Network access method and device, electronic equipment and storage medium

Abstract

The invention discloses a network access method and device, electronic equipment and a storage medium. The method comprises the steps that NPS servers are deployed on multiple cross-regional nodes respectively; based on an AI model, basic information of a vehicle and network information of the NPS server side, the optimally matched NPS server side is obtained, and the basic information of the vehicle at least comprises vehicle regional information; and matching the NPS server with the lowest time delay based on the DNS analysis service and the current vehicle regional information. According to the invention, network penetration and routing based on geographical location awareness are realized. The method can be used for network penetration of automatic driving.

Description

Technical Field

[0001] The present application relates to the field of network access technology, and in particular to a network access method, device, electronic device, and storage medium. Background Art

[0002] NPS (Network Policy Server) is a lightweight, high-performance, and powerful intranet penetration proxy server, which is mainly used to achieve communication between the intranet and the extranet. NPS supports TCP and UDP traffic forwarding, and can support any TCP and UDP upper layer protocols, allowing users to easily set up and use it.

[0003] In related technologies, NPS can be used as an intranet penetration tool for autonomous driving to access intranet services on the public network. However, as the complexity of business increases, the single-node network penetration method based on NPS cannot meet the cross-regional (across different cities) and cross-country business needs of autonomous driving. In addition, it cannot guarantee low latency in the usage scenario. Summary of the invention

[0004] The embodiments of the present application provide a network access method, device, electronic device, and storage medium to implement an autonomous driving network penetration and routing solution based on geographic location perception.

[0005] The present application embodiment adopts the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a network access method, wherein the method includes:

[0007] Deploy NPS servers on multiple nodes across regions;

[0008] Based on the AI ​​model, basic information of the vehicle, and network information of the NPS server, obtaining the best matching NPS server, wherein the basic information of the vehicle includes at least vehicle region information; and

[0009] Based on the DNS resolution service and the current vehicle geographical information, the NPS server with the lowest latency is matched.

[0010] In some embodiments, the deploying of NPS servers on multiple nodes across regions respectively includes:

[0011] Determining at least two nodes within the cross-region;

[0012] Deploy NPS servers respectively according to the at least two nodes, wherein an actual deployment location of the NPS server is the same as or different from a geographical location of any one of the at least two nodes;

[0013] According to the NPS server, the corresponding open NPS port is obtained.

[0014] In some embodiments, the AI ​​model, basic information of the vehicle, and network information of the NPS server are used to obtain the best matching NPS server, wherein the basic information of the vehicle includes at least vehicle region information, including:

[0015] Maintain any one or more of the basic information of the vehicle: license plate, SN, domain controller information, vehicle area information and vehicle trajectory information obtained every minute;

[0016] Based on the AI ​​model, the vehicle geographical information, the network information of the NPS server, and the location of the NPS server are taken as inputs, and the AI ​​model outputs the NPS server that is routed to and / or accessed with the best vehicle network load when accessing the NPS service as the optimally matched NPS server.

[0017] In some embodiments, the AI ​​model uses a network analysis model, and the network analysis model includes a linear model to predict network delay, and the linear model includes:

[0018] Network delay = w1*vehicle network log feature 1+w2*vehicle network log feature 2+…+w n * Vehicle network log features n+b,

[0019] The delay includes the network delay from the NPS server to the vehicle;

[0020] w1,w2,...w n are the linear model parameters, which can be learned through a preset algorithm;

[0021] The vehicle network log feature 1, vehicle network log feature 2, ..., vehicle network log feature n are features extracted from the vehicle network log;

[0022] The b is a bias term.

[0023] In some embodiments, the matching of the NPS server with the lowest latency based on the DNS resolution service and the current vehicle region information includes:

[0024] Determine the NPS server node closest to the current vehicle based on the current vehicle region information;

[0025] In response to accessing the vehicle-side domain control environment and / or calling the vehicle-side service, the NPS server with the lowest latency is matched according to the NPS server node closest to the current vehicle.

