CN118972630A - A cloud classroom live broadcast transmission method and system based on the Internet - Google Patents

Abstract

The invention provides a cloud classroom live broadcast transmission method and system based on the Internet, which relate to the technical field of live broadcast, and the method comprises the following steps: acquiring user parameters and live broadcast activity parameters, and distributing a first broadband resource of the live broadcast activity according to the content type, the platform network condition and the number of participants of the live broadcast activity; transmitting first direct broadcast data from a first set of devices to a second set of devices based on a set of transmission policies, wherein the set of transmission policies includes a plurality of different transmission policies, the first set of devices includes one or more first devices, and the second set of devices includes one or more second devices; and each transmission strategy is dynamically adjusted according to the network condition and the data transmission quality of the user, so that the transmission efficiency, stability and user experience of the cloud class live broadcast are improved, and meanwhile, the dynamic adjustment can be carried out according to the real-time network condition and the change of the user demand, so that the high-quality live broadcast service can be provided in various complex environments.

Description

Translated fromChinese

一种基于互联网的云课堂直播传输方法及系统A cloud classroom live broadcast transmission method and system based on the Internet

技术领域Technical Field

本申请涉及网络直播技术领域，尤其涉及一种基于互联网的云课堂直播传输方法及系统。The present application relates to the field of network live broadcast technology, and in particular to a cloud classroom live broadcast transmission method and system based on the Internet.

背景技术Background Art

随着在线教育行业的蓬勃发展，云课堂直播已成为教育服务的重要形式之一。然而，当前的云课堂直播传输方法在面对复杂多变的网络环境、大规模用户参与以及多样化的用户需求时，暴露出了一系列的问题：With the booming development of the online education industry, cloud classroom live broadcast has become one of the important forms of educational services. However, the current cloud classroom live broadcast transmission method has exposed a series of problems in the face of complex and changeable network environments, large-scale user participation, and diverse user needs:

现有的直播传输方法往往不能有效地适应不同用户的网络状况。在带宽不稳定或低带宽环境下，直播视频容易出现卡顿、延迟甚至中断，严重影响用户体验；直播活动的资源分配通常基于静态规则或简单预测，缺乏实时性和动态性。在直播高峰期，资源分配不均可能导致部分用户无法顺畅观看，而部分资源却未被充分利用。Existing live broadcast transmission methods often cannot effectively adapt to the network conditions of different users. In unstable or low-bandwidth environments, live broadcast videos are prone to freezes, delays, or even interruptions, which seriously affects the user experience. Resource allocation for live broadcasts is usually based on static rules or simple predictions, lacking real-time and dynamic features. During peak live broadcast periods, uneven resource allocation may result in some users being unable to watch smoothly, while some resources are not fully utilized.

传统方法采用固定的传输策略，无法根据直播内容类型、用户参与度和网络条件的变化进行灵活调整。例如，在视频内容密集或用户互动频繁的时段，未能相应增加带宽或优化传输协议，导致数据传输效率低下。现有的直播系统往往无法根据用户的实际网络条件、设备性能和观看需求动态调整媒体质量(如视频分辨率、帧率、音频码率等)。这导致在高带宽环境下用户可能无法享受到更高的视频质量，而在低带宽环境下则可能因画质模糊而降低学习效果。在多个通信链路可选的情况下，现有方法往往缺乏智能的链路选择和负载均衡机制。这可能导致数据传输路径不合理，增加了传输延迟和丢包率，同时也未能充分利用网络资源的潜力。传统的缓存策略往往基于固定的缓存大小和策略，无法根据用户的地理位置、网络状况以及实时流量变化进行动态调整。这可能导致缓存数据过时、冗余或不足，影响数据传输的效率和用户体验。Traditional methods use fixed transmission strategies and cannot be flexibly adjusted according to changes in live content type, user engagement, and network conditions. For example, during periods of dense video content or frequent user interaction, the bandwidth is not increased or the transmission protocol is not optimized accordingly, resulting in low data transmission efficiency. Existing live broadcast systems often cannot dynamically adjust media quality (such as video resolution, frame rate, audio bit rate, etc.) according to users' actual network conditions, device performance, and viewing needs. This results in users not being able to enjoy higher video quality in high-bandwidth environments, while in low-bandwidth environments, the learning effect may be reduced due to blurred image quality. In the case of multiple communication links available, existing methods often lack intelligent link selection and load balancing mechanisms. This may lead to unreasonable data transmission paths, increased transmission delays and packet loss rates, and also fail to fully utilize the potential of network resources. Traditional caching strategies are often based on fixed cache sizes and strategies, and cannot be dynamically adjusted according to users' geographic locations, network conditions, and real-time traffic changes. This may cause cached data to be outdated, redundant, or insufficient, affecting data transmission efficiency and user experience.

发明内容Summary of the invention

针对上述问题，本发明提出了一种基于互联网的云课堂直播传输方法及系统；通过引入智能的宽带资源分配算法、灵活的传输策略集、动态的媒体质量调整机制、智能的链路选择和负载均衡技术，以及多级缓存机制，旨在提升云课堂直播的传输效率、稳定性和用户体验，同时能够根据实时网络状况和用户需求的变化进行动态调整，确保在各种复杂环境下都能提供高质量的直播服务。In view of the above problems, the present invention proposes a cloud classroom live broadcast transmission method and system based on the Internet; by introducing an intelligent broadband resource allocation algorithm, a flexible transmission strategy set, a dynamic media quality adjustment mechanism, an intelligent link selection and load balancing technology, and a multi-level cache mechanism, it aims to improve the transmission efficiency, stability and user experience of the cloud classroom live broadcast, and at the same time can be dynamically adjusted according to the real-time network status and changes in user needs, to ensure that high-quality live broadcast services can be provided in various complex environments.

本申请的目的采用以下技术方案实现：The purpose of this application is achieved by the following technical solutions:

第一方面，本申请提供了一种基于互联网的云课堂直播传输方法，所述方法包括：In a first aspect, the present application provides a cloud classroom live broadcast transmission method based on the Internet, the method comprising:

获取用户参数以及直播活动参数，其中，所述用户参数包括用户的网络状况和数据传输质量，所述直播活动参数包括直播活动的内容类型、平台网络状况、参与人数、第一直播数据；Acquire user parameters and live broadcast activity parameters, wherein the user parameters include the user's network status and data transmission quality, and the live broadcast activity parameters include the content type of the live broadcast activity, the platform network status, the number of participants, and the first live broadcast data;

根据所述直播活动的内容类型、平台网络状况以及参与人数，分配所述直播活动的第一宽带资源；Allocate a first broadband resource for the live broadcast activity according to the content type, platform network status, and number of participants of the live broadcast activity;

基于传输策略集，将第一直播数据从第一设备集传输至第二设备集，其中，所述传输策略集包括多个不同的传输策略，所述第一设备集包括一个或多个第一设备，所述第二设备集包括一个或多个第二设备；Based on a transmission strategy set, transmitting the first live broadcast data from a first device set to a second device set, wherein the transmission strategy set includes a plurality of different transmission strategies, the first device set includes one or more first devices, and the second device set includes one or more second devices;

根据用户的网络状况和数据传输质量动态调整各传输策略，其中，所述传输策略包括智能选择数据传输链路、动态调整媒体质量参数、以及动态调整缓冲区大小以及相邻两个调整的时间间隔。Dynamically adjust each transmission strategy according to the user's network status and data transmission quality, wherein the transmission strategy includes intelligently selecting a data transmission link, dynamically adjusting media quality parameters, and dynamically adjusting the buffer size and the time interval between two adjacent adjustments.

优选地，所述根据所述直播活动的内容类型、平台网络状况以及参与人数，分配所述直播活动的第一宽带资源；包括：Preferably, allocating the first broadband resource of the live broadcast activity according to the content type, platform network status and number of participants of the live broadcast activity comprises:

通过历史数据，建立第一宽带资源预测模型；所述历史数据包括直播活动的内容类型、峰值人数、平均在线人数、平台网络状况、同一时间段的直播活动类型和总量以及总参与人数；Establishing a first broadband resource prediction model through historical data; the historical data includes content type of live broadcast activities, peak number of people, average number of online people, platform network status, type and total amount of live broadcast activities in the same time period, and total number of participants;

根据t时刻的实时数据，通过宽带资源预测模型，预测对应t+1时刻直播活动的第一宽带资源。According to the real-time data at time t, the first broadband resource corresponding to the live broadcast activity at time t+1 is predicted through the broadband resource prediction model.

优选地，所述传输策略集包括：Preferably, the transmission strategy set includes:

对多个类型的第一直播数据进行实时性评分；根据实时性评分获得传输优先级；根据传输优先级设置传输队列；所述第一直播数据的类型包括文件数据、视频数据、音频数据和/或书写数据；Performing real-time scoring on multiple types of first live broadcast data; obtaining a transmission priority according to the real-time scoring; setting a transmission queue according to the transmission priority; the types of the first live broadcast data include file data, video data, audio data and/or written data;

响应于文件数据的变化，第一设备仅传输文件数据的变化部分至第二电子设备；In response to a change in the file data, the first device transmits only the changed portion of the file data to the second electronic device;

根据视频数据、音频数据或交互数据的刷新频率，设置对应类型的第一直播数据类型的传输频率；According to the refresh frequency of the video data, the audio data or the interactive data, the transmission frequency of the first live data type of the corresponding type is set;

对网络环境进行全面评估，并智能选择数据传输链路；根据网络状况、用户信息以及环境信息，动态调整媒体质量参数；Comprehensively evaluate the network environment and intelligently select data transmission links; dynamically adjust media quality parameters based on network conditions, user information, and environmental information;

建立多级缓存机制，根据用户地理位置、网络状况以及节点评分，动态调整缓冲区大小以及相邻两个调整的时间间隔。A multi-level cache mechanism is established to dynamically adjust the buffer size and the time interval between two adjacent adjustments based on the user's geographic location, network conditions, and node scores.

优选地，所述对网络环境进行全面评估，并智能选择数据传输链路；包括：Preferably, the comprehensive assessment of the network environment and intelligent selection of a data transmission link includes:

根据用户地理位置，通过网络拓扑结构获得发送端和接收端的多条通信链路；According to the user's geographical location, multiple communication links between the sender and the receiver are obtained through the network topology;

根据t时刻的链路第一评分、地理距离以及链路负载，通过约束条件，预测t+1时刻的可用链路。According to the first link score, geographical distance and link load at time t, the available links at time t+1 are predicted through constraints.

优选地，所述根据t时刻的链路第一评分、地理距离以及链路负载，通过约束条件，预测t+1时刻的可用链路，包括：Preferably, the predicting of the available links at time t+1 according to the first link score at time t, the geographical distance and the link load through the constraint conditions includes:

收集可用链路的实时性能指标，其中，性能指标包括丢包率、丢包残差、丢包率残差变化率、实时带宽、延迟时间以及链路可靠性；Collect real-time performance indicators of available links, including packet loss rate, packet loss residual, packet loss rate residual change rate, real-time bandwidth, delay time, and link reliability;

通过机器学习模型，输出t时刻的链路第一评分；Through the machine learning model, the first link score at time t is output;

利用时间序列分析预测t+1时刻的链路性能指标，并结合t时刻的链路第一评分预测t+1时刻的第一评分；Use time series analysis to predict the link performance index at time t+1, and combine the first link score at time t to predict the first score at time t+1;

通过链路的地理距离和负载预测，计算t+1时刻的链路第二评分；Calculate the second link score at time t+1 based on the geographical distance and load prediction of the link;

定义约束条件，所述约束条件包括最大可接受的丢包率、最小带宽要求、最大延迟以及负载均衡；defining constraints, including maximum acceptable packet loss rate, minimum bandwidth requirement, maximum delay, and load balancing;

根据t+1时刻链路的第二评分和约束条件，预测t+1时刻的可用链路；According to the second score and constraint condition of the link at time t+1, predict the available link at time t+1;

根据业务的冗余需求，选择多条可用链路；并选择第二评分最高的可用链路作为主链路；通过传输队列中的数据量和链路负载，分配传输队列中的数据到不同的可用链路。According to the redundancy requirements of the business, multiple available links are selected; and the available link with the second highest score is selected as the main link; according to the amount of data in the transmission queue and the link load, the data in the transmission queue is distributed to different available links.

