Data processing method and device, equipment and medium

Abstract

The invention provides a data processing method and device, equipment and a medium, and relates to the technical field of computers, network snapshots of an intelligent Internet of Vehicles state are obtained, the network snapshots comprise network topology, routing, queuing data, a traffic matrix and time data, and the network snapshots are processed based on a trained time-space diagram attention network. And obtaining a plurality of network paths and the score corresponding to each network path. And the network path is planned, so that the quality of the intelligent Internet of Vehicles is improved.

Description

Background Art

[0002] Intelligent vehicle self-organizing networks represent the latest progress of modern intelligent technologies in intelligent transportation systems. In recent years, intelligent vehicle self-organizing networks have played an important role in solving road traffic challenges, alleviating traffic congestion, and improving traffic efficiency and safety. However, although intelligent vehicle networking is very efficient, some of its inherent characteristics bring many challenges. Since the vehicle networking environment is highly dynamic, it is very important to ensure the stability and efficiency of communication between vehicles and between vehicles and base stations and roadside units, while minimizing computing consumption through precise network optimization. Summary of the invention

[0003] The present disclosure provides a data processing method, device, equipment and medium, which at least to a certain extent improve the stability of an intelligent vehicle-mounted self-organizing network.

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

[0005] According to one aspect of the present disclosure, there is provided a data processing method, comprising:

[0006] Get a network snapshot of the smart car network status, including network topology, routing, queuing data, traffic matrix, and time data;

[0007] Based on the trained spatiotemporal graph attention network, the network snapshot is processed to obtain multiple network paths and the corresponding scores for each network path.

[0008] In one embodiment of the present disclosure, a network snapshot is processed based on a trained spatiotemporal graph attention network to obtain multiple network paths and scores corresponding to each network path, including:

[0009] Based on the parsing module in the spatiotemporal graph attention network, the network snapshot is parsed to obtain the network topology, routing scheme and queuing scheme corresponding to the network snapshot.

[0010] In one embodiment of the present disclosure, a network snapshot is processed based on a trained spatiotemporal graph attention network to obtain multiple network paths and scores corresponding to each network path, including:

[0011] The network topology, routing scheme, and queuing scheme are input into the hidden layer of the spatiotemporal graph attention network to obtain the hidden vectors corresponding to the links and paths respectively.

[0012] In one embodiment of the present disclosure, a network snapshot is processed based on a trained spatiotemporal graph attention network to obtain multiple network paths and scores corresponding to each network path, including:

[0013] The temporal features of network snapshots are extracted from the network snapshots based on the temporal module in the spatiotemporal graph attention network.

[0014] In one embodiment of the present disclosure, a network snapshot is processed based on a trained spatiotemporal graph attention network to obtain multiple network paths and scores corresponding to each network path, including:

[0015] The hidden vectors corresponding to the links and paths and the time features corresponding to the network snapshots are input into the self-attention layer, so that the gating units in the self-attention layer determine the attention scores of the links on the paths.

[0016] In one embodiment of the present disclosure, a network snapshot is processed based on a trained spatiotemporal graph attention network to obtain multiple network paths and scores corresponding to each network path, including:

[0017] The attention scores of the links on the path, the hidden vectors corresponding to the links and paths, and the time features corresponding to the network snapshots are input into the readout layer of the spatiotemporal graph attention network to obtain multiple network paths and the scores corresponding to each network path. The scores include delay score, jitter score, and packet loss rate.

[0018] In one embodiment of the present disclosure, the method further includes:

[0019] The spatiotemporal graph attention network is trained based on historical network snapshots, historical network paths, and the scores corresponding to the historical paths;

[0020] When the loss function value reaches the preset value, the training is stopped and the trained spatiotemporal graph attention network is obtained.

[0021] According to another aspect of the present disclosure, there is provided a data processing device, comprising:

[0022] The acquisition module is used to obtain the network snapshot of the intelligent vehicle network status, which includes network topology, routing, queuing data, traffic matrix and time data;

[0023] The processing module is used to process the network snapshot based on the trained spatiotemporal graph attention network to obtain multiple network paths and the corresponding score of each network path.

[0024] In one embodiment of the present disclosure, the processing module includes:

[0025] The parsing unit is used to parse the network snapshot based on the parsing module in the spatiotemporal graph attention network to obtain the network topology, routing scheme and queuing scheme corresponding to the network snapshot.

[0026] In one embodiment of the present disclosure, the processing module includes:

[0027] The first input unit is used to input the network topology, routing scheme and queuing scheme into the hidden layer of the spatiotemporal graph attention network to obtain the hidden vectors corresponding to the links and paths respectively.

