Information processing method and related device

Abstract

The invention discloses an information processing method and a related device, and relates to the field of networks, and the method comprises the following steps: extracting target parameter information from a file request website; wherein the file request website is a website for requesting a playlist file, the file request website carries target parameter information, and the target parameter information is obtained by analyzing a playlist file request sent by a client by an edge node of a first manufacturer; determining a target manufacturer node of which the service performance meets a preset condition based on the target parameter information; and generating a fragment downloading address containing the domain name of the target manufacturer node, and adding the fragment downloading address to the playlist file, so that the client sends a fragment request to the target manufacturer node based on the playlist file. The service quality of the manufacturer node can be ensured.

Description

Technical Field

[0001] The present application relates to the field of network technology, and in particular to an information processing method and related devices. Background Art

[0002] With the explosive growth of live streaming services, video platforms are integrating resources from multiple CDN vendors using converged CDNs (Content Delivery Networks). Existing CDN scheduling relies on internal optimization within a single vendor, leading to overloaded nodes at some vendors due to concentrated traffic and reduced service quality. Summary of the Invention

[0003] In view of the above problems, this application provides an information processing method and related devices to ensure the service quality of the manufacturer node. The specific solution is as follows:

[0004] The first aspect of the present application provides an information processing method, comprising:

[0005] Extracting target parameter information from a file request URL; wherein the file request URL is a URL for requesting a playlist file, and the file request URL carries the target parameter information, the target parameter information being obtained by parsing the playlist file request sent by the client by the edge node of the first manufacturer;

[0006] Determining a target vendor node whose service performance meets a preset condition based on the target parameter information; wherein the target vendor node is an edge node of the first vendor or an edge node of a second vendor, and the first vendor is different from the second vendor;

[0007] Generate a fragment download address containing the domain name of the target manufacturer node, and add the fragment download address to the playlist file, so that the client sends a fragment request to the target manufacturer node based on the playlist file.

[0008] In a possible implementation, determining, based on the target parameter information, a target manufacturer node whose service performance meets a preset condition includes:

[0009] Determine the edge nodes of each manufacturer that match the target parameter information, and calculate the service performance indicators of the matched manufacturer edge nodes;

[0010] Performing a weighted sum operation on the service performance indicator and the corresponding indicator weight value to obtain the decision value of the matched manufacturer edge node;

[0011] The manufacturer edge node corresponding to the decision value being smaller than the preset value is determined as the target manufacturer node whose service performance meets the preset conditions.

[0012] In a possible implementation, determining the edge nodes of each manufacturer that match the target parameter information and calculating the service performance indicators of the matched manufacturer edge nodes includes:

[0013] Determine each manufacturer edge node under the target area, target operator and target live stream identifier, and obtain the matched manufacturer edge node;

[0014] For each matched manufacturer edge node, a first service performance indicator within a first preset time period is obtained, and based on the number of times the target event occurs within the first preset time period, a second service performance indicator corresponding to the target event is obtained; wherein, the first service performance indicator includes load rate and / or delay, and the target event includes at least one of a freeze event, a packet loss event, and a connection failure event. The second service performance indicator corresponding to the freeze event is the freeze rate, the second service performance indicator corresponding to the packet loss event is the packet loss rate, and the second service performance indicator corresponding to the connection failure event is the connection failure rate.

[0015] In a possible implementation, obtaining a second service performance indicator corresponding to the target event based on the number of times the target event occurs within the first preset time period includes:

[0016] Determining an exponential decay weight based on a difference between a current time and a time at which the target event occurs;

[0017] Performing a weighted sum operation on the exponential decay weight and the number of times the target event occurs to obtain a first weighted sum value;

[0018] Performing a weighted sum operation on the exponential decay weight and the total number of events to obtain a second weighted sum value; wherein the total number of events is the sum of the number of target events and the number of normal events;

[0019] The ratio of the first weighted sum value to the second weighted sum value is used as a second service performance indicator corresponding to the target event.

[0020] In a possible implementation, performing a weighted sum operation on the service performance indicator and the corresponding indicator weight value to obtain the decision value of the matched vendor edge node includes:

[0021] Determine an indicator weight value corresponding to the service performance indicator according to the live stream type, and obtain a target indicator weight value;

[0022] A weighted sum operation is performed on the service performance indicator and the target indicator weight value to obtain the decision value of the matched manufacturer edge node.

[0023] In a possible implementation, after adding the segment download address to the playlist file, the method further includes:

[0024] The edge node of the first manufacturer obtains the playlist file;

[0025] When the target manufacturer node is the edge node of the first manufacturer, the edge node of the first manufacturer obtains the end time of the current segment from the playlist file, and sends a new playlist file request within a second preset time period before the end time of the current segment.

[0026] A second aspect of the present application provides an information processing system, comprising:

[0027] a parameter acquisition module, configured to extract target parameter information from a file request URL; wherein the file request URL is a URL for requesting a playlist file, and the file request URL carries the target parameter information, the target parameter information being obtained by the first manufacturer's edge node parsing the playlist file request sent by the client;

[0028] a vendor node determination module, configured to determine, based on the target parameter information, a target vendor node whose service performance meets a preset condition; wherein the target vendor node is an edge node of the first vendor or an edge node of a second vendor, the first vendor being different from the second vendor;

[0029] The file generation module is used to generate a fragment download address containing the domain name of the target manufacturer node, and add the fragment download address to the playlist file, so that the client sends a fragment request to the target manufacturer node based on the playlist file.