[0026] In some embodiments, the matching of the NPS server with the lowest latency based on the DNS resolution service and the current vehicle region information includes:

[0027] When accessing the vehicle-side service through the unique NPS service access address, the domain name is resolved through the dynamic DNS resolution service;

[0028] According to the resolution result of the dynamic DNS resolution service, the terminal interface is called and the NPS server address is matched, and the NPS server address is resolved to the corresponding NPS server address.

[0029] In some embodiments, the method further comprises:

[0030] The NPS server with the lowest latency is synchronized to the local database where the NPS server with the best match for the vehicle provided by the AI ​​model is located.

[0031] In a second aspect, an embodiment of the present application further provides a network access device, wherein the device includes:

[0032] Initialization module, used to deploy NPS servers on multiple nodes across regions;

[0033] A first matching module, configured to obtain the best matching NPS server based on the AI ​​model, basic information of the vehicle, and network information of the NPS server, wherein the basic information of the vehicle includes at least vehicle region information; and

[0034] The second matching module is used to match the NPS server with the lowest delay based on the DNS resolution service and the current vehicle regional information.

[0035] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor; and a memory arranged to store computer executable instructions, wherein the executable instructions, when executed, cause the processor to perform the above method.

[0036] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes the above method.

[0037] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: deploy the NPS server on multiple nodes across regions respectively, and then obtain the best matching NPS server based on the AI ​​model, the basic information of the vehicle, and the network information of the NPS server, wherein the basic information of the vehicle includes at least the vehicle geographical information. At the same time, based on the DNS resolution service and the current vehicle geographical information, match the NPS server with the lowest delay. Through the above method, the dynamic distributed transformation of NPS is realized to obtain the best matching NPS server, and at the same time, according to the current vehicle geographical information, match the NPS server with the lowest delay. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0039] Figure 1 This is a schematic diagram of the overall implementation principle of the network access method in the embodiment of the present application;

[0040] Figure 2 A schematic diagram of the implementation principle of the network analysis model of the network access method in the embodiment of the present application;

[0041] Figure 3 A flowchart of a network access method in an embodiment of the present application;

[0042] Figure 4 This is a schematic diagram of the structure of a network access device in an embodiment of the present application;

[0043] Figure 5 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0045] In related technologies, the shortcomings of the NPS server include:

[0046] (1) Using a single-node NPS server for forwarding can easily lead to increased network latency.

[0047] No matter where the vehicle is traveling, especially when traveling across regions or countries, the fixed NPS single-node server delay will inevitably become slow or even unavailable as the network interaction delay increases. Therefore, the single-node solution cannot meet the network penetration mapping requirements of mobile edge devices such as autonomous driving.

[0048] (2) The NPS server is deployed in a single-node manner.

[0049] The NPS server is deployed as a single server, and no high availability methods such as clusters are provided, which makes the operation of the NPS server subject to single point failure.

[0050] (3) The upper limit of the number of ports that can be mapped is fixed.

[0051] Since NPS can only be deployed on a single node, the port for penetration mapping is limited to the server port range (0-65535). However, when there are many vehicles and each vehicle needs to map many services, the server port range becomes a restriction.

[0052] The NPS penetration technology among related technologies has significant deficiencies when facing scenarios such as autonomous driving, where vehicles are distributed in different regions and countries, and even a single vehicle often changes regions and countries.

[0053] In the embodiment of the present application, a network access method is provided, which effectively meets the basic penetration requirements and realizes the high availability of NPS, guarantees data consistency, unlimited port mapping, and the ability to minimize cross-regional latency. This ensures the real-time access of personnel and programs to the autonomous driving vehicle domain control environment, and better ensures the stable operation of the entire autonomous driving basic operating environment.

[0054] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0055] like Figure 1 As shown, the network penetration method mainly includes the following steps:

[0056] S11, user NPS addition, deletion, modification and query operations.

[0057] S12, the NPS control plane uniformly manages the front end.