优选地，所述方法还包括：Preferably, the method further comprises:

建立闭环反馈机制，持续监测链路性能，根据实际性能调整评分模型和预测算法的参数；Establish a closed-loop feedback mechanism to continuously monitor link performance and adjust the parameters of the scoring model and prediction algorithm based on actual performance;

根据历史数据和新出现的网络状况，自适应地调整约束条件和评分权重；引入异常检测算法，识别并隔离网络中的异常行为和/或故障链路。Adaptively adjust constraints and scoring weights based on historical data and emerging network conditions; introduce anomaly detection algorithms to identify and isolate abnormal behaviors and/or faulty links in the network.

优选地，所述通过传输队列中的数据量和链路负载，分配传输队列中的数据到不同的可用链路；包括：Preferably, the allocating data in the transmission queue to different available links according to the amount of data in the transmission queue and the link load comprises:

将同一优先级的数据分成不同的数据块；通过哈希函数来确定数据块的边界；确保相同内容的数据块有相同的哈希值；Divide data of the same priority level into different data blocks; determine the boundaries of data blocks through hash functions; ensure that data blocks with the same content have the same hash value;

将优先级最高的数据块分配给主链路，直到达到预设的负载阈值；Assign the highest priority data blocks to the primary link until the preset load threshold is reached;

将剩余数据块根据剩余选择链路的第二评分，以及对应链路的负载进行依次分配。The remaining data blocks are distributed in sequence according to the second scores of the remaining selected links and the loads of the corresponding links.

优选地，所述根据网络状况，用户信息以及环境信息，动态调整媒体质量参数，包括：Preferably, dynamically adjusting the media quality parameters according to the network status, user information and environment information includes:

收集用户端传输链路第一评分、用户信息、直播时间、环境信息以及媒体质量参数；所述用户信息包括用户设备信息、设备电池寿命以及电量、地理位置以及偏好；所述媒体质量参数包括音频质量、媒体清晰度以及交互响应速度；Collecting the first score of the user-side transmission link, user information, live broadcast time, environmental information and media quality parameters; the user information includes user device information, device battery life and power, geographic location and preferences; the media quality parameters include audio quality, media clarity and interactive response speed;

通过历史训练数据，训练深度学习模型，学习不同条件下媒体质量与用户满意度之间的关系；Through historical training data, deep learning models are trained to learn the relationship between media quality and user satisfaction under different conditions;

根据实时网络状况、用户信息、直播时间和环境信息，利用深度学习模型，预测最优媒体质量参数。Based on real-time network conditions, user information, live broadcast time and environmental information, deep learning models are used to predict optimal media quality parameters.

优选地，所述建立多级缓存机制，根据用户地理位置网络状况、以及节点评分，动态调整缓冲区大小，包括：Preferably, the multi-level cache mechanism is established to dynamically adjust the buffer size according to the user's geographical location, network status, and node score, including:

构建分布式缓存网络；所述分布式缓存网络包括多个节点；并获得节点评分；Constructing a distributed cache network; the distributed cache network includes a plurality of nodes; and obtaining node scores;

根据节点评分，调整缓冲区的大小以及相邻两次缓冲区大小调整的时间间隔。According to the node score, the buffer size and the time interval between two adjacent buffer size adjustments are adjusted.

本申请提供一种基于互联网的云课堂直播传输系统，所述系统包括：The present application provides an Internet-based cloud classroom live broadcast transmission system, the system comprising:

第一获取模块，用于获取用户参数以及直播活动参数，其中，所述用户参数包括用户的网络状况和数据传输质量，所述直播活动参数包括直播活动的内容类型、平台网络状况、参与人数、第一直播数据；A first acquisition module, used to acquire user parameters and live broadcast activity parameters, wherein the user parameters include the user's network status and data transmission quality, and the live broadcast activity parameters include the content type of the live broadcast activity, the platform network status, the number of participants, and the first live broadcast data;

第一分配模块，根据所述直播活动的内容类型、平台网络状况以及参与人数，分配所述直播活动的第一宽带资源；A first allocation module allocates a first broadband resource for the live broadcast activity according to the content type, platform network status, and number of participants of the live broadcast activity;

传输模块，用于基于传输策略集，将第一直播数据从第一设备集传输至第二设备集，其中，所述传输策略集包括多个不同的传输策略，所述第一设备集包括一个或多个第一设备，所述第二设备集包括一个或多个第二设备；A transmission module, configured to transmit the first live broadcast data from the first device set to the second device set based on a transmission strategy set, wherein the transmission strategy set includes a plurality of different transmission strategies, the first device set includes one or more first devices, and the second device set includes one or more second devices;

调整模块，用于根据用户的网络状况和数据传输质量动态调整各传输策略，其中，所述传输策略包括智能选择数据传输链路、动态调整媒体质量参数、以及动态调整缓冲区大小以及相邻两个调整的时间间隔。The adjustment module is used to dynamically adjust various transmission strategies according to the user's network status and data transmission quality, wherein the transmission strategy includes intelligently selecting a data transmission link, dynamically adjusting media quality parameters, and dynamically adjusting the buffer size and the time interval between two adjacent adjustments.

本发明的有益效果包括：第一宽带资源预测模型通过分析历史数据，预测直播活动所需的宽带资源，确保资源分配既不过剩也不不足，提高了资源利用效率。实时性评分与优先级设置确保了不同类型数据的及时传输，特别是对文件数据变化的精准传输，减少了不必要的数据传输量，提高了传输效率。智能链路选择与媒体质量参数调整能够根据网络状况和用户需求动态调整，保证了传输的稳定性和高质量，同时降低了延迟和卡顿现象。多级缓存机制与动态调整缓冲区大小相结合，确保了即使在网络状况不佳时，用户也能获得流畅的观看体验，减少了缓冲等待时间。深度学习模型预测媒体质量参数能够根据用户设备状况、地理位置和偏好等信息，提供个性化的内容质量设置，增强了用户满意度和参与度。闭环反馈机制与异常检测算法能够及时发现并隔离网络中的异常行为或故障链路，减少了直播中断的可能性，提高了系统的稳定性和可靠性。动态调整机制使得系统能够适应不断变化的网络环境和用户需求，提高了系统的灵活性和可扩展性，能够应对突发的大流量需求。通过精确的资源分配和高效的传输策略，减少了不必要的资源浪费，降低了运营成本，提高了整个系统的成本效益。The beneficial effects of the present invention include: the first broadband resource prediction model predicts the broadband resources required for live broadcast activities by analyzing historical data, ensuring that resource allocation is neither excessive nor insufficient, and improving resource utilization efficiency. Real-time scoring and priority setting ensure the timely transmission of different types of data, especially the accurate transmission of file data changes, reducing unnecessary data transmission and improving transmission efficiency. Intelligent link selection and media quality parameter adjustment can be dynamically adjusted according to network conditions and user needs, ensuring the stability and high quality of transmission, while reducing delays and jamming. The multi-level cache mechanism is combined with the dynamic adjustment of the buffer size to ensure that users can get a smooth viewing experience even when the network conditions are poor, reducing the buffer waiting time. The deep learning model predicts media quality parameters and can provide personalized content quality settings based on information such as user device conditions, geographic location and preferences, thereby enhancing user satisfaction and participation. The closed-loop feedback mechanism and anomaly detection algorithm can timely detect and isolate abnormal behaviors or faulty links in the network, reduce the possibility of live broadcast interruption, and improve the stability and reliability of the system. The dynamic adjustment mechanism enables the system to adapt to the ever-changing network environment and user needs, improves the flexibility and scalability of the system, and can cope with sudden large traffic demands. Through precise resource allocation and efficient transmission strategies, unnecessary resource waste is reduced, operating costs are lowered, and the cost-effectiveness of the entire system is improved.

附图说明BRIEF DESCRIPTION OF THE DRAWINGS

图1是本申请实施例提供的一种基于互联网的云课堂直播传输方法示意图。FIG1 is a schematic diagram of an Internet-based cloud classroom live broadcast transmission method provided in an embodiment of the present application.

具体实施方式DETAILED DESCRIPTION

下面，结合附图以及具体实施方式，对本申请做进一步描述，需要说明的是，在不相冲突的前提下，以下描述的各实施例之间或各技术特征之间可以任意组合形成新的实施例。Below, the present application is further described in conjunction with the accompanying drawings and specific implementation methods. It should be noted that, under the premise of no conflict, the various embodiments or technical features described below can be arbitrarily combined to form a new embodiment.

参见图1，本申请实施例提供了一种基于互联网的云课堂直播传输方法，所述方法包括：Referring to FIG. 1 , an embodiment of the present application provides a method for transmitting live broadcast of a cloud classroom based on the Internet, the method comprising:

获取用户参数以及直播活动参数，其中，所述用户参数包括用户的网络状况和数据传输质量，所述直播活动参数包括直播活动的内容类型、平台网络状况、参与人数、第一直播数据；Acquire user parameters and live broadcast activity parameters, wherein the user parameters include the user's network status and data transmission quality, and the live broadcast activity parameters include the content type of the live broadcast activity, the platform network status, the number of participants, and the first live broadcast data;

根据所述直播活动的内容类型、平台网络状况以及参与人数，分配所述直播活动的第一宽带资源；Allocate a first broadband resource for the live broadcast activity according to the content type, platform network status, and number of participants of the live broadcast activity;

基于传输策略集，将第一直播数据从第一设备集传输至第二设备集，其中，所述传输策略集包括多个不同的传输策略，所述第一设备集包括一个或多个第一设备，所述第二设备集包括一个或多个第二设备；Based on a transmission strategy set, transmitting the first live broadcast data from a first device set to a second device set, wherein the transmission strategy set includes a plurality of different transmission strategies, the first device set includes one or more first devices, and the second device set includes one or more second devices;

根据用户的网络状况和数据传输质量动态调整各传输策略，其中，所述传输策略包括智能选择数据传输链路、动态调整媒体质量参数、以及动态调整缓冲区大小以及相邻两个调整的时间间隔。Dynamically adjust each transmission strategy according to the user's network status and data transmission quality, wherein the transmission strategy includes intelligently selecting a data transmission link, dynamically adjusting media quality parameters, and dynamically adjusting the buffer size and the time interval between two adjacent adjustments.

其中，获取用户参数以及直播活动参数，包括：Among them, obtaining user parameters and live broadcast activity parameters includes:

响应于账号密码识别或生物识别，获得用户信息；所述用户标识包括用户基本信息、设备信息和地理位置；根据所述用户基本信息分配对应的功能和权限；In response to account password recognition or biometric recognition, user information is obtained; the user identification includes basic user information, device information and geographic location; corresponding functions and permissions are allocated according to the basic user information;

获取讲师的第一直播数据以及用户交互信息，所述交互信息包括用户互动信息、操作日志和反馈评价。The lecturer's first live broadcast data and user interaction information are obtained, wherein the interaction information includes user interaction information, operation logs and feedback evaluations.

上述技术方案的工作原理为：The working principle of the above technical solution is:

首先通过账号密码识别或生物识别技术进行用户身份验证，获取用户信息，包括用户的基本信息、所用设备的信息和地理位置。这些信息用于后续的服务个性化和权限管理。First, user identity verification is performed through account and password recognition or biometrics technology to obtain user information, including basic user information, device information and geographic location. This information is used for subsequent service personalization and permission management.

收集直播活动的相关参数，包括直播的内容类型(如讲座、研讨会、实验演示等)、平台当前的网络状况、预期的参与人数以及讲师提供的第一直播数据。根据收集到的直播活动参数，系统智能地分配第一宽带资源。这一过程考虑了内容类型(影响所需带宽)、平台网络状况(可能限制实际可用带宽)以及参与人数(影响带宽需求量)，以确保直播活动的顺利进行。Collect relevant parameters of the live broadcast event, including the type of live broadcast content (such as lectures, seminars, experimental demonstrations, etc.), the current network status of the platform, the expected number of participants, and the first live broadcast data provided by the lecturer. Based on the collected live broadcast event parameters, the system intelligently allocates the first broadband resource. This process takes into account the content type (affecting the required bandwidth), the platform network status (which may limit the actual available bandwidth), and the number of participants (affecting the bandwidth demand) to ensure the smooth progress of the live broadcast event.

