CN114070852A - Live broadcast delay optimization method and device - Google Patents

Live broadcast delay optimization method and device Download PDF

Info

Publication number
CN114070852A
CN114070852A CN202111348858.3A CN202111348858A CN114070852A CN 114070852 A CN114070852 A CN 114070852A CN 202111348858 A CN202111348858 A CN 202111348858A CN 114070852 A CN114070852 A CN 114070852A
Authority
CN
China
Prior art keywords
information
target
user
live broadcast
live
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202111348858.3A
Other languages
Chinese (zh)
Other versions
CN114070852B (en
Inventor
姜栋
廖大达
朱翔
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Bilibili Technology Co Ltd
Original Assignee
Shanghai Bilibili Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Bilibili Technology Co Ltd filed Critical Shanghai Bilibili Technology Co Ltd
Priority to CN202111348858.3A priority Critical patent/CN114070852B/en
Publication of CN114070852A publication Critical patent/CN114070852A/en
Application granted granted Critical
Publication of CN114070852B publication Critical patent/CN114070852B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
    • H04L67/1004—Server selection for load balancing
    • H04L67/1021—Server selection for load balancing based on client or server locations
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/21—Server components or server architectures
    • H04N21/218—Source of audio or video content, e.g. local disk arrays
    • H04N21/2187—Live feed
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
    • H04N21/4788—Supplemental services, e.g. displaying phone caller identification, shopping application communicating with other users, e.g. chatting
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

The application provides a live broadcast delay optimization method and a live broadcast delay optimization device, wherein the live broadcast delay optimization method comprises the following steps: receiving a target live broadcast stream, and determining a target anchor according to the target live broadcast stream; acquiring historical live broadcast information of the target anchor, and counting a position information set of a target user corresponding to the target anchor according to the historical live broadcast information; generating a user edge computing node set according to the position information set; and pushing the target live broadcast stream to the user edge computing nodes in the user edge computing node set. According to the method and the device, through analyzing the historical live broadcast information of the target anchor, the distribution condition of the user is watched in the next live broadcast mode is predicted according to the change trend of the historical live broadcast information, the live broadcast stream is pushed to the corresponding edge computing node in advance, the delay of the first frame of the live broadcast watching of the user is reduced, and the experience degree of the live broadcast watching of the user is improved.

