Collaborative awareness cloud platform device

Abstract

The invention discloses a collaborative awareness cloud platform device, which realizes a 5G-V2X technology through a data receiving and transmitting module, a load balancing module, a Netty server cluster module, a message queue module and a storage module, ensures low-delay and high-bandwidth data transmission between a vehicle and a roadside sensor, and adopts a high-availability design of the load balancing module, so that the reliability of the system is improved. The system stability is guaranteed, intelligent cooperative sensing of multi-source data is realized, and the global sensing and autonomous decision-making capabilities of the vehicle are improved.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle-mounted cloud control platforms, and in particular to a collaborative perception cloud platform device. Background Art

[0002] With the continuous development of vehicle technology, vehicle driving safety, intelligent management and precise control have become key requirements.

[0003] When driving, vehicles generally rely on a single sensor for environmental perception. Due to the limitations of detection distance and environmental factors, there are blind spots in perception, making it difficult to fully perceive the complex environment during high-speed driving, which affects the vehicle's driving safety and intelligence level. Summary of the invention

[0004] In view of this, the present application provides a collaborative perception cloud platform device, and its specific solution is as follows:

[0005] A collaborative sensing cloud platform device, comprising:

[0006] A data transceiver module, used to obtain a plurality of sensing data transmitted by a vehicle and / or a roadside sensor, and capable of outputting control data obtained after processing the plurality of sensing data;

[0007] A load balancing module is used to obtain the multiple perception data obtained by the data transceiver module, perform load balancing processing, and distribute the multiple perception data to different Netty servers in the Netty server cluster module respectively;

[0008] A Netty server cluster module, comprising at least two Netty servers, for processing the allocated perception data in parallel through the at least two Netty servers;

[0009] A message queue module, used to obtain the perception data processed by the Netty server cluster module, and publish and subscribe to message queues based on the processed perception data;

[0010] The storage module is used to store the control data generated based on the subscription message queue, so that the data transceiver module can call the control data stored in the storage module and output it.

[0011] Furthermore, the storage module includes:

[0012] A database storage module, used for storing the control data in structured and unstructured data;

[0013] The cache and distributed storage module is used to cache the first data of the first access request, and when the cached second data is requested for access again, in response to the re-access request, retrieve the cached second data from the cache and distributed storage module.

[0014] Furthermore, the database storage module consists of a MongoDB cluster.

[0015] Furthermore, the cache and distributed storage module is composed of a Redis sentinel cluster.

[0016] Furthermore, the load balancing module includes:

[0017] A Linux virtual server unit, configured to perform a first load balancing on the plurality of sensing data according to a load balancing strategy, and distribute the plurality of sensing data subjected to the first load balancing to a load balancing unit;

[0018] A load balancing unit, configured to perform a second load balancing on the acquired perception data allocated by the Linux virtual server unit and processed by the first load balancing, and distribute the plurality of perception data processed by the second load balancing to different Netty servers in the Netty server cluster module;

[0019] The Keepalived unit is used to monitor the status of the Linux virtual server unit.

[0020] Furthermore, the Keepalived unit included in the load balancing module communicates via a virtual routing redundancy protocol.

[0021] Further, the Keepalived unit includes:

[0022] The user space layer is used to monitor the status of the Linux virtual server unit and can output instructions to the kernel space layer;

[0023] The kernel space layer is used to obtain instructions from the user space layer and perform communication or data processing based on the instructions from the user space layer.

[0024] Furthermore, the user space layer at least includes:

[0025] a scheduler I / O multiplexer for allocating system resources and monitoring the status of the Linux virtual server units so that the Linux virtual server units can be executed in parallel;

[0026] A memory management structure is used to manage the system resources so that the system resources allocated by the scheduler I / O multiplexer can be allocated and reclaimed.

[0027] Furthermore, it also includes:

[0028] The data processing module is used to process the obtained subscription message queue to generate the control data, and send the control data to the storage module.

[0029] Furthermore, it also includes:

[0030] The API interface module is used to provide interfaces between different modules to achieve data exchange and remote calls.

