Network quality prediction methods, devices, servers, and storage media

Abstract

This invention discloses a network quality prediction method, apparatus, server, and storage medium. The network quality prediction method includes: receiving measurement data of the network quality of the currently serving cell uploaded by a vehicle; determining first data of the current grid region where the vehicle is located based on the measurement data; the first data representing the network quality of the current grid region; and determining a predicted value of the network quality of the target grid region based on the first data and historical grid data of the target grid region; the target grid region is the area to be traversed by the vehicle, and the historical grid data representing the historical network quality of the target grid region.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to a network quality prediction method, apparatus, server, and storage medium. Background Technology

[0002] In related technologies, vehicle-mounted systems equipped with IoT data communication cards can obtain coverage signal strength information at the current location by receiving power control messages from the current serving cell. However, the network status information obtained by the vehicle is real-time data, making it difficult to predict network quality information along the future driving trajectory. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a network quality prediction method, apparatus, server, and storage medium, which can predict the network quality of a target area.

[0004] The technical solution of this invention is implemented as follows:

[0005] On one hand, embodiments of the present invention provide a network quality prediction method, the method comprising:

[0006] Receive network quality measurement data of the current serving cell uploaded by the vehicle terminal;

[0007] Based on the measurement data, first data is determined for the current grid area where the vehicle is located; the first data characterizes the network quality of the current grid area where the vehicle is located.

[0008] Based on the first data and the historical raster data of the target raster region, a predicted value of the network quality of the target raster region is determined; the target raster region is the area to be traversed by the vehicle, and the historical raster data characterizes the historical network quality of the target raster region.

[0009] In the above scheme, before determining the first data of the current grid area of ​​the vehicle based on the measurement data, the method further includes:

[0010] Determine whether the measurement data uploaded by the vehicle meets the preset format requirements;

[0011] If the measurement data uploaded by the vehicle does not meet the preset format requirements, the measurement data will be discarded.

[0012] If the measurement data uploaded by the vehicle meets the preset format requirements, then the first data is determined based on the measurement data.

[0013] In the above scheme, before determining the predicted value of the network quality of the target raster region based on the first data and the historical raster data of the target raster region, the method further includes:

[0014] Based on the identifier of the target raster region, the historical raster data of the target raster region is queried in the cloud server; the cloud server stores the historical raster data of each target raster region.

[0015] In the above scheme, the method further includes:

[0016] Obtain the most recently uploaded first historical raster data of the target raster region from the cloud server;

[0017] Correspondingly, determining the predicted value of the network quality of the target raster region based on the first data and historical raster data of the target raster region includes:

[0018] Based on the first data and the first historical raster data, a predicted value of the network quality of the target raster region is determined;

[0019] Correspondingly, after determining the predicted value of the network quality of the target raster region, the method further includes:

[0020] The predicted value is recorded as the second historical raster data of the target raster area and stored in the cloud server.

[0021] In the above scheme, the measurement data includes a first measurement value of the network quality of the first serving cell and a second measurement value of the network quality of the second serving cell; the first serving cell is the serving cell of the network service currently used by the vehicle, and the second serving cell is the serving cell with the strongest network quality among the serving cells that the vehicle can currently access, excluding the first serving cell;

[0022] The first data for determining the current grid area of ​​the vehicle based on the measurement data includes:

[0023] The first data is determined based on the first measurement value and the second measurement value.

[0024] In the above scheme, determining the first data based on the first measured value and the second measured value includes:

[0025] A first weight value is determined based on the difference between the first measured value and the second measured value;

[0026] The first measurement value and the second measurement value are weighted based on the first weight value to obtain the first data.

[0027] In the above scheme, determining the predicted value of the network quality of the target raster region based on the first data and the historical raster data of the target raster region includes:

[0028] The predicted value is obtained by weighting the first data and the historical raster data of the target raster region based on a preset second weight value.

[0029] In the above scheme, the method further includes:

[0030] Upon receiving a network switching request message uploaded by the vehicle, the second weight value is reduced from a first set value to a second set value; the switching request message indicates that the vehicle is currently in a network switching zone;

[0031] Upon receiving the network switching completion message uploaded by the vehicle, the second weight value is adjusted to the first set value.

[0032] In the above scheme, the method further includes:

[0033] Fill the predicted value into the target grid area;

[0034] Update map information based on the target raster area with updated predicted values;

[0035] The updated map information is sent to the vehicle.

[0036] On the other hand, embodiments of the present invention provide a network quality prediction device, the device comprising:

[0037] The receiving module is used to receive measurement data on the network quality of the current serving cell uploaded by the vehicle.

[0038] The first determining module is used to determine first data of the grid area where the vehicle is currently located based on the measurement data; the first data characterizes the network quality of the grid area where the vehicle is currently located.

[0039] The second determining module is used to determine a predicted value of the network quality of the target grid region based on the first data and the historical grid data of the target grid region; the target grid region is the area to be traversed by the vehicle end, and the historical grid data characterizes the historical network quality of the target grid region.

[0040] On the other hand, embodiments of the present invention provide a server including a processor and a memory interconnected thereto. The memory is used to store a computer program, the computer program including program instructions, and the processor is configured to invoke the program instructions to execute the steps of the network quality prediction method provided in the embodiments of the present invention.

[0041] On the other hand, embodiments of the present invention provide a computer-readable storage medium, comprising: the computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the steps of the network quality prediction method provided in embodiments of the present invention.

