Data processing method, related equipment and computer storage medium

Abstract

The embodiment of the invention discloses a data processing method, related equipment and a computer storage medium. The method comprises the following steps: acquiring a signal quality map dynamically constructed based on historical communication quality data of each communication cell in a navigation map, a traffic load map dynamically constructed based on historical traffic load data of each communication cell, and a traffic transmission map dynamically constructed based on traffic transmission data of each communication cell; then, fusing the signal quality map, the traffic load map and the traffic transmission map to obtain a network quality map; and finally, determining a driving control strategy of the vehicle-mounted terminal according to the network quality map, so that the vehicle-mounted terminal performs vehicle control processing according to the driving control strategy. According to the technical scheme of the embodiment of the invention, the estimation accuracy of the network quality can be improved.

Description

Technical Field

[0001] The present application relates to the field of computer and communication technology, and in particular, to a data processing method, a video processing device, an electronic device, a computer storage medium, and a computer program product. Background Art

[0002] As an important branch of intelligent transportation, Internet of Vehicles technology plays a huge role in safe driving. The core of Internet of Vehicles technology is data sharing between related equipment such as vehicle terminals, roadside base stations, and Internet of Vehicles servers. Since the vehicle terminals are in a mobile state, and the network conditions at different locations are different; therefore, the data transmission quality of the vehicle terminals is often affected by network instability. In related technologies, the network conditions at the location of the vehicle terminal are predicted by constructing a network quality map, so that a response strategy can be provided according to the network conditions at the corresponding location, thereby improving the data transmission quality. However, the accuracy of the current network quality map is low, resulting in a significant improvement in the data transmission quality of the vehicle terminal. Therefore, how to improve the accuracy of network quality estimation is an urgent problem to be solved. Summary of the invention

[0003] The embodiments of the present application provide a data processing method, a data processing device, an electronic device, a computer storage medium, and a computer program product, which can improve the accuracy of network quality estimation.

[0004] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0005] In a first aspect, an embodiment of the present application provides a data processing method, including:

[0006] Obtaining a signal quality map dynamically constructed based on historical communication quality data of each communication cell in the navigation map, a traffic load map dynamically constructed based on historical traffic load data of each communication cell, and a traffic transmission map dynamically constructed based on traffic transmission data of each communication cell;

[0007] The signal quality map, the traffic load map and the traffic transmission map are fused to obtain a network quality map; wherein the network quality map includes an estimated data throughput of each position in the navigation map, and the estimated data throughput of each position is obtained based on the map data of the corresponding position in the signal quality map, the traffic load map and the traffic transmission map;

[0008] The driving control strategy of the vehicle-mounted terminal is determined according to the network quality map, so that the vehicle-mounted terminal performs vehicle control processing according to the driving control strategy.

[0009] In a second aspect, an embodiment of the present application provides a data processing device, the device comprising an acquisition unit and a processing unit, wherein:

[0010] The acquisition unit is used to acquire a signal quality map dynamically constructed based on historical communication quality data of each communication cell in the navigation map, a traffic load map dynamically constructed based on historical traffic load data of each communication cell, and a traffic transmission map dynamically constructed based on traffic transmission data of each communication cell;

[0011] The processing unit is used to fuse the signal quality map, the traffic load map and the traffic transmission map to obtain a network quality map; wherein the network quality map includes an estimated data throughput of each position in the navigation map, and the estimated data throughput of each position is obtained based on the map data of the corresponding position in the signal quality map, the traffic load map and the traffic transmission map;

[0012] The processing unit is further used to determine the driving control strategy of the vehicle-mounted terminal according to the network quality map, so that the vehicle-mounted terminal performs vehicle control processing according to the driving control strategy.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, which includes an input interface and an output interface, and also includes: a processor, suitable for implementing one or more instructions; and a computer storage medium, wherein the computer storage medium stores one or more instructions, and the one or more instructions are suitable for being loaded by the processor and executing the above-mentioned data processing method.

[0014] In a fourth aspect, an embodiment of the present application provides a computer storage medium, wherein the computer storage medium stores one or more computer programs, and the one or more computer programs are suitable for being loaded by a processor and executing the above-mentioned data processing method.

[0015] In a fifth aspect, an embodiment of the present application provides a computer program product or a computer program, wherein the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium; a processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, which, when executed by the processor, are used to execute the above-mentioned data processing method.

[0016] In the technical solution provided in the embodiments of the present application, the network quality map is obtained by integrating the transmission quality measurement data of multiple data dimensions such as signal quality, traffic load and traffic transmission by fusing the signal quality map, traffic load map and traffic transmission map; and the network quality map obtained by measuring multi-dimensional data can better simulate the complex and changeable actual network environment. Therefore, the map data in the network quality map in the embodiments of the present application will be more accurate, which is conducive to improving the accuracy of network quality estimation.

[0017] In addition, since the network quality map is obtained by integrating the dynamically constructed signal quality map, traffic load map, and traffic transmission map, the network quality map is also dynamically updated and has time-varying properties. Therefore, the network quality map in the embodiment of the present application can avoid inaccurate map data caused by data lag to a certain extent, which is conducive to further improving the accuracy of network quality estimation.

[0018] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a structural diagram of a data processing system provided in an embodiment of the present application;

[0020] Figure 2 It is a flowchart of a data processing method provided in an embodiment of the present application;

[0021] Figure 3 It is a flowchart of another data processing method provided in an embodiment of the present application;

[0022] Figure 4 is a schematic diagram of a map construction process provided in an embodiment of the present application;

[0023] Figure 5 is a structural diagram of another data processing system provided in an embodiment of the present application;

[0024] Figure 6 It is a schematic diagram of the architecture of a vehicle network data transmission system provided by an embodiment of the present application;

[0025] Figure 7 It is a flowchart of another data processing method provided in an embodiment of the present application;

[0026] Figure 8 is a schematic diagram of a data throughput prediction process provided by an embodiment of the present application;

[0027] Fig. 9 It is a flowchart of another data processing method provided in an embodiment of the present application;

[0028] Fig.10 is a schematic diagram of cross-layer optimization of data transmission provided by an embodiment of the present application;

[0029] Fig.11 is a structural block diagram of a data processing device provided in an embodiment of the present application;

[0030] Fig.12 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0031] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are only examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0032] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0033] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all contents and operations, nor must they be executed in the order described. For example, some operations may be decomposed, while some operations may be combined or partially combined, so the actual execution order may change according to actual conditions.

[0034] It should also be noted that the "multiple" mentioned in this application refers to two or more than two. "And / or" describes the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship.

[0035] With the continuous development of Internet technology, artificial intelligence (AI) technology has also been better developed. The so-called artificial intelligence technology refers to the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science; it mainly produces a new intelligent machine that can respond in a similar way to human intelligence by understanding the essence of intelligence, so that the intelligent machine has multiple functions such as perception, reasoning and decision-making. Correspondingly, AI technology is a comprehensive discipline, which mainly includes several major directions such as computer vision technology (Computer Vision, CV), speech technology, natural language processing technology and machine learning (Machine Learning, ML) / deep learning.

[0036] Among them, machine learning is a multi-disciplinary cross-discipline involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills, and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of AI and the fundamental way to make computer devices intelligent; the so-called machine learning is a multi-disciplinary cross-discipline involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines; it specializes in studying how computer devices simulate or implement human learning behavior to acquire new knowledge or skills, and reorganize existing knowledge structures to continuously improve their performance. Deep learning is a technology that uses deep neural network systems to perform machine learning; machine learning / deep learning can usually include artificial neural networks, reinforcement learning (RL), supervised learning, unsupervised learning and other technologies; the so-called supervised learning refers to the processing method of using training samples with known categories (with labeled categories) for model training, and unsupervised learning refers to the processing method of using training samples with unknown categories (not labeled) for model training.

[0037] In the related art, on the one hand, the network quality of the vehicle terminal is directly estimated through data such as the queue length of the data buffer queue of the vehicle terminal; however, the network environment is complex and changeable, and is affected by various factors (such as location, travel speed, number of surrounding vehicles, etc.). If the network quality is estimated based on a single piece of information, the result is actually not accurate. On the other hand, based on the sampled data collected by multiple terminal devices, the corresponding machine learning model can be trained or the corresponding variable function can be constructed to obtain a network quality map; the sampled data includes multiple environmental variables such as location and weather, as well as data related to network conditions such as network bandwidth. However, the network environment will change over time, and the network quality map constructed based on the sampled data can only estimate the network quality map under fixed environmental variables, and cannot be updated in time, so the accuracy of the network quality map is not high.

[0038] Based on this, the embodiment of the present application provides a data processing solution, which first obtains the dynamically constructed signal quality map, traffic load map and traffic transmission map; then fuses the signal quality map, traffic load map and traffic transmission map to finally obtain a network quality map. Finally, the driving control strategy of the vehicle terminal can be further determined based on the network quality map, so that the vehicle terminal performs vehicle control processing according to the driving control strategy.

[0039] Among them, the signal quality map is dynamically constructed based on the historical communication quality data of each communication cell in the navigation map; the traffic load map is dynamically constructed based on the historical traffic load data of each communication cell; and the traffic transmission map is dynamically constructed based on the traffic transmission data of each communication cell.

[0040] At the same time, since the network quality can be specifically measured by the amount of data successfully transmitted per unit time, the network quality map specifically includes the estimated data throughput of each location in the navigation map. Among them, the estimated data throughput of each location is obtained based on the signal quality map, the traffic load map, and the map data of the corresponding location in the traffic transmission map. Specifically, the map data of each location in the signal quality map is data that characterizes the signal quality of each location; the map data of each location in the traffic load map is data that characterizes the load conditions of each location; the map data of each location in the traffic transmission map is data that characterizes the transmission quality of each location. In addition, the driving control strategy can specifically be a strategy that can improve the data transmission quality of the vehicle-mounted terminal.

[0041] This solution integrates the signal quality map, traffic load map and traffic transmission map to make the network quality map a combination of data from three dimensions: signal quality, traffic load and traffic transmission. Multi-dimensional data can reflect the network situation from multiple perspectives. Therefore, compared with the network quality map obtained only by signal quality, traffic load or traffic transmission, the network quality map obtained by measuring multi-dimensional data is more similar to the complex and changeable actual network environment, and the estimated data throughput of each location is also more accurate.

[0042] In addition, since the signal quality map, traffic load map, and traffic transmission map are all dynamically constructed, the network quality map obtained by integrating the signal quality map, traffic load map, and traffic transmission map will also be dynamically updated. Therefore, the network quality map obtained by this solution can avoid data inaccuracy caused by data lag to a certain extent, which is conducive to improving the accuracy of network quality estimation.

[0043] It can be seen that this solution can greatly improve the accuracy of network quality estimation by constructing a network quality map in multiple dimensions through signal quality maps, traffic load maps, and traffic transmission maps, and dynamically updating the network quality map. In addition, this solution can specify a more reasonable driving control strategy through a highly accurate network quality map, which is conducive to improving the driver's driving experience.

[0044] Based on the above data processing solution, the present application embodiment provides a data processing system, which can be seen in Figure 1 , Figure 1 The data processing system shown may include multiple vehicle-mounted terminals 101 and multiple servers 102. Among them, a communication connection is established between any vehicle-mounted terminal and any server. For example, the vehicle-mounted terminal 101 may include any one or more of a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart vehicle-mounted device, and a smart wearable device. A map navigation client, a multimedia player client, a browser client, an information stream client, etc. can be run in the vehicle-mounted terminal 101. The server 102 can be a server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms. Any vehicle-mounted terminal 101 and any server 102 can be directly or indirectly connected in communication through wired or wireless communication, and this application is not limited here.

