Method and related equipment for pre-storing network data in a vehicle before entering a signal blind spot

Abstract

The present application discloses a method for pre-storing network data in a vehicle before entering a signal blind spot and related equipment, and relates to the field of vehicle-mounted communication technology. The method for pre-storing network data in a vehicle before entering a signal blind spot includes obtaining the vehicle navigation route, determining the corresponding base station signal distribution map and navigation route historical signal data; predicting each predicted signal blind spot in the vehicle navigation route through a preset blind spot prediction model based on the base station signal distribution map and the navigation route historical signal data; if it is detected that the vehicle is about to enter the predicted signal blind spot, obtaining the vehicle's current driving information and predicting the duration of the signal blind spot, and pre-storing the network data in the vehicle according to the signal blind spot duration through preset pre-stored rules. Before the vehicle approaches the signal blind spot, the present application predicts the signal blind spot distribution based on the vehicle navigation route, and pre-stores network data accordingly, thereby improving the reliability of network data in a blind spot environment.

Description

Technical Field

[0001] The present application relates to the field of vehicle-mounted communication technology, and in particular to a method and related equipment for pre-storing network data in a vehicle before entering a signal blind spot. Background Art

[0002] With the development of vehicle-to-everything (V2X) technology, in-vehicle wireless networks have become the core of intelligent transportation systems, enabling data exchange between vehicles and the cloud, infrastructure, and other vehicles. However, existing technologies still have some shortcomings. For example, when a vehicle enters a signal blind spot, traditional technologies rely on offline map caches and cannot update dynamic traffic information such as accidents and congestion in real time. This results in the navigation system being unable to provide accurate route suggestions within these blind spots. In addition, when the network is interrupted, users' applications often need to manually reconnect and lack the ability to maintain an "online" state during network outages, resulting in a poor user experience. Finally, existing resource allocation strategies are usually fixed and fail to flexibly adjust according to the duration of the blind spot and the specific needs of users, resulting in poor network data reliability within vehicles in blind spot environments.

[0003] Therefore, how to improve the reliability of in-vehicle wireless networks in blind area environments is an urgent problem to be solved. Summary of the Invention

[0004] The main purpose of this application is to provide a method and related equipment for pre-storing network data in a vehicle before entering a signal blind spot, aiming to solve the technical problem of poor reliability of the vehicle-mounted wireless network in a blind spot environment.

[0005] To achieve the above objectives, the present application proposes a method for pre-storing network data in a vehicle before entering a signal blind spot, the method comprising:

[0006] Obtain the vehicle navigation route, determine the corresponding base station signal distribution map and navigation route historical signal data;

[0007] According to the base station signal distribution map and the historical signal data of the navigation route, each predicted signal blind spot in the vehicle navigation route is predicted by a preset blind spot prediction model;

[0008] If it is detected that a vehicle is about to enter the predicted signal blind spot, the vehicle's current driving information is obtained and the duration of the signal blind spot is predicted. Based on the duration of the signal blind spot, the network data in the vehicle is pre-stored using preset pre-stored rules.

[0009] In one embodiment, the method for predicting each predicted signal blind spot in the vehicle navigation route based on the base station signal distribution map and the navigation route historical signal data using a preset blind spot prediction model includes:

[0010] By using a preset long short-term memory neural network model, time series feature extraction is performed on the navigation history signal data to obtain the historical signal time series feature;

[0011] Using a preset convolutional neural network model, spatial feature extraction is performed on the base station signal distribution map to obtain current spatial vector features;

[0012] Obtaining real-time weather information and real-time topographic information of the vehicle's navigation route;

[0013] The real-time weather information, the real-time terrain information, the historical signal time series characteristics and the current space vector characteristics are input into a blind spot prediction model to predict each predicted signal blind spot on the vehicle navigation route.

[0014] In one embodiment, before the step of inputting the real-time weather information, the real-time terrain information, the historical signal time series features, and the current spatial vector features into the blind spot prediction model and predicting each predicted signal blind spot on the vehicle navigation route, the step includes:

[0015] Obtain historical signal time series samples, base station space vector samples, and signal blind area distribution labels;

[0016] Projecting the historical signal time series samples and the base station space vector samples to the same dimension, and generating a time-space weighted feature representation based on a preset attention matrix model;

[0017] Obtain the influencing factors of severe weather and severe landforms;

[0018] generating a severe condition weight according to the severe weather influencing factor and the severe landform influencing factor;

[0019] Inputting the time-space weighted feature representation and the harsh condition weight into the signal blind spot prediction model to be trained, predicting the signal blind spot, and obtaining a signal blind spot prediction result;

[0020] Comparing the signal blind spot prediction result with the signal blind spot distribution label to obtain a prediction error value;

[0021] If the prediction error value does not meet the preset threshold, the hyperparameters of the attention matrix model are adjusted, and the step of projecting the historical signal time series samples and the base station space vector samples to the same dimension is returned to generate a time-space weighted feature representation according to the preset attention matrix model until the prediction error value meets the preset threshold and the prediction signal blind spot is output.

[0022] In one embodiment, the steps of obtaining the vehicle's current driving information and predicting the duration of the signal blind spot, and pre-storing the vehicle's network data according to the signal blind spot duration using a preset pre-stored rule include:

[0023] Get the list of active background applications in the vehicle and the remaining local storage space;

[0024] Determining the network data pre-storage priority of background active applications in the vehicle based on a preset application pre-storage priority list and the background active application list;

[0025] Allocate multimedia cache data space for each background active application according to the blind zone duration, the remaining local storage space, and the network data pre-storage priority;

[0026] Acquire and pre-store network data into the multimedia cache data space.

[0027] In one embodiment, the step of acquiring and pre-storing network data in the multimedia cache data space includes:

[0028] Pre-storing real-time traffic event information of the vehicle navigation route based on the blind spot duration;

[0029] When entering a signal blind spot, converting the real-time traffic event information into a traffic event mark supported by an offline map;

[0030] Adding the traffic event mark to the offline map;

[0031] Obtain the acceleration direction, vehicle speed and driving direction of the vehicle to obtain the driving information of the vehicle in the blind spot;

[0032] In combination with the vehicle navigation route and the blind spot vehicle driving information, the vehicle position is updated in the offline map in real time;

[0033] When it is detected that the vehicle position reaches the traffic event mark, a preset reminder solution is executed.

[0034] In one embodiment, the step of pre-storing the in-vehicle network data according to the signal blind zone duration using a preset pre-stored rule includes:

[0035] Determine active target anti-disconnection applications based on the user's preset anti-disconnection application list;

[0036] Sending simulated first protocol response data to the target anti-disconnection application through a pseudo-handshake mechanism;

[0037] Recording protocol request data of the target anti-disconnection application;

[0038] When the network signal strength recovers to a preset threshold, the protocol request data is uploaded, and the second protocol response data responded by the server is obtained to update the first protocol response data.

[0039] In addition, to achieve the above-mentioned purpose, the present application also proposes a vehicle-in-vehicle network data pre-storage device before entering a signal blind spot, the vehicle-in-vehicle network data pre-storage device before entering a signal blind spot comprising:

[0040] An acquisition module is used to obtain the vehicle navigation route and determine the corresponding base station signal distribution map and navigation route historical signal data;

[0041] A prediction module, configured to predict each predicted signal blind spot in the vehicle navigation route based on the base station signal distribution map and the historical signal data of the navigation route using a preset blind spot prediction model;

[0042] The pre-storage module is used to obtain the vehicle's current driving information and predict the duration of the signal blind spot if it is detected that the vehicle is about to enter the predicted signal blind spot, and pre-store the network data in the vehicle according to the preset pre-storage rules based on the duration of the signal blind spot.