第一直播数据从第一设备集(通常是讲师的设备)传输至第二设备集(参与者的设备)；这一过程采用了传输策略集，其中包含多种不同的传输策略，以适应不同的网络条件和用户需求。传输策略集包括但不限于智能选择数据传输链路、动态调整媒体质量参数(如视频分辨率、帧率等)以及动态调整缓冲区大小和调整的时间间隔。这些策略能够根据实时监测到的用户网络状况和数据传输质量进行动态调整，以维持最优的直播体验。The first live broadcast data is transmitted from the first device set (usually the lecturer's device) to the second device set (the participant's device); this process adopts a transmission strategy set, which contains a variety of different transmission strategies to adapt to different network conditions and user needs. The transmission strategy set includes but is not limited to intelligent selection of data transmission links, dynamic adjustment of media quality parameters (such as video resolution, frame rate, etc.), and dynamic adjustment of buffer size and adjustment time interval. These strategies can be dynamically adjusted according to the real-time monitored user network status and data transmission quality to maintain the optimal live broadcast experience.

持续监控用户的网络状况和数据传输质量，并根据这些变化动态调整传输策略。例如，如果检测到某个用户的网络连接变差，系统可能会降低传输给该用户的媒体质量，或者增加缓冲区大小，以防止播放中断。Continuously monitor the user's network status and data transmission quality, and dynamically adjust the transmission strategy based on these changes. For example, if it detects that a user's network connection has deteriorated, the system may reduce the quality of the media transmitted to the user or increase the buffer size to prevent playback interruptions.

上述技术方案的效果为：The effects of the above technical solution are:

通过根据用户的传输链路网络状况和数据传输质量动态调整传输策略，如智能选择数据传输链路、动态调整媒体质量参数等，能够确保视频流在不同网络条件下都能保持流畅，显著提升用户的观看体验；系统根据用户的基本信息和地理位置等信息，可以为用户提供更加个性化的服务和推荐，如根据用户偏好调整直播内容推送，增强用户满意度。根据直播活动的内容类型、平台网络状况以及参与人数来分配第一宽带资源，能够确保在资源有限的情况下，直播活动能够获得最优的带宽支持，避免资源浪费，提高资源利用效率。动态调整缓冲区大小以及相邻两个调整的时间间隔，可以进一步优化数据传输的稳定性，减少因网络波动导致的卡顿现象，同时保证数据的连续性和完整性。By dynamically adjusting the transmission strategy according to the user's transmission link network status and data transmission quality, such as intelligently selecting data transmission links and dynamically adjusting media quality parameters, it can ensure that the video stream remains smooth under different network conditions, significantly improving the user's viewing experience; the system can provide users with more personalized services and recommendations based on the user's basic information and geographic location, such as adjusting the live content push according to user preferences to enhance user satisfaction. Allocating the first broadband resource based on the content type, platform network status and number of participants of the live event can ensure that the live event can obtain the best bandwidth support when resources are limited, avoid resource waste and improve resource utilization efficiency. Dynamically adjusting the buffer size and the time interval between two adjacent adjustments can further optimize the stability of data transmission, reduce the jamming caused by network fluctuations, and ensure the continuity and integrity of the data.

通过获取用户交互信息，如用户互动信息、操作日志和反馈评价，系统可以实时了解用户的反馈和需求，从而调整直播内容和形式，增强师生之间的互动性和学生的参与度。用户的反馈评价能够帮助讲师及时调整教学策略，提升教学质量；同时，用户的操作日志也为系统优化提供了宝贵的数据支持。通过账号密码识别或生物识别技术获取用户信息，提高了系统的安全性和用户身份的准确性，防止了非法访问和数据泄露的风险。多种传输策略的组合使用，以及根据网络状况的动态调整，确保了数据传输的稳定性和可靠性，减少了因网络问题导致的直播中断或数据丢失的风险。By obtaining user interaction information, such as user interaction information, operation logs, and feedback evaluations, the system can understand user feedback and needs in real time, thereby adjusting the content and form of live broadcasts, and enhancing the interactivity between teachers and students and the participation of students. User feedback and evaluations can help lecturers adjust teaching strategies in a timely manner and improve teaching quality; at the same time, user operation logs also provide valuable data support for system optimization. Obtaining user information through account password recognition or biometric technology improves the security of the system and the accuracy of user identity, and prevents the risk of illegal access and data leakage. The combined use of multiple transmission strategies and dynamic adjustments based on network conditions ensure the stability and reliability of data transmission, and reduce the risk of live broadcast interruption or data loss due to network problems.

在一些实施例中，所述根据所述直播活动的内容类型、平台网络状况以及参与人数，分配所述直播活动的第一宽带资源；包括：In some embodiments, allocating the first broadband resource of the live broadcast activity according to the content type, platform network status, and number of participants of the live broadcast activity includes:

通过历史数据，建立第一宽带资源预测模型；所述历史数据包括直播活动的内容类型、峰值人数、平均在线人数、平台网络状况、同一时间段的直播活动类型和总量以及总参与人数；Establishing a first broadband resource prediction model through historical data; the historical data includes content type of live broadcast activities, peak number of people, average number of online people, platform network status, type and total amount of live broadcast activities in the same time period, and total number of participants;

根据t时刻的实时数据，通过宽带资源预测模型，预测对应t+1时刻直播活动的第一宽带资源。According to the real-time data at time t, the first broadband resource corresponding to the live broadcast activity at time t+1 is predicted through the broadband resource prediction model.

上述技术方案的工作原理为：首先收集大量的历史数据，这些数据涵盖了不同直播活动的各种关键指标，包括直播活动的内容类型(如讲座、研讨会、课程等)、峰值人数(即直播过程中同时在线的最大人数)、平均在线人数、平台网络状况(如网络带宽、延迟、丢包率等)、同一时间段的直播活动类型和总量以及总参与人数等。The working principle of the above technical solution is: first, a large amount of historical data is collected, which covers various key indicators of different live broadcast activities, including the content type of the live broadcast activity (such as lectures, seminars, courses, etc.), peak number of people (that is, the maximum number of people online at the same time during the live broadcast), average number of people online, platform network conditions (such as network bandwidth, latency, packet loss rate, etc.), type and total amount of live broadcast activities in the same time period, and total number of participants.

收集到的历史数据会经过预处理步骤，包括数据清洗(去除错误或异常值)、数据转换(如将时间戳转换为统一的日期时间格式)、数据标准化或归一化(确保不同量纲的数据可以在同一模型中公平比较)等，以便后续建模使用。The collected historical data will undergo preprocessing steps, including data cleaning (removing errors or outliers), data conversion (such as converting timestamps to a unified date and time format), data standardization or normalization (ensuring that data of different dimensions can be fairly compared in the same model), etc., for subsequent modeling use.

基于预处理后的历史数据，利用机器学习算法(如线性回归、决策树、随机森林、神经网络等)或统计方法，建立一个预测模型。这个模型的目标是，在给定的输入特征(如直播活动的内容类型、预计峰值人数、平均在线人数、平台网络状况等)下，预测出直播活动所需的宽带资源量。模型的训练过程涉及调整模型参数以最小化预测误差(如均方误差、绝对误差等)，并通过交叉验证等技术评估模型的泛化能力，确保模型在未见过的数据上也能表现良好。Based on the preprocessed historical data, a prediction model is established using machine learning algorithms (such as linear regression, decision trees, random forests, neural networks, etc.) or statistical methods. The goal of this model is to predict the amount of broadband resources required for live events given input features (such as the content type of the live event, the expected peak number of people, the average number of online people, the platform network status, etc.). The model training process involves adjusting the model parameters to minimize the prediction error (such as mean square error, absolute error, etc.), and evaluating the generalization ability of the model through cross-validation and other techniques to ensure that the model performs well on unseen data.

在t时刻，系统会收集到关于即将开始或正在进行的直播活动的实时数据，包括当前的网络状况、已注册或在线的参与人数、直播内容类型等；这些实时数据被输入到已训练好的宽带资源预测模型中，模型根据输入的特征计算出t+1时刻(即直播活动即将开始或正在进行时)直播活动所需的第一宽带资源量。At time t, the system will collect real-time data about the live broadcast event that is about to begin or is in progress, including the current network status, the number of registered or online participants, the type of live broadcast content, etc.; these real-time data are input into the trained broadband resource prediction model, and the model calculates the first amount of broadband resources required for the live broadcast event at time t+1 (i.e., when the live broadcast event is about to begin or is in progress) based on the input features.

根据模型的预测结果，为直播活动分配相应的宽带资源。如果预测结果显示所需资源超出当前可用资源，可能会提前进行资源调度，如从其他非高峰时段的直播活动中借用资源，或通知用户调整直播设置以减少带宽需求。在直播过程中，持续监控网络状况和传输质量，并根据需要动态调整已分配的宽带资源，以确保直播的流畅性和稳定性。直播结束后，会将实际使用的宽带资源与预测值进行比较，计算预测误差。这些误差数据将被用于进一步优化预测模型，提高未来预测的准确性。同时，系统还会收集用户的反馈意见和直播效果评估数据，作为改进直播传输方法和优化资源分配的参考依据。Based on the prediction results of the model, appropriate broadband resources are allocated for the live broadcast event. If the prediction results show that the required resources exceed the currently available resources, resource scheduling may be carried out in advance, such as borrowing resources from other live broadcast events during non-peak hours, or notifying users to adjust live broadcast settings to reduce bandwidth requirements. During the live broadcast process, the network status and transmission quality are continuously monitored, and the allocated broadband resources are dynamically adjusted as needed to ensure the smoothness and stability of the live broadcast. After the live broadcast ends, the actual broadband resources used will be compared with the predicted values to calculate the prediction error. These error data will be used to further optimize the prediction model and improve the accuracy of future predictions. At the same time, the system will also collect user feedback and live broadcast effect evaluation data as a reference for improving live broadcast transmission methods and optimizing resource allocation.

上述技术方案的效果为：通过基于历史数据的宽带资源预测模型，能够更准确地预测直播活动所需的宽带资源量，从而避免资源的过度分配或不足；这有助于确保资源的有效利用，减少资源浪费，降低运营成本。预测模型能够根据实时数据动态调整宽带资源分配，确保在直播过程中为用户提供稳定的网络连接和流畅的观看体验。即使在网络条件不佳的情况下，也能通过智能调整减少卡顿和延迟，提升用户满意度；该方案使得系统能够快速适应直播活动的变化，如参与人数的突然增加或网络状况的波动。通过实时数据驱动的资源分配，系统能够迅速响应并作出调整，确保直播活动的顺利进行。利用机器学习算法和统计方法建立的预测模型，能够不断从实际使用中收集数据并优化自身，从而提高预测的准确性。随着时间的推移，模型的预测能力将越来越强，为直播活动提供更加精准的资源分配建议。在大型教育平台上，经常需要同时支持多个直播活动。该技术方案通过智能的宽带资源分配机制，使得系统能够同时处理多个直播活动的资源需求，确保每个活动都能获得足够的带宽支持，满足大规模并发的需求。在预测到资源不足时，系统能够提前进行资源调度，如从其他非高峰时段的直播活动中借用资源，或者通过负载均衡技术将流量分散到多个服务器上。这有助于平衡系统负载，减少单点故障的风险，提高系统的稳定性和可靠性。通过收集和分析实际使用的宽带资源数据、用户反馈意见和直播效果评估数据，系统能够为决策者提供数据驱动的决策支持。这有助于优化直播传输策略、改进资源分配方案，并推动教育服务的持续改进和创新。The effect of the above technical solution is: through the broadband resource prediction model based on historical data, the amount of broadband resources required for live broadcast activities can be predicted more accurately, thereby avoiding over-allocation or under-allocation of resources; this helps to ensure the effective use of resources, reduce resource waste, and reduce operating costs. The prediction model can dynamically adjust the allocation of broadband resources according to real-time data to ensure that users are provided with stable network connections and smooth viewing experience during the live broadcast process. Even in the case of poor network conditions, it can reduce freezes and delays through intelligent adjustments to improve user satisfaction; this solution enables the system to quickly adapt to changes in live broadcast activities, such as a sudden increase in the number of participants or fluctuations in network conditions. Through real-time data-driven resource allocation, the system can respond quickly and make adjustments to ensure the smooth progress of live broadcast activities. The prediction model established using machine learning algorithms and statistical methods can continuously collect data from actual use and optimize itself, thereby improving the accuracy of predictions. Over time, the model's prediction ability will become stronger and stronger, providing more accurate resource allocation suggestions for live broadcast activities. On large-scale educational platforms, it is often necessary to support multiple live broadcast activities at the same time. This technical solution uses an intelligent broadband resource allocation mechanism to enable the system to handle the resource requirements of multiple live events at the same time, ensuring that each event can obtain sufficient bandwidth support to meet the needs of large-scale concurrency. When insufficient resources are predicted, the system can schedule resources in advance, such as borrowing resources from other live events during non-peak hours, or distributing traffic to multiple servers through load balancing technology. This helps balance the system load, reduce the risk of single point failures, and improve the stability and reliability of the system. By collecting and analyzing actual broadband resource data, user feedback, and live broadcast effect evaluation data, the system can provide decision makers with data-driven decision support. This helps optimize live broadcast transmission strategies, improve resource allocation plans, and promote continuous improvement and innovation in educational services.

