WO2023077813A1 - 确定直播间刷量的方法及装置 - Google Patents

确定直播间刷量的方法及装置 Download PDF

Info

Publication number
WO2023077813A1
WO2023077813A1 PCT/CN2022/099477 CN2022099477W WO2023077813A1 WO 2023077813 A1 WO2023077813 A1 WO 2023077813A1 CN 2022099477 W CN2022099477 W CN 2022099477W WO 2023077813 A1 WO2023077813 A1 WO 2023077813A1
Authority
WO
WIPO (PCT)
Prior art keywords
terminal
live broadcast
information
room
historical
Prior art date
Application number
PCT/CN2022/099477
Other languages
English (en)
French (fr)
Inventor
孙袁袁
Original Assignee
上海哔哩哔哩科技有限公司
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 上海哔哩哔哩科技有限公司 filed Critical 上海哔哩哔哩科技有限公司
Publication of WO2023077813A1 publication Critical patent/WO2023077813A1/zh

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00Network architectures or network communication protocols for network security
    • H04L63/14Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
    • H04L63/1408Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
    • H04L63/1425Traffic logging, e.g. anomaly detection
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47End-user applications
    • H04N21/478Supplemental services, e.g. displaying phone caller identification, shopping application
    • H04N21/4788Supplemental services, e.g. displaying phone caller identification, shopping application communicating with other users, e.g. chatting

