Method for distributing and scheduling slow live broadcast of articulated naturality web and electronic equipment

Abstract

The invention discloses an articulated naturality web slow live broadcast distribution scheduling method and electronic equipment, and belongs to the technical field of computers. The method comprises the following steps: determining a target edge cloud access node through an intelligent scheduling decision engine; judging whether the target edge cloud access node is the same as an original edge cloud access node or not, if the target edge cloud access node is a reselected node, initiating an edge cloud access node switching command to terminal equipment, and executing switching of the target edge cloud access node; and the second-level streaming media distribution platform corresponding to the target edge cloud access node initiates a stream pulling request to the target edge cloud access node, and stream pulling is realized by adopting an on-demand back-to-source stream pulling mode. According to the invention, on-demand stream pulling and backflow of the live stream are realized based on the target edge cloud access node, the access nodes are dynamically allocated, the live stream is distributed and prefetched on demand, load balancing is realized, resource consumption is reduced, and distribution efficiency is improved.

Description

Technical Field

[0001] This application belongs to the field of computer technology, and particularly relates to a method and an electronic device for slow live broadcast distribution scheduling in a visual network. Background Art

[0002] Slow live broadcast, as an emerging live broadcast form, refers to using live broadcast devices to record a real scene in real time for a long time and presenting it to the audience in its most original state. This live broadcast form is significantly different from traditional fast-paced live broadcasts. Slow live broadcast shows the real-time state of an event or a scene in the most authentic way through a fixed camera position, providing the audience with a new sense of participation and immersive experience.

[0003] The characteristics of slow live broadcast lie in its continuity and authenticity. It can continuously record and transmit information, enabling the audience to feel the passage of time and the progress of events, thus generating a feeling of being present at the scene synchronously. This live broadcast form has been widely applied in fields such as news reporting, natural landscape display, and security monitoring; with the development of technology, slow live broadcast is gradually becoming a normalized dissemination method. It attracts a specific audience group with its low production cost and "unadulterated" real reporting characteristics.

[0004] Existing slow live broadcast distribution platforms have the following problems: 1. The edge cloud access nodes for device access are fixed. After selecting a node for the first access scheduling, it remains unchanged subsequently; 2. The edge cloud streaming media platform and the live broadcast distribution platform for device access are integrated, and it is impossible to perform transcoding and distribution optimization for slow live broadcast streams separately; 3. The scheduling strategies for device access and distribution are relatively single, generally only selecting based on the location of the device, without considering the location and load of the streaming media platform for distribution.

[0005] In view of the above problems, this application proposes a method and an electronic device for slow live broadcast distribution scheduling in a visual network. Summary of the Invention

[0006] To solve the deficiencies of the existing technology, this application provides a method and an electronic device for slow live broadcast distribution scheduling in a visual network, which solve the problems in the existing technology such as fixed edge cloud access nodes, inability to perform transcoding and distribution optimization for slow live broadcast streams separately, and lack of consideration for load balancing.

[0007] The technical effects to be achieved by this application are realized through the following solutions: In a first aspect, this application provides a method for slow live broadcast distribution scheduling in a visual network, and the method includes: Determine a target edge cloud access node through an intelligent scheduling decision engine; Determine whether the target edge cloud access node is the same as the original edge cloud access node, and if the target edge cloud access node is the reselected node, initiate an edge cloud access node switching command to the terminal device to execute the switching of the target edge cloud access node; The secondary streaming media distribution platform corresponding to the target edge cloud access node initiates a stream pulling request to the target edge cloud access node, and implements stream pulling by adopting an on-demand back-to-source stream pulling mode.

[0008] In some embodiments, determining the target edge cloud access node by the intelligent scheduling decision engine includes: Through the multi-dimensional parameter collection module, the location of the terminal device, the edge cloud access node load index, the network quality index and the transcoding capability index of the secondary streaming media distribution platform are obtained in real time; Calculate dynamic quality scores based on edge cloud access node load index, network quality index, and secondary streaming media distribution platform transcoding capability index; Based on the location of the terminal device and the dynamic quality score, a target edge cloud access node is determined.