Description

Live broadcast delay optimization method and device
Technical Field
The application relates to the technical field of computer networks, in particular to a live broadcast delay optimization method. The application also relates to a live broadcast delay optimization device, a computing device and a computer readable storage medium.
Background
With the development and popularization of network live broadcast, more and more users choose to watch live broadcast on the network, and at present, due to the problem of hardware performance of the network and equipment, the problem that the delay of a live broadcast first frame is high is a frequent problem. When a user watches a live broadcast, the time consumed for loading the first frame is serious, so that the live broadcast picture needs to be loaded for a long time, and therefore, extremely poor watching experience is brought to the user.
Disclosure of Invention
In view of this, the present application provides a live broadcast delay optimization method. The application also relates to a live broadcast delay optimization device, a computing device and a computer readable storage medium, which are used for solving the problems that the speed of loading a live broadcast first frame picture is slow and the waiting time for a user to enter a live broadcast room to watch is long in the prior art.
According to a first aspect of an embodiment of the present application, a live broadcast delay optimization method is provided, including:
receiving a target live broadcast stream, and determining a target anchor according to the target live broadcast stream;
acquiring historical live broadcast information of the target anchor, and counting a position information set of a target user corresponding to the target anchor according to the historical live broadcast information, wherein the position information set comprises at least one piece of position information;
generating a user edge computing node set according to the position information set;
and pushing the target live broadcast stream to the user edge computing nodes in the user edge computing node set.
According to a second aspect of the embodiments of the present application, there is provided a live broadcast delay optimization apparatus, including:
the determining module is configured to receive a target live stream and determine a target anchor according to the target live stream;
the statistical module is configured to acquire historical live broadcast information of the target anchor and perform statistics on a position information set of a target user corresponding to the target anchor according to the historical live broadcast information;
a generating module configured to generate a set of user edge computing nodes from the set of location information;
a pushing module configured to push the target live stream to a user edge computing node in the user edge computing node set.
According to a third aspect of embodiments herein, there is provided a computing device comprising a memory, a processor, and computer instructions stored on the memory and executable on the processor, the processor implementing the steps of the live delay optimization method when executing the computer instructions.
According to a fourth aspect of embodiments of the present application, there is provided a computer-readable storage medium storing computer instructions which, when executed by a processor, implement the steps of the live delay optimization method.
According to the live broadcast delay optimization method, a target live broadcast stream is received, and a target anchor is determined according to the target live broadcast stream; acquiring historical live broadcast information of the target anchor, and counting a position information set of a target user corresponding to the target anchor according to the historical live broadcast information; generating a user edge computing node set according to the position information set; and pushing the target live broadcast stream to the user edge computing nodes in the user edge computing node set. The distribution condition of watching users of the anchor can be predicted according to the historical live broadcast information of the anchor, so that video data is extracted, transmitted and preheated; when a watching user enters a live broadcasting room, the live broadcasting video stream can be rapidly sent to the watching user through the edge computing node which acquires live broadcasting data in advance, the effect of improving the speed of loading live broadcasting pictures and optimizing the delay of the live broadcasting first frame is achieved, and therefore the watching experience of the user is improved.
Drawings
Fig. 1 is a flowchart of a live broadcast delay optimization method according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a live broadcast delay optimization method applied to a cate live broadcast of zhang san according to an embodiment of the present application;
fig. 3 is a processing flow diagram of a live broadcast delay optimization method applied to a food live broadcast of zhang san according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a live broadcast delay optimization apparatus according to an embodiment of the present application;
fig. 5 is a block diagram of a computing device according to an embodiment of the present application.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is capable of implementation in many different ways than those herein set forth and of similar import by those skilled in the art without departing from the spirit of this application and is therefore not limited to the specific implementations disclosed below.
The terminology used in the one or more embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of the present application. As used in one or more embodiments of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present application refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It will be understood that, although the terms first, second, etc. may be used herein in one or more embodiments of the present application to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first aspect may be termed a second aspect, and, similarly, a second aspect may be termed a first aspect, without departing from the scope of one or more embodiments of the present application. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
First, the noun terms to which one or more embodiments of the present application relate are explained.
The first frame is time-consuming: the user clicks on the time it takes to start watching the live to watch the first picture of the live.
Edge computing node: edge computing nodes are deployed all over the country and used for receiving live streams pushed by a main broadcast, and in the edge computing nodes, due to the fact that the edge computing nodes are close to the physical distance of a user, the user can obtain needed memories nearby, and the effects of being low in transmission delay and improving the response speed of the user for accessing websites are achieved.
If the live broadcast is watched, the first picture needs to be loaded for a long time to be played, so that the watching experience of a user is reduced, and a unified solution for optimizing the problems does not exist in the existing live broadcast architecture in the industry.
Based on the above, the present application provides a live broadcast delay optimization method, and the present application also relates to a live broadcast delay optimization apparatus, a computing device, and a computer-readable storage medium. When watching the live broadcast, the user does not need to obtain the live stream from the edge computing node pushing the live stream from the anchor broadcast, but obtains the live stream from the edge computing node closest to the user, and finally the effect of optimizing the first frame speed is achieved. Details are described in the following examples one by one.
Fig. 1 shows a flowchart of a live broadcast delay optimization method provided in an embodiment of the present application, which specifically includes the following steps:
step 102: receiving a target live broadcast stream, and determining a target anchor according to the target live broadcast stream.
The live broadcast delay optimization method is applied to a live broadcast stream server, the live broadcast stream server can also be understood as an anchor edge computing node, and the live broadcast stream receives a live broadcast stream sent by an anchor and pushes the live broadcast stream to a corresponding user edge computing node. When the target anchor is broadcast, the target live broadcast stream is pushed to the anchor edge computing node closest to the target anchor, and in practical application, many anchors may be broadcast simultaneously, so each anchor edge computing node receives many live broadcast streams. Therefore, the anchor edge computing node needs to determine a target live stream to be optimized in a plurality of live streams, and determine a corresponding target anchor according to the target live stream, so that subsequent operations such as audience distribution prediction and the like can be performed on the target anchor.
In practical application, after receiving a target live stream, an anchor edge computing node can determine identity information of a target anchor according to information carrying an anchor identity in the target live stream.
In a specific embodiment of the present application, after receiving a live stream a sent by an anchor a, an anchor edge computing node SH may determine that the live stream a is sent by the anchor a according to that the live stream a carries identity information of the anchor a. Similarly, the anchor edge computing node SH may also obtain other identity information of the anchor a according to other identification information carried in the live stream a. For example, the live broadcast stream a carries the live broadcast geographical position information of the anchor a, and the anchor edge computing node SH may obtain where the anchor a performs live broadcast; or the live stream a carries the live type of the anchor a, the anchor edge computing node SH may obtain the live content of the anchor a.
Step 104: and acquiring historical live broadcast information of the target anchor.
The historical live broadcast information can be understood as live broadcast information of a target anchor live broadcast within past preset time, and can include live broadcast attention information and live broadcast watching information of the target anchor broadcast.
Specifically, the obtaining of the historical live broadcast information of the target anchor includes:
and acquiring live broadcasting attention information and live broadcasting watching information of the target anchor, wherein the live broadcasting attention information is attention user information for paying attention to the target anchor, and the live broadcasting watching information is watching user information for watching the live broadcasting of the target anchor.
The live broadcasting concern information may be a log of concern user information of a concern target anchor established for the anchor meeting a preset condition, and the preset condition may be that when the concern users of the concern anchor exceed a preset number and the live broadcasting duration of the anchor exceeds a preset time, for example, the preset condition is that the concern users of the concern anchor are greater than or equal to 200, and if the concern users of the concern anchor a are 201, a log of concern user information of the concern anchor a is established for the anchor a; and when the preset condition is that the live broadcast time length of the anchor A exceeds 300 hours, if the live broadcast time length of the anchor A is 301 hours, establishing a record log of the concerned user information concerning the anchor A for the anchor A. The attention user information of the attention anchor can be collected through the attention log. The information of the concerned users can be understood as information of users concerning the target anchor, and the information of the concerned users includes, but is not limited to, the number of the concerned users, account information of each concerned user, duration of the concerned target anchor, and the like. In practical application, the live broadcast attention information may be obtained from an attention user data model map of an attention anchor established for the anchor, the map takes a city as a unit, and the address distribution position of the attention user paying attention to the anchor is obtained according to the attention user data model map, for example, if 30 people pay attention to the anchor in beijing, 30 points are added to the city of "beijing".
