environment data during the process of optimizing and detecting the network of the vehicle, optimization logs during the process of optimizing and detecting the network of the vehicle, and network optimization strategies.

[0154] In one possible implementation, the processing module 802 is specifically used to: switch the base station of the network access of the detection vehicle to a second base station when the result of locating the network problem is that the number of network connection interruptions of the detection vehicle within a preset time period is greater than the preset number of network connection interruptions and registration with the base station fails; and the detection vehicle is within the coverage of the second base station.

[0155] In a possible implementation, the processing module 802 is further used to: synchronously detect the policy version information of the vehicle and the cloud server; the policy version information includes at least one of the vehicle version information of the detected vehicle, the version information of the network optimization model, and the network optimization policy.

[0156] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0157] Figure 9 FIG. 1 is a block diagram of an electronic device according to an exemplary embodiment. Figure 9 As shown, the electronic device 900 includes but is not limited to: a processor 901 and a memory 902 .

[0158] The memory 902 is configured to store executable instructions of the processor 901. It is understood that the processor 901 is configured to execute instructions to implement the network optimization method in the above embodiment.

[0159] It should be noted that those skilled in the art can understand that Figure 9 The electronic device structure shown in the figure does not limit the electronic device, and the electronic device may include Figure 9 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.

[0160] The processor 901 is the control center of the electronic device 900. It connects the various parts of the entire electronic device 900 using various interfaces and lines. By running or executing software programs and / or modules stored in the memory 902 and calling data stored in the memory 902, it performs various functions of the electronic device 900 and processes data, thereby monitoring the electronic device 900 as a whole. The processor 901 may include one or more processing units. Optionally, the processor 901 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly handles wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 901.

[0161] The memory 902 can be used to store software programs and various data. The memory 902 may primarily include a program storage area and a data storage area. The program storage area may store an operating system, application programs required by at least one functional module (such as the processing module 702), and the like. Furthermore, the memory 902 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0162] In an exemplary embodiment, a computer-readable storage medium including instructions is further provided, such as a memory 902 including instructions. The above instructions can be executed by the processor 901 of the electronic device 900 to implement the network optimization method in the above embodiment.

[0163] In actual implementation, Figure 8 The functions of the communication module 801 and the processing module 802 in Figure 9 The processor 901 in the embodiment calls the computer program stored in the memory 902. The specific execution process can be referred to the description of the network optimization method in the above embodiment, which will not be repeated here.

[0164] Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0165] In an exemplary embodiment, the present disclosure further provides a computer program product including one or more instructions, which can be executed by the processor 901 of the electronic device 900 to implement the network optimization method in the above embodiment.

[0166] It should be noted that when the instructions in the above-mentioned computer-readable storage medium or one or more instructions in the computer program product are executed by the processor of the electronic device, the various processes of the above-mentioned network optimization method embodiment are implemented, and the same technical effect as the above-mentioned network optimization method can be achieved. To avoid repetition, they will not be repeated here.

[0167] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete the full classification or partial functions described above.

[0168] In the several embodiments provided in the present disclosure, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0169] The units described as separate components may or may not be physically separate, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0170] In addition, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0171] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present disclosure is essentially or the part that contributes to the prior art or the full classification part or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for enabling a device (which can be a single-chip microcomputer, chip, etc.) or a processor to execute the full classification part or part of the steps of the various embodiments of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks or optical disks.

[0172] The above are only specific embodiments of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Any changes or replacements within the technical scope disclosed in the present disclosure should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. A network optimization method, characterized in that: Applied to vehicle inspection, including: Acquire the position environment data of the detection vehicle; the position environment data includes: the detection vehicle position and the environment information of the detection vehicle position; Inputting the location environment data into a network optimization model to obtain a network fault type of the detection vehicle and a network optimization strategy corresponding to the network fault type; The network for detecting vehicles is optimized according to the network optimization strategy.