[0043] In addition, to achieve the above-mentioned purpose, the present application also proposes a device for pre-storing network data in a vehicle before entering a signal blind spot, the device comprising: a memory, a processor, and a computer program stored on the memory and runnable on the processor, the computer program being configured to implement the steps of the method for pre-storing network data in a vehicle before entering a signal blind spot as described above.

[0044] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the method for pre-storing network data in the vehicle before entering the signal blind spot as described above are implemented.

[0045] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the method for pre-storing network data in the vehicle before entering the signal blind spot as described above.

[0046] One or more technical solutions proposed in this application have at least the following technical effects:

[0047] Compared with the related art, in the prior art, when the in-vehicle navigation system enters a signal blind spot, it only relies on pre-downloaded offline maps to provide static route navigation; when the vehicle exits the signal blind spot, the navigation application needs to be manually refreshed to reconnect to the network due to network disconnection, and the multimedia player is interrupted due to insufficient cache and needs to wait for the network to recover and then reload, resulting in frequent service interruptions and operation redundancy during driving in the blind spot environment, resulting in poor reliability of the in-vehicle wireless network. In comparison, the present application obtains the vehicle navigation route, determines the corresponding base station signal distribution map and navigation route historical signal data; based on the base station signal distribution map and the navigation route historical signal data, a preset blind spot prediction model is used to predict each predicted signal blind spot in the vehicle navigation route; if it is detected that the vehicle is about to enter the predicted signal blind spot, the vehicle's current driving information is obtained and the signal blind spot duration is predicted, and based on the signal blind spot duration, the vehicle's network data is pre-stored according to the preset pre-stored rules. The present application mainly includes three core components: obtaining the vehicle navigation route, predicting the blind spot distribution, and pre-storing the in-vehicle wireless network data according to the blind spot duration. The acquisition of the vehicle's navigation route provides the entire system with basic information about the driving path. The combination of base station signal distribution maps and historical navigation route signal data helps accurately predict the distribution of blind spots, predicting the duration of the blind spot the vehicle will enter, and pre-storing the required onboard wireless network data in the blind spot based on preset pre-stored rules to ensure that relevant application services can still be provided even when the network signal is poor. The operating principle is that before the vehicle approaches a signal blind spot, it predicts the length of the blind spot by analyzing real-time and historical signal data, and pre-loads the necessary network data accordingly. This allows accurate navigation information and other application services to be provided immediately after entering the blind spot, avoiding frequent operations and delayed information updates caused by network interruptions, and improving the reliability of network data in blind spot environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0050] Figure 1 A flowchart illustrating a method for pre-storing network data in a vehicle before entering a signal blind spot according to a first embodiment of the present invention;

[0051] Figure 2A flowchart illustrating a second embodiment of the method for pre-storing network data in a vehicle before entering a signal blind spot is provided in this application;

[0052] Figure 3 A flowchart illustrating a third embodiment of the method for pre-storing network data in a vehicle before entering a signal blind spot is provided in this application;

[0053] Figure 4 This is a schematic diagram of the module structure of the network data pre-storage device in a vehicle before entering a signal blind area according to an embodiment of the present application;

[0054] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the method for pre-storing network data in a vehicle before entering a signal blind spot in an embodiment of the present application.

[0055] 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 DESCRIPTION

[0056] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0057] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0058] The main solutions of the embodiments of this application are:

[0059] Obtain the vehicle navigation route, determine the corresponding base station signal distribution map and navigation route historical signal data;

[0060] According to the base station signal distribution map and the historical signal data of the navigation route, each predicted signal blind spot in the vehicle navigation route is predicted by a preset blind spot prediction model;

[0061] If it is detected that a vehicle is about to enter the predicted signal blind spot, the vehicle's current driving information is obtained and the duration of the signal blind spot is predicted. Based on the duration of the signal blind spot, the network data in the vehicle is pre-stored using preset pre-stored rules.

[0062] In this embodiment, the present application uses the network data pre-storage device in the vehicle before entering the signal blind spot as the execution body. For the convenience of expression, it is specifically described below as "device".

[0063] When a vehicle enters a signal blind spot, existing technologies rely on offline map caching, which is unable to update dynamic traffic information such as accidents and congestion in real time. This results in the navigation system being unable to provide accurate route suggestions within these blind spots. Furthermore, when the network is interrupted, user applications often need to be manually reconnected, lacking the ability to maintain an "online" state during a network outage, resulting in a poor user experience. Finally, existing resource allocation strategies are typically fixed and fail to flexibly adjust based on the duration of the blind spot and the specific needs of users, resulting in poor reliability of in-vehicle wireless networks in blind spots.

[0064] The present application provides a solution, which determines the corresponding base station signal distribution map and navigation route historical signal data by obtaining the vehicle navigation route; based on the base station signal distribution map and the navigation route historical signal data, the preset blind spot prediction model is used to predict each predicted signal blind spot in the vehicle navigation route; if it is detected that the vehicle is about to enter the predicted signal blind spot, the vehicle's current driving information is obtained and the duration of the signal blind spot is predicted, and based on the duration of the signal blind spot, the vehicle's network data is pre-stored according to the preset pre-stored rules. The present application mainly includes three core components: obtaining the vehicle navigation route, predicting the blind spot distribution, and pre-storing the vehicle-mounted wireless network data according to the blind spot duration. The acquisition of the vehicle navigation route provides the basic information of the driving path for the entire system; the combination of the base station signal distribution map and the navigation route historical signal data helps to accurately predict the blind spot distribution; predict the duration of the blind spot that the vehicle is about to enter; and pre-store the required vehicle-mounted wireless network data in the blind spot according to the preset pre-stored rules to ensure that the relevant application services can still be provided when the network signal is poor. The working principle is to predict the length of the blind spot by analyzing real-time and historical signal data before the vehicle approaches the blind spot, and load the necessary network data in advance accordingly, so that accurate navigation information and other application services can be provided immediately after entering the blind spot, avoiding frequent operations and information update delays caused by network interruptions, and improving the reliability of network data in the blind spot environment.

[0065] Based on this, the embodiment of the present application provides a method for pre-storing network data in a vehicle before entering a signal blind area, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for pre-storing network data in a vehicle before entering a signal blind spot.

[0066] In this embodiment, the method for pre-storing network data in a vehicle before entering a signal blind spot includes steps S10 to S30:

[0067] Step S10, obtaining the vehicle navigation route, determining the corresponding base station signal distribution map and navigation route historical signal data;

[0068] It should be noted that a vehicle navigation route is the path a vehicle takes from its starting point to its destination, typically provided by an onboard navigation system. It includes the route's geographic coordinates and travel direction. A base station signal distribution map is a cloud-stored map of base station signal strength, used to describe signal coverage in different areas. Historical navigation route signal data is historical signal strength data collected along the route and used to assist in blind spot prediction.

[0069] It is understandable that, referring to Figure 2 ,Suppose a car plans to pass through a mountain road. Since the base station signal fails to cover the entire mountain road, there is a signal blind spot on the mountain road.