[0058] S13, control plane NPS management backend.

[0059] S14, the vehicle agent reports the vehicle area information once a minute.

[0060] S15, real-time regional information of the vehicle.

[0061] S16, network analysis model, gives the network status of the vehicle and each NPS Server.

[0062] S17, MYSQL, stores the basic NPS information and synchronizes it to the NPS server closest to the vehicle, and updates the vehicle NPS to the NPS server closest to the vehicle every minute.

[0063] S18, by region.

[0064] Beijing NPS server (file database), Nanjing NPS server (file database), Xinjiang NPS server (file database).

[0065] like Figure 2 The schematic diagram of the implementation principle of the network analysis model mainly includes the following steps:

[0066] S21, AI model support (including Beijing NPS server, Nanjing NPS server, Xinjiang NPS server) and provide the NPS server with the best network solution to the control plane NPS management backend. The control plane NPS management backend obtains the best NPS server address from the control plane before DNS resolution.

[0067] S22, dynamic DNS resolution service.

[0068] S23, access nps.x.com to access a process service on the vehicle side.

[0069] S24, select the best NPS server address from Beijing NPS server, Nanjing NPS server, and Xinjiang NPS server.

[0070] The present application embodiment provides a network access method, such as Figure 3 As shown, a schematic diagram of a network access method in an embodiment of the present application is provided, and the method at least includes the following steps S310 to S330:

[0071] Step S310, deploying NPS servers on multiple nodes across regions respectively.

[0072] "Cross-region" refers to the cross-region situation in domestic cities. The NPS server can be deployed on multiple nodes across regions, and each node is still deployed as a single node (server service + server storage file).

[0073] For example, a cloud server is applied for NPS server deployment in Beijing node and Dali node respectively, and NPS port is opened. In other words, NPS server is deployed in Beijing node and Dali node respectively.

[0074] Furthermore, after the NPS server deployed on multiple nodes is encapsulated in the upper layer, the original node still works as a single machine, but can achieve a distributed effect and synchronize NPS nodes in real time.

[0075] Step S320, based on the AI ​​model and the basic information of the vehicle and the network information of the NPS server, the best matching NPS server is obtained, and the basic information of the vehicle includes at least the vehicle geographical information.

[0076] The "AI model" can be a machine learning model or a pre-trained large language model, which is not specifically limited in the embodiments of the present application. The "basic information of the vehicle" needs to include at least the vehicle's geographical information, such as initial positioning based on GPS, and high-precision specific positioning combined with RTK on the vehicle.

[0077] Through the AI ​​model, the basic information of the vehicle, and the network information of the NPS server, the best matching NPS server can be screened and obtained. It can be understood that the "best matching NPS server" refers to the one obtained after comprehensively considering the location of the vehicle, the attributes of the vehicle, and the network conditions of the NPS server.

[0078] Step S330, matching the NPS server with the lowest delay based on the DNS resolution service and the current vehicle regional information.

[0079] Since the vehicle regional information may be constantly changing, based on the DNS resolution service and the current vehicle regional information, the NPS server with the lowest latency can be matched from the best matching NPS server, thereby meeting the network access requirements.

[0080] Furthermore, the AI ​​model needs to obtain the basic vehicle and vehicle regional information in real time, and perform real-time analysis on the network communication delay between the vehicle and the nearest multiple NPS Servers (for example, the vehicle is in Shanghai or the user is in Beijing) based on the collected network information, so as to select the one with the best communication quality. In this way, when accessing the NPS server through the unified target network, it will be routed to and / or access the NPS server with the best vehicle network load. At the same time, the information of the vehicle and its best matching NPS server can be updated in the background database at regular intervals. It can be understood that network information includes, but is not limited to, basic network communication logs, service link delays, load conditions, etc. By analyzing these network information, the network quality of the NPS server can be characterized.