Definitions

  • the present application relates to the technical field of live webcasting, and in particular to a method for determining the swiping amount between live broadcasts.
  • the present application also relates to a device for determining the amount of brushing between live broadcasts, a computing device, a computer-readable storage medium, and a computer program.
  • the embodiment of the present application provides a method for determining the amount of brushing between live broadcasts.
  • the present application also relates to a device for determining the amount of swiping in a live room, a computing device, a computer-readable storage medium, and a computer program to solve the problems existing in the prior art that the method for determining whether the amount of swiping in a live room is single, problem with lower accuracy.
  • a method for determining the amount of brushing between live broadcasts including:
  • the historical ratio of the terminal and the current ratio of the terminal it is determined whether there is a brushing situation in the target live broadcast room.
  • a device for determining the amount of brushing between live broadcasts including:
  • the statistical module is configured to count the historical terminal information of the live broadcast platform and determine the historical proportion of terminals
  • the collection module is configured to collect the current terminal information of the target live broadcast room, and determine the current ratio of the terminal based on the current terminal information;
  • the determining module is configured to determine whether there is a brushing situation in the target live broadcast room according to the historical ratio of the terminal and the current ratio of the terminal.
  • a computing device including a memory, a processor, and computer instructions stored in the memory and operable on the processor.
  • the processor executes the computer instructions, the computer instructions are implemented. Describe the steps of the method for determining the swiping volume of the live room.
  • a computer-readable storage medium which stores computer instructions, and when the computer instructions are executed by a processor, the steps of the method for determining the amount of inter-broadcasting of live broadcasts are implemented.
  • a computer program is provided, wherein, when the computer program is executed in a computer, the computer is instructed to execute the steps of the above-mentioned method for determining the amount of brushing between live broadcasts.
  • the method for determining the number of brushes in the live broadcast room is to count the historical terminal information of the live broadcast platform, determine the historical proportion of the terminal; collect the current terminal information of the target live broadcast room, and determine the current proportion of the terminal based on the current terminal information; according to the terminal
  • the historical ratio and the current ratio of the terminal are used to determine whether there is a brushing situation in the target live broadcast room.
  • An embodiment of the present application realizes the statistics of the terminal information used by the viewers, and judges whether there is a brush volume in the live broadcast room according to the way of comparing the terminal information with the historical record, which enriches the means of judging the brush volume of the live room, and effectively improves the judgment The accuracy of brush volume.
  • FIG. 1 is a flow chart of a method for determining the amount of brushing between live broadcasts provided in the first embodiment of the present application
  • Fig. 2 is a statistical schematic diagram within a preset time interval of a certain type of live broadcast room provided by the first embodiment of the present application;
  • Fig. 3 is a processing flow chart of a method for determining the amount of brushing between live broadcasts provided by the second embodiment of the present application;
  • Fig. 4 is a processing flow chart of a method for determining the amount of brushing between live broadcasts provided by the third embodiment of the present application;
  • Fig. 5 is a schematic structural diagram of a device for determining the amount of brushing between live broadcasts provided by an embodiment of the present application
  • Fig. 6 is a structural block diagram of a computing device provided by an embodiment of the present application.
  • Live Popularity The number of viewers, the number of bullet screens, the number of gifts, etc. are calculated according to a certain ratio, and are used to rank the live broadcast platform according to the popularity.
  • Number of Live Broadcasters The real number of people watching the live broadcast room in real time.
  • Swipe volume By simulating normal user visits, a large number of false viewings are generated, that is, simulating watching live broadcast rooms through illegal means.
  • Terminal The device used by the user to watch the live broadcast, such as desktop computer, mobile phone, tablet computer, etc.
  • Terminal system the operating system corresponding to the terminal.
  • the client player is generally used to regularly report the heartbeat to count the number of people.
  • it is generally calculated by calculating the total number of people in the live broadcast room and judging whether the total number of people will increase sharply. Or a sudden drop, under normal circumstances, the number of people in a room increases gradually, and the number of people rises in a curve.
  • the live broadcast room with the number of users cannot accurately control the number of users. The number of people increased from 200 to 3000 within 2 minutes. As for the total number of people, it is not precise enough to judge whether the number of users is enough. If the control of the live broadcast room of the number of users is accurate enough, it can also simulate the effect of the slow increase of the total number of people. It is not accurate enough to judge only by the total number of people.
  • This application also relates to a device for determining the amount of brushing between live broadcasts, a computing device, and a computer-readable storage medium, as follows The examples are described in detail one by one.
  • Fig. 1 shows a flow chart of a method for determining the amount of intermittent live streaming according to an embodiment of the present application, which specifically includes the following steps:
  • Step 102 Count the historical terminal information of the live broadcast platform, and determine the historical proportion of terminals.
  • the live broadcast platform is a platform that provides users with various live broadcasts.
  • the anchor creates a live broadcast room on the live broadcast platform for live broadcast. Users can enter a live broadcast room to watch live broadcast through the live broadcast platform. In practical applications, users need to use terminal equipment to enter the live room, such as mobile phones, tablets, laptops, etc.
  • terminal equipment such as mobile phones, tablets, laptops, etc.
  • the live broadcast platform will obtain the information of the terminal used by the user, for example, a user A uses a mobile phone to enter the live broadcast room, a user B logs in to a computer and uses a browser to enter the live broadcast room, and so on.
  • the historical terminal information specifically refers to the terminal information of the terminals connected to the live broadcast platform in the past period of time, for example, the terminal information of the terminals watching the live broadcast in the past 24 hours.
  • the historical proportion of terminals specifically refers to the proportion of terminals that are classified based on subsequent processing rules after obtaining historical terminal information. For example, after the historical terminal information is collected, it is classified according to the historical terminal type, including web terminal and mobile terminal, then the historical proportion of terminals is web terminal: mobile terminal; if it is divided into web terminal, IOS terminal and Android terminal according to the historical terminal type , then the terminal history ratio is web: IOS: Android.
  • the specific form of the terminal historical ratio is not limited, and the actual application shall prevail.
  • the terminal types are divided into web terminal and mobile terminal as an example for explanation.
  • the historical terminal information of the live broadcast platform is counted to determine the historical proportion of terminals, including:
  • the type of live broadcast room specifically refers to the specific type of live broadcast in the live broadcast room, such as large-scale online games, mobile games, entertainment shows, radio stations (live broadcast with only sound), etc.
  • Different types of live broadcast rooms have different live broadcast status, which will also affect the distribution of terminals.
  • the large-scale online game types most games are PC-side, and the live broadcast screen occupies the entire computer screen. If users use mobile terminals to watch, due to The screen of the mobile device is small, the picture quality is compressed, the picture is small, and there is no way to watch the details clearly.
  • PC terminal web terminal
  • entertainment Singing and seeing live broadcasts most of which are male and female anchors singing, chatting, etc.
  • there is often only one person on the screen usually using a mobile phone to live broadcast
  • the screen is larger, and only one character is displayed on the entire screen, which will also affect Experience
  • you use a mobile phone to watch the screen of the mobile phone will be completely displayed, so for entertainment, viewing users will concentrate on the mobile phone. Therefore, different types of live broadcast rooms will have different terminal distributions.
  • the types of live broadcast rooms in the live broadcast platform should be classified first.
  • the type of live room After determining the type of live room, count the historical terminal information corresponding to each type of live room. For example, for game-type live rooms, the proportion of live broadcasts watched on the web is relatively high; for entertainment-type live rooms, the proportion of live broadcasts watched on mobile phones relatively high. After the live room is classified, the terminal information of the type of the live room is collected.
  • the distribution of terminals is different in different time periods. For example, during the day, due to the user's work, the proportion of using the mobile terminal will be relatively high, and the proportion of the web terminal will be higher at night. In the early hours of the morning, due to the need to sleep, the proportion of mobile phone terminals will increase again. Therefore, the terminal information of different live room types can also be counted through the preset time interval.
  • the preset time interval is a predetermined time, such as the past 24 hours, the past 48 hours, and so on.
  • the preset time interval will also include at least one statistical period, and there will be multiple statistical time points in each statistical cycle.
  • the statistical time point refers to the time point for statistical terminal information within the preset time interval, for example, every 1 Statistics are made every minute and every 5 minutes, and the terminal information used by the viewers in all live broadcast rooms is counted at the statistical time point.
  • the statistical period specifically refers to a time period used to collect statistics on terminals.
  • a statistical period includes multiple statistical time points
  • a preset time interval includes multiple statistical cycles.
  • the preset time interval is For the past 24 hours, the past 24 hours are divided into 24 statistical periods in units of hours, and terminal information is collected every 1 minute in each statistical period. Referring to FIG. 2 , FIG.
  • FIG. 2 shows a schematic diagram of statistics within a preset time interval of a certain type of live broadcast room provided by the first embodiment of the present application.
  • the maximum terminal proportion and the minimum terminal proportion within a certain statistical period, and then determine the terminal proportion information interval, for example, for a type A live broadcast room , in the statistical period from 0 to 1 point, the maximum proportion of the web terminal is 25%, the minimum proportion is 18%, the maximum proportion of the mobile terminal is 82%, and the minimum proportion is 75%.
  • the information interval of the proportion of the web terminal from 0-1 point is "18%-25%", and the information interval of the proportion of the mobile terminal is "75%-82%".
  • the historical terminal information corresponding to each live room type is counted, including:
  • Step 104 Collect current terminal information of the target live broadcast room, and determine the current ratio of terminals based on the current terminal information.
  • the target live room is the live room that needs to be judged whether there is a traffic violation. For example, if it is necessary to judge whether there is a traffic violation in the live broadcast room 1, the live broadcast room 1 is the target live room; if it is necessary to determine whether the live broadcast room 2 has a traffic violation, Then live room 2 is the target live room.
  • the overall data of the live broadcast platform can be obtained.
  • the current terminal information of the target live broadcast room that is, to obtain The total number of terminals in the target live broadcast room at the current time point, and the number of each terminal type, and then calculate the current proportion of terminals of each terminal type at the current time point based on the number of each terminal type and the total number of terminals.
  • the method also includes:
  • the initial live broadcast room is determined to be the target live broadcast room.
  • the initial live broadcast room is determined on the live broadcast platform, which is used to determine whether the initial live broadcast room needs to be judged for the number of live broadcasts.
  • the number of people in the live broadcast room in the initial live broadcast room is obtained.
  • the threshold value the initial live room is determined as the target live room. For example, for a live room with only 10 viewers, there is no need to judge whether there is a brush volume in the live room, because the data is too small to have a global The same attribute, but only after the number of people in the initial live broadcast room exceeds a certain number, it will be judged.
  • the current terminal information of the target live broadcast room is collected, and the current terminal ratio is determined based on the current terminal information, including:
  • the type of the target live room is specifically determined, such as game type, entertainment singing and dancing type, and the like.
  • the current time point is 20:30, collect the total number of terminals in the target live room at 20:30, and the number of each terminal type, and then calculate the target live room according to the number of each terminal type and the total number of terminals The current terminal proportion information at 20:30.
  • Step 106 According to the historical proportion of the terminal and the current proportion of the terminal, determine whether there is a situation of brushing in the target live broadcast room.
  • determining whether there is a brushing situation in the target live broadcast room includes:
  • the target terminal history ratio corresponding to the target live room type can be obtained from the terminal history ratio, for example, the target live room
  • the target live broadcast room type of the target live broadcast room is the entertainment live broadcast type
  • the information range of the web terminal proportion of the entertainment live broadcast live broadcast room in the terminal historical ratio is "18%-25%”
  • the current terminal proportion information of the target live broadcast room is the web terminal The proportion information is 38%.
  • the target live room type of the target live room is a large-scale online game type
  • the current terminal proportion information of the target live room is 56% of the terminal proportion information on the web side
  • the large-scale online game type The information range of the proportion of the web terminal in the live room’s historical proportion of terminals is “40%-60%”. At this time, if the current terminal proportion information meets the target historical proportion of terminals, it can be determined that there is no brushing in the target live room.
  • the method for determining the amount of swiping between live broadcasts is to count the historical terminal information of the live broadcast platform, determine the historical proportion of terminals; collect the current terminal information of the target live broadcast room, and determine the current proportion of terminals based on the current terminal information; According to the historical ratio of the terminal and the current ratio of the terminal, it is determined whether there is a brushing situation in the target live broadcast room.
  • Figure 3 shows a schematic flow chart of the method for determining the amount of live broadcast intervals provided by the second embodiment of the present application. Further combine the attribute information of the terminal to judge whether there is a brushing situation in the live broadcast room, which specifically includes the following steps:
  • Step 302 Count the terminal system information participating in the live broadcast on the live broadcast platform, and determine historical terminal system proportion information according to the terminal system information.
  • the statistics of the terminal system information participating in the live broadcast on the live broadcast platform include:
  • Step 304 Count the terminal attribute information corresponding to each terminal system, and determine historical terminal attribute proportion information corresponding to each terminal system according to the terminal attribute information of each terminal system.
  • the terminal used by the user will not change significantly in a short period of time
  • the brand used by user a is brand A
  • the model is 11, and the publication year is 2020
  • the user's mobile phone system information is marked as "brand A, model 11, 2020”
  • the browser brand is C brand
  • the model is MO
  • the publication year is 2019, then the user's web system information is marked as "C brand, MO, 2019”.