The live broadcast watching information can be a log of watching user information for watching live broadcasts of the target anchor, which is established for each live broadcast of the anchor, the watching user information corresponding to each live broadcast can be obtained by watching the log, the watching user information can be understood as information of users watching the target anchor, and the watching user information includes but is not limited to the number of watching users, account information of each user, duration of watching the target anchor and the like; the account information may also carry information related to the account, such as the account level, the account frequently logging on the land, and the like. In practical application, the live broadcast viewing information can be obtained by establishing a viewing user data model map once per live broadcast by a main broadcast, each live broadcast corresponds to a different viewing data model map, the map takes a city as a unit, and the address distribution position of each viewing user and the interactive information generated when each viewing user views the live broadcast can be obtained according to the viewing data model map, for example, a user with a user ID of '12345' in Beijing is always viewing the live broadcast, and 1 point is added to the 'Beijing' city.
In a specific embodiment of the present application, following the above example, the anchor edge computing node SH obtains historical live broadcast information of the anchor a, where the historical live broadcast information includes live broadcast attention information and live broadcast viewing information, that is, information such as the number and the position of users paying attention to the anchor a and information such as the number and the position of users viewing the anchor a can be obtained according to the historical live broadcast information.
Specifically, the acquiring of the live viewing information of the target anchor includes:
and determining the preset number of live broadcast fields of the target anchor, and acquiring live broadcast watching information corresponding to each live broadcast field.
In practical application, the corresponding amount of live viewing information can be acquired according to a preset rule. The preset rules include, but are not limited to: the method comprises the steps of obtaining historical live broadcast information of a preset live broadcast field, obtaining historical live broadcast information in preset live broadcast time and the like. For example, when the preset rule is historical live broadcast information of the target anchor within the last 5 days, the historical live broadcast information of all live broadcast fields of the target anchor within the last 5 days is acquired; and when the preset rule is to acquire the historical live broadcast information of 20 fields of the target anchor, acquiring the historical live broadcast information of the latest 20 fields of the target anchor. The historical live broadcast information of corresponding quantity is obtained through the preset rule, and the data processing efficiency and the accuracy of the processing result can be improved.
In a specific embodiment of the present application, the above example is used, and if it is determined that the number of the live broadcast sessions to be acquired by the anchor a is 3, the live broadcast viewing information corresponding to the past 3 live broadcast sessions of the anchor a is acquired.
Specifically, acquiring live viewing information corresponding to each live session includes:
acquiring a field identifier of each live broadcast;
and acquiring corresponding live broadcast watching information in a database according to each live broadcast field identification.
Wherein, the identification of each live broadcast can be understood as the identification information of each live broadcast, and different live broadcast fields have different field identifications. For example, anchor a starts a live broadcast in 7/month 3, and after the live broadcast is finished, the live broadcast content may be saved in a database in the form of a video file. The video file carries a corresponding field identifier, which may be 13 o 'clock 00/3/7/2021-14 o' clock 00/7/3/2021. In the embodiment of the present application, the session identifier takes time as an example, but in practical application, different identifiers can be taken to identify a video file containing live content according to actual requirements, and the present application is not particularly limited herein.
In a specific embodiment of the present application, following the above example, after it is determined that the number of live broadcast fields to be acquired by the anchor a is 3, the field identifiers of the 3 live broadcasts are respectively: 2021\7\23\13.00, 2021\7\24\08.00, 2021\7\25\ 20.00. And acquiring corresponding live broadcast watching information in the database according to each live broadcast field identification.
Step 106: and counting a position information set of a target user corresponding to the target anchor according to the historical live broadcast information, wherein the position information set comprises at least one piece of position information.
The target user can be understood as a user screened out from the concerned user and the watching user according to a preset condition, and the target user can be used as a user for predicting watching in next live broadcast. The preset conditions can be the limiting conditions such as the grade of the user, the watching time of the user and the like, and the preset conditions are not specifically limited by the application and can be determined according to actual requirements. The location information set can be understood as a set of location distribution conditions of the target user. For example, the location information set may include, but is not limited to, a city name, a number of users in the city, and a quality of users in the city.
Specifically, the step of counting a position information set of a target user corresponding to the target anchor according to the historical live broadcast information includes:
and counting the city information set of the target user corresponding to the target anchor according to the historical live broadcast information.
In practical applications, the location information set of the statistical target user may be understood as a city information set of the statistical target user.
In a specific embodiment of the present application, the above example is used, and according to historical live broadcast information of the anchor a in the past 3 live broadcasts, a position information set, namely a city information set, of a target user corresponding to the anchor a is counted, where the city information set includes { beijing: 100. and (3) stone house village: 40. shenyang: 50 … …, wherein "100, 40, 50" respectively represent the number of viewers in the corresponding city.
Specifically, the counting of the location information set of the target user corresponding to the target anchor according to the historical live broadcast information includes S1062 to S1064:
s1062, determining at least one target user according to the historical live broadcast information.
Specifically, the determining at least one target user according to the historical live broadcast information includes:
determining an attention user in the live broadcasting attention information according to a preset attention rule, and determining a watching user in the live broadcasting watching information according to a preset watching rule;
and determining a target user according to the concerned user and the watching user.
The preset attention rules include, but are not limited to, attention duration of a user concerning a target anchor, online duration of the user, user activity and other rules; the preset viewing rules include, but are not limited to, a viewing time of the user viewing the target anchor, an interaction between the user and the anchor when viewing, and the like. In practical applications, the preset attention rule and the preset viewing rule may be determined according to actual needs, which is not specifically limited in the present application.
In a specific embodiment of the present application, the above example is continued, the preset attention rule is that the time length for the user to pay attention to the target anchor is longer than 24 hours, the preset viewing rule is that the viewing time length for the user to view the target anchor is longer than 15 minutes, and the number of the barrages sent when the user views the live broadcast is greater than or equal to 5. The method comprises the steps that 100 users who acquire an attention anchor in live broadcast attention information are screened out, and 50 attention users are screened out according to a preset attention rule (the attention duration is longer than 24 hours); 200 users who acquire live broadcast watching in the watching attention information are screened out to be 150 users according to a preset watching rule (the watching time of the user watching the target anchor broadcast is longer than 15 minutes, and the number of the barrage sent by the user when watching the live broadcast is larger than or equal to 5), and the finally determined number of the target users is 190 (wherein 10 of the 150 users are attention users).
In another specific embodiment of the present application, the determining at least one target user according to the historical live broadcast information may further be obtained by:
and inputting the live broadcasting attention information and the live broadcasting watching information into a user determination model for processing to obtain at least one target user output by the user determination model.
The user determination model is a pre-trained data screening model, a preset attention rule and a preset watching rule which are actually needed can be input into the model, and the live broadcast attention information and the live broadcast watching information are input into the model, so that the relevant information of the target user can be obtained.
S1604, counting the position information of the at least one target user, and generating a position information set.
In practical application, a plurality of target users can be determined according to live broadcast attention information included in historical live broadcast information and live broadcast watching information corresponding to each live broadcast, then a preset target user quality calculation method can be adopted based on interaction information between the target users and the anchor broadcast to calculate the quality score of each target user, wherein the preset target user quality coefficient can be as follows: and when the target user sends a bullet screen, the quality of the target user is divided into the number of people and the corresponding bullet screen quality score (the number of people is 0.5), and when the target user sends a gift, the quality of the target user is divided into the number of people and the corresponding gift quality score (the gift value is 2), and the quality scores of all the target users are counted and combined with corresponding position information to generate a position information set.
In a specific embodiment of the present application, following the above example, 390 target users are determined according to the live broadcast information of the main broadcast a in the past 3 fields, the position information of the 390 target users is counted, the statistical result is that there are 100 people in beijing, 40 people in shijiazhuang, and 50 people in shenyang … …, meanwhile, the quality score of the target user in each city is calculated according to the preset target user quality coefficient, and finally, all the quality scores are added to generate a position information set: { Beijing 600, Shijiazhu 240, Shenyang 150 … … }.