综上所述，该技术方案在云课堂直播传输中实施时，能够显著提高资源利用效率、优化用户体验、增强系统灵活性和响应速度、提升预测准确性、支持大规模并发直播、促进资源调度和负载均衡，并提供数据驱动的决策支持。In summary, when this technical solution is implemented in cloud classroom live broadcast transmission, it can significantly improve resource utilization efficiency, optimize user experience, enhance system flexibility and response speed, improve prediction accuracy, support large-scale concurrent live broadcasts, promote resource scheduling and load balancing, and provide data-driven decision support.

在一些实施例中，对多个类型的第一直播数据进行实时性评分；根据实时性评分获得传输优先级；根据传输优先级设置传输队列；所述第一直播数据的类型包括文件数据、视频数据、音频数据和/或书写数据；In some embodiments, a real-time score is performed on multiple types of first live broadcast data; a transmission priority is obtained according to the real-time score; a transmission queue is set according to the transmission priority; the types of the first live broadcast data include file data, video data, audio data and/or written data;

响应于文件数据的变化，第一设备仅传输文件数据的变化部分至第二电子设备；In response to a change in the file data, the first device transmits only the changed portion of the file data to the second electronic device;

根据视频数据、音频数据或交互数据的刷新频率，设置对应类型的第一直播数据类型的传输频率；According to the refresh frequency of the video data, the audio data or the interactive data, the transmission frequency of the first live data type of the corresponding type is set;

对网络环境进行全面评估，并智能选择数据传输链路；根据网络状况、用户信息以及环境信息，动态调整媒体质量参数；Comprehensively evaluate the network environment and intelligently select data transmission links; dynamically adjust media quality parameters based on network conditions, user information, and environmental information;

建立多级缓存机制，根据用户地理位置、网络状况以及节点评分，动态调整缓冲区大小以及相邻两个调整的时间间隔。A multi-level cache mechanism is established to dynamically adjust the buffer size and the time interval between two adjacent adjustments based on the user's geographic location, network conditions, and node scores.

上述技术方案的工作原理和效果为：首先对不同类型的第一直播数据(文件数据、视频数据、音频数据、书写数据)进行实时性评估。这个评分会考虑数据的时效性、重要性以及用户关注度等因素。The working principle and effect of the above technical solution are as follows: First, different types of first live broadcast data (file data, video data, audio data, written data) are evaluated in real time. This evaluation will take into account factors such as the timeliness, importance, and user attention of the data.

基于实时性评分，系统为每个数据流分配一个传输优先级；优先级高的数据流将优先传输，以确保关键信息的及时传递。根据传输优先级，系统建立传输队列。队列中的每个位置对应一个数据流，按照优先级顺序进行传输。这有助于在有限的网络资源下，最大化关键信息的传输效率。Based on the real-time score, the system assigns a transmission priority to each data stream; data streams with high priority will be transmitted first to ensure timely delivery of key information. Based on the transmission priority, the system establishes a transmission queue. Each position in the queue corresponds to a data stream, which is transmitted in order of priority. This helps to maximize the transmission efficiency of key information under limited network resources.

对于文件数据，系统采用差异化传输策略。当文件数据发生变化时，系统仅传输变化的部分至第二电子设备，而非整个文件。这大大减少了数据传输量，提高了传输效率。For file data, the system adopts a differentiated transmission strategy. When the file data changes, the system only transmits the changed part to the second electronic device instead of the entire file. This greatly reduces the amount of data transmission and improves the transmission efficiency.

基于刷新频率的传输频率：系统根据视频数据、音频数据或交互数据的刷新频率(即更新速度)，动态设置对应类型数据的传输频率。高刷新频率的数据将更频繁地传输，以满足实时性需求；而低刷新频率的数据则减少传输次数，以节省网络资源。Transmission frequency based on refresh rate: The system dynamically sets the transmission frequency of the corresponding type of data according to the refresh rate (i.e. update speed) of video data, audio data or interactive data. Data with high refresh rate will be transmitted more frequently to meet real-time requirements; while data with low refresh rate will be transmitted less frequently to save network resources.

全面评估当前网络环境，包括带宽、延迟、丢包率等指标。基于评估结果，智能选择最优的数据传输链路，以确保数据传输的稳定性和高效性。Comprehensively evaluate the current network environment, including bandwidth, latency, packet loss rate and other indicators. Based on the evaluation results, intelligently select the optimal data transmission link to ensure the stability and efficiency of data transmission.

根据网络状况、用户信息(如设备性能、网络套餐以及设备电池健康)以及环境信息(包括环境噪声和环境亮度)，动态调整媒体质量参数(如视频分辨率、帧率、音频码率等)。在网络条件不佳时，降低媒体质量以保证流畅性；在网络条件良好时，提升媒体质量以提升观看体验。Dynamically adjust media quality parameters (such as video resolution, frame rate, audio bitrate, etc.) based on network conditions, user information (such as device performance, network package, and device battery health), and environmental information (including ambient noise and ambient brightness). When network conditions are poor, media quality is reduced to ensure smoothness; when network conditions are good, media quality is increased to improve viewing experience.

建立多级缓存机制，根据用户地理位置、网络状况以及节点评分(即缓存节点的性能、稳定性等指标)，动态调整缓冲区大小以及相邻两次调整的时间间隔。在网络拥堵或用户设备性能较低时，增加缓冲区大小以减少因网络延迟或处理能力不足导致的卡顿现象；在网络畅通或用户设备性能较高时，减少缓冲区大小以释放缓存资源。A multi-level cache mechanism is established to dynamically adjust the buffer size and the time interval between two consecutive adjustments based on the user's geographic location, network conditions, and node scores (i.e., cache node performance, stability, and other indicators). When the network is congested or the user's device performance is low, the buffer size is increased to reduce the jamming caused by network delays or insufficient processing power; when the network is unobstructed or the user's device performance is high, the buffer size is reduced to release cache resources.

综上所述，该传输策略集通过实时性评分、差异化传输、智能链路选择、动态媒体质量调整以及多级缓存机制等策略，实现了对直播数据传输的全面优化。这些策略相互配合，确保了直播数据的高效、稳定传输，提升了用户体验。In summary, this transmission strategy set achieves comprehensive optimization of live data transmission through real-time scoring, differentiated transmission, intelligent link selection, dynamic media quality adjustment, and multi-level cache mechanism. These strategies work together to ensure efficient and stable transmission of live data and improve user experience.

在一些实施例中，所述对网络环境进行全面评估，并智能选择数据传输链路；包括：In some embodiments, the comprehensive assessment of the network environment and intelligent selection of a data transmission link includes:

根据用户地理位置，通过网络拓扑结构获得发送端和接收端的多条通信链路；According to the user's geographical location, multiple communication links between the sender and the receiver are obtained through the network topology;

根据t时刻的链路第一评分、地理距离以及链路负载，通过约束条件，预测t+1时刻的可用链路。According to the first link score, geographical distance and link load at time t, the available links at time t+1 are predicted through constraints.

在一些实施例中，所述根据t时刻的链路第一评分、地理距离以及链路负载，通过约束条件，预测t+1时刻的可用链路，包括：In some embodiments, predicting the available links at time t+1 according to the first link score, geographical distance, and link load at time t through constraints includes:

收集可用链路的实时性能指标，其中，性能指标包括丢包率、丢包残差、丢包率残差变化率、实时带宽、延迟时间以及链路可靠性；Collect real-time performance indicators of available links, including packet loss rate, packet loss residual, packet loss rate residual change rate, real-time bandwidth, delay time, and link reliability;

通过机器学习模型，输出t时刻的链路第一评分；Through the machine learning model, the first link score at time t is output;

利用时间序列分析预测t+1时刻的链路性能指标，并结合t时刻的链路第一评分预测t+1时刻的第一评分；Use time series analysis to predict the link performance index at time t+1, and combine the first link score at time t to predict the first score at time t+1;

通过链路的地理距离和负载预测，计算t+1时刻的链路第二评分；Calculate the second link score at time t+1 based on the geographical distance and load prediction of the link;

定义约束条件，所述约束条件包括最大可接受的丢包率、最小带宽要求、最大延迟以及负载均衡；defining constraints, including maximum acceptable packet loss rate, minimum bandwidth requirement, maximum delay, and load balancing;

根据t+1时刻链路的第二评分和约束条件，预测t+1时刻的可用链路；According to the second score and constraint condition of the link at time t+1, predict the available link at time t+1;

根据业务的冗余需求，选择多条可用链路；并选择第二评分最高的可用链路作为主链路；通过传输队列中的数据量和链路负载，分配传输队列中的数据到不同的可用链路。According to the redundancy requirements of the business, multiple available links are selected; and the available link with the second highest score is selected as the main link; according to the amount of data in the transmission queue and the link load, the data in the transmission queue is distributed to different available links.

上述技术方案的工作原理为：根据用户地理位置，首先利用现有的网络拓扑结构信息，确定发送端(如直播服务器)和接收端(如用户设备)之间可能存在的多条通信链路。这些链路可能包括不同的网络运营商、不同的物理路径或不同的传输技术(如有线、无线)。The working principle of the above technical solution is as follows: based on the user's geographical location, the existing network topology information is first used to determine the multiple communication links that may exist between the sender (such as the live broadcast server) and the receiver (such as the user device). These links may include different network operators, different physical paths or different transmission technologies (such as wired, wireless).

对于每条发现的链路，系统实时收集其性能指标，这些指标包括但不限于丢包率、丢包残差、丢包率残差变化率、实时带宽、延迟时间以及链路可靠性。这些指标反映了链路的当前状态和质量。For each discovered link, the system collects its performance indicators in real time, including but not limited to packet loss rate, packet loss residual, packet loss rate residual change rate, real-time bandwidth, delay time, and link reliability. These indicators reflect the current status and quality of the link.

利用机器学习模型，系统根据收集到的实时性能指标对每条链路进行评分(称为第一评分)。这个评分综合考虑了链路的多个方面，以评估其在当前时刻的优劣。Using machine learning models, the system scores each link based on the collected real-time performance metrics (called the first score). This score takes into account multiple aspects of the link to assess its quality at the current moment.

系统利用时间序列分析技术，结合历史数据和当前状态，预测t+1时刻链路的性能指标。然后，结合t时刻的链路第一评分，通过机器学习模型或统计方法，预测t+1时刻的链路第一评分；有助于提前了解未来链路的状况。The system uses time series analysis technology to combine historical data and current status to predict the performance indicators of the link at time t+1. Then, combined with the first score of the link at time t, the first score of the link at time t+1 is predicted through machine learning models or statistical methods, which helps to understand the status of future links in advance.