[0030] A third aspect of the present application provides a computer program product, comprising computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the information processing method of the first aspect or any implementation of the first aspect.

[0031] A fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0032] The memory is used to store computer programs;

[0033] The processor is used to execute the computer program so that the electronic device can implement the information processing method of the first aspect or any implementation manner of the first aspect.

[0034] In a fifth aspect, the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the information processing method of the first aspect or any implementation method of the first aspect.

[0035] By means of the above technical solution, the information processing method and related device provided by the present application extract target parameter information from the file request URL; determine the target manufacturer node whose service performance meets the preset conditions based on the target parameter information; generate a fragment download address containing the domain name of the target manufacturer node, and add the fragment download address to the playlist file, so that the client sends a fragment request to the target manufacturer node based on the playlist file. When the service performance of the current manufacturer node meets the preset conditions, the fragment request is processed by the current manufacturer node. When the service performance of the current manufacturer node does not meet the preset conditions, the request sent by the client is processed by the switched manufacturer node by switching the manufacturer node. This can avoid the problem of poor user experience due to the decline in the service quality of the manufacturer node, thereby ensuring the service quality of the manufacturer node. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.

[0037] Figure 1 A flow chart of an information processing method provided for this application;

[0038] Figure 2 A hierarchical scheduling architecture diagram provided for this application;

[0039] Figure 3 A structural diagram of an information processing system provided for this application;

[0040] Figure 4 This is a schematic diagram of the structure of an electronic device provided in this application. DETAILED DESCRIPTION

[0041] The following describes the embodiments of the present application in conjunction with the accompanying drawings. The terms used in the implementation methods of the present application are only used to explain the specific embodiments of the present application and are not intended to limit the present application.

[0042] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0043] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, and this is merely a way of distinguishing the objects of the same attributes when describing them in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0044] Reference Figure 1 , Figure 1 A flow chart of an information processing method provided in an embodiment of the present application is shown as follows: Figure 1 As shown, an information processing method provided by an embodiment of the present application may include steps 101 to 103, and these steps are described in detail below.

[0045] Step 101: extract target parameter information from the file request URL; wherein the file request URL is the URL for requesting a playlist file, and the file request URL carries target parameter information, which is obtained by the edge node of the first manufacturer parsing the playlist file request sent by the client.

[0046] The target parameter information may include a target area, a target operator, and a target live stream identifier (Identity document, ID). The client sends a playlist file request to the edge node of the first manufacturer. The edge node of the first manufacturer obtains the target area and target operator based on the user's IP (Internet Protocol) address using an IP library to resolve the IP address, and obtains the target live stream identifier from the playlist file request address. The playlist file may be an m3u8 file. The edge node may be a CDN service edge node.

[0047] The client requests the playlist file, i.e., the m3u8 file, from the edge node of the first manufacturer. The edge node checks whether the m3u8 file is cached. If so, it sends it to the client. If not, it returns the target parameter information to the source, such as Figure 2As shown, after the first manufacturer's CDN service edge node obtains the target parameter information through the m3u8 file request sent by the client, it rewrites the back-to-source path, adds the target parameter information, namely the target region, target operator and target live stream identifier, to the back-to-source path, and requests the m3u8 file from the CDN service regional source station. If the regional source station does not cache the m3u8 file, it also needs to carry the target parameter information for back-to-source, that is, rewrite the back-to-source path, add the target region, target operator and target live stream identifier to the back-to-source path, and request the m3u8 file from the CDN service center source station. If the central source station does not cache the m3u8 file, it continues to carry the target parameter information for back-to-source, and requests the m3u8 file from the core source station. The core source station can extract the target region, target operator and target live stream identifier from the file request URL.

[0048] Step 102: Determine a target manufacturer node whose service performance meets preset conditions based on the target parameter information; wherein the target manufacturer node is an edge node of a first manufacturer or an edge node of a second manufacturer, and the first manufacturer and the second manufacturer are different.

[0049] When determining the target manufacturer node whose service performance meets the preset conditions based on the target parameter information, the determined target manufacturer can be one manufacturer or multiple different manufacturers. If there are multiple different manufacturers, the edge nodes of each target manufacturer belong to the same target area, the same target operator and have the same target live stream identifier. The service performance of the target manufacturer node needs to meet the preset conditions. If the service performance of the edge node of the first manufacturer meets the preset conditions, it can be determined that the target manufacturer node includes the edge node of the first manufacturer. If the service performance of the edge node of the first manufacturer does not meet the preset conditions, the manufacturer is switched, and the edge node corresponding to the second manufacturer different from the first manufacturer is used as the target manufacturer node, wherein the edge node of the second manufacturer can be the edge node of one manufacturer or the edge node corresponding to multiple different manufacturers.