Specifically, counting the location information of the at least one target user, and generating a location information set, including:
searching the position information of each target user in the historical live broadcast information;
and generating a position information set according to the position information of each target user.
In practical application, after the target users are determined according to the historical live broadcast information, the position information of each target user can be searched in the historical live broadcast information and a position information set is generated, the quality score of each target user can also be calculated, and the position information set is generated according to the position and the quality score of each target user.
In a specific embodiment of the present application, along the above example, after determining that the target users are 390, finding locations corresponding to 390 target users, and finding 100 target users whose locations are in beijing, 40 target users whose locations are in shijiazhuang, and 50 target users whose locations are in sheng yang … …, a location information set { beijing 100 people, shijiazhuang 40 people, sheng yang 50 people … … } can be generated.
In another embodiment of the present application, following the above example, after determining that the target users are 390, searching the location and interaction information of 390 target users, a location information set { beijing 600, shi jia 240, sheng yang 150 … … } may be generated according to the target user quality calculation method.
Specifically, generating a location information set according to the location information of each target user includes:
generating an initial position information set according to the position information of each user, and sequencing the position information in the initial position information set;
and determining a preset amount of position information according to the sorting result to generate a position information set.
The initial position information set can be understood as a set which is not sorted and contains position information of each city, the set is sorted, and the city position with high user quality can be quickly obtained according to the sorting result.
In practical application, the ranking of the position information in the initial position information set according to the user quality score may be performed from top to bottom, specifically, the ranking of the position information in the initial position information set includes:
and sorting the position information in the initial position information set from top to bottom according to the user quality score of each position information.
In a specific embodiment of the present application, following the above example, the user quality scores of cities are counted, where the user quality scores of cities are 600 in beijing (actual number of 100 people, gift quality score 300, and bullet screen quality score 200), 450 in texas (actual number of 45 people, gift quality score 300, and bullet screen quality score 105), 240 in shijiazhuang (actual number of 40 people, gift quality score 50, and bullet screen quality score 150), and a location information set { 1: beijing 600, 2: texas 450, 3: stone house 240 }.
After the position information in the initial position information set is sorted and the sorting result is obtained, the position information set can be generated in two ways. A first way to generate the position information set is to generate the position information set according to preset position information.
Specifically, determining the position information set according to the sorting result includes:
and determining a preset amount of position information according to the sorting result to generate a position information set.
In a specific embodiment of the present application, following the above example, the user quality of each city is counted, the user quality of the cities in beijing is 600 (actual number of 100 people, gift quality score 300, and bullet screen quality score 200), the user quality of texas is 450 (actual number of 45 people, gift quality score 300, bullet screen quality score 105), the user quality of shijiazhuang is 240 (actual number of 40 people, gift quality score 50, and bullet screen quality score 150), and the like, all cities are ranked from high to low according to the quality scores, the ranking result is "1, beijing, 2, texas, 3, and shijiazhuan", the top 2 cities are measured according to the preset number, and the position information set { 1: beijing 600, 2: texas 450 }.
In addition to the above-described manner of generating the location information set according to the preset location information, the location information set may also be generated according to a user quality score exceeding a preset user quality score.
Specifically, determining the position information set according to the sorting result includes:
and determining the position information of which the user quality score exceeds the preset user quality score according to the sequencing result to generate a position information set.
In a specific embodiment of the present application, following the above example, the user quality of each city is counted, the user quality scores of cities such as 600 for beijing (actual number of 100 people, gift quality score 300, and bullet screen quality score 200), 450 for texas (actual number of 45 people, gift quality score 300, and bullet screen quality score 105), 240 for shijiazhuang (actual number of 40 people, gift quality score 50, and bullet screen quality score 150), and all cities are ranked from high to low according to the quality scores, and the ranking result is "1, beijing, 2, texas, 3, and shijiazhuan", and a location information set { 1: beijing 600, 2: texas 450 }.
Step 108: and generating a user edge computing node set according to the position information set.
Specifically, generating a user edge computing node set according to the location information set includes:
determining target location information in the set of location information;
determining a corresponding target edge computing node according to the target position information;
and generating a user edge computing node set according to each target edge computing node.
The user edge computing node receives the live stream pushed by the anchor edge computing node and sends the live stream to a user watching the live stream. When a user accesses a website or watches live broadcasting, data can be pulled according to the edge computing node closest to the user in the user edge computing node set, so that the response speed of access is improved.
In practical application, the location information set includes a plurality of cities, each city may have one or more user edge computing nodes according to actual conditions, or each user edge computing node corresponds to one or more cities, and after the target location information is determined, a user edge computing node set including at least one user edge computing node may be generated according to the target location information.
In an embodiment of the present application, following the above example, the position information set is { 1: beijing 600, 2: texas 450 }. Determining that the target position information is Beijing in the position information set, and determining that 3 target edge computing nodes corresponding to the Beijing are G1, G2 and G3 respectively; and then determining that the target position information is Texas, and 2 target edge computing nodes corresponding to Texas are G4 and G5 respectively, and generating a user edge computing node set of { G1, G2, G3, G4 and G5} according to the target edge computing nodes corresponding to the two cities.
Specifically, determining a corresponding target edge computing node according to the target position information includes:
determining pushing range information according to the target position information;
and determining the edge computing node in the pushing range information as a target edge computing node.
For example, the target location information is three zones B1, B2, and B3 in the city B, each zone corresponds to one user edge computing node, and if the push range is the entire city B, the push range information is three zones B1, B2, and B3, and the live stream is pushed to the user edge computing nodes corresponding to the three zones. However, in practical applications, the push range is determined to be the whole B city, which may reduce the delay of the first frame when all users in the B city watch live broadcast, but in consideration of cost, the push range with the maximum profit needs to be determined, for example, if the user quality score in B2 is high, the push range is determined to be the B2 area, and the live broadcast stream is pushed only to the user edge computing node corresponding to the B2 area. When the users in the b1 and b2 areas watch the live broadcast, the live broadcast stream can be obtained from the user edge computing node corresponding to the b2 area, so that the speed of loading the live broadcast first frame picture is improved.
In addition, the push range can also be determined according to the live content, the live position and other information of the anchor. Taking the live content of the anchor as an example, and taking the live content of the target anchor as a game, the ages of target users in three areas B1, B2 and B3 in the city B are obtained, and the ages of the target users in the area B1 are determined to be younger, so that the live stream is pushed to the user edge computing node corresponding to the area B1. Taking the live broadcast position of the anchor as an example, the target anchor is often live broadcast in China, and then, few users watching the live broadcast abroad are available, so that the push range is not necessary to be pushed to abroad.
In a specific embodiment of the present application, following the above example, it is determined that the target location information is beijing, and if it is desired to push the entire beijing, it is determined that the required edge computing nodes are G1, G2, and G3 according to the push range information, and the live stream is pushed to the 3 user edge computing nodes.
In another specific embodiment of the present application, the above example is used, it is determined that the target location information is beijing, it is found that target users in the sunny region and the eastern city region are concentrated, and the user quality is high, the push range is the sunny region and the eastern city region, and the required edge computing node is determined to be G1 according to the push range information, and the live stream is pushed to the 1 user edge computing node.
Step 110: and pushing the target live broadcast stream to the user edge computing nodes in the user edge computing node set.
In practical application, when the anchor is broadcasted, the live stream is pushed to the edge computing node closest to the anchor, and is actively pushed to the user edge computing node in the user edge computing node set, so that when a user near the user edge computing node which pushes the live stream watches the live stream, the loading speed is increased.
Optionally, after pushing the target live stream to a user edge computing node in the user edge computing node set, the method further includes:
and after the target anchor finishes live broadcasting, storing live broadcasting watching information corresponding to the target live broadcasting stream into a database.
In practical application, after the target anchor finishes live broadcasting, live broadcasting watching information corresponding to the live broadcasting stream of the live broadcasting is stored in a database so as to predict a user edge computing node set to be pushed in the next live broadcasting.