  • the client player will regularly report the viewing information of the current user to the server in the form of heartbeat reporting, including room number, viewing time, terminal system (web terminal, ios or Android), terminal attribute information (brand + Model + version number), after the server receives the heartbeat information, it summarizes all the information, and determines the historical terminal attribute ratio information corresponding to each terminal system according to the terminal attribute information of each terminal system.
  • heartbeat reporting including room number, viewing time, terminal system (web terminal, ios or Android), terminal attribute information (brand + Model + version number), after the server receives the heartbeat information, it summarizes all the information, and determines the historical terminal attribute ratio information corresponding to each terminal system according to the terminal attribute information of each terminal system.
  • ios-model A has 10,000 people
  • ios-model B has 40,000 people
  • ios-model B has 40,000 people.
  • Step 306 Collect the current terminal information of the target live broadcast room at the current time point.
  • the terminal system information of the target live broadcast room is collected every once in a while (for example, 5 minutes).
  • the number of people in the target live broadcast room will also be counted.
  • the number of people in the target live broadcast room exceeds the preset threshold, then it is judged whether the target live room has brushing behavior. For example, there are 12,000 people collected in the target live broadcast room at the current time, among which 4,000 users use the web terminal, 6,000 users use the Android system, and 2,000 users use the ios system.
  • There are 5 types of device numbers corresponding to the terminal 8 types of device numbers corresponding to the Android system, and 3 types of device numbers corresponding to the ios system.
  • Step 308 According to the current terminal information, calculate the current terminal system proportion information of the target live broadcast room and the current terminal attribute proportion information corresponding to each terminal system.
  • the terminal system proportion information at the current time point in the target live broadcast room can be calculated, as well as the corresponding terminal attribute proportion information under each terminal system.
  • Step 310 Judging whether the current terminal system proportion information and the historical terminal system proportion information meet the system usage determination rule, if yes, perform step 312, if not, proceed to step 314.
  • the proportion information of the current terminal system and the proportion information of the historical terminal system After obtaining the proportion information of the current terminal system and the proportion information of the historical terminal system, it can be judged according to the proportion information of the current terminal system and the proportion information of the historical terminal system, and judge whether there is a brushing behavior in the target live broadcast room. Specifically, Select any two elements in the current terminal system proportion information and the historical terminal system proportion information. If the difference exceeds the system threshold, it is determined that there is a traffic brushing behavior in the target live broadcast room. Otherwise, follow-up further judgments will be made.
  • the system threshold is 10%, that is, if the difference between the proportions of any two systems exceeds 10%, it is determined that there is a brushing behavior.
  • step 314 is executed.
  • Step 312 Determine that the target live broadcast room has spam.
  • target live room For a target live room that meets the conditions, it can be directly determined that the target live room has spam.
  • Step 314 Determine the target terminal system, and judge whether the current terminal attribute proportion information corresponding to the target terminal system and the historical terminal attribute proportion information corresponding to the target terminal system satisfy the determination rule of attribute brush volume, and if so, execute step 312 , if not, go to step 316.
  • the difference between the current terminal system proportion information and the historical terminal system proportion information is smaller than the threshold, it means that the terminal system proportion information cannot be directly determined. Whether there is traffic brushing behavior in the target live broadcast room, at this time, it needs to be further judged according to the proportion of terminal attributes in each terminal system.
  • the current terminal attribute ratio information is 0.5
  • the historical terminal attribute ratio information is 0.25
  • the attribute threshold is 8%.
  • step 316 is executed.
  • Step 316 Determine that there is no brushing in the target live broadcast room.
  • any two terminal attribute ratio information under any terminal system if the difference between the current terminal attribute ratio information and the historical terminal attribute ratio information is smaller than the attribute threshold, it can be determined that there is no brush volume in the target live room Condition.
  • the method for determining the amount of live streaming provided by the second embodiment of the present application first judges whether the proportion information of the terminal system meets the system threshold, and then refines it to each terminal system when the proportion information of the terminal system meets the system threshold.
  • the proportion information of the terminal attributes to determine whether the proportion information of the terminal attributes meets the attribute threshold, and to comprehensively judge the amount of swiping in the live broadcast room through the terminal system combined with the terminal attributes, further enriching the method of judging whether there is a swiping amount in the live broadcast room, and improving the The accuracy of judging the brush volume.
  • Figure 4 shows a schematic flow chart of the method for determining the amount of live broadcast intervals provided by the third embodiment of the present application.
  • it is judged through the preset statistical time interval combined with historical terminal information Whether there is a brush volume in the live broadcast room, specifically include the following steps:
  • Step 402 Count terminal information at each statistical time point of the live broadcast platform within a preset time interval.
  • the statistics of the terminal information of the live broadcast platform at each statistical time point within the preset time interval include:
  • the preset time interval is a predetermined time, such as the past 24 hours, the past 48 hours, and so on. Users use terminals differently in different time periods. For example, the usage ratio of mobile terminals is higher during the day, and the usage ratio of web terminals is higher at night, and the usage ratio of mobile terminals will increase again when it is close to the early morning. Therefore, according to the preset time The terminal information at each statistical time point in the interval is used for judgment.
  • the preset time interval usually includes at least one statistical cycle, and each statistical cycle includes multiple statistical time points, for example, the preset time interval is the past 24 hours, and the past 24 hours are divided into 24 statistics period, in which terminal information is collected every 1 minute. The user set corresponding to each statistical time point is obtained, and the terminal information of the terminal used by the user in each user set is counted.
  • Step 404 Calculate the terminal historical proportion in each statistical period according to the terminal information at each statistical time point, wherein the preset time interval includes at least one statistical period, and the statistical period includes at least one statistical time point.
  • the proportion of terminal history in each statistical period can be calculated according to the terminal information at each statistical time point, for example, in the statistical period of 9:00-10:00, the terminal history The proportion is that the proportion of mobile terminals is "65%-85%"; in the statistical period of 19:00-20:00, the historical proportion of terminals is that the proportion of mobile terminals is "23%-48%".
  • Step 406 Collect the current terminal information of the target live broadcast room at the current time point.
  • the current terminal information of the target live room at the current time point is collected, for example, taking the current time point as 19:20 in the evening as an example, at this time, the current terminal of the target live room at 19:20
  • the information is that a total of 336 people used mobile phones to watch the live broadcast in the target live broadcast room, and 498 people used the web terminal.
  • Step 408 Determine the current proportion of terminals at the current time point based on the current terminal information.
  • the current proportion of terminals at the current time point is the proportion information of the mobile terminal as "42%".
  • Step 410 Determine a target statistical time point in the estimated time interval according to the current time point.
  • the target statistical time point is determined to be 19:20 according to the current time point of 19:20 in the estimated time interval.
  • Step 412 Obtain the historical ratio of the target terminal in the target statistical period corresponding to the target statistical time point.
  • the target statistical cycle is determined as 19:00-20:00 according to the target statistical time point of 19:20, and within the statistical cycle of 19:00-20:00, the historical proportion of the target terminal is mobile phone The proportion range of the terminal is "23%-48%".
  • Step 414 When the current ratio of the terminal satisfies the historical ratio of the target terminal, determine that the target live broadcast room does not use traffic.
  • the current proportion of terminals is "42% of mobile terminal proportion information", which is in line with the target terminal historical proportion "mobile terminal proportion range is 23%-48%", so the target live broadcast can be determined There is no amount of brushing during the period.
  • Step 416 In the case that the current ratio of the terminal does not meet the historical ratio of the target terminal, determine that the target live broadcast room has spam.
  • the current ratio of terminals does not match the historical ratio of target terminals, it can be determined that there is a situation of spam in the target live broadcast room.
  • the method for determining the amount of brushing between live broadcasts obtains the historical proportion of terminals in the past preset time interval, and then according to the current terminal information of the target live broadcast room at the current time point, the current terminal information corresponds to the past Compare the historical ratio of terminals within the statistical period, and comprehensively judge the amount of swiping in the live broadcast room according to the combination of the preset time interval and terminal information, which further enriches the method of judging whether there is a swiping amount in the live broadcast room, and improves the accuracy of judging the amount of swiping in the live broadcast room Accuracy.
  • this application also provides an embodiment of a device for determining the amount of swiping between live broadcasts.
  • Figure 5 shows a device for determining the amount of swiping between live broadcasts provided by an embodiment of the present application Schematic diagram of the structure. As shown in Figure 5, the device includes:
  • the statistical module 502 is configured to count the historical terminal information of the live broadcast platform, and determine the historical proportion of the terminal;
  • the collection module 504 is configured to collect the current terminal information of the target live broadcast room, and determine the current terminal ratio based on the current terminal information;
  • the determining module 506 is configured to determine whether the target live broadcast room has a brushing situation according to the historical ratio of the terminal and the current ratio of the terminal.
  • the statistical module 502 is further configured to:
  • the historical ratio of terminals in each statistical period is calculated according to the terminal information at each statistical time point, wherein the preset time interval includes at least one statistical period, and the statistical period includes at least one statistical time point.
  • the collection module 504 is further configured to:
  • the determining module 506 is further configured to:
  • the statistical module 502 is further configured to:
  • the statistical module 502 is further configured to:
  • the collection module 504 is further configured to:
  • the determining module 506 is further configured to:
  • the statistical module 502 is further configured to:
  • the statistical module 502 is further configured to:
  • the terminal attribute information corresponding to each terminal system is counted, and the historical terminal attribute proportion information corresponding to each terminal system is determined according to the terminal attribute information of each terminal system.
  • the collection module 504 is further configured to:
  • the determining module 506 is further configured to:
  • the statistical module 502 is further configured to:
  • the device also includes:
  • the live broadcast number acquisition module is configured to determine the initial live broadcast room in the live broadcast platform, and obtain the number of people in the live broadcast room in the initial live broadcast room;
  • the live room determining module 506 is configured to determine the initial live room as the target live room when the number of people in the live room exceeds a preset threshold.
  • the device for determining the number of brushes between live broadcasts counts the historical terminal information of the live broadcast platform to determine the historical proportion of terminals; collects the current terminal information of the target live broadcast room, and determines the current proportion of terminals based on the current terminal information; according to the The historical ratio of the terminal and the current ratio of the terminal are used to determine whether there is a brushing situation in the target live broadcast room.
  • a method for judging whether there is brush volume in the live broadcast room has been established, and the accuracy rate of judging the brush volume has been improved.
  • the foregoing is a schematic solution of a device for determining the amount of live broadcast inter-browsing in this embodiment. It should be noted that the technical solution of the device for determining the amount of swiping between live broadcasts and the technical solution of the above-mentioned method for determining the amount of swiping between live broadcasts belong to the same concept, and the technical solution of the device for determining the amount of swiping between live broadcasts does not describe details in detail. For details, please refer to the description of the technical solution of the above-mentioned method for determining the amount of brushing between live broadcasts.
  • FIG. 6 shows a structural block diagram of a computing device 600 provided according to an embodiment of the present application.
  • Components of the computing device 600 include, but are not limited to, memory 610 and processor 620 .
  • the processor 620 is connected to the memory 610 through the bus 630, and the database 650 is used for saving data.
  • Computing device 600 also includes an access device 640 that enables computing device 600 to communicate via one or more networks 660 .
  • networks include the Public Switched Telephone Network (PSTN), Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), or a combination of communication networks such as the Internet.
  • Access device 640 may include one or more of any type of network interface (e.g., a network interface card (NIC)), wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, Worldwide Interoperability for Microwave Access ( Wi-MAX) interface, Ethernet interface, Universal Serial Bus (USB) interface, cellular network interface, Bluetooth interface, Near Field Communication (NFC) interface, etc.
  • NIC network interface card
  • the above-mentioned components of the computing device 600 and other components not shown in FIG. 6 may also be connected to each other, for example, through a bus. It should be understood that the structural block diagram of the computing device shown in FIG. 6 is only for the purpose of illustration, rather than limiting the scope of the application. Those skilled in the art can add or replace other components as needed.
  • Computing device 600 may be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile telephones (e.g., smartphones), ), wearable computing devices (eg, smart watches, smart glasses, etc.), or other types of mobile devices, or stationary computing devices such as desktop computers or PCs.
  • mobile computers or mobile computing devices e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.
  • mobile telephones e.g., smartphones
  • wearable computing devices eg, smart watches, smart glasses, etc.
  • desktop computers or PCs e.g., desktop computers or PCs.
  • Computing device 600 may also be a mobile or stationary server.
  • processor 620 executes the computer instructions, the steps of the method for determining the amount of live broadcast intervals are implemented.
  • An embodiment of the present application also provides a computer-readable storage medium, which stores computer instructions, and when the computer instructions are executed by a processor, the steps of the method for determining the amount of brushing between live broadcasts as described above are implemented.
  • An embodiment of the present application also provides a computer program, wherein, when the computer program is executed in a computer, the computer is instructed to execute the steps of the above-mentioned method for determining the amount of brushing between live broadcasts.
  • the computer instructions include computer program code, which may be in source code form, object code form, executable file or some intermediate form, and the like.
  • the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a removable hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM, Read-Only Memory) , Random Access Memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.
  • ROM Read-Only Memory
  • RAM Random Access Memory
  • electrical carrier signal telecommunication signal and software distribution medium, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • General Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Hardware Design (AREA)
  • Computing Systems (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Multimedia (AREA)
  • Telephonic Communication Services (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

