Network adaptive transmission method and system in process of returning data to cloud

Abstract

The invention provides a network adaptive transmission method and system in a process of returning data to a cloud end, and belongs to the technical field of intelligent automobiles, and the method comprises the steps: obtaining the network data of a target network collected through a network monitoring sensor and a communication interface, and calculating the network state of the target network according to the collected network data of the target network; according to the acquired network data of the target network and the calculated network state of the target network, performing data feature analysis and network condition evaluation; and dynamically adjusting data transmission parameters and strategies of the target network according to data feature analysis and network condition evaluation results. According to the invention, the integrity and accuracy of the intelligent driving return data can be improved, and the transmission efficiency of the return data is optimized.

Description

Technical Field

[0001] This invention relates to the field of intelligent vehicle technology, and in particular to a network adaptive transmission method and system for data back to the cloud. Background Technology

[0002] During the research and development and mass production phases of autonomous driving, vehicles generate massive amounts of data, including but not limited to sensor data (such as image data captured by cameras and point cloud data acquired by LiDAR), vehicle driving status data (speed, acceleration, steering angle, etc.), and intermediate data from algorithm operation. This data is crucial for optimizing autonomous driving algorithms and improving vehicle safety and reliability, and needs to be transmitted back to the cloud in a timely and accurate manner for storage, analysis, and model training.

[0003] However, current data backhaul faces many challenges.

[0004] On the one hand, network conditions vary greatly under different driving environments. In densely populated urban areas, network signals are easily blocked and interfered with by tall buildings, resulting in unstable signal strength and significant bandwidth fluctuations. In addition, due to the large number of network users, network congestion often occurs, causing data transmission delays or even packet loss. In remote areas or high-speed driving scenarios, network coverage may be insufficient and signal quality may be poor, making it difficult to meet the needs of rapid transmission of large amounts of data.

[0005] On the other hand, traditional data transmission methods struggle to dynamically adjust transmission strategies based on real-time network changes. When network conditions are poor, transmitting large amounts of autonomous driving data at predetermined rates and packet sizes not only leads to low transmission efficiency but also poses a risk of data loss, potentially compromising data integrity and availability and impacting the accuracy of subsequent algorithm analysis and model training. Conversely, when network conditions are good, network bandwidth cannot be fully utilized, resulting in resource waste.

[0006] Therefore, how to efficiently and stably transmit autonomous driving data back to the cloud has become a key technical problem that urgently needs to be solved. Summary of the Invention

[0007] This invention aims to solve at least one of the above-mentioned technical problems in the prior art, and proposes a network adaptive transmission technology solution for cloud-based data backhaul scenarios in autonomous driving R&D / mass production. This solution can meet the data needs of autonomous driving after-sales problem analysis and vehicle performance improvement, while maximizing the use of network resources and reducing transmission costs.

[0008] In a first aspect, embodiments of the present invention provide a network adaptive transmission method during data backhaul to the cloud, comprising:

[0009] Acquire target network data collected through network monitoring sensors and communication interfaces, and calculate the target network status based on the collected target network data;

[0010] Based on the collected target network data and the calculated target network status, data feature analysis and network status assessment are performed.

[0011] The target network data transmission parameters and strategies are dynamically adjusted based on data feature analysis and network condition assessment results.

[0012] In a preferred embodiment, the steps of acquiring target network data collected through network monitoring sensors and communication interfaces, and calculating the target network status based on the acquired target network data, include:

[0013] Periodically send test data packets of a preset size and number to the cloud through the target network, record the round-trip time of the test data packets and the number of test data packets successfully received by the cloud, in order to calculate the target network bandwidth;

[0014] Record the time difference between the test data packet sent through the target network and the corresponding response packet received, in order to calculate the target network latency data;

[0015] The difference between the total number of test data packets sent through the target network and the number of test data packets that did not receive confirmation from the cloud is used to calculate the packet loss rate of the target network.