According to the live broadcast delay optimization method, a target live broadcast stream is received, and a target anchor is determined according to the target live broadcast stream; acquiring historical live broadcast information of the target anchor, and counting a position information set of a target user corresponding to the target anchor according to the historical live broadcast information; generating a user edge computing node set according to the position information set; and pushing the target live broadcast stream to the user edge computing nodes in the user edge computing node set. The distribution condition of watching users of the anchor can be predicted according to the historical live broadcast information of the anchor, so that the live broadcast stream is pushed in advance to achieve the preheating effect; when a watching user enters a live broadcasting room, the live broadcasting video stream can be quickly sent to the watching user through the edge computing node which acquires the live broadcasting stream in advance, so that the effects of improving the speed of loading the live broadcasting picture and optimizing the delay of the live broadcasting first frame are realized, and the watching experience of the user is improved.
The following description will further describe the live broadcast delay optimization method with reference to fig. 2 and fig. 3, by taking an application of the live broadcast delay optimization method provided by the present application to the live broadcast of the food of zhang san as an example. Fig. 2 shows a schematic structural diagram of a live broadcast delay optimization method applied to the direct broadcast of the food for Zhang III according to an embodiment of the present application. As shown in fig. 2, live broadcasting is started in shanghai by anchor program three, and the highest quality score is determined according to historical live broadcasting information of anchor program three, so that the user edge computing nodes D1 and D2 which are determined to be corresponding to both are user edge computing nodes pushed in advance, and then the live broadcasting stream is pushed to two user edge computing nodes D1 and D2, so that when users in the same category watch the live broadcasting of anchor program three, the live broadcasting stream does not need to be obtained from the anchor edge computing node S1, but the live broadcasting stream is obtained from the user edge computing nodes D1 and D2, thereby achieving the effect of optimizing the delay of the first frame of the live broadcasting and improving the watching experience of the users.
Fig. 3 shows a processing flow chart of a live broadcast delay optimization method applied to the food live broadcast of zhang san according to an embodiment of the present application, which specifically includes the following steps:
step 302: receiving a live broadcast stream, and determining a target anchor as a food anchor according to the live broadcast stream.
Specifically, each anchor edge computing node receives a plurality of live streams of different anchors all the time, and each anchor edge computing node can determine information such as the identity and the live type of the anchor according to the live streams.
In an embodiment of the present application, following the previous example, after zhangsan is started to live in shanghai, the anchor edge computing node S1 closest to zhangsan receives a live stream of zhangsan. After receiving the live broadcast stream, the anchor edge computing node S1 analyzes the live broadcast stream, and determines that the identity of the anchor is zhang san and the live broadcast type is gourmet live broadcast.
Step 304: and acquiring the live broadcasting attention information of the third anchor program and the live broadcasting watching information of the nearest 3 fields of the third anchor program.
The live broadcasting attention information is attention user information for paying attention to anchor program three, and the live broadcasting watching information is watching user information for watching anchor program three live broadcasting.
Specifically, after the anchor edge computing node determines the identity of the target anchor, the live broadcast attention information and the live broadcast viewing information of the target anchor, that is, the historical live broadcast information of the target anchor, may be acquired. The number of the live broadcasts needing to be acquired is determined, the live broadcast watching information corresponding to each live broadcast is acquired, and the live broadcast watching information of each live broadcast and the live broadcast attention information of the target anchor are used as historical live broadcast data.
In a specific embodiment of the present application, following the above example, if the number of sessions for obtaining historical live broadcasts is preset to be 3, the anchor edge computing node S1 obtains a session identifier corresponding to each live broadcast of 3 live broadcasts before anchor zhangsan, the session identifiers of the latest 3 live broadcasts are respectively Z1, Z2, and Z3, the anchor edge computing node S1 finds out corresponding live broadcast viewing information Z11, Z21, and Z31 in the database according to the session identifier of the 3 historical live broadcasts, and uses the attention information of the live broadcast viewing information Z11, Z21, and Z31 and the anchor zhangsan as live broadcast historical data of this time.
Step 306: and determining an attention user in the live broadcasting attention information according to a preset attention rule, determining a watching user in the live broadcasting watching information according to a preset watching rule, and determining a target user according to the attention user and the watching user.
Wherein, the attention rule is preset that the attention anchor duration exceeds 48 hours, and the watching rule is that the watching duration of the current time exceeds 30 minutes.
Specifically, after the historical live broadcast data of the main broadcast three is obtained, a target user can be determined according to the historical live broadcast data, and the target user is a predicted user watching the next live broadcast. And screening the concerned users from the live broadcast concerned information, screening the corresponding watching users from the live broadcast watching information corresponding to each live broadcast, and determining the target users according to the concerned users and the watching users corresponding to each live broadcast.
In a specific embodiment of the application, the above example is continued, a total of 300 people who pay attention to the anchor third are obtained according to the live broadcast attention information of the anchor third, and 200 people who pay attention to the anchor third are screened out according to a preset attention rule; according to 3 live broadcast watching information Z11, Z21 and Z31 of Chassian III, respectively acquiring that the number of watching people of Z1 live broadcast is 500, the number of watching people of Z2 live broadcast is 400 and the number of watching people of Z3 live broadcast is 600, screening out 200, 100 and 300 watching users of each live broadcast according to a preset watching rule, and determining the total number of 1000 people of a target user according to 400 people of a concerned user and 200, 100 and 300 people of the watching users of 3 live broadcast.
Step 308: and searching the position information of each target user in the historical live broadcast information.
Specifically, after the target users are determined, the number of target users in which city is represented according to the geographic location of the target users is large, the quality score of each target user is calculated, and the quality score of the target user in which city is represented by combining the geographic location of the target user is high.
In a specific embodiment of the present application, following the above example, the location information corresponding to each of 1000 target users is found in the historical live broadcast information: "user ID1: le mountain, user ID2: long sand. Pu Tian ", and calculate the respective corresponding quality scores of 1000 target users: "user ID1:1.2, user ID2:1.
Step 310: and generating an initial position information set according to the position information of each user, sequencing the position information in the initial position information set, and determining a preset number of position information according to a sequencing result to generate the position information set.
Specifically, after the location information of each target user is obtained, an initial location information set including the number of target users in each city and the user quality score may be generated, and the location information in the initial location information set may be sorted from high to low according to the user quality score, so as to screen out the location information of a preset number to generate the location information set.
In a specific embodiment of the present application, following the above example, the number of target users in each city is counted, the statistical results are 12 cities such as "Chengdu 300, Shenzhen 80 … … Changsha 120", etc., the user quality in each city is calculated, the statistical results are ranked according to the user quality from top to bottom, and the ranking result is "1: success rate 300, 2: chongqing 140, 3: long sand 120 … … 12: shanghai 10 ", take the first 3 cities as required to generate a position information set { composition is: 300, Chongqing: 140 persons, Changsha: 120}.
Step 312: determining target position information in the position information set, determining pushing range information according to the target position information, determining edge computing nodes in the pushing range information as target edge computing nodes, and generating an edge computing node set according to each target edge computing node.
Specifically, the city with the maximum benefit after pushing is determined according to actual requirements, and the pushing range information can be determined according to the specific position of each user in the city after the city is determined, so that the maximum benefit is obtained from the minimized cost.
In a specific embodiment of the present application, following the above example, a city with destination location information as a turn-down is determined in the location information set, a push range can be determined as a turn-down according to location information of each destination user in the turn-down, 2 edge computing nodes in the push range are determined as destination edge computing nodes, and an edge computing node set { D1, D2} is generated.
Step 314: and pushing the target live broadcast stream to the user edge computing nodes in the user edge computing node set.
Specifically, the live stream may be pushed to at least one user edge computing node in the user edge computing node set.
In a specific embodiment of the present application, following the above example, there are 2 edge computing nodes (D1, D2) in the edge computing node set, and before the next start of the main program three, the live stream is transmitted to the 2 user edge computing nodes in advance, so that the first frame delay of users in the three cities while watching the live program three is reduced.
The method is applied to the live broadcast delay optimization of the food live broadcast of the anchor program III, and the target anchor is determined according to the target live broadcast stream by receiving the target live broadcast stream; acquiring historical live broadcast information of the target anchor, and counting a position information set of a target user corresponding to the target anchor according to the historical live broadcast information; generating a user edge computing node set according to the position information set; and pushing the target live broadcast stream to the user edge computing nodes in the user edge computing node set. The target user distribution condition in the next live broadcast can be predicted according to the historical live broadcast information of Zhang III, so that the live broadcast stream is pushed in advance to achieve a preheating effect; when a user enters a live broadcast room, the live broadcast video stream can be quickly sent to a watching user through the user edge computing node which acquires the live broadcast stream in advance, so that the effects of improving the speed of loading the live broadcast picture and optimizing the delay of the live broadcast first frame are realized, and the watching experience of the user is improved. The broadcasting information of the third anchor program can be actively pushed to all users within the range, more users are attracted to watch the live broadcasting of the third anchor program, and more people can be obtained for the third anchor program.