[0081] Through the above method, first, NPS servers are deployed on multiple nodes across regions; then, based on the AI ​​model, basic information of the vehicle, and network information of the NPS server, the best matching NPS server is obtained, and the basic information of the vehicle includes at least the vehicle region information; finally, based on the DNS resolution service and the current vehicle region information, the NPS server with the lowest latency is matched. Not only is network penetration of the best matching NPS server achieved, but also the NPS server with the lowest latency is matched based on the DNS resolution service according to the vehicle region information.

[0082] Through the above method, the NPS server is transformed from a single point to a distributed one. The vehicle NPS information is modified in real time through the AI ​​model and the user front end to the optimal NPS server on the network. In addition, the unified domain name of the NPS server is dynamically accessed and resolved to the optimal NPS server.

[0083] Different from the related art, the use of a single-node NPS server forwarding can easily lead to the problem of increased network latency. With the above method, the default web front-end of NPS is no longer used, because a single web front-end only manages a single NPS server. Instead, the user performs maintenance operations on the NPS data on the front-end page, controls the back-end Mysql database to store a copy of the basic data through the front-end page, and synchronizes the current NPS information to the local database of the vehicle's optimal matching NPS server provided by AI. At the same time, the Mysql stores the optimal NPS server address, NPSkey, NPS user information, vehicle port, and mapping port for the current vehicle connection.

[0084] Different from the problem of single-node deployment of NPS server in related technologies, the above method controls the back-end Mysql database to store a copy of basic data through the front-end page, and synchronizes the current NPS information to the local database of the vehicle optimal matching NPS server provided by AI.

[0085] Different from the problem of the upper limit of the number of ports that can be mapped in the related art, the DNS resolution service in the above method not only supports access to the distributed system, but also can obtain the vehicle and vehicle optimal NPS server address in the distributed system, and then dynamically load the result to the optimal NPS server based on the current vehicle regional information. In other words, the ports mapped by NPS on each node are not repeated.

[0086] In one embodiment of the present application, the respectively deploying NPS servers on multiple nodes across regions includes: determining at least two nodes within the cross-region; respectively deploying NPS servers based on the at least two nodes, the actual deployment location of the NPS server being the same as or different from the geographical location of any one of the at least two nodes; and obtaining a corresponding open NPS port based on the NPS server.

[0087] The NPS server is transformed into a cross-region distributed deployment, transforming a single node (server service + server storage file) into a cross-regional multi-node NPS server. All NPS server nodes are centrally scheduled through a self-developed distributed management system.

[0088] When deploying the NPS server on multiple nodes, apply for a cloud server for the Beijing node and Dali node in the cloud for NPS server deployment and open the NPS port.

[0089] In one embodiment of the present application, the best matching NPS server is obtained based on the AI ​​model and the basic information of the vehicle and the network information of the NPS server, and the basic information of the vehicle includes at least the vehicle geographical information, including: maintaining any one or more of the basic information of the vehicle: license plate, SN, domain controller information and vehicle geographical information obtained every minute, and vehicle trajectory information; based on the AI ​​model, the vehicle geographical information, the network information of the NPS server, and the location of the NPS server are used as input, and the NPS server with the best vehicle network load that is routed to and / or accessed when accessing the NPS service is obtained through the output of the AI ​​model as the best matching NPS server.

[0090] In the vehicle management system, the basic information of the vehicle is maintained, including but not limited to license plate information, vehicle SN information, and domain controller information, and the vehicle's trajectory information and location information are obtained from the vehicle reporting agent module every minute and updated to the vehicle basic information. The best NPS server to be routed when accessing the NPS service is obtained through the output of the AI ​​model. The best NPS server when accessing the vehicle network load is obtained through the output of the AI ​​model.

[0091] It is understandable that the location of the NPS server can be located in multiple different places or in the same place.

[0092] In one embodiment of the present application, the AI ​​model adopts a network analysis model, which includes a linear model to predict network delay, and the linear model includes: network delay = w1*vehicle network log feature 1+w2*vehicle network log feature 2+…+w n* Vehicle network log feature n+b, the delay includes the network delay from the NPS server to the vehicle; the w1, w2, ... w n is a linear model parameter, which can be learned through a preset algorithm; the vehicle network log feature 1, vehicle network log feature 2, ..., vehicle network log feature n are based on features extracted from the vehicle network log; and b is a bias term.