[0031] It can be seen from the above technical scheme that the collaborative perception cloud platform device disclosed in the present application includes: a data transceiver module, which is used to obtain multiple perception data transmitted by vehicles and / or roadside sensors, and can output the control data obtained after processing the multiple perception data; a load balancing module, which is used to obtain the multiple perception data obtained by the data transceiver module, perform load balancing processing, and distribute the multiple perception data to different Netty servers in the Netty server cluster module; a Netty server cluster module, including at least two Netty servers, which is used to process the allocated perception data in parallel through at least two Netty servers; a message queue module, which is used to obtain the perception data processed by the Netty server cluster module, and publish a subscription message queue based on the processed perception data; a storage module, which is used to store the control data generated based on the subscription message queue, so that the data transceiver module can call the control data stored in the storage module and output it. This solution implements 5G-V2X technology through data transceiver modules, load balancing modules, Netty server cluster modules, message queue modules and storage modules, ensuring low-latency and high-bandwidth data transmission between vehicles and roadside sensors. It adopts the high availability design of the load balancing module to ensure system stability, realize intelligent collaborative perception of multi-source data, and enhance the vehicle's global perception and autonomous decision-making capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 A schematic diagram of the structure of a collaborative sensing cloud platform device disclosed in an embodiment of the present application;

[0034] Figure 2 A schematic diagram of the structure of a collaborative sensing cloud platform device disclosed in an embodiment of the present application applied to a collaborative sensing system;

[0035] Figure 3 A schematic diagram of the structure of a message queue module disclosed in an embodiment of the present application;

[0036] Figure 4 A schematic diagram of a process for processing request information output by a user disclosed in an embodiment of the present application;

[0037] Figure 5 A schematic diagram of the structure of a collaborative perception cloud platform device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0038] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0039] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0040] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0041] This application discloses a collaborative sensing cloud platform device, and its structural diagram is as follows: Figure 1 As shown, including:

[0042] Data transceiver module 11, load balancing module 12, Netty server cluster module 13, message queue module 14 and storage module 15.

[0043] The data transceiver module 11 is used to obtain a plurality of sensing data transmitted by the vehicle and / or roadside sensors, and can output control data obtained after processing the plurality of sensing data;

[0044] The load balancing module 12 is used to obtain multiple perception data obtained by the data transceiver module, perform load balancing processing, and distribute the multiple perception data to different Netty servers in the Netty server cluster module;

[0045] The Netty server cluster module 13 includes at least two Netty servers, and is used to process the allocated perception data in parallel through at least two Netty servers;

[0046] The message queue module 14 is used to obtain the perception data processed by the Netty server cluster module, and publish and subscribe to the message queue based on the processed perception data;

[0047] The storage module 15 is used to store the control data generated based on the subscription message queue, so that the data transceiver module can call the control data stored in the storage module and output it.

[0048] With the continuous development of vehicle technology, vehicle driving safety, intelligent management and precise control have become key requirements.

[0049] When driving, vehicles generally rely on a single sensor for environmental perception. Due to the limitations of detection distance and environmental factors, there are blind spots in perception, making it difficult to fully perceive the complex environment during high-speed driving, which affects the vehicle's driving safety and intelligence level.

[0050] Based on this, this solution realizes low-latency, high-bandwidth data transmission between vehicles and roadside sensors through data transceiver modules, load balancing modules, Netty server cluster modules, message queue modules and storage modules. The Netty server cluster module ensures efficient data processing capabilities. The high availability design of the load balancing module ensures system stability and ensures that the vehicle is not limited by detection distance and environmental factors, reducing perception blind spots and improving vehicle driving safety and intelligence.

[0051] Among them, the data transceiver module includes a data collector and a data output unit. The data collector is used to collect multiple perception data transmitted by vehicles and / or roadside sensors; the data output unit is used to output the control data processed by the collaborative perception cloud platform device disclosed in this embodiment.

[0052] The data collector is used to collect data from the vehicle's sensors and external data sources, where the data from the external data source can be: data output by roadside sensors, whether it is a vehicle sensor or a roadside sensor, the sensors may include: image collectors, lidar, millimeter-wave radar, etc. These sensors collect perception data of the environment, including: images, depth information, radar point cloud information, etc., in order to provide the necessary perception data for the vehicle's autonomous driving.

[0053] After receiving the perception data obtained by the data collector, the collaborative perception cloud platform device disclosed in this embodiment performs complex processing and analysis on the perception data, such as: using cloud computing resources to perform large-scale data processing, train AI models, and provide decision support, etc., to obtain control data.