本申请提供确定直播间刷量的方法及装置,其中确定直播间刷量的方法包括:统计直播平台的历史终端信息,确定终端历史比例(102);采集目标直播间的当前终端信息,并基于当前终端信息确定终端当前比例(104);根据终端历史比例和终端当前比例,确定目标直播间是否存在刷量情况(106)。通过本方法,统计观众使用的终端信息,并根据终端信息与历史记录进行比对的方式来判断直播间是否存在刷量的情况,丰富了判断直播间刷量的手段,有效提高判断刷量的准确率。

Description

确定直播间刷量的方法及装置
本申请要求于2021年11月02日提交中国专利局、申请号为202111290640.7、发明名称为“确定直播间刷量的方法及装置”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及网络直播技术领域,特别涉及一种确定直播间刷量的方法。本申请同时涉及一种确定直播间刷量的装置,一种计算设备,一种计算机可读存储介质以及一种计算机程序。
背景技术
随着网络通信技术的进步和宽带网络的提速,直播得到了越来越多的发展和应用。在现有直播体系中,人气是用于直播平台各个房间排名的重要指标,一般而言人气越高,排名越靠前,主播越有可能被用户观看。人气计算中直播间实时观看人数是关键一环,而一些主播为了提高人气,会通过非法手段模拟观看直播间,伪造直播间的在线观看人数,即通过刷量提高人气排名。因而,如何精确判断直播间是否存在刷量情况,是维护直播平台生态稳定的重要手段。
目前是通过判断直播间总人数是否会出现陡增或抖动的方式来确定是否存在直播间刷量的情况,判断方法单一,有时会出现判断错误的情况出现。
发明内容
有鉴于此,本申请实施例提供了一种确定直播间刷量的方法。本申请同时涉及一种确定直播间刷量的装置,一种计算设备,一种计算机可读存储介质以及一种计算机程序,以解决现有技术中存在的确定直播间是否刷量的方法单一、准确性较低的问题。
根据本申请实施例的第一方面,提供了一种确定直播间刷量的方法,包括:
统计直播平台的历史终端信息,确定终端历史比例;
采集目标直播间的当前终端信息,并基于所述当前终端信息确定终端当前比例;
根据所述终端历史比例和所述终端当前比例,确定所述目标直播间是否存在刷量情况。
根据本申请实施例的第二方面,提供了一种确定直播间刷量的装置,包括:
统计模块,被配置为统计直播平台的历史终端信息,确定终端历史比例;
采集模块,被配置为采集目标直播间的当前终端信息,并基于所述当前终端信息确定终端当前比例;
确定模块,被配置为根据所述终端历史比例和所述终端当前比例,确定所述目标直播 间是否存在刷量情况。
根据本申请实施例的第三方面,提供了一种计算设备,包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机指令,所述处理器执行所述计算机指令时实现所述确定直播间刷量的方法的步骤。
根据本申请实施例的第四方面,提供了一种计算机可读存储介质,其存储有计算机指令,该计算机指令被处理器执行时实现所述确定直播间刷量的方法的步骤。
根据本申请实施例的第五方面,提供了一种计算机程序,其中,当所述计算机程序在计算机中执行时,令计算机执行上述确定直播间刷量的方法的步骤。
本申请提供的确定直播间刷量的方法,统计直播平台的历史终端信息,确定终端历史比例;采集目标直播间的当前终端信息,并基于所述当前终端信息确定终端当前比例;根据所述终端历史比例和所述终端当前比例,确定所述目标直播间是否存在刷量情况。本申请一实施例实现了统计观众使用的终端信息,并根据终端信息与历史记录进行比对的方式来判断直播间是否存在刷量的情况,丰富了判断直播间刷量的手段,有效提高判断刷量的准确率。
附图说明
图1是本申请第一实施例提供的一种确定直播间刷量的方法的流程图;
图2是本申请第一实施例提供的某类型直播间的预设时间区间内的统计示意图;
图3是本申请第二实施例提供的一种确定直播间刷量的方法的处理流程图;
图4是本申请第三实施例提供的一种确定直播间刷量的方法的处理流程图;
图5是本申请一实施例提供的一种确定直播间刷量的装置的结构示意图;
图6是本申请一实施例提供的一种计算设备的结构框图。
具体实施方式
在下面的描述中阐述了很多具体细节以便于充分理解本申请。但是本申请能够以很多不同于在此描述的其它方式来实施,本领域技术人员可以在不违背本申请内涵的情况下做类似推广,因此本申请不受下面公开的具体实施的限制。
在本申请一个或多个实施例中使用的术语是仅仅出于描述特定实施例的目的,而非旨在限制本申请一个或多个实施例。在本申请一个或多个实施例和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式,除非上下文清楚地表示其他含义。还应当理解,本申请一个或多个实施例中使用的术语“和/或”是指并包含一个或多个相关联的列出项目的任何或所有可能组合。
应当理解,尽管在本申请一个或多个实施例中可能采用术语第一、第二等来描述各种信息,但这些信息不应限于这些术语。这些术语仅用来将同一类型的信息彼此区分开。例 如,在不脱离本申请一个或多个实施例范围的情况下,第一也可以被称为第二,类似地,第二也可以被称为第一。取决于语境,如在此所使用的词语“如果”可以被解释成为“在……时”或“当……时”或“响应于确定”。
首先,对本申请一个或多个实施例涉及的名词术语进行解释。
直播人气:综合观看人数、弹幕数、礼物数等按照一定比例算出的数值,用于在直播平台按照人气的高低进行排名。
直播人数:实时观看直播间的真实人数。
刷量:通过模拟正常用户访问,产生大量虚假观看的情况,即通过非法手段模拟观看直播间。
终端:用户观看直播时使用的设备,如台式电脑、手机、平板电脑等等。
终端***:终端对应的操作***。
现有的直播体系中,一般用客户端播放器定时上报心跳的方式进行人数统计,判断一个直播间是否存在刷量情况时,一般是计算直播间的总人数,判断总人数是否会出现陡增或陡降的情况,一般情况下,一个房间的人数是逐渐增多,人数呈现曲线上涨的,刷量的直播间一般无法精准控制刷量情况,会出现某个时刻人数陡增的情况,例如在2分钟之内人数从200人增加到3000人。而针对总人数判断是否刷量不够精细,如果刷量的直播间控制的足够精准,也是可以模拟出总人数缓慢上升的效果,仅通过总人数来判断就不够准确了。
基于此,在本申请中,提供了一种确定直播间刷量的方法,本申请同时涉及一种确定直播间刷量的装置,一种计算设备,以及一种计算机可读存储介质,在下面的实施例中逐一进行详细说明。
图1示出了根据本申请一实施例提供的一种确定直播间刷量的方法的流程图,具体包括以下步骤:
步骤102:统计直播平台的历史终端信息,确定终端历史比例。
其中,直播平台就是向用户提供各种直播的平台,主播在直播平台中创建直播间进行直播,用户可以通过直播平台进入某个直播间观看直播,在实际应用中,用户需要使用终端设备进入直播间,例如手机、平板电脑、笔记本电脑等等。用户在登录直播平台时,直播平台会获取到用户使用的终端的信息,例如某个用户A使用手机端进入直播间,某个用户B登录电脑使用浏览器进入直播间等等。
历史终端信息具体是指在过去一段时间内直播平台中接入终端的终端信息,例如在过去24小时内,观看直播的终端信息。
终端历史比例具体是指在获取的历史终端信息之后,基于后续的处理规则,将终端进 行分类,分类之后的终端之间的比例。例如,在历史终端信息进行统计之后,根据历史终端类型进行分类,包括web端和移动端,则终端历史比例是web端:移动端;如果根据历史终端类型分为web端、IOS端和Android端,则终端历史比例是web:IOS:Android。
在实际应用中,对终端历史比例的具体形式不做限定,以实际应用为准。为了便于解释说明,在本申请提供的第一实施例中,以终端类型分为web端和移动端为例进行解释说明。在本申请提供的第一实施例中,统计直播平台的历史终端信息,确定终端历史比例,包括:
确定直播平台中的直播间类型;
统计每个直播间类型对应的历史终端信息;
根据每个直播间类型对应的历史终端信息计算每个直播间类型对应的终端历史比例。
直播间类型具体是指该直播间内进行直播的具体类型,例如有大型网游、手游、娱乐唱见、电台(只有声音的直播)等等。不同类型的直播间拥有不同的直播状态,进而也会影响终端的分布情况,例如,大型网游类型中,游戏大多数为PC端,直播的画面占据整个电脑屏幕,若用户使用移动端观看,由于移动端设备屏幕较小,画面画质被压缩,画面较小,没有办法观看清楚细节,因此,大多数用户会使用web端(PC端)观看,以便获得最佳的观看体验;又例如对于娱乐唱见类型的直播,大多数是男女主播进行唱歌、聊天等,画面往往只有一个人,通常使用手机直播,如果用户使用web端观看,屏幕较大,而且整个屏幕只有一个人物显示,一样会影响体验,如果用手机观看,则手机屏幕正好完全显示,因此对于娱乐唱见而言,观看用户会集中手机端。因此不同的直播间类型会有不同的终端分布,再统计终端信息之前,先将直播平台中的直播间类型进行分类。
在确定直播间类型之后,再统计每种直播间类型对应的历史终端信息,例如对于游戏类型的直播间,web端观看直播的比例比较高、对于娱乐类型的直播间,手机端观看直播的比例比较高。在对直播间进行分类之后,即对直播间类型的终端信息进行统计。
在实际应用中,即便是同一个类型的直播间,在不同的时间段,终端的分布情况也有所不同,例如,白天由于用户工作,因此使用手机端的比例会比较高,晚上的时候web端的比例会增加,在接近凌晨的时候,由于需要睡觉,因此,手机端的比例会再次增高。因此,还可以通过预设时间区间统计不同直播间类型的终端信息。其中,预设时间区间为预先规定的时间,例如过去的24小时、过去的48小时等等。
在预设时间区间内还会包括至少一个统计周期,每个统计周期内会有多个统计时间点,统计时间点是指在预设时间区间内的统计终端信息的时间点,例如每隔1分钟统计一次、每隔5分钟统计一次,在统计时间点对所有直播间中观众使用的终端信息进行统计。统计周期具体是指用于对终端进行统计的一个时间周期,通常情况下,一个统计周期中包括多 个统计时间点,一个预设时间区间内包括多个统计周期,例如,预设时间区间为过去的24小时,将过去的24小时以小时为单位划分为24个统计周期,在每个统计周期中每隔1分钟统计一次终端信息。参见图2,图2示出了本申请第一实施例提供的某类型直播间的预设时间区间内的统计示意图。如图2中的a所示,在晚高峰22:42分的统计时间点,web端的占比为526/3300=16%,如图2中的b所示,在凌晨4:08分的统计时间点,web端的占比为262/11000=2%。
在统计完每个统计时间点的终端占比信息之后,可以确定在某个统计周期内的终端最大占比和终端最小占比,进而确定终端占比信息区间,例如,对于A类型的直播间,其在0-1点的统计周期内,web端的最大占比为25%,最小占比为18%,移动端的最大占比为82%,最小占比为75%,则A类型直播间在0-1点的web端占比信息区间为“18%-25%”,移动端占比信息区间为“75%-82%”。
具体的,统计每个直播间类型对应的历史终端信息,包括:
获取每个直播间类型对应的用户集合;
确定每个用户集合中用户使用终端的终端信息。
在实际应用中,统计每个直播间类型的历史终端信息时,先要确定每个直播间类型的用户集合,再分别获取用户集合中每个用户所使用的终端的类型,例如web端、移动端等等。
步骤104:采集目标直播间的当前终端信息,并基于所述当前终端信息确定终端当前比例。
目标直播间即为需要判断是否存在刷量情况的直播间,例如现在需要判断直播间1是否存在刷量情况,则直播间1为目标直播间;如果需要判断直播间2是否存在刷量情况,则直播间2为目标直播间。
在实际应用中,在经过上述步骤102之后,即可获得直播平台的整体数据,此时需要对目标直播间是否存在刷量情况进行判断,具体的,获取目标直播间的当前终端信息,即获取目标直播间在当前时间点的终端总数量,以及每个终端类型的数量,进而根据每个终端类型的数量和终端总数量,计算在当前时间点每个终端类型的终端当前比例。
在实际应用中,每个直播间的人数各不相同,而如果一个直播间的人数较少,明显不存在刷量的情况,则无需再对该直播间进行判断,因此,在采集目标直播间的当前终端信息之前,所述方法还包括:
在所述直播平台中确定初始直播间,并获取所述初始直播间的直播间人数;