[0028] In one embodiment of the present disclosure, the processing module includes:

[0029] The extraction unit is used to extract the temporal features of the network snapshot based on the temporal module in the spatiotemporal graph attention network.

[0030] In one embodiment of the present disclosure, the processing module includes:

[0031] The determination unit is used to input the hidden vectors corresponding to the links and paths and the time features corresponding to the network snapshots into the self-attention layer, so that the gating unit in the self-attention layer determines the attention scores of the links on the paths.

[0032] In one embodiment of the present disclosure, the processing module includes:

[0033] The second input unit is used to input the attention scores of the links on the paths, the hidden vectors corresponding to the links and paths, and the time features corresponding to the network snapshots into the readout layer of the spatiotemporal graph attention network to obtain multiple network paths and the scores corresponding to each network path, wherein the scores include delay scores, jitter scores, and packet loss rates.

[0034] In one embodiment of the present disclosure, the device further includes:

[0035] The first training module is used to train the spatiotemporal graph attention network based on historical network snapshots, historical network paths, and scores corresponding to the historical paths;

[0036] The second training module is used to stop training when the loss function value reaches a preset value, thereby obtaining a trained spatiotemporal graph attention network.

[0037] According to another aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the above-mentioned data processing method by executing the executable instructions.

[0038] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned data processing method is implemented.

[0039] The data processing method provided by the embodiment of the present disclosure obtains a network snapshot of the state of the intelligent vehicle network, which includes network topology, routing, queuing data, traffic matrix and time data, processes the network snapshot based on the trained spatiotemporal graph attention network, and obtains multiple network paths and scores corresponding to each network path. The network path is planned to improve the quality of the intelligent vehicle network.

[0040] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0042] Figure 1 A schematic diagram of a data processing method according to an embodiment of the present disclosure is shown;

[0043] Figure 2 A schematic diagram showing another data processing method flow in an embodiment of the present disclosure is shown;

[0044] Figure 3 A schematic diagram of a flow chart of another data processing method in an embodiment of the present disclosure is shown;

[0045] Figure 4 A schematic diagram of a flow chart of another data processing method in an embodiment of the present disclosure is shown;

[0046] Figure 5 A schematic diagram of a flow chart of another data processing method in an embodiment of the present disclosure is shown;

[0047] Figure 6 A schematic diagram of another data processing device in an embodiment of the present disclosure is shown; and

[0048] Figure 7 A structural block diagram of another electronic device in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0049] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0050] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0051] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0052] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0053] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0054] In order to solve the above technical problems, the present disclosure provides a data processing method, device, equipment and medium.

[0055] Below, the data processing method provided by the present disclosure is first described.

[0056] Figure 1 A schematic flow chart of a data processing method in an embodiment of the present disclosure is shown.

[0057] like Figure 1 As shown, the data processing method provided by the embodiment of the present disclosure may include:

[0058] S110, obtaining a network snapshot of the intelligent vehicle network status, where the network snapshot includes network topology, routing, queuing data, traffic matrix, and time data;

[0059] S120, processing the network snapshot based on the trained spatiotemporal graph attention network to obtain multiple network paths and a score corresponding to each network path.

[0060] Exemplarily, a network snapshot can be expressed as:

[0061] (1) a set of nodes, }, representing cars, base stations, and other entities that send, forward, and receive in the intelligent Internet of Vehicles. Represents the set of nodes in the network snapshot, Represents the first nodes, there are a total of nodes.

[0062] (2) a set of links, , indicating the communication connection between two nodes. Represents the collection of links in the network snapshot, Represents the first There are links in this set. Links.

[0063] (3) a set of paths, , describes the routing scheme within the network. Represents a collection of routing paths in a network snapshot, Represents the first There are a total of path.

[0064] path by sequence Definition, where express Middle The characteristics of links and paths are respectively and express.

[0065] The data processing method provided by the embodiment of the present disclosure obtains a network snapshot of the state of the intelligent vehicle network, which includes network topology, routing, queuing data, traffic matrix and time data, processes the network snapshot based on the trained spatiotemporal graph attention network, and obtains multiple network paths and scores corresponding to each network path. The network path is planned to improve the quality of the intelligent vehicle network.

[0066] Figure 2 A schematic flow chart of a data processing method in an embodiment of the present disclosure is shown.