[0009] In some embodiments, the quality dynamic score is calculated using the following formula: QoS = Σ(α Ln+β Bn+γ*Dn), Among them, QoS represents the dynamic quality score, Ln represents the edge cloud access node load index, Bn represents the network quality index, Dn represents the transcoding capability index of the secondary streaming media distribution platform, α, β, and γ represent coefficient parameters and α+β+γ=1.

[0010] In some embodiments, determining a target edge cloud access node based on the location of the terminal device and the dynamic quality score includes: Determine a candidate node set, wherein the candidate node set includes a plurality of edge cloud access nodes to be selected; The first-level candidate pool is determined through the first-level screening, wherein the first-level screening is the nodes whose geographical distance to the terminal device is less than a preset distance and whose network delay is less than a preset delay; The candidate node list is determined by second-level sorting, wherein the second-level sorting is to sort the nodes according to the dynamic quality score corresponding to each node; The target edge cloud access node is determined through the third-level optimization, wherein the third-level optimization indicators include cost indicators, stability indicators and / or load balancing indicators.

[0011] In some embodiments, the initiating an edge cloud access node switching command to a terminal device to execute the switching of the target edge cloud access node includes: Obtaining address information corresponding to the target edge cloud access node; The server determines whether the terminal device is online. If the terminal device is online, a switch address message is sent to the terminal device. After receiving the switching address message, the terminal device parses the switching address message according to a predefined format to obtain the address information and related configuration parameters of the target edge cloud access node.

[0012] In some embodiments, it also includes: After the terminal device obtains the address information and related configuration parameters of the target edge cloud access node, it updates its own streaming media platform address configuration; The terminal device stops connecting to the current streaming platform and connects to the new server streaming platform according to the updated streaming platform address configuration.

[0013] In some embodiments, the secondary streaming media distribution platform corresponding to the target edge cloud access node initiates a stream pulling request to the target edge cloud access node, and implements stream pulling using an on-demand back-to-source stream pulling mode, including: The user's viewing behavior data is collected in real time through APP embedding probes. The viewing behavior data includes: number of clicks, viewing time, and playback operation events, and a multi-dimensional feature vector is constructed. Based on the multi-dimensional feature vector, a prediction model is trained to output a live stream prediction score; According to the live stream prediction score, determine whether to trigger the full pre-fetch strategy or the partial pre-fetch strategy; Among them, the full pre-fetch strategy is: if the live stream prediction score is greater than the live stream threshold, the live stream corresponding to the live stream prediction score is completely pre-fetched and cached to the edge cloud access node; The partial prefetching strategy is: if the live stream prediction score is less than or equal to the live stream threshold, only the key frames and metadata corresponding to the live stream prediction are prefetched and cached to the edge cloud access node.

[0014] In some embodiments, it also includes: The user initiates a slow live broadcast request from the APP side, and a CDN cache check is performed based on the slow live broadcast request to determine whether the CDN cache is hit: If the CDN cache is hit, the content is directly extracted from the CDN cache and the cache stream is returned to the user to complete the request response; If the CDN cache is not hit, the on-demand back-to-origin mechanism is triggered and the back-to-origin process begins.

[0015] In some embodiments, the back-to-source process includes: If the CDN cache is not hit, a back-to-source request is sent to the secondary streaming media distribution platform. The secondary streaming media distribution platform checks whether the live stream exists. If so, the live stream is returned. If the live stream does not exist, a stream pulling request is sent to the edge cloud access node corresponding to the terminal device to obtain the live stream requested by the user; The edge cloud access node of the terminal device performs an existence check on the requested live stream; If the live stream exists, an RTMP communication link is established, and the live stream is transmitted to the user through this RTMP communication link to complete the playback request response; If the live stream does not exist, an error message is returned to the user, indicating that the content cannot be obtained.

[0016] In a second aspect, the present application provides an electronic device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the method described in any one of the foregoing is implemented.