[0093] The model uses the Online Gradient Descent model to obtain vehicle basic and vehicle regional information in real time, and conducts real-time analysis on the network communication delay between the vehicle and the nearest NPS Servers (users in Shanghai or users in Beijing) based on the collected network information (basic network communication logs, service link delays, load conditions, etc.), and selects the one with the best communication conditions. When accessing nps through nps.x.com, it will be routed to the NPS server with the best vehicle network load. The vehicle and its best matching NPS server information will be updated to the control plane database once a minute.

[0094] The model can be expressed as: Network delay = w1*vehicle network log feature 1+w2*vehicle network log feature 2+...+w n * Vehicle network log features n+b.

[0095] Delay is the network delay from the NPS server to the vehicle. w1,w2,...,w n is a model parameter that needs to be learned through the OGD algorithm. b is a bias term. Vehicle network log feature 1, vehicle network log feature 2, ..., vehicle network log feature n are features extracted from vehicle network logs, such as network load, vehicle location, network type, etc.

[0096] The update rules of the OGD algorithm are as follows:

[0097] Where: w i (t) is the value of the i-th parameter at time t. η is the learning rate, which controls the step size of each update. is the loss function L i About w i The loss function can be the mean square error (MSE) or other suitable loss functions.

[0098] Based on the packaged distributed management system, the consistency of all nodes on the NPS server is guaranteed. The default NPS web front end is no longer used, because a single web front end only manages a single NPS server. Users perform NPS data maintenance operations on the front end, and the back-end Mysql storage stores a copy of the basic data and synchronizes the NPS information to the local database of the vehicle optimal matching NPS server provided by AI.

[0099] In one embodiment of the present application, the matching of the NPS server with the lowest latency based on the DNS resolution service and the current vehicle geographical information includes: determining the NPS server node closest to the current vehicle based on the current vehicle geographical information; in response to accessing the vehicle-side domain control environment and / or calling the vehicle-side service, matching the NPS server with the lowest latency based on the NPS server node closest to the current vehicle.

[0100] NPS is transformed from a single point to a distributed one. The vehicle NPS information is modified in real time to the optimal NPS Server on the network through AI models and front-end and back-end programs. NPS unified domain name is dynamically accessed and resolved to the optimal NPS server: Based on the basic information after the above transformation, through AI models, front-end and back-end programs, and DNS dynamic resolution, vehicles and users are always allowed to interact through the optimal NPS Server.

[0101] In one embodiment of the present application, the NPS server with the lowest delay is matched based on the DNS resolution service and the current vehicle geographical information, including: when accessing the vehicle-side service through a unique NPS service access address, performing domain name resolution through a dynamic DNS resolution service; calling a terminal interface according to the resolution result of the dynamic DNS resolution service and matching the NPS server address, and resolving the NPS server address to a corresponding NPS server address.

[0102] Intelligent routing ensures that the latency of cross-regional NPS access is always the lowest, and users access through a unified NPS domain name. When a vehicle travels to a specific area (corresponding to the vehicle's regional information), the NPS domain name is automatically resolved to the NPS server node closest to the vehicle, so that when users access the vehicle-side domain control environment or call vehicle-side services, the latency is always the lowest.

[0103] In specific implementation, GeoDNS can be used to support access to distributed systems, obtain the optimal NPS server addresses of vehicles and vehicles in the distributed system, and then dynamically load to the optimal NPS server based on the returned results. For example, when the nps.x.com domain name is used as the unified access domain name for all NPS servers, the impact of changes in the number and IP addresses of backend NPS servers can be shielded.