[0050] The service performance of the manufacturer's node can be reflected through service performance indicators, which may include but are not limited to the jam rate, load rate, network delay, packet loss rate, connection failure rate, etc. The manufacturer's edge node service performance meeting the preset conditions means that one of the jam rate, load rate, network delay, packet loss rate, and connection failure rate is less than the threshold, or the weighted sum of several of them is less than the threshold, to avoid overloading the manufacturer's node due to traffic concentration and resulting in degraded service quality.

[0051] In one possible implementation, determining a target manufacturer node whose service performance meets a preset condition based on the target parameter information includes:

[0052] Determine the edge nodes of each manufacturer that match the target parameter information and calculate the service performance indicators of the matched manufacturer edge nodes;

[0053] Perform a weighted sum operation on the service performance index and the corresponding index weight value to obtain the decision value of the matched manufacturer edge node;

[0054] The manufacturer edge node corresponding to the decision value less than the preset value is determined as the target manufacturer node whose service performance meets the preset conditions.

[0055] Determine the edge nodes of each manufacturer that match the target parameter information. The edge nodes of each manufacturer have consistent target parameter information, that is, the edge nodes of each target manufacturer belong to the same target area, the same target operator and have the same target live stream identifier, thereby obtaining the matched manufacturer edge nodes. Then calculate the service performance indicators of the matched manufacturer edge nodes, including the freeze rate, load rate, network delay, packet loss rate, and connection failure rate. Each service performance indicator corresponds to an indicator weight value. The indicator weight values ​​of different service performance indicators can be the same or different. Perform a weighted sum operation on the service performance indicator and the corresponding indicator weight value to obtain the decision value of the matched manufacturer edge node, and determine the manufacturer edge node whose decision value is less than the preset value as the target manufacturer node whose service performance meets the preset conditions.

[0056] In one possible implementation, determining edge nodes of each manufacturer that match target parameter information and calculating service performance indicators of the matched manufacturer edge nodes include:

[0057] Determine the edge nodes of each manufacturer under the target area, target operator and target live stream identification, and obtain the matched manufacturer edge nodes;

[0058] For each matched manufacturer edge node, a first service performance indicator within a first preset time period is obtained, and based on the number of times the target event occurs within the first preset time period, a second service performance indicator corresponding to the target event is obtained; wherein, the first service performance indicator includes load rate and / or delay, the target event includes at least one of a freeze event, a packet loss event and a connection failure event, the second service performance indicator corresponding to the freeze event is the freeze rate, the second service performance indicator corresponding to the packet loss event is the packet loss rate, and the second service performance indicator corresponding to the connection failure event is the connection failure rate.

[0059] For the first service performance indicator, the load rate and network delay within the first preset duration can be directly obtained. The first preset duration can be 30 seconds or other values. For the second service performance indicator, the second service performance indicator corresponding to the target event can be obtained based on the number of target events occurring within the first preset duration. For a jam event, the jam rate can be obtained based on the number of jams occurring within the first preset duration. For a packet loss event, the packet loss rate can be obtained based on the number of packet losses occurring within the first preset duration. For a connection failure event, the connection failure rate can be obtained based on the number of connection failures sent within the first preset duration.

[0060] In one possible implementation, obtaining a second service performance indicator corresponding to the target event based on the number of times the target event occurs within the first preset time period includes:

[0061] Determine the exponential decay weight based on the difference between the current time and the time when the target event occurs;

[0062] Performing a weighted sum operation on the exponential decay weight and the number of times the target event occurs to obtain a first weighted sum value;

[0063] Performing a weighted sum operation on the exponential decay weight and the total number of events to obtain a second weighted sum value; wherein the total number of events is the sum of the number of target events and the number of normal events;

[0064] The ratio of the first weighted sum value to the second weighted sum value is used as the second service performance indicator corresponding to the target event.

[0065] By determining the exponential decay weight based on the difference between the current time and the time when the target event occurred, the weight of recent events can be changed to better reflect the current network status.

[0066] In a converged CDN network, multi-dimensional performance metrics q are collected in real time across four dimensions: vendor v, region r, operator o, and live stream IDs. This allows for recording live stream service performance data in different scenarios. Where q = 1 represents the freeze rate, q = 2 represents the load rate, q = 3 represents network latency, q = 4 represents the packet loss rate, and q = 5 represents the connection failure rate.

[0067] For the target region r, target operator o, and target live stream IDs, a time-weighted sliding window (with a first preset duration of τ = 30s) is used to calculate the real-time freeze rate, packet loss rate, and connection failure rate of manufacturer v. The calculation formula is as follows:

[0068]

[0069] Where M(r,o,s,v,t) represents the jamming rate, packet loss rate, or connection failure rate, and f(·) is the indicator function, a Boolean function used to determine whether a condition is met. If the condition is met, its value is 1, and if not, its value is 0.