[0017] Through the method and electronic device for slow live broadcast distribution scheduling of the visual network provided by the present application, the method determines a suitable target edge cloud access node through an intelligent scheduling decision engine, and then updates the target edge cloud access node to the terminal device, so that on-demand stream pulling and stream return of the live stream can be realized based on the target edge cloud access node, realizing dynamic allocation of access nodes and on-demand distribution and prefetching of live streams, achieving load balancing, reducing resource consumption, and improving distribution efficiency. Description of the Drawings

[0018] In order to more clearly illustrate the embodiments of the present application or the existing technical solutions, the following will briefly introduce the drawings required for use in the description of the embodiments or the existing technical solutions. Obviously, the drawings in the following description are only some embodiments recorded in the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 It is a flowchart of the method for slow live broadcast distribution scheduling of the visual network in an embodiment of the present application; Figure 2 It is a schematic diagram of a three-layer decision-making mechanism of the method for slow live broadcast distribution scheduling of the visual network in an embodiment of the present application; Figure 3 It is a schematic diagram of the update of the edge cloud access node of the method for slow live broadcast distribution scheduling of the visual network in an embodiment of the present application; Figure 4 It is a schematic diagram of the prefetching of the live stream of the method for slow live broadcast distribution scheduling of the visual network in an embodiment of the present application; Figure 5 It is a schematic diagram of the origin-pulling stream of the method for slow live broadcast distribution scheduling of the visual network in an embodiment of the present application; Figure 6Schematic block diagram of an electronic device in an embodiment of the present application. Detailed implementation manners

[0020] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with specific embodiments and the corresponding drawings. Apparently, the described embodiments are only a part rather than all of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without making creative efforts shall fall within the scope of protection of the present application.

[0021] It should be noted that unless otherwise defined, the technical terms or scientific terms used in one or more embodiments of the present application should have the ordinary meaning understood by those of ordinary skill in the art to which the present application belongs. The terms "first", "second" and similar words used in one or more embodiments of the present application do not denote any order, quantity or importance, but are only used to distinguish different components. Words such as "including" or "comprising" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. Words such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right", etc. are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0022] Currently, the mainstream device scheduling solutions generally adopt a centralized cloud architecture, including the following functions: 1) Device access layer When the device is first connected to the network, it obtains the cloud server address from the central scheduling node; 2) Resource scheduling layer Adopt an artificial pre-configuration strategy to fixedly allocate devices to the specified cloud server; 3) Distribution service layer Distribute the video stream of the camera through a streaming media platform + CDN.

[0023] The present application proposes a method for slow live broadcast distribution scheduling in a video networking, mainly adopting the following concept: 1. When starting a live broadcast: According to the location of the device, the load of the currently accessed edge cloud node and the network bandwidth occupancy, the bandwidth, latency, packet loss rate of the edge cloud node dynamically detected by the device, the load of the streaming media platform and the bandwidth, latency, packet loss rate to each edge cloud node, calculate and select the ones with the highest scores through these parameters: edge cloud access nodes, secondary streaming media distribution platforms; 2. If the reselected edge cloud access point changes, send a command to switch the edge cloud to the device terminal, and the device terminal will initiate a streaming push to the new edge cloud; 3. The secondary streaming media distribution platform sends a pull stream request to the edge cloud, adopting the on-demand backhaul pull stream mode, that is: only when the user plays this stream, will the backhaul pull stream be triggered to maximize the saving of bandwidth and computing resources.

[0024] The following will describe various non-limiting embodiments of the present application in detail with reference to the accompanying drawings.

[0025] First, refer to Figure 1 , and describe the method for video networking slow live distribution scheduling of the present application in detail.

[0026] The present application provides a method for video networking slow live distribution scheduling, and the method includes: S1: Determine the target edge cloud access node through the intelligent scheduling decision engine; S2: Determine whether the target edge cloud access node is the same as the original edge cloud access node. If the target edge cloud access node is a reselected node, send an edge cloud access node switching command to the terminal device and perform the switching of the target edge cloud access node; S3: The secondary streaming media distribution platform corresponding to the target edge cloud access node sends a pull stream request to the target edge cloud access node and realizes the pull stream by adopting the on-demand backhaul pull stream mode.