[0042] This application embodiment receives network quality measurement data of the currently serving cell uploaded by the vehicle-mounted terminal. Based on the measurement data, it determines the first data of the current grid area where the vehicle-mounted terminal is located, which represents the network quality of the current grid area. Based on the first data and historical grid data of the target grid area, it determines the predicted value of the network quality of the target grid area. The target grid area is the area to be traversed by the vehicle-mounted terminal, and the historical grid data represents the historical network quality of the target grid area. This application embodiment utilizes data geographic rasterization, and based on the first data of the current grid area where the vehicle-mounted terminal is located and the historical grid data of the target grid area, it can accurately predict the network quality of the target grid area, thus solving the need for road network condition guidance. The network quality of the target grid area can guide the vehicle-mounted terminal's decision-making and operation in the next stage, for example, the vehicle-mounted terminal can plan the optimal route based on the network quality of the target grid area. Attached Figure Description

[0043] Figure 1 This is a schematic diagram illustrating how the vehicle's infotainment system obtains network signal strength, provided by relevant technologies.

[0044] Figure 2 This is a schematic diagram illustrating the implementation process of a network quality prediction method provided in an embodiment of the present invention;

[0045] Figure 3 This is a schematic diagram of a network quality prediction process provided in an embodiment of the present invention;

[0046] Figure 4 This is a schematic diagram illustrating predictive parameter tuning in a network handover band, provided by an embodiment of the present invention.

[0047] Figure 5 This is a schematic diagram of a road network condition prediction system provided in an embodiment of the present invention;

[0048] Figure 6 This is a schematic diagram of a data path provided in an embodiment of the present invention;

[0049] Figure 7 This is a schematic diagram of a sample data format provided in an embodiment of the present invention;

[0050] Figure 8 This is a schematic diagram illustrating a method for switching sample data formats provided in an embodiment of the present invention;

[0051] Figure 9 This is an example of the effect of rasterizing sample points according to an embodiment of the present invention;

[0052] Figure 10 This is a schematic diagram of the network condition map creation process provided in an embodiment of the present invention;

[0053] Figure 11 This is a schematic diagram of a network quality prediction device provided in an embodiment of the present invention;

[0054] Figure 12 This is a schematic diagram of the server provided in an embodiment of the present invention. Detailed Implementation

[0055] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] The development of intelligent vehicles has been rapid in recent years, and the network requirements for in-vehicle applications are becoming increasingly stringent. In particular, remote vehicle control, autonomous driving, high-precision maps, and 5G in-vehicle applications all require a timely, reliable, and stable network quality environment to ensure service execution. Therefore, timely network quality prediction and push notifications during vehicle operations have become an unresolved issue in 5G+vehicle-to-everything (V2X) applications.

[0057] In related technologies, such as Figure 1 As shown, the vehicle-mounted infotainment system (T-BOX) equipped with an IoT data communication card determines the vehicle's precise location through dual positioning using the Global Navigation Satellite System (GNSS) and base station-assisted positioning. The wireless base station transmits Reference Signal Received Power (RSRP) information to the vehicle via the Uu air interface (an open air interface connecting user equipment and base station), allowing the vehicle to view the coverage signal strength information for the current location.

[0058] The vehicle-mounted system obtains coverage strength information for its current location by receiving power control messages from the serving cell. Firstly, from the perspective of the comprehensiveness of network quality information acquisition, the technology only obtains field strength information, which cannot fully and accurately describe the network environment. Secondly, the acquired network information is real-time data, making it difficult to predict network quality information along the future driving trajectory, and even less able to guide the next stage of business decisions and operations.

[0059] The relevant technologies primarily rely on the wireless communication module in the vehicle's infotainment system to receive power messages from the base station and combine this with real-time dual positioning to present the network coverage level at the current location. However, these technologies have certain drawbacks and limitations in improving vehicle-side network condition awareness. For example, in a certain scenario, the current wireless network environment may meet the conditions for service execution, but if the wireless environment suddenly changes after a few seconds of vehicle movement, the service may abruptly terminate without any warning or guidance, leading to a degraded user experience and potentially even causing a vehicle accident. With the rapid development of intelligent vehicles, the dependence of in-vehicle infotainment systems on the network is becoming increasingly stringent, thus creating an urgent need for vehicle-to-everything (V2X) service assistance functions based on network quality prediction.

[0060] The main drawbacks of the related technologies are as follows:

[0061] 1. Network quality data has a single dimension, mainly using the current RSRP and Received Signal Strength Indicator (RSSI) to determine communication performance and decide on the next step.

[0062] 2. In vehicle-road cooperative scenarios, the network condition data collected by traffic participants (mobile operator network quality of service (QoS) data) lacks systematic data training and value mining, and cannot be coordinated and shared in specific applications, especially in cross-mobile base station service areas or cross-multi-access edge computing (MEC) without fusion analysis.

[0063] 3. The network condition data of the Uu interface lacks a prediction mechanism, making it difficult to accurately guide the development of unmanned and autonomous driving services in Cellular-Vehicle to Everything (C-V2X) or New Radio-Vehicle to Everything (NR-V2X) NR-V2X mode3 (base station centralized scheduling) modes.

[0064] To address the shortcomings of the aforementioned related technologies, embodiments of the present invention provide a network quality prediction method capable of predicting the network quality of a target area. To illustrate the technical solution described in this invention, specific embodiments are provided below.

[0065] Figure 2 This is a schematic diagram illustrating the implementation flow of a network quality prediction method provided in an embodiment of the present invention. The execution entity of the network quality prediction method is a server. (Reference) Figure 2 Network quality prediction methods include:

[0066] S201, Receive measurement data on the network quality of the currently serving cell uploaded by the vehicle terminal.

[0067] The vehicle-side can refer to the vehicle-mounted terminal or vehicle-mounted system, and the measurement data can be network status information such as the current RSRP and RSSI measured by the vehicle-side.

[0068] The network quality measurement data in this embodiment may include at least one of the following:

[0069] RSRP (sample level) of voltage level at a single latitude and longitude;

[0070] Reference Signal Received Quality (RSRQ) (sample quality) over a single latitude and longitude coordinate.