[0070] The device extracts the vehicle's driving route from the on-board navigation system, including the starting point, end point, path line and key nodes along the way (such as tunnels and mountain roads).

[0071] The device obtains a signal distribution map of base stations along the driving route from the cloud according to the driving route of the vehicle.

[0072] It is understandable that the device marks areas with weak signal coverage based on the signal distribution map, which can be used for subsequent signal blind spot prediction.

[0073] The device retrieves historical vehicle driving data from a cloud or locally stored vehicle driving history database. The device extracts signal strength records when vehicles pass through the same or similar road sections, providing data support for subsequent verification of the location and length of signal blind spots.

[0074] It can be understood that by obtaining the vehicle navigation route and determining the corresponding base station signal distribution map and navigation route historical signal data, data support can be provided for subsequent prediction of signal blind spots, thereby improving the reliability of the prediction results.

[0075] Step S20, predicting each predicted signal blind spot in the vehicle navigation route using a preset blind spot prediction model based on the base station signal distribution map and the navigation route historical signal data;

[0076] It should be noted that the blind spot prediction model includes but is not limited to a prediction model based on a machine learning algorithm, which is used to analyze the base station signal distribution map and the historical signal data of the navigation route to predict the blind spot location on the navigation route.

[0077] Imagine a car traveling through a mountainous road and a tunnel. Mountainous roads and tunnels have poor signal coverage, resulting in multiple blind spots. Before entering a blind spot, the vehicle's in-vehicle network data pre-storage device performs the following steps to ensure reliable service within the blind spot.

[0078] The device extracts the vehicle's route information from the on-board navigation system, including the starting point, end point, path line, key nodes along the way (such as mountainous sections and tunnels), and expected driving speed.

[0079] The device inputs the vehicle's planned route information into a preset blind spot prediction model. This model combines base station signal distribution maps and historical signal data to predict the location of blind spots along the navigation route. For example, if historical records show a signal disconnection on a mountain road along a mountainside along the navigation route, the corresponding signal disconnection point is predicted as a candidate blind spot. Based on the base station distribution corresponding to the navigation route, the model calculates high-confidence areas in the blind spot, preparing for the subsequent preloading step.

[0080] In a feasible embodiment, the method for predicting each predicted signal blind spot in the vehicle navigation route based on the base station signal distribution map and the navigation route historical signal data by using a preset blind spot prediction model includes:

[0081] By using a preset long short-term memory neural network model, time series feature extraction is performed on the navigation history signal data to obtain the historical signal time series feature;

[0082] Using a preset convolutional neural network model, spatial feature extraction is performed on the base station signal distribution map to obtain current spatial vector features;

[0083] Obtaining real-time weather information and real-time topographic information of the vehicle's navigation route;

[0084] The real-time weather information, the real-time terrain information, the historical signal time series characteristics and the current space vector characteristics are input into a blind spot prediction model to predict each predicted signal blind spot on the vehicle navigation route.

[0085] It should be noted that the base station signal distribution map includes but is not limited to the base station signal strength distribution map stored in the cloud, which is used to describe the signal coverage of different areas and also includes real-time updated signal strength data.

[0086] The historical signal data of the vehicle navigation route includes, but is not limited to, the signal strength data recorded during the vehicle's historical driving process, and also includes information such as the location and duration of signal blind spots.

[0087] For example, a two-branch network is constructed to extract temporal and spatial features respectively:

[0088] Time branching: Use LSTM to process historical signal sequences and capture temporal patterns such as traffic tides and base station loads.

[0089] Spatial branch: CNN and graph neural network (GNN) are used to fuse base station distribution and terrain three-dimensional data to model the physical attenuation of signal propagation.

[0090] Cross-attention layer: Through the attention matrix, temporal features are used as queries and spatial features as key-values, dynamically focusing on the most relevant spatial regions at the current moment. For example, during heavy rain, the status of nearby base stations is prioritized.

[0091] Adding a parallel subnetwork:

[0092] Weather classification head: predicts the current weather level based on spatial features and optimizes feature encoding through backpropagation.

[0093] Landform recognition head: Analyzes terrain risks through elevation maps and outputs the probability of dangerous landforms such as landslides or canyons.

[0094] The loss functions of these two sub-networks serve as auxiliary tasks to enhance the model's sensitivity to harsh environments.

[0095] It can be understood that the device predicts the distribution of blind spots on the navigation route by combining real-time and historical spatiotemporal data.

[0096] In a feasible implementation manner, before the step of inputting the real-time weather information, the real-time terrain information, the historical signal time series features, and the current spatial vector features into the blind spot prediction model and predicting each predicted signal blind spot on the vehicle navigation route, the step includes:

[0097] Obtain historical signal time series samples, base station space vector samples, and signal blind area distribution labels;

[0098] Projecting the historical signal time series samples and the base station space vector samples to the same dimension, and generating a time-space weighted feature representation based on a preset attention matrix model;

[0099] Obtain the influencing factors of severe weather and severe landforms;

[0100] generating a severe condition weight according to the severe weather influencing factor and the severe landform influencing factor;

[0101] Inputting the time-space weighted feature representation and the harsh condition weight into the signal blind spot prediction model to be trained, predicting the signal blind spot, and obtaining a signal blind spot prediction result;

[0102] Comparing the signal blind spot prediction result with the signal blind spot distribution label to obtain a prediction error value;

[0103] If the prediction error value does not meet the preset threshold, the hyperparameters of the attention matrix model are adjusted, and the step of projecting the historical signal time series samples and the base station space vector samples to the same dimension is returned to generate a time-space weighted feature representation according to the preset attention matrix model until the prediction error value meets the preset threshold and the prediction signal blind spot is output.

[0104] It should be noted that historical signal time series samples refer to the chronologically recorded network signal strength data sequences of a vehicle during its past travel. These samples reflect the vehicle's signal reception conditions at different points in time and locations. By analyzing these historical signal time series samples, we can extract patterns in signal strength over time, providing temporal features to support the prediction of future signal blind spots.

[0105] Base station spatial vector samples refer to the location information of base stations related to the vehicle's navigation route, expressed as vectors. These vectors typically include information such as the base station's geographic coordinates (such as longitude and latitude) and its coverage area. Base station spatial vector samples describe the distribution of base stations along the vehicle's route. By extracting spatial features, the signal coverage area and potential signal blind spots can be clearly identified.

[0106] Blind spot distribution labels refer to pre-labeled locations of blind spots along a vehicle's navigation route. These labels are typically derived from historical data or field testing and indicate areas with insufficient signal coverage. Blind spot distribution labels serve as the "answer" to the training data, supervising the learning process and helping the model learn how to accurately identify blind spots.

[0107] A time-space weighted feature representation is a feature vector derived from a weighted fusion of time series features (historical signal timing features) and spatial features (base station spatial vector features) through an attention mechanism. This representation emphasizes the more important temporal and spatial features in signal blind spot prediction. By generating a time-space weighted feature representation, the model can better comprehensively consider the impact of temporal and spatial factors on signal coverage, thereby improving the accuracy of signal blind spot prediction.

[0108] The severe weather impact factor quantifies the degree to which severe weather (such as heavy rain, snow, and dense fog) affects signal transmission. This factor is typically calculated based on factors such as weather type and intensity. Severe weather can affect both signal transmission and reception. By incorporating the severe weather impact factor, the model can more accurately predict the distribution of signal blind spots under adverse weather conditions.