[0027] In some embodiments, the determining the target edge cloud access node through the intelligent scheduling decision engine includes: Obtain the location of the terminal device, the load index of the edge cloud access node, the network quality index, and the transcoding ability index of the secondary streaming media distribution platform in real time through the multi-dimensional parameter acquisition module; Calculate the quality dynamic score based on the load index of the edge cloud access node, the network quality index, and the transcoding ability index of the secondary streaming media distribution platform; Determine the target edge cloud access node based on the location of the terminal device and the quality dynamic score.

[0028] Exemplarily, different parameters can correspond to different proportions. For the edge cloud node load index, for example, the dynamic weight ratio of CPU / memory / bandwidth utilization is 30%; for the network quality index, for example, the comprehensive score of delay / packet loss rate / jitter accounts for 40%; for the transcoding ability index of the distribution platform, for example, it accounts for 30%; this is exemplary, and the parameter ratio can be determined according to the actual situation.

[0029] In some embodiments, the following formula is used to calculate the quality dynamic score: QoS = Σ(αLn+β Bn + γ * Dn), where QoS represents the quality dynamic score, Ln represents the load index of the edge cloud access node, Bn represents the network quality index, Dn represents the transcoding ability index of the secondary streaming media distribution platform, and α, β, and γ represent coefficient parameters and α + β + γ = 1.

[0030] In some embodiments, determining a target edge cloud access node based on the location of the terminal device and the quality dynamic score includes: Determining a candidate node set, where the candidate node set includes multiple edge cloud access nodes to be selected; Determining a primary candidate pool through a first-level screening, where the first-level screening is for nodes whose geographical distance from the terminal device is less than a preset distance and whose network latency is less than a preset time delay; Determining a candidate node list through a second-level sorting, where the second-level sorting is to sort the nodes according to the quality dynamic score corresponding to each node; Determining the target edge cloud access node through a third-level optimization, where the metrics for the third-level optimization include cost metrics, stability metrics, and / or load balancing metrics.

[0031] Exemplarily, the decision tree model is as Figure 2 shown. Determine the candidate node set, determine the primary candidate pool through the first-level screening, determine the primary candidate pool through the geographical distance (such as nodes with a distance < 200KM) and network reachability (nodes with a latency < 150ms). Here, the distance and latency are exemplary and can be adjusted and determined according to specific situations; determine the candidate node list through the second-level sorting, sort the nodes according to the quality dynamic score (i.e., QoS score) corresponding to each node, such as the Top5 node list (the top five nodes), and determine the target edge cloud access node through the third-level optimization. For example, according to cost priority, select the node with the lowest cost per unit bandwidth. For example, according to stability priority, select the node with the highest historical availability rate. For example, according to load balancing, select the node with the lowest regional load.

[0032] In some embodiments, the sending an edge cloud access node switching command to the terminal device and performing the switching of the target edge cloud access node includes: Obtaining the address information corresponding to the target edge cloud access node; The server determines whether the terminal device is online. If the terminal device is online, the switching address message is sent to the terminal device; After receiving the switching address message, the terminal device parses the switching address message according to a predefined format to obtain the address information and related configuration parameters of the target edge cloud access node.

[0033] In some embodiments, it further includes: After the terminal device obtains the address information and related configuration parameters of the target edge cloud access node, it updates the address configuration of its own streaming media platform; The terminal device stops connecting to the current streaming media platform and connects to the new server streaming media platform according to the updated streaming media platform address configuration.

[0034] Exemplarily, reference can be made to Figure 3 , the server prepares a switch address message, checks whether the terminal device is online. If the device is online, the server sends the switch address message. The terminal device (such as a home camera device) receives the message, parses the message and obtains the new streaming media platform address, the terminal device updates the streaming media platform address configuration, and the terminal device uses the new address to connect to the streaming media platform.