[0071] Signal to Interference (SINR) over a single latitude and longitude (sample interference);

[0072] Field strength information RSSI (sample energy) at a single latitude and longitude;

[0073] Uplink and downlink throughput rates (cell throughput) on a single latitude and longitude;

[0074] Uplink and downlink resource utilization (resource usage) on a single latitude and longitude;

[0075] Handover messages on a single latitude and longitude (SA handover request & SA handover success);

[0076] Serving cell frequency and Physical Cell Identifier (PCI) (base station information) on a single latitude and longitude.

[0077] The strongest neighboring cell frequency and PCI (Neighbor Information) on a single latitude and longitude.

[0078] The data reported by the vehicle to the server may also include at least one of the following:

[0079] Latitude and longitude information (location information).

[0080] Time and speed (vehicle speed information) at a single latitude and longitude.

[0081] Time (time series information) on a single latitude and longitude.

[0082] S202, based on the measurement data, determine the first data of the grid area where the vehicle is currently located; the first data characterizes the network quality of the grid area where the vehicle is currently located.

[0083] The current grid area where the vehicle is located may have network coverage from multiple serving cells. The measurement data represents the network quality of the serving cell where the vehicle is currently located. To represent the network quality of the current grid area, it can be determined by combining the network quality of multiple serving cells in the current grid area. For example, the measurement data of the network quality of multiple serving cells in the current grid area of ​​the vehicle can be obtained, and then the average (or weighted sum) can be calculated to obtain the network quality of the current grid area of ​​the vehicle.

[0084] Alternatively, the measurement data can be directly used as the first data of the current grid area on the vehicle.

[0085] S203, based on the first data and the historical grid data of the target grid area, determine the predicted value of the network quality of the target grid area; the target grid area is the area to be traversed by the vehicle, and the historical grid data characterizes the historical network quality of the target grid area.

[0086] Here, the target raster region can include multiple raster regions. For example, if a cross is drawn with the current raster region as the center, all raster regions within the cross's range are considered target raster regions. Assuming the cross's query range is 4 raster regions, then including the current raster region, there are a total of 17 target raster regions. Assuming each raster region is 25 meters in size, then the target raster region is the raster region within a 100-meter range in each of the four cardinal directions (north, south, east, and west).

[0087] The more target grid areas there are, the easier it is for the vehicle to plan the best route, providing real-time road network information assistance for remote control, semi-autonomous driving, and driverless driving services in vehicle-to-everything (V2X) applications.

[0088] The historical raster data of the target raster area represents the historical network quality. It can be the measurement value of the network quality when a vehicle travels to the target raster area at a historical time, or the prediction value of the network quality of the target raster area at a historical time.

[0089] For example, by performing weighted operations or averaging operations on the first data and the historical raster data of the target raster area, the result is the predicted value of the network quality of the target raster area.

[0090] This application embodiment receives network quality measurement data of the currently serving cell uploaded by the vehicle-mounted terminal. Based on the measurement data, it determines the first data of the current grid area where the vehicle-mounted terminal is located, which represents the network quality of the current grid area. Based on the first data and historical grid data of the target grid area, it determines the predicted value of the network quality of the target grid area. The target grid area is the area to be traversed by the vehicle-mounted terminal, and the historical grid data represents the historical network quality of the target grid area. This application embodiment utilizes data geographic rasterization, and based on the first data of the current grid area where the vehicle-mounted terminal is located and the historical grid data of the target grid area, it can accurately predict the network quality of the target grid area, thus solving the need for road network condition guidance. The network quality of the target grid area can guide the vehicle-mounted terminal's decision-making and operation in the next stage, for example, the vehicle-mounted terminal can plan the optimal route based on the network quality of the target grid area.

[0091] In one embodiment, before determining the first data of the current grid region of the vehicle based on the measurement data, the method further includes:

[0092] Determine whether the measurement data uploaded by the vehicle meets the preset format requirements;

[0093] If the measurement data uploaded by the vehicle does not meet the preset format requirements, the measurement data will be discarded.

[0094] If the measurement data uploaded by the vehicle meets the preset format requirements, then the first data is determined based on the measurement data.

[0095] The vehicle-mounted data acquisition module (or probe-type module) has a preset sample format and collects and reports data according to a time series. All reported vehicle-mounted data must adhere to preset data format requirements. For example, the preset format requirements for measurement data are: the measurement data must include latitude and longitude, SINR, and RSRQ, with latitude and longitude within a preset range and vehicle speed less than the theoretical value. Data samples that do not meet the preset format requirements will be discarded, such as missing latitude and longitude, latitude and longitude outside the range, positive RSRP, missing SINR or RSRQ, or vehicle speed exceeding the theoretical value. If any aspect of the measurement data does not meet the preset format requirements, the measurement data will be discarded.

[0096] In one embodiment, before determining the predicted value of the network quality of the target raster region based on the first data and historical raster data of the target raster region, the method further includes:

[0097] Based on the identifier of the target raster region, the historical raster data of the target raster region is queried in the cloud server; the cloud server stores the historical raster data of each target raster region.

[0098] In one embodiment, the method further includes:

[0099] Obtain the most recently uploaded first historical raster data of the target raster region from the cloud server;

[0100] Correspondingly, determining the predicted value of the network quality of the target raster region based on the first data and historical raster data of the target raster region includes:

[0101] Based on the first data and the first historical raster data, a predicted value of the network quality of the target raster region is determined;

[0102] Correspondingly, after determining the predicted value of the network quality of the target raster region, the method further includes:

[0103] The predicted value is recorded as the second historical raster data of the target raster area and stored in the cloud server.

[0104] In this embodiment, the server is connected to a cloud server, which can connect to multiple servers. The cloud server is primarily responsible for data collaboration between servers to ensure the continuity of user services. The server stores historical raster data for the target raster area in the cloud server.