在所述直播间人数超过预设阈值的情况下,确定所述初始直播间为目标直播间。
具体的,在直播平台中确定初始直播间,用于判断初始直播间是否需要进行直播刷量 的判定,在确定初始直播间之后,获取初始直播间的直播间人数,在直播间人数超过预设阈值的情况下,则将该初始直播间确定为目标直播间,例如对于一个直播间,观众人数只有10人,则无需判断该直播间是否存在刷量的情况,因为数据太少,不具有全局同样的属性,而只有初始直播间的直播间人数超过一定数量之后,才会对其进行判断。通过筛选直播间的人数,可以将人数不足的直播间过滤,无需对其进行判断,减轻服务器的计算压力,有效提升资源利用率。
在本申请提供的第一实施例中,采集目标直播间的当前终端信息,并基于所述当前终端信息确定终端当前比例,包括:
确定所述目标直播间的目标直播间类型和所述目标直播间对应当前终端信息;
根据所述当前终端信息计算所述目标直播间的当前终端占比信息。
在本申请提供的第一实施例中,具体确定目标直播间的目标直播间类型,例如是游戏类型、娱乐唱跳类型等等。同时还要确定目标直播间对应当前终端信息,再根据当前终端信息计算所述目标直播间的当前终端占比信息。例如当前时间点为20:30分,采集目标直播间在20:30分的终端总数量,以及每个终端类型的数量,进而根据每个终端类型的数量和终端总数量来计算目标直播间在20:30分的当前终端占比信息。
步骤106:根据所述终端历史比例和所述终端当前比例,确定所述目标直播间是否存在刷量情况。
在获得终端历史比例和终端当前比例之后,即可根据这两个比例信息来判断目标直播间是否存在刷量情况。
在本申请提供的第一实施例中,根据所述终端历史比例和所述终端当前比例,确定所述目标直播间是否存在刷量情况,包括:
根据所述目标直播间类型在所述终端历史比例中确定目标终端历史比例;
在所述当前终端占比信息满足所述目标终端历史比例的情况下,确定所述目标直播间不存在刷量情况;
在所述当前终端占比信息未满足所述目标终端历史比例的情况下,确定所述目标直播间存在刷量情况。
在第一实施例中,要判断目标直播间的目标直播间类型,在确定目标直播间类型后,即可在终端历史比例中获取目标直播间类型对应的目标终端历史比例,例如,目标直播间的目标直播间类型为娱乐唱见类型,娱乐唱见类型的直播间在终端历史比例中web端占比信息区间为“18%-25%”,目标直播间的当前终端占比信息为web端占比信息为38%,此时,当前终端占比信息未满足目标终端历史比例,则可以确定目标直播间存在刷量情况。
在第一实施例的另一具体实施方式中,目标直播间的目标直播间类型为大型网游类型, 目标直播间的当前终端占比信息为web端的终端占比信息为56%,大型网游类型的直播间在终端历史比例中web端占比信息区间为“40%-60%”,此时,当前终端占比信息满足目标终端历史比例,则可以确定目标直播间不存在刷量情况。
本申请第一实施例提供的确定直播间刷量的方法,统计直播平台的历史终端信息,确定终端历史比例;采集目标直播间的当前终端信息,并基于所述当前终端信息确定终端当前比例;根据所述终端历史比例和所述终端当前比例,确定所述目标直播间是否存在刷量情况。采用直播间类型结合终端分布综合分析的方式判断直播间是否存在刷量的情况,根据历史的终端占比信息和当前的终端占比信息综合判断刷量情况的防刷策略,丰富了判断直播间是否存在刷量的方法,提升了判断刷量的准确率。
如图3所示,图3示出了本申请第二实施例提供的确定直播间刷量的方法的流程示意图,在实际应用中,为了更精细化的确定直播间刷量的方法,还可以进一步的结合终端的属性信息判断直播间是否存在刷量情况,具体包括以下步骤:
步骤302:统计直播平台中参与直播的终端***信息,根据所述终端***信息确定历史终端***占比信息。
其中,统计直播平台中参与直播的终端***信息,包括:
获取所述直播平台中参与直播的用户集合;
确定每个用户集合中用户使用终端的终端***信息。
终端***信息是指用户使用终端的操作***信息,例如web端、ios端、Android端。分别统计每个操作***对应的数量,进而确定历史终端***占比信息。在实际应用中,通常确定直播平台中参与直播的用户集合,再确定每个用户集合中每个用户所使用终端的终端***信息,例如,在过去的24小时,一共有21万人参与直播,其中,使用web端的用户有3万人,使用ios端的用户有6万人,使用Android端的用户有12万人,则历史终端***占比信息为“web:Android:ios=1:4:2”。
步骤304:统计每个终端***对应的终端属性信息,根据每个终端***的终端属性信息确定每个终端***对应的历史终端属性占比信息。
在实际应用中,由于用户的手机、平板、电脑的浏览器等是不会经常更换的(一天内更换多次),基于此,可以认为用户使用的终端在短时间内不会发生明显的变化,例如,用户a使用的品牌是A品牌,型号是11,出版年份为2020年,则该用户的手机***信息标记为“A品牌、型号11、2020”;又例如,用户b使用的是web端,浏览器的品牌是C品牌,型号为MO,出版年份为2019年,则该用户的web***信息标记为“C品牌、MO、2019”。
在实际应用中,无论是手机、平板电脑、浏览器,其品牌、型号是固定不变的,出版年份随着厂商的升级而更新,一般厂商的更新周期在几个月,因此“品牌+型号+版本号”可以 作为一个用户的观看标识,即用户使用的终端的终端属性信息。
在实际应用中,客户端播放器会通过心跳上报的形式,定时给服务器上报当前用户的观看信息,包括房间号、观看时间、终端***(web端、ios或Android),终端属性信息(品牌+型号+版本号),服务器在接收到心跳信息后,对所有的信息进行汇总,根据每个终端***的终端属性信息确定每个终端***对应的历史终端属性占比信息。
在ios***下,分为有三个型号,分别为ios-型号A,ios-型号B,ios-型号C,其中,ios-型号A有1万人、ios-型号B有4万人,ios-型号C有1万人,则可以确定在ios***下,历史终端属性占比信息为“型号A:型号B:型号C=1:4:1”。
步骤306:采集所述目标直播间在当前时间点的当前终端信息。
在本申请提供的第二实施例中,每隔一段时间(例如5分钟)采集一次目标直播间的终端***信息,在实际应用中,为了便于提高计算效率,还会统计目标直播间的人数信息,若目标直播间的人数超过预设阈值,再对目标直播间是否存在刷量行为进行判断。例如,采集到目标直播间在当前时间点的人数一共有1.2万人,其中,使用web端的用户有4000人,使用Android***的用户有6000人,使用ios***的用户有2000人,其中,web端对应的设备号有5种,Android***对应的设备号有8种,ios***对应的设备号有3种。
步骤308:根据所述当前终端信息计算所述目标直播间的当前终端***占比信息和每个终端***对应的当前终端属性占比信息。
根据采集到的当前终端信息即可计算在目标直播间的当前时间点的终端***占比信息,以及每个终端***下,对应的终端属性占比信息,例如,沿用上例,web端用户有4000人,Android***的用户有6000人,ios***的用户有2000人,因此目标直播间的当前终端***占比为“web:Android:ios=2:3:1”。对于web端,共有5种设备型号,web端对应的当前终端属性占比信息为“web1:web2:web3:web4:web5=1:2:3:4:5”;对于Android***,共有8种设备型号,Android***对应的当前终端属性占比信息为“Android1:Android2:Android3:Android4:Android5:Android6:Android7:Android8=1:2:3:4:5:6:7:8”;对于ios***,共有3种设备型号,ios***对应的当前终端属性占比信息为“iosA:iosB:iosC=1:2:3”。
步骤310:判断所述当前终端***占比信息与所述历史终端***占比信息是否满足***刷量判定规则,若是,则执行步骤312,若否,则还行步骤314。
在获得当前终端***占比信息和历史终端***占比信息之后,可以先根据当前终端***占比信息和历史终端***占比信息进行判断,判断目标直播间是否为存在刷量行为,具体的,选取当前终端***占比信息和历史终端***占比信息中任意两个元素相比,若差值超过***阈值,则确定该目标直播间存在刷量行为,反之,则进行后续更进一步的判断。
在本说明书提供的第二实施例中,当前终端***占比信息为“web:Android:ios=2:3:1”,历史终端***占比信息为“web:Android:ios=1:4:2”,***阈值为10%,即任意两个***占比的差值超过百分之10,则认定存在刷量行为,以“web:ios”为例,当前终端***占比信息为“web:ios=2:1=2”,历史终端***占比信息为“web:ios=1:2=0.5”。则对于“web:ios”而言,当前终端***占比信息与历史终端***占比信息间的差值为“(当前终端***占比信息-历史终端***占比信息)/历史终端***占比信息”,即(2-0.5)/0.5=300%,远超阈值10%,执行步骤312。
若对于任意两个终端***,当前终端***占比信息与历史终端***占比信息之差均小于***阈值,则执行步骤314。
步骤312:确定所述目标直播间存在刷量情况。
对于满足条件的目标直播间,则可以直接确定该目标直播间存在刷量情况。
步骤314:确定目标终端***,判断所述目标终端***对应的当前终端属性占比信息与所述目标终端***对应的历史终端属性占比信息是否满足属性刷量判定规则,若是,则执行步骤312,若否,则执行步骤316。
在本说明书提供的第二实施例中,若对于任意两个终端***,当前终端***占比信息与历史终端***占比信息之差均小于阈值,说明从终端***占比信息中无法直接确定该目标直播间是否存在刷量行为,此时,需要根据每个终端***中的终端属性占比信息来进一步判断。
基于此,在多个终端***中,确定一个目标终端***,判断目标终端***对应的当前终端属性占比信息和历史终端属性占比信息是否满足属性刷量判定规则,即两者的差值是否超过属性阈值,具体的计算规则,参见上述当前终端***占比信息与历史终端***占比信息的计算方法,在此不再赘述。
以ios***为例,ios***对应的当前终端属性占比信息为“iosA:iosB:iosC=1:2:3”,历史终端属性占比信息为“iosA:iosB:iosC=1:4:1”,以“iosA:iosB”为例,当前终端属性占比信息为0.5,历史终端属性占比信息为0.25,属性阈值为8%,则对于“iosA:iosB”而言,其当前终端***占比信息与历史终端***占比信息间的差为“(0.5-0.25)/0.25=100%”,超过属性阈值8%,则执行步骤312。
若对于任意终端***下的任意两个终端属性占比信息,当前终端属性占比信息与历史终端属性占比信息之差均小于属性阈值,则执行步骤316。
步骤316:确定所述目标直播间不存在刷量情况。
对于任意终端***下的任意两个终端属性占比信息,当前终端属性占比信息与历史终端属性占比信息之差均小于属性阈值的目标直播间,则可以确定该目标直播间不存在刷量 情况。
本申请第二实施例提供的确定直播间刷量的方法,首先判断终端***占比信息是否满足***阈值,在终端***占比信息满足***阈值的情况下,再细化到每个终端***下的终端属性占比信息,判断终端属性占比信息是否满足属性阈值,通过终端***结合终端属性的方式综合判断直播间刷量的情况,进一步丰富了判断直播间是否存在刷量的方法,提升了判断刷量的准确率。
如图4所示,图4示出了本申请第三实施例提供的确定直播间刷量的方法的流程示意图,在第三实施例中,通过预设的统计时间区间结合历史终端信息来判断直播间是否存在刷量情况,具体包括以下步骤:
步骤402:统计直播平台在预设时间区间内每个统计时间点的终端信息。
其中,统计直播平台在预设时间区间内每个统计时间点的终端信息,具体包括:
获取直播平台在预设时间区间内每个统计时间点的用户集合;
确定每个用户集合中用户使用终端的终端信息。
在本申请提供的第三实施例中,预设时间区间为预先规定的时间,例如过去的24小时、过去的48小时等等。不同的时间段用户使用终端的情况也各不相同,例如白天手机端的使用比例较高、晚上web端的使用比例较高、接近凌晨的时候手机端的使用比例会再次增高,因此,可以根据预设时间区间内每个统计时间点的终端信息来进行判断。