[0035] Specifically, the server initiates migration preparation: calculates the best edge cloud access site (i.e., the target edge cloud access node) according to the decision engine, and queries the dictionary table to obtain the address information of edge access.

[0036] Terminal device online status check: The server grasps the online status of the terminal device in real time through a regular polling mechanism or an active reporting mechanism of the terminal device. After preparing the switch address message, the server first confirms whether the target home camera device is in an online state, because only an online terminal device can receive and execute subsequent migration instructions.

[0037] Migration instruction sending (when the terminal device is online): If the server confirms that the terminal device is online, it sends the encapsulated switch address message to the terminal device (such as a home camera device) through the reliable message transmission protocol with a message retransmission mechanism, such as the MQTT protocol, via the TCP / IP-based long connection communication channel established with the terminal device. This process ensures that the message can be accurately delivered to the terminal device.

[0038] Terminal device receives and parses the message: The terminal device (such as a home camera device) listens for messages sent by the server in real time while maintaining a long connection with the server. When receiving the switch address message, the terminal device first checks the integrity and legality of the message to ensure that the message has not been tampered with and the format is correct. After passing the verification, the terminal device parses the message content according to the predefined format and extracts the new server streaming media platform address and related configuration parameters.

[0039] The terminal device updates the address configuration and connects to the new platform: After the terminal device extracts the new address and other information, it updates its own streaming platform address configuration. Subsequently, the terminal device stops connecting to the current streaming platform and tries to connect to the new server streaming platform based on the new address. During the connection process, the terminal device automatically configures network parameters such as port number and protocol to adapt to the requirements of the new platform.

[0040] Server recording and subsequent processing (when the terminal device is offline): If the server checks and finds that the terminal device is offline, it records the switch address message and waits for the terminal device to come online. When the terminal device comes online, the server sends the previously recorded switch address message to the terminal device. The subsequent process is the same as the processing process after the terminal device receives the message when it is online, that is, the terminal device receives and parses the message, updates the address configuration and connects to the new platform.

[0041] In some embodiments, the secondary streaming media distribution platform corresponding to the target edge cloud access node initiates a stream pulling request to the target edge cloud access node, and implements stream pulling using an on-demand back-to-source stream pulling mode, including: The user's viewing behavior data is collected in real time through APP embedding probes. The viewing behavior data includes: number of clicks, viewing time, and playback operation events, and a multi-dimensional feature vector is constructed. Based on the multi-dimensional feature vector, a prediction model is trained to output a live stream prediction score; According to the live stream prediction score, determine whether to trigger the full pre-fetch strategy or the partial pre-fetch strategy; Among them, the full pre-fetch strategy is: if the live stream prediction score is greater than the live stream threshold, the live stream corresponding to the live stream prediction score is completely pre-fetched and cached to the edge cloud access node; The partial prefetching strategy is: if the live stream prediction score is less than or equal to the live stream threshold, only the key frames and metadata corresponding to the live stream prediction are prefetched and cached to the edge cloud access node.

[0042] For example, Figure 4 As shown, live stream prefetching is achieved through the following steps: The behavior analysis engine collects data: It collects user viewing behavior data through APP embedding probes, including: number of clicks, viewing time, playback operation events, and constructs a multi-dimensional feature vector.

[0043] Generate prediction model: train the prediction model based on the user behavior characteristics output by the behavior analysis engine; pre-fetch decision execution: call the prediction model interface based on the user's real-time behavior data and output the potential hotspot flow prediction score.

[0044] Pre-fetch score judgment: Determine whether to trigger full pre-fetch or partial pre-fetch strategy based on the score of the live stream; Full pre-fetch to edge nodes: If the live stream score is higher than the threshold, "Full pre-fetch to edge nodes" is executed to completely pre-fetch the predicted potential hotspot stream and cache it to the edge node; Partial prefetching: If the live stream score does not reach the threshold, "Prefetch key frames only" is executed, and only video key frames (I frames) and metadata are prefetched.