[0045] In some embodiments, the above data processing method can be performed only by Figure 1The server 102 in the data processing system shown is executed, and the specific execution process is: the server 102 can obtain a signal quality map dynamically constructed based on the historical communication quality data of each communication cell in the navigation map, a traffic load map dynamically constructed based on the historical traffic load data of each communication cell, and a traffic transmission map dynamically constructed based on the traffic transmission data of each communication cell. Then, the server 102 can fuse the signal quality map, the traffic load map, and the traffic transmission map to obtain a network quality map. Afterwards, the server 102 can determine the driving control strategy of each vehicle terminal in the network quality map based on the network quality map, so that each vehicle terminal performs vehicle control processing according to the corresponding driving control strategy.

[0046] Optionally, the above data processing method may also be performed only by Figure 1 The vehicle-mounted terminal 101 in the data processing system shown is executed. The specific execution process can refer to the specific execution process of the server 102, which will not be repeated here.

[0047] In other embodiments, the above data processing method may be run in a data processing system, which may include a vehicle-mounted terminal and a server. Figure 1 The data processing system shown is jointly completed by the vehicle terminal 101 and the server 102 included in the system, and the specific execution process is as follows: the server 102 can obtain a signal quality map dynamically constructed based on the historical communication quality data of each communication cell in the navigation map, a traffic load map dynamically constructed based on the historical traffic load data of each communication cell, and a traffic transmission map dynamically constructed based on the traffic transmission data of each communication cell; then, the server 102 can fuse the signal quality map, the traffic load map and the traffic transmission map to obtain a network quality map; thereafter, the server 102 can determine the driving control strategy of the vehicle terminal 101 according to the network quality map; finally, the server 102 can send the driving control strategy to the vehicle terminal 101, so that the vehicle terminal 101 performs vehicle control processing according to the driving control strategy.

[0048] Optionally, the server 102 may also generate a control instruction that matches the driving control strategy, and then send the control instruction to the vehicle terminal 101, so as to control the vehicle terminal 101 to perform corresponding vehicle control processing through the control instruction.

[0049] It should be noted that the embodiments of the present application can be applied to various Internet of Vehicles scenarios such as intelligent driving and assisted driving, and can also be used for various network-dependent applications such as remote control applications, map navigation applications, video applications, etc., without limitation.

[0050] Specifically, the technical solution of the embodiment of the present application can be applied to intelligent driving scenarios, such as the vehicle can be set as an unmanned vehicle, and the server can be an assisted driving server that provides services for unmanned driving. Since many operations related to unmanned driving need to rely on the network to be carried out, there are high requirements for data transmission quality; therefore, the assisted driving server can obtain dynamically constructed signal quality maps, traffic load maps, and traffic transmission maps; then, the assisted driving server can fuse the signal quality map, traffic load map, and traffic transmission map to obtain a network quality map. After the assisted driving server obtains the network quality map, it can formulate in advance a strategy for optimizing the data transmission quality of the on-board terminal in the unmanned vehicle, thereby ensuring the driving of the unmanned vehicle. Specifically, the assisted driving server can determine the driving control strategy of the on-board terminal based on the network quality map, so that the on-board terminal in the unmanned vehicle performs vehicle control processing according to the driving control strategy.

[0051] For another example, the technical solution of the embodiment of the present application is applied to a video playback application, the vehicle-mounted terminal may be a vehicle-mounted terminal running a video application, and the server may be a video transmission server that provides services for the video application. Specifically, in order to enable the vehicle-mounted terminal to send the collected video to the video transmission server in a timely manner, and the vehicle-mounted terminal to receive the video sent by the video transmission server in a timely manner; the video transmission server may obtain a dynamically constructed signal quality map, traffic load map, and traffic transmission map; then, the video transmission server may fuse the signal quality map, traffic load map, and traffic transmission map to obtain a network quality map. After the video transmission server obtains the network quality map, it may formulate a strategy in advance to optimize the data transmission quality of the vehicle-mounted terminal, thereby ensuring video transmission. Among them, the video transmission server may determine the driving control strategy of the vehicle-mounted terminal based on the network quality map, so that the vehicle-mounted terminal performs vehicle control processing according to the driving control strategy.

[0052] It should be noted that in the specific implementation of the present application, if historical communication quality data, historical traffic load data, traffic transmission data and other related data or information are related to objects, when the embodiments of the present application are applied to specific products or technologies, it is necessary to obtain the permission or consent of the object, and the collection, use and processing of relevant data or information need to comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0053] The following is a detailed description of various implementation details of the technical solution of the embodiment of the present application:

[0054] like Figure 2 As shown, Figure 2 is a flow chart of a data processing method according to an embodiment of the present application, which can be applied to Figure 1The data processing system shown in the figure, the method can be executed by the terminal device or the server, or can be executed by the terminal device and the server together. In the embodiment of the present application, the method is executed by the server as an example for explanation, wherein the data processing method may include S201 to S203, which are described in detail as follows:

[0055] S201. Obtain a signal quality map dynamically constructed based on historical communication quality data of each communication cell in the navigation map, a traffic load map dynamically constructed based on historical traffic load data of each communication cell, and a traffic transmission map dynamically constructed based on traffic transmission data of each communication cell.

[0056] In the embodiment of the present application, the communication cell may be an area covered by a base station or a part of a base station, and a terminal device within this area may communicate with the base station through a wireless channel.

[0057] Meanwhile, the historical communication quality data of each communication cell may include the quality data of the historical communication sessions generated in each communication cell, wherein the number of historical communication sessions includes one or more, and the quality data of each historical communication session includes the index collection value of each historical communication session under each type of signal index.

[0058] Specifically, the signal indicator may include at least one of signal strength (Received Signal Strength Indication, RSSI), signal to noise ratio (Signal to Interference plus Noise Ratio, SINR) and signal reception success rate (Reference Signal Receiving Power, RSRP). Optionally, the signal indicator may also include other types of indicators that can measure communication resources such as signal quality or signal strength, such as reference signal receiving quality (Reference Signal Receiving Quality, RSRQ), which are not limited here.

[0059] In addition, the historical traffic load data of each communication cell may include the load index of each communication cell at each historical time point. Optionally, the historical traffic load data of each communication cell may include the load index of each communication cell at each historical time point, and the load index of each communication cell at the current time point. Specifically, the load index may include at least one of the number of access devices and data throughput. Optionally, the load index may also include other indicators that can measure the available channel resources in the communication cell, which are not limited here.

[0060] In addition, the traffic transmission data of each communication cell may include the index value of the data transmission index of each communication cell at the historical time point and / or the current time point. Specifically, the data transmission index may include at least one of data throughput, data transmission delay and packet loss rate. Optionally, the data transmission index may also include other indicators that can measure the quality of data transmission, such as bit error rate, which are not limited here.

[0061] In one embodiment, dynamic construction is equivalent to periodic construction, and the update period of the signal quality map, the traffic load map, and the traffic transmission map can be the same or different. Specifically, it can be set to construct a new signal quality map, a new traffic load map, and a new traffic transmission map every preset time period, so the signal quality map, the traffic load map, and the traffic transmission map are time-varying. Among them, the preset time period can be 1 millisecond, 1 second, 2 minutes, 1 day, 2 months, etc., and is not limited here.

[0062] Optionally, since signal quality is mainly determined by the signal base station, the location and antenna direction of the signal base station usually do not change, so the signal quality at each location is difficult to change in a short time, so the update period of the signal quality map can be longer than the update period of the traffic load map and the traffic transmission map. Optionally, since the load of each communication cell changes steadily over time, there is no need to pursue real-time performance too much, so the update period of the traffic load map can be longer than the update period of the traffic transmission map.

[0063] S202: Fusing the signal quality map, the traffic load map, and the traffic transmission map to obtain a network quality map.

[0064] In the embodiment of the present application, since a larger data throughput indicates a better network quality, the network quality can be characterized by the data throughput; therefore, the network quality map can specifically include the estimated data throughput of each location in the navigation map. The estimated data throughput of each location is obtained based on the map data of the corresponding location in the signal quality map, the traffic load map, and the traffic transmission map.

[0065] It should be noted that each location in the map can be a small area in the map, such as an area of ​​1 square meter, an area of ​​5 square meters, etc., without limitation. In addition, since Quality of Service (QoS) can be used to characterize the service capabilities that network communications can provide, the network quality map can also be called a QoS map.

[0066] Optionally, since signal quality can be numerically expressed by the amount of communication resources, the signal quality map can specifically include the amount of communication resources at each location in the navigation map. Optionally, since the better the channel quality, the greater the number of devices and the amount of data that the channel can carry, the traffic load situation can be characterized by the channel quality; therefore, the traffic load map can specifically include the channel quality at each location in the navigation map. Optionally, since the better the data transmission quality, the better the traffic transmission situation, the traffic transmission situation can be characterized by the data transmission quality; therefore, the traffic transmission map can specifically include the data transmission quality at each location in the navigation map.

[0067] Then, the map data of the corresponding position in the signal quality map may refer to the amount of communication resources at the corresponding position in the signal quality map; the map data of the corresponding position in the traffic load map may refer to the channel quality of the corresponding position in the traffic load map; and the map data of the corresponding position in the traffic transmission map may refer to the data transmission quality of the corresponding position in the traffic transmission map.

[0068] In one embodiment, the specific method of fusion processing can be: for any location in the navigation map, the map data of the corresponding location in the signal quality map, the traffic load map and the traffic transmission map are weighted added to obtain the estimated data throughput of any location.

[0069] Optionally, the map data weights of different maps may be the same or different. Optionally, since the update cycles of the signal quality map, traffic load map, and traffic transmission map mentioned in step S201 may be different, and map data with a short update cycle has a higher real-time performance, the map data weights of different maps may be determined according to the update cycle; wherein the update cycle is inversely correlated with the map data weight, that is, the longer the update cycle, the smaller the map data weight.

[0070] Optionally, the map data in the signal quality map, the traffic load map, and the traffic transmission map may be fused in other ways to obtain a network quality map, which is not limited here.

[0071] S203: Determine a driving control strategy of the vehicle-mounted terminal according to the network quality map, so that the vehicle-mounted terminal performs vehicle control processing according to the driving control strategy.

[0072] In the embodiment of the present application, the driving control strategy may specifically be a strategy for improving the data transmission quality of the vehicle-mounted terminal. Specifically, the driving control strategy may include one or more strategies for improving the data transmission quality of the vehicle-mounted terminal, such as selecting a path with better network quality for the vehicle, controlling the data transmission rate of the vehicle-mounted terminal, and controlling the encoding bit rate of the vehicle-mounted terminal for data.

[0073] In one embodiment, a specific method for determining the driving control strategy of the vehicle-mounted terminal based on the network quality map may be: the server first determines multiple driving paths based on the vehicle's terminal position and current driving position; then, the server may determine the network quality of each driving path based on the network quality map; if the network quality of a certain driving path is higher than the network quality of the current driving path, the server may generate a driving control strategy based on the driving path, and send the driving control strategy to the vehicle-mounted terminal, so that the vehicle-mounted terminal controls the vehicle to travel along the driving path.

[0074] In an embodiment of the present application, by integrating the signal quality map, the traffic load map and the traffic transmission map, the network quality map is obtained by integrating the data of the three dimensions of signal quality, traffic load and traffic transmission; the multi-dimensional data can reflect the network situation from multiple perspectives. Therefore, compared with the network quality map obtained only by signal quality, only by traffic load or only by traffic transmission, the network quality map obtained by measuring the multi-dimensional data can better simulate the complex and changeable actual network environment, thereby greatly improving the accuracy of network quality estimation.

[0075] In addition, since the network quality map is obtained by integrating the dynamically constructed signal quality map, traffic load map, and traffic transmission map, the network quality map is also dynamically updated and has time-varying properties. Therefore, the network quality map in the embodiment of the present application can avoid inaccurate map data caused by data lag to a certain extent, which is conducive to further improving the accuracy of network quality estimation.