[0105] The cloud server stores historical grid data of the target grid area and binds it to the identifier of the target grid area so that historical grid data can be found based on the identifier.

[0106] In some embodiments, based on the identifier of the target raster region, the most recently uploaded first historical raster data of the target raster region is obtained from the cloud server. The most recently uploaded first historical raster data has a stronger timeliness, which is beneficial for predicting the network quality of the target raster region.

[0107] In this embodiment, the server also stores the current predicted value as the second historical raster data of the target raster area in the cloud server, and retrieves the most recently uploaded second historical raster data of the target raster area when making the next prediction.

[0108] In one embodiment, the measurement data includes a first measurement value of the network quality of a first serving cell and a second measurement value of the network quality of a second serving cell; the first serving cell is the serving cell for which the vehicle is currently using the network service, and the second serving cell is the serving cell with the strongest network quality among the serving cells that the vehicle can currently access, excluding the first serving cell;

[0109] The first data for determining the current grid area of ​​the vehicle based on the measurement data includes:

[0110] The first data is determined based on the first measurement value and the second measurement value.

[0111] This embodiment combines network quality measurements from the first serving cell and the second serving cell to determine the network quality of the current grid area. The first serving cell is the serving cell currently connected to by the vehicle, and the second serving cell is the serving cell with the strongest network quality (e.g., the strongest signal) other than the first serving cell. Generally, the vehicle will choose to connect to the serving cell with the strongest signal or the most stable signal. This embodiment, by combining the network quality measurements from the first and second serving cells, yields a more accurate network quality determination for the current grid area.

[0112] In one embodiment, determining the first data based on the first measurement value and the second measurement value includes:

[0113] A first weight value is determined based on the difference between the first measured value and the second measured value;

[0114] The first measurement value and the second measurement value are weighted based on the first weight value to obtain the first data.

[0115] For example, taking the prediction of RSRP value as an example, let the first data be Y. t The first measurement value is S t The second measurement value is N t The variable weight is α.

[0116] According to the weighted average formula, Y is obtained as follows: t =α·S t +(1-α)·N t The values ​​can be determined according to Table 1 below:

[0117]

[0118]

[0119] Table 1

[0120] In one embodiment, determining the predicted value of the network quality of the target raster region based on the first data and historical raster data of the target raster region includes:

[0121] The predicted value is obtained by weighting the first data and the historical raster data of the target raster region based on a preset second weight value.

[0122] For example, the first data Y is calculated. t Then, compare it with the historical raster data of the target raster area. Perform a weighted calculation, setting the second weight to β, as shown in the following formula: Received This is the predicted value of the network quality of the target raster region.

[0123] The second weight value β can be an exponential smoothing variable coefficient. The weighting operation is an exponential smoothing operation. Exponential smoothing is a special type of weighted moving average method. Exponential smoothing further strengthens the role of recent observations in the predicted value. Different weights are assigned to observations at different times, thereby increasing the weight of recent observations and enabling the predicted value to quickly reflect changes in the network quality of the target grid area.

[0124] like Figure 3 As shown, after the vehicle's infotainment system initiates the reporting of measurement data, the MEC server receives the measurement data and calculates Y. t Simultaneously, it retrieves the previous grid calculation value (historical grid data) from the edge cloud server. This grid data query is based on the location information reported by the vehicle's infotainment system. The result is calculated by combining the historical samples and the real-time sample Y. t Exponential smoothing prediction calculations are performed.

[0125] Assuming the variable coefficient β is set to 0.9 (adjustable), smoothing prediction begins at time Y1 (time) and continues until the next Uu-side data Y2 (time) is reported again. t Recalculate. Real-time reporting of sample D1 at time Y1, sample D2 at time Y2, and sample D3 at time Y3.

[0126] Get the previous grid calculation value G1, and based on G1 and Y... t Perform exponential smoothing forecast calculation. The time interval between the two reports from Y1 to Y2 is T1. The result of the forecast calculation from Y1 to Y2 (time period) is recorded as the most recent historical value G2 of the server. MEC reports G2 to the edge cloud database.

[0127] The time interval between the two reports from Y2 to Y3 is T2. When the MEC receives another data report from the Uu side at time Y3, it retrieves G2 from the edge cloud server as historical raster data and, based on G2 and Y... t Exponential smoothing forecasting is performed, and the result of the forecasting calculation for Y2 to Y3 (time period) is recorded as the server's most recent historical value G3. The same logic is then executed sequentially for Y4 and Y5. It's important to note that sample data reported by the real-time Uu interface may be reported simultaneously (slow-moving and congested scenarios do not cross grid lines), which could cause Y1 to Y2 (time period) to approach 0 infinitely. t The difference between Gt and Gt tends to stabilize within a small fluctuation range, which is consistent with the sample convergence and can truly reflect the network condition.

[0128] The advantage of smoothing forecasts is that they can utilize historical data, with more recent data receiving greater weight, allowing for faster responses to network changes. A larger variable coefficient β indicates a focus on recent data. If the data in the sequence fluctuates significantly, the value of the variable coefficient β can be lowered to better reflect changing trends. Therefore, applying this principle, for smoothing forecast calculations within the switching band, the variable coefficient β can be set to 0.5 (which must be less than the initial parameter of 0.9).

[0129] In one embodiment, the method further includes:

[0130] Upon receiving a network switching request message uploaded by the vehicle, the second weight value is reduced from a first set value to a second set value; the switching request message indicates that the vehicle is currently in a network switching zone;

[0131] Upon receiving the network switching completion message uploaded by the vehicle, the second weight value is adjusted to the first set value.