[0070] f(e i =e1,r i =r,o i =o,s i =s,v i =v) indicates the judgment of the i-th event e i The target event can be a freeze event, a packet loss event, or a connection failure event, and the region r corresponding to the event i Whether it is the target region r, operator o i Whether it is the target operator o, target live stream ID s i Whether it is the target live stream IDs, manufacturer v i Whether it is the target manufacturer v, when these conditions are met at the same time, the value of the indicator function is 1, otherwise it is 0. i ∈{e1,e2},r i =r,o i =o,s i =s,v i =v) indicates the judgment of the i-th event e i Is it the target event e1 or the normal event e2, and the region r corresponding to the event i Whether it is the target region r, operator o i Whether it is the target operator o, target live stream ID s i Whether it is the target live stream ID s, manufacturer v i Whether it is the target manufacturer v, if the conditions are met, the indicator function value is 1, otherwise it is 0.

[0071] ω i is the exponential decay weight of the i-th event, Where λ is the attenuation factor, which can be 0.1 or other values, t is the current time, t i is the timestamp of the i-th event, which makes recent events have a higher weight and better reflects the current network status.

[0072] is the summation symbol, k is the number of events, It is to sum the weighted values ​​of all events e1 that meet the conditions within the time window, that is, to add the weighted values ​​of all target events that occur in the time window in the target region r, target operator o, target live stream IDs, and when the service is provided by manufacturer v. e1 can be a freeze event, a packet loss event, or a connection failure event. It is the sum of the weighted values ​​of all events that meet the conditions within the time window (including target events and normal playback events), and e2 is a normal event.

[0073] Real-time lag rate, packet loss rate, and connection failure rate for the target region r, target operator o, and target live stream IDs, when provided by vendor v. Using a time-weighted sliding window approach, the calculated lag rate, packet loss rate, and connection failure rate more accurately reflect the current situation by comprehensively considering recent network conditions.

[0074] In one possible implementation, a weighted sum operation is performed on the service performance indicator and the corresponding indicator weight value to obtain the decision value of the matched manufacturer edge node, including:

[0075] Determine the indicator weight value corresponding to the service performance indicator according to the live stream type, and obtain the target indicator weight value;

[0076] The service performance index and the target index weight value are weighted and summed to obtain the decision value of the matched manufacturer edge node.

[0077] When determining the indicator weights corresponding to service performance indicators based on the live stream type, for live streams with high bitrates and strict real-time requirements, such as live sports events, the latency weight can be increased, giving priority to vendor nodes with low latency to ensure smooth and real-time live video. For cost-sensitive e-commerce live streams, the load rate weight can be increased, selecting vendor nodes with low load rates and appropriate costs to control costs while ensuring service quality. The indicator weights corresponding to the stuttering rate, load rate, network latency, packet loss rate, and connection failure rate are obtained.

[0078] When performing a weighted sum operation on the service performance indicator and the target indicator weight value, the calculation formula is as follows:

[0079] D(r,o,s,v)=α·J+β·L+γ·T+δ·P+∈·C.

[0080] Where D(r, o, s, v) is the decision value, D(·) is the decision function, J is the jam rate, which reflects the frequency of jams during live streaming, L is the load rate, which reflects the busyness of the node in processing requests, and T is the network delay, which refers to the standardized value of the transmission time from the client to the edge node. The calculation formula of T is: t min is the lower limit of time, t min =0ms, t max As the time limit, live events are sensitive to delays, so you can set t max＝100ms , e-commerce live streaming is cost-sensitive and has a higher tolerance for delays. You can set tmax＝1000ms , t is the current time, P is the packet loss rate, that is, the proportion of data packets lost during transmission, C is the connection failure rate, which indicates the probability of failure to establish a connection between the client and the node, α, β, γ, δ, ∈ are the indicator weights corresponding to the service performance indicators, which can be set to α = 0.2, β = 0.6, γ = 0.1, δ = 0.05, ∈ = 0.05, or other values ​​according to the type of live stream.

[0081] When D(r,o,s,v)>a, a vendor switch is triggered. a is a preset value that can be set to 0.6 or other values. By comprehensively considering multiple indicators and the characteristics of different live streams, this decision function can evaluate the service quality of the vendor node and select the optimal distribution path for the live stream.

[0082] Step 103: Generate a fragment download address containing the domain name of the target manufacturer node, and add the fragment download address to the playlist file, so that the client sends a fragment request to the target manufacturer node based on the playlist file.

[0083] When generating a fragment download address containing the domain name of the target manufacturer node, a signed absolute URL (Uniform Resource Locator) can be generated for the TS fragment. The specific format is:

[0084] http(s): / / <target manufacturer domain name> / <shard path>?<business parameters>&<signature parameters>

[0085] The segment download address is added to the playlist file, and the playlist file is propagated back to the client in a tiered manner. Specifically, the core origin sends the segment to the central origin, which in turn sends it to the regional origin, which in turn sends it to the edge node. The edge node then returns an m3u8 file containing the target vendor node's TS segment URL to the client. The client can send segment requests to the target vendor node using the segment download address in the playlist file, such as http(s): / / v.cdn.com / seg.ts.