[0045] Update cache metadata: Regardless of whether full prefetching or key frame prefetching is performed, cache metadata is updated to record information such as the storage location, type, and priority of the prefetched content to ensure the consistency and traceability of cache data.

[0046] Waiting for user requests: After completing pre-fetching and updating cache metadata, the system enters a waiting state. When the user actually initiates a request, it responds quickly directly from the edge node cache, improving content loading efficiency.

[0047] In some embodiments, it also includes: The user initiates a slow live broadcast request from the APP side, and a CDN cache check is performed based on the slow live broadcast request to determine whether the CDN cache is hit: If the CDN cache is hit, the content is directly extracted from the CDN cache and the cache stream is returned to the user to complete the request response; If the CDN cache is not hit, the on-demand back-to-origin mechanism is triggered and the back-to-origin process begins.

[0048] In some embodiments, the back-to-source process includes: If the CDN cache is not hit, a back-to-source request is sent to the secondary streaming media distribution platform. The secondary streaming media distribution platform checks whether the live stream exists. If so, the live stream is returned. If the live stream does not exist, a stream pull request is sent to the edge cloud access node corresponding to the terminal device to obtain the live stream requested by the user; The edge cloud access node of the terminal device performs an existence check on the requested live stream; If the live stream exists, an RTMP communication link is established, and the live stream is transmitted to the user through the RTMP communication link to complete the playback request response; If the live stream does not exist, an error message is returned to the user, indicating that the content cannot be obtained.

[0049] For example, Figure 5 As shown, the back-to-source streaming is triggered based on the user's actual viewing behavior: 1) User playback request trigger: The user initiates a slow live broadcast playback request from the APP side, and the system receives and processes the request as the starting point of the process execution.

[0050] 2) CDN cache check: Check the CDN cache for the content requested by the user to determine if the cache is hit: If the cache is hit, directly extract the content from the CDN cache, return the cache stream to the user, and complete the request response. If the cache is not hit, trigger the on-demand origin return mechanism and enter the subsequent origin return process.

[0051] 3) On-demand origin return: When the CDN cache is not hit, send an origin return request to the distribution streaming media server. The distribution platform checks if the stream exists. If it exists, return the live stream; otherwise, proceed to the next step.

[0052] 4) Pull stream request to the edge cloud of the terminal device: The distribution streaming media server sends a pull stream request to the edge cloud of the terminal device to obtain the live stream requested by the user.

[0053] 5) Processing of the origin pull stream request: The edge cloud of the terminal device performs an existence verification on the requested stream: If the live stream exists, establish an RTMP (Real-Time Messaging Protocol) communication link, and transmit the streaming media content to the user side through this link to complete the playback request response. If the live stream does not exist, return an error message to the user, indicating that the content cannot be obtained.

[0054] Through the method and electronic device for live slow video distribution scheduling provided by this application, this method determines a suitable target edge cloud access node through an intelligent scheduling decision engine, and then updates this target edge cloud access node to the terminal device. Thus, on-demand pull and return of the live stream can be achieved based on this target edge cloud access node, realizing dynamic allocation of access nodes and on-demand distribution and prefetching of the live stream, achieving load balancing, reducing resource consumption, and improving distribution efficiency.

[0055] It should be noted that the method of one or more embodiments of this application can be executed by a single device, such as a computer or a server. The method of this embodiment can also be applied to a distributed scenario, and multiple devices cooperate with each other to complete it. In this case of a distributed scenario, one of these multiple devices can only execute one or more steps of the method of one or more embodiments of this application, and these multiple devices will interact with each other to complete the described method.

[0056] It should be noted that the above description is for specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired results. Additionally, the processes depicted in the figures do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0057] Based on the same inventive concept, corresponding to any of the above-described method embodiments, the present application also discloses an electronic device; Specifically, Figure 6 FIG. shows a schematic hardware structure diagram of an electronic device for a method of slow live broadcast distribution scheduling in a video networking system according to this embodiment. The device may include: a processor 410, a memory 420, an input / output interface 430, a communication interface 440, and a bus 450. Among them, the processor 410, the memory 420, the input / output interface 430, and the communication interface 440 are communicatively connected to each other inside the device through the bus 450.

[0058] The processor 410 may be implemented in a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0059] The memory 420 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 420 may store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of the present application through software or firmware, the relevant program codes are stored in the memory 420 and are called and executed by the processor 410.

[0060] The input / output interface 430 is used to connect to an input / output module to achieve information input and output. The input / output module may be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Among them, the input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0061] The communication interface 440 is used to connect to a communication module (not shown in the figure) to achieve communication interaction between this device and other devices. The communication module can communicate through a wired method (for example, USB, network cable, etc.) or through a wireless method (for example, mobile network, WIFI, Bluetooth, etc.).

[0062] The bus 450 includes a path for transmitting information between various components of the device (for example, the processor 410, the memory 420, the input / output interface 430, and the communication interface 440).

[0063] It should be noted that although the above device only shows the processor 410, the memory 420, the input / output interface 430, the communication interface 440, and the bus 450, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device may also only include the components necessary to implement the solution of the embodiments of the present application, and does not necessarily include all the components shown in the figure.

[0064] The electronic device in the above embodiment is used to implement the corresponding slow live broadcast distribution scheduling method of the visual networking in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0065] Based on the same inventive concept, corresponding to the method in any of the above embodiments, one or more embodiments of the present application also provide a non-transitory computer-readable storage medium. The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the computer to execute the slow live broadcast distribution scheduling method of the visual networking as described in any of the foregoing embodiments.

[0066] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0067] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the method for live slow distribution scheduling of the vision network as described in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0068] Those of ordinary skill in the art should understand that: the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the present application (including the claims) is limited to these examples; within the concept of the present application, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of one or more embodiments of the present application as described above, which are not provided in detail for the sake of brevity.

[0069] In addition, for the sake of simplicity of description and discussion, and in order not to make one or more embodiments of the present application difficult to understand, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. In addition, the device may be shown in block diagram form to avoid making one or more embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which one or more embodiments of the present application are to be implemented (i.e., these details should be fully within the understanding of those skilled in the art). In the case where specific details (such as circuits) are set forth to describe the exemplary embodiments of the present application, it will be apparent to those skilled in the art that one or more embodiments of the present application can be implemented without these specific details or with variations of these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0070] Although the present application has been described in connection with specific embodiments of the present application, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art based on the foregoing description. For example, other memory architectures (such as dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0071] One or more embodiments of the present application are intended to cover all such alternatives, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of the present application shall be included within the protection scope of the present application.

Claims

1. A method for slow live broadcast distribution scheduling in a video networking system, characterized in that The method includes: Determining a target edge cloud access node through an intelligent scheduling decision engine; Judging whether the target edge cloud access node is the same as the original edge cloud access node. If the target edge cloud access node is a newly selected node, an edge cloud access node switching command is sent to the terminal device to perform the switching of the target edge cloud access node; The secondary streaming media distribution platform corresponding to the target edge cloud access node sends a pull stream request to the target edge cloud access node, and realizes pull stream by adopting a pull stream mode of on-demand backhaul; 2. The method for slow live broadcast distribution scheduling of the vision Internet according to claim 1, wherein The determining of the target edge cloud access node through the intelligent scheduling decision engine includes: Real-time obtaining the location of the terminal device, the load index of the edge cloud access node, the network quality index, and the transcoding ability index of the secondary streaming media distribution platform through a multi-dimensional parameter acquisition module; Calculating a quality dynamic score based on the load index of the edge cloud access node, the network quality index, and the transcoding ability index of the secondary streaming media distribution platform; Determining the target edge cloud access node based on the location of the terminal device and the quality dynamic score; 3. The method for slow live broadcast distribution scheduling of the vision Internet according to claim 2, characterized in that, The quality dynamic score is calculated using the following formula: QoS = Σ(α Ln + β Bn + γ * Dn), where QoS represents the quality dynamic score, Ln represents the load index of the edge cloud access node, Bn represents the network quality index, Dn represents the transcoding ability index of the secondary streaming media distribution platform, and α, β, γ represent coefficient parameters and α + β + γ = 1; 4. The method for live slow video distribution scheduling in the vision Internet according to claim 2 or 3, characterized in that, Determining the target edge cloud access node based on the location of the terminal device and the quality dynamic score includes: Determining a candidate node set, where the candidate node set includes multiple edge cloud access nodes to be selected; Determining a primary candidate pool through a first-level screening, where the first-level screening is a node whose geographical distance from the terminal device is less than a preset distance and whose network delay is less than a preset time delay; Determining a candidate node list through a second-level sorting, where the second-level sorting is to sort the nodes according to the quality dynamic score corresponding to each node; Determining the target edge cloud access node through a third-level optimization, where the indicators of the third-level optimization include cost indicators, stability indicators, and / or load balancing indicators; 5. The method for slow live distribution scheduling of the visual networking according to claim 1, wherein The sending of the edge cloud access node switching command to the terminal device to perform the switching of the target edge cloud access node includes: Obtaining the address information corresponding to the target edge cloud access node; The server judges whether the terminal device is online. If the terminal device is online, the switching address message is sent to the terminal device; After receiving the switching address message, the terminal device parses the switching address message according to a predefined format to obtain the address information and related configuration parameters of the target edge cloud access node; 6. The method for slow live broadcast distribution scheduling of the vision Internet according to claim 5, wherein, It also includes: After the terminal device obtains the address information and related configuration parameters of the target edge cloud access node, it updates its streaming media platform address configuration; The terminal device stops connecting to the current streaming media platform and connects to the new server streaming media platform according to the updated streaming media platform address configuration; 7. The method for slow live broadcast distribution scheduling of the vision Internet according to claim 2, wherein The secondary streaming media distribution platform corresponding to the target edge cloud access node sends a pull stream request to the target edge cloud access node, and realizes pull stream by adopting a pull stream mode of on-demand backhaul, including: The user's viewing behavior data is collected in real time through APP embedding probes. The viewing behavior data includes: number of clicks, viewing time, and playback operation events, and a multi-dimensional feature vector is constructed. Based on the multi-dimensional feature vector, a prediction model is trained to output a live stream prediction score; According to the live stream prediction score, determine whether to trigger the full pre-fetch strategy or the partial pre-fetch strategy; Among them, the full pre-fetch strategy is: if the live stream prediction score is greater than the live stream threshold, the live stream corresponding to the live stream prediction score is completely pre-fetched and cached to the edge cloud access node; The partial prefetching strategy is: if the live stream prediction score is less than or equal to the live stream threshold, only the key frames and metadata corresponding to the live stream prediction are prefetched and cached to the edge cloud access node.

8. The method for slow live broadcast distribution scheduling of the vision Internet according to claim 7, characterized in that, Also includes: The user initiates a slow live broadcast request from the APP side, and a CDN cache check is performed based on the slow live broadcast request to determine whether the CDN cache is hit: If the CDN cache is hit, the content is directly extracted from the CDN cache and the cache stream is returned to the user to complete the request response; If the CDN cache is not hit, the on-demand back-to-origin mechanism is triggered and the back-to-origin process begins.

9. The method for slow live broadcast distribution scheduling of the vision Internet according to claim 8, characterized in that, The return-to-source process includes: If the CDN cache is not hit, a back-to-source request is sent to the secondary streaming media distribution platform. The secondary streaming media distribution platform checks whether the live stream exists. If so, the live stream is returned. If the live stream does not exist, a stream pull request is sent to the edge cloud access node corresponding to the terminal device to obtain the live stream requested by the user; The edge cloud access node of the terminal device performs an existence check on the requested live stream; If the live stream exists, an RTMP communication link is established, and the live stream is transmitted to the user through the RTMP communication link to complete the playback request response; If the live stream does not exist, an error message is returned to the user, indicating that the content cannot be obtained.

10. An electronic device, the electronic device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 9 when executing the computer program.

Images