[0076] In one embodiment of the present application, another data processing method is provided, which can be applied to Figure 1 The data processing system shown in the figure, the method can be executed by the terminal device or the server, or by the terminal device and the server together. In the embodiment of the present application, the method is described by taking the server as an example. Figure 3 FIG. 1 is a flow chart showing another data processing method. Figure 2 This paper expands on the method shown in .

[0077] Among them, S301 to S305 are described in detail as follows:

[0078] S301. Dynamically construct a signal quality map according to historical communication quality data of each communication cell within a first preset unit time period.

[0079] In the embodiment of the present application, the unit time period refers to the time period of an update cycle; the first preset unit time period refers to: the time period corresponding to the previous update cycle of the current update cycle of the signal quality map. The time length of the update cycle of the signal quality map can be set manually, or it can be set by the vehicle-mounted device or server in the above-mentioned data processing system, and there is no limitation on this. For example, when the update cycle of the signal quality map is 1 day, today's signal quality map is constructed based on the historical communication quality data generated by each communication cell yesterday.

[0080] In addition, the historical communication quality data within the first preset unit time period may include communication quality data at each historical time point within the first preset unit time period.

[0081] In one embodiment, the specific method of dynamically constructing a signal quality map can be: determining the index values ​​of various signal indicators based on the quality data of historical communication sessions generated in each communication cell; determining the communication resource amount of the corresponding communication cell based on the index values ​​of various signal indicators; and dynamically constructing a signal quality map based on the communication resource amount of each communication cell.

[0082] The historical communication sessions generated in each communication cell are specifically historical communication sessions generated in each communication cell within a first preset unit time period from the current time point. The number of historical communication sessions generated in a communication cell may include one or more.

[0083] Optionally, since the quality data of each historical communication session mentioned in step S201 may specifically include the index collection values ​​of each historical communication session under each type of signal index, then the specific method of determining the index values ​​of each type of signal index may be: for multiple historical communication sessions generated in any communication cell, calculate the weighted sum of the index collection values ​​belonging to the same type of signal index to obtain the index values ​​of each type of signal index.

[0084] Among them, the weights of different historical communication sessions can be the same or different. For example, the weights of each historical communication session in a communication cell can be set to be the inverse of the number of all historical communication sessions in the communication cell, so the weighted sum is equivalent to finding the average value of the index collection values ​​of the same type of signal index in the communication cell. For another example, if the generation time of different historical communication sessions is different, the weight of the historical communication session with a shorter generation time from the current time point can be set to be greater than the weight of the historical communication session with a longer generation time from the current time point.

[0085] In one embodiment, the communication resource amount of a communication cell may include the communication resource amount of each location in the communication cell; the communication resource amount of each location in a communication cell may be the same.

[0086] Then, based on the index values ​​of various signal indicators, the specific method for determining the communication resource amount of the corresponding communication cell can be: weighted addition of the index values ​​of various signal indicators to obtain the communication resource amount of the communication cell. Among them, the weights of different types of signal indicators can be the same or different. For example, the weights of signal strength, signal-to-noise ratio and signal reception success rate can be set to 0.2, 0.3 and 0.5 respectively; or the weights of signal strength, signal-to-noise ratio and signal reception success rate can be set to 1.

[0087] Optionally, the indicator values ​​of various signal indicators may be processed by other mathematical methods to obtain the communication resource amount of the communication cell, which is not limited here.

[0088] In a possible implementation, the amount of communication resources at various locations within a communication cell may be different. Since the locations where historical communication sessions are generated may be different, multiple historical communication sessions may be historical communication sessions generated at different time points at the same location, or may be historical communication sessions generated at the same time point at different locations; therefore, the specific method of determining the index values ​​of various signal indicators based on the quality data of historical communication sessions generated in each communication cell may also be: determining the index values ​​of various signal indicators corresponding to each historical communication session based on the quality data of each historical communication session generated in each communication cell.

[0089] Then, based on the index values ​​of various signal indicators, the specific method of determining the communication resource amount of the corresponding communication cell can be: based on the index values ​​of various signal indicators corresponding to each historical communication session, determine the communication resource amount of the corresponding position in the corresponding communication cell.

[0090] The communication resource amount of any location can be determined according to the indicator values ​​of various signal indicators corresponding to various historical communication sessions generated at different time points in any location in the communication cell. The specific method for determining the communication resource amount of any location can refer to the specific method for determining the communication resource amount of the corresponding communication cell mentioned above, which will not be repeated here.

[0091] S302: Dynamically construct a traffic load map based on the historical traffic load data of each communication cell within a second preset unit time period.

[0092] In the embodiment of the present application, the unit time period refers to the time period of an update cycle; the second preset unit time period refers to: the time period corresponding to the previous update cycle of the current update cycle of the traffic load map. The time length of the update cycle of the traffic load map can be set manually, or it can be set by the vehicle-mounted device or server in the above-mentioned data processing system, and there is no limitation on this. In addition, the second preset unit time period may be smaller than the first preset unit time period. For example, if the update cycle of the traffic load map is 1 hour, the traffic load map from 15:00 to 16:00 is constructed based on the historical traffic load data from 14:00 to 15:00.

[0093] In addition, the historical traffic load data within the second preset unit time period may include traffic load data at each historical time point within the second preset unit time period.

[0094] In one embodiment, since the historical traffic load data of each communication cell mentioned in step S201 may include the load indicators of each communication cell at each historical time point; therefore, the specific method of dynamically constructing the traffic load map may be: determining the channel quality at each historical time point according to the load indicators of each communication cell at each historical time point; determining the channel quality change trend of the corresponding communication cell according to the channel qualities at multiple historical time points; predicting the channel quality of the corresponding communication cell at the current time point based on the channel qualities at multiple historical time points and the channel quality change trend of the corresponding communication cell; and dynamically constructing the traffic load map according to the channel quality of each communication cell at the current time point.

[0095] Among them, the above-mentioned historical time points refer to the historical time points within the second preset unit time period from the current time point. In addition, the specific method of determining the channel quality at each historical time point can be: weighted addition of the load indicators of each communication cell at each historical time point to obtain the channel quality at each historical time point. Among them, the weights of each load indicator can be the same or different. Optionally, the load indicators of each historical time point can also be processed by other mathematical methods to obtain the channel quality of each historical time point, which is not limited here.

[0096] In addition, the channel quality change trend may include one or more information such as the change direction of the channel quality, the change gradient of the channel quality, etc. Specifically, the change direction of the channel quality may include a decrease in the channel quality or an increase in the channel quality; the change gradient of the channel quality may include the difference in the channel quality between any two time points, or may include the difference in the channel quality within a certain time period, without limitation.

[0097] Then, based on the channel quality at multiple historical time points and the channel quality change trend of the corresponding communication cell, the specific method of predicting the channel quality of the corresponding communication cell at the current time point can be: based on the channel quality at multiple historical time points, the direction of change of channel quality and the gradient of change of channel quality, predict the channel quality of the corresponding communication cell at the current time point.

[0098] S303: Dynamically construct a traffic transmission map based on the real-time traffic transmission data of each communication cell.

[0099] In the embodiment of the present application, since it takes time to collect data, real-time is a relative concept, which refers to a historical time point that is close to the current time point, and will not be elaborated later.

[0100] Then, real-time traffic transmission data refers to traffic data generated at a historical time point close to the current time point. Real-time traffic transmission data may specifically include: historical index values ​​of data transmission indicators of each communication cell at each historical time point within a third preset unit time period. The third preset unit time period refers to: the time period corresponding to the previous update cycle of the current update cycle of the traffic transmission map.

[0101] Among them, the third preset unit time period is smaller than the second preset unit time period; the time length of the update cycle of the traffic transmission map can be set manually or by the vehicle-mounted device or server in the above-mentioned data processing system, and there is no limitation on this.

[0102] Specifically, the update period of the traffic load map can be a shorter period of time, such as one minute, 30 seconds, etc., without limitation. For example, if the update period of the traffic load map is 10 seconds, the traffic transmission map from 15:50 to 16:00 is constructed based on the real-time traffic transmission data from 15:40 to 15:50.

[0103] In one embodiment, the specific method of dynamically constructing a traffic transmission map can be: determining the data transmission quality of each communication cell according to the real-time indicator value of the data transmission indicator of each communication cell; and constructing a traffic transmission map in real time according to the data transmission quality of each communication cell.

[0104] The real-time index value is the historical index value of the data transmission index at each historical time point within the third preset time period from the current time point. In addition, according to the real-time index value of the data transmission index of each communication cell, the specific method of determining the data transmission quality of each communication cell can be: using the real-time index value of the data transmission index of each communication cell as the data transmission quality of each communication cell.

[0105] Optionally, when the number of data transmission indicators includes multiple ones, the weighted sum of the real-time indicator values ​​of each data transmission indicator of each communication cell can be calculated, and the weighted sum is used as the data transmission quality of each communication cell. The weights of each data transmission indicator can be the same or different, and there is no limitation on this.

[0106] Optionally, since the above-mentioned real-time traffic transmission data can also include historical indicator values ​​of data transmission indicators at various historical time points within a third preset time period from the current time point; therefore, the specific method of dynamically constructing a traffic transmission map can be: determining the data transmission quality of each communication cell according to the historical indicator values ​​of the data transmission indicators of each communication cell; and constructing a traffic transmission map in real time according to the data transmission quality of each communication cell. It should be noted that the specific implementation method of determining the data transmission quality of each communication cell based on the historical indicator values ​​can refer to the above-mentioned specific implementation method of determining the data transmission quality based on the real-time indicator values, which will not be repeated here.

[0107] Optionally, the specific method of dynamically constructing a traffic transmission map may also be: determining the data transmission quality of each communication cell based on the historical indicator value and real-time indicator value of the data transmission indicator of each communication cell; and constructing a traffic transmission map in real time based on the data transmission quality of each communication cell.

[0108] Among them, for any data transmission indicator, the historical indicator value and the real-time indicator value of any data transmission indicator of each communication cell can be weighted added to obtain the target indicator value of any data transmission indicator of each communication cell; then, the target indicator values ​​of each data transmission indicator of each communication cell are weighted added to obtain the data transmission quality of each communication cell.

[0109] Specifically, the weights of the historical index value and the real-time index value of the data transmission index may be the same or different. In a specific implementation, the weight of the real-time index value may be set to be greater than the weight of the historical index value.

[0110] Optionally, the real-time indicator value and / or historical indicator value of each data transmission indicator may be processed by other mathematical methods to obtain the data transmission quality of the corresponding communication cell, which is not limited here.

[0111] S304: Fusing the signal quality map, the traffic load map, and the traffic transmission map to obtain a network quality map.

[0112] In an embodiment of the present application, the specific method of fusion processing can be: respectively obtaining the communication resource amount, channel quality and data transmission quality of each location from the signal quality map, traffic load map and traffic transmission map; fusing the communication resource amount, channel quality and data transmission quality of each location to obtain the initial data throughput of each location; updating the initial data throughput of each location according to the initial data throughput of the location within a preset range from each location to obtain the estimated data throughput of each location; generating a network quality map based on the estimated data throughput of each location.

[0113] In one embodiment, the specific method of data fusion may be: weighted addition of the communication resource amount, channel quality and data transmission quality of each location to obtain the initial data throughput of each location. The communication resource amount, channel quality and data transmission quality of each location are equivalent to the map data of the corresponding location in the signal quality map, traffic load map and traffic transmission map mentioned in step S201; therefore, the weights of the communication resource amount, channel quality and data transmission quality of each location can be specifically referred to the specific description of the weights of the map data in step S201, which will not be repeated here. Optionally, the communication resource amount, channel quality and data transmission quality can also be processed by other mathematical methods to obtain the initial data throughput, which is not limited here.