[0086] like Figure 2As shown in the figure, if the target manufacturer node is the edge node of manufacturer A, the ts shard request is sent to the edge node of manufacturer A. If manufacturer A has a ts shard cached, it is returned to the client. If there is no ts shard cached, the ts shard is returned to the source ts shard, that is, the ts shard request is sent to the regional source station of manufacturer A. If there is no ts shard cached, the ts shard request is sent to the central source station of manufacturer A, until it is returned to the core source station. Similarly, if the target manufacturer node is the edge node of manufacturer B, the ts shard request is sent to the edge node of manufacturer B. If manufacturer B has a ts shard cached, it is returned to the client. If there is no ts shard cached, the ts shard is returned to the source ts shard, that is, the ts shard request is sent to the regional source station of manufacturer B. If there is no ts shard cached, the ts shard request is sent to the central source station of manufacturer B, until it is returned to the core source station. The core source station then returns the TS slices to the edge node step by step, that is, the core source station returns the TS slices to the central source station, the central source station returns the TS slices to the regional source station, the regional source station returns the TS slices to the edge node, and the edge node returns the TS slices to the client.

[0087] In one possible implementation, after adding the segment download address to the playlist file, the information processing method provided by this application further includes:

[0088] The edge node of the first manufacturer obtains the playlist file;

[0089] When the target manufacturer node is the edge node of the first manufacturer, the edge node of the first manufacturer obtains the end time of the current segment from the playlist file, and sends a new playlist file request within a second preset time period before the end time of the current segment.

[0090] In order to ensure that the manufacturer's node switching occurs at the boundary of the media segment, avoid interruption of video frame parsing, and achieve user-unaware switching, it is necessary to make the edge node initiate the back-to-source request at the second preset time before the end time of the current TS segment. The second preset time can be 50ms, that is, a new playlist file request is sent within 50ms before the end time of the current segment. This ensures that after the core source station returns the new playlist file, the client can obtain the new segment download address within the second preset time after the segment end time, that is, obtain the new segment download address within 50ms after the end time of the current segment. In actual applications, the switching time window can be set to the end time t of the current TS segment. end ±50ms, that is, the switching time t switch The time range is: t switch ∈[t end -50ms, t end+50ms]. CDN edge nodes adopt active back-to-source mode and switch node manufacturers within this time window, which can ensure the continuity of live streaming. Users will not notice any interruption or freeze in the picture during viewing, greatly improving the viewing experience.

[0091] In summary, the client accesses the m3u8 file through a unified domain name (such as https: / / live.proxy.com / stream2025.m3u8). The CDN service edge node reconstructs the original m3u8 file request into a labeled path back to the source based on the user's IP resolution result, separates the scheduling of m3u8 and ts slices, uses a separate domain name service for m3u8, and uses CDN vendor services for ts slices. The core source station selects a target vendor node whose service performance meets the preset conditions for each request based on the user's region, operator information, and live stream ID, and dispatches the request to the target vendor node to ensure high-quality transmission of the live stream. The target vendor node returns the TS fragment with the adapted signature, realizing end-to-end optimization of "user-region-operator-vendor-live stream". During the reception and playback process, the client can seamlessly switch to the new vendor node without any additional operations, without any perception throughout the process, ensuring the smoothness and stability of live viewing.

[0092] To further illustrate the information processing method provided by this application, please refer to the following examples.

[0093] Assume the user's IP address is 116.228.xxx.xxx. The IP database resolves the address to region r = R and operator o = Y. The live stream ID s = SPORTS2025 is extracted from the m3u8 request URL parameter stream_id = SPORTS2025. The edge node generates the label r_o_s = R_Y_SPORTS2025, which serves as the cache key and back-to-origin path parameter.

[0094] Query manufacturer A's metrics under the R_Y_SPORTS2025 dimension from Redis. The collection frequency can be 10 times / second. The load rate L is 0.85 and the latency T is 80 ms.

[0095] If the current time is t = 15:30:00 (unit: seconds), the time window is τ = 30s, that is, the monitoring interval is [15:29:30, 15:30:00].

[0096] Assume that five freezes are detected within the time window, three of which occurred 10 seconds ago and two occurred 20 seconds ago, with the occurrence times being t1 = 15:29:50 (10 seconds ago) and t2 = 15:29:40 (20 seconds ago). This means there are 15 normal playback events and 5 freeze events, for a total of 20 events.

[0097] When calculating weights, the exponential decay formula is: Where λ = 0.1, time difference Δt = tt i .

[0098] Jam event 1 (10 seconds ago): Δt = 10s, ω1 = e -0.1×10 =e -1 , the value of ω1 can be set to 0.3679.

[0099] Stall event 2 (20 seconds ago): Δt = 20s, ω2 = e -0.1×20 =e -2 , ω2 can be taken as 0.1353.

[0100] The weight of recent events is higher than that of distant events, for example, the weight of events 10 seconds ago is higher than that of events 20 seconds ago, to ensure real-time performance.

[0101] The weight calculation method for normal events is the same. For example, if a normal event occurs 5 seconds ago, ω3=e -0.1×5 =e -0.5 , ω3 can be set to 0.6065. The 15 normal events are assumed to be evenly distributed in the window, and the average weight is simplified to be about 0.3. The actual calculation needs to be based on the specific time.

[0102] When calculating the real-time jam rate, the numerator is the weighted sum of jam events, and the denominator is the weighted sum of all events.