除了性能指标外，还考虑链路的地理距离和当前负载。地理距离影响数据传输的延迟和成本，而负载则反映了链路的拥塞程度。通过综合考虑这些因素，计算t+1时刻的链路第二评分。第二评分可以为第一评分与地理距离评分、当前负载评分的加权评分；In addition to performance indicators, the geographical distance and current load of the link are also considered. The geographical distance affects the delay and cost of data transmission, while the load reflects the congestion level of the link. By comprehensively considering these factors, the second score of the link at time t+1 is calculated. The second score can be a weighted score of the first score, the geographical distance score, and the current load score;

定义一系列约束条件，如最大可接受的丢包率、最小带宽要求、最大延迟以及负载均衡等，这些条件反映了业务对链路质量的最低要求；根据t+1时刻链路的第二评分和这些约束条件，系统筛选出可用的链路。A series of constraints are defined, such as the maximum acceptable packet loss rate, minimum bandwidth requirement, maximum delay, and load balancing. These conditions reflect the minimum requirements of the business for link quality. Based on the second score of the link at time t+1 and these constraints, the system selects available links.

为了提高传输的可靠性和容错能力，系统根据业务的冗余需求选择多条可用链路。在多条可用链路中，选择第二评分最高的链路作为主链路，以确保主要数据流的传输质量。In order to improve the reliability and fault tolerance of transmission, the system selects multiple available links according to the redundancy requirements of the business. Among the multiple available links, the link with the second highest score is selected as the main link to ensure the transmission quality of the main data flow.

根据传输队列中的数据量和各条链路的负载情况，动态地将数据分配到不同的可用链路中。这有助于平衡各条链路的负载，提高整体传输效率。同时，系统也会监控各条链路的实时性能，并根据需要进行动态调整。Dynamically distribute data to different available links based on the amount of data in the transmission queue and the load of each link. This helps balance the load of each link and improve overall transmission efficiency. At the same time, the system also monitors the real-time performance of each link and makes dynamic adjustments as needed.

综上所述，通过全面评估网络环境、智能选择数据传输链路，并结合实时性能指标、地理距离、链路负载以及业务约束条件，实现了对直播数据传输链路的高效、灵活选择和管理。这有助于提高数据传输的稳定性、可靠性和效率，从而提升用户体验。In summary, by comprehensively evaluating the network environment, intelligently selecting data transmission links, and combining real-time performance indicators, geographical distance, link load, and business constraints, efficient and flexible selection and management of live data transmission links are achieved. This helps improve the stability, reliability, and efficiency of data transmission, thereby improving user experience.

上述技术方案的效果为：通过收集实时性能指标并利用机器学习模型进行评分，系统能够准确评估当前链路的质量。结合时间序列分析预测未来链路状态，能够提前发现并规避潜在的网络问题，从而显著提高数据传输的稳定性。选择性能最优的链路作为主链路，并合理分配传输队列中的数据到不同的可用链路，可以减少延迟、丢包等问题，确保用户能够流畅地接收直播内容或数据，提升用户满意度和体验。The effect of the above technical solution is: by collecting real-time performance indicators and scoring them using machine learning models, the system can accurately evaluate the quality of the current link. Combining time series analysis to predict future link status can detect and avoid potential network problems in advance, thereby significantly improving the stability of data transmission. Selecting the link with the best performance as the main link and reasonably allocating data in the transmission queue to different available links can reduce delays, packet loss and other problems, ensure that users can smoothly receive live content or data, and improve user satisfaction and experience.

根据业务的冗余需求选择多条可用链路，并在主链路出现故障时迅速切换到备用链路，确保了数据传输的连续性和可靠性。这种冗余设计大大降低了系统因单点故障而中断的风险。通过考虑链路的负载情况来分配数据，有助于实现负载均衡，避免某些链路因过载而导致性能下降。这不仅可以提高整体网络的利用率，还可以延长设备的使用寿命。Select multiple available links according to the redundancy requirements of the business, and quickly switch to the backup link when the main link fails, ensuring the continuity and reliability of data transmission. This redundant design greatly reduces the risk of system interruption due to single point failure. Distributing data by considering the load of the link helps to achieve load balancing and avoid performance degradation of certain links due to overload. This not only improves the utilization of the overall network, but also extends the service life of the equipment.

在一些实施例中，所述方法还包括：In some embodiments, the method further comprises:

建立闭环反馈机制，持续监测链路性能，根据实际性能调整评分模型和预测算法的参数；Establish a closed-loop feedback mechanism to continuously monitor link performance and adjust the parameters of the scoring model and prediction algorithm based on actual performance;

根据历史数据和新出现的网络状况，自适应地调整约束条件和评分权重；引入异常检测算法，识别并隔离网络中的异常行为和/或故障链路。Adaptively adjust constraints and scoring weights based on historical data and emerging network conditions; introduce anomaly detection algorithms to identify and isolate abnormal behaviors and/or faulty links in the network.

上述技术方案的工作原理和效果为：通过部署在网络中的监测点或代理，持续收集链路的实时性能指标数据，如丢包率、带宽、延迟等。收集到的数据被输入到评分模型和预测算法中，进行链路性能的实时评估。评估结果不仅用于当前链路的选择，还作为后续调整评分模型和预测算法参数的依据。根据链路性能的实际表现，系统会对评分模型和预测算法的参数进行动态调整。这些调整旨在提高评分和预测的准确性，以更好地适应网络环境的变化。系统会对历史数据进行分析，以了解不同时间段、不同网络状况下的链路性能特点。这些数据为约束条件和评分权重的调整提供了重要依据。同时，系统还会实时监测新的网络状况，如网络拥塞、设备故障等，这些都会影响到链路的选择和评分。The working principle and effect of the above technical solution are as follows: through monitoring points or agents deployed in the network, real-time performance indicator data of the link, such as packet loss rate, bandwidth, delay, etc., are continuously collected. The collected data is input into the scoring model and prediction algorithm to evaluate the link performance in real time. The evaluation results are not only used for the selection of the current link, but also as the basis for the subsequent adjustment of the parameters of the scoring model and prediction algorithm. According to the actual performance of the link, the system will dynamically adjust the parameters of the scoring model and prediction algorithm. These adjustments are aimed at improving the accuracy of scoring and prediction to better adapt to changes in the network environment. The system will analyze historical data to understand the performance characteristics of the link under different time periods and different network conditions. These data provide an important basis for the adjustment of constraints and scoring weights. At the same time, the system will also monitor new network conditions in real time, such as network congestion, equipment failure, etc., which will affect the selection and scoring of the link.

基于历史数据和新出现的网络状况，系统会自适应地调整约束条件和评分权重。例如，在网络拥塞时期，可能会增加对带宽和延迟的重视程度，降低对丢包率的容忍度。Based on historical data and emerging network conditions, the system will adaptively adjust constraints and scoring weights. For example, during periods of network congestion, it may increase the emphasis on bandwidth and latency and reduce the tolerance for packet loss.

首先，系统会对收集到的链路性能数据进行预处理，如去噪、归一化等，以提高异常检测的准确性。然后，利用异常检测算法对处理后的数据进行分析，识别出与正常模式偏离较大的数据点，即异常行为或故障链路。一旦识别出异常行为或故障链路，系统会立即采取措施进行隔离，防止其对整体网络性能造成影响。同时，还会触发故障恢复机制，尝试恢复故障链路的正常运行或切换到备用链路。First, the system pre-processes the collected link performance data, such as denoising and normalization, to improve the accuracy of anomaly detection. Then, the anomaly detection algorithm is used to analyze the processed data to identify data points that deviate greatly from the normal pattern, that is, abnormal behavior or faulty links. Once abnormal behavior or faulty links are identified, the system will immediately take measures to isolate them to prevent them from affecting the overall network performance. At the same time, the fault recovery mechanism will be triggered to try to restore the normal operation of the faulty link or switch to a backup link.

通过上述工作原理，所述方法能够建立一个动态、自适应的网络环境评估与链路选择机制。闭环反馈机制确保了评分模型和预测算法的持续优化；自适应调整约束条件和评分权重使系统能够灵活应对网络环境的变化；异常检测算法则增强了系统的稳定性和可靠性。这些机制共同作用下，能够为用户提供高质量、稳定的数据传输服务。Through the above working principle, the method can establish a dynamic and adaptive network environment evaluation and link selection mechanism. The closed-loop feedback mechanism ensures the continuous optimization of the scoring model and prediction algorithm; the adaptive adjustment of constraints and scoring weights enables the system to flexibly respond to changes in the network environment; and the anomaly detection algorithm enhances the stability and reliability of the system. Together, these mechanisms can provide users with high-quality and stable data transmission services.

在一些实施例中，所述通过传输队列中的数据量和链路负载，分配传输队列中的数据到不同的可用链路；包括：In some embodiments, allocating data in the transmission queue to different available links according to the amount of data in the transmission queue and the link load includes:

将同一优先级的数据分成不同的数据块；通过哈希函数来确定数据块的边界；确保相同内容的数据块有相同的哈希值；Divide data of the same priority level into different data blocks; determine the boundaries of data blocks through hash functions; ensure that data blocks with the same content have the same hash value;

将优先级最高的数据块分配给主链路，直到达到预设的负载阈值；Assign the highest priority data blocks to the primary link until the preset load threshold is reached;

将剩余数据块根据剩余选择链路的第二评分，以及对应链路的负载进行依次分配。The remaining data blocks are distributed in sequence according to the second scores of the remaining selected links and the loads of the corresponding links.

上述技术方案的工作原理为：将同一优先级的数据集按照某种策略(如固定大小、内容特性等)分成多个数据块。这样做的目的是便于管理和传输，同时提高数据处理的灵活性。The working principle of the above technical solution is: divide the data sets of the same priority into multiple data blocks according to a certain strategy (such as fixed size, content characteristics, etc.) The purpose of this is to facilitate management and transmission, while improving the flexibility of data processing.

使用哈希函数对数据的每个部分进行处理，根据哈希值来确定数据块的边界。哈希函数具有将任意长度的输入通过散列算法变换成固定长度的输出(即哈希值)的特性。由于哈希函数的确定性，相同内容的数据块将产生相同的哈希值，从而确保数据块的一致性和可识别性。通过比较哈希值来验证数据块的完整性和一致性。如果两个数据块的哈希值相同，则可以认为这两个数据块在内容上是一致的。Use a hash function to process each part of the data, and determine the boundaries of the data block based on the hash value. The hash function has the characteristic of transforming an input of any length into an output of fixed length (i.e., a hash value) through a hash algorithm. Due to the determinism of the hash function, data blocks with the same content will produce the same hash value, thereby ensuring the consistency and identifiability of the data blocks. The integrity and consistency of the data blocks are verified by comparing the hash values. If the hash values of two data blocks are the same, it can be considered that the two data blocks are consistent in content.

根据数据的优先级进行排序。优先级高的数据块将被优先处理。将优先级最高的数据块分配给主链路进行传输。主链路通常是性能最优、稳定性最高的链路，能够确保高优先级数据块的快速、可靠传输。在分配过程中，需要监控主链路的负载情况，确保不超过预设的负载阈值。一旦达到阈值，将停止向主链路分配数据块。对于剩余的数据块，根据剩余选择链路的第二评分(即综合考虑链路性能、地理距离、负载等因素得出的评分)以及对应链路的当前负载情况进行依次分配；分配时，优先选择评分高且负载较低的链路，以确保数据传输的高效性和稳定性。Sort the data according to their priority. Data blocks with high priority will be processed first. The data blocks with the highest priority will be allocated to the main link for transmission. The main link is usually the link with the best performance and the highest stability, which can ensure the fast and reliable transmission of high-priority data blocks. During the allocation process, it is necessary to monitor the load of the main link to ensure that it does not exceed the preset load threshold. Once the threshold is reached, the allocation of data blocks to the main link will stop. For the remaining data blocks, they will be allocated in sequence according to the second score of the remaining selected links (that is, the score obtained by comprehensively considering factors such as link performance, geographical distance, and load) and the current load of the corresponding links; when allocating, links with high scores and low loads are given priority to ensure the efficiency and stability of data transmission.