[0114] In one embodiment, the preset range may be manually set or may be set by the server or vehicle terminal in the above data processing system, and is not limited thereto. In addition, since the position mentioned in step S202 may be a small area, the area of ​​the preset range may be larger than the area corresponding to each position.

[0115] For specific implementation, please refer to the attached Figure 4 , shows a schematic diagram of a map construction process. A network quality map can be generated through three levels of dynamic construction of signal quality map, traffic load map and traffic transmission map.

[0116] First, a relatively static signal quality map can be constructed. The server can obtain the quality data of historical communication sessions generated in each communication cell in the previous cycle, and analyze the average signal strength, average signal to interference and noise ratio, and average signal receiving power of each historical communication session; then, the server constructs the signal quality map of the current cycle based on the analyzed data.

[0117] Since the average values ​​of various signal indicators are relatively stable, the server can combine the indicator values ​​from different historical time points to build offline Figure 4The update period of the signal quality map 401 shown may be based on days, such as 1 day, 10 days, 15 days, etc. If the update period is 1 day, the quality data of the historical communication sessions generated in each communication cell yesterday can be obtained to construct today's signal quality map.

[0118] Secondly, a dynamic traffic load map can be constructed. Compared with the average value of the signal index, the load index of the communication cell changes steadily over time; therefore, the server can set the frequency of updating the traffic load map in hours to obtain the following: Figure 4 The traffic load map 402 shown in FIG. 402 may be updated at a period of, for example, 1 hour, 3 hours, or 8 hours.

[0119] Specifically, if the update cycle is 1 hour, the server can build a traffic load map for the current update cycle at four o'clock based on the historical traffic load data from three to four o'clock (including the number of access nodes and the total data throughput transmitted by the communication cell).

[0120] Finally, a real-time traffic transmission map can be constructed. Compared with the first two types of maps, the traffic transmission map has a higher requirement for real-time performance because the network conditions fluctuate in real time. The server can then set the traffic transmission map to update at a frequency of minutes. For example, the update cycle can be set to 1 minute, 2 minutes, or 10 minutes.

[0121] Specifically, the server can construct the following by obtaining the data transmission indicators (including throughput, data transmission delay, packet loss rate, etc.) of each communication cell at each moment: Figure 4 A real-time traffic transmission map 403 is shown.

[0122] After obtaining the signal quality map 401, the traffic load map 402, and the traffic transmission map 403, Figure 4 As shown, the three maps can be combined to construct a network quality map. Specifically, the initial data throughput Thht0(x,y) of each location in the map can be calculated first, and the calculation formula (1-1) is as follows:

[0123] Throughput0(x,y)=α*S(x,y)*T(x,y)+β*R(x,y) (1-1)

[0124] Among them, α and β are adjustable parameters, and (x, y) are the coordinates of a certain position in the map. S(x, y) represents the amount of communication resources (also called radio resources) at a certain position in the signal quality map; T(x, y) represents the channel quality of the communication cell to which a certain position belongs in the traffic load map; and R(x, y) represents the data transmission quality at a certain position in the traffic transmission map, which can reflect the current real-time network status.

[0125] Then, the initial data throughput of each location can be smoothed by Gaussian filtering to obtain the estimated data throughput Thh(,y) of each location. The calculation formula (1-2) is as follows:

[0126]

[0127] Where n is the coordinate of a location within a preset range from the location (,y).

[0128] S305: Determine the driving control strategy of the vehicle-mounted terminal according to the network quality map, so that the vehicle-mounted terminal performs vehicle control processing according to the driving control strategy.

[0129] In the embodiment of the present application, the specific implementation of step S305 can refer to the specific implementation of step S203 in the above embodiment, which will not be repeated here.

[0130] Since the signal quality of each location is difficult to change in a short period of time, and the load of each communication cell changes steadily over time; therefore, the real-time requirements of the signal quality map and the traffic load map are not as high as those of the traffic transmission map, and the real-time requirements of the signal quality map are lower than those of the traffic load map.

[0131] Therefore, the embodiment of the present application uses historical communication quality data, historical traffic load data and real-time traffic transmission data from different historical time periods to respectively construct a signal quality map, a traffic load map and a traffic transmission map, so that the three maps are Figure 3 The update frequency realizes the three-level dynamic construction of the map. If the signal quality map, traffic load map, and traffic transmission map are all constructed in real time, the server will need to process a large amount of data at the same time, which places extremely high demands on device performance; therefore, the embodiment of the present application can guarantee the accuracy of the generated network quality map to a certain extent through the three-level dynamic construction of the signal quality map, traffic load map, and traffic transmission map, while also reducing the requirements on device performance, facilitating promotion and expanding application prospects.

[0132] In one embodiment of the present application, another data processing system is provided, which can be found in Figure 5 , Figure 5The data processing system shown may include a vehicle terminal 501, an associated device 502 of the vehicle terminal 501, a roadside base station 503, a signal base station 504, and a server 505 deployed at the signal base station 504. Among them, a communication connection is established between the vehicle terminal 501 and the roadside base station 503 and the signal base station 504, a communication connection is established between the roadside base station 503 and the signal base station 504, a communication connection is established between the signal base station 504 and the server 505, and a communication connection is established between the associated device 502 and the server 505; the vehicle terminal 501 establishes a communication connection with the associated device 502 through the roadside base station 503 and / or the signal base station 504.

[0133] Among them, the vehicle terminal 501 may include any one or more of a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart TV (TV), a smart vehicle-mounted device, and a smart wearable device. A remote driving client, a multimedia player client, a social client, a browser client, etc. may be run in the vehicle terminal 501. The associated device 502 may include any one or more of a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart TV (TV), a smart vehicle-mounted device, and a smart wearable device. A remote driving client, a multimedia player client, a social client, a browser client, etc. may be run in the associated device 502.

[0134] Server 505 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), as well as big data and artificial intelligence platforms.

[0135] In the remote driving scenario, the associated device 502 can remotely control the vehicle terminal 501 through the remote driving client. The server 505 can be the server of the remote driving client. Among them, since the vehicle equipped with the vehicle terminal 501 is in a moving state, the signal base station 504 is difficult to cover all the locations where the vehicle is traveling; therefore, the vehicle terminal 501 will first send the Internet of Vehicles data required for remote driving to the closer roadside base station 503, which will be relayed to the signal base station 504 by the roadside base station 503; afterwards, the Internet of Vehicles data can be sent to the associated device 502 through the server 505 deployed by the signal base station 504.

[0136] In some embodiments, a vehicle network data transmission system can be built based on the vehicle terminal 501, the associated device 502, the roadside base station 503, the signal base station 504 and the server 505, such as Figure 6FIG. 1 shows a schematic diagram of the architecture of a vehicle network data transmission system. The vehicle network data transmission system may mainly include an environment perception layer, a data processing and analysis layer, a data transmission optimization layer, and an application service layer.

[0137] Among them, the environmental perception layer mainly collects Internet of Vehicles data through the collection equipment connected to the vehicle terminal 501. Specifically, the vehicle terminal 501 can collect Internet of Vehicles data (such as video data, sensor data, etc.) through collection equipment such as vehicle sensors, cameras, global positioning systems (GPS), inertial measurement units (IMU), etc., and transmit the Internet of Vehicles data to the signal base station 504, so that the server 505 deployed at the signal base station 504 can perceive the environment (including position, speed, posture, road conditions, vehicle status, etc.) of the vehicle in real time.

[0138] The data processing and analysis layer is mainly used to process and analyze the Internet of Vehicles data. Specifically, the server 505 can process, analyze and model the collected Internet of Vehicles data through data processing, model calculation and other methods, thereby updating the network quality map and related machine learning models.

[0139] The data transmission optimization layer is mainly used to generate driving control strategies. The server 505 can further generate driving control strategies based on the updated network quality map, and send the driving control strategies to the vehicle terminal 501, so that the vehicle terminal 501 performs vehicle control processing according to the driving control strategies, thereby ensuring the transmission quality of the Internet of Vehicles data and optimizing data transmission.

[0140] The application service layer is mainly used to provide rich application services for the users of the vehicle terminal 501 and the users of the associated device 502, such as real-time video, vehicle status monitoring, remote driving assistance, etc., which are not limited here.

[0141] In one embodiment of the present application, another data processing method is provided, which can be applied to Figure 5 The data processing system shown in the figure, the method can be executed by the terminal device or the server, or by the terminal device and the server together. In the embodiment of the present application, the method is described by taking the server as an example. Figure 7 FIG. 1 is a flow chart of another data processing method. Figure 2 and Figure 3 The driving control strategy in the data processing method can specifically include selecting a target path from multiple alternative paths and controlling the vehicle to travel along the target path.

[0142] Among them, S701 to S706 are described in detail as follows:

[0143] S701. Obtain a signal quality map dynamically constructed based on historical communication quality data of each communication cell in the navigation map, a traffic load map dynamically constructed based on historical traffic load data of each communication cell, and a traffic transmission map dynamically constructed based on traffic transmission data of each communication cell.

[0144] In the embodiment of the present application, the specific implementation of step S701 can refer to the specific implementation of step S201 and steps S301 to S303 in the above embodiment, which will not be repeated here.

[0145] S702: Fusing the signal quality map, the traffic load map, and the traffic transmission map to obtain a network quality map.

[0146] In the embodiment of the present application, the specific implementation of step S702 can refer to the specific implementation of step S202 and step S304 in the above embodiment, which will not be repeated here.

[0147] S703: Determine multiple alternative routes for the vehicle based on the terminal position, current driving speed, and current driving position of the vehicle.

[0148] In the embodiment of the present application, the method for determining the alternative path may specifically be: obtaining multiple initial paths according to the terminal position and the current driving position of the vehicle; determining the travel time of each initial path according to the current driving speed of the vehicle; selecting multiple alternative paths from the multiple initial paths according to the travel time of each initial path; wherein the travel time of the alternative path is less than the initial path other than the selected alternative path among the multiple initial paths. For example, the three initial paths with the shortest travel time may be selected as alternative paths.

[0149] In one embodiment, since the driving position of the vehicle may change, the alternative paths may also change, so it is necessary to continuously predict and update the alternative paths so as to update the target path in a timely manner.

[0150] Then, the predicted driving position of the vehicle at a future time point can also be determined based on the current driving speed of the vehicle; multiple alternative paths can be updated according to the predicted driving position and the terminal position to obtain multiple updated alternative paths, so as to determine the target path based on the multiple updated alternative paths.

[0151] The future time point may be one or more time points that occur later than the current time point. Since the current speed of the vehicle is a vector, including the magnitude and direction of the current speed, the predicted driving position of the vehicle at the future time point can be determined directly based on the current speed.

[0152] S704: Predict a future network quality map based on the historical network quality map.

[0153] In the embodiment of the present application, since the network quality map is dynamically updated and time-varying, the network quality maps at different time points are different. Therefore, the historical network quality map may include: network quality maps at one or more historical time points; and the future network quality map may include: network quality maps at one or more future time points.

[0154] The specific method of predicting the future network quality map based on the historical network quality map may be: calling the map prediction model to process the historical network quality map to obtain the future network quality map. In a specific implementation, the network structure of the map prediction model may be a deep convolutional network, a generative adversarial network, an encoder-decoder structure, etc., which is not limited here.

[0155] In one embodiment, the training process of the map prediction model may specifically be: obtaining multiple training network quality maps, wherein each network quality map corresponds to a different historical time point, and the multiple historical time points corresponding to the multiple training network quality maps are continuous; calling the map prediction model to be trained, processing the first network quality map among the multiple training network quality maps, and obtaining a predicted network quality map; based on the predicted network quality map and the second network quality map among the multiple training network quality maps, training the map prediction model to be trained to obtain a map prediction model.

[0156] The historical time point corresponding to the second network quality map is after the historical time point corresponding to the first network quality map. Based on the predicted network quality map and the second network quality map, the specific process of training the map prediction model to be trained may be: determining the loss value between the predicted network quality map and the second network quality map; and training the map prediction model to be trained in the direction of reducing the loss value.