[0103] Numerator = 3 × 0.3679 + 2 × 0.1353 = 1.1037 + 0.2706 = 1.3743;

[0104] Denominator = 1.3743 + 15 × 0.3 = 1.3743 + 4.5 = 5.8743;

[0105] The jam rate = 1.3743 / 5.8743, so the jam rate can be set to 0.234.

[0106] The calculation of indicators such as packet loss rate and connection failure rate is similar to that of the freeze rate and will not be repeated here.

[0107] If the live broadcast type is sports live broadcast (sports live broadcast is characterized by high bit rate and high real-time requirements, the delay can be reduced, and the standardized delay range is: 0ms-100ms).

[0108] The candidate manufacturers are manufacturer A (ie, the current service manufacturer) and manufacturer B (the candidate switching manufacturer).

[0109] The real-time indicators are shown in Table 1 and are collected in a 30-second sliding window.

[0110] Table 1 Index data

[0111] index Manufacturer A Manufacturer B Stuttering rate J 15％(0.15) 12％(0.12) Load factor L 85％(0.85) 60％(0.60) Delay T 80ms(0.8) 60ms(0.6)

[0112] For sports indicators, weights can be adjusted, that is, the delay weight is increased to γ ​​= 0.2 (default 0.1) to give priority to low-latency nodes, the jamming rate weight is α = 0.6 (default value 0.6, unchanged), and the load rate weight is β = 0.2 (default is 0.6, reduced to adapt to real-time requirements).

[0113] The decision function is D(r,o,s,v)=α·J+β·L+γ·T.

[0114] Manufacturer A's decision value: D A =0.6×0.15+0.2×0.85+0.2×0.8=0.09+0.17+0.16=0.42.

[0115] Manufacturer B's decision value: D B =0.6×0.12+0.2×0.60+0.2×0.6=0.072+0.12+0.12=0.312.

[0116] Trigger condition: Switching is triggered when D(r, o, s, v)>T, T=0.3.

[0117] Manufacturer A: D A =0.42>0.3, it is judged that the performance does not meet the standard;

[0118] Manufacturer B: D B =0.312>0.3, close to the threshold of 0.3 but not up to standard, at this time the threshold T can be dynamically adjusted (for example, the live sports scene allows for higher delay tolerance, which can be set to T=0.35, then D B performance standards are met).

[0119] Manufacturer B: D B =0.312<0.35, the switching condition is met, triggering the switch to manufacturer B.

[0120] The edge node extracts the end time T_end=15:30:05.000 of the current segment seg-0.ts from the m3u8 timestamp annotation and defines the time window [15:30:04.950,15:30:05.050]. end -50ms=15:30:04.950Initiate a back-to-origin request, and the unified server is at T end +20ms=15:30:05.020 Return the new m3u8, ensuring that the client obtains the new URL within 50ms after the fragmentation ends.

[0121] Reconstruction of m3u8 back-to-source path:

[0122] The original path http: / / live.proxy.com / SPORTS2025 / stream.m3u8 is rewritten as:

[0123] http: / / live.proxy.com / R_Y_SPORTS2025 / stream.m3u8.

[0124] The path parameter R_Y_SPORTS2025 is used for origin database queries and cache shards.

[0125] TS fragment URL generation:

[0126] Generate a signed URL for seg-1.ts using the SHA-256 algorithm:

[0127] http: / / B.cdn.com / TS / SPORTS2025 / seg-1.ts?sign=HMAC_SHA256(key B ,"B.cdn.com / TS / SPORTS2025 / seg-1.ts?t=1690000000&rand=12345"

[0128] Among them, B.cdn.com is the domain name of manufacturer B, and the key is key B Pre-shared by the core source station and manufacturer B.

[0129] The m3u8 file is distributed through a unified domain name CDN (such as live.proxy.com). The edge node caches the m3u8 corresponding to the label R_Y_SPORTS2025, and the TTL (Time To Live) is 60 seconds.

[0130] The TS segment request is directed to the node http: / / RY.B.cdn.com of manufacturer B, which uses its local node acceleration to reduce the average delay to 60ms (25% lower than that of manufacturer A).

[0131] Client in T end After seg-0.ts is played, seg-1.ts (manufacturer B) is immediately requested. The actual switching interruption time is 28ms (lower than the human eye perception threshold of 100ms).

[0132] If the load rate of a vendor B node exceeds 90% for 30 seconds, the vendor B node is overloaded, triggering disaster recovery. At this point, the system checks the metrics of other vendors' nodes in the same region. If D < 0.3, a failover occurs. If all fail, the system returns to the core origin server, issues an alarm, and automatically restarts the failed node (recovery time < 30 seconds).

[0133] When edge nodes cache m3u8 files, they use a composite key:

[0134] CacheKey=m3u8 <r> <o> <s>=m3u8_R_Y_SPORTS2025.

[0135] The cache hit rate increased to 85%, and the number of back-to-origin requests decreased by 40% (compared to the 65% hit rate of the traditional two-dimensional key m3u8_R_Y).