上述技术方案的效果为：优先将高优先级的数据块分配给性能较好的主链路，可以确保这些关键数据得到快速处理，从而缩短整体传输时间，提高传输效率。根据链路的第二评分和当前负载情况来分配剩余数据块，可以确保资源得到合理分配，避免某些链路过载而其他链路闲置，从而提高整个网络的资源利用率。通过哈希函数确定数据块边界，并确保相同内容的数据块具有相同的哈希值，有助于在数据传输过程中进行数据完整性和一致性的校验，从而增强系统的稳定性和可靠性。The effect of the above technical solution is: by allocating high-priority data blocks to the main link with better performance, it can ensure that these key data are processed quickly, thereby shortening the overall transmission time and improving transmission efficiency. Allocating the remaining data blocks according to the second score of the link and the current load situation can ensure that resources are reasonably allocated, avoid overloading some links while other links are idle, thereby improving the resource utilization of the entire network. Determining the data block boundaries through hash functions and ensuring that data blocks with the same content have the same hash value helps to verify data integrity and consistency during data transmission, thereby enhancing the stability and reliability of the system.

该策略具有动态调整的能力，能够根据网络状况的变化(如链路负载、性能波动等)实时调整数据分配方案，确保数据传输的连续性和稳定性。通过将复杂的数据传输任务分解为多个可管理的数据块，并基于明确的优先级和分配规则进行处理，可以大大降低数据传输管理的复杂度和难度。This strategy has the ability to dynamically adjust and can adjust the data allocation plan in real time according to changes in network conditions (such as link load, performance fluctuations, etc.) to ensure the continuity and stability of data transmission. By breaking down complex data transmission tasks into multiple manageable data blocks and processing them based on clear priorities and allocation rules, the complexity and difficulty of data transmission management can be greatly reduced.

在一些实施例中，所述根据网络状况，用户信息以及环境信息，动态调整媒体质量参数，包括：In some embodiments, dynamically adjusting the media quality parameters according to the network status, user information and environment information includes:

收集用户端传输链路第一评分、用户信息、直播时间、环境信息以及媒体质量参数；所述用户信息包括用户设备信息、设备电池寿命以及电量、地理位置以及偏好；所述媒体质量参数包括音频质量、媒体清晰度以及交互响应速度；若直播数据通过多条链路传输至某一用户端，则用户端的多条链路第一评分进行融合，获得该用户端链路融合融合评分，将所述融合评分作为深度学习模型的输入；Collect the first score of the user terminal transmission link, user information, live broadcast time, environmental information and media quality parameters; the user information includes user device information, device battery life and power, geographic location and preferences; the media quality parameters include audio quality, media clarity and interactive response speed; if the live broadcast data is transmitted to a certain user terminal through multiple links, the first scores of multiple links of the user terminal are fused to obtain the fusion score of the user terminal link fusion, and the fusion score is used as the input of the deep learning model;

其中，融合评分为：The fusion score is:

其中Rj为第j个用户端n条传输链路的融合评分，Pij为第j个用户端第i条传输线路的第一评分；wij为第j个用户端第i条传输线路的权重；Pij为第j个用户端第i条传输线路的最大负载，Dij为第j个用户端第i条传输线路的传输距离；Where Rj is the fusion score of the n transmission links of the jth user end, Pij is the first score of the i-th transmission line of the jth user end; wij is the weight of the i-th transmission line of the jth user end; Pij is the maximum load of the i-th transmission line of the jth user end, and Dij is the transmission distance of the i-th transmission line of the jth user end;

通过历史训练数据，训练深度学习模型，学习不同条件下媒体质量与用户满意度之间的关系；Through historical training data, deep learning models are trained to learn the relationship between media quality and user satisfaction under different conditions;

根据实时网络状况、用户信息、直播时间和环境信息，利用深度学习模型，预测最优媒体质量参数。Based on real-time network conditions, user information, live broadcast time and environmental information, deep learning models are used to predict optimal media quality parameters.

上述技术方案的工作原理为：The working principle of the above technical solution is:

对于通过多条链路传输至用户端的情况，首先收集每条传输链路的第一评分(Pij)，该评分基于链路的性能指标(如带宽、延迟、丢包率等)和环境信息综合得出。For the case of transmission to the user end via multiple links, the first score (Pij) of each transmission link is first collected. The score is obtained based on the performance indicators of the link (such as bandwidth, delay, packet loss rate, etc.) and environmental information.

收集用户端的相关信息，包括用户设备信息(如设备型号、处理能力)、设备电池寿命、地理位置以及用户偏好等。记录直播的具体时间，因为不同时间段的网络状况可能有所不同。收集用户端所处的环境信息，如网络覆盖情况、天气条件等，这些信息可能影响传输链路的性能。Collect relevant information about the user end, including user device information (such as device model, processing power), device battery life, geographic location, and user preferences. Record the specific time of the live broadcast, because the network conditions may vary in different time periods. Collect environmental information about the user end, such as network coverage, weather conditions, etc., which may affect the performance of the transmission link.

初始媒体质量参数设定，包括音频质量、媒体清晰度以及交互响应速度等，这些参数将作为后续调整的依据。对于多条传输链路的情况，使用给定的公式计算链路融合评分；这种权重分配方式考虑了链路的负载能力和传输成本(距离)，以更全面地评估链路的性能。Initial media quality parameter settings, including audio quality, media clarity, and interactive response speed, will serve as the basis for subsequent adjustments. For multiple transmission links, the link fusion score is calculated using a given formula; this weight distribution method takes into account the link's load capacity and transmission cost (distance) to more comprehensively evaluate the link's performance.

利用历史训练数据，包括不同条件下的网络状况、用户信息、直播时间、环境信息和对应的媒体质量参数，训练深度学习模型。模型学习媒体质量与用户满意度之间的关系，建立预测模型，以在给定条件下预测最优的媒体质量参数。在直播过程中，根据实时网络状况、用户信息、直播时间和环境信息，利用训练好的深度学习模型进行预测。模型输出最优的媒体质量参数，包括音频质量、媒体清晰度和交互响应速度等，以实现媒体质量的动态调整。根据深度学习模型的预测结果，调整媒体质量参数，以匹配当前的网络状况和用户需求。The deep learning model is trained using historical training data, including network conditions, user information, live broadcast time, environmental information, and corresponding media quality parameters under different conditions. The model learns the relationship between media quality and user satisfaction, and establishes a prediction model to predict the optimal media quality parameters under given conditions. During the live broadcast process, the trained deep learning model is used for prediction based on the real-time network conditions, user information, live broadcast time, and environmental information. The model outputs the optimal media quality parameters, including audio quality, media clarity, and interactive response speed, to achieve dynamic adjustment of media quality. According to the prediction results of the deep learning model, the media quality parameters are adjusted to match the current network conditions and user needs.

例如，在网络状况不佳时降低媒体清晰度以减少卡顿，或在用户设备性能较高时提升画质和音质；在用户电池电量低，电池健康不佳的情况降低媒体清晰度；当用户设备的电池电量低于某个阈值(如20％)时，系统可以自动降低媒体清晰度、减少视频帧率或调整音频质量，以减少对电量的消耗，延长设备的使用时间。例如，从高清切换到标清，或者从60帧每秒降低到30帧每秒。同时，系统可以提示用户当前电池电量较低，并询问是否愿意继续以当前媒体质量观看，或者自动切换到更节能的观看模式。如果用户设备的电池健康度不佳(如电池老化导致容量降低)，同样可以采取类似的措施来减少电量消耗。这包括降低媒体质量参数、调整屏幕亮度等，以减轻电池负担，避免电池过快耗尽。定期检测电池健康度，并根据检测结果自动调整媒体质量参数，以确保用户能够在电池状况不佳的情况下仍然获得相对流畅的观看体验。还可以根据电池电量和电池健康度的综合情况来制定更复杂的调整策略。例如，当电池电量低且电池健康度不佳时，系统可以进一步降低媒体质量参数，以最大程度地延长设备使用时间。系统还可以考虑用户的偏好和观看习惯。例如，如果用户经常在观看直播时关闭屏幕以节省电量，系统可以记住这一习惯，并在用户再次观看直播时自动调整媒体质量参数以适应这种场景。For example, when the network condition is poor, the media definition can be reduced to reduce lag, or the image and sound quality can be improved when the user's device performance is high; when the user's battery is low and the battery health is poor, the media definition can be reduced; when the battery power of the user's device is lower than a certain threshold (such as 20%), the system can automatically reduce the media definition, reduce the video frame rate, or adjust the audio quality to reduce power consumption and extend the use time of the device. For example, switch from high definition to standard definition, or reduce from 60 frames per second to 30 frames per second. At the same time, the system can prompt the user that the current battery power is low and ask whether he is willing to continue watching with the current media quality, or automatically switch to a more energy-saving viewing mode. If the battery health of the user's device is poor (such as battery aging resulting in reduced capacity), similar measures can be taken to reduce power consumption. This includes reducing media quality parameters, adjusting screen brightness, etc. to reduce the burden on the battery and avoid the battery from being exhausted too quickly. Regularly check the battery health and automatically adjust the media quality parameters based on the test results to ensure that users can still get a relatively smooth viewing experience when the battery is in poor condition. More complex adjustment strategies can also be formulated based on the comprehensive situation of battery power and battery health. For example, when the battery is low and battery health is poor, the system can further reduce media quality parameters to maximize device usage time. The system can also take into account user preferences and viewing habits. For example, if a user often turns off the screen to save power when watching live broadcasts, the system can remember this habit and automatically adjust the media quality parameters to adapt to this scenario when the user watches the live broadcast again.

上述技术方案的效果为：通过实时评估网络状况、用户信息以及环境信息，并据此调整媒体质量参数，可以确保用户在不同条件下都能获得最佳的观看体验。The effect of the above technical solution is: by real-time evaluation of network conditions, user information and environmental information, and adjusting media quality parameters accordingly, it can ensure that users can get the best viewing experience under different conditions.

多条链路传输时，通过计算链路融合评分并选择最优链路或组合，可以更有效地利用网络资源，避免单一链路过载导致的性能瓶颈。同时，根据链路的负载能力和传输成本分配权重，有助于实现资源的均衡利用。在网络状况不佳时，通过降低媒体质量来减少数据传输的负载，从而有效降低卡顿和延迟现象的发生。在网络状况良好且用户设备性能较高时，提升媒体质量参数(如媒体清晰度和音频质量)，使用户能够获得更加清晰、逼真的观看体验。通过优化媒体质量参数中的交互响应速度部分，可以确保用户在观看直播时能够流畅地进行互动操作，提升整体的用户体验。When multiple links are transmitting, by calculating the link fusion score and selecting the optimal link or combination, network resources can be used more effectively to avoid performance bottlenecks caused by overloading a single link. At the same time, allocating weights according to the link's load capacity and transmission cost helps to achieve balanced resource utilization. When the network condition is poor, the data transmission load is reduced by reducing the media quality, thereby effectively reducing the occurrence of freezes and delays. When the network condition is good and the user's device performance is high, improve the media quality parameters (such as media clarity and audio quality) so that users can get a clearer and more realistic viewing experience. By optimizing the interactive response speed part of the media quality parameters, it can ensure that users can interact smoothly when watching live broadcasts, improving the overall user experience.

在一些实施例中，所述建立多级缓存机制，根据用户地理位置网络状况、以及节点评分，动态调整缓冲区大小，包括：In some embodiments, the multi-level cache mechanism is established to dynamically adjust the buffer size according to the user's geographic location, network status, and node score, including:

构建分布式缓存网络；所述分布式缓存网络包括多个节点；并获得节点评分；Constructing a distributed cache network; the distributed cache network includes a plurality of nodes; and obtaining node scores;

根据节点评分，调整缓冲区的大小以及相邻两次缓冲区大小调整的时间间隔。According to the node score, the buffer size and the time interval between two adjacent buffer size adjustments are adjusted.