[0157] In one embodiment, when the network structure of the map prediction model is an encoder-decoder structure, the specific method of calling the map prediction model to process the historical network quality map to obtain the future network quality map can be: calling the map prediction model to perform feature encoding processing on the historical network quality map to obtain map features; and performing feature prediction processing on the map features to obtain the future network quality map.

[0158] S705 . Predict the future data throughput of each position in each candidate path according to the historical data throughput of each position in each candidate path.

[0159] In the embodiment of the present application, the historical data throughput of each position in each candidate path may specifically include: the historical data throughput of each position in each candidate path at one or more historical time points. The future data throughput of each position in each candidate path may specifically include: the data throughput of each position in each candidate path at one or more future time points.

[0160] The specific method of predicting the future data throughput may be: for any position in any candidate path, calling the throughput prediction model to process the historical data throughput of any position to obtain the future data throughput of any position.

[0161] In a specific implementation, the throughput prediction model may be a neural network with the ability to process time series data, such as a gated recurrent neural network (GRU), a recurrent neural network (RNN), or a Long Short Term Memory (LSTM, a neural network with the ability to memorize long-term and short-term information), without limitation.

[0162] In one embodiment, since the historical data throughput of any location may include multiple ones, the specific process of the throughput prediction model processing the historical data throughput of any location may be: in the process of traversing multiple historical data throughputs of any location in the alternative path, based on the hidden state features obtained in the previous traversal, the state extraction processing is performed on the historical data throughput of the current traversal to obtain the hidden state features obtained in the current traversal; based on the hidden state features obtained in the current traversal and the data features obtained in the previous traversal, the data features obtained in the current traversal are obtained; based on the hidden state features obtained in the current traversal and the data features obtained in the previous traversal, the future data throughput of any location is predicted.

[0163] Among them, the specific process of predicting the future data throughput of any position based on the hidden state features and data features obtained from the last traversal can be: in the process of traversing multiple future time points, the hidden state features and data features obtained from the last traversal are respectively used as the hidden state features and data features obtained from the previous traversal corresponding to the future time point of the first traversal; the data features obtained from the previous traversal are classified and predicted to predict the future data throughput of any position at the future time point of the current traversal; based on the hidden state features obtained from the previous traversal, the data throughput obtained from the current traversal is state extracted to obtain the hidden state features obtained from the current traversal; based on the hidden state features obtained from the current traversal, the data features obtained from the current traversal are obtained, until the future data throughput of any position at the future time point of the last traversal is obtained.

[0164] Specifically, the specific implementation methods of state extraction processing, data feature acquisition and classification prediction processing can refer to the specific process of extracting hidden states, extracting features and activating classification in GRU, LSTM and other networks, which will not be repeated here.

[0165] S706: Based on the future network quality map, the historical data throughput of each position in each candidate path, and the future data throughput of each position in each candidate path, select a target path from multiple candidate paths to generate a driving control strategy.

[0166] In the embodiment of the present application, the specific method of selecting the target path from multiple candidate paths may be:

[0167] 1) According to the future network quality map, the future data throughput of each position in each candidate path is adjusted to obtain the target data throughput of each position in each candidate path;

[0168] In one embodiment, the specific adjustment method may be: for any position in any candidate path, weighted addition is performed on the data throughput of the corresponding position in the future network quality map and the future data throughput of any position to obtain the target data throughput of any position.

[0169] The weight of the data throughput of the corresponding position in the future network quality map and the future data throughput of any position may be the same or different. Specifically, since the future data throughput of any position is predicted for a local alternative path, it is more accurate than the data throughput predicted for the entire map; therefore, the weight of the future data throughput of any position may be set to be larger than the weight of the data throughput of the corresponding position in the future network quality map.

[0170] In one embodiment, the specific method of adjustment may also be: for any position in any alternative path, determine the difference between the data throughput of the corresponding position in the future network quality map and the future data throughput of any position; if the difference is less than or equal to the preset difference, use the future data throughput of any position as the target data throughput of any position; if the difference is greater than the preset difference, perform weighted addition on the data throughput of the corresponding position in the future network quality map and the future data throughput of any position to obtain the target data throughput of any position. The preset difference may be set manually or by the vehicle-mounted device or server in the above-mentioned data processing system, which is not limited thereto.

[0171] Optionally, since steps S704 and S705 mention that the future network quality map may include predicted future network quality maps at multiple future time points, the future data throughput at any location may include the future data throughput at any location at multiple future time points; therefore, a correspondence between the future network quality map and the future data throughput at the same time point at the corresponding future time point may be established, and the target data throughput at any location also includes the target data throughput at any location at multiple future time points.

[0172] Then, the weighted addition and difference determination between the above data throughputs may be performed between data throughputs whose corresponding future time points are the same future time point. Optionally, the weighted addition and difference determination between the above data throughputs may also be performed between data throughputs whose corresponding future time points are adjacent future time points, which is not limited.

[0173] Optionally, the future data throughput may be adjusted based on the future network quality map in other ways, which are not limited here.

[0174] 2) According to the historical data throughput of each position in each candidate path and the target data throughput of each position in each candidate path, the estimated data throughput of each position in each candidate path at the current time point is corrected to obtain the corrected data throughput of each position in each candidate path at the current time point;

[0175] The estimated data throughput of each position in each candidate path at the current time point is obtained from the network quality map at the current time point.

[0176] In one embodiment, the specific method of correction may be: for any position in any alternative path, weighted addition of the historical data throughput, target data throughput, and estimated data throughput of any position at the current time point is performed to obtain the corrected data throughput of any position at the current time point.

[0177] The weights of the historical data throughput, the target data throughput, and the estimated data throughput at the current time point may be the same or different. Specifically, since the estimated data throughput at the current time point is mainly corrected, the weight of the estimated data throughput at the current time point may be set to be greater than both the historical data throughput and the target data throughput, and the weight of the target data throughput may be greater than the historical data throughput; or the weight of the estimated data throughput at the current time point may be set to be greater than both the historical data throughput and the target data throughput, and the weight of the target data throughput may be the same as the weight of the historical data throughput, which is not limited here.

[0178] In one embodiment, the specific method of correction may also be: for any position in any alternative path, determine a first difference between the historical data throughput of any position and the estimated data throughput of any position at the current time point, and a second difference between the target data throughput of any position and the estimated data throughput of any position at the current time point; if the first difference is greater than a first preset threshold or the second difference is greater than a second preset threshold, perform weighted addition on the historical data throughput of any position, the target data throughput, and the estimated data throughput of any position at the current time point to obtain the corrected data throughput of any position at the current time point; if the first difference is less than or equal to the first preset threshold and the second difference is less than or equal to the second preset threshold, use the estimated data throughput of any position at the current time point as the corrected data throughput of any position at the current time point.

[0179] The first preset threshold and the second preset threshold may be set manually or by the vehicle-mounted device or server in the above data processing system, and there is no limitation on this.

[0180] Optionally, the estimated data throughput of each location at the current time point may be adjusted based on the historical data throughput and target data throughput of each location in other ways, which are not limited here.

[0181] 3) determining the network quality of each candidate path based on the corrected data throughput of each position in each candidate path at the current time point;

[0182] In one embodiment, the specific method of determining the network quality of each candidate path may be: calculating the sum of the corrected data throughput of each position in each candidate path at the current time point, and taking the sum of the throughput as the network quality of each candidate path.

[0183] In one embodiment, the specific method for determining the network quality of each alternative path may also be: in the process of traversing multiple positions in any alternative path, if the corrected data throughput of any position in any alternative path is less than or equal to the reference throughput, then the network quality obtained last time is updated to obtain the current network quality; if the corrected data throughput of any position in any alternative path is greater than the reference throughput, then the network quality obtained last time is used as the current network quality; and the finally obtained network quality is used as the network quality of each alternative path.

[0184] The network quality obtained after the update is lower than the network quality obtained last time. In addition, the network quality obtained last time corresponding to the first traversal position in any candidate path can be set as the initial quality, and the initial quality of each candidate path is the same.

[0185] Optionally, the network quality of the alternative path may be determined based on the correction data throughput in other ways, which are not limited here.

[0186] 4) Determine the target path based on the network quality of each alternative path.

[0187] Specifically, the alternative path with the highest network quality can be determined as the target path.

[0188] Optionally, network quality can be used as an important reference for the vehicle's driving path, but the vehicle's final driving path is still based on the driver's wishes. Therefore, the server can also send each candidate path and its network quality to the vehicle terminal, and the vehicle terminal outputs each candidate path and its network quality; then, the vehicle terminal can respond to the driver's path selection operation and use the path selected by the driver as the target path.

[0189] Optionally, the selection of the current path may further take into account the future network quality of the path. Therefore, the target path may be determined according to the network quality of each candidate path: the target path may be determined according to the target data throughput of each position in each candidate path and the network quality of each candidate path.

[0190] In actual application, please refer to the attached Figure 8 , which shows a schematic diagram of the data throughput prediction process. Figure 8 As shown, after obtaining the historical network quality maps 801 of multiple historical time points, the data throughput of each position in each alternative path at the corresponding historical time point can be determined according to each historical network quality map, thereby obtaining the historical data throughput 802 of each alternative path (composed of multiple historical data throughputs of each position in each alternative path, and the multiple historical data throughputs of any position can be regarded as a throughput sequence).

[0191] Afterwards, the future network quality map within a short period of time in the future, such as the network quality map of the next 1 second, can be predicted from a global perspective based on multiple historical network quality maps 801. Specifically, the prediction of the network quality map is essentially a problem of generating a two-dimensional image sequence; therefore, the network structure of the map prediction model can use an encoder-decoder machine learning architecture to extract the features of the network quality map sequence (i.e., multiple historical network quality maps) over a period of time in the past to predict the future network quality map at a future time point. Among them, the encoder in the map prediction model can specifically use a three-dimensional convolutional neural network.

[0192] Therefore, after obtaining multiple historical network quality maps 801, the encoder 803 in the map prediction model can be called to perform feature encoding processing on the multiple historical network quality maps 801 to obtain map features 804; then, the decoder 805 in the map prediction model can be called to perform feature prediction processing on the map features 804 to obtain the future network quality map 806.

[0193] At the same time, based on the historical data throughput 802 of each candidate path, the future data throughput of each location in each candidate path in the future for a long period of time, such as the next 7 seconds, can be accurately predicted locally. Specifically, the network structure of the throughput prediction model can be LSTM. Figure 8 As shown, after the historical data throughput 802 of each candidate path is input into the throughput prediction model 807, the throughput prediction model 807 can process the throughput sequence of any position to obtain the hidden state features of each historical data throughput (such as Figure 8 H t-1 , H t and H t+1 , where t refers to the sequence number of the currently traversed historical data throughput in the throughput sequence); and the throughput prediction model 807 also extracts the data features of each historical data throughput ( Figure 8 X in t-1 , X t and X t+1 Finally, the throughput prediction model 807 may output the future data throughput 808 of each candidate path (composed of multiple future data throughputs at each position in each candidate path).

[0194] After obtaining the future network quality map 806 and the future data throughput 808 of each candidate path, the estimated data throughput of each position in each candidate path at the current time point can be corrected by Kalman filtering based on the historical data throughput of each position in each candidate path, the future network quality map 806 and the future data throughput 808 of each candidate path, thereby determining the network quality 809 of each candidate path. Subsequently, according to the network quality 809 of each candidate path, a target path can be selected from multiple candidate paths and a driving control strategy can be generated.

[0195] In a specific implementation, the data processing and analysis layer can be used to train and update the machine learning models such as the map prediction model and the throughput prediction model mentioned in step S704 and step S705. At the same time, the data transmission optimization layer can determine the target path based on the predicted future network quality map and the future data throughput of each location in each candidate path to generate a driving control strategy.