[0132] like Figure 4 As shown, when the vehicle experiences a network handover zone, if the information reported by the vehicle includes a network handover request message (SAhandoverrequest), the MEC immediately triggers an adjustment of the variable coefficient β (second weight value) in a specified grid area, lowering β. For example, β is adjusted from its original value of 0.9 (first set value) to 0.5 (second set value). This reduces the volatility of the predicted data and optimizes data confidence. When the information reported by the vehicle includes a network handover success message (SAhandover success), the MEC triggers a variable coefficient reversal switch, reverting β back to its original value before adjustment. For example, β is adjusted from 0.5 to its original value of 0.9.

[0133] This application combines the characteristics of weighted averaging and single exponential smoothing algorithms. When selecting measured values, it uses adjustable weight parameters based on optimization expert experience to perform a weighted average of the strongest neighbor cell sample and the primary serving cell sample. This aims to account for network condition fluctuations caused by frequent handovers and varying coverage scenarios in road network environments. This method is applicable to various network condition indicators such as SINR, RSSI, RSRQ, throughput, and resource utilization. Threshold intervals and parameter configuration values ​​can be set as needed. In the stage of fusing historical data with measured values ​​for prediction, single exponential smoothing is used to focus on the impact of historical data, enhancing the stability of the predicted values. The selection of parameters also considers the possibility of large network condition fluctuations during handover, combined with a handover signaling-triggered parameter adjustment mechanism. The data calculation method for customized optimization parameters has been simplified, mainly considering the characteristics of fast sample update speed, high mobility (frequent handovers), low latency, and high reliability in road network environments. It emphasizes the high weight of recent data, the continuity of historical network condition data, and the continuity of wireless networks, which are more suitable for vehicle-road cooperative services.

[0134] In one embodiment, the method further includes:

[0135] Fill the predicted value into the target grid area;

[0136] Update map information based on the target raster area with updated predicted values;

[0137] The updated map information is sent to the vehicle.

[0138] The prediction results are updated to the assigned raster and backfilled. All raster values ​​with updated predictions are iterated through map information, packaged into a local map file, and distributed to the vehicle via Uu. Since the MEC server typically only handles information collection and analysis within a specific geographic area, it matches the location of the vehicle requesting prediction to its assigned MEC and distributes a network condition map for that area to the vehicle. In cases involving multiple MEC jurisdictions, edge cloud servers are required for map collaboration between MECs; for example, MEC1 and MEC2 might simultaneously distribute update results to the vehicle.

[0139] After receiving the real-time updated network condition map, the vehicle can work with the in-vehicle navigation software to provide network condition guidance and prompts for the destination route. In remote control and autonomous driving scenarios, the vehicle's system can plan the optimal route based on the predicted network condition values.

[0140] like Figure 5 As shown, Figure 5 This is an architecture diagram of a road network condition prediction system provided in an embodiment of the present invention. A 5G Radio Access Network (RAN) is deployed near the road, primarily using the Uu interface of the base station (generationNodeB, gNodeB) to establish uplink and downlink data links for vehicle-side data reporting and prediction result distribution. The vehicle-side, acting as a user equipment (UE), connects to the 5G network via the Uu interface to request services and receive results (uplink and downlink).

[0141] The gNodeB connects to the near-end edge computing server (MEC). The MEC is primarily responsible for data storage, computation, and analysis of the managed road segments. Data cleaning, rasterization, and prediction algorithms are all executed within the MEC. The gNodeB and MEC communicate with each other for data transmission and the distribution of analysis results.

[0142] MECs and edge cloud servers communicate with each other. Edge cloud servers primarily store, compute, and analyze historical data, and are classified as cloud computing servers. Before performing data computation, MECs need to retrieve historical data from the edge cloud server. Simultaneously, the computation results from several MECs need to be transmitted back to the edge cloud server for data fusion and wide-area map updates.

[0143] exist Figure 5 When a vehicle enters the signal coverage area of ​​a base station, it initiates a prediction request, which reaches MEC1 via the base station's NR-Uu-1 radio interface. MEC1 then predicts the network quality of the predicted grid. When the vehicle enters a network handover zone (an area where the signals of two base stations mutually cover each other), a network handover is performed. After the vehicle completes the network handover, it initiates a prediction request to MEC2 via the NR-Uu-2 radio interface.

[0144] The edge cloud server connects several MECs (including MEC1 and MEC2) and is primarily responsible for data collaboration between MECs to ensure the continuity of user services. It also collects analysis results data returned from each MEC to manage a wide-area map.

[0145] Data is primarily introduced from two supply sides. One is network condition data collected and reported in real time by the vehicle, such as voltage level, quality, vehicle speed, resource usage, and throughput. This type of data mainly reflects the vehicle's network awareness level via the Uu interface. The data path is from the vehicle to the MEC via the Uu interface, and from the MEC to the mobile edge cloud (including V2X servers).

[0146] Another type is historical data accumulated in the cloud (including V2X servers). This type of data mainly objectively describes the changing trends of network conditions from a time-domain perspective and provides feedback on the average coverage level from a location-domain perspective. The data path is from the mobile edge cloud (including V2X servers) database down to the MEC and then distributed to the vehicle via the Uu interface.

[0147] Data path as follows Figure 6 As shown, the vehicle-mounted system (T-BOX) collects and reports measurement data in real time, the 5G-Uu interface serves as the output for conclusion data and the input for samples; the MEC is a computing node used for data processing and analysis; and the edge cloud server is a historical data pool.

[0148] The MEC mainly includes four functions: data preprocessing, sample point rasterization, network condition prediction, and conclusion fitting map push. Data samples entering the MEC are processed sequentially from preprocessing to result push, and finally sent to the requesting vehicle end through the 5G-Uu exit.