其中，节点评分为：The node score is:

若中任一值大于0，则like If any value in is greater than 0, then

若均小于等于0，则：like are both less than or equal to 0, then:

其中，Qk为第k个节点当前数据量，Qka为第k个节点在当前缓冲区域大小设置下预设时间段内的平均数据量；Fk为第k个节点当前负载，Fka为第k个节点在当前缓冲区域大小设置下预设时间段内的平均负载；Tk为第k个节点当前延迟；Tka为第k个节点在当前缓冲区域大小设置下预设时间段内的平均延迟；max()为取最大值；Wherein, Qk is the current data volume of the kth node, Qka is the average data volume of the kth node in the preset time period under the current buffer area size setting; Fk is the current load of the kth node, Fka is the average load of the kth node in the preset time period under the current buffer area size setting; Tk is the current delay of the kth node; Tka is the average delay of the kth node in the preset time period under the current buffer area size setting; max() is the maximum value;

若节点评分大于第一预设阈值，则进行第一调节，调整缓冲区的大小；If the node score is greater than a first preset threshold, a first adjustment is performed to adjust the size of the buffer;

若节点评分小于第二预设阈值，则进行第二调节，调整缓冲区的大小；If the node score is less than the second preset threshold, a second adjustment is performed to adjust the size of the buffer;

其中，skt1为第一调节后的第k个节点的缓冲区大小；skt2为第二调节后的第k个节点的缓冲区大小；α为调节系数，范围(0～3)；Skc为当前第k个节点缓冲区大小，Jy1为第一阈值；Jy2为第二阈值；skt1、skt2均在[skmin，skmax]范围之内，skmin为最小要求缓冲区大小；skmax为最大要求缓冲区大小。Among them, skt1 is the buffer size of the kth node after the first adjustment; skt2 is the buffer size of the kth node after the second adjustment; α is the adjustment coefficient, ranging from (0 to 3); Skc is the current buffer size of the kth node, Jy1 is the first threshold; Jy2 is the second threshold; skt1 and skt2 are both within the range of [skmin, skmax], skmin is the minimum required buffer size; skmax is the maximum required buffer size.

若前一次调整时间点到当前时间点的间隔小于最小时间间隔，则当前不做调整，下一次再调整。If the interval from the last adjusted time point to the current time point is less than the minimum time interval, no adjustment is made at the current time and adjustment is made next time.

上述技术方案的工作原理为：构建一个分布式缓存网络，该网络由多个节点组成，每个节点负责存储和分发数据。这些节点分布在不同的地理位置，以优化数据的访问速度和可靠性。The working principle of the above technical solution is to build a distributed cache network consisting of multiple nodes, each of which is responsible for storing and distributing data. These nodes are distributed in different geographical locations to optimize the access speed and reliability of data.

定期(或根据特定事件触发)计算每个节点的评分(Jk)；评分基于三个关键指标：数据量、负载和延迟。The score (Jk) of each node is calculated periodically (or triggered by specific events); the score is based on three key indicators: data volume, load and latency.

比较当前数据量(Qk)与预设时间段内的平均数据量(Qka)。Compare the current data volume (Qk) with the average data volume (Qka) within a preset time period.

比较当前负载(Fk)与预设时间段内的平均负载(Fka)。Compare the current load (Fk) with the average load (Fka) over a preset time period.

比较当前延迟(Tk)与预设时间段内的平均延迟(Tka)。Compare the current delay (Tk) with the average delay (Tka) over a preset time period.

对于每个指标，如果当前值大于平均值，则计算该指标的增长率(即(当前值-平均值)/平均值)，并取所有增长率中的最大值作为节点的评分(Jk)。如果所有指标的增长率都小于或等于0，则取最小值作为评分，尽管在这种情况下，评分可能是一个负数或非常接近0的值，表示节点状态相对稳定或有所下降。For each indicator, if the current value is greater than the average value, the growth rate of the indicator is calculated (i.e. (current value - average value) / average value), and the maximum value of all growth rates is taken as the node score (Jk). If the growth rates of all indicators are less than or equal to 0, the minimum value is taken as the score, although in this case, the score may be a negative number or a value very close to 0, indicating that the node status is relatively stable or has declined.

根据节点评分(Jk)，系统动态调整每个节点的缓冲区大小。According to the node score (Jk), the system dynamically adjusts the buffer size of each node.

如果Jk大于第一预设阈值(Jy1)，表示节点可能面临较高的负载或数据量增长，系统将通过增加缓冲区大小来应对。具体调整公式为skt1＝(1+α×(Jk-Jy1)/JK)×Skc，其中α是调节系数，JK可能是一个归一化因子或所有节点评分的某种聚合值(具体取决于系统设计)，Skc是当前缓冲区大小。If Jk is greater than the first preset threshold (Jy1), it means that the node may face a higher load or data volume growth, and the system will respond by increasing the buffer size. The specific adjustment formula is skt1 = (1 + α × (Jk-Jy1) / JK) × Skc, where α is the adjustment coefficient, JK may be a normalization factor or some aggregate value of all node scores (depending on the system design), and Skc is the current buffer size.

小于第二预设阈值：如果Jk小于第二预设阈值(Jy2)，表示节点当前状态较为空闲，系统可能会减少缓冲区大小以释放资源。具体调整公式为skt2＝(1-α×(Jk-Jy2)/Jy2)×Skc。Less than the second preset threshold: If Jk is less than the second preset threshold (Jy2), it means that the node is currently idle and the system may reduce the buffer size to release resources. The specific adjustment formula is skt2 = (1-α×(Jk-Jy2)/Jy2)×Skc.

调整后的缓冲区大小(skt1或skt2)必须在最小(skmin)和最大(skmax)要求缓冲区大小之间。The adjusted buffer size (skt1 or skt2) must be between the minimum (skmin) and maximum (skmax) required buffer sizes.

为了避免过于频繁的调整，系统还会考虑前一次调整时间点到当前时间点的间隔。如果这个间隔小于设定的最小时间间隔，系统将推迟下一次调整，直到达到最小时间间隔后再进行评估和调整。To avoid too frequent adjustments, the system will also consider the interval between the last adjustment time point and the current time point. If this interval is less than the set minimum time interval, the system will postpone the next adjustment until the minimum time interval is reached before evaluating and adjusting.

综上所述，该多级缓存机制通过综合考虑节点状态(包括数据量、负载和延迟)以及用户地理位置和网络状况，动态调整缓冲区大小，以优化缓存性能和资源利用率。In summary, the multi-level cache mechanism dynamically adjusts the buffer size to optimize cache performance and resource utilization by comprehensively considering the node status (including data volume, load and latency) as well as the user's geographical location and network conditions.

上述技术方案的效果为：通过动态调整缓冲区大小，系统能够更有效地管理缓存资源，减少数据访问时的等待时间，从而降低延迟。在高峰期，通过增加缓冲区大小，系统能够处理更多的并发请求，提高整体的吞吐量。根据节点的实际负载和数据量动态调整缓冲区大小，避免了资源的浪费和过度分配。通过减少不必要的缓存资源使用，可以降低存储和维护成本；通过在不同节点之间动态调整缓冲区大小，可以实现更均衡的负载分布，减少单个节点的压力。The effects of the above technical solution are as follows: by dynamically adjusting the buffer size, the system can manage cache resources more effectively, reduce the waiting time when accessing data, and thus reduce latency. During peak hours, by increasing the buffer size, the system can handle more concurrent requests and improve overall throughput. Dynamically adjusting the buffer size according to the actual load and data volume of the node avoids waste and over-allocation of resources. By reducing unnecessary use of cache resources, storage and maintenance costs can be reduced; by dynamically adjusting the buffer size between different nodes, a more balanced load distribution can be achieved, reducing the pressure on a single node.

本申请提供一种基于互联网的云课堂直播传输系统，所述系统包括：The present application provides an Internet-based cloud classroom live broadcast transmission system, the system comprising:

第一获取模块，用于获取用户参数以及直播活动参数，其中，所述用户参数包括用户的网络状况和数据传输质量，所述直播活动参数包括直播活动的内容类型、平台网络状况、参与人数、第一直播数据；A first acquisition module, used to acquire user parameters and live broadcast activity parameters, wherein the user parameters include the user's network status and data transmission quality, and the live broadcast activity parameters include the content type of the live broadcast activity, the platform network status, the number of participants, and the first live broadcast data;

第一分配模块，用于根据所述直播活动的内容类型、平台网络状况以及参与人数，分配所述直播活动的第一宽带资源；A first allocation module, configured to allocate a first broadband resource for the live broadcast activity according to the content type, platform network status, and number of participants of the live broadcast activity;

传输模块，用于基于传输策略集，将第一直播数据从第一设备集传输至第二设备集，其中，所述传输策略集包括多个不同的传输策略，所述第一设备集包括一个或多个第一设备，所述第二设备集包括一个或多个第二设备；A transmission module, configured to transmit the first live broadcast data from the first device set to the second device set based on a transmission strategy set, wherein the transmission strategy set includes a plurality of different transmission strategies, the first device set includes one or more first devices, and the second device set includes one or more second devices;

调整模块，用于根据用户的网络状况和数据传输质量动态调整各传输策略，其中，所述传输策略包括智能选择数据传输链路、动态调整媒体质量参数、以及动态调整缓冲区大小以及相邻两个调整的时间间隔。The adjustment module is used to dynamically adjust various transmission strategies according to the user's network status and data transmission quality, wherein the transmission strategy includes intelligently selecting a data transmission link, dynamically adjusting media quality parameters, and dynamically adjusting the buffer size and the time interval between two adjacent adjustments.

在一些实施例中，所述第一分配模块，包括：In some embodiments, the first allocation module includes:

第一模型建立单元，用于通过历史数据，建立第一宽带资源预测模型；所述历史数据包括直播活动的内容类型、峰值人数、平均在线人数、平台网络状况、同一时间段的直播活动类型和总量以及总参与人数；A first model building unit is used to build a first broadband resource prediction model through historical data; the historical data includes the content type of live broadcast activities, peak number of people, average number of online people, platform network status, type and total amount of live broadcast activities in the same time period, and total number of participants;

第一预测单元，用于根据t时刻的实时数据，通过宽带资源预测模型，预测对应t+1时刻直播活动的第一宽带资源。The first prediction unit is used to predict the first broadband resource corresponding to the live broadcast activity at time t+1 according to the real-time data at time t through the broadband resource prediction model.

在一些实施例中，所述传输策略集包括：In some embodiments, the transmission strategy set includes:

对多个类型的第一直播数据进行实时性评分；根据实时性评分获得传输优先级；根据传输优先级设置传输队列；所述第一直播数据的类型包括文件数据、视频数据、音频数据和/或书写数据；Performing real-time scoring on multiple types of first live broadcast data; obtaining a transmission priority according to the real-time scoring; setting a transmission queue according to the transmission priority; the types of the first live broadcast data include file data, video data, audio data and/or written data;

响应于文件数据的变化，第一设备仅传输文件数据的变化部分至第二电子设备；In response to a change in the file data, the first device transmits only the changed portion of the file data to the second electronic device;

根据视频数据、音频数据或交互数据的刷新频率，设置对应类型的第一直播数据类型的传输频率；According to the refresh frequency of the video data, the audio data or the interactive data, the transmission frequency of the first live data type of the corresponding type is set;

对网络环境进行全面评估，并智能选择数据传输链路；根据网络状况、用户信息以及环境信息，动态调整媒体质量参数；Comprehensively evaluate the network environment and intelligently select data transmission links; dynamically adjust media quality parameters based on network conditions, user information, and environmental information;

建立多级缓存机制，根据用户地理位置、网络状况以及节点评分，动态调整缓冲区大小以及相邻两个调整的时间间隔。A multi-level cache mechanism is established to dynamically adjust the buffer size and the time interval between two adjacent adjustments based on the user's geographic location, network conditions, and node scores.

上述技术方案的工作原理和效果与本申请方法实施例中相同，在此不做赘述。The working principle and effect of the above technical solution are the same as those in the embodiment of the method of the present application and will not be described in detail here.

本申请从使用目的上，效能上，进步及新颖性等观点进行阐述，已符合专利法所强调的功能增进及使用要件，本申请以上的说明书及说明书附图，仅为本申请的较佳实施例而已，并非以此局限本申请，因此，凡一切与本申请构造，装置，特征等近似、雷同的，即凡依本申请专利申请范围所作的等同替换或修饰等，皆应属本申请的专利申请保护的范围之内。This application is explained from the perspectives of purpose of use, effectiveness, progress and novelty, and has met the functional enhancement and usage requirements emphasized by the Patent Law. The above description and drawings of this application are only the preferred embodiments of this application, and are not intended to limit this application. Therefore, all structures, devices, features, etc. that are similar or identical to this application, that is, all equivalent replacements or modifications made in accordance with the scope of the patent application of this application, should fall within the scope of protection of the patent application of this application.