[0067] like Figure 2 As shown, the data processing method provided by the embodiment of the present disclosure may include:

[0068] S210, obtaining a network snapshot of the intelligent vehicle network status, where the network snapshot includes network topology, routing, queuing data, traffic matrix, and time data;

[0069] S220, parsing the network snapshot based on the parsing module in the spatiotemporal graph attention network to obtain the network topology, routing scheme and queuing scheme corresponding to the network snapshot.

[0070] In some embodiments, the present disclosure parses the network snapshot using a parsing module through multiple trainings, wherein the parsing module may include at least two of an input layer, a hidden layer, an output layer, and a convolutional layer.

[0071] In some embodiments, training can be performed based on historical network snapshots and historical network topology, historical routing documents, and historical queuing solutions to obtain a trained parsing module.

[0072] S230, determining a plurality of network paths and a score corresponding to each network path based on the network topology, routing scheme, and queuing scheme corresponding to the network snapshot.

[0073] The data processing method provided by the embodiment of the present disclosure obtains a network snapshot of the state of the intelligent vehicle network, which includes network topology, routing, queuing data, traffic matrix and time data, processes the network snapshot based on the trained spatiotemporal graph attention network, and obtains multiple network paths and scores corresponding to each network path. The network path is planned to improve the quality of the intelligent vehicle network.

[0074] Figure 3 A schematic flow chart of a data processing method in an embodiment of the present disclosure is shown.

[0075] like Figure 3 As shown, the data processing method provided by the embodiment of the present disclosure may include:

[0076] S310, obtaining a network snapshot of the intelligent vehicle network status, where the network snapshot includes network topology, routing, queuing data, traffic matrix, and time data;

[0077] S320, parsing the network snapshot based on the parsing module in the spatiotemporal graph attention network to obtain a network topology, a routing scheme, and a queuing scheme corresponding to the network snapshot;

[0078] S330, input the network topology, routing scheme and queuing scheme into the hidden layer of the spatiotemporal graph attention network to obtain the hidden vectors corresponding to the links and paths respectively.

[0079] In some embodiments, the hidden vector corresponding to the link may be:

[0080]

[0081] The hidden vector corresponding to the path can be:

[0082]

[0083] Link state and path state are learned by functions and The mutual conversion reflects the dependency between links and paths. Specifically, the path state Through the function Aggregate Path Status of the link passed , capturing the impact of each link on the path on the overall performance of the path. At the same time, the link status Through the function Aggregate all passing links Path status , reflecting the overall impact of the path on the link status.

[0084] S340, determining multiple network paths and a score corresponding to each network path based on the hidden vector.

[0085] The data processing method provided by the embodiment of the present disclosure obtains a network snapshot of the state of the intelligent vehicle network, which includes network topology, routing, queuing data, traffic matrix and time data, processes the network snapshot based on the trained spatiotemporal graph attention network, and obtains multiple network paths and scores corresponding to each network path. The network path is planned to improve the quality of the intelligent vehicle network.

[0086] Figure 4 A schematic flow chart of a data processing method in an embodiment of the present disclosure is shown.

[0087] like Figure 4 As shown, the data processing method provided by the embodiment of the present disclosure may include:

[0088] S410, obtaining a network snapshot of the intelligent vehicle network status, where the network snapshot includes network topology, routing, queuing data, traffic matrix, and time data.

[0089] S420, extracting time features of the network snapshot from the network snapshot based on the time module in the spatiotemporal graph attention network;

[0090] In some embodiments, the spatiotemporal graph attention network extracts temporal features from network snapshots , and integrate its time module into the path feature and through manually adjustable coefficients Adjustments are made, as follows:

[0091]

[0092] in is the time feature, is the initial path feature, It is a balance factor that can be adjusted manually.

[0093] S430, inputting the hidden vectors corresponding to the links and paths and the time features corresponding to the network snapshots into the self-attention layer, so that the gating unit in the self-attention layer determines the attention scores of the links on the paths.

[0094] In some embodiments, the attention mechanism utilizes attention weights Evaluate the contribution of each link, update it through the gated recurrent unit, and adjust each link's contribution to the current path state The influence of is expressed as:

[0095] , .

[0096] The symbol Indicates The attention coefficient when passing each message in turn, Represents the path hidden vector of the tth round; Indicates The link hidden vector of the round, A gate control unit is used here. is an intermediate variable.

[0097] S440, input the attention scores of the links on the paths, the hidden vectors corresponding to the links and paths, and the time features corresponding to the network snapshots into the readout layer of the spatiotemporal graph attention network to obtain multiple network paths and the scores corresponding to each network path, the scores including delay scores, jitter scores, and packet loss rates.