[0109] The adverse terrain impact factor quantifies the degree to which complex terrain (such as valleys, tunnels, and densely populated areas) affects signal transmission. This factor is typically calculated based on factors such as terrain type and elevation differences. Complex terrain can block or weaken signals. By incorporating the adverse terrain impact factor, the model can more accurately predict the distribution of signal blind spots in complex terrain conditions.

[0110] The adverse conditions weight is a weighted adjustment applied to the input features of the signal blind spot prediction model, taking into account the impact of severe weather and terrain. This weight is used to highlight the uncertainty of signal coverage under adverse conditions. The adverse conditions weight enables the model to prioritize signal variations under adverse weather and complex terrain when predicting blind spots, thereby improving prediction robustness.

[0111] The prediction error value refers to the degree of discrepancy between the blind spot prediction result and the actual blind spot distribution label. This value is typically measured by calculating a distance (such as Euclidean distance or cross-entropy) between the predicted value and the true value. The prediction error value is used to evaluate the performance of the blind spot prediction model. By comparing the prediction error value with a preset threshold, we can determine whether the model has achieved the expected prediction accuracy.

[0112] The attention matrix model is a neural network model based on the attention mechanism that performs weighted processing on input feature data. It dynamically assigns importance weights to different features by calculating the correlation between input features. The attention matrix model automatically learns which features are most important for predicting signal blind spots, thereby generating more representative spatiotemporal weighted feature representations and improving the model's predictive performance.

[0113] The preset threshold is a set value used to determine whether the prediction error meets the required level during blind spot prediction. This threshold is typically determined based on the actual application scenario and the required prediction accuracy. The preset threshold controls the training process of the blind spot prediction model. If the prediction error does not meet the preset threshold, the model will continue to adjust parameters until the error meets the required level, thereby ensuring the model's prediction accuracy.

[0114] For example, a multi-source data input system is first constructed, integrating historical vehicle navigation signal time series data, base station 3D topology information, and real-time meteorological and geomorphological environmental data. For temporal features, a bidirectional memory network is used to extract the temporal evolution of signal strength and, combined with an attention mechanism, to focus on key time nodes. For spatial features, a graph neural network is used to model the coordinated coverage relationships between base stations. Three-dimensional terrain data is then integrated to construct a lightweight electromagnetic propagation model to calculate the impact of terrain obstruction on signal attenuation. An innovative spatiotemporal cross-attention mechanism is designed to dynamically guide the spatial focus area using temporal features, automatically increasing the attention weight of neighboring base stations in adverse weather conditions. A harsh environment perception module is introduced, which dynamically adjusts the fusion ratio of spatiotemporal features by training weather classification and terrain recognition auxiliary tasks in parallel. This improves the sensitivity of signal attenuation prediction in areas with sudden terrain changes during heavy rain. A phased training strategy is employed, first pre-training the basic feature extractor through signal reconstruction tasks, then jointly optimizing the main prediction network and auxiliary classifiers using a multi-task loss function. Finally, adversarial example generation is used to enhance model robustness. The model outputs a high-precision blind spot probability distribution map, which, combined with real-time positioning information, triggers graded warnings and supports low-latency inference in edge computing architectures. This solution innovatively combines physical propagation models with deep learning to achieve reliable prediction and adaptive optimization of navigation blind spots in complex environments.

[0115] It's important to note that the device dynamically optimizes the prediction model by adjusting the weights for inclement weather and terrain in real time to ensure accurate predictions. For example, when driving in rainy conditions, the device increases the weight for inclement weather to improve the accuracy of signal attenuation predictions. By comparing predicted results with actual labels, the device continuously adjusts model parameters to ensure prediction errors remain within acceptable limits. This high-precision prediction effectively avoids service interruptions caused by model errors.

[0116] Step S30: If it is detected that the vehicle is about to enter the predicted signal blind spot, the current driving information of the vehicle is obtained and the duration of the signal blind spot is predicted. Based on the duration of the signal blind spot, the network data in the vehicle is pre-stored according to the preset pre-stored rules.

[0117] It should be noted that current vehicle driving information refers to data related to the vehicle's driving status collected in real time during driving, including but not limited to the vehicle's speed, acceleration, driving direction, and geographic location. By obtaining the vehicle's current driving information, it is possible to more accurately predict the time when the vehicle enters a signal blind spot and its driving trajectory within the blind spot, thereby providing a basis for predicting the duration of the signal blind spot.

[0118] The duration of a signal blind spot refers to the length of time between a vehicle entering and exiting a signal blind spot. This duration is affected by factors such as vehicle speed, direction, and the extent of the signal blind spot. The duration of a signal blind spot is a key parameter in determining the vehicle's network data pre-storage strategy. The amount and type of pre-stored network data must be appropriately allocated based on the duration of the signal blind spot to ensure that the vehicle can function properly within the signal blind spot.

[0119] Pre-set pre-storage rules are a set of pre-defined rules that determine network data pre-storage strategies based on the vehicle's driving status, the characteristics of the signal blind spot, and the needs of in-vehicle network applications. These rules guide the selection of pre-stored network data before the vehicle enters a signal blind spot, including the type of data to be pre-stored (such as video, audio, and text messages), the priority of the pre-stored data, and the amount of pre-stored data, ensuring the best possible network experience within the signal blind spot.

[0120] In-vehicle network data refers to data that various network applications within the vehicle (such as navigation systems, multimedia entertainment systems, and connected car applications) require from the network during operation. Pre-storing in-vehicle network data ensures that these applications can continue to operate normally even when the vehicle enters a signal blind spot, unaffected by network signal interruptions. Pre-stored data can include map data, multimedia content, real-time traffic information, and more.

[0121] A pre-storage strategy is a specific network data pre-storage plan developed based on preset pre-storage rules, the vehicle's current driving information, and the duration of the signal blind spot. This strategy includes data pre-storage priority, data volume allocation, and data type selection. The pre-storage strategy is designed to rationally allocate pre-stored data within limited local storage space, ensuring that the vehicle prioritizes access to the most important network data within signal blind spots, thereby improving the availability of in-vehicle network applications and user experience.

[0122] Remaining local storage space refers to the remaining capacity of the vehicle's storage devices (such as hard drives and solid-state drives) available for data storage. Remaining local storage space is a key factor in developing pre-storage strategies. The amount of pre-stored network data should be appropriately allocated based on the remaining local storage space to avoid pre-storage failures or partial data inability to be pre-stored due to insufficient storage space.

[0123] Network data pre-storage priority is a prioritized list of different types of network data, sorted by the importance of in-vehicle network applications and user needs. High-priority data is pre-stored to the vehicle's local storage first. This system prioritizes data that has the greatest impact on vehicle safety, navigation functionality, or user experience, such as navigation map data and emergency communication data, within limited storage space and pre-storage time.

[0124] Multimedia cache data space refers to temporary storage space within the vehicle for multimedia data (such as audio, video, and images). This space is typically used to cache multimedia content that is about to be played or displayed, improving playback smoothness. During signal blackouts, the multimedia cache data space is used to store pre-stored multimedia data, ensuring that multimedia applications within the vehicle (such as the in-car entertainment system) can continue to play or display content normally even when the signal is interrupted.