[0104] For example, when a user accesses the vehicle-side service through "nps.x.com:port" (for example: nps.x.com:35157) on the program side, bastion machine terminal, or http interface, the domain name is first resolved through GeoDNS, and then the distributed backend interface is called according to GeoDNS, the nps server address is matched through port 35157, and finally the domain name is resolved to the specific NPS server address.

[0105] It should be noted that when users access the NPS server, the mapped ports cannot be repeated.

[0106] When the current number of 0-65535 ports can meet the mapping requirements of all vehicle services, ensure that the vehicle port is mapped to a unique port of 0-65535. In other words, 0-65535 is allocated to each NPS server. When a user accesses the service through nps.x.com:38816, the backend MySQL database will match the NPS server IP address according to 38816.

[0107] At the same time, when the number of ports 0-65535 cannot meet the mapping ports of all vehicle services, it is necessary to add virtual ports to meet the needs. For example, the current Mysql fields are vehicle SN, NPS server address, vehicle service port, and NPS server mapping port. The "NPS server mapping port" is always unique, so when the user accesses the service through something like nps.x.com:38816, the control plane Mysql database will match the NPS server IP address according to 38816.

[0108] In addition, in order to avoid duplication when adding virtual ports, for example, ports 0-100000 can meet the mapping requirements of the current vehicle-side service. The Mysql fields are modified to vehicle SN, NPS server address, vehicle-side service port, NPS server mapping port, and virtual port. When users access the service at nps.x.com:98816, they will go to the control plane Mysql database to match the NPS server IP address and the actual mapping port according to 98816 for access.

[0109] In one embodiment of the present application, the method further includes: synchronizing the NPS server with the lowest delay to a local database where the NPS server with the best match for the vehicle provided by the AI ​​model is located.

[0110] According to the NPS server with the lowest delay, it is synchronized to the local database where the NPS server with the best match for the vehicle provided by the AI ​​model is located, and the NPS server with the lowest delay is further matched.

[0111] The present application embodiment also provides a network access device 400, such as Figure 4 As shown, a schematic diagram of the structure of a network access device in an embodiment of the present application is provided, wherein the network access device 400 at least includes: an initialization module 410, a first matching module 420, and a second matching module 430, wherein:

[0112] In one embodiment of the present application, the acquisition module 410 is specifically used to: deploy NPS servers on multiple nodes across regions respectively.

[0113] "Cross-region" refers to the cross-region situation in domestic cities. The NPS server can be deployed on multiple nodes across regions, and each node is still deployed as a single node (server service + server storage file).

[0114] For example, a cloud server is applied for NPS server deployment in Beijing node and Dali node respectively, and NPS port is opened. In other words, NPS server is deployed in Beijing node and Dali node respectively.

[0115] Furthermore, after the NPS server deployed on multiple nodes is encapsulated in the upper layer, the original node still works as a single machine, but can achieve a distributed effect and synchronize NPS nodes in real time.

[0116] In one embodiment of the present application, the first matching module 420 is specifically used to obtain the best matching NPS server based on the AI ​​model, basic information of the vehicle, and network information of the NPS server, wherein the basic information of the vehicle includes at least vehicle geographical information.

[0117] The "AI model" can be a machine learning model or a pre-trained large language model, which is not specifically limited in the embodiments of the present application. The "basic information of the vehicle" needs to include at least the vehicle's geographical information, such as initial positioning based on GPS, and high-precision specific positioning combined with RTK on the vehicle.

[0118] Through the AI ​​model, the basic information of the vehicle, and the network information of the NPS server, the best matching NPS server can be screened and obtained. It can be understood that the "best matching NPS server" refers to the one obtained after comprehensively considering the location of the vehicle, the attributes of the vehicle, and the network conditions of the NPS server.

[0119] In one embodiment of the present application, the second matching module 430 is specifically used to match the NPS server with the lowest delay based on the DNS resolution service and the current vehicle regional information.

[0120] Since the vehicle regional information may be constantly changing, based on the DNS resolution service and the current vehicle regional information, the NPS server with the lowest latency can be matched from the best matching NPS server, thereby meeting the network access requirements.

[0121] Furthermore, the AI ​​model needs to obtain the basic vehicle and vehicle regional information in real time, and perform real-time analysis on the network communication delay between the vehicle and the nearest multiple NPS Servers (for example, the vehicle is in Shanghai or the user is in Beijing) based on the collected network information, so as to select the one with the best communication quality. In this way, when accessing the NPS server through the unified target network, it will be routed to and / or access the NPS server with the best vehicle network load. At the same time, the information of the vehicle and its best matching NPS server can be updated in the background database at regular intervals. It can be understood that network information includes, but is not limited to, basic network communication logs, service link delays, load conditions, etc. By analyzing these network information, the network quality of the NPS server can be characterized.

[0122] In one embodiment of the present application, the initialization module 410 is also used to

[0123] Determining at least two nodes within the cross-region;

[0124] Deploy NPS servers respectively according to the at least two nodes, wherein an actual deployment location of the NPS server is the same as or different from a geographical location of any one of the at least two nodes;

[0125] According to the NPS server, the corresponding open NPS port is obtained.

[0126] In one embodiment of the present application, the first matching module 420 is also used to

[0127] Maintain any one or more of the basic information of the vehicle: license plate, SN, domain controller information, vehicle area information and vehicle trajectory information obtained every minute;

[0128] Based on the AI ​​model, the vehicle geographical information, the network information of the NPS server, and the location of the NPS server are taken as inputs, and the AI ​​model outputs the NPS server that is routed to and / or accessed with the best vehicle network load when accessing the NPS service as the optimally matched NPS server.

[0129] In one embodiment of the present application, the AI ​​model adopts a network analysis model, and the network analysis model includes a linear model to predict network delay, and the linear model includes:

[0130] Network delay = w1*vehicle network log feature 1+w2*vehicle network log feature 2+…+w n * Vehicle network log features n+b,

[0131] The delay includes the network delay from the NPS server to the vehicle;

[0132] w1,w2,...w n are the linear model parameters, which can be learned through a preset algorithm;

[0133] The vehicle network log feature 1, vehicle network log feature 2, ..., vehicle network log feature n are features extracted from the vehicle network log;

[0134] The b is a bias term.

[0135] In one embodiment of the present application, the second matching module 430 is further used to

[0136] Determine the NPS server node closest to the current vehicle based on the current vehicle region information;

[0137] In response to accessing the vehicle-side domain control environment and / or calling the vehicle-side service, the NPS server with the lowest latency is matched according to the NPS server node closest to the current vehicle.

[0138] In one embodiment of the present application, the second matching module 430 is further used to

[0139] When accessing the vehicle-side service through the unique NPS service access address, the domain name is resolved through the dynamic DNS resolution service;

[0140] According to the resolution result of the dynamic DNS resolution service, the terminal interface is called and the NPS server address is matched, and the NPS server address is resolved to the corresponding NPS server address.

[0141] In one embodiment of the present application, it further includes: a synchronization module for

[0142] The NPS server with the lowest latency is synchronized to the local database where the NPS server with the best match for the vehicle provided by the AI ​​model is located.

[0143] It can be understood that the above-mentioned network access device can implement each step of the network access method provided in the above-mentioned embodiment, and the relevant explanations about the network access method are applicable to the network access device and will not be repeated here.

[0144] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 5At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0145] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0146] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0147] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a network access device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0148] Deploy NPS servers on multiple nodes across regions;

[0149] Based on the AI ​​model, basic information of the vehicle, and network information of the NPS server, obtaining the best matching NPS server, wherein the basic information of the vehicle includes at least vehicle region information; and

[0150] Based on the DNS resolution service and the current vehicle geographical information, the NPS server with the lowest latency is matched.

[0151] The above application Figure 3The method performed by the network access device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0152] The electronic device may also perform Figure 3 The method executed by the network access device in Figure 3 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0153] The present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to execute Figure 3 The method performed by the network access device in the illustrated embodiment is specifically used to perform:

[0154] Deploy NPS servers on multiple nodes across regions;

[0155] Based on the AI ​​model, basic information of the vehicle, and network information of the NPS server, obtaining the best matching NPS server, wherein the basic information of the vehicle includes at least vehicle region information; and

[0156] Based on the DNS resolution service and the current vehicle geographical information, the NPS server with the lowest latency is matched.

[0157] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0158] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0159] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0160] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0161] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0162] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0163] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0164] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0165] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0166] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A network access method, wherein: The method comprises: Deploy NPS servers on multiple nodes across regions; Based on the AI ​​model, basic information of the vehicle, and network information of the NPS server, obtaining the best matching NPS server, wherein the basic information of the vehicle includes at least vehicle region information; and Based on the DNS resolution service and the current vehicle geographical information, the NPS server with the lowest latency is matched.

2. The method of claim 1, wherein: The NPS server is deployed on multiple nodes across regions respectively, including: Determining at least two nodes within the cross-region; Deploy NPS servers respectively according to the at least two nodes, wherein an actual deployment location of the NPS server is the same as or different from a geographical location of any one of the at least two nodes; According to the NPS server, the corresponding open NPS port is obtained.

3. The method of claim 1, wherein: The method of obtaining the best matching NPS server based on the AI ​​model, the basic information of the vehicle, and the network information of the NPS server, wherein the basic information of the vehicle includes at least the vehicle region information, includes: Maintain any one or more of the basic information of the vehicle: license plate, SN, domain controller information, vehicle area information and vehicle trajectory information obtained every minute; Based on the AI ​​model, the vehicle geographical information, the network information of the NPS server, and the location of the NPS server are taken as inputs, and the AI ​​model outputs the NPS server that is routed to and / or accessed with the best vehicle network load when accessing the NPS service as the optimally matched NPS server.

4. The method of claim 3, wherein: The AI ​​model adopts a network analysis model, which includes a linear model to predict network delay, and the linear model includes: Network delay = w1*vehicle network log feature 1+w2*vehicle network log feature 2+…+w n * Vehicle network log features n+b, The network delay is the network delay from the NPS server to the vehicle. w1,w2,...w n are the linear model parameters, which can be learned through a preset algorithm; The vehicle network log feature 1, vehicle network log feature 2, ..., vehicle network log feature n are features extracted from the vehicle network log; The b is a bias term.

5. The method of claim 1, wherein: The matching of the NPS server with the lowest latency based on the DNS resolution service and the current vehicle regional information includes: Determine the NPS server node closest to the current vehicle based on the current vehicle region information; In response to accessing the vehicle-side domain control environment and / or calling the vehicle-side service, the NPS server with the lowest latency is matched according to the NPS server node closest to the current vehicle.

6. The method of claim 5, wherein: The matching of the NPS server with the lowest latency based on the DNS resolution service and the current vehicle regional information includes: When accessing the vehicle-side service through the unique NPS service access address, the domain name is resolved through the dynamic DNS resolution service; According to the resolution result of the dynamic DNS resolution service, the terminal interface is called and the NPS server address is matched, and the NPS server address is resolved to the corresponding NPS server address.

7. The method according to any one of claims 1 to 6, wherein: The method further comprises: The NPS server with the lowest latency is synchronized to the local database where the NPS server with the best match for the vehicle provided by the AI ​​model is located.

8. A network access device, wherein: The device comprises: Initialization module, used to deploy NPS servers on multiple nodes across regions; A first matching module, configured to obtain the best matching NPS server based on the AI ​​model, basic information of the vehicle, and network information of the NPS server, wherein the basic information of the vehicle includes at least vehicle region information; and The second matching module is used to match the NPS server with the lowest delay based on the DNS resolution service and the current vehicle regional information.

9. An electronic device, comprising: processor; as well as A memory arranged to store computer executable instructions, which when executed cause the processor to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, causes the electronic device to execute any one of the methods of claims 1 to 7.

Images