[0016] In a preferred embodiment, the step of performing data feature analysis and network status assessment based on the collected target network data and the calculated target network status includes:

[0017] Predict the target network bandwidth change trend based on historical network bandwidth data;

[0018] The network quality level of the target network is determined based on network latency data and packet loss rate.

[0019] In a preferred embodiment, the step of dynamically adjusting the target network data transmission parameters and strategies based on data feature analysis and network condition assessment results includes:

[0020] Adjust packet size and transmission rate according to network quality level;

[0021] When the target data is of an emergency security-related type, the target network should be used to prioritize the transmission of the target data.

[0022] In a preferred embodiment, the step of acquiring target network data collected through network monitoring sensors and communication interfaces, and calculating the target network status based on the acquired target network data, further includes:

[0023] When the target network is a wireless network, the signal strength information of the target network is obtained in real time through the interface of the vehicle wireless communication module;

[0024] The step of dynamically adjusting the target network data transmission parameters and strategies based on data feature analysis and network condition assessment results also includes:

[0025] When the target network is a wireless network, if the network condition is good based on the target network signal strength information, 5G network is used first for data transmission. When the 5G signal is weak, it is switched to 4G or WiFi network; or multiple types of wireless networks are used as the target network, and the data is transmitted in a split manner through the multiple types of wireless networks using the MPTCP protocol.

[0026] In a preferred embodiment, it further includes:

[0027] The target network data transmission parameters and strategies are dynamically adjusted based on the data integrity and data reception rate information fed back from the cloud; the network status of the target network is fed back to the cloud.

[0028] In a preferred embodiment, it further includes:

[0029] When the target network is a weak network environment or a high-bandwidth environment, and the target object is a large object, the data chunking upload mechanism is used to upload the target object; or when the total size of the target object is unknown, the data chunking upload mechanism is used to upload the target object.

[0030] In a second aspect, embodiments of the present invention provide a network adaptive transmission system for data back to the cloud, the system being capable of implementing any of the methods described in the first aspect, the system comprising:

[0031] The real-time network status monitoring module is used to acquire target network data collected through network monitoring sensors and communication interfaces, and to calculate the target network status based on the acquired target network data.

[0032] The data feature analysis and network status assessment module is used to perform data feature analysis and network status assessment based on the collected target network data and the calculated target network status.

[0033] The transmission parameter dynamic adjustment and strategy optimization module is used to dynamically adjust the target network data transmission parameters and strategies based on data feature analysis and network condition assessment results.

[0034] Thirdly, embodiments of the present invention provide an electronic device comprising: one or more processors; a memory for storing one or more programs; and, when the one or more programs are executed by the one or more processors, causing the one or more processors to implement the method as described in any embodiment of the first aspect.

[0035] Fourthly, embodiments of the present invention provide a computer-readable medium storing a computer program that, when executed by a processor, implements the steps of the method as described in any embodiment of the first aspect.

[0036] Beneficial effects of this invention:

[0037] This invention can improve the integrity and accuracy of intelligent driving data transmission: by monitoring network status in real time and dynamically adjusting transmission strategies, it ensures the integrity and accuracy of data in various network environments, providing reliable data support for autonomous driving algorithm optimization and vehicle performance improvement.

[0038] This invention can optimize the efficiency of backhaul data transmission: it dynamically adjusts transmission parameters, such as data packet size and transmission rate, according to network conditions, to ensure the priority of data transmission when network resources are limited, thereby improving overall transmission efficiency.

[0039] This invention enables the rational use of resources: by fully considering data priority and network status, it intelligently adjusts transmission strategies to avoid resource waste and reduce transmission costs. In extreme scenarios, it can prioritize the transmission of the most critical after-sales (accident) analysis data.