[0125] In a feasible implementation, the steps of obtaining the vehicle's current driving information and predicting the duration of the signal blind spot, and pre-storing the vehicle's network data according to the signal blind spot duration using a preset pre-stored rule include:

[0126] Get the list of active background applications in the vehicle and the remaining local storage space;

[0127] Determining the network data pre-storage priority of background active applications in the vehicle based on a preset application pre-storage priority list and the background active application list;

[0128] Allocate multimedia cache data space for each background active application according to the blind zone duration, the remaining local storage space, and the network data pre-storage priority;

[0129] Acquire and pre-store network data into the multimedia cache data space.

[0130] It should be noted that pre-storage includes but is not limited to the process of dynamically adjusting the amount and type of pre-stored data based on real-time prediction results and user needs, and also includes the update and optimization mechanism of cached data.

[0131] The multimedia cache data space includes, but is not limited to, the space allocated to the multimedia application data cache in the vehicle storage device, and also includes a dynamically adjusted storage area.

[0132] For example, suppose a car plans to travel from City A to City B, passing through a mountainous road and a tunnel. Signal coverage on mountainous roads and in tunnels is poor, with multiple blind spots. Before entering a blind spot, the vehicle's in-vehicle network data pre-storage device performs the following steps to ensure reliable service within the blind spot.

[0133] The device detects that the vehicle's currently active multimedia applications include a navigation system, a music player, and a message notification application. The device uses a blind spot prediction model to obtain the duration of the vehicle's blind spots when entering mountain roads and tunnels, which are 2 minutes and 3 minutes respectively. The device calculates the space available for multimedia data caching based on the duration of the blind spots and the remaining local storage space. For example, a blind spot on a mountain road requires caching 2 minutes of multimedia data, and a blind spot in a tunnel requires caching 3 minutes of multimedia data. While the vehicle is driving, the device monitors the storage space and network status in real time and dynamically adjusts the pre-stored data. For example, if the storage space is insufficient, priority is given to retaining data for key applications; if the network status improves, the cached data is updated in advance.

[0134] As can be understood, the device dynamically adjusts the type and amount of pre-stored data based on the duration of the blind spot and user needs. For example, the amount of pre-stored data is increased when the blind spot lasts longer; when storage space is insufficient, data for critical applications is prioritized. The device intelligently allocates cached data based on available local storage space. For example, if storage space is limited, critical data required for navigation and multimedia applications is prioritized for caching to ensure service continuity within the blind spot. After the vehicle exits the blind spot, the device automatically uploads cached protocol request data, obtains the latest server response data, and updates the local cache to ensure data timeliness. In mountain tunnels, the device uses pre-stored real-time traffic event information and multimedia data to ensure that the navigation system can provide accurate route suggestions and the multimedia player can play content smoothly, avoiding service interruptions caused by network outages. The device uses a pseudo-handshake mechanism to maintain the "online" status of critical applications. For example, when the vehicle enters a tunnel, the device simulates protocol response data to ensure that user applications (such as the music player or navigation system) can continue to operate without manual refresh. Through intelligent cache allocation, the device reduces unnecessary data pre-storage, reduces storage space usage, optimizes network bandwidth usage, and improves overall system efficiency. By implementing dynamic pre-storage strategies and intelligent cache allocation within the vehicle's network data pre-storage device before entering a signal-blind zone, the vehicle can provide continuous navigation and multimedia services within the blind spot, significantly improving the reliability of the in-vehicle wireless network within the blind spot. This technology not only reduces redundant operations caused by network outages, but also optimizes the overall driving experience, reduces system resource consumption, and improves overall system efficiency.

[0135] In a feasible implementation manner, the step of acquiring and pre-storing network data in the multimedia cache data space includes:

[0136] Pre-storing real-time traffic event information of the vehicle navigation route based on the blind spot duration;

[0137] When entering a signal blind spot, converting the real-time traffic event information into a traffic event mark supported by an offline map;

[0138] Adding the traffic event mark to the offline map;

[0139] Obtain the acceleration direction, vehicle speed and driving direction of the vehicle to obtain the driving information of the vehicle in the blind spot;

[0140] In combination with the vehicle navigation route and the blind spot vehicle driving information, the vehicle position is updated in the offline map in real time;

[0141] When it is detected that the vehicle position reaches the traffic event mark, a preset reminder solution is executed.

[0142] It should be noted that real-time traffic event information includes but is not limited to dynamic information such as traffic accidents, road construction, traffic congestion, etc. on the current road, and also includes road conditions affected by weather.

[0143] Offline maps include but are not limited to static map data stored in the vehicle device, and also include pre-downloaded geographic information and navigation routes.

[0144] Traffic event markers include, but are not limited to, markers used to identify the location and type of traffic event, as well as the severity and estimated duration of the event.

[0145] For example, assume a car is traveling on a highway and an accident causes traffic congestion on the road ahead. The in-vehicle network data pre-storage device, prior to entering a blind spot, ensures that traffic event information is acquired and updated before the vehicle enters the blind spot, ensuring accurate navigation services can still be provided within the blind spot.

[0146] The device uses the blind spot prediction model to determine that the duration of the signal blind spot that the vehicle is about to enter is 3 minutes.

[0147] The device pre-stores real-time traffic event information on the vehicle's navigation route based on the duration of the blind spot, including traffic accidents and congestion conditions on the road ahead.

[0148] When a vehicle enters a signal blind spot, the device converts the pre-stored real-time traffic event information into traffic event markers supported by the offline map. For example, the location of a traffic accident is converted into a red marker on the map, and a congested road section is converted into a yellow marker.

[0149] The device adds these traffic event markers to the offline map, ensuring that the navigation system can still display real-time traffic conditions in blind spots.

[0150] After the vehicle exits the blind spot, the device automatically obtains the latest traffic event information and updates the marks in the offline map to ensure the timeliness of the information.

[0151] It is understandable that the device dynamically pre-stores real-time traffic event information on the vehicle navigation route based on the duration of the blind spot, ensuring that key traffic dynamics can still be obtained in the blind spot.

[0152] The device can convert real-time traffic event information into markers supported by offline maps and seamlessly integrate it into offline maps to provide continuous navigation services.

[0153] After the vehicle exits the blind spot, the device automatically obtains and updates traffic event information to ensure that the offline map data remains up to date.

[0154] In signal blind spots, the device ensures that the navigation system can provide accurate route suggestions through pre-stored and converted traffic event markers, avoiding information delays caused by network interruptions.

[0155] The device updates traffic event information in real time to ensure that users can obtain the latest road conditions even in blind spots, reducing driving delays caused by traffic events.

[0156] By pre-storing and displaying traffic event markers, the device helps drivers understand road conditions in advance, make safer driving decisions, and reduce accident risks.

[0157] By dynamically pre-storing and intelligently converting network data stored in the vehicle's in-vehicle network data storage device before entering a signal-blind zone, the vehicle can provide continuous and accurate navigation services within the blind spot, significantly improving the reliability of the in-vehicle navigation system in blind spots. This technology not only optimizes the user experience but also reduces driving risks and ensures driving safety.

[0158] In a feasible implementation manner, the step of pre-storing the in-vehicle network data according to the signal blind zone duration using a preset pre-stored rule includes:

[0159] Determine active target anti-disconnection applications based on the user's preset anti-disconnection application list;

[0160] Sending simulated first protocol response data to the target anti-disconnection application through a pseudo-handshake mechanism;

[0161] Recording protocol request data of the target anti-disconnection application;

[0162] When the network signal strength recovers to a preset threshold, the protocol request data is uploaded, and the second protocol response data responded by the server is obtained to update the first protocol response data.