[0054] After obtaining the control data, the control data calculated in the cloud is output to the vehicle and / or roadside infrastructure through the data output unit in the data transceiver module for collaborative perception and decision-making, thereby realizing multi-party perception and collaborative control in the fields of autonomous driving, intelligent transportation, and vehicle networking.

[0055] Therefore, the collaborative perception system applied by the collaborative perception cloud platform device disclosed in this embodiment is as follows: Figure 2 As shown, it may include: a collaborative perception cloud platform device, a vehicle and a roadside infrastructure, and each of the vehicle and the roadside infrastructure may be one or more. Among them, the roadside infrastructure may include: a roadside sensor, and may also include other infrastructure such as: a traffic light controller, etc.

[0056] In addition, it should be noted that, on the vehicle side, the perception data collected by the vehicle's sensors can be directly sent to the collaborative perception cloud platform device, or the vehicle's sensors can first perform preliminary processing on the vehicle's central control computer after collecting the perception data, and then send the perception data collected by the vehicle's sensors and / or the data after preliminary processing to the collaborative perception cloud platform device disclosed in this embodiment.

[0057] The collaborative perception cloud platform device disclosed in this embodiment may also include a load balancing module, which is used to obtain multiple perception data obtained by the data collector and perform load balancing processing so as to distribute the multiple perception data to different Netty servers in the Netty server cluster respectively.

[0058] The load balancing module performs load balancing processing on the received multiple sensing data so that the multiple sensing data can be processed in parallel, and on the basis of parallel processing, ensures load balancing to ensure high availability and high concurrency of the device.

[0059] The Netty server cluster module includes at least two Netty servers. Each Netty server is assigned different perception data by the load balancing module, and processes the perception data separately, performs multi-threaded data analysis and processing, so that at least two Netty servers included in the Netty server cluster module can process multiple perception data in parallel at the same time, so as to improve data processing efficiency and ensure low latency.

[0060] The message queue module is composed of a Kafka cluster, which is responsible for data publishing and subscription, and is used to coordinate the real-time data flow between modules to ensure the real-time and reliability of data. The message queue module obtains the perception data processed by the Netty server cluster module, and publishes and subscribes to the message queue based on the processed perception data.

[0061] In addition, the collaborative perception cloud platform device disclosed in this embodiment may also include: a storage module, which is used for data storage, and can store the control data generated based on the subscription message queue, and after storage, output it through the data output unit in the data transceiver module.

[0062] This embodiment implements 5G-V2X technology through various modules in vehicles, roadside infrastructure and collaborative perception cloud platform devices, so as to achieve real-time and efficient information interaction and collaborative perception between vehicles and roadside infrastructure, vehicles and collaborative perception cloud platform devices through ultra-low latency and high-bandwidth wireless communication capabilities, which can significantly expand the vehicle's perception range and improve the vehicle's operating safety and intelligence level.

[0063] The collaborative perception cloud platform device disclosed in this embodiment includes: a data transceiver module, which is used to obtain multiple perception data transmitted by vehicles and / or roadside sensors, and can output control data obtained after processing the multiple perception data; a load balancing module, which is used to obtain the multiple perception data obtained by the data transceiver module, perform load balancing processing, and distribute the multiple perception data to different Netty servers in the Netty server cluster module; the Netty server cluster module includes at least two Netty servers, which are used to process the distributed perception data in parallel through at least two Netty servers; a message queue module, which is used to obtain the perception data processed by the Netty server cluster module, and publish a subscription message queue based on the processed perception data; a storage module, which is used to store the control data generated based on the subscription message queue, so that the data transceiver module can call the control data stored in the storage module and output it. This solution implements 5G-V2X technology through data transceiver modules, load balancing modules, Netty server cluster modules, message queue modules and storage modules, ensuring low-latency and high-bandwidth data transmission between vehicles and roadside sensors. It adopts the high availability design of the load balancing module to ensure system stability, realize intelligent collaborative perception of multi-source data, and enhance the vehicle's global perception and autonomous decision-making capabilities.

[0064] Furthermore, the collaborative perception cloud platform device disclosed in this embodiment may also include:

[0065] The data processing module is used to process the obtained subscription message queue to generate control data and send the control data to the storage module. The data processing device can be arranged between the message queue module and the storage module to store the subscription message queue in the storage module after processing.