[0149] Data preprocessing includes:

[0150] Both historical data and updated vehicle-side data must adhere to the regulated data format requirements. Data samples that do not meet these requirements will be discarded during the data cleaning process, such as missing latitude and longitude coordinates, data outside the specified range, positive RSRP values, missing SINR and RSRQ values, or vehicle speeds exceeding theoretical values. Data cleaning is completed on the MEC side and is the first step in data preprocessing. The vehicle's infotainment system is equipped with a data acquisition module (or probe-type module), pre-configured with a sample format (a specific protocol must be agreed upon, such as collecting sample data every 0.2 seconds, including vehicle speed, latitude and longitude, and RSRQ), and collects and reports data according to a time sequence. The cycle is approximately 0.2-0.5 seconds to complete a sample at a single latitude and longitude coordinate, which is then uploaded to the MEC side via 5G-Uu. The MEC performs data preprocessing according to the following format: Figure 7 and Figure 8 As shown.

[0151] It should be noted that network handover events are random, and handover data is not reported continuously; it needs to be reported according to a time sequence. Figure 7 The sample data shown is matched and merged. Once the sample data has been cleaned and merged, it can proceed to the next step of sample point rasterization.

[0152] Sample point rasterization includes:

[0153] The sample data obtained from data preprocessing are all point samples. Each point sample is identified based on its unique latitude, longitude, and time series. The military grid method is introduced to divide the geographic information (map) under the jurisdiction of the MEC into 25-meter grids, and all point samples are projected into their respective grids.

[0154] A new raster index format is defined based on the Military Grid Reference System (MGRS). The format of MGRS coordinates is: Universal Transverse Mercator (UTM) longitude zone number + UTM latitude zone number + MGRS longitude zone number + MGRS latitude zone number + MGRS longitude east offset + MGRS longitude north offset.

[0155] The raster index format can be: MGRS area number - Normalized MGRS longitude east offset - Normalized MGRS longitude north offset - Raster precision. The MGRS area number consists of the first 5 digits of the MGRS coordinates. The specific formula for processing the normalized MGRS longitude northeast offset is as follows:

[0156] Normalized MGRS longitude east offset = int(MGRS longitude east offset / raster precision)

[0157] Normalized MGRS longitude north offset = int(MGRS longitude north offset / raster precision)

[0158] Three grid precisions are available for customization: 25, 50, and 100. These represent square areas with side lengths of 25 meters, 50 meters, and 100 meters in the military grid coordinate system, respectively.

[0159] The conversion method between latitude / longitude coordinates and raster index is as follows: First, convert the latitude / longitude coordinates to military raster coordinates. Then, use the formula above to convert the military raster coordinates to normalized military raster coordinates according to the raster precision. For example, the sampling point at latitude / longitude coordinates (110.3456, 31.2468) has the converted military raster coordinates 49RDQ3768757138. The raster index after conversion with 50-meter precision is 49RDQ-753-1142-50; and the raster index after conversion with 100-meter precision is 49RDQ-376-571-100. The latitude and longitude range of a raster area can be calculated from its index. For example, the raster with index 49RDQ-753-1142-50 represents the square area defined by the military coordinates 49RDQ3765057100 and 49RDQ3770057150, which translates to a square area defined by the diagonal points (110.345204, 31.246448) and (110.345726, 31.246902). Similarly, the raster 49RDQ-376-571-100 represents the square area defined by the military coordinates 49RDQ3760057100 and 49RDQ3770057200, which can also be converted to the corresponding latitude and longitude range. This allows for the calculation of the Geographic Information System (GIS) area on MapInfo. System (GIS) rendering.

[0160] Will Figure 7 The effect of converting the example data in the image into raster data is as follows: Figure 9 As shown, the rasterized sample data can reflect the characteristic indicators of all included sample points within a raster precision range, such as 25*25 square meters. The mean, maximum, and minimum values ​​of the samples can be used as references. Various indicators can be rasterized in this way. This step adds geographical location tags to various network condition information samples, facilitating subsequent location-based query operations.

[0161] After collecting and preprocessing the standardized sample data reported in real time by the vehicle-side acquisition device, MEC rasterizes the real-time data and iteratively updates it with the historical raster database obtained from the edge cloud server, preparing the corresponding underlying data for the next prediction algorithm.

[0162] When a user initiates a forecast request at a single latitude and longitude, the MEC receives the forecast request message and the latitude and longitude of the forecast initiation point through Uu, and then queries the historical raster library to find the raster to which that latitude and longitude belongs.

[0163] Simultaneously, starting from the current raster number, the grid information query for the cross-shaped range of raster cells can be expanded. (See also...) Figure 5 The four pentagram positions in the grid range are defined in this embodiment. The cross query range used in this application is four grids (a total of 17 grid information), each grid size is 25 meters, that is, the grid network condition prediction information within a 100-meter range in each of the east, south, west, and north directions. MEC completes the four pentagram marking ranges (see...). Figure 5 After determining the raster index, the query results are used as updates to populate the map.

[0164] Cross-grid queries, through predictions in four directions, can effectively adapt to real-time vehicle dynamics, such as left and right turns, reversing, and emergency braking. This embodiment uses a value of 100 meters, primarily considering the possible braking distance range of a vehicle at a speed of 120 km / h, enabling network data to effectively guide the vehicle's next decision.

[0165] like Figure 10 As shown, Figure 10 This is a schematic diagram of the network condition map production process provided in the embodiment of the present invention. The current prediction result value is backfilled into the corresponding grid, the grid signal map of the MEC area is updated, and the map is returned to the requesting vehicle.

[0166] The prediction results are updated to the assigned raster and backfilled. All raster values ​​with updated predictions are iterated through map information, packaged into a local map file, and distributed to the requesting vehicle via Uu. Since MECs typically only handle information collection and analysis within a specific geographic area, the location of the currently requesting vehicle is matched to its assigned MEC, and a network condition map for that area is distributed to the vehicle. In cases involving cross-MEC jurisdictions, edge cloud servers are required for map collaboration between MECs; for example, MEC1 and MEC2 may simultaneously distribute update results to the vehicle.