[0163] It should be noted that the pseudo-handshake mechanism is a mechanism that simulates handshake signals during data transmission to maintain the "online" state of the application, including but not limited to avoiding application disconnection due to network interruption by simulating protocol response data.

[0164] Target anti-disconnection applications include but are not limited to in-vehicle applications with high network connection requirements, such as navigation systems, multimedia players, and communication applications. These applications need to maintain an "online" state in signal blind spots.

[0165] Protocol response data includes but is not limited to response data generated according to the communication protocol and is used to maintain the normal operation of the application. The first protocol response data is simulated and used to maintain the "online" status of the application; the second protocol response data is real and used to update the simulated data.

[0166] For example, assuming that a car is about to enter a signal blind spot, the network data pre-storage device in the vehicle before entering the signal blind spot ensures that the vehicle can still provide reliable services in the blind spot through the following steps.

[0167] The device uses the blind spot prediction model to determine that the duration of the signal blind spot that the vehicle is about to enter is 3 minutes.

[0168] The device detects that the target anti-disconnection applications currently active in the vehicle include the navigation system, music player, and message notification applications.

[0169] The device uses a pseudo-handshake mechanism to send simulated first protocol response data to the target anti-disconnection application to maintain the application's "online" status. For example, it sends simulated location update data to a navigation system and simulated playback status data to a music player.

[0170] The device records protocol request data generated by the target anti-disconnection application within the blind area. For example, it records real-time traffic information requested by the navigation system and the next song data requested by the music player.

[0171] When the vehicle exits the signal blind spot and the network signal strength returns to a preset threshold, the device automatically uploads the recorded protocol request data, obtains the second protocol response data from the server, and updates the previously simulated first protocol response data. For example, it can upload real-time traffic information requested by a navigation system, obtain the latest response from the server, and update the navigation system's traffic data.

[0172] It can be understood that the device sends simulated first protocol response data to the target anti-disconnection application through a pseudo-handshake mechanism to ensure that the application remains "online" in the blind area and avoid application disconnection due to network interruption.

[0173] The device records the application's protocol request data within the blind area and automatically uploads it after the network is restored to ensure data integrity and timeliness.

[0174] After the vehicle exits the blind spot, the device automatically obtains and updates the protocol response data to ensure the accuracy and currency of the application data.

[0175] In signal blind spots, the device ensures that users can continue to use key applications such as navigation and music playback by maintaining the application's "online" status, avoiding service interruptions caused by network interruptions.

[0176] By keeping the navigation system online, the device helps drivers obtain accurate navigation information even in blind spots, making safer driving decisions and reducing the risk of accidents.

[0177] The device reduces data loss due to network interruptions by recording and uploading protocol request data, thereby improving the overall efficiency and reliability of the system.

[0178] By leveraging a pseudo-handshake mechanism and automatic update capabilities within the vehicle's network data storage device before entering a signal blind spot, the vehicle can provide continuous and reliable service within the blind spot, significantly improving the stability of in-vehicle applications and user experience within the blind spot. This technology not only optimizes the driving experience, but also reduces driving risks and ensures driving safety.

[0179] This embodiment provides a method for pre-storing network data in a vehicle before entering a signal blind spot. This application first improves the reliability of the vehicle network in the blind spot environment:

[0180] By pre-downloading the necessary in-vehicle wireless network data for potential blind spots along the route, the in-vehicle navigation system and multimedia player can continue to provide timely and accurate service even in environments with poor network signals or blind spots, eliminating the need for frequent operations and waiting for network recovery. This reduces service interruptions and improves the user experience. By combining the vehicle's navigation route, base station signal distribution maps, and historical signal data, the duration of the signal blind spot the vehicle is about to enter is predicted. This enables the system to more accurately predict the location and duration of the blind spot, allowing for pre-emptive data preparation and resource allocation, enhancing the flexibility and responsiveness of the in-vehicle network. By analyzing real-time and historical signal data based on the vehicle's planned route information and combining it with a blind spot prediction model, the system can flexibly adjust resource allocation and pre-store required network data to ensure the continuous availability of the in-vehicle wireless network within the blind spot.

[0181] Through the above technical effects, this application can provide a service experience without feeling blind spots around signal blind spots, reduce interference with the normal use of vehicle navigation systems and multimedia players, and improve the overall reliability and user experience of the in-vehicle network system.

[0182] For example, in order to help understand the implementation process of the method for pre-storing network data in a vehicle before entering a signal blind area obtained by combining this embodiment with the above embodiment 1, please refer to Figure 3 , Figure 3 A simplified flowchart of a method for pre-storing network data in a vehicle before entering a signal blind spot is provided. Specifically:

[0183] The device extracts the vehicle's route information from the vehicle's navigation system, including the starting point (city A), the end point (city B), key nodes along the way (such as mountainous sections and tunnels), and the estimated driving speed. Simultaneously, the device obtains a signal distribution map of base stations along the route from the cloud and, combined with historical signal data, generates the vehicle's planned route information.

[0184] The device inputs the vehicle's planned route information into a pre-set blind spot prediction model. Combined with the current vehicle speed and a base station signal strength heat map, it predicts the duration of the vehicle's signal blind spot. For example, it predicts that a vehicle will enter a signal blind spot on a mountain road or in a tunnel for 2 minutes and 3 minutes, respectively.

[0185] The device dynamically stores the required vehicle-mounted wireless network data based on the blind spot duration and preset storage rules. The specific steps are as follows:

[0186] Determine pre-stored multimedia applications: The vehicle's currently active multimedia applications are detected to include the navigation system, music player, and message notification applications.

[0187] Allocate multimedia data cache space: Calculate the available space for multimedia data caching based on the duration of the blind spot and the remaining local storage space. For example, a blind spot on a mountain road requires caching 2 minutes of multimedia data, while a blind spot in a tunnel requires caching 3 minutes of multimedia data.

[0188] Pre-store multimedia application network data: Pre-store the data required by the navigation system, music player and message notification applications in the multimedia cache data space.

[0189] The device stores real-time traffic event information along the vehicle's navigation route, including traffic accidents and congestion on the road ahead. When the vehicle enters a signal blind spot, this real-time traffic event information is converted into markers supported by the offline map and added to the offline map.

[0190] The device uses a pseudo-handshake mechanism to send simulated first-protocol response data to the target anti-disconnection application (such as a navigation system or music player), maintaining the application's "online" status. At the same time, it records the protocol request data generated by the application within the blind area.

[0191] When the vehicle exits the signal blind spot and the network signal strength returns to the preset threshold, the device automatically uploads the recorded protocol request data, obtains the second protocol response data from the server, and updates the previously simulated first protocol response data.

[0192] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the method of pre-storing network data in the vehicle before entering the signal blind spot. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0193] This application also provides a device for pre-storing network data in a vehicle before entering a signal blind area. Please refer to Figure 4 The network data pre-storage device in the vehicle before entering the signal blind area includes:

[0194] An acquisition module 10 is used to acquire a vehicle navigation route and determine a corresponding base station signal distribution map and navigation route historical signal data;

[0195] The prediction module 20 is configured to predict each predicted signal blind spot in the vehicle navigation route based on the base station signal distribution map and the historical signal data of the navigation route using a preset blind spot prediction model;

[0196] The pre-storage module 30 is used to obtain the vehicle's current driving information and predict the duration of the signal blind spot if it is detected that the vehicle is about to enter the predicted signal blind spot, and pre-store the network data in the vehicle according to the preset pre-storage rules based on the duration of the signal blind spot.