[0136] The request parameters can be:

[0137]

[0138]

[0139] Response parameters:

[0140]

[0141] This application builds a four-dimensional monitoring system for region, operator, manufacturer, and live stream ID through user IP resolution. It combines time-weighted sliding window collection of multi-dimensional performance indicators such as load rate, latency, freeze rate, connection failure rate, packet loss rate, etc., and uses dynamic weight decision functions to achieve fine-grained scheduling of "manufacturer-region-operator-live stream ID". Through labeled back-to-source path reconstruction and source station layered architecture, it accurately switches at the boundaries of media segments to ensure that the client is unaware. This solves the problem of unbalanced load on nodes of various manufacturers and the inability to automatically switch to nodes of other manufacturers, causing some nodes to be overloaded due to concentrated traffic and reduced service quality, while other nodes have idle resources and insufficient overall utilization, or forced switching leads to interruption of TS segment loading, resulting in black screen or freeze issues. It can significantly improve resource allocation accuracy and network utilization efficiency, effectively reduce cross-domain back-to-source costs, and achieve efficient distribution and smooth playback of live streams. It is suitable for large-scale cross-domain live broadcast scenarios.

[0142] The above describes an information processing method provided by an embodiment of the present application. The following describes a system for executing the above information processing method.

[0143] See also Figure 3 , Figure 3 This is a structural diagram of an information processing system provided in an embodiment of the present application. Figure 3 As shown, the information processing system includes:

[0144] The parameter acquisition module 301 is used to extract target parameter information from the file request URL; wherein, the file request URL is the URL for requesting the playlist file, and the file request URL carries target parameter information, which is obtained by the edge node of the first manufacturer parsing the playlist file request sent by the client.

[0145] The manufacturer node determination module 302 is used to determine a target manufacturer node whose service performance meets preset conditions based on target parameter information; wherein the target manufacturer node is an edge node of a first manufacturer or an edge node of a second manufacturer, and the first manufacturer and the second manufacturer are different.

[0146] The file generation module 303 is used to generate a fragment download address containing the domain name of the target manufacturer node, and add the fragment download address to the playlist file, so that the client sends a fragment request to the target manufacturer node based on the playlist file.

[0147] In a possible implementation, the manufacturer node determination module 302 is specifically configured to:

[0148] Determine the edge nodes of each manufacturer that match the target parameter information and calculate the service performance indicators of the matched manufacturer edge nodes;

[0149] Perform a weighted sum operation on the service performance index and the corresponding index weight value to obtain the decision value of the matched manufacturer edge node;

[0150] The manufacturer edge node corresponding to the decision value less than the preset value is determined as the target manufacturer node whose service performance meets the preset conditions.

[0151] In a possible implementation, the manufacturer node determination module 302 is further configured to:

[0152] Determine the edge nodes of each manufacturer under the target area, target operator and target live stream identification, and obtain the matched manufacturer edge nodes;

[0153] For each matched manufacturer edge node, a first service performance indicator within a first preset time period is obtained, and based on the number of times the target event occurs within the first preset time period, a second service performance indicator corresponding to the target event is obtained; wherein, the first service performance indicator includes load rate and / or delay, the target event includes at least one of a freeze event, a packet loss event and a connection failure event, the second service performance indicator corresponding to the freeze event is the freeze rate, the second service performance indicator corresponding to the packet loss event is the packet loss rate, and the second service performance indicator corresponding to the connection failure event is the connection failure rate.

[0154] In a possible implementation, the manufacturer node determination module 302 is further configured to:

[0155] Determine the exponential decay weight based on the difference between the current time and the time when the target event occurs;

[0156] Performing a weighted sum operation on the exponential decay weight and the number of times the target event occurs to obtain a first weighted sum value;

[0157] Performing a weighted sum operation on the exponential decay weight and the total number of events to obtain a second weighted sum value; wherein the total number of events is the sum of the number of target events and the number of normal events;

[0158] The ratio of the first weighted sum value to the second weighted sum value is used as the second service performance indicator corresponding to the target event.

[0159] In a possible implementation, the manufacturer node determination module 302 is further configured to:

[0160] Determine the indicator weight value corresponding to the service performance indicator according to the live stream type, and obtain the target indicator weight value;

[0161] The service performance index and the target index weight value are weighted and summed to obtain the decision value of the matched manufacturer edge node.

[0162] In one possible implementation, the information processing system provided by this application further includes:

[0163] A sending module is used to enable the edge node of the first manufacturer to obtain the playlist file after the fragment download address is added to the playlist file; when the target manufacturer node is the edge node of the first manufacturer, the edge node of the first manufacturer obtains the end time of the current fragment from the playlist file and sends a new playlist file request within a second preset time before the end time of the current fragment.

[0164] An electronic device is also provided in an embodiment of the present application. Figure 4 , which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present application. The electronic device in the embodiments of the present application may include but is not limited to fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 4 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0165] like Figure 4 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage device 408 into a random access memory (RAM) 403. When the electronic device is powered on, the RAM 403 also stores various programs and data required for the operation of the electronic device. The processing device 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0166] Typically, the following devices may be connected to the I / O interface 405: an input device 406 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 408 including, for example, a memory card, a hard disk, etc.; and a communication device 409. The communication device 409 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The electronic device is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0167] An embodiment of the present application also provides a computer program product including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any one of the information processing methods provided in the embodiments of the present application.

[0168] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any information processing method provided in the embodiment of the present application.