[0098] In some embodiments, the spatiotemporal graph attention network predicts packet-level behavior, and path-level key performance indicators need to be obtained through mathematical modeling.

[0099] For example, regarding delay and jitter, The delay and jitter of a path are defined as and The sample mean and variance As their estimated values ​​respectively. Output of spatiotemporal graph attention network Parameterized probability distribution to approximate Mathematically, the output of the algorithm is Let be a binary vector representing the mean and variance of the packet distribution, representing delay and jitter, respectively.

[0100]

[0101] in represents the standard normal distribution, As an activation function, the positivity of the parameters is guaranteed. represent the mean and standard deviation of the distribution respectively.

[0102] Regarding the packet loss rate, by introducing discrete distributions such as binomial distribution, the model can be used to predict the probability of packet loss within the path.

[0103]

[0104] in represents the binomial distribution, Used to map the result between 0 and 1. Is the path Packet loss rate on the path The total number of received packets on , the number of packets discarded is .

[0105] The data processing method provided by the embodiment of the present disclosure obtains a network snapshot of the state of the intelligent vehicle network, which includes network topology, routing, queuing data, traffic matrix and time data, processes the network snapshot based on the trained spatiotemporal graph attention network, and obtains multiple network paths and scores corresponding to each network path. The network path is planned to improve the quality of the intelligent vehicle network.

[0106] Figure 5 A schematic flow chart of a data processing method in an embodiment of the present disclosure is shown.

[0107] like Figure 5 As shown, the data processing method provided by the embodiment of the present disclosure may include:

[0108] S510, training a spatiotemporal graph attention network based on historical network snapshots, historical network paths, and scores corresponding to the historical paths;

[0109] S520, when the loss function value reaches a preset value, stop training and obtain a trained spatiotemporal graph attention network.

[0110] S530, obtaining a network snapshot of the intelligent vehicle network status, where the network snapshot includes network topology, routing, queuing data, traffic matrix, and time data;

[0111] S540, processing the network snapshot based on the trained spatiotemporal graph attention network to obtain multiple network paths and a score corresponding to each network path.

[0112] In some embodiments, based on the distribution modeling of delay and jitter, the training of this part of the model can be achieved by maximizing the log-likelihood function of the normal distribution, that is, minimizing the difference loss from the actual data packet distribution, where the loss function is the negative of the log-likelihood function.

[0113]

[0114] represents the total number of packets received. The loss function designed for heteroscedastic regression combines the squared delay error with the jitter error term. The sample mean and variance of each path delay are expressed as and express.

[0115] Based on the distribution model of packet loss rate, the log-likelihood function of binomial distribution is as follows, where Represents the number of observed losses. Such loss functions are also common in binary classification problems.

[0116]

[0117] in, Is the path The packet loss rate on the network is , and the total number of received packets is .

[0118] The data processing method provided by the embodiment of the present disclosure obtains a network snapshot of the state of the intelligent vehicle network, which includes network topology, routing, queuing data, traffic matrix and time data, processes the network snapshot based on the trained spatiotemporal graph attention network, and obtains multiple network paths and scores corresponding to each network path. The network path is planned to improve the quality of the intelligent vehicle network.

[0119] Based on the same inventive concept, the present disclosure also provides a data processing device in the following embodiments. Since the principle of solving the problem in the device embodiment is similar to that in the above method embodiment, the implementation of the device embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0120] Figure 6 A schematic diagram of a data processing device in an embodiment of the present disclosure is shown. Figure 6 As shown, the device comprises:

[0121] An acquisition module 601 is used to acquire a network snapshot of the intelligent vehicle network status, where the network snapshot includes network topology, routing, queuing data, traffic matrix, and time data;

[0122] The processing module 602 is used to process the network snapshot based on the trained spatiotemporal graph attention network to obtain multiple network paths and the score corresponding to each network path.

[0123] The data processing device provided by the embodiment of the present disclosure obtains a network snapshot of the state of the intelligent vehicle network, which includes network topology, routing, queuing data, traffic matrix and time data, processes the network snapshot based on the trained spatiotemporal graph attention network, and obtains multiple network paths and scores corresponding to each network path. The network path is planned to improve the quality of the intelligent vehicle network.

[0124] In one embodiment of the present disclosure, the processing module includes:

[0125] The parsing unit is used to parse the network snapshot based on the parsing module in the spatiotemporal graph attention network to obtain the network topology, routing scheme and queuing scheme corresponding to the network snapshot.