Corresponding to the above method embodiment, the present application further provides an embodiment of a live broadcast delay optimization apparatus, and fig. 4 shows a schematic structural diagram of a live broadcast delay optimization apparatus provided in an embodiment of the present application. As shown in fig. 4, the apparatus includes:
a determining module 402 configured to receive a target live stream, and determine a target anchor according to the target live stream;
a counting module 404, configured to obtain historical live broadcast information of the target anchor, and count a position information set of a target user corresponding to the target anchor according to the historical live broadcast information, where the position information set includes at least one piece of position information;
a generating module 406 configured to generate a set of user edge computing nodes from the set of location information;
a pushing module 408 configured to push the target live stream to a user edge computing node in the user edge computing node set.
Optionally, the statistic module 404 may be further configured to:
and acquiring live broadcasting attention information and live broadcasting watching information of the target anchor, wherein the live broadcasting attention information is information of an attention person who pays attention to the target anchor, and the live broadcasting watching information is information of a watching person who watches the live broadcasting of the target anchor.
Optionally, the statistic module 404 may be further configured to:
and determining the preset number of live broadcast fields of the target anchor, and acquiring live broadcast watching information corresponding to each live broadcast field.
Optionally, the statistic module 404 may be further configured to:
acquiring a field identifier of each live broadcast;
and acquiring corresponding live broadcast watching information in a database according to each live broadcast field identification.
Optionally, the statistic module 404 may be further configured to:
determining at least one target user according to the historical live broadcast information;
and counting the position information of the at least one target user and generating a position information set.
Optionally, the statistic module 404 may be further configured to:
the determining at least one target user according to the historical live broadcast information includes:
determining an attention user in the live broadcasting attention information according to a preset attention rule, and determining a watching user in the live broadcasting watching information according to a preset watching rule;
and determining a target user according to the concerned user and the watching user.
Optionally, the statistic module 404 may be further configured to:
the determining at least one target user according to the historical live broadcast information includes:
and inputting the live broadcasting attention information and the live broadcasting watching information into a user determination model for processing to obtain at least one target user output by the user determination model.
Optionally, the statistic module 404 may be further configured to:
searching the position information of each target user in the historical live broadcast information;
and generating a position information set according to the position information of each target user.
Optionally, the statistic module 404 may be further configured to:
generating an initial position information set according to the position information of each user, and sequencing the position information in the initial position information set;
and determining a preset amount of position information according to the sorting result to generate a position information set.
Optionally, the generating module 406 may be further configured to:
and sorting the position information in the initial position information set from top to bottom according to the user quality score of each position information.
Optionally, the generating module 406 may be further configured to:
and determining the position information with preset quantity or the position information with the user quality score exceeding the preset user quality score according to the sorting result to generate a position information set.
Optionally, the generating module 406 may be further configured to:
determining target location information in the set of location information;
determining a corresponding target edge computing node according to the target position information;
and generating an edge computing node set according to each target edge computing node.
Optionally, the generating module 406 may be further configured to:
determining pushing range information according to the target position information;
and determining the edge computing node in the pushing range information as a target edge computing node.
Optionally, the generating module 406 may be further configured to:
and after the target anchor finishes live broadcasting, storing live broadcasting watching information corresponding to the target live broadcasting stream into a database.
Optionally, the statistic module 404 may be further configured to:
and counting the city information set of the target user corresponding to the target anchor according to the historical live broadcast information.
The live broadcast delay optimization device comprises a determining module, a determining module and a processing module, wherein the determining module is configured to receive a target live broadcast stream and determine a target anchor according to the target live broadcast stream; the statistical module is configured to acquire historical live broadcast information of the target anchor and perform statistics on a position information set of a target user corresponding to the target anchor according to the historical live broadcast information; a generating module configured to generate a set of user edge computing nodes from the set of location information; a pushing module configured to push the target live stream to a user edge computing node in the user edge computing node set. The distribution condition of watching users in next live broadcast can be predicted according to the historical live broadcast information of the anchor, so that the live broadcast stream is pushed in advance to achieve the preheating effect; when a watching user enters a live broadcasting room, the live broadcasting video stream can be rapidly sent to the watching user through the edge computing node which acquires live broadcasting data in advance, the effect of improving the speed of loading live broadcasting pictures and optimizing the delay of the live broadcasting first frame is achieved, and therefore the watching experience of the user is improved.
The foregoing is an exemplary scheme of a live broadcast delay optimization apparatus according to this embodiment. It should be noted that the technical solution of the live broadcast delay optimization apparatus and the technical solution of the live broadcast delay optimization method belong to the same concept, and details that are not described in detail in the technical solution of the live broadcast delay optimization apparatus can be referred to the description of the technical solution of the live broadcast delay optimization method.
Fig. 5 illustrates a block diagram of a computing device 500 provided according to an embodiment of the present application. The components of the computing device 500 include, but are not limited to, a memory 510 and a processor 520. Processor 520 is coupled to memory 510 via bus 530, and database 550 is used to store data.
Computing device 500 also includes access device 540, access device 540 enabling computing device 500 to communicate via one or more networks 560. Examples of such networks include the Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the internet. The access device 540 may include one or more of any type of network interface, e.g., a Network Interface Card (NIC), wired or wireless, such as an IEEE802.11 Wireless Local Area Network (WLAN) wireless interface, a worldwide interoperability for microwave access (Wi-MAX) interface, an ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a bluetooth interface, a Near Field Communication (NFC) interface, and so forth.
In one embodiment of the application, the above-described components of computing device 500 and other components not shown in FIG. 5 may also be connected to each other, such as by a bus. It should be understood that the block diagram of the computing device architecture shown in FIG. 5 is for purposes of example only and is not limiting as to the scope of the present application. Those skilled in the art may add or replace other components as desired.
Computing device 500 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., tablet, personal digital assistant, laptop, notebook, netbook, etc.), mobile phone (e.g., smartphone), wearable computing device (e.g., smartwatch, smartglasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or PC. Computing device 500 may also be a mobile or stationary server.
Wherein processor 520, when executing the computer instructions, performs the steps of the live delay optimization method.
The above is an illustrative scheme of a computing device of the present embodiment. It should be noted that the technical solution of the computing device and the technical solution of the live broadcast delay optimization method belong to the same concept, and details that are not described in detail in the technical solution of the computing device can all be referred to in the description of the technical solution of the live broadcast delay optimization method.
An embodiment of the present application further provides a computer readable storage medium storing computer instructions, which when executed by a processor, implement the steps of the live broadcast delay optimization method as described above.
The above is an illustrative scheme of a computer-readable storage medium of the present embodiment. It should be noted that the technical solution of the storage medium and the technical solution of the live broadcast delay optimization method belong to the same concept, and details that are not described in detail in the technical solution of the storage medium can be referred to the description of the technical solution of the live broadcast delay optimization method.
The foregoing description of specific embodiments of the present application has been presented. Other embodiments are within the scope of the following 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 desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The computer instructions comprise computer program code which may be in the form of source code, object code, an executable file or some intermediate form, or the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
It should be noted that, for the sake of simplicity, the above-mentioned method embodiments are described as a series of acts or combinations, but those skilled in the art should understand that the present application is not limited by the described order of acts, as some steps may be performed in other orders or simultaneously according to the present application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
The preferred embodiments of the present application disclosed above are intended only to aid in the explanation of the application. Alternative embodiments are not exhaustive and do not limit the invention to the precise embodiments described. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the application and its practical applications, to thereby enable others skilled in the art to best understand and utilize the application. The application is limited only by the claims and their full scope and equivalents.