[0167] This application embodiment is based on the "vehicle-MEC-cloud server" network architecture of the Internet of Vehicles (IoV). It utilizes the high speed, low latency, reliability, and security characteristics of MEC computing, and integrates data analysis and Geographic Information System (GIS) processing methods to achieve the collection, analysis, prediction, and push of road network condition data. This enables the prediction capability of road condition in vehicle-road cooperative scenarios and provides real-time road network information assistance for remote control, semi-autonomous driving, and unmanned driving services in IoV applications.

[0168] Through the embodiments of this application, vehicles can initiate prediction requests using the operator's wireless network connection (Uu interface) and instantly and seamlessly obtain network condition information in the future driving trajectory, effectively guiding the vehicle to execute the next operational strategy based on the network conditions. This method and process can provide real-time road condition assistance information for remote control, semi-autonomous driving, and autonomous driving services in vehicle-to-everything (V2X) applications.

[0169] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0170] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0171] It should be noted that the technical solutions described in the embodiments of the present invention can be combined arbitrarily without conflict.

[0172] In addition, in the embodiments of the present invention, "first," "second," etc. are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0173] refer to Figure 11 , Figure 11 This is a schematic diagram of a network quality prediction device provided in an embodiment of the present invention, such as... Figure 11 As shown, the device includes:

[0174] The receiving module 1101 is used to receive measurement data on the network quality of the current serving cell uploaded by the vehicle terminal;

[0175] The first determining module 1102 is used to determine first data of the grid area where the vehicle is currently located based on the measurement data; the first data characterizes the network quality of the grid area where the vehicle is currently located.

[0176] The second determining module 1103 is used to determine a predicted value of the network quality of the target grid region based on the first data and historical grid data of the target grid region; the target grid region is the area to be traversed by the vehicle, and the historical grid data characterizes the historical network quality of the target grid region.

[0177] In one embodiment, the device further includes:

[0178] The third determining module is used to determine whether the measurement data uploaded by the vehicle meets the preset format requirements;

[0179] The discard module is used to discard the measurement data if the measurement data uploaded by the vehicle does not meet the preset format requirements.

[0180] The first determining module 1102 is specifically used to determine the first data based on the measurement data if the measurement data uploaded by the vehicle meets the preset format requirements.

[0181] In one embodiment, the device further includes:

[0182] The query module is used to query the historical raster data of the target raster area in the cloud server based on the identifier of the target raster area; the cloud server stores the historical raster data of each target raster area.

[0183] In one embodiment, the device further includes:

[0184] The acquisition module is used to acquire the most recently uploaded first historical raster data of the target raster area from the cloud server;

[0185] Correspondingly, the second determining module 1103 is specifically used for:

[0186] Based on the first data and the first historical raster data, a predicted value of the network quality of the target raster region is determined;

[0187] The device further includes:

[0188] The storage module is used to store the predicted value as the second historical raster data of the target raster area into the cloud server.

[0189] In one embodiment, the measurement data includes a first measurement value of the network quality of a first serving cell and a second measurement value of the network quality of a second serving cell; the first serving cell is the serving cell for which the vehicle is currently using the network service, and the second serving cell is the serving cell with the strongest network quality among the serving cells that the vehicle can currently access, excluding the first serving cell;

[0190] The first determining module 1102 is specifically used for:

[0191] The first data is determined based on the first measurement value and the second measurement value.

[0192] In one embodiment, the first determining module 1102 is specifically used for:

[0193] A first weight value is determined based on the difference between the first measured value and the second measured value;

[0194] The first measurement value and the second measurement value are weighted based on the first weight value to obtain the first data.

[0195] In one embodiment, the second determining module 1103 is specifically used to: perform a weighted operation on the first data and the historical raster data of the target raster region based on a preset second weight value to obtain the predicted value.

[0196] In one embodiment, the device further includes:

[0197] The adjustment module is used to reduce the second weight value from a first set value to a second set value when receiving a network switching request message uploaded by the vehicle terminal; the switching request message indicates that the vehicle terminal is currently in a network switching zone;

[0198] Upon receiving the network switching completion message uploaded by the vehicle, the second weight value is adjusted to the first set value.

[0199] In one embodiment, the device further includes:

[0200] The filling module is used to fill the predicted value into the target grid area;

[0201] The update module is used to update map information for target raster areas based on updated prediction values;

[0202] The distribution module is used to distribute the updated map information to the vehicle.

[0203] In practical applications, the receiving module 1101, the first determining module 1102, and the second determining module 1103 can be implemented by processors in the server, such as central processing units (CPUs), digital signal processors (DSPs), microcontroller units (MCUs), or field-programmable gate arrays (FPGAs).

[0204] It should be noted that the network quality prediction device provided in the above embodiments is only illustrated by the division of the above modules when performing network quality prediction. In practical applications, the above processing can be assigned to different modules as needed, that is, the internal structure of the device can be divided into different modules to complete all or part of the processing described above. In addition, the network quality prediction device and the network quality prediction method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0205] The aforementioned network quality prediction device can be in the form of an image file. After execution, this image file can run as a container or virtual machine to implement the network quality prediction method described in this application. However, it is not limited to the image file format; any software implementation capable of the network quality prediction method described in this application is within the scope of protection of this application.

[0206] Based on the hardware implementation of the above program modules, and in order to implement the method of the embodiments of this application, the embodiments of this application also provide a server, wherein the above network quality prediction method is implemented by the processor of the server. Figure 12 This is a schematic diagram of the hardware structure of the server in an embodiment of this application, as shown below. Figure 12 As shown, the server includes:

[0207] The communication interface 1201 enables information exchange with other devices, such as network devices.

[0208] The processor 1202 is connected to the communication interface 1201 to enable information interaction with other devices and, when running a computer program, executes the methods provided by one or more of the aforementioned server-side technical solutions. The computer program is stored in the memory 1203.