[0196] In an embodiment of the present application, by predicting the future network quality map based on the historical network quality map, a preliminary prediction of the future data throughput of each location in the alternative path can be achieved from the perspective of the global map; at the same time, in an embodiment of the present application, the future data throughput of the alternative path is predicted by the historical data throughput of each location in the alternative path, so that an accurate prediction of the future data throughput of each location in the alternative path can be achieved from the perspective of the local path.

[0197] Since the estimated data throughput of each position in the alternative path at the current time point is originally estimated, there is an error with the actual data throughput, and the data throughput in continuous time is related; therefore, in the embodiment of the present application, the estimated data throughput of each position in the alternative path at the current time point is corrected by combining the future network quality map, the historical data throughput of each alternative path and the future data throughput, so that the data throughput of each position at the current time point is more accurate, which is conducive to further improving the accuracy of network quality estimation.

[0198] In addition, the estimated data throughput of each location at the current time point is more accurate, which also makes the target path determined subsequently a path with better actual network quality, which is conducive to the driving control strategy generated according to the target path to better improve the data transmission quality of the vehicle terminal.

[0199] In one embodiment of the present application, another data processing method is provided, which can be applied to Figure 1The data processing system shown in the figure, the method can be executed by the terminal device or the server, or by the terminal device and the server together. In the embodiment of the present application, the method is described by taking the server as an example. Fig. 9 FIG. 1 is a flow chart of another data processing method. Figure 2 , Figure 3 and Figure 7 The driving control strategy is expanded on the basis of the method shown in , and includes controlling the vehicle terminal to send the Internet of Vehicles data to the associated device at a target sending rate.

[0200] Among them, S901 to S905 are described in detail as follows:

[0201] S901. Obtain a signal quality map dynamically constructed based on historical communication quality data of each communication cell in the navigation map, a traffic load map dynamically constructed based on historical traffic load data of each communication cell, and a traffic transmission map dynamically constructed based on traffic transmission data of each communication cell.

[0202] In the embodiment of the present application, the specific implementation of step S901 can refer to the specific implementation of step S201 and steps S301 to S303 in the above embodiment, which will not be repeated here.

[0203] S902: Fusing the signal quality map, the traffic load map, and the traffic transmission map to obtain a network quality map.

[0204] In the embodiment of the present application, the specific implementation of step S902 can refer to the specific implementation of step S202 and step S304 in the above embodiment, which will not be repeated here.

[0205] S903: Process the transmission feedback information received from the associated device using a preset rate control algorithm to obtain an estimated transmission rate of the vehicle-mounted terminal at the current time point.

[0206] In an embodiment of the present application, the transmission feedback information includes an indicator value of a preset transmission quality indicator, wherein the preset transmission quality indicator may include one or more of a packet loss rate, a data round trip time, and a data transmission delay.

[0207] In addition, the preset rate control algorithm may specifically include one or more congestion control algorithms such as slow-start, congestion avoidance, fast retransmission, fast recovery, BBR (Bottleneck Bandwidth and Round-trip propagation time), etc. Since the process of processing transmission feedback information according to the congestion control algorithm is well known to those skilled in the art, it will not be described in detail here.

[0208] S904: According to the estimated data throughput of the current driving position of the vehicle in the network quality map, a predicted sending rate of the vehicle terminal at the current time point is predicted.

[0209] In an embodiment of the present application, the estimated data throughput of the current driving position refers to the estimated data throughput of the current driving position at the current time point, and the estimated data throughput of the current driving position can be obtained from the network quality map at the current time point (also referred to as the current network quality map).

[0210] In addition, the prediction method of the predicted sending rate can be specifically: calling the rate decision model, processing the estimated data throughput of the current driving position of the vehicle, and obtaining the predicted sending rate. In a specific implementation, the network structure of the rate decision model can be a convolutional neural network, a deep convolutional neural network, a generative network, etc., which is not limited here.

[0211] Optionally, the training process of the rate decision model can be a supervised learning process; the training process of the rate decision model can specifically be: obtaining the training data throughput and the labeled sending rate; calling the rate decision model to be trained, processing the training data throughput, and obtaining a reference sending rate; training the rate decision model to be trained according to the reference sending rate and the labeled sending rate to obtain the rate decision model.

[0212] The marked sending rate may be obtained by relevant personnel with rich experience in the field of data transmission through measurement and experimental marking. The specific method of training the rate decision model to be trained according to the reference sending rate and the marked sending rate may be: determining the rate difference between the reference sending rate and the marked sending rate; and training the rate decision model to be trained in the direction of reducing the rate difference. Since the specific process of model training is well known to those skilled in the art, it will not be described here.

[0213] In one embodiment, since the target transmission rate obtained based on the predicted transmission rate is mainly used by the vehicle terminal at the current time point and in a future period after the current time point; therefore, the future data throughput of the current driving position can also be predicted based on the historical network quality map; and then the predicted transmission rate of the vehicle terminal at the current time point is predicted based on the estimated data throughput of the current driving position obtained from the current network quality map and the future data throughput of the current driving position. The prediction process of the future data throughput of the current driving position can refer to the specific implementation method of predicting the future data throughput in step S706, which will not be repeated here.

[0214] Then, the specific method of predicting the sending rate may be: calling the rate prediction model, processing the estimated data throughput of the current driving position of the vehicle, and the future data throughput or the corrected data throughput of the current driving position, to obtain the predicted sending rate. It should be noted that since the input data has changed, the rate prediction model also needs to adjust the data range of the training data and re-train accordingly.

[0215] In one embodiment, since the corrected data throughput of each position mentioned in step S706 at the current time point is more accurate; therefore, based on the estimated data throughput of the current driving position of the vehicle in the network quality map, the specific method of predicting the predicted sending rate of the vehicle terminal at the current time point can also be: first, based on the estimated data throughput of the current driving position of the vehicle in the network quality map, the future network quality map and the historical data throughput of the current driving position, the estimated data throughput of the current driving position can be corrected to obtain the corrected data throughput of the current driving position; then, based on the corrected data throughput of the current driving position, the predicted sending rate of the vehicle terminal at the current time point is predicted.

[0216] Optionally, the predicted sending rate of the vehicle terminal at the current time point may also be predicted based on the corrected data throughput of the current driving position and the future data throughput.

[0217] S905: Based on the estimated sending rate and the predicted sending rate, obtain a target sending rate to generate a driving control strategy.

[0218] In an embodiment of the present application, based on the estimated sending rate and the predicted sending rate, a specific method for obtaining the target sending rate may be: weighted addition of the estimated sending rate and the predicted sending rate to obtain the target sending rate. The weights of the estimated sending rate and the predicted sending rate may be the same or different, and there is no limitation on this. Specifically, since the estimated sending rate is obtained through the transmission feedback information sent by the associated device, there is a certain information lag; therefore, the weight of the predicted sending rate may be set to be greater than the weight of the estimated sending rate.

[0219] In one possible implementation, after the data transmission rate changes, in order to match the data transmission rate of the transmission layer and further improve the data transmission quality, the encoding bit rate of the data in the application layer can also be adjusted accordingly. Therefore, the driving control strategy can also include controlling the vehicle terminal to encode the Internet of Vehicles data according to the target bit rate; then, the generation process of the driving control strategy can also include: processing the transmission feedback information through a preset bit rate control algorithm to obtain the estimated bit rate of the vehicle terminal; predicting the predicted bit rate of the vehicle terminal based on the estimated data throughput of the current driving position in the network quality map; based on the estimated bit rate and the predicted bit rate, obtaining the target bit rate to generate the driving control strategy.

[0220] The preset bit rate control algorithm may be any one or more methods for controlling the encoding bit rate, such as constant bit rate (CBR), variable bit rate (VBR), constant rate factor (CRF), etc., which are not limited here. Since the process of processing the transmission feedback information according to the bit rate control algorithm is well known to those skilled in the art, it will not be described in detail here.

[0221] In one embodiment, based on the estimated bit rate and the predicted bit rate, a specific method of obtaining the target bit rate may be: weighted addition of the estimated bit rate and the predicted bit rate to obtain the target bit rate. The weights of the estimated bit rate and the predicted bit rate may be the same or different. Specifically, since the estimated bit rate is obtained through transmission feedback information sent by an associated device, there is a certain information lag; therefore, the weight of the predicted bit rate may be set to be greater than the weight of the estimated bit rate.

[0222] In one embodiment, the prediction process of the predicted bitrate may specifically be: calling the bitrate decision model, processing the estimated data throughput of the current driving position, and obtaining the predicted bitrate. In a specific implementation, the network structure of the bitrate decision model may specifically be a convolutional neural network, a deep convolutional neural network, a generative network, etc., which is not limited here.

[0223] Optionally, the training process of the rate decision model can be a supervised learning process, and the training process of the rate decision model can specifically be: obtaining the training data throughput and the labeled bit rate; calling the rate decision model to be trained, processing the training data throughput, and obtaining a reference bit rate; training the rate decision model to be trained according to the reference bit rate and the labeled bit rate to obtain the rate decision model.

[0224] The marked bit rate may be obtained by relevant personnel with rich experience in the field of data transmission through measurement and experimental marking. The specific method of training the bit rate decision model to be trained according to the reference bit rate and the marked bit rate may be: determining the bit rate difference between the reference bit rate and the marked bit rate; and training the bit rate decision model to be trained in the direction of reducing the bit rate difference. Since the specific process of model training is well known to those skilled in the art, it will not be described here.

[0225] Optionally, since the target bit rate obtained based on the predicted bit rate is mainly used by the vehicle terminal at the current time point and in the future after the current time point; therefore, the estimated data throughput of the current driving position can be further processed to obtain the corrected data throughput of the current driving position; then based on the corrected data throughput of the current driving position, the estimated data throughput and the future data throughput, or the corrected data throughput and the corrected data throughput, the predicted bit rate is predicted. The specific prediction method of the predicted bit rate can be seen in the specific implementation method of predicting the sending rate in step S902, which will not be repeated here.

[0226] In one possible implementation, the rate decision model and the bit rate decision model can also be combined into an overall decision model, so that the overall decision model can generate a driving control strategy including controlling the vehicle-mounted terminal to send Internet of Vehicles data to the associated device at the target sending rate, and controlling the vehicle-mounted terminal to encode the Internet of Vehicles data at the target bit rate.

[0227] Then, after obtaining the estimated data throughput of the current driving position, the total decision model can be called to process the estimated data throughput of the current driving position to obtain the predicted sending rate and the predicted bit rate; the transmission feedback information is processed by the preset rate control algorithm and the preset bit rate control algorithm respectively to obtain the estimated sending rate and the estimated bit rate; based on the estimated sending rate and the predicted sending rate, the target rate is obtained; based on the estimated bit rate and the predicted bit rate, the target bit rate is obtained; finally, the driving control strategy is generated according to the target rate and the target bit rate.

[0228] In actual application, please refer to the attached Fig.10 , which shows a schematic diagram of cross-layer optimization of data transmission. Fig.10 As shown, the overall decision model 1001 running in the server can improve the transmission efficiency and stability by dynamically adjusting the encoding bit rate of the application layer 1002 and the data sending rate of the transport layer 1003, thereby further improving the data transmission quality of the vehicle terminal.

[0229] The application layer 1002 includes the application layer of the vehicle terminal and the application layer of the associated device, and the transport layer 1003 includes the transport layer of the vehicle terminal and the transport layer of the associated device. The application layer of the vehicle terminal includes a data encoder 1004 and a bit rate controller 1005, and the transport layer includes a sending buffer 1006 and a sending rate controller 1008; the transport layer of the associated device includes a receiving buffer 1007, and the application layer includes a data decoder 1009.