[0066] The data processing module may include a multi-thread processing unit and an analysis data processing unit. The multi-thread processing unit can directly process the data output by the message queue module. After the data output by the message queue module is processed by the multi-thread processing unit, it can be further processed by the analysis data processing unit.

[0067] In addition, the collaborative perception cloud platform device disclosed in this embodiment may also include:

[0068] The API interface module is used to provide an interface between different modules to achieve data exchange and remote calls. Its specific form can be adjusted based on project requirements.

[0069] Furthermore, in the collaborative perception cloud platform device disclosed in this embodiment, the message queue module can be composed of a Kafka cluster, which can be written in the programming language Scala, and can be used as the basis of LinkedIn's activity stream (Activity Stream) and operational data processing pipeline (Pipeline), with high horizontal scalability and high throughput.

[0070] The message queue module composed of Kafka cluster is a distributed stream platform, which is mainly used for publishing and subscribing real-time data streams and processing large-scale message streams and event streams.

[0071] Among them, the message queue module may include: Kafka cluster, message producer Producer and message consumer Consumer, such as Figure 3 shown.

[0072] The Kafka cluster includes multiple Kafka nodes, which can be called brokers. Each Kafka node is responsible for receiving, storing and forwarding messages. The message producer is used to push data to the Kafka cluster. The message producer sends messages to a specific topic in the Kafka cluster. The message consumer is used to subscribe to topics in the Kafka cluster and consume messages. Consumers obtain data by consuming message streams. Usually, these data are used for subsequent processing or analysis. A topic can have multiple partitions to improve concurrent processing capabilities.

[0073] The message producer sends messages to a specific topic. The Kafka node stores and manages these messages and ensures the persistence and high availability of the data. The message consumer reads messages from the Kafka cluster by subscribing to a specific topic.

[0074] Among them, the deployment plan of the Kafka cluster can be: Since the Kafka cluster saves the status in the Zookeeper cluster, you need to build the Zookeeper cluster first. The first step is to test the software environment. The Zookeeper cluster needs to work more than half to provide services to the outside world. Therefore, you can choose 3 servers for testing; then, configure and install the Zookeeper cluster. First, install Java, then download the Zookeeper cluster, and then modify the configuration files of the three servers. After the server configuration is completed, start the server and check the server status, prepare for Kafka cluster deployment, prepare the environment, and download the Kafka cluster related file package.

[0075] This application discloses a collaborative sensing cloud platform device, and its structural diagram is as follows: Figure 1 As shown, including:

[0076] Data transceiver module 11, load balancing module 12, Netty server cluster module 13, message queue module 14 and storage module 15.

[0077] In addition to the same structure as the previous embodiment, the storage structure 15 in this embodiment may include: a database storage module and a cache and distributed storage module.

[0078] Wherein, the database storage module is used to store control data in structured and unstructured data;

[0079] The cache and distributed storage module is used to cache the first data of the first access request, and when the cached second data is requested for access again, in response to the access request again, retrieve the cached second data from the cache and distributed storage module.

[0080] The database storage module may be composed of a MongoDB cluster for storing structured and unstructured data. The MongoDB cluster is formed by combining multiple MongoDB instances to achieve high availability, load balancing and horizontal expansion of data.

[0081] The architecture modes of MongoDB cluster mainly include replica sets and sharding. Replica sets are used to achieve high availability and read-write separation of data, while sharding is used for horizontal expansion, processing large-scale data sets and high-concurrency read-write architecture modes. You can choose the appropriate cluster architecture mode according to your business needs.

[0082] The cache and distributed storage module can be composed of a Redis Sentinel cluster, which is composed of Redis caches, and can cache commonly used data and reduce access delays to achieve the purpose of optimizing data read and write performance and ensuring efficient operation of the system. Of course, the cache and distributed storage module is not limited to being composed of a Redis Sentinel cluster, and it can also be other storage structures, which is not specifically limited here.

[0083] When the cache and distributed storage modules are composed of Redis Sentinel clusters, the key processes are as follows: Figure 4 As shown, it can be: the user initiates a request message, and based on the request message, the Redis cache is first queried to determine whether the data requested in the request message is stored in the Redis cache; if the requested data does not exist in the Redis cache, it indicates that this is the first request for the data. At this time, the requested data can be loaded from the back-end database or other data sources, and the loaded data is stored in the Redis cache; further, if the back-end database or other data sources do not include the requested data, caching is still required at this time, and an empty object can be stored in the Redis cache to avoid repeated queries to the back-end database or other data sources when the data is requested again later; if the requested data exists in the Redis cache, it indicates that this is not the first request for the data. At this time, the data can be returned directly from the Redis cache without querying the back-end database or other data sources, so as to improve the response speed and throughput and reduce the query pressure on the back-end database or other data sources.

[0084] The collaborative perception cloud platform device disclosed in this embodiment includes: a data transceiver module, a load balancing module, a Netty server cluster module, a message queue module and a storage module, wherein the storage module includes a database storage module and a cache and distributed storage module, the database storage module is used to store control data in structured and unstructured data; the cache and distributed storage module is used to cache the first data of the first access request, and when the cached second data is requested for access again, in response to the access request again, the cached second data is retrieved from the cache and distributed storage module. The storage module in this solution includes a database storage module composed of a MongoDB cluster, which realizes high availability, load balancing and horizontal expansion of data. The storage module also includes a cache and distributed storage module composed of a Redis sentinel cluster, which can cache commonly used data and reduce access delays to optimize data read and write performance. Through the distributed storage and cache optimization of the MongoDB cluster and the Redis sentinel cluster, fast response and high-performance operation in high-concurrency scenarios are ensured.

[0085] This application discloses a collaborative sensing cloud platform device, and its structural diagram is as follows: Figure 1 As shown, including:

[0086] Data transceiver module 11, load balancing module 12, Netty server cluster module 13, message queue module 14 and storage module 15.

[0087] In addition to the same structure as the previous embodiment, the load balancing module in this embodiment may include: a Linux virtual server unit, a load balancing unit and a Keepalived unit.

[0088] The Linux virtual server unit is used to perform a first load balancing on the multiple sensed data according to the load balancing strategy, and distribute the multiple sensed data after the first load balancing to the load balancing unit;

[0089] The load balancing unit is used to perform a second load balancing on the perception data obtained from the Linux virtual server unit and processed by the first load balancing, and distribute the plurality of perception data processed by the second load balancing to different Netty servers in the Netty server cluster module;

[0090] The Keepalived unit is used to monitor the status of the Linux virtual server unit.

[0091] The main process inside the load balancing module is as follows: the Linux virtual server unit (LVS) performs primary load balancing and distributes data to different load balancing units (HaProxy). The Keepalived unit is mainly responsible for monitoring the Linux virtual server unit (LVS). On the one hand, it configures and manages the Linux virtual server unit (LVS) and performs health checks on the nodes in the Linux virtual server unit (LVS). On the other hand, it achieves high availability of the network. The load balancing unit (HaProxy) performs load balancing before the data enters the Netty server cluster module and distributes the data to different Netty servers.

[0092] Among them, the Linux Virtual Server Unit (LVS) is a high-performance load balancing solution that can distribute requests or data to multiple backend servers according to different load balancing strategies. The load balancing module may include one Linux Virtual Server Unit (LVS) or multiple Linux Virtual Server Units (LVS), depending on the specific deployment requirements and architecture design. The Linux Virtual Server Unit (LVS) can be composed of an IP Virtual Server (IPVS), which is used to implement network traffic distribution and load balancing on the Linux operating system. It works at the IP layer and can forward data. It supports multiple load balancing algorithms, such as round-robin, weighted round-robin, least connections, etc., and can be flexibly customized based on the configuration file.

[0093] The load balancing unit (HaProxy) is an open source software load balancer that mainly performs load balancing at the application layer. After obtaining the data initially allocated by the Linux Virtual Server unit (LVS), it further distributes the data to different Netty servers. The load balancing unit (HaProxy) can be one or more, and the number of load balancing units (HaProxy) depends on the application scenario and requirements.

[0094] Among them, the Linux virtual server unit (LVS) and / or load balancing unit (HaProxy) in the load balancing module in the collaborative perception cloud platform device disclosed in this embodiment can be replaced by other load balancing technologies, such as: Nginx unit, which is a highly available HTTP and reverse proxy server with built-in multiple load balancing algorithms, and can distribute requests or data to the back-end server cluster according to different strategies. Of course, it can also be replaced by other load balancing technologies, which are not specifically limited here.

[0095] Keepalived units are used to achieve high availability of network services. They monitor and manage multiple servers through the virtual router redundancy protocol to ensure that when problems occur on the primary server, the backup server can quickly take over the service, thereby ensuring service continuity and stability. That is, the status of the Linux virtual server unit is monitored through the virtual router redundancy protocol VRRP to achieve high availability of the Keepalived unit. In addition, HeartBeat can also be used to monitor the status of the Linux virtual server unit to achieve high availability. However, compared to HeartBeat, the deployment and use of the Keepalived unit is simpler and only requires a configuration file.

[0096] Furthermore, the Keepalived unit may include a user space layer and a kernel space layer. The user space layer is used to monitor the status of the Linux virtual server unit and can output instructions to the kernel space layer; the kernel space layer is used to obtain instructions from the user space layer and perform communication or data processing based on the instructions from the user space layer.

[0097] Among them, the user space layer is the interface for interacting with the administrator in the Keepalived unit. It provides configuration files and command line tools for defining and managing virtual IP addresses, monitoring and inspection scripts, and health check policies. The user space layer can also parse and apply commands in the configuration files, monitor the status of each service, and perform corresponding operations according to preset policies. For example, when a failure is detected on the primary server, the user space layer triggers the switching mechanism to migrate the virtual IP address from the primary server to the backup server, thereby ensuring service continuity and high availability.

[0098] The kernel space layer is the part where the Keepalived unit interacts with the operating system kernel. It is mainly responsible for actual network communication and data packet processing. The kernel space layer can communicate with the user space layer through the Netlink socket, receive instructions and requests from the user space layer, and feed back the execution results to the user space layer; the kernel space layer can also manage network interfaces, configure routing tables, process ARP requests and other underlying network operations.

[0099] Furthermore, the user space layer may include at least: a scheduler I / O multiplexer (Scheduler I / O Multiplexer) and a memory management structure (Memory Management).

[0100] The Scheduler I / O Multiplexer is used to allocate system resources (such as CPU time, memory, etc.) to ensure that multiple tasks or processes can be effectively executed concurrently; and monitor the status of Linux virtual server units to enable Linux virtual server units to be executed in parallel, thereby improving system throughput and efficiency;

[0101] The memory management structure is used to manage system resources so that the system resources allocated by the scheduler I / O multiplexer can be allocated and reclaimed. It is mainly used to manage memory resources, including allocating and reclaiming memory, protecting memory from illegal access, and optimizing memory usage.

[0102] In addition, the user space layer may also include: Control Plane, which refers to the plane responsible for managing and controlling data forwarding in a computer network. Corresponding to the data plane, the data plane is responsible for actual data forwarding and processing. The control plane collects and analyzes network status information, formulates and issues routing strategies to ensure efficient operation and reliability of the network;

[0103] The user space layer can also include: Core components, which are the basic and key parts of a system or application and are the basis for stable operation of the system and provision of high-quality services.

[0104] Furthermore, the Scheduler I / O Multiplexer in the user space layer may include: monitoring and recovery tools, such as: WatchDog, and may also include: Checkers, Virtual Routing Redundancy Protocol Stack VRRP stack, IP Virtual Server Wrapper IPVS wrapper, Netlink Reflector NetlinkReflector.

[0105] The kernel space layer may include: IP virtual server IPVS and Netlink communication mechanism.

[0106] Specifically, the structural diagram of the collaborative perception cloud platform device disclosed in this embodiment can be as follows: Figure 5As shown, it includes: a data collector, the data collector is connected to a load balancing module, the load balancing module is composed of LVS, Haproxy and KeepAlived, the load balancing module is connected to a Netty server cluster module composed of multiple Netty servers, the Netty server cluster module is connected to a message queue module composed of a Kafka cluster, the Kafka cluster includes multiple message queues MQ, the message queue module is connected to a data processing module composed of a multi-threaded processing unit and an analysis data processing unit, the multi-threaded processing unit can be connected to the analysis data processing unit, and can also be connected to a database storage module composed of a MongoDB cluster, the database storage module composed of the MongoDB cluster can also be connected to the analysis data processing unit, the analysis data processing unit and the database storage module composed of the MongoDB cluster can both be connected to a cache and distributed storage module composed of a Redis sentinel cluster, the analysis data processing unit, the database storage module composed of the MongoDB cluster, and the cache and distributed storage module composed of the Redis sentinel cluster can all be connected to an API interface module, and the API interface module is connected to a data output unit. The collaborative perception cloud platform device disclosed in this embodiment processes the sensing data collected by the vehicle and roadside sensors, and outputs the control data to the vehicle or roadside infrastructure after obtaining it, so as to realize intelligent collaborative perception.

[0107] The collaborative perception cloud platform device disclosed in this embodiment realizes high availability of network services and ensures the continuity and stability of services through the KeepAlived unit in the load balancing module composed of the user space layer and the kernel space layer. This solution forms a collaborative perception cloud platform device through a data transceiver module, a load balancing module, a Netty server cluster module, a message queue module and a storage module, realizes low-latency, high-bandwidth data transmission between vehicles and roadside infrastructure or other vehicles through 5G-V2X technology, realizes efficient data processing through the Netty server cluster module and the message queue module composed of the Kafka cluster, and ensures fast response and high-performance operation in high-concurrency scenarios through the database storage module composed of the MongoDB cluster and the cache and distributed storage module composed of the Redis sentinel cluster, and realizes intelligent collaborative perception of multi-source data, improving the vehicle's global perception and autonomous decision-making capabilities.

[0108] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0109] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0110] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0111] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. A collaborative sensing cloud platform device, characterized in that: include: A data transceiver module, used to obtain a plurality of sensing data transmitted by a vehicle and / or a roadside sensor, and capable of outputting control data obtained after processing the plurality of sensing data; A load balancing module is used to obtain the multiple perception data obtained by the data transceiver module, perform load balancing processing, and distribute the multiple perception data to different Netty servers in the Netty server cluster module respectively; A Netty server cluster module, comprising at least two Netty servers, for processing the allocated perception data in parallel through the at least two Netty servers; A message queue module, used to obtain the perception data processed by the Netty server cluster module, and publish and subscribe to message queues based on the processed perception data; The storage module is used to store the control data generated based on the subscription message queue, so that the data transceiver module can call the control data stored in the storage module and output it.

2. The device according to claim 1, characterized in that The storage module comprises: A database storage module, used for storing the control data in structured and unstructured data; The cache and distributed storage module is used to cache the first data of the first access request, and when the cached second data is requested for access again, in response to the re-access request, retrieve the cached second data from the cache and distributed storage module.

3. The device according to claim 2, characterized in that The database storage module consists of a MongoDB cluster.

4. The device according to claim 2, characterized in that The cache and distributed storage module consists of a Redis sentinel cluster.

5. The device according to claim 1, characterized in that The load balancing module includes: A Linux virtual server unit, configured to perform a first load balancing on the plurality of sensing data according to a load balancing strategy, and distribute the plurality of sensing data subjected to the first load balancing to a load balancing unit; A load balancing unit, configured to perform a second load balancing on the acquired perception data allocated by the Linux virtual server unit and processed by the first load balancing, and distribute the plurality of perception data processed by the second load balancing to different Netty servers in the Netty server cluster module; The Keepalived unit is used to monitor the status of the Linux virtual server unit.

6. The device according to claim 5, characterized in that The Keepalived unit included in the load balancing module communicates via a virtual routing redundancy protocol.

7. The device according to claim 5, characterized in that The Keepalived unit includes: The user space layer is used to monitor the status of the Linux virtual server unit and can output instructions to the kernel space layer; The kernel space layer is used to obtain instructions from the user space layer and perform communication or data processing based on the instructions from the user space layer.

8. The device according to claim 7, characterized in that The user space layer at least includes: a scheduler I / O multiplexer for allocating system resources and monitoring the status of the Linux virtual server units so that the Linux virtual server units can be executed in parallel; A memory management structure is used to manage the system resources so that the system resources allocated by the scheduler I / O multiplexer can be allocated and reclaimed.

9. The device according to claim 1, characterized in that Also includes: The data processing module is used to process the obtained subscription message queue to generate the control data, and send the control data to the storage module.

10. The device according to claim 1, characterized in that Also includes: The API interface module is used to provide interfaces between different modules to achieve data exchange and remote calls.

Images