Claims (18)

1. A live broadcast delay optimization method is applied to a live broadcast stream server and comprises the following steps:
receiving a target live broadcast stream, and determining a target anchor according to the target live broadcast stream;
acquiring historical live broadcast information of the target anchor, and counting a position information set of a target user corresponding to the target anchor according to the historical live broadcast information, wherein the position information set comprises at least one piece of position information;
generating a user edge computing node set according to the position information set;
and pushing the target live broadcast stream to the user edge computing nodes in the user edge computing node set.
2. The live delay optimization method of claim 1, wherein obtaining historical live information of the target anchor comprises:
and acquiring live broadcasting attention information and live broadcasting watching information of the target anchor, wherein the live broadcasting attention information is attention user information for paying attention to the target anchor, and the live broadcasting watching information is watching user information for watching the live broadcasting of the target anchor.
3. The live delay optimization method of claim 2, wherein obtaining live viewing information of the target anchor comprises:
and determining the preset number of live broadcast fields of the target anchor, and acquiring live broadcast watching information corresponding to each live broadcast field.
4. The live broadcast delay optimization method of claim 3, wherein obtaining live broadcast viewing information corresponding to each live broadcast session comprises:
acquiring a field identifier of each live broadcast;
and acquiring corresponding live broadcast watching information in a database according to each live broadcast field identification.
5. The live broadcast delay optimization method of claim 1, wherein the counting a set of location information of a target user corresponding to the target anchor according to the historical live broadcast information comprises:
determining at least one target user according to the historical live broadcast information;
and counting the position information of the at least one target user and generating a position information set.
6. The live delay optimization method of claim 5, wherein the historical live information includes live attention information and live viewing information;
the determining at least one target user according to the historical live broadcast information includes:
determining an attention user in the live broadcasting attention information according to a preset attention rule, and determining a watching user in the live broadcasting watching information according to a preset watching rule;
and determining a target user according to the concerned user and the watching user.
7. The live delay optimization method of claim 5, wherein the historical live information includes live attention information and live viewing information;
the determining at least one target user according to the historical live broadcast information includes:
and inputting the live broadcasting attention information and the live broadcasting watching information into a user determination model for processing to obtain at least one target user output by the user determination model.
8. The live delay optimization method of claim 5, wherein counting location information of the at least one target user and generating a set of location information comprises:
searching the position information of each target user in the historical live broadcast information;
and generating a position information set according to the position information of each target user.
9. The live delay optimization method of claim 8, wherein generating a set of location information from the location information of each target user comprises:
generating an initial position information set according to the position information of each user, and sequencing the position information in the initial position information set;
and determining a preset amount of position information according to the sorting result to generate a position information set.
10. The live delay optimization method of claim 9, wherein sorting the location information in the initial set of location information comprises:
and sorting the position information in the initial position information set from top to bottom according to the user quality score of each position information.
11. The live delay optimization method of claim 10, wherein sorting the location information in the initial set of location information according to a user quality score of each location information from top to bottom comprises:
and determining the position information with preset quantity or the position information with the user quality score exceeding the preset user quality score according to the sorting result to generate a position information set.
12. The live delay optimization method of claims 1-11, wherein generating a set of user edge compute nodes from the set of location information comprises:
determining target location information in the set of location information;
determining a corresponding target edge computing node according to the target position information;
and generating a user edge computing node set according to each target edge computing node.
13. The live broadcast delay optimization method of claim 12, wherein determining a corresponding target edge compute node based on the target location information comprises:
determining pushing range information according to the target position information;
and determining the edge computing node in the pushing range information as a target edge computing node.
14. The live broadcast delay optimization method of claim 12, wherein after pushing the target live broadcast stream to a user edge compute node in the set of user edge compute nodes, further comprising:
and after the target anchor finishes live broadcasting, storing live broadcasting watching information corresponding to the target live broadcasting stream into a database.
15. The live broadcast delay optimization method of claims 1-11, wherein counting a set of location information of a target user corresponding to the target anchor according to the historical live broadcast information comprises:
and counting the city information set of the target user corresponding to the target anchor according to the historical live broadcast information.
16. A live broadcast delay optimization apparatus, comprising:
the determining module is configured to receive a target live stream and determine a target anchor according to the target live stream;
the statistical module is configured to acquire historical live broadcast information of the target anchor and perform statistics on a position information set of a target user corresponding to the target anchor according to the historical live broadcast information;
a generating module configured to generate a set of user edge computing nodes from the set of location information;
a pushing module configured to push the target live stream to a user edge computing node in the user edge computing node set.
17. A computing device comprising a memory, a processor, and computer instructions stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any one of claims 1-15 when executing the computer instructions.
18. A computer-readable storage medium storing computer instructions, which when executed by a processor, perform the steps of the method of any one of claims 1 to 15.
CN202111348858.3A 2021-11-15 2021-11-15 Live broadcast delay optimization method and device Active CN114070852B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111348858.3A CN114070852B (en) 2021-11-15 2021-11-15 Live broadcast delay optimization method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111348858.3A CN114070852B (en) 2021-11-15 2021-11-15 Live broadcast delay optimization method and device