[0040] This invention enhances stability by optimizing the transmission system in real time and adjusting the transmission strategy to improve system stability and effectively cope with changes in the network environment. Attached Figure Description

[0041] Figure 1 A flowchart illustrating a network adaptive transmission method for data back to the cloud, provided in an embodiment of the present invention;

[0042] Figure 2 This is a flowchart illustrating an optional specific implementation method of step S1 in an embodiment of the present invention;

[0043] Figure 3 This is a flowchart illustrating an optional specific implementation method of step S2 in an embodiment of the present invention;

[0044] Figure 4 This is a flowchart illustrating an optional specific implementation method of step S3 in an embodiment of the present invention;

[0045] Figure 5 This is a schematic diagram of an embodiment of the present invention;

[0046] Figure 6 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0047] To enable those skilled in the art to better understand the technical solutions of the present invention, exemplary embodiments of the present invention are described below in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0048] Where there is no conflict, the various embodiments of the present invention and the features thereof may be combined with each other.

[0049] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0050] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Terms such as “connected” or “linked” are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0051] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having the meaning consistent with their meaning in the context of the relevant art and the invention, and will not be interpreted as having an idealized or overly formal meaning unless expressly so defined herein.

[0052] In the technical solution of this invention, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information all comply with relevant laws and regulations and do not violate public order and good morals. The use of user data in this technical solution follows relevant national laws and regulations (e.g., the "Information Security Technology - Personal Information Security Specification"). For example: appropriate measures are taken for personal information access control; restrictions are imposed on the display of personal information; the purpose of using personal information does not exceed the scope of direct or reasonable association; and explicit identity targeting is eliminated when using personal information to avoid precisely locating a specific individual.

[0053] In this invention, some technical terms have the following meanings:

[0054] An EDR (Event Data Recorder) is a system used to record data related to vehicle collision events.

[0055] DSSAD (Data Storage System for Automated Driving) is a data recording system designed specifically for autonomous vehicles.

[0056] In related technologies, Chinese patent document CN115022834A discloses a method and system for screening and switching network on a remote driving vehicle. In this technical solution, the vehicle-mounted connected terminal periodically detects the network status. When the network status does not meet the requirements for remote driving, a network pre-screening process is performed. Thresholds are set based on attributes such as network switching latency, signal strength, available bandwidth, and network cost, and networks that do not meet the thresholds are eliminated. Then, a better network is selected from the remaining networks and switched to using a network switching algorithm (such as the TOPSIS ranking algorithm). Although this technical solution considers network status and performs screening and switching, it lacks a degradation transmission strategy in terms of data transmission. When the quality of the switched network is still poor, stable transmission of remote driving data cannot be guaranteed, and problems such as data transmission delay and loss may occur, affecting the safety and smoothness of remote driving.

[0057] In related technologies, Chinese patent document CN114025401A discloses a remote driving processing method, device, and vehicle. In this technical solution, when a vehicle is controlled by a remote control terminal via a first network (such as a 5G network), if the first network signal is detected to be disconnected, the network is switched to a second network (such as a 4G network). After switching, downgraded data transmission is performed, such as reducing the number of video data channels transmitted and / or compressing the video data during transmission, to ensure that the remote control terminal can continue to remotely control the vehicle. This technical solution mainly addresses emergency handling after a network signal disconnection and is not comprehensive enough for real-time monitoring of the network status. Switching and downgraded transmission are only performed when the network is disconnected. In cases where the network signal is not completely disconnected but the quality is poor (such as weak signal strength or insufficient bandwidth), network screening and optimization cannot be performed in advance, failing to fully utilize network resources and potentially leading to a decline in the driving experience.

[0058] In summary, the data backhaul technology involved in the relevant technologies still has many problems in terms of transmission stability, how to ensure the integrity and accuracy of the backhauled data, how to meet the needs of rapid transmission of large amounts of data, how to optimize the efficiency of backhaul data transmission, and how to make full use of network resources.