[0209] Of course, in practical applications, the various components in the server are coupled together through the bus system 1204. It can be understood that the bus system 1204 is used to implement communication between these components. In addition to the data bus, the bus system also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 12 The general designated all buses as Bus System 1204.

[0210] The memory 1203 in this embodiment is used to store various types of data to support server operations. Examples of such data include any computer programs used to operate on the server.

[0211] In this application, the server can be a single hardware device or a cluster of multiple hardware devices, such as a cloud computing platform. A cloud computing platform is a cluster device that organizes multiple independent server physical hardware resources into a pool of resources, providing the necessary virtual resources and services to the outside world.

[0212] The memory 1203 in this embodiment is used to store various types of data to support the operation of the server. Examples of such data include any computer programs used to operate on the server.

[0213] It is understood that memory 1203 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memories described in the embodiments of this application are intended to include, but are not limited to, these and any other suitable types of memories.

[0214] The methods disclosed in the embodiments of this application can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor may be a general-purpose processor, a DSP, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. A general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in memory. The processor reads the program from the memory and, in conjunction with its hardware, completes the steps of the aforementioned method.

[0215] Optionally, when the processor executes the program, it implements the corresponding processes implemented by the server in the various methods of the embodiments of this application. For the sake of brevity, these will not be described in detail here.

[0216] In an exemplary embodiment, this application also provides a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, such as a first memory storing a computer program, which can be executed by a server's processor to complete the steps described in the aforementioned method. The computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disc, or CD-ROM.

[0217] In the several embodiments provided in this application, it should be understood that the disclosed apparatus, server, and method can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0218] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0219] In addition, each functional unit in the various embodiments of this application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0220] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0221] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0222] It should be noted that the technical solutions described in the embodiments of this application can be combined arbitrarily without conflict.

[0223] In addition, in this application example, terms such as "first" and "second" are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0224] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A network quality prediction method, characterized in that, The method includes: Receive network quality measurement data of the current serving cell uploaded by the vehicle terminal; Based on the measurement data, first data is determined for the current grid area where the vehicle is located; the first data characterizes the network quality of the current grid area where the vehicle is located. The first data and the historical raster data of the target raster region are weighted based on a preset second weight value to determine the predicted value of the network quality of the target raster region; the target raster region is the area to be traversed by the vehicle, and the historical raster data characterizes the historical network quality of the target raster region; wherein, the method further includes: Upon receiving a network switching request message uploaded by the vehicle terminal, the second weight value is reduced from the first set value to the second set value; the switching request message indicates that the vehicle terminal is currently in a network switching zone; upon receiving a network switching completion message uploaded by the vehicle terminal, the second weight value is adjusted back to the first set value.

2. The method according to claim 1, characterized in that, Before determining the first data of the current grid area of ​​the vehicle based on the measurement data, the method further includes: Determine whether the measurement data uploaded by the vehicle meets the preset format requirements; If the measurement data uploaded by the vehicle does not meet the preset format requirements, the measurement data will be discarded. If the measurement data uploaded by the vehicle meets the preset format requirements, then the first data is determined based on the measurement data.

3. The method according to claim 1, characterized in that, Before determining the predicted value of the network quality of the target raster region based on the first data and historical raster data of the target raster region, the method further includes: Based on the identifier of the target raster region, the historical raster data of the target raster region is queried in the cloud server; the cloud server stores the historical raster data of each target raster region.

4. The method according to claim 3, characterized in that, The method further includes: Obtain the most recently uploaded first historical raster data of the target raster region from the cloud server; Correspondingly, determining the predicted value of the network quality of the target raster region based on the first data and historical raster data of the target raster region includes: Based on the first data and the first historical raster data, a predicted value of the network quality of the target raster region is determined; Correspondingly, after determining the predicted value of the network quality of the target raster region, the method further includes: The predicted value is recorded as the second historical raster data of the target raster area and stored in the cloud server.

5. The method according to claim 1, characterized in that, The measurement data includes a first measurement value of the network quality of the first serving cell and a second measurement value of the network quality of the second serving cell; the first serving cell is the serving cell for which the vehicle is currently using the network service, and the second serving cell is the serving cell with the strongest network quality among the serving cells that the vehicle can currently access, excluding the first serving cell; The first data for determining the current grid area of ​​the vehicle based on the measurement data includes: The first data is determined based on the first measurement value and the second measurement value.

6. The method according to claim 5, characterized in that, Determining the first data based on the first measurement value and the second measurement value includes: A first weight value is determined based on the difference between the first measured value and the second measured value; The first measurement value and the second measurement value are weighted based on the first weight value to obtain the first data.

7. The method according to claim 1, characterized in that, The method further includes: Fill the predicted value into the target grid area; Update map information based on the target raster area with updated predicted values; The updated map information is sent to the vehicle.

8. A network quality prediction device, characterized in that, include: The receiving module is used to receive measurement data on the network quality of the current serving cell uploaded by the vehicle. The first determining module is used to determine the first data of the grid area where the vehicle end is currently located based on the measurement data; The first data characterizes the network quality of the grid area where the vehicle is currently located; The second determining module is used to perform a weighted operation on the first data and the historical grid data of the target grid region based on a preset second weight value to determine the predicted value of the network quality of the target grid region; the target grid region is the area to be traversed by the vehicle end, and the historical grid data represents the historical network quality of the target grid region; The adjustment module is used to reduce the second weight value from a first set value to a second set value when receiving a network switching request message uploaded by the vehicle terminal; the switching request message indicates that the vehicle terminal is currently in a network switching zone; Upon receiving the network switching completion message uploaded by the vehicle, the second weight value is adjusted to the first set value.

9. A server comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the network quality prediction method as described in claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the network quality prediction method as described in claims 1 to 7.

Images