[0197] And / or, the prediction module 20 includes:

[0198] A first extraction module is used to extract time series features from the navigation history signal data using a preset long short-term memory neural network model to obtain time series features of the historical signals;

[0199] A second extraction module is used to extract spatial features from the base station signal distribution map using a preset convolutional neural network model to obtain current spatial vector features;

[0200] A first acquisition module is used to obtain real-time weather information and real-time terrain information of the vehicle navigation route;

[0201] The first prediction module is used to input the real-time weather information, the real-time terrain information, the historical signal time series characteristics and the current space vector characteristics into a blind spot prediction model to predict each predicted signal blind spot on the vehicle navigation route.

[0202] And / or, the network data pre-storage device in the vehicle before entering the signal blind zone includes:

[0203] The second acquisition module is used to obtain historical signal time series samples, base station space vector samples and signal blind area distribution labels;

[0204] A first projection module is used to project the historical signal time series samples and the base station space vector samples into the same dimension, and generate a time-space weighted feature representation according to a preset attention matrix model;

[0205] The third acquisition module is used to obtain the influencing factors of severe weather and severe landforms;

[0206] A first generating module is used to generate a severe condition weight according to the severe weather influencing factor and the severe landform influencing factor;

[0207] A second prediction module is used to input the time-space weighted feature representation and the harsh condition weight into the signal blind spot prediction model to be trained, predict the signal blind spot, and obtain a signal blind spot prediction result;

[0208] A first comparison module is used to compare the signal blind spot prediction result and the signal blind spot distribution label to obtain a prediction error value;

[0209] The first loop module is used to adjust the hyperparameters of the attention matrix model if the prediction error value does not meet the preset threshold, return to the step of projecting the historical signal time series samples and the base station space vector samples to the same dimension, and generate a time-space weighted feature representation according to the preset attention matrix model until the prediction error value meets the preset threshold and outputs the predicted signal blind spot.

[0210] And / or, the pre-stored module 30 includes:

[0211] The fourth acquisition module is used to obtain a list of active background applications in the vehicle and the remaining local storage space;

[0212] A first determining module is configured to determine the network data pre-storage priority of background active applications in the vehicle according to a preset application pre-storage priority list and the background active application list;

[0213] A first allocation module is configured to allocate multimedia cache data space to each background active application according to the blind zone duration, the local remaining storage space, and the network data pre-storage priority;

[0214] The first pre-storage module is used to obtain and pre-store network data into the multimedia cache data space.

[0215] And / or, the first pre-stored module includes:

[0216] A second pre-storage module is used to pre-store real-time traffic event information of the vehicle navigation route based on the blind spot duration;

[0217] A first conversion module is used to convert the real-time traffic event information into a traffic event mark supported by an offline map when entering a signal blind spot;

[0218] A first adding module, configured to add the traffic event mark to the offline map;

[0219] The fifth acquisition module is used to obtain the acceleration direction, vehicle speed and driving direction of the vehicle to obtain the blind spot vehicle driving information;

[0220] A first updating module is configured to update the vehicle position in the offline map in real time based on the vehicle navigation route and the blind spot vehicle driving information;

[0221] The first execution module is configured to execute a preset reminder plan when it is detected that the vehicle position reaches the traffic event mark.

[0222] And / or, the network data pre-storage device in the vehicle before entering the signal blind zone includes:

[0223] The second determination module is used to determine an active target anti-disconnection application based on a user-preset anti-disconnection application list;

[0224] A first sending module, configured to send simulated first protocol response data to the target anti-disconnection application through a pseudo handshake mechanism;

[0225] A first recording module, configured to record protocol request data of the target anti-disconnection application;

[0226] The sixth acquisition module is used to upload the protocol request data when the network signal strength recovers to a preset threshold, and obtain the second protocol response data responded by the server to update the first protocol response data.

[0227] The in-vehicle network data pre-storage device provided in this application, which utilizes the in-vehicle network data pre-storage method described in the aforementioned embodiments, can address the technical issue of poor reliability of in-vehicle wireless networks within blind spot environments. Compared to the prior art, the in-vehicle network data pre-storage device provided in this application, which provides the same beneficial effects as the in-vehicle network data pre-storage method described in the aforementioned embodiments, also provides the same other technical features as those disclosed in the aforementioned embodiments and are not further elaborated upon here.

[0228] The present application provides a device for pre-storing network data in a vehicle before entering a signal blind spot. The device for pre-storing network data in a vehicle before entering a signal blind spot includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for pre-storing network data in a vehicle before entering a signal blind spot in the above-mentioned embodiment one.

[0229] Reference below Figure 5, which shows a schematic diagram of the structure of a device for pre-storing network data in a vehicle before entering a signal blind spot, suitable for implementing an embodiment of the present application. The device for pre-storing network data in a vehicle before entering a signal blind spot in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, tablet computers, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PMPs (Portable Media Players), in-vehicle terminals (such as in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The network data pre-storage device in the vehicle before entering the signal blind spot is shown as merely an example and should not impose any limitations on the functions and scope of use of the embodiments of the present application.

[0230] like Figure 5 As shown, the device for pre-storing in-vehicle network data before entering a blind spot may include a processing device 1001 (e.g., a central processing unit, graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 1002 or programs loaded from storage device 1003 into random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the device for pre-storing in-vehicle network data before entering a blind spot. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O 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, a magnetic tape, hard disk, etc.; and communication devices 1009. Communication devices 1009 can allow the in-vehicle network data pre-storage device before entering a signal blind spot to communicate wirelessly or wired with other devices to exchange data. While the figure shows the in-vehicle network data pre-storage device before entering a signal blind spot with various systems, it should be understood that implementation or presence of all illustrated systems is not required. More or fewer systems may alternatively be implemented or present.

[0231] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0232] The in-vehicle network data pre-storage device provided in this application, which utilizes the in-vehicle network data pre-storage method described in the aforementioned embodiment, can address the technical issue of poor reliability of in-vehicle wireless networks within blind spot environments. Compared to the prior art, the in-vehicle network data pre-storage device provided in this application achieves the same beneficial effects as the in-vehicle network data pre-storage method described in the aforementioned embodiment. Other technical features of the in-vehicle network data pre-storage device are the same as those disclosed in the aforementioned embodiment and are not further elaborated upon here.

[0233] It should be understood that 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 one or more embodiments or examples in a suitable manner.

[0234] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0235] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, and the computer-readable program instructions are used to execute the method for pre-storing network data in a vehicle before entering a signal blind spot in the above-mentioned embodiment.

[0236] The computer-readable storage medium provided herein may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, 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.

[0237] The computer-readable storage medium may be included in the network data pre-storage device in the vehicle before entering the signal blind spot; or it may exist independently and not be installed in the network data pre-storage device in the vehicle before entering the signal blind spot.

[0238] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the network data pre-storage device in the vehicle before entering the signal blind spot, the network data pre-storage device in the vehicle before entering the signal blind spot: obtains the vehicle navigation route, determines the corresponding base station signal distribution map and the navigation route historical signal data; predicts each predicted signal blind spot in the vehicle navigation route according to the base station signal distribution map and the navigation route historical signal data through a preset blind spot prediction model; if it is monitored that the vehicle is about to enter the predicted signal blind spot, obtains the current driving information of the vehicle and predicts the duration of the signal blind spot, and pre-stores the network data in the vehicle according to the preset pre-stored rules based on the signal blind spot duration.