具体的,预设时间区间通常会包括至少一个统计周期,每个统计周期会包括多个统计时间点,例如预设时间区间为过去的24小时,将过去的24小时以小时为单位划分为24个统计周期,在每个统计周期中每隔1分钟统计一次终端信息。获取每个统计时间点对应的用户集合,统计每个用户集合中用户使用终端的终端信息。
步骤404:根据每个统计时间点的终端信息计算每个统计周期内的终端历史比例,其中预设时间区间包括至少一个统计周期,统计周期包括至少一个统计时间点。
在本申请提供的第三实施例中,根据每个统计时间点的终端信息进而可以计算出每个统计周期内终端历史比例,例如,在9:00-10:00的统计周期内,终端历史比例为手机端占比区间为“65%-85%”;在19:00-20:00的统计周期内,终端历史比例为手机端占比区间为“23%-48%”。
步骤406:采集目标直播间在当前时间点的当前终端信息。
在本申请提供的第三实施例中,采集目标直播间在当前时间点的当前终端信息,例如以当前时间点为晚上19:20为例,此时,目标直播间在19:20时刻当前终端信息为观看目标直播间直播的终端中共有336人使用手机,有498人使用web端。
步骤408:基于所述当前终端信息确定所述当前时间点的终端当前比例。
在本申请提供的第三实施例中,根据手机端336和web段498,确定在当前时间点的终端当前比例为手机端占比信息为“42%”。
步骤410:根据所述当前时间点在所述预计时间区间中确定目标统计时间点。
在本申请提供的第三实施例中,根据当前时间点19:20在所述预计时间区间确定目标统计时间点为19:20。
步骤412:获取所述目标统计时间点对应的目标统计周期的目标终端历史比例。
在本申请提供的第三实施例中,根据目标统计时间点19:20确定目标统计周期为19:00-20:00,19:00-20:00的统计周期内,目标终端历史比例为手机端占比区间为“23%-48%”。
步骤414:在所述终端当前比例满足所述目标终端历史比例的情况下,确定所述目标直播间不存在刷量情况。
在本申请提供的第三实施例中,终端当前比例为“手机端占比信息为42%”,符合目标终端历史比例“手机端占比区间为23%-48%”,因此可以确定目标直播间不存在刷量情况。
步骤416:在所述终端当前比例未满足所述目标终端历史比例的情况下,确定所述目标直播间存在刷量情况。
在本申请提供的第三实施例中,若终端当前比例不符合目标终端历史比例,则可以确定目标直播间存在刷量情况。
本申请第三实施例提供的确定直播间刷量的方法,获取在过去预设时间区间内的终端历史比例,再根据目标直播间在当前时间点的当前终端信息,通过当前终端信息与过去对应统计周期内的终端历史比例进行比较,根据预设时间区间和终端信息相结合的方式综合判断直播间刷量的情况,进一步丰富了判断直播间是否存在刷量的方法,提升了判断刷量的准确率。
与上述确定直播间刷量的方法实施例相对应,本申请还提供了确定直播间刷量的装置实施例,图5示出了本申请一实施例提供的一种确定直播间刷量的装置的结构示意图。如图5所示,该装置包括:
统计模块502,被配置为统计直播平台的历史终端信息,确定终端历史比例;
采集模块504,被配置为采集目标直播间的当前终端信息,并基于所述当前终端信息确定终端当前比例;
确定模块506,被配置为根据所述终端历史比例和所述终端当前比例,确定所述目标直播间是否存在刷量情况。
可选的,所述统计模块502,进一步被配置为:
统计直播平台在预设时间区间内每个统计时间点的终端信息;
根据每个统计时间点的终端信息计算每个统计周期内的终端历史比例,其中预设时间区间包括至少一个统计周期,统计周期包括至少一个统计时间点。
可选的,所述采集模块504,进一步被配置为:
采集目标直播间在当前时间点的当前终端信息;
基于所述当前终端信息确定所述当前时间点的终端当前比例。
可选的,所述确定模块506,进一步被配置为:
根据所述当前时间点在所述预设时间区间中确定目标统计时间点;
获取所述目标统计时间点对应的目标统计周期的目标终端历史比例;
在所述终端当前比例满足所述目标终端历史比例的情况下,确定所述目标直播间不存在刷量情况;
在所述终端当前比例未满足所述目标终端历史比例的情况下,确定所述目标直播间存在刷量情况。
可选的,所述统计模块502,进一步被配置为:
获取直播平台在预设时间区间内每个统计时间点的用户集合;
确定每个用户集合中用户使用终端的终端信息。
可选的,所述统计模块502,进一步被配置为:
确定直播平台中的直播间类型;
统计每个直播间类型对应的历史终端信息;
根据每个直播间类型对应的历史终端信息计算每个直播间类型对应的终端历史比例。
可选的,所述采集模块504,进一步被配置为:
确定所述目标直播间的目标直播间类型和所述目标直播间对应当前终端信息;
根据所述当前终端信息计算所述目标直播间的当前终端占比信息。
可选的,所述确定模块506,进一步被配置为:
根据所述目标直播间类型在所述终端历史比例中确定目标终端历史比例;
在所述当前终端占比信息满足所述目标终端历史比例的情况下,确定所述目标直播间不存在刷量情况;
在所述当前终端占比信息未满足所述目标终端历史比例的情况下,确定所述目标直播间存在刷量情况。
可选的,所述统计模块502,进一步被配置为:
获取每个直播间类型对应的用户集合;
确定每个用户集合中用户使用终端的终端信息。
可选的,所述统计模块502,进一步被配置为:
统计所述直播平台中参与直播的终端***信息,根据所述终端***信息确定历史终端***占比信息;
统计每个终端***对应的终端属性信息,根据每个终端***的终端属性信息确定每个终端***对应的历史终端属性占比信息。
可选的,所述采集模块504,进一步被配置为:
采集所述目标直播间在当前时间点的当前终端信息;
根据所述当前终端信息计算所述目标直播间的当前终端***占比信息和每个终端***对应的当前终端属性占比信息。
可选的,所述确定模块506,进一步被配置为:
判断所述当前终端***占比信息与所述历史终端***占比信息是否满足***刷量判定规则;
若是,则确定所述目标直播间存在刷量情况;
若否,确定目标终端***,判断所述目标终端***对应的当前终端属性占比信息与所述目标终端***对应的历史终端属性占比信息是否满足属性刷量判定规则;
若是,则确定所述目标直播间存在刷量情况;
若否,则确定所述目标直播间不存在刷量情况。
可选的,所述统计模块502,进一步被配置为:
获取所述直播平台中参与直播的用户集合;
确定每个用户使用终端的终端***信息。
可选的,所述装置还包括:
直播人数获取模块,被配置为在所述直播平台中确定初始直播间,并获取所述初始直播间的直播间人数;
直播间确定模块506,被配置为在所述直播间人数超过预设阈值的情况下,确定所述初始直播间为目标直播间。
本申请实施例提供的确定直播间刷量的装置,统计直播平台的历史终端信息,确定终端历史比例;采集目标直播间的当前终端信息,并基于所述当前终端信息确定终端当前比例;根据所述终端历史比例和所述终端当前比例,确定所述目标直播间是否存在刷量情况。采用时间、直播间类型结合终端分布综合分析的方式判断直播间是否存在刷量的情况,根据历史的终端占比信息和当前时间点的终端占比信息综合判断刷量情况的防刷策略,丰富 了判断直播间是否存在刷量的方法,提升了判断刷量的准确率。
上述为本实施例的一种确定直播间刷量的装置的示意性方案。需要说明的是,该确定直播间刷量的装置的技术方案与上述的确定直播间刷量的方法的技术方案属于同一构思,确定直播间刷量的装置的技术方案未详细描述的细节内容,均可以参见上述确定直播间刷量的方法的技术方案的描述。
图6示出了根据本申请一实施例提供的一种计算设备600的结构框图。该计算设备600的部件包括但不限于存储器610和处理器620。处理器620与存储器610通过总线630相连接,数据库650用于保存数据。
计算设备600还包括接入设备640,接入设备640使得计算设备600能够经由一个或多个网络660通信。这些网络的示例包括公用交换电话网(PSTN)、局域网(LAN)、广域网(WAN)、个域网(PAN)或诸如因特网的通信网络的组合。接入设备640可以包括有线或无线的任何类型的网络接口(例如,网络接口卡(NIC))中的一个或多个,诸如IEEE802.11无线局域网(WLAN)无线接口、全球微波互联接入(Wi-MAX)接口、以太网接口、通用串行总线(USB)接口、蜂窝网络接口、蓝牙接口、近场通信(NFC)接口,等等。
在本申请的一个实施例中,计算设备600的上述部件以及图6中未示出的其他部件也可以彼此相连接,例如通过总线。应当理解,图6所示的计算设备结构框图仅仅是出于示例的目的,而不是对本申请范围的限制。本领域技术人员可以根据需要,增添或替换其他部件。
计算设备600可以是任何类型的静止或移动计算设备,包括移动计算机或移动计算设备(例如,平板计算机、个人数字助理、膝上型计算机、笔记本计算机、上网本等)、移动电话(例如,智能手机)、可佩戴的计算设备(例如,智能手表、智能眼镜等)或其他类型的移动设备,或者诸如台式计算机或PC的静止计算设备。计算设备600还可以是移动式或静止式的服务器。
其中,处理器620执行所述计算机指令时实现所述的确定直播间刷量的方法的步骤。
上述为本实施例的一种计算设备的示意性方案。需要说明的是,该计算设备的技术方案与上述的确定直播间刷量的方法的技术方案属于同一构思,计算设备的技术方案未详细描述的细节内容,均可以参见上述确定直播间刷量的方法的技术方案的描述。
本申请一实施例还提供一种计算机可读存储介质,其存储有计算机指令,该计算机指令被处理器执行时实现如前所述确定直播间刷量的方法的步骤。
上述为本实施例的一种计算机可读存储介质的示意性方案。需要说明的是,该存储介质的技术方案与上述的确定直播间刷量的方法的技术方案属于同一构思,存储介质的技术方案未详细描述的细节内容,均可以参见上述确定直播间刷量的方法的技术方案的描述。
本申请一实施例还提供一种计算机程序,其中,当所述计算机程序在计算机中执行时,令计算机执行上述确定直播间刷量的方法的步骤。
上述为本申请实施例的一种计算机程序的示意性方案。需要说明的是,该计算机程序的技术方案与上述的确定直播间刷量的方法的技术方案属于同一构思,计算机程序的技术方案未详细描述的细节内容,均可以参见上述确定直播间刷量的方法的技术方案的描述。
上述对本申请特定实施例进行了描述。其它实施例在所附权利要求书的范围内。在一些情况下,在权利要求书中记载的动作或步骤可以按照不同于实施例中的顺序来执行并且仍然可以实现期望的结果。另外,在附图中描绘的过程不一定要求示出的特定顺序或者连续顺序才能实现期望的结果。在某些实施方式中,多任务处理和并行处理也是可以的或者可能是有利的。
所述计算机指令包括计算机程序代码,所述计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。所述计算机可读介质可以包括:能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、电载波信号、电信信号以及软件分发介质等。需要说明的是,所述计算机可读介质包含的内容可以根据司法管辖区内立法和专利实践的要求进行适当的增减,例如在某些司法管辖区,根据立法和专利实践,计算机可读介质不包括电载波信号和电信信号。
需要说明的是,对于前述的各方法实施例,为了简便描述,故将其都表述为一系列的动作组合,但是本领域技术人员应该知悉,本申请并不受所描述的动作顺序的限制,因为依据本申请,某些步骤可以采用其它顺序或者同时进行。其次,本领域技术人员也应该知悉,说明书中所描述的实施例均属于优选实施例,所涉及的动作和模块并不一定都是本申请所必须的。
在上述实施例中,对各个实施例的描述都各有侧重,某个实施例中没有详述的部分,可以参见其它实施例的相关描述。
以上公开的本申请优选实施例只是用于帮助阐述本申请。可选实施例并没有详尽叙述所有的细节,也不限制该发明仅为所述的具体实施方式。显然,根据本申请的内容,可作很多的修改和变化。本申请选取并具体描述这些实施例,是为了更好地解释本申请的原理和实际应用,从而使所属技术领域技术人员能很好地理解和利用本申请。本申请仅受权利要求书及其全部范围和等效物的限制。