[0230] Specifically, after the associated device receives the Internet of Vehicles data packet (which may include real-time vehicle environment video, vehicle status monitoring data, etc.) sent by the vehicle terminal through the receiving buffer 1007 in the transport layer, the Internet of Vehicles data packet can be sent to the data decoder 1009 in the application layer; the data decoder 1009 decodes the Internet of Vehicles data packet so that the corresponding Internet of Vehicles data can be displayed on the associated device in the end.

[0231] At the same time, the receiving buffer 1007 can also generate transmission feedback information based on the packet loss of the Internet of Vehicles data packet, data transmission delay and other indicator information related to data transmission quality, and send the transmission feedback information to the vehicle terminal.

[0232] The transmission rate controller 1008 in the transmission layer of the vehicle terminal will call the preset rate control algorithm to process the received transmission feedback information, thereby obtaining the estimated transmission rate and sending it to the data encoder 1004; and the bit rate controller 1005 in the application layer of the vehicle terminal will call the preset bit rate control algorithm to process the transmission feedback information, thereby obtaining the estimated bit rate and sending it to the transmission buffer 1006. At the same time, the overall decision model 1001 can also process the corrected data throughput of the current driving position of the vehicle to obtain the predicted transmission rate and predicted bit rate of the current driving position.

[0233] Finally, if Fig.10 As shown, the total decision model 1001 can send the predicted transmission rate and the predicted bit rate to the vehicle terminal. The data encoder 1004 in the application layer of the vehicle terminal will determine the target bit rate according to the estimated bit rate and the predicted bit rate, and then encode the vehicle network data to be sent to the associated device according to the target bit rate, obtain the corresponding vehicle network data packet and send it to the transmission buffer 1006 in the transmission layer of the vehicle terminal.

[0234] The sending buffer 1006 in the transport layer of the vehicle terminal determines the target sending rate based on the estimated sending rate and the predicted sending rate, and sends the Internet of Vehicles data packet encoded by the data encoder 1004 at the target sending rate.

[0235] In a possible implementation, the data transmission method or data transmission protocol can be further optimized. Optionally, the data transmission quality can be optimized based on multi-channel transmission; specifically, multiple transmission channels (such as 4G, Wifi, etc.) of the vehicle terminal can be used to transmit Internet of Vehicles data in parallel, so as to utilize the bandwidth resources of multiple channels to improve the data transmission rate and stability, thereby achieving the purpose of improving data transmission quality.

[0236] Optionally, the transmission efficiency and real-time performance can be improved by optimizing the transmission protocol, thereby improving the quality of data transmission. Specifically, more efficient video compression encoding technologies (such as H.265, etc.) can be used, and protocol acceleration and low transmission delay can also be supported.

[0237] Optionally, the quality of data transmission can be optimized by reducing data retransmission; specifically, forward error correction technology (FEC) can be used to prevent data errors or losses, thereby optimizing the transmission quality and stability of Internet of Vehicles data.

[0238] In a possible implementation, the driving control strategy may include multiple driving control strategies mentioned in all the above embodiments at the same time. Through multiple driving control strategies, it is possible to concurrently improve the data transmission quality of the vehicle terminal from multiple dimensions such as path, data transmission rate, and encoding bit rate, which is conducive to significantly improving the data transmission quality of the vehicle terminal, thereby further improving the object usage experience and satisfaction in the vehicle networking scenario.

[0239] In the embodiment of the present application, the predicted transmission rate and the predicted bit rate are integrated with the estimated transmission rate and the estimated bit rate obtained based on the traditional congestion control algorithm (including the preset bit rate control algorithm and the preset rate control algorithm) to achieve multi-factor regulation of the application layer and the transport layer, so that the target transmission rate and the target bit rate obtained in the end are more in line with the current and future network quality. Therefore, the driving control strategy generated according to the target transmission rate or the target bit rate can further improve the data transmission quality of the vehicle terminal.

[0240] Specifically, in the Internet of Vehicles scenario, the data transmission quality of Internet of Vehicles data such as video can be optimized through the above-mentioned target path, target transmission rate, target bit rate and other driving control strategies. The optimization of data transmission quality is conducive to avoiding problems such as freezing of Internet of Vehicles data such as video, and providing users with smoother, high-definition, and real-time application services (such as real-time environmental video, vehicle status detection, remote driving assistance, etc.), which is conducive to improving the user experience and satisfaction of application service objects.

[0241] Secondly, the optimization of data transmission quality enables the Internet of Vehicles data to be transmitted to the server in a timely and effective manner, which is conducive to improving traffic safety. Since the server can timely process and analyze the Internet of Vehicles data such as environment and video collected by the vehicle sensors, and through the transmission of high-definition real-time video, the remote driver can improve his perception of the road conditions ahead and avoid traffic accidents.

[0242] In addition, the optimization of data transmission quality can reduce the delay and congestion of Internet of Vehicles data such as video during transmission, improve transmission efficiency and stability, and reduce the cost of traffic information transmission. It provides new ideas and practical references for the development and application of Internet of Vehicles technology at the network optimization level, and helps promote the further development of Internet of Vehicles technology.

[0243] Here, the device embodiment of the present application is introduced, which can be used to execute the data processing method in the above embodiment of the present application. For details not disclosed in the device embodiment of the present application, please refer to the above embodiment of the data processing method of the present application.

[0244] The present application embodiment provides a data processing device, such as Fig.11 As shown, the device includes an acquisition unit 1101 and a processing unit 1102, wherein:

[0245] An acquisition unit 1101 is used to acquire a signal quality map dynamically constructed based on historical communication quality data of each communication cell in the navigation map, a traffic load map dynamically constructed based on historical traffic load data of each communication cell, and a traffic transmission map dynamically constructed based on traffic transmission data of each communication cell;

[0246] The processing unit 1102 is used to fuse the signal quality map, the traffic load map and the traffic transmission map to obtain a network quality map; wherein the network quality map includes an estimated data throughput of each position in the navigation map, and the estimated data throughput of each position is obtained based on the map data of the corresponding position in the signal quality map, the traffic load map and the traffic transmission map;

[0247] The processing unit 1102 is further used to determine the driving control strategy of the vehicle-mounted terminal according to the network quality map, so that the vehicle-mounted terminal performs vehicle control processing according to the driving control strategy.

[0248] In one embodiment of the present application, based on the aforementioned scheme, when the processing unit 1102 fuses the signal quality map, the traffic load map and the traffic transmission map to obtain the network quality map, it can be specifically used to: obtain the communication resource amount, channel quality and data transmission quality of each location from the signal quality map, the traffic load map and the traffic transmission map respectively; fuse the communication resource amount, channel quality and data transmission quality of each location to obtain the initial data throughput of each location; update the initial data throughput of each location according to the initial data throughput of the location within a preset range from each location to obtain the estimated data throughput of each location; generate a network quality map based on the estimated data throughput of each location.

[0249] In one embodiment of the present application, based on the aforementioned scheme, the acquisition unit 1101 can further be used to: dynamically construct a signal quality map based on the historical communication quality data of each communication cell within a first preset unit time period; dynamically construct a traffic load map based on the historical traffic load data of each communication cell within a second preset unit time period; wherein the second preset unit time period is smaller than the first preset unit time period; and dynamically construct a traffic transmission map based on the real-time traffic transmission data of each communication cell.

[0250] In one embodiment of the present application, based on the aforementioned scheme, when the acquisition unit 1101 dynamically constructs a signal quality map based on the historical communication quality data of each communication cell within a first preset unit time period, it can be specifically used to: determine the index values ​​of various signal indicators based on the quality data of historical communication sessions generated in each communication cell; wherein the signal indicators include at least one type of signal strength, signal-to-noise ratio and signal reception success rate; determine the amount of communication resources of the corresponding communication cell based on the index values ​​of various signal indicators; and dynamically construct a signal quality map based on the amount of communication resources of each communication cell.

[0251] In one embodiment of the present application, based on the aforementioned scheme, when the acquisition unit 1101 dynamically constructs a traffic load map based on the historical traffic load data of each communication cell within a second preset unit time period, it can be specifically used to: determine the channel quality at each historical time point based on the load index of each communication cell at each historical time point; wherein the load index includes at least one of the number of access devices and data throughput; determine the channel quality change trend of the corresponding communication cell based on the channel quality at multiple historical time points; predict the channel quality of the corresponding communication cell at the current time point based on the channel quality at multiple historical time points and the channel quality change trend of the corresponding communication cell; and dynamically construct a traffic load map based on the channel quality of each communication cell at the current time point.

[0252] In one embodiment of the present application, based on the aforementioned scheme, when the acquisition unit 1101 dynamically constructs a traffic transmission map according to the real-time traffic transmission data of each communication cell, it can be specifically used to: determine the data transmission quality of each communication cell according to the real-time indicator value of the data transmission indicator of each communication cell; wherein the data transmission indicator includes at least one of data throughput, data transmission delay and packet loss rate; and construct a traffic transmission map in real time according to the data transmission quality of each communication cell.

[0253] In one embodiment of the present application, the driving control strategy includes selecting a target path from multiple alternative paths and controlling the vehicle to travel along the target path; based on the aforementioned scheme, when the processing unit 1102 determines the driving control strategy of the vehicle terminal according to the network quality map, it can be specifically used to: determine multiple alternative paths for the vehicle based on the vehicle's terminal position, current driving speed and current driving position; predict the future network quality map based on the historical network quality map; predict the future data throughput of each position in each alternative path based on the historical data throughput of each position in each alternative path; select the target path from multiple alternative paths based on the future network quality map, the historical data throughput of each position in each alternative path, and the future data throughput of each position in each alternative path to generate a driving control strategy.

[0254] In one embodiment of the present application, based on the aforementioned scheme, when the processing unit 1102 selects a target path from multiple alternative paths based on the future network quality map, the historical data throughput of each position in each alternative path, and the future data throughput of each position in each alternative path, it can be specifically used to: adjust the future data throughput of each position in each alternative path according to the future network quality map to obtain the target data throughput of each position in each alternative path; correct the estimated data throughput of each position in each alternative path at the current time point according to the historical data throughput of each position in each alternative path and the target data throughput of each position in each alternative path to obtain the corrected data throughput of each position in each alternative path at the current time point; determine the network quality of each alternative path based on the corrected data throughput of each position in each alternative path at the current time point; and determine the target path according to the network quality of each alternative path.

[0255] In one embodiment of the present application, based on the aforementioned scheme, when the processing unit 1102 determines multiple alternative paths for the vehicle based on the vehicle's terminal position, current driving speed and current driving position, it can be specifically used to: determine the predicted driving position of the vehicle at a future time point based on the vehicle's current driving speed; update the multiple alternative paths according to the predicted driving position and the terminal position to obtain multiple updated alternative paths, so as to determine the target path based on the updated multiple alternative paths.

[0256] In one embodiment of the present application, the driving control strategy includes controlling the vehicle terminal to send Internet of Vehicles data to the associated device at a target sending rate; based on the aforementioned scheme, when the processing unit 1102 determines the driving control strategy of the vehicle terminal according to the network quality map, it can be specifically used to: process the transmission feedback information sent by the received associated device through a preset rate control algorithm to obtain the estimated sending rate of the vehicle terminal at the current time point; wherein the transmission feedback information includes an indicator value of a preset transmission quality indicator; based on the estimated data throughput of the current driving position of the vehicle in the network quality map, the predicted sending rate of the vehicle terminal at the current time point is predicted; based on the estimated sending rate and the predicted sending rate, the target sending rate is obtained to generate a driving control strategy.

[0257] In one embodiment of the present application, based on the aforementioned scheme, when the processing unit 1102 predicts the predicted sending rate of the vehicle terminal at the current time point according to the estimated data throughput of the current driving position of the vehicle in the network quality map, it can be specifically used to: predict the future data throughput of the current driving position according to the historical network quality map; predict the predicted sending rate according to the estimated data throughput of the current driving position obtained from the current network quality map and the future data throughput of the current driving position.