[0169] It should also be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided in this application, the connection relationship between the modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines.

[0170] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course can also be implemented by special hardware including application-specific integrated circuits, special CPUs, special memories, special components, etc. In general, all functions performed by computer programs can be easily implemented with corresponding hardware, and the specific hardware structures used to implement the same function can also be diverse, such as analog circuits, digital circuits or special circuits, etc. However, for the present application, software program implementation is a better implementation method in most cases. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer's floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc., and includes a number of instructions to enable a computer device (which can be a personal computer, training equipment, or network equipment, etc.) to execute the methods described in each embodiment of the present application.

[0171] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0172] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, a computer, a training device or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website, a computer, a training device or a data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).< / s> < / o> < / r>

Claims

1. An information processing method, characterized in that: include: Extracting target parameter information from a file request URL; wherein the file request URL is a URL for requesting a playlist file, and the file request URL carries the target parameter information, the target parameter information being obtained by parsing the playlist file request sent by the client by the edge node of the first manufacturer; Determining a target vendor node whose service performance meets a preset condition based on the target parameter information; wherein the target vendor node is an edge node of the first vendor or an edge node of a second vendor, and the first vendor is different from the second vendor; Generate a fragment download address containing the domain name of the target manufacturer node, and add the fragment download address to the playlist file, so that the client sends a fragment request to the target manufacturer node based on the playlist file.

2. The information processing method according to claim 1, wherein: The determining, based on the target parameter information, a target manufacturer node whose service performance meets a preset condition includes: Determine the edge nodes of each manufacturer that match the target parameter information, and calculate the service performance indicators of the matched manufacturer edge nodes; Performing a weighted sum operation on the service performance indicator and the corresponding indicator weight value to obtain the decision value of the matched manufacturer edge node; The manufacturer edge node corresponding to the decision value being smaller than the preset value is determined as the target manufacturer node whose service performance meets the preset conditions.

3. The information processing method according to claim 2, wherein: The determining of the edge nodes of each manufacturer matching the target parameter information and calculating the service performance indicators of the matched edge nodes of the manufacturer includes: Determine each manufacturer edge node under the target area, target operator and target live stream identifier, and obtain the matched manufacturer edge node; For each matched manufacturer edge node, a first service performance indicator within a first preset time period is obtained, and based on the number of times the target event occurs within the first preset time period, a second service performance indicator corresponding to the target event is obtained; wherein, the first service performance indicator includes load rate and / or delay, and the target event includes at least one of a freeze event, a packet loss event, and a connection failure event. The second service performance indicator corresponding to the freeze event is the freeze rate, the second service performance indicator corresponding to the packet loss event is the packet loss rate, and the second service performance indicator corresponding to the connection failure event is the connection failure rate.

4. The information processing method according to claim 3, wherein: The obtaining, based on the number of times the target event occurs within the first preset time period, a second service performance indicator corresponding to the target event includes: Determining an exponential decay weight based on a difference between a current time and a time at which the target event occurs; Performing a weighted sum operation on the exponential decay weight and the number of times the target event occurs to obtain a first weighted sum value; Performing a weighted sum operation on the exponential decay weight and the total number of events to obtain a second weighted sum value; wherein the total number of events is the sum of the number of target events and the number of normal events; The ratio of the first weighted sum value to the second weighted sum value is used as a second service performance indicator corresponding to the target event.

5. The information processing method according to claim 2, wherein: The step of performing a weighted sum operation on the service performance indicator and the corresponding indicator weight value to obtain the decision value of the matched manufacturer edge node includes: Determine an indicator weight value corresponding to the service performance indicator according to the live stream type, and obtain a target indicator weight value; A weighted sum operation is performed on the service performance indicator and the target indicator weight value to obtain the decision value of the matched manufacturer edge node.

6. The information processing method according to claim 1, wherein: After adding the segment download address to the playlist file, the method further includes: The edge node of the first manufacturer obtains the playlist file; When the target manufacturer node is the edge node of the first manufacturer, the edge node of the first manufacturer obtains the end time of the current segment from the playlist file, and sends a new playlist file request within a second preset time period before the end time of the current segment.

7. An information processing system, characterized in that: include: a parameter acquisition module, configured to extract target parameter information from a file request URL; wherein the file request URL is a URL for requesting a playlist file, and the file request URL carries the target parameter information, the target parameter information being obtained by the first manufacturer's edge node parsing the playlist file request sent by the client; a vendor node determination module, configured to determine, based on the target parameter information, a target vendor node whose service performance meets a preset condition; wherein the target vendor node is an edge node of the first vendor or an edge node of a second vendor, the first vendor being different from the second vendor; The file generation module is used to generate a fragment download address containing the domain name of the target manufacturer node, and add the fragment download address to the playlist file, so that the client sends a fragment request to the target manufacturer node based on the playlist file.

8. A computer program product, characterized in that The method comprises computer-readable instructions, which, when executed on an electronic device, enable the electronic device to implement the information processing method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: comprising at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is configured to execute the computer program so that the electronic device can implement the information processing method according to any one of claims 1 to 6.

10. A computer storage medium, characterized in that The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the information processing method according to any one of claims 1 to 6.

Images