2. The method according to claim 1, characterized in that The network optimization model is trained in the following way: Obtaining a training sample set; the training sample set includes multiple training samples and a label for each training sample; the training sample includes sample features of a sample vehicle; the sample features are used to represent environmental information and network status of the location of the sample vehicle; The labels of the training samples include: the network fault type of the sample vehicle and the network optimization strategy of the sample vehicle; An initial network optimization model is trained based on the training sample set to obtain the network optimization model.

3. The method according to claim 2, characterized in that The sample features are obtained in the following way: Collecting sample data corresponding to the sample feature based on a collection frequency; the sample data includes environmental information and network status of the location of the sample vehicle; the collection frequency is negatively correlated with the network status; The sample data is preprocessed and features are extracted to obtain the sample features; the data preprocessing includes data cleaning and denoising and / or normalization processing.

4. The method according to claim 1, wherein The network optimization strategy includes: Switching the network access base station of the detection vehicle to the first base station, raising the network signal receiving and transmitting position of the network antenna of the detection vehicle, adjusting the network standard of the detection vehicle, and adjusting the network bandwidth resource allocation ratio of the application of the detection vehicle; Among them, the first base station meets at least one of the following conditions: the signal strength of the first base station detected by the detection vehicle is greater than a preset strength, the detection vehicle is in the coverage range of the first base station, and the network load of the first base station is lower than a preset load.

5. The method according to claim 4, characterized in that After optimizing the network for detecting vehicles according to the network optimization strategy, the method further includes: Obtaining a network optimization result after optimizing the network of the detection vehicle; the network optimization result is used to indicate the difference between the network performance after optimizing the network of the detection vehicle and the preset network performance; When the network optimization result indicates that a difference between network performance after optimizing the network of the detection vehicle and a preset network performance is greater than a preset difference, obtaining network optimization analysis data; A network problem locating result of the detected vehicle is determined based on the network optimization analysis data.

6. The method according to claim 5, characterized in that The obtaining of a network optimization result after optimizing the network of the detection vehicle includes: Obtaining network performance parameters after optimizing the network of the detection vehicle; the network performance parameters including: network signal strength, received signal strength indicator RSSI, reference signal received power RSRP, reference signal received quality RSRQ, signal to interference plus noise ratio SINR, data transmission rate, delay, packet loss rate, transmission control protocol TCP retransmission rate and network connection status; The network optimization result is determined according to the network performance parameter and the difference between the network performance indicators.

7. The method according to claim 5, characterized in that The network optimization analysis data includes: location environment data during the process of optimizing the network of the detection vehicle, optimization logs during the process of optimizing the network of the detection vehicle, and the network optimization strategy.

8. The method according to claim 5, characterized in that After determining the network problem location result of the detected vehicle according to the network optimization analysis data, the method further includes: When the network problem locating result is that the number of network connection interruptions of the detection vehicle within a preset time period is greater than the preset number of network connection interruptions and registration with the base station fails, the base station of the network access of the detection vehicle is switched to a second base station; the detection vehicle is within the coverage of the second base station.

9. The method according to any one of claims 1 to 8, characterized in that Also includes: Synchronize the policy version information of the detection vehicle and the cloud server; the policy version information includes at least one of the vehicle version information of the detection vehicle, the version information of the network optimization model and the network optimization policy.

10. A network optimization device, characterized in that: The network optimization device is used for detecting vehicles, and the network optimization device includes: a communication unit and a processing unit; The communication unit is used to obtain the position environment data of the detection vehicle; the position environment data includes: the detection vehicle position and the environment information of the detection vehicle position; The processing unit is configured to input the location environment data into a network optimization model to obtain a network fault type of the detection vehicle and a network optimization strategy corresponding to the network fault type; The processing unit is further configured to optimize the network for detecting vehicles according to the network optimization strategy.

11. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the network optimization method according to any one of claims 1 to 9.

12. A vehicle, characterized in that: The vehicle is used to implement the network optimization method according to any one of claims 1 to 9.

Images