[0126] The data processing device provided by the embodiment of the present disclosure obtains a network snapshot of the state of the intelligent vehicle network, which includes network topology, routing, queuing data, traffic matrix and time data, processes the network snapshot based on the trained spatiotemporal graph attention network, and obtains multiple network paths and scores corresponding to each network path. The network path is planned to improve the quality of the intelligent vehicle network.

[0127] In one embodiment of the present disclosure, the processing module includes:

[0128] The first input unit is used to input the network topology, routing scheme and queuing scheme into the hidden layer of the spatiotemporal graph attention network to obtain the hidden vectors corresponding to the links and paths respectively.

[0129] The data processing device provided by the embodiment of the present disclosure obtains a network snapshot of the state of the intelligent vehicle network, which includes network topology, routing, queuing data, traffic matrix and time data, processes the network snapshot based on the trained spatiotemporal graph attention network, and obtains multiple network paths and scores corresponding to each network path. The network path is planned to improve the quality of the intelligent vehicle network.

[0130] In one embodiment of the present disclosure, the processing module includes:

[0131] The extraction unit is used to extract the temporal features of the network snapshot based on the temporal module in the spatiotemporal graph attention network.

[0132] The data processing device provided by the embodiment of the present disclosure obtains a network snapshot of the state of the intelligent vehicle network, which includes network topology, routing, queuing data, traffic matrix and time data, processes the network snapshot based on the trained spatiotemporal graph attention network, and obtains multiple network paths and scores corresponding to each network path. The network path is planned to improve the quality of the intelligent vehicle network.

[0133] In one embodiment of the present disclosure, the processing module includes:

[0134] The determination unit is used to input the hidden vectors corresponding to the links and paths and the time features corresponding to the network snapshots into the self-attention layer, so that the gating unit in the self-attention layer determines the attention scores of the links on the paths.

[0135] The data processing device provided by the embodiment of the present disclosure obtains a network snapshot of the state of the intelligent vehicle network, which includes network topology, routing, queuing data, traffic matrix and time data, processes the network snapshot based on the trained spatiotemporal graph attention network, and obtains multiple network paths and scores corresponding to each network path. The network path is planned to improve the quality of the intelligent vehicle network.

[0136] In one embodiment of the present disclosure, the processing module includes:

[0137] The second input unit is used to input the attention scores of the links on the paths, the hidden vectors corresponding to the links and paths, and the time features corresponding to the network snapshots into the readout layer of the spatiotemporal graph attention network to obtain multiple network paths and the scores corresponding to each network path, wherein the scores include delay scores, jitter scores, and packet loss rates.

[0138] The data processing device provided by the embodiment of the present disclosure obtains a network snapshot of the state of the intelligent vehicle network, which includes network topology, routing, queuing data, traffic matrix and time data, processes the network snapshot based on the trained spatiotemporal graph attention network, and obtains multiple network paths and scores corresponding to each network path. The network path is planned to improve the quality of the intelligent vehicle network.

[0139] In one embodiment of the present disclosure, the device further includes:

[0140] The first training module is used to train the spatiotemporal graph attention network based on historical network snapshots, historical network paths, and scores corresponding to the historical paths;

[0141] The second training module is used to stop training when the loss function value reaches a preset value, thereby obtaining a trained spatiotemporal graph attention network.

[0142] The data processing device provided by the embodiment of the present disclosure obtains a network snapshot of the state of the intelligent vehicle network, which includes network topology, routing, queuing data, traffic matrix and time data, processes the network snapshot based on the trained spatiotemporal graph attention network, and obtains multiple network paths and scores corresponding to each network path. The network path is planned to improve the quality of the intelligent vehicle network.

[0143] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0144] Refer to the following Figure 7 An electronic device 700 according to this embodiment of the present disclosure is described. Figure 7 The electronic device 700 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0145] like Figure 7 As shown, the electronic device 700 is in the form of a general computing device. The components of the electronic device 700 may include but are not limited to: at least one processing unit 710, at least one storage unit 720, and a bus 730 connecting different system components (including the storage unit 720 and the processing unit 710).

[0146] The storage unit stores program codes, which can be executed by the processing unit 710, so that the processing unit 710 performs the steps of various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification. For example, the processing unit 710 can perform the following steps of the above method embodiment:

[0147] Get a network snapshot of the smart car network status, including network topology, routing, queuing data, traffic matrix, and time data;

[0148] Based on the trained spatiotemporal graph attention network, the network snapshot is processed to obtain multiple network paths and the corresponding scores for each network path.