Claims (18)

  1. 一种确定直播间刷量的方法,包括:
    统计直播平台的历史终端信息,确定终端历史比例;
    采集目标直播间的当前终端信息,并基于所述当前终端信息确定终端当前比例;
    根据所述终端历史比例和所述终端当前比例,确定所述目标直播间是否存在刷量情况。
  2. 如权利要求1所述的确定直播间刷量的方法,统计直播平台的历史终端信息,确定终端历史比例,包括:
    统计直播平台在预设时间区间内每个统计时间点的终端信息;
    根据每个统计时间点的终端信息计算每个统计周期内的终端历史比例,其中预设时间区间包括至少一个统计周期,统计周期包括至少一个统计时间点。
  3. 如权利要求2所述的确定直播间刷量的方法,采集目标直播间的当前终端信息,并基于所述当前终端信息确定终端当前比例,包括:
    采集目标直播间在当前时间点的当前终端信息;
    基于所述当前终端信息确定所述当前时间点的终端当前比例。
  4. 如权利要求3所述的确定直播间刷量的方法,根据所述终端历史比例和所述终端当前比例,确定所述目标直播间是否存在刷量情况,包括:
    根据所述当前时间点在所述预设时间区间中确定目标统计时间点;
    获取所述目标统计时间点对应的目标统计周期的目标终端历史比例;
    在所述终端当前比例满足所述目标终端历史比例的情况下,确定所述目标直播间不存在刷量情况;
    在所述终端当前比例未满足所述目标终端历史比例的情况下,确定所述目标直播间存在刷量情况。
  5. 如权利要求2-4任意一项所述的确定直播间刷量的方法,统计直播平台在预设时间区间内每个统计时间点的终端信息,包括:
    获取直播平台在预设时间区间内每个统计时间点的用户集合;
    确定每个用户集合中用户使用终端的终端信息。
  6. 如权利要求1-5任意一项所述的确定直播间刷量的方法,统计直播平台的历史终端信息,确定终端历史比例,包括:
    确定直播平台中的直播间类型;
    统计每个直播间类型对应的历史终端信息;
    根据每个直播间类型对应的历史终端信息计算每个直播间类型对应的终端历史比例。
  7. 如权利要求6所述的确定直播间刷量的方法,采集目标直播间的当前终端信息,并基于所述当前终端信息确定终端当前比例,包括:
    确定所述目标直播间的目标直播间类型和所述目标直播间对应当前终端信息;
    根据所述当前终端信息计算所述目标直播间的当前终端占比信息。
  8. 如权利要求7所述的确定直播间刷量的方法,根据所述终端历史比例和所述终端当前比例,确定所述目标直播间是否存在刷量情况,包括:
    根据所述目标直播间类型在所述终端历史比例中确定目标终端历史比例;
    在所述当前终端占比信息满足所述目标终端历史比例的情况下,确定所述目标直播间不存在刷量情况;
    在所述当前终端占比信息未满足所述目标终端历史比例的情况下,确定所述目标直播间存在刷量情况。
  9. 如权利要求6-8任意一项所述的确定直播间刷量的方法,统计每个直播间类型对应的历史终端信息,包括:
    获取每个直播间类型对应的用户集合;
    确定每个用户集合中用户使用终端的终端信息。
  10. 如权利要求1-9任意一项所述的确定直播间刷量的方法,统计直播平台的历史终端信息,确定终端历史比例,包括:
    统计所述直播平台中参与直播的终端***信息,根据所述终端***信息确定历史终端***占比信息;
    统计每个终端***对应的终端属性信息,根据每个终端***的终端属性信息确定每个终端***对应的历史终端属性占比信息。
  11. 如权利要求10所述的确定直播间刷量的方法,采集目标直播间的当前终端信息,并基于所述当前终端信息确定终端当前比例,包括:
    采集所述目标直播间在当前时间点的当前终端信息;
    根据所述当前终端信息计算所述目标直播间的当前终端***占比信息和每个终端***对应的当前终端属性占比信息。
  12. 如权利要求11所述的确定直播间刷量的方法,根据所述终端历史比例和所述终端当前比例,确定所述目标直播间是否存在刷量情况,包括:
    判断所述当前终端***占比信息与所述历史终端***占比信息是否满足***刷量判定规则;
    若是,则确定所述目标直播间存在刷量情况;
    若否,确定目标终端***,判断所述目标终端***对应的当前终端属性占比信息与所述目标终端***对应的历史终端属性占比信息是否满足属性刷量判定规则;
    若是,则确定所述目标直播间存在刷量情况;
    若否,则确定所述目标直播间不存在刷量情况。
  13. 如权利要求10-12任意一项所述的确定直播间刷量的方法,统计所述直播平台中参与直播的终端***信息,包括:
    获取所述直播平台中参与直播的用户集合;
    确定每个用户集合中用户使用终端的终端***信息。
  14. 如权利要求1-13任意一项所述的确定直播间刷量的方法,在采集目标直播间的当前终端信息之前,所述方法还包括:
    在所述直播平台中确定初始直播间,并获取所述初始直播间的直播间人数;
    在所述直播间人数超过预设阈值的情况下,确定所述初始直播间为目标直播间。
  15. 一种确定直播间刷量的装置,包括:
    统计模块,被配置为统计直播平台的历史终端信息,确定终端历史比例;
    采集模块,被配置为采集目标直播间的当前终端信息,并基于所述当前终端信息确定终端当前比例;
    确定模块,被配置为根据所述终端历史比例和所述终端当前比例,确定所述目标直播间是否存在刷量情况。
  16. 一种计算设备,包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机指令,所述处理器执行所述计算机指令时实现权利要求1-14任意一项所述方法的步骤。
  17. 一种计算机可读存储介质,其存储有计算机指令,该计算机指令被处理器执行时实现权利要求1-14任意一项所述方法的步骤。
  18. 一种计算机程序,当所述计算机程序在计算机中执行时,令计算机执行权利要求1-14任意一项所述方法的步骤。
PCT/CN2022/099477 2021-11-02 2022-06-17 确定直播间刷量的方法及装置 WO2023077813A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111290640.7 2021-11-02
CN202111290640.7A CN114024737B (zh) 2021-11-02 2021-11-02 确定直播间刷量的方法、装置及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2023077813A1 true WO2023077813A1 (zh) 2023-05-11