[0239] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0240] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0241] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0242] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned method for pre-storing in-vehicle network data before entering a blind spot. This method can address the technical issue of poor reliability of in-vehicle wireless networks within blind spots. Compared to existing technologies, the computer-readable storage medium provided in this application offers the same beneficial effects as the method for pre-storing in-vehicle network data before entering a blind spot provided in the aforementioned embodiments, and will not be further elaborated upon here.

[0243] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for pre-storing network data in a vehicle before entering a signal blind spot.

[0244] The computer program product provided in this application can address the technical issue of poor reliability of in-vehicle wireless networks in blind spots. Compared to existing technologies, the computer program product provided in this application offers the same beneficial effects as the method for pre-storing in-vehicle network data before entering a blind spot, as described in the aforementioned embodiment, and will not be further elaborated here.

[0245] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for pre-storing network data in a vehicle before entering a signal blind area, characterized in that: The method includes: Obtain the vehicle navigation route, determine the corresponding base station signal distribution map and navigation route historical signal data; According to the base station signal distribution map and the historical signal data of the navigation route, each predicted signal blind spot in the vehicle navigation route is predicted by a preset blind spot prediction model; The method for predicting each predicted signal blind spot in the vehicle navigation route based on the base station signal distribution map and the navigation route historical signal data by using a preset blind spot prediction model includes: By using a preset long short-term memory neural network model, time series feature extraction is performed on the historical signal data of the navigation route to obtain the historical signal time series features; Using a preset convolutional neural network model, spatial feature extraction is performed on the base station signal distribution map to obtain current spatial vector features; Obtaining real-time weather information and real-time topographic information of the vehicle's navigation route; Inputting the real-time weather information, the real-time topographic information, the historical signal time series features, and the current spatial vector features into a blind spot prediction model to predict each predicted signal blind spot on the vehicle navigation route, wherein the blind spot prediction model dynamically guides the focus area of the current spatial vector features through the historical signal time series features, and automatically enhances the attention weight of neighboring base stations under severe weather conditions; If it is detected that a vehicle is about to enter the predicted signal blind spot, the vehicle's current driving information is obtained and the duration of the signal blind spot is predicted. Based on the duration of the signal blind spot, the network data in the vehicle is pre-stored using preset pre-stored rules.

2. The method according to claim 1, wherein Before the step of inputting the real-time weather information, the real-time terrain information, the historical signal time series features, and the current spatial vector features into the blind spot prediction model to predict each predicted signal blind spot on the vehicle navigation route, the following steps are included: Obtain historical signal time series samples, base station space vector samples, and signal blind area distribution labels; Projecting the historical signal time series samples and the base station space vector samples to the same dimension, and generating a time-space weighted feature representation based on a preset attention matrix model; Obtain the influencing factors of severe weather and severe landforms; generating a severe condition weight according to the severe weather influencing factor and the severe landform influencing factor; Inputting the time-space weighted feature representation and the harsh condition weight into the signal blind spot prediction model to be trained, predicting the signal blind spot, and obtaining a signal blind spot prediction result; Comparing the signal blind spot prediction result with the signal blind spot distribution label to obtain a prediction error value; If the prediction error value does not meet the preset threshold, the hyperparameters of the attention matrix model are adjusted, and the step of projecting the historical signal time series samples and the base station space vector samples to the same dimension is returned to generate a time-space weighted feature representation according to the preset attention matrix model until the prediction error value meets the preset threshold and the prediction signal blind spot is output.

3. The method according to claim 1, wherein The steps of obtaining the vehicle's current driving information and predicting the duration of the signal blind zone, and pre-storing the vehicle's network data according to the signal blind zone duration using a preset pre-stored rule include: Get the list of active background applications in the vehicle and the remaining local storage space; Determining the network data pre-storage priority of background active applications in the vehicle based on a preset application pre-storage priority list and the background active application list; Allocate multimedia cache data space for each background active application according to the blind zone duration, the remaining local storage space, and the network data pre-storage priority; Acquire and pre-store network data into the multimedia cache data space.

4. The method according to claim 3, wherein The step of acquiring and pre-storing network data in the multimedia cache data space includes: Pre-storing real-time traffic event information of the vehicle navigation route based on the blind spot duration; When entering a signal blind spot, converting the real-time traffic event information into a traffic event mark supported by an offline map; Adding the traffic event mark to the offline map; Obtain the acceleration direction, vehicle speed and driving direction of the vehicle to obtain the driving information of the vehicle in the blind spot; In combination with the vehicle navigation route and the blind spot vehicle driving information, the vehicle position is updated in the offline map in real time; When it is detected that the vehicle position reaches the traffic event mark, a preset reminder solution is executed.

5. The method according to claim 1, wherein After the step of pre-storing the network data in the vehicle according to the signal blind zone duration using a preset pre-stored rule, the following steps are included: Determine active target anti-disconnection applications based on the user's preset anti-disconnection application list; Sending simulated first protocol response data to the target anti-disconnection application through a pseudo-handshake mechanism; Recording protocol request data of the target anti-disconnection application; When the network signal strength recovers to a preset threshold, the protocol request data is uploaded, and the second protocol response data responded by the server is obtained to update the first protocol response data.

6. A network data pre-storage device in a vehicle before entering a signal blind area, characterized in that: The device comprises: An acquisition module is used to obtain the vehicle navigation route and determine the corresponding base station signal distribution map and navigation route historical signal data; A prediction module, configured to predict each predicted signal blind spot in the vehicle navigation route based on the base station signal distribution map and the historical signal data of the navigation route using a preset blind spot prediction model; The method for predicting each predicted signal blind spot in the vehicle navigation route based on the base station signal distribution map and the navigation route historical signal data by using a preset blind spot prediction model includes: By using a preset long short-term memory neural network model, time series feature extraction is performed on the historical signal data of the navigation route to obtain the historical signal time series features; Using a preset convolutional neural network model, spatial feature extraction is performed on the base station signal distribution map to obtain current spatial vector features; Obtaining real-time weather information and real-time topographic information of the vehicle's navigation route; Inputting the real-time weather information, the real-time topographic information, the historical signal time series features, and the current spatial vector features into a blind spot prediction model to predict each predicted signal blind spot on the vehicle navigation route, wherein the blind spot prediction model dynamically guides the focus area of the current spatial vector features through the historical signal time series features, and automatically enhances the attention weight of neighboring base stations under severe weather conditions; The pre-storage module is used to obtain the vehicle's current driving information and predict the duration of the signal blind spot if it is detected that the vehicle is about to enter the predicted signal blind spot, and pre-store the network data in the vehicle according to the preset pre-storage rules based on the duration of the signal blind spot.

7. A network data pre-storage device in a vehicle before entering a signal blind area, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for pre-storing network data in a vehicle before entering a signal blind spot as described in any one of claims 1 to 5.

8. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the method for pre-storing network data in a vehicle before entering a signal blind spot as described in any one of claims 1 to 5 are implemented.

9. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the method for pre-storing network data in a vehicle before entering a signal blind area according to any one of claims 1 to 5 are implemented.

Images