[0149] The storage unit 720 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 7201 and / or a cache memory unit 7202 , and may further include a read-only memory unit (ROM) 7203 .

[0150] The storage unit 720 may also include a program / utility 7207 having a set (at least one) of program modules 7207, such program modules 7207 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include an implementation of a network environment.

[0151] Bus 730 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0152] The electronic device 700 may also communicate with one or more external devices 770 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 700, and / or communicate with any device that enables the electronic device 700 to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication may be performed through an input / output (I / O) interface 770. In addition, the electronic device 700 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through a network adapter 770. As shown, the network adapter 770 communicates with other modules of the electronic device 700 through a bus 730. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 700, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0153] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0154] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, which may be a readable signal medium or a readable storage medium. A program product capable of implementing the above method of the present disclosure is stored thereon. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present disclosure described in the above “Exemplary Method” section of this specification.

[0155] More specific examples of computer-readable storage media in the present disclosure may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0156] In the present disclosure, a computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein a readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A readable signal medium may also be any readable medium other than a 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.

[0157] Alternatively, the program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0158] In specific implementation, the program code for performing the operation of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0159] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, 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 multiple modules or units to be embodied.

[0160] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0161] Through the description of the above implementation modes, it is easy for those skilled in the art to understand that the example implementation modes described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation mode of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation mode of the present disclosure.

[0162] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the appended claims.

Claims

1. A data processing method, characterized in that: include: Obtaining a network snapshot of the intelligent vehicle network status, wherein the network snapshot includes network topology, routing, queuing data, traffic matrix, and time data; Processing the network snapshot based on the trained spatiotemporal graph attention network to obtain multiple network paths and a score corresponding to each network path; The network snapshot is processed based on the trained spatiotemporal graph attention network to obtain multiple network paths and scores corresponding to each network path, including: Parsing the network snapshot based on the parsing module in the spatiotemporal graph attention network to obtain a network topology, a routing scheme, and a queuing scheme corresponding to the network snapshot; The network topology, routing scheme and queuing scheme are input into the hidden layer of the spatiotemporal graph attention network to obtain hidden vectors corresponding to links and paths respectively.

2. The data processing method according to claim 1, characterized in that: The network snapshot is processed based on the trained spatiotemporal graph attention network to obtain multiple network paths and scores corresponding to each network path, including: The time feature of the network snapshot is extracted from the network snapshot based on the time module in the spatiotemporal graph attention network.

3. The data processing method according to claim 2, characterized in that: The network snapshot is processed based on the trained spatiotemporal graph attention network to obtain multiple network paths and scores corresponding to each network path, including: The hidden vectors corresponding to the links and paths, respectively, and the time features corresponding to the network snapshots are input into a self-attention layer, so that a gating unit in the self-attention layer determines an attention score of the links on the paths.

4. The data processing method according to claim 3, characterized in that: The network snapshot is processed based on the trained spatiotemporal graph attention network to obtain multiple network paths and scores corresponding to each network path, including: The attention scores of the links on the path, the hidden vectors corresponding to the links and paths, and the time features corresponding to the network snapshots are input into the readout layer of the spatiotemporal graph attention network to obtain multiple network paths and the scores corresponding to each network path, wherein the scores include delay scores, jitter scores, and packet loss rates.

5. The data processing method according to claim 1, characterized in that: The method further comprises: The spatiotemporal graph attention network is trained based on historical network snapshots, historical network paths, and the scores corresponding to the historical paths; When the loss function value reaches the preset value, the training is stopped and the trained spatiotemporal graph attention network is obtained.

6. A data processing device, characterized in that: include: An acquisition module, used to acquire a network snapshot of the intelligent vehicle network status, wherein the network snapshot includes network topology, routing, queuing data, traffic matrix and time data; A processing module, used to process the network snapshot based on the trained spatiotemporal graph attention network to obtain multiple network paths and a score corresponding to each network path; Processing module, including: A parsing unit, used to parse the network snapshot based on the parsing module in the spatiotemporal graph attention network to obtain the network topology, routing scheme and queuing scheme corresponding to the network snapshot; The first input unit is used to input the network topology, routing scheme and queuing scheme into the hidden layer of the spatiotemporal graph attention network to obtain the hidden vectors corresponding to the links and paths respectively.

7. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to execute the data processing method according to any one of claims 1 to 5 by executing the executable instructions.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that When the computer program is executed by a processor, the data processing method according to any one of claims 1 to 5 is implemented.

Images