[0059] This invention proposes a network adaptive transmission technology specifically for transmitting autonomous driving R&D / mass production data back to the cloud. By monitoring the network status of the vehicle's environment in real time and dynamically adjusting data transmission parameters and strategies based on the monitoring results, it ensures that data can be transmitted back to the cloud quickly, accurately, and completely in complex and ever-changing network environments.

[0060] In this embodiment of the invention, for ease of description, the following description uses the vehicle as the executing entity. The vehicle can be a software module or other electronic devices capable of performing the following functions.

[0061] Figure 1 This is a flowchart illustrating a network adaptive transmission method during data backhaul to the cloud, as provided in an embodiment of the present invention; Figure 1 As shown, the method includes:

[0062] Step S1: Acquire target network data collected through network monitoring sensors and communication interfaces, and calculate the target network status based on the collected target network data;

[0063] Step S2: Based on the collected target network data and the calculated target network status, perform data feature analysis and network status assessment.

[0064] Step S3: Dynamically adjust the target network data transmission parameters and strategies based on the data feature analysis and network condition assessment results to ensure that data can be quickly, accurately, and completely transmitted back to the cloud through the target network in a complex and ever-changing network environment.

[0065] In some embodiments, such as Figure 2 As shown, step S1, which involves acquiring target network data collected through network monitoring sensors and communication interfaces, and calculating the target network status based on the acquired target network data, includes the following steps:

[0066] Step S101: Periodically send test data packets of a preset size and number to the cloud through the target network, record the round-trip time of the test data packets and the number of test data packets successfully received by the cloud, in order to calculate the target network bandwidth;

[0067] Step S102: Record the time difference between the test data packet sent through the target network and the corresponding response packet received, so as to calculate the target network latency data. Multiple measurements can be taken and the average value can be taken to improve accuracy.

[0068] Step S103: Calculate the difference between the total number of test data packets sent through the target network and the number of test data packets that did not receive confirmation from the cloud, in order to calculate the target network packet loss rate and evaluate the reliability of the target network transmission.

[0069] In some embodiments, such as Figure 3 As shown, step S2, which involves data feature analysis and network status assessment based on the collected target network data and calculated target network status, includes:

[0070] Step S201: Predict the target network bandwidth change trend based on historical network bandwidth data;

[0071] Step S202: Classify the network quality level of the target network based on network latency data and packet loss rate.

[0072] In some embodiments, such as Figure 4 As shown, step S3, which involves dynamically adjusting the target network data transmission parameters and strategies based on data feature analysis and network condition assessment results, includes:

[0073] Step S301: Adjust the data packet size and transmission rate according to the network quality level;

[0074] Step S302: When the data type of the target data is emergency safety related data, the target network is used to prioritize the transmission of the target data, such as EDR or DSSAD data when AEB is triggered. Regardless of the network conditions, its transmission is always prioritized, and more network resources are allocated to it to ensure that this type of data can be transmitted back to the cloud at the fastest speed and with the highest accuracy, so as to provide timely data support for the safe operation of the vehicle.

[0075] When the target data is general sensor data and non-critical algorithm intermediate data, the target network data transmission parameters and strategies can be dynamically adjusted according to the target network status, and the above step S301 method can be adopted. Under the premise of not affecting the transmission of critical data, the back transmission of this type of data should be completed as much as possible to accumulate data for subsequent algorithm optimization and vehicle performance analysis.

[0076] In some embodiments, the network quality level includes: excellent, average, and poor; adjusting the data packet size and transmission rate according to the network quality level specifically includes:

[0077] When the target network has a high network quality level, increase the data packet size and increase the transmission rate to make full use of network bandwidth and improve data return efficiency. For example, merge smaller data packets into larger data packets for transmission, while increasing the data transmission rate and speeding up the data upload to the cloud.

[0078] When the network quality level of the target network is average, adjust the data packet size to a moderate level and reduce the transmission rate to reduce the risk of network congestion and balance transmission efficiency and reliability. For example, adjusting the data packet size to a moderate value can avoid increased packet loss due to excessively large data packets, and avoid increased transmission overhead due to excessively small data packets.

[0079] When the target network has a poor network quality level, the transmission rate is significantly reduced, the data packet size is decreased, and a highly reliable transmission protocol or enhanced retransmission mechanism is enabled to prioritize the reliability of data transmission, reduce the amount of data sent per unit time, reduce network load, and reduce the impact of a single lost data packet on the overall data. The enabled highly reliable transmission protocol or enhanced retransmission mechanism, such as adopting a transmission protocol with stronger error correction capabilities and increasing the dynamic adjustment strategy of retransmission number and retransmission interval, ensures that the data can be successfully transmitted to the cloud.

[0080] In some embodiments, classifying the network quality level of the target network based on network latency data and packet loss rate specifically includes:

[0081] The network quality score is calculated using parameters such as measured bandwidth (Mbit / s), round-trip time, packet loss rate, and reference signal strength. Different transmission strategies are then formulated based on the score, such as adjusting the data packet size and transmission rate.

[0082] After normalizing the score, the network quality level can be divided according to the score size. There can be 4 network quality levels (ABCD) or more. For example, a score greater than 0.75 is level A, a score greater than 0.45 and less than or equal to 0.75 is level B, a score greater than 0.15 and less than or equal to 0.45 is level C, and a score less than or equal to 0.15 is level D.

[0083] In some embodiments, step S1, which involves acquiring target network data collected through network monitoring sensors and communication interfaces, and calculating the target network status based on the acquired target network data, further includes:

[0084] Step S104: When the target network is a wireless network, the signal strength information of the target network is obtained in real time through the interface of the vehicle wireless communication module. The real-time changes in signal strength are accurately sensed in a 4G, 5G or WiFi network environment through the vehicle wireless communication module, such as a 4G, 5G or WiFi communication module.

[0085] Step S3, which involves dynamically adjusting the target network data transmission parameters and strategies based on data feature analysis and network condition assessment results, further includes:

[0086] Step S303: When the target network is a wireless network, if the network condition is good according to the target network signal strength information, 5G network is used first for data transmission. When the 5G signal is weak, switch to 4G or WiFi network; or multiple types of wireless networks are used as the target network, and the data is transmitted in a split manner through multiple types of wireless networks using the MPTCP protocol.

[0087] The MPTCP (Multi-Path TCP) protocol can utilize multiple network paths simultaneously for data transmission. It divides data into multiple sub-streams, sends them to the receiving end through different network paths, and then reassembles them at the receiving end. During multi-path transmission, the data transmission rate and traffic allocation of each sub-stream are dynamically adjusted based on the real-time status of each path (such as bandwidth, latency, packet loss rate, etc.) to fully utilize network resources and improve transmission efficiency. Data traffic is dynamically allocated based on the real-time status of each network.

[0088] In some embodiments, such as Figure 5 As shown, the method also includes:

[0089] Step S4: Dynamically adjust the target network data transmission parameters and strategies based on the data integrity and data reception rate information fed back from the cloud; and feed back the target network status to the cloud.

[0090] During data transmission, the cloud server provides real-time feedback on the received data status (such as data integrity and data reception rate) to the vehicle. Based on this feedback, the vehicle further optimizes its transmission parameters and strategies, forming a closed-loop adaptive transmission system. For example, if the cloud reports incomplete data reception or significant packet loss within a certain period, the vehicle can immediately reduce the transmission rate again, further decrease the data packet size, and strengthen the retransmission mechanism to ensure that lost data is successfully retransmitted to the cloud. Conversely, if the cloud reports a low data reception rate, the vehicle can appropriately increase the transmission rate and data transmission volume, provided the network conditions permit.

[0091] The vehicle-side feeds back information such as changes in its network status and data generation to the cloud. Based on this feedback, the cloud adjusts its data storage, analysis, and model training plans accordingly. For example, if the vehicle-side reports that the network status will deteriorate rapidly in a short period, the cloud can adjust its data reception strategy in advance, such as suspending the reception of some non-urgent data and prioritizing the storage of critical data; or, based on the large amount of new data generated by the vehicle-side, the cloud can plan storage and computing resources in advance according to the algorithm to prepare for the upcoming data processing.

[0092] In some embodiments, such as Figure 5 As shown, the method also includes:

[0093] Step S5: If the target network is a weak network environment or a high bandwidth environment, and the target object is a large object, the data chunking upload mechanism is used to upload the target object; or if the total size of the target object is unknown, the data chunking upload mechanism is used to upload the target object.

[0094] In weak network environments, using smaller chunks can reduce the impact of network failures and enable object resuming. In high-bandwidth environments, concurrent object chunking can fully utilize network bandwidth, and out-of-order uploads do not affect the final assembled objects. Chunked uploads allow for pausing and resuming the upload of a single large object at any time. Unless a termination operation is initiated, all incomplete objects can be uploaded at any time. Chunked uploads are also suitable for uploading objects when the total size is unknown; the upload can be initiated first, and the objects can then be assembled to obtain the complete size.

[0095] One specific embodiment of the present invention is as follows:

[0096] Vehicle-side hardware deployment and software integration: High-performance onboard computing units are equipped in autonomous vehicles to run software modules related to network adaptive transmission. Various sensors and communication interfaces required for real-time network status monitoring are integrated with the onboard computing unit to ensure accurate and real-time network data acquisition. Dedicated data acquisition drivers and communication protocol stacks are developed within the onboard operating system to achieve efficient acquisition and processing of network data. Hardware interfaces of onboard wireless communication modules (such as 4G / 5G modules and WiFi modules) are used to acquire real-time information such as network signal strength; precise monitoring of network bandwidth, latency, and packet loss rate is achieved through the onboard Ethernet interface combined with software algorithms. At the software level, network adaptive transmission software systems are developed using programming languages ​​such as C++ and Python to enable collaborative work between various functional modules.

[0097] Cloud Server Configuration and Software Setup: A high-performance server cluster is deployed in the cloud to receive, store, and process data from autonomous vehicles. The server cluster is equipped with high-speed network interfaces to ensure rapid reception of large volumes of data uploaded by vehicles. A dedicated cloud-based data receiving and management software system is built, capable of real-time analysis of data sent from vehicles, recording data reception status, and promptly sending feedback information back to the vehicles. Leveraging the elastic computing resources and distributed storage technology of the cloud computing platform, server resource allocation is dynamically adjusted based on data generation from vehicles and network conditions, optimizing data storage and processing workflows. For example, when a large number of vehicles are expected to upload data simultaneously under good network conditions, more computing resources are allocated in advance for real-time data analysis and preliminary processing. For storage, a distributed file system is employed to ensure the reliability and scalability of data storage.

[0098] System Testing and Optimization: Extensive testing was conducted on autonomous vehicles equipped with the network adaptive transmission system under various real-world driving scenarios (such as congested urban roads, highways, and rural roads). Network status data, data transmission status, and cloud data reception and processing results were collected during the testing process. In-depth analysis of the test data was used to evaluate the system's performance in various scenarios, including data transmission success rate, average transmission rate, and data integrity. Based on the test evaluation results, the software algorithms, transmission parameter settings, and overall system architecture on both the vehicle and cloud sides were optimized and adjusted. For example, to address the issue of unstable transmission due to large network fluctuations in certain scenarios, the network status prediction algorithm and transmission strategy adjustment mechanism were optimized; for situations where cloud data processing efficiency was low, the data storage structure and processing flow were optimized to ensure that the entire network adaptive transmission system could operate stably and efficiently in complex and changing real-world environments, meeting the needs of autonomous driving R&D and mass production data back to the cloud.

[0099] The advantages of this invention are:

[0100] Customized Multi-Dimensional Network Monitoring and Precise Evaluation for Autonomous Driving Scenarios: This invention targets data feedback scenarios in autonomous driving R&D and mass production. It not only comprehensively collects conventional network parameters such as bandwidth, latency, packet loss rate, and signal strength, but also deeply integrates vehicle driving scenarios (urban, highway, remote areas, etc.) and data types (emergency safety data, general sensor data, etc.) for multi-dimensional network status monitoring. Through data analysis algorithms and machine learning models specifically designed for autonomous driving scenarios, it performs precise analysis and dynamic evaluation of the collected complex data. This allows for a deeper and more accurate understanding of the impact of network status on different types of autonomous driving data transmission. Compared to traditional general network monitoring methods, it has stronger targeting and adaptability, providing a more scientific and precise basis for optimizing and adjusting transmission strategies.

[0101] A dual-driven intelligent transmission strategy based on data priority and network status: This invention fully considers the diversity and varying importance of data in autonomous driving R&D and mass production, innovatively combining data priority with real-time network status to achieve intelligent transmission strategy adjustment. When network resources are limited, priority is given to ensuring the transmission of critical data such as emergency safety-related data, ensuring the safe operation of vehicles and the effective optimization of core algorithms. Simultaneously, the transmission parameters and priorities of general data are dynamically adjusted according to network status, maximizing the satisfaction of various data transmission needs under different network environments and improving overall data return efficiency and quality. This dual-driven transmission strategy is not fully considered in existing technologies and can better adapt to the complex data transmission scenarios of autonomous driving.

[0102] A Closed-Loop Optimized Transmission System with Two-Way Feedback Between Vehicles and the Cloud: This invention constructs an efficient and real-time two-way feedback mechanism between the vehicle and the cloud, forming a closed-loop optimized transmission system. The vehicle adjusts transmission parameters and strategies promptly based on data reception feedback from the cloud, while the cloud rationally plans data processing flows based on network status and data generation feedback from the vehicle. Both sides collaborate and dynamically optimize. This two-way feedback mechanism can quickly respond to changes in the network environment and various problems arising during data transmission, effectively improving the stability, accuracy, and timeliness of data feedback. Compared to traditional one-way transmission or simple feedback mechanisms, it has significant technical advantages, providing strong support for the reliable feedback of data from autonomous driving R&D and mass production.

[0103] Based on the same inventive concept, embodiments of the present invention also provide a network adaptive transmission system for data back to the cloud, the system being capable of implementing any of the methods described in the above embodiments, the system comprising:

[0104] The real-time network status monitoring module is used to acquire target network data collected through network monitoring sensors and communication interfaces, and to calculate the target network status based on the acquired target network data.

[0105] The data feature analysis and network status assessment module is used to perform data feature analysis and network status assessment based on the collected target network data and the calculated target network status.

[0106] The transmission parameter dynamic adjustment and strategy optimization module is used to dynamically adjust the target network data transmission parameters and strategies based on data feature analysis and network condition assessment results.

[0107] Based on the same inventive concept, embodiments of the present invention also provide an electronic device. Figure 6 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Figure 6 As shown, an embodiment of the present invention provides an electronic device including: one or more processors 101, a memory 102, and one or more I / O interfaces 103. The memory 102 stores one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement any of the methods described in the above embodiments; the one or more I / O interfaces 103 are connected between the processor and the memory, configured to enable information interaction between the processor and the memory.

[0108] The processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH); the I / O interface (read / write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus).

[0109] In some embodiments, the processor 101, memory 102, and I / O interface 103 are interconnected via bus 104, and thus connected to other components of the computing device.

[0110] In some embodiments, the one or more processors 101 include a field-programmable gate array.

[0111] This invention also provides a computer-readable medium. The computer-readable medium stores a computer program, which, when executed by a processor, implements the steps of any of the methods described in the above embodiments. The computer-readable storage medium may be a volatile or non-volatile computer-readable storage medium.

[0112] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).

[0113] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable program instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0114] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0115] The computer program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of the invention.

[0116] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0117] Various aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0118] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0119] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0120] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0121] Example embodiments have been disclosed herein, and while specific terminology has been used, it is for illustrative purposes only and should be construed as such, and is not intended to be limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in conjunction with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in conjunction with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of the invention as set forth in the appended claims.

Claims

1. A network adaptive transmission method during data backhaul to the cloud, characterized in that, include: Acquire target network data collected through network monitoring sensors and communication interfaces, and calculate the target network status based on the collected target network data; Based on the collected target network data and the calculated target network status, data feature analysis and network status assessment are performed. The target network data transmission parameters and strategies are dynamically adjusted based on data feature analysis and network condition assessment results.

2. The method according to claim 1, characterized in that, The steps of acquiring target network data collected through network monitoring sensors and communication interfaces, and calculating the target network status based on the acquired target network data, include: Periodically send test data packets of a preset size and number to the cloud through the target network, record the round-trip time of the test data packets and the number of test data packets successfully received by the cloud, in order to calculate the target network bandwidth; Record the time difference between the test data packet sent through the target network and the corresponding response packet received, in order to calculate the target network latency data; The difference between the total number of test data packets sent through the target network and the number of test data packets that did not receive confirmation from the cloud is used to calculate the packet loss rate of the target network.

3. The method according to claim 2, characterized in that, The steps of performing data feature analysis and network status assessment based on the collected target network data and calculated target network status include: Predict the target network bandwidth change trend based on historical network bandwidth data; The network quality level of the target network is determined based on network latency data and packet loss rate.

4. The method according to claim 3, characterized in that, The steps for dynamically adjusting target network data transmission parameters and strategies based on data feature analysis and network condition assessment results include: Adjust packet size and transmission rate according to network quality level; When the target data is of an emergency security-related type, the target network should be used to prioritize the transmission of the target data.

5. The method according to claim 4, characterized in that, The step of acquiring target network data collected through network monitoring sensors and communication interfaces, and calculating the target network status based on the acquired target network data, further includes: When the target network is a wireless network, the signal strength information of the target network is obtained in real time through the interface of the vehicle wireless communication module; The step of dynamically adjusting the target network data transmission parameters and strategies based on data feature analysis and network condition assessment results also includes: When the target network is a wireless network, if the network condition is good based on the target network signal strength information, 5G network is used first for data transmission. When the 5G signal is weak, it is switched to 4G or WiFi network; or multiple types of wireless networks are used as the target network, and the data is transmitted in a split manner through the multiple types of wireless networks using the MPTCP protocol.

6. The method according to claim 1, characterized in that, Also includes: The target network data transmission parameters and strategies are dynamically adjusted based on the data integrity and data reception rate information fed back from the cloud; the network status of the target network is fed back to the cloud.

7. The method according to claim 1, characterized in that, Also includes: When the target network is a weak network environment or a high bandwidth environment, and the target object is a large object, the data chunking upload mechanism is used to upload the target object; Alternatively, if the total size of the target object is unknown, a data chunking upload mechanism can be used to upload the target object.

8. A network adaptive transmission system for data back to the cloud, characterized in that, The system is capable of implementing the method as described in any one of claims 1 to 7, and the system comprises: The real-time network status monitoring module is used to acquire target network data collected through network monitoring sensors and communication interfaces, and to calculate the target network status based on the acquired target network data. The data feature analysis and network status assessment module is used to perform data feature analysis and network status assessment based on the collected target network data and the calculated target network status. The transmission parameter dynamic adjustment and strategy optimization module is used to dynamically adjust the target network data transmission parameters and strategies based on data feature analysis and network condition assessment results.

9. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 7.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images