Family

ID=80059773

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/099477 WO2023077813A1 (zh) 2021-11-02 2022-06-17 确定直播间刷量的方法及装置

Country Status (2)

Country Link
CN (1) CN114024737B (zh)
WO (1) WO2023077813A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114024737B (zh) * 2021-11-02 2023-10-17 上海哔哩哔哩科技有限公司 确定直播间刷量的方法、装置及计算机可读存储介质
CN114945097B (zh) * 2022-04-26 2024-02-23 上海哔哩哔哩科技有限公司 视频流处理方法及装置

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107465698A (zh) * 2017-09-26 2017-12-12 武汉斗鱼网络科技有限公司 一种数据校验方法及服务器
CN108206961A (zh) * 2018-01-12 2018-06-26 武汉斗鱼网络科技有限公司 一种计算直播平台人气的方法及相关设备
WO2019114514A1 (zh) * 2017-12-14 2019-06-20 广州酷狗计算机科技有限公司 在直播间显示音高信息的方法及装置、存储介质
CN110754076A (zh) * 2017-08-30 2020-02-04 深圳市欢太科技有限公司 刷量终端确定方法及装置
CN110770724A (zh) * 2017-08-30 2020-02-07 深圳市欢太科技有限公司 刷量资源确定方法及装置
CN112995689A (zh) * 2021-02-24 2021-06-18 上海哔哩哔哩科技有限公司 确定直播间刷量的方法及装置
CN113068052A (zh) * 2021-03-15 2021-07-02 上海哔哩哔哩科技有限公司 确定直播间刷量的方法、直播方法以及数据处理方法
CN114024737A (zh) * 2021-11-02 2022-02-08 上海哔哩哔哩科技有限公司 确定直播间刷量的方法及装置

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107454441B (zh) * 2017-06-30 2019-12-03 武汉斗鱼网络科技有限公司 一种检测直播间刷人气行为的方法、直播平台服务器及计算机可读存储介质
CN108184146B (zh) * 2018-01-12 2020-01-03 武汉斗鱼网络科技有限公司 一种计算直播平台人气的方法及相关设备
CN109241343B (zh) * 2018-07-27 2022-07-22 北京奇艺世纪科技有限公司 一种刷量用户识别***、方法及装置
CN109257617B (zh) * 2018-09-30 2021-11-09 武汉斗鱼网络科技有限公司 一种确定直播平台中嫌疑用户的方法以及相关设备
WO2020257988A1 (zh) * 2019-06-24 2020-12-30 深圳市欢太科技有限公司 刷量用户识别方法及相关产品
CN112788351B (zh) * 2019-11-01 2022-08-05 武汉斗鱼鱼乐网络科技有限公司 一种目标直播间的识别方法、装置、设备和存储介质

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110754076A (zh) * 2017-08-30 2020-02-04 深圳市欢太科技有限公司 刷量终端确定方法及装置
CN110770724A (zh) * 2017-08-30 2020-02-07 深圳市欢太科技有限公司 刷量资源确定方法及装置
CN107465698A (zh) * 2017-09-26 2017-12-12 武汉斗鱼网络科技有限公司 一种数据校验方法及服务器
WO2019114514A1 (zh) * 2017-12-14 2019-06-20 广州酷狗计算机科技有限公司 在直播间显示音高信息的方法及装置、存储介质
CN108206961A (zh) * 2018-01-12 2018-06-26 武汉斗鱼网络科技有限公司 一种计算直播平台人气的方法及相关设备
CN112995689A (zh) * 2021-02-24 2021-06-18 上海哔哩哔哩科技有限公司 确定直播间刷量的方法及装置
CN113068052A (zh) * 2021-03-15 2021-07-02 上海哔哩哔哩科技有限公司 确定直播间刷量的方法、直播方法以及数据处理方法
CN114024737A (zh) * 2021-11-02 2022-02-08 上海哔哩哔哩科技有限公司 确定直播间刷量的方法及装置

Also Published As

Publication number Publication date
CN114024737B (zh) 2023-10-17
CN114024737A (zh) 2022-02-08

Similar Documents

Publication Publication Date Title
WO2023077813A1 (zh) 确定直播间刷量的方法及装置
CN113068052B (zh) 确定直播间刷量的方法、直播方法以及数据处理方法
US11363353B2 (en) Video highlight determination method and apparatus, storage medium, and electronic device
WO2015074540A1 (zh) 页面操作数据处理方法及装置
WO2021196097A1 (zh) 用户画像列表构建方法、装置、服务器以及存储介质
CN103686237A (zh) 推荐视频资源的方法及***
Schwartz et al. Angry apps: The impact of network timer selection on power consumption, signalling load, and web qoe
CN106604137B (zh) 一种预测视频观看时长的方法及装置
CN109428910B (zh) 一种数据处理方法、装置及***
WO2022193835A1 (zh) 数据处理方法、直播方法、鉴权服务器及直播数据服务器
WO2023098030A1 (zh) 确定直播间刷量的方法及装置
CN106412106B (zh) 消息发送方法和装置
CN109495378A (zh) 检测异常帐号的方法、装置、服务器及存储介质
Xu et al. Modeling buffer starvations of video streaming in cellular networks with large-scale measurement of user behavior
CN112423125A (zh) 视频加载方法及装置
Mo et al. Understanding gaming experience in mobile multiplayer online battle arena games
CN104333456A (zh) 一种云计算环境下服务计费的方法及***
CN109688217B (zh) 一种消息推送方法、装置及电子设备
CN111569412B (zh) 一种云游戏资源调度的方法和装置
CN109218766B (zh) 一种召集粉丝的方法、直播平台服务器及主播端
WO2023151426A1 (zh) 直播间人数统计方法及装置
CN114945097B (zh) 视频流处理方法及装置
WO2023179162A1 (zh) 数据处理方法及装置
CN114363666B (zh) 视频处理方法、装置及电子设备
CN112995686B (zh) 数据处理方法、直播方法、鉴权服务器及直播数据服务器

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22888849

Country of ref document: EP

Kind code of ref document: A1