Claims (10)

Translated fromChinese

1.一种基于互联网的云课堂直播传输方法，其特征在于，所述方法包括：1. A cloud classroom live transmission method based on the Internet, characterized in that the method comprises:获取用户参数以及直播活动参数，其中，所述用户参数包括用户的网络状况和数据传输质量，所述直播活动参数包括直播活动的内容类型、平台网络状况、参与人数、第一直播数据；Acquire user parameters and live broadcast activity parameters, wherein the user parameters include the user's network status and data transmission quality, and the live broadcast activity parameters include the content type of the live broadcast activity, the platform network status, the number of participants, and the first live broadcast data;根据所述直播活动的内容类型、平台网络状况以及参与人数，分配所述直播活动的第一宽带资源；Allocate a first broadband resource for the live broadcast activity according to the content type, platform network status, and number of participants of the live broadcast activity;基于传输策略集，将第一直播数据从第一设备集传输至第二设备集，其中，所述传输策略集包括多个不同的传输策略，所述第一设备集包括一个或多个第一设备，所述第二设备集包括一个或多个第二设备；Based on a transmission strategy set, transmitting the first live broadcast data from a first device set to a second device set, wherein the transmission strategy set includes a plurality of different transmission strategies, the first device set includes one or more first devices, and the second device set includes one or more second devices;根据用户的网络状况和数据传输质量动态调整各传输策略，其中，所述传输策略包括智能选择数据传输链路、动态调整媒体质量参数、以及动态调整缓冲区大小以及相邻两个调整的时间间隔。Dynamically adjust each transmission strategy according to the user's network status and data transmission quality, wherein the transmission strategy includes intelligently selecting a data transmission link, dynamically adjusting media quality parameters, and dynamically adjusting a buffer size and a time interval between two adjacent adjustments.2.根据权利要求1所述的方法，其特征在于，所述根据所述直播活动的内容类型、平台网络状况以及参与人数，分配所述直播活动的第一宽带资源；包括：2. The method according to claim 1, characterized in that the first broadband resource of the live broadcast activity is allocated according to the content type, platform network status and number of participants of the live broadcast activity; comprising:通过历史数据，建立第一宽带资源预测模型；所述历史数据包括直播活动的内容类型、峰值人数、平均在线人数、平台网络状况、同一时间段的直播活动类型和总量以及总参与人数；Establishing a first broadband resource prediction model through historical data; the historical data includes content type of live broadcast activities, peak number of people, average number of online people, platform network status, type and total amount of live broadcast activities in the same time period, and total number of participants;根据t时刻的实时数据，通过宽带资源预测模型，预测对应t+1时刻直播活动的第一宽带资源。According to the real-time data at time t, the first broadband resource corresponding to the live broadcast activity at time t+1 is predicted through the broadband resource prediction model.3.根据权利要求1所述的方法，其特征在于，所述传输策略集包括：3. The method according to claim 1, wherein the transmission strategy set comprises:对多个类型的第一直播数据进行实时性评分；根据实时性评分获得传输优先级；根据传输优先级设置传输队列；所述第一直播数据的类型包括文件数据、视频数据、音频数据和/或书写数据；Performing real-time scoring on multiple types of first live broadcast data; obtaining a transmission priority according to the real-time scoring; setting a transmission queue according to the transmission priority; the types of the first live broadcast data include file data, video data, audio data and/or written data;响应于文件数据的变化，第一设备仅传输文件数据的变化部分至第二电子设备；In response to a change in the file data, the first device transmits only the changed portion of the file data to the second electronic device;根据视频数据、音频数据或交互数据的刷新频率，设置对应类型的第一直播数据类型的传输频率；According to the refresh frequency of the video data, the audio data or the interactive data, the transmission frequency of the first live data type of the corresponding type is set;对网络环境进行全面评估，并智能选择数据传输链路；根据网络状况、用户信息以及环境信息，动态调整媒体质量参数；Comprehensively evaluate the network environment and intelligently select data transmission links; dynamically adjust media quality parameters based on network conditions, user information, and environmental information;建立多级缓存机制，根据用户地理位置、网络状况以及节点评分，动态调整缓冲区大小以及相邻两个调整的时间间隔。A multi-level cache mechanism is established to dynamically adjust the buffer size and the time interval between two adjacent adjustments based on the user's geographic location, network conditions, and node scores.4.根据权利要求3所述的方法，其特征在于，所述对网络环境进行全面评估，并智能选择数据传输链路；包括：4. The method according to claim 3, characterized in that the comprehensive evaluation of the network environment and the intelligent selection of the data transmission link include:根据用户地理位置，通过网络拓扑结构获得发送端和接收端的多条通信链路；According to the user's geographical location, multiple communication links between the sender and the receiver are obtained through the network topology;根据t时刻的链路第一评分、地理距离以及链路负载，通过约束条件，预测t+1时刻的可用链路。According to the first link score, geographical distance and link load at time t, the available links at time t+1 are predicted through constraints.5.根据权利要求4所述的方法，其特征在于，所述根据t时刻的链路第一评分、地理距离以及链路负载，通过约束条件，预测t+1时刻的可用链路，包括：5. The method according to claim 4, characterized in that the predicting of the available links at time t+1 according to the first link score, geographical distance and link load at time t and through constraints comprises:收集可用链路的实时性能指标，其中，性能指标包括丢包率、丢包残差、丢包率残差变化率、实时带宽、延迟时间以及链路可靠性；Collect real-time performance indicators of available links, including packet loss rate, packet loss residual, packet loss rate residual change rate, real-time bandwidth, delay time, and link reliability;通过机器学习模型，输出t时刻的链路第一评分；Through the machine learning model, the first link score at time t is output;利用时间序列分析预测t+1时刻的链路性能指标，并结合t时刻的链路第一评分预测t+1时刻的第一评分；Use time series analysis to predict the link performance index at time t+1, and combine the first link score at time t to predict the first score at time t+1;通过链路的地理距离和负载预测，计算t+1时刻的链路第二评分；Calculate the second link score at time t+1 based on the geographical distance and load prediction of the link;定义约束条件，所述约束条件包括最大可接受的丢包率、最小带宽要求、最大延迟以及负载均衡；defining constraints, including maximum acceptable packet loss rate, minimum bandwidth requirement, maximum delay, and load balancing;根据t+1时刻链路的第二评分和约束条件，预测t+1时刻的可用链路；According to the second score and constraint condition of the link at time t+1, predict the available link at time t+1;根据业务的冗余需求，选择多条可用链路；并选择第二评分最高的可用链路作为主链路；通过传输队列中的数据量和链路负载，分配传输队列中的数据到不同的可用链路。According to the redundancy requirements of the business, multiple available links are selected; and the available link with the second highest score is selected as the main link; according to the amount of data in the transmission queue and the link load, the data in the transmission queue is distributed to different available links.6.根据权利要求5所述的方法，其特征在于，所述方法还包括：6. The method according to claim 5, characterized in that the method further comprises:建立闭环反馈机制，持续监测链路性能，根据实际性能调整评分模型和预测算法的参数；Establish a closed-loop feedback mechanism to continuously monitor link performance and adjust the parameters of the scoring model and prediction algorithm based on actual performance;根据历史数据和新出现的网络状况，自适应地调整约束条件和评分权重；引入异常检测算法，识别并隔离网络中的异常行为和/或故障链路。Adaptively adjust constraints and scoring weights based on historical data and emerging network conditions; introduce anomaly detection algorithms to identify and isolate abnormal behaviors and/or faulty links in the network.7.根据权利要求5所述的方法，其特征在于，所述通过传输队列中的数据量和链路负载，分配传输队列中的数据到不同的可用链路；包括：7. The method according to claim 5, characterized in that the step of allocating data in the transmission queue to different available links according to the amount of data in the transmission queue and the link load comprises:将同一优先级的数据分成不同的数据块；通过哈希函数来确定数据块的边界；确保相同内容的数据块有相同的哈希值；Divide data of the same priority level into different data blocks; determine the boundaries of data blocks through hash functions; ensure that data blocks with the same content have the same hash value;将优先级最高的数据块分配给主链路，直到达到预设的负载阈值；Assign the highest priority data blocks to the primary link until the preset load threshold is reached;将剩余数据块根据剩余选择链路的第二评分，以及对应链路的负载进行依次分配。The remaining data blocks are distributed in sequence according to the second scores of the remaining selected links and the loads of the corresponding links.8.根据权利要求5所述的方法，其特征在于，所述根据网络状况，用户信息以及环境信息，动态调整媒体质量参数，包括：8. The method according to claim 5, wherein the step of dynamically adjusting the media quality parameters according to network conditions, user information and environmental information comprises:收集用户端传输链路第一评分、用户信息、直播时间、环境信息以及媒体质量参数；所述用户信息包括用户设备信息、设备电池寿命以及电量、地理位置以及偏好；所述媒体质量参数包括音频质量、媒体清晰度以及交互响应速度；Collecting the first score of the user-side transmission link, user information, live broadcast time, environmental information and media quality parameters; the user information includes user device information, device battery life and power, geographic location and preferences; the media quality parameters include audio quality, media clarity and interactive response speed;通过历史训练数据，训练深度学习模型，学习不同条件下媒体质量与用户满意度之间的关系；Through historical training data, deep learning models are trained to learn the relationship between media quality and user satisfaction under different conditions;根据实时网络状况、用户信息、直播时间和环境信息，利用深度学习模型，预测最优媒体质量参数。Based on real-time network conditions, user information, live broadcast time and environmental information, deep learning models are used to predict optimal media quality parameters.9.根据权利要求5所述的方法，其特征在于，所述建立多级缓存机制，根据用户地理位置网络状况、以及节点评分，动态调整缓冲区大小，包括：9. The method according to claim 5, characterized in that the establishment of a multi-level cache mechanism dynamically adjusts the buffer size according to the user's geographical location, network status, and node score, including:构建分布式缓存网络；所述分布式缓存网络包括多个节点；并获得节点评分；Constructing a distributed cache network; the distributed cache network includes a plurality of nodes; and obtaining node scores;根据节点评分，调整缓冲区的大小以及相邻两次缓冲区大小调整的时间间隔。According to the node score, the buffer size and the time interval between two adjacent buffer size adjustments are adjusted.10.一种基于互联网的云课堂直播传输系统，其特征在于，所述系统包括：10. A cloud classroom live transmission system based on the Internet, characterized in that the system includes:第一获取模块，用于获取用户参数以及直播活动参数，其中，所述用户参数包括用户的网络状况和数据传输质量，所述直播活动参数包括直播活动的内容类型、平台网络状况、参与人数、第一直播数据；A first acquisition module, used to acquire user parameters and live broadcast activity parameters, wherein the user parameters include the user's network status and data transmission quality, and the live broadcast activity parameters include the content type of the live broadcast activity, the platform network status, the number of participants, and the first live broadcast data;第一分配模块，根据所述直播活动的内容类型、平台网络状况以及参与人数，分配所述直播活动的第一宽带资源；A first allocation module allocates a first broadband resource for the live broadcast activity according to the content type, platform network status, and number of participants of the live broadcast activity;传输模块，用于基于传输策略集，将第一直播数据从第一设备集传输至第二设备集，其中，所述传输策略集包括多个不同的传输策略，所述第一设备集包括一个或多个第一设备，所述第二设备集包括一个或多个第二设备；A transmission module, configured to transmit the first live broadcast data from the first device set to the second device set based on a transmission strategy set, wherein the transmission strategy set includes a plurality of different transmission strategies, the first device set includes one or more first devices, and the second device set includes one or more second devices;调整模块，用于根据用户的网络状况和数据传输质量动态调整各传输策略，其中，所述传输策略包括智能选择数据传输链路、动态调整媒体质量参数、以及动态调整缓冲区大小以及相邻两个调整的时间间隔。The adjustment module is used to dynamically adjust various transmission strategies according to the user's network status and data transmission quality, wherein the transmission strategy includes intelligently selecting a data transmission link, dynamically adjusting media quality parameters, and dynamically adjusting the buffer size and the time interval between two adjacent adjustments.