[0258] In one embodiment of the present application, the driving control strategy also includes controlling the vehicle terminal to encode and process the Internet of Vehicles data according to the target bit rate; based on the aforementioned scheme, the processing unit 1102 can further be used to: process the transmission feedback information through a preset bit rate control algorithm to obtain an estimated bit rate of the vehicle terminal; predict the predicted bit rate of the vehicle terminal based on the estimated data throughput of the current driving position in the network quality map; obtain the target bit rate based on the estimated bit rate and the predicted bit rate to generate a driving control strategy.

[0259] It should be noted that the device provided in the above embodiment and the method provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment and will not be repeated here.

[0260] The device provided in the above-mentioned embodiment can be arranged in a terminal device or in a server. The device provided in the embodiment of the present application can integrate the signal quality map, the traffic load map and the traffic transmission map to obtain a network quality map that integrates the transmission quality measurement data of multiple data dimensions such as signal quality, traffic load and traffic transmission; and the network quality map obtained by measuring the multi-dimensional data can better restore the complex and changeable actual network environment. Therefore, the map data in the network quality map in the embodiment of the present application will be more accurate, which is conducive to improving the accuracy of network quality estimation. In addition, since the network quality map is also dynamically updated and has time-varying properties. Therefore, the network quality map in the embodiment of the present application can avoid data inaccuracies caused by data lag to a certain extent, which is conducive to further improving the accuracy of network quality estimation.

[0261] An embodiment of the present application also provides an electronic device, comprising one or more processors and a storage device, wherein the storage device is used to store one or more computer programs, and when the one or more computer programs are executed by one or more processors, the electronic device implements the above data processing method.

[0262] Fig.12 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown.

[0263] It should be noted that Fig.12 The computer system 1200 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0264] like Fig.12 As shown, the computer system 1200 includes a processor (Central Processing Unit, CPU) 1201, which can perform various appropriate actions and processes according to the program stored in the read-only memory (Read-Only Memory, ROM) 1202 or the program loaded from the storage part 1208 to the random access memory (Random Access Memory, RAM) 1203, such as executing the method in the above embodiment. In RAM 1203, various programs and data required for system operation are also stored. CPU 1201, ROM 1202 and RAM 1203 are connected to each other through bus 1204. Input / output (Input / Output, I / O) interface 1205 is also connected to bus 1204.

[0265] In some embodiments, the following components are connected to the I / O interface 1205: an input section 1206 including a keyboard, a mouse, etc.; an output section 1207 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1208 including a hard disk, etc.; and a communication section 1209 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 1209 performs communication processing via a network such as the Internet. A drive 1210 is also connected to the I / O interface 1205 as needed. A removable medium 1211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1210 as needed, so that a computer program read therefrom is installed into the storage section 1208 as needed.

[0266] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 1209, and / or installed from a removable medium 1211. When the computer program is executed by a processor (CPU) 1201, various functions defined in the system of the present application are executed.

[0267] It should be noted that the computer-readable medium shown in the embodiment of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (Erasable Programmable Read Only Memory), a flash memory, an optical fiber, a portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. This propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. A computer program contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0268] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the devices, methods and computer program products according to various embodiments of the present application. Among them, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the 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 from the order 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 or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and a computer program.

[0269] The units or modules involved in the embodiments described in this application may be implemented by software or hardware, and the units or modules described may also be set in a processor. The names of these units or modules do not, in some cases, constitute limitations on the units or modules themselves.

[0270] Another aspect of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the data processing method as described above is implemented. The computer-readable storage medium may be included in the electronic device described in the above embodiment, or may exist independently without being assembled into the electronic device.

[0271] Another aspect of the present application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. A processor of an electronic device reads the computer program from the computer-readable storage medium, and the processor executes the computer program, so that the electronic device executes the data processing method as described above in the above embodiments.

[0272] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0273] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.

[0274] The above content is only a preferred exemplary embodiment of the present application and is not intended to limit the implementation scheme of the present application. A person of ordinary skill in the art can easily make corresponding changes or modifications based on the main concept and spirit of the present application. Therefore, the scope of protection of the present application shall be based on the scope of protection required by the claims.

Claims

1. A data processing method, characterized in that: include: Obtaining a signal quality map dynamically constructed based on historical communication quality data of each communication cell in the navigation map, a traffic load map dynamically constructed based on historical traffic load data of each communication cell, and a traffic transmission map dynamically constructed based on traffic transmission data of each communication cell; The signal quality map, the traffic load map and the traffic transmission map are fused to obtain a network quality map; wherein the network quality map includes an estimated data throughput of each position in the navigation map, and the estimated data throughput of each position is obtained based on the map data of the corresponding position in the signal quality map, the traffic load map and the traffic transmission map; The driving control strategy of the vehicle-mounted terminal is determined according to the network quality map, so that the vehicle-mounted terminal performs vehicle control processing according to the driving control strategy.

2. The method according to claim 1, characterized in that The fusing the signal quality map, the traffic load map and the traffic transmission map to obtain a network quality map includes: Obtaining the communication resource amount, channel quality and data transmission quality of each location from the signal quality map, the traffic load map and the traffic transmission map respectively; Performing data fusion on the communication resource amount, channel quality and data transmission quality of each location to obtain the initial data throughput of each location; According to the initial data throughput of the locations within the preset range from the locations, the initial data throughput of the locations is updated to obtain the estimated data throughput of the locations; The network quality map is generated based on the estimated data throughput of each location.

3. The method according to claim 1 or 2, characterized in that: The method further comprises: Dynamically construct the signal quality map according to the historical communication quality data of each communication cell within a first preset unit time period; Dynamically construct the traffic load map according to the historical traffic load data of each communication cell in a second preset unit time period; wherein the second preset unit time period is smaller than the first preset unit time period; The traffic transmission map is dynamically constructed according to the real-time traffic transmission data of each communication cell.

4. The method according to claim 3, characterized in that The dynamically constructing the signal quality map according to the historical communication quality data of each communication cell within a first preset unit time period includes: Determining the index values ​​of various signal indicators according to the quality data of the historical communication sessions generated in each communication cell; wherein the signal indicators include at least one type of signal strength, signal-to-noise ratio and signal reception success rate; Determining the communication resource amount of the corresponding communication cell based on the indicator values ​​of the various signal indicators; The signal quality map is dynamically constructed according to the communication resource amount of each communication cell.

5. The method according to claim 3, characterized in that: The dynamically constructing the traffic load map according to the historical traffic load data of each communication cell in the second preset unit time period includes: Determine the channel quality of each historical time point according to the load index of each communication cell at each historical time point; wherein the load index includes at least one of the number of access devices and data throughput; Determine the channel quality change trend of the corresponding communication cell according to the channel quality at multiple historical time points; Based on the channel qualities at the multiple historical time points and the channel quality change trend of the corresponding communication cells, predicting the channel quality of the corresponding communication cells at the current time point; The traffic load map is dynamically constructed according to the channel quality of each communication cell at the current time point.

6. The method according to claim 3, characterized in that The dynamically constructing the traffic transmission map according to the real-time traffic transmission data of each communication cell includes: Determining the data transmission quality of each communication cell according to the real-time indicator value of the data transmission indicator of each communication cell; wherein the data transmission indicator includes at least one of data throughput, data transmission delay and packet loss rate; The traffic transmission map is constructed in real time according to the data transmission quality of each communication cell.

7. The method according to claim 1, characterized in that The driving control strategy includes selecting a target path from a plurality of candidate paths and controlling the vehicle to travel along the target path; the driving control strategy of the vehicle terminal is determined according to the network quality map, including: Determining a plurality of alternative routes for the vehicle based on the terminal position, the current travel speed, and the current travel position of the vehicle; Predict future network quality maps based on historical network quality maps; Predicting the future data throughput of each location in each candidate path based on the historical data throughput of each location in each candidate path; Based on the future network quality map, the historical data throughput of each position in each candidate path, and the future data throughput of each position in each candidate path, the target path is selected from multiple candidate paths to generate the driving control strategy.

8. The method according to claim 7, characterized in that The selecting the target path from multiple candidate paths based on the future network quality map, the historical data throughput of each position in each candidate path, and the future data throughput of each position in each candidate path includes: According to the future network quality map, adjusting the future data throughput of each position in each candidate path to obtain the target data throughput of each position in each candidate path; According to the historical data throughput of each position in each candidate path and the target data throughput of each position in each candidate path, the estimated data throughput of each position in each candidate path at the current time point is corrected to obtain the corrected data throughput of each position in each candidate path at the current time point; Determining the network quality of each candidate path based on the corrected data throughput of each position in each candidate path at the current time point; Determine the target path based on the network quality of each alternative path.

9. The method according to claim 7, characterized in that: The determining of a plurality of alternative paths for the vehicle based on the terminal position, the current driving speed, and the current driving position of the vehicle comprises: Determining a predicted driving position of the vehicle at a future time point based on a current driving speed of the vehicle; The multiple candidate paths are updated according to the predicted driving position and the terminal position to obtain the updated multiple candidate paths, so as to determine the target path based on the updated multiple candidate paths.

10. The method according to claim 1, characterized in that The driving control strategy includes controlling the vehicle terminal to send Internet of Vehicles data to the associated device at a target sending rate; and determining the driving control strategy of the vehicle terminal according to the network quality map includes: The transmission feedback information received from the associated device is processed by a preset rate control algorithm to obtain an estimated transmission rate of the vehicle-mounted terminal at the current time point; wherein the transmission feedback information includes an indicator value of a preset transmission quality indicator; Predicting a predicted sending rate of the vehicle terminal at a current time point according to the estimated data throughput of the current driving position of the vehicle in the network quality map; Based on the estimated sending rate and the predicted sending rate, the target sending rate is obtained to generate the driving control strategy.

11. The method according to claim 10, characterized in that The predicting of obtaining a predicted sending rate of the vehicle terminal at a current time point according to the estimated data throughput of the current driving position of the vehicle in the network quality map includes: predicting future data throughput at the current driving location based on the historical network quality map; The predicted sending rate is predicted based on the estimated data throughput of the current driving position obtained from the current network quality map and the future data throughput of the current driving position.

12. The method according to claim 10, characterized in that The driving control strategy also includes controlling the vehicle-mounted terminal to encode the vehicle network data according to the target bit rate; the method also includes: Processing the transmission feedback information by a preset bit rate control algorithm to obtain an estimated bit rate of the vehicle terminal; Predicting a predicted bit rate of the vehicle-mounted terminal according to the estimated data throughput of the current driving position in the network quality map; Based on the estimated bit rate and the predicted bit rate, the target bit rate is obtained to generate the driving control strategy.

13. A data processing device, characterized in that: It includes an acquisition unit and a processing unit, wherein: The acquisition unit is used to acquire a signal quality map dynamically constructed based on historical communication quality data of each communication cell in the navigation map, a traffic load map dynamically constructed based on historical traffic load data of each communication cell, and a traffic transmission map dynamically constructed based on traffic transmission data of each communication cell; The processing unit is used to fuse the signal quality map, the traffic load map and the traffic transmission map to obtain a network quality map; wherein the network quality map includes an estimated data throughput of each position in the navigation map, and the estimated data throughput of each position is obtained based on the map data of the corresponding position in the signal quality map, the traffic load map and the traffic transmission map; The processing unit is further used to determine the driving control strategy of the vehicle-mounted terminal according to the network quality map, so that the vehicle-mounted terminal performs vehicle control processing according to the driving control strategy.

14. A computer storage medium, characterized in that: The computer storage medium stores one or more computer programs, and the one or more computer programs are suitable for being loaded by a processor and executing the data processing method according to any one of claims 1 to 12.

15. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the data processing method as described in any one of claims 1 to 12.

Images