Publications (2)

Publication Number Publication Date
CN114070852A true CN114070852A (en) 2022-02-18
CN114070852B CN114070852B (en) 2024-03-12

Family

ID=80272241

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111348858.3A Active CN114070852B (en) 2021-11-15 2021-11-15 Live broadcast delay optimization method and device

Country Status (1)

Country Link
CN (1) CN114070852B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114679598A (en) * 2022-03-24 2022-06-28 上海哔哩哔哩科技有限公司 Live broadcast pushing method and device
CN114760487A (en) * 2022-03-18 2022-07-15 阿里巴巴（中国）有限公司 Live broadcasting method and device
CN115460427A (en) * 2022-08-26 2022-12-09 上海哔哩哔哩科技有限公司 Live broadcast scheduling method and device, computing equipment and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106851343A (en) * 2017-01-23 2017-06-13 百度在线网络技术（北京）有限公司 For the method and apparatus of net cast
CN106846032A (en) * 2016-11-24 2017-06-13 北京小米移动软件有限公司 Interactive approach, apparatus and system in electric business application program
WO2019062391A1 (en) * 2017-09-29 2019-04-04 上海掌门科技有限公司 Method and device for pushing anchor information to user
CN109951716A (en) * 2019-03-26 2019-06-28 北京达佳互联信息技术有限公司 A kind of main broadcaster's dispatching method, device, electronic equipment and readable storage medium storing program for executing
CN110868339A (en) * 2019-11-25 2020-03-06 北京三体云时代科技有限公司 Node distribution method and device, electronic equipment and readable storage medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106846032A (en) * 2016-11-24 2017-06-13 北京小米移动软件有限公司 Interactive approach, apparatus and system in electric business application program
CN106851343A (en) * 2017-01-23 2017-06-13 百度在线网络技术（北京）有限公司 For the method and apparatus of net cast
WO2019062391A1 (en) * 2017-09-29 2019-04-04 上海掌门科技有限公司 Method and device for pushing anchor information to user
CN109951716A (en) * 2019-03-26 2019-06-28 北京达佳互联信息技术有限公司 A kind of main broadcaster's dispatching method, device, electronic equipment and readable storage medium storing program for executing
CN110868339A (en) * 2019-11-25 2020-03-06 北京三体云时代科技有限公司 Node distribution method and device, electronic equipment and readable storage medium

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114760487A (en) * 2022-03-18 2022-07-15 阿里巴巴（中国）有限公司 Live broadcasting method and device
CN114679598A (en) * 2022-03-24 2022-06-28 上海哔哩哔哩科技有限公司 Live broadcast pushing method and device
CN114679598B (en) * 2022-03-24 2023-11-21 上海哔哩哔哩科技有限公司 Live broadcast pushing method and device
CN115460427A (en) * 2022-08-26 2022-12-09 上海哔哩哔哩科技有限公司 Live broadcast scheduling method and device, computing equipment and storage medium
CN115460427B (en) * 2022-08-26 2024-03-12 上海哔哩哔哩科技有限公司 Live broadcast scheduling method, device, computing equipment and storage medium

Also Published As

Publication number Publication date
CN114070852B (en) 2024-03-12

Similar Documents

Publication Publication Date Title
CN114070852A (en) Live broadcast delay optimization method and device
CN110769270B (en) Live broadcast interaction method and device, electronic equipment and storage medium
CN110278466B (en) Short video advertisement putting method, device and equipment
CN107666615A (en) Method for digging, device and the server of potentiality main broadcaster user
US11496603B2 (en) Providing content based on event related information
CN108810052B (en) Live broadcast server selection method and device
US20140344286A1 (en) Method and apparatus for displaying webcast roomss
US10200268B2 (en) Methods and systems for congestion-based content delivery
CN111866528A (en) Live program pushing method and readable storage medium
US10614079B1 (en) Identifying a level of relevancy of a keyword cluster related to an event category for a given time period relative to the event
CN103718166A (en) Information processing apparatus, information processing method, and computer program product
CN106326297B (en) Application program recommendation method and device
WO2014144225A2 (en) Displaying social media content
CN113316015B (en) Bullet screen processing method, device and system
CN103997662A (en) Program pushing method and system
WO2022193835A1 (en) Data processing method, live streaming method, authentication server and live streaming data server
WO2023098030A1 (en) Method and apparatus for determining click-farming of live streaming room
CN113709527B (en) Method and device for paying attention to anchor in multi-anchor scene
CN103942275A (en) Video identification method and device
KR101778660B1 (en) System for providing contents and online community platform based on Social Networking Service fusion type
CN113766282A (en) Live video processing method and device
CN111026969B (en) Content recommendation method and device, storage medium and server
CN108415908B (en) Multimedia data processing method and server
CN111782919A (en) Online document processing method and device, computer equipment and storage medium
US11368758B2 (en) VOD service system based on AI video learning platform

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant