WO2017161776A1 - 弹幕推送方法及装置 - Google Patents

弹幕推送方法及装置 Download PDF

Info

Publication number
WO2017161776A1
WO2017161776A1 PCT/CN2016/089346 CN2016089346W WO2017161776A1 WO 2017161776 A1 WO2017161776 A1 WO 2017161776A1 CN 2016089346 W CN2016089346 W CN 2016089346W WO 2017161776 A1 WO2017161776 A1 WO 2017161776A1
Authority
WO
WIPO (PCT)
Prior art keywords
tag
author
user
barrage
personality
Prior art date
Application number
PCT/CN2016/089346
Other languages
English (en)
French (fr)
Inventor
王若韬
Original Assignee
乐视控股（北京）有限公司
乐视网信息技术（北京）股份有限公司
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 乐视控股（北京）有限公司, 乐视网信息技术（北京）股份有限公司 filed Critical 乐视控股（北京）有限公司
Priority to US15/246,738 priority Critical patent/US20170272800A1/en
Publication of WO2017161776A1 publication Critical patent/WO2017161776A1/zh

Links

Images

Classifications

    • 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
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
    • H04N21/2343—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements
    • 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
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
    • H04N21/25866—Management of end-user data
    • H04N21/25891—Management of end-user data being end-user preferences
    • 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
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
    • H04N21/2343—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements
    • H04N21/234336—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements by media transcoding, e.g. video is transformed into a slideshow of still pictures or audio is converted into text
    • 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
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/239—Interfacing the upstream path of the transmission network, e.g. prioritizing client content requests
    • 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
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/239—Interfacing the upstream path of the transmission network, e.g. prioritizing client content requests
    • H04N21/2393—Interfacing the upstream path of the transmission network, e.g. prioritizing client content requests involving handling client requests
    • 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
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • 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
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/252—Processing of multiple end-users' preferences to derive collaborative data
    • 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
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
    • 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
    • H04N21/488—Data services, e.g. news ticker
    • 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
    • H04N21/488—Data services, e.g. news ticker
    • H04N21/4884—Data services, e.g. news ticker for displaying subtitles
    • 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]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/81—Monomedia components thereof
    • 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]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/81—Monomedia components thereof
    • H04N21/8126—Monomedia components thereof involving additional data, e.g. news, sports, stocks, weather forecasts

Definitions

  • Embodiments of the present invention relate to the field of data statistics and processing technologies, and in particular, to a barrage pushing method and device.
  • the prior art barrage technology displays the text comments of the user at the same time node simultaneously on the video screen that the user is watching.
  • the current barrage technology includes a text barrage and an audio barrage (referred to as a sound bomb); wherein the text barrage is commented by the user typing, and the content of the comment is simultaneously displayed on the video screen during the video playing, and the audio is The barrage is commented by the user's recording, and the recorded comment audio will be played at the corresponding time node during the video playback.
  • a text barrage and an audio barrage referred to as a sound bomb
  • the current text barrage technology does not distinguish the user's comment content on the playback interface, and clears the previous comment content after the comment reaches a certain number. Most of the comments that are often displayed in this way are watered content. Not really what users are interested in. In addition, due to the different evaluation criteria of the individual, the application information platform is different, so how to make the user see the comment content that he is interested in when displaying the text barrage becomes a major problem.
  • the current audio barrage technology because the user prefers to hear the content of interest when playing the sound bomb, does not want to hear the irrigation content, affecting its audiovisual experience, but because of the different evaluation criteria, the application information platform is different. , so how to make the user play the sound bomb It is a major problem to hear the contents of the sound bombs that he is interested in.
  • the purpose of the embodiments of the present invention is to provide a method and a device for pushing a barrage, which can preferentially push a salvage screen of interest to a target user, and can be widely applied to mobile phones, tablet computers, televisions, computers, and vehicle systems. Wait for the terminal.
  • the barrage of the video corresponding to the successful author's personality tag is preferentially pushed to the target push user.
  • Another aspect of the embodiments of the present invention further discloses a barrage pushing device, including:
  • a barrage acquisition request receiving module configured to receive a barrage acquisition request of the target push user for the video being watched
  • a user personality tag obtaining module configured to acquire a first history record of the target push user, and obtain a user personality tag of the target push user according to the first history record;
  • a human personality tag acquisition module configured to acquire a second history record of at least one barrage author of the video and/or an author tag tagged by another user; and, according to the second history of the barrage author and / or its author's label, respectively, to analyze the respective author's individual label of the barrage author;
  • a tag matching module configured to match a user personalized tag of the target push user with an author personality tag of the barrage author
  • the barrage pushing module is configured to preferentially push the barrage made by the barrage author corresponding to the successfully matched author's personality tag to the target push user.
  • a barrage pushing device including: a processor, a memory, and a bus system.
  • the processor and the memory are connected by the bus system,
  • the memory is for storing instructions
  • the processor is configured to execute the memory stored instructions for:
  • the barrage of the video corresponding to the successful author's personality tag is preferentially pushed to the target push user.
  • Another aspect of the present invention also provides a computer readable storage medium for storing a calculation
  • the machine executable instructions are used to perform the aforementioned methods when the instructions are executed by one or more processors.
  • the barrage pushing method and device can extract the user personalized tag representing the personal preference from the first history record of the target pushing user, and the user personalized tag and the bullet.
  • the author's author's personality tag is matched, and the barrage made by the matching barrage author is preferentially pushed to the target push user, so that he can see or hear the barrage that is more likely to be of interest, not just Pushing the user's general play barrage to the target, thereby improving the pertinence of the barrage playback and improving the user experience.
  • FIG. 1 is a schematic flowchart of an embodiment of a method for pushing a barrage according to an embodiment of the present invention
  • FIG. 2 is a schematic flow chart of another embodiment of a method for pushing a barrage according to an embodiment of the present invention
  • FIG. 3 is a schematic structural diagram of a module of an embodiment of a barrage pushing device according to an embodiment of the present invention.
  • FIG. 4 is a schematic block diagram showing the structure of an embodiment of a barrage pushing device 4 according to an embodiment of the present invention.
  • FIG. 1 is a schematic flow chart of an embodiment of a barrage pushing method provided by the present invention.
  • the barrage pushing method is applied to a server, and includes the following steps:
  • Step 101 Receiving a barrage request of the target push user for the video being watched; in general, the barrage acquisition request is automatically sent to the server by the user terminal when the user opens the play interface of the video, and is used for Requesting the server to push the barrage (including the text barrage and the audio barrage) associated with the video; however, it is not excluded that the barrage acquisition request is manually issued by the user, such as clicking a button for acquiring the barrage to issue Barrage acquisition request;
  • Step 102 Acquire a first history record of the target push user, and obtain a user personality tag of the target push user according to the first history record;
  • the first history record may include any information about the target push user.
  • Historical operation record such as historical viewing history, created album, etc.
  • the user personality tag is a tag that can be analyzed from the first history record and can push the user's personality and preferences on behalf of the target, usually The number of labels in the user personality tag is at least two;
  • Step 103 Acquire a second history record of at least one barrage author of the video and/or an author tag tagged by another user; likewise, the second history record may include any about the barrage author Historical operation records, such as historical viewing records, created albums, etc.;
  • Step 104 According to the respective second history records of the barrage authors and/or their author tags, respectively analyzing the respective author personal tags of the barrage authors; the author personality tags are from the second history records. A label that can be analyzed and can represent the personality and preferences of the author of the barrage. Typically, the tag in the author's personality tag The number is at least two;
  • Step 105 Match the user personalized tag of the target push user with the author personality tag of the barrage author according to a preset matching rule
  • Step 106 The barrage of the video corresponding to the successful author's personal tag is preferentially pushed to the target push user.
  • the barrage pushing method can extract the user personality tag representing the personal preference from the first history record of the target pushing user, and the user personality tag and the barrage author.
  • the author's personality tag is matched, and the barrage made by the matching barrage author is preferentially pushed to the target push user, so that it can see or hear the barrage that is more likely to be of interest, not just to the target. Pushing users to play a generalized barrage, thus improving the pertinence of the barrage playback and improving the user experience.
  • the first history record includes a first history view record and a first view interaction record of the target push user;
  • the first history view record includes a target push user once viewed Video, including movies, short films, TV series, entertainment programs, etc., as well as the viewing time, duration, etc. of these videos;
  • the first viewing interaction record refers to the target pushing user watching video or using video software, video website
  • the step of obtaining the user personalized tag of the target push user according to the first historical record analysis includes:
  • the analyzed related tags related to the user's viewing habits, the user interaction record personal tags are tags related to the user's interaction habits analyzed from the first viewing interaction record;
  • a user personality tag including the user viewing record personality tag and the user interaction record personality tag is obtained.
  • the user personality tag includes the label related to the viewing habit and the interaction habit of the target pushing user, thereby enriching the content of the user's personalized tag, and more fully reflecting the preference of the target pushing user.
  • the second history record includes a second historical viewing record and a second viewing interaction record of the barrage author;
  • the second historical viewing record includes a video that the barrage author has watched. , including movies, short films, TV series, entertainment programs, etc., as well as the viewing time, duration, etc. of these videos;
  • the second viewing interaction record refers to the process of watching the video or using video software and video websites by the barrage author. Some interactions, such as creating an album of interest to you, praising the video, commenting, etc.
  • the steps of separately analyzing the respective author's personality tags of the barrage authors according to the respective second history records of the barrage authors and their author tags include:
  • the author of the barrage author is separately analyzed to view the recording personality tag and the author interaction record personality tag;
  • the author viewing the recording personality tag is from the second historical viewing record
  • An author personality tag is obtained that includes the author viewing record personality tag, the author interaction record personality tag, and the author tag.
  • the author personality tag includes the viewing habits of the barrage author, the interaction habits, and the tags related to the author itself, thereby enriching the content of the author's personality tag, and more fully reflecting the barrage author. The preference.
  • the target pushes the first history of the user
  • the viewing record includes the video that the target push user viewed;
  • the first viewing interaction record includes an album created by the target push user, a published comment, and a praised user;
  • the step of obtaining the user personalized tag of the target push user according to the first historical record analysis may further include the following steps:
  • the viewed video may be a video that has been viewed during a preset period, for example, a video that has been viewed within 30 days, and for accuracy, a video may be selected for a longer period of time, but may be given later.
  • the video of the time is weighted with a large weight, giving the video of the earlier time a small weight to highlight the target point of interest of the user at the current stage;
  • the video tag includes the tag for the target push user and other users for it
  • the label that is marked, that is, the label that all users put on, may also include a type label that the service provider pre-applies to the video, such as a palace, a science fiction, a funny class, etc.;
  • the first preset frequency may be preset , or it can be user-defined, for example, 5 times within 30 days;
  • the album here refers to the albums that users create themselves according to the type they are interested in, such as American comedy, Korean soap operas, etc. Since the album created by the user can better reflect the user's interest, the target can be pushed to the user.
  • the label of the created album is used as a personalized standard for pushing the user's account, for example, increasing the weight of the user's personalized album label; in addition, according to the morning and evening of the album creation date and the morning and evening of the update date, the corresponding user can also be given accordingly. Personality album labels with different weights;
  • the published comment may be a comment published within a preset period, for example, a comment published within 30 days, and for accuracy, a comment may be selected for a longer period of time, but a later comment may be given accordingly With a large weight, the earlier time comment is given a small weight to highlight the target to push the user's current point of interest;
  • the second preset frequency may be preset or user-defined, for example Appeared twice in 30 days;
  • the user who is praised by the target push user is a self-character tag, which is derived from the type of content that is published, and may include the viewed video, the created album, the published comment, or may include the target push.
  • a user personality tag including the user personality video tag, the user personality album tag, the user personality comment tag, and the user personality appreciation tag is obtained.
  • the user personalized tag includes a specific tag that can better reflect the user's preference, thereby enriching the content of the user's personalized tag, and more fully reflecting the preference of the target pushing user.
  • the second viewing history of the barrage author includes a video viewed by the barrage author, the second viewing interaction record including an album created by the barrage author, published User comments and praised users;
  • the author tags tagged by other users include a personality tag and a work tag, the personality tag being the barr author's own tag, and the work tag is the work of the barrage author
  • the label, the personalized label and the work label may be labels labeled by the barrage author himself or by other users to the barrage author;
  • the step of separately analyzing the respective author's personality tags of the barrage authors according to the respective second history records of the barrage authors and their author tags may further include the following steps: Step:
  • the viewed video may be a video that has been viewed during a preset period, for example, a video that has been viewed within 30 days, and for accuracy, a video may be selected for a longer period of time, but may be given later.
  • the video of time is weighted with a small weight to give the video of the earlier time a small weight to highlight the current point of interest of the barrage author; the video tag includes the tag for the barrage author and other users for it.
  • the labeled label may also include a type label that the service provider pre-applies to the video, such as a palace class, a science fiction class, a funny class, etc.;
  • the third preset frequency may be preset It can also be customized by the barrage author, for example, 5 times within 30 days, which may or may not be equal to the first preset frequency as needed;
  • the album here refers to the album created by the barrage author according to the type he is interested in, such as American comedy, Korean soap opera, etc., because the album created by the barrage author can better reflect the interest of the barrage author. Therefore, the label of the album created by the barrage author can be used as the personalization standard of the account of the barrage author, for example, to increase the weight of the author's personalized album label; in addition, according to the morning and evening of the album creation date and the morning and evening of the update date, Correspondingly, as a standard that gives the corresponding author's personalized album labels different weights;
  • the published comment may be a comment published within a preset period, such as Comments published within 30 days, for accuracy, you can choose a comment for a longer period of time, but you can give a later weight to the comments with a larger weight, giving the earlier comments a small weight to highlight the barrage
  • the current point of interest of the author may be preset or may be customized by the barrage author, for example, appearing twice in 30 days, and may be equal to the second preset frequency as needed Can also wait;
  • the same user who is praised by the barrage author is a self-character tag, derived from the type of content he publishes, and may include videos that have been viewed, created albums, published comments, or a label tagged by other users, including the author of the barrage, or a tag that the user himself is playing for himself;
  • An author personality tag including the author's personalized video tag, the author's personalized album tag, the author's personalized review tag, the author's personalized appreciation tag, the personality tag, and the work tag is obtained.
  • the author of the barrage is a celebrity or a star
  • the barrage made by the barrage is usually invited by the operator, and therefore, the author's personality tag of this type of barrage author also includes the operator.
  • the author's personality tag of this type of barrage author also includes the operator.
  • pre-defined author tags such as comic actor may be given the label "traditional Chinese humor” and “cross talk”, while young actor may be given the label “youth” and "avant-garde”.
  • the author's personality tag includes a specific tag that can better reflect the preferences of the barrage author, thereby enriching the content of the author's personality tag, and more fully reflecting the preferences of the barrage author.
  • the step of matching the user personalized tag of the target push user with the author personality tag of the barrage author includes:
  • the author personal tag of the barrage author and the user of the target push user Determining, when the same number of the author personality tag of the barrage author and the user personalized tag of the target push user is greater than or equal to a preset number threshold, determining the author personal tag of the barrage author and the user of the target push user
  • the personalized tags are matched; the preset number threshold may be two or more, and of course, may be preset or user-defined as needed.
  • the step of preferentially pushing the user to the target push user by the barrage player corresponding to the successfully matched author personality tag for the video player is:
  • the sorted barrage is sequentially pushed to the target push user.
  • the number of identical personality tags of the matching screen authors A, B, and C and the target push user are 5, 4, and 3 respectively.
  • the barrage made by the barrage author A is first pushed, and then the barrage is pushed.
  • the barrage made by the author B finally pushes the barrage made by the barrage author C, but when the barrage of the three appears at the same or the same time point, the barrage is pushed in the order of A to B and then C, so that Make the barrage push more targeted.
  • all user personalized tags can be sorted according to the weight of the user's personalized tag, and then the weights of the user's personalized tag and the user's personalized tag are sorted according to the weight of the user's personalized tag, and the top priority is ranked. Push to the target to push the user.
  • the user personality tag includes a, b, and c, and the weights are 0.5, 0.3, and 0.2, respectively, and the author's personality tag of the barrage author A is a, d, and the author's personality tag of the barrage author B is b, e, and the barrage The author's author's personality tag is c, f.
  • the preset number threshold is 1, the barrage authors A, B, C and the target push user are all successfully matched, according to the same tag.
  • the weights are A ⁇ a ⁇ 0.5, B ⁇ b ⁇ 0.3, C ⁇ c ⁇ 0.2. Therefore, when pushing, the user pushes the barrage to the target in the order of A to B and then C. This can further improve The targeting of the barrage push.
  • the step of preferentially pushing to the target push user further includes:
  • the text barrage corresponding to the successfully matched text content is preferentially pushed to the target push user.
  • the text barrage closer to the video theme can be preferentially pushed, which reduces the irrigation content.
  • the barr author corresponding to the author's personality tag matching the success is a bomb for the video.
  • the step of preferentially pushing the target push user includes:
  • the audio barr corresponding to the successfully matched text content is preferentially pushed to the target push user.
  • the audio barrage closer to the video theme is preferentially pushed, and the watering content is reduced.
  • FIG. 2 is a schematic flow chart of another embodiment of a barrage pushing method provided by the present invention.
  • the barrage pushing method comprises the following steps:
  • Step 201 Receive a barrage acquisition request of the target push user for the video being watched;
  • Step 202 Obtain a video tag of the video that the target pushes the user to watch, and extract, from the video tag, a video tag whose appearance frequency is higher than the first preset frequency as the user personalized video tag.
  • Step 203 Push an album created by the user according to the target, and extract an album label as a user personalized album label;
  • Step 204 Acquire a comment published by the target push user, and extract a comment tag whose appearance frequency is higher than the second preset frequency as the user personality comment tag from the comment;
  • Step 205 Acquire a user label of the user that the target push user likes, and use it as a user personality appreciation label
  • Step 206 Obtain a user personality tag including the user personalized video tag, the user personalized album tag, the user personalized comment tag, and the user personalized appreciation tag.
  • Step 207 Obtain a video tag of the video viewed by the barrage author, and extract a video tag whose appearance frequency is higher than a third preset frequency from the video tag as an author personalized video tag.
  • Step 208 Extract an album label as an author personalized album label according to the album created by the barrage author;
  • Step 209 Acquire a comment published by the barrage author, and extract a comment tag whose appearance frequency is higher than the fourth preset frequency as the author personality comment tag from the comment;
  • Step 210 Obtain a user label of the user that the title of the browser is praised, and use it as an author's personality appreciation label;
  • Step 211 Obtain an author including the author personalized video tag, the author's personalized album tag, the author's personalized comment tag, the author's personalized appreciation tag, the personality tag, and the work tag. Personality label.
  • Step 212 Compare the user personalized tag of the target push user with the author personality tag of the barrage author
  • Step 213 When the same number of the user personality tag of the barrage author and the user personality tag of the target push user is greater than or equal to a preset number threshold, determine the author personality tag of the barrage author and the target push The user's user personality tag matches;
  • Step 214 Sort the barrage of the video by the barrage author corresponding to the author's personalized tag according to the number of the user's personalized tag matching the target push user, in order of the number from the most to the least. ;
  • Step 215 determining the type of the barrage
  • Step 216 When the barrage made by the barrage player for the video is a text barrage, matching the text content of the text barrage made by the sorted player to the video to match the tag of the video ;
  • Step 217 Push the text barr corresponding to the successfully matched text content to the target push user first.
  • Step 218 When the barrage of the video player is an audio barr for the video, converting the audio content of the audio barr made by the sorted player to the text content into text content;
  • Step 219 Match the converted text content with the label of the video
  • Step 220 Push the audio barr corresponding to the successfully matched text content to the target push user.
  • the barrage pushing method can extract the user personality tag representing the personal preference from the first history record of the target pushing user, and the user personality tag and the barrage author.
  • the author's personality tag is matched, and the barrage made by the matching barrage author is preferentially pushed to the target push user, thereby It sees or hears the barrage that is more likely to be of interest, and not just pushes the user to play the generalized barrage to the target, thereby improving the pertinence of the barrage playback and improving the user experience.
  • FIG. 3 is a schematic structural diagram of a module of an embodiment of a barrage pushing device provided by the present invention.
  • the barrage pushing device 3 includes:
  • the barrage acquisition request receiving module 301 is configured to receive a barrage acquisition request of the target push user for the video being watched; in general, the barrage acquisition request is when the user opens the play interface of the video, the user terminal Automatically sent to the server for requesting the server to push the barrage (including the text barrage and the audio barrage) associated with the video; however, it is not excluded that the barrage acquisition request is manually sent by the user, for example Click the button to get the barrage to issue a barrage request;
  • the user personality tag obtaining module 302 is configured to acquire a first history record of the target push user, and obtain a user personality tag of the target push user according to the first history record;
  • the first history record may include The target pushes the user's arbitrary historical operation record, such as a history watch record, a created album, etc.;
  • the user personality tag is a character that can be analyzed from the first history record and can push the user's personality on behalf of the target a favorite tag, usually, the number of tags in the user personality tag is at least two;
  • the author personality tag obtaining module 303 is configured to acquire a second history record of at least one barrage author of the video and/or an author tag tagged by another user; and, according to the second history record of the barrage author And/or its author label, respectively analyzing the author's individual personality tags of the barrage author; likewise, the second history record may include any historical operation records about the barrage author, such as historical viewing records , Created albums, etc.; the author personality tag is a tag that can be analyzed from the second history record and can represent the personality and preferences of the barrage author, usually in the author's personality tag The number of tags is at least two;
  • the tag matching module 304 is configured to match the user personality tag of the target push user with the author personality tag of the barrage author;
  • the barrage pushing module 305 is configured to preferentially push the barrage made by the barrage author corresponding to the successfully matched author's personality tag to the target push user.
  • the barrage pushing device provided by the embodiment of the present invention can extract the user personalized tag representing the personal preference from the first history record of the target pushing user, and the user personality tag and the barrage author.
  • the author's personality tag is matched, and the barrage made by the matching barrage author is preferentially pushed to the target push user, so that it can see or hear the barrage that is more likely to be of interest, not just to the target. Pushing users to play a generalized barrage, thus improving the pertinence of the barrage playback and improving the user experience.
  • the first history record includes a first history view record and a first view interaction record of the target push user;
  • the first history view record includes a target push user once viewed Video, including movies, short films, TV series, entertainment programs, etc., as well as the viewing time, duration, etc. of these videos;
  • the first viewing interaction record refers to the target pushing user watching video or using video software, video website
  • the user personality tag obtaining module 302 is specifically configured to:
  • the user viewing record personality tag is from the first historical viewing record
  • a user personality tag including the user viewing record personality tag and the user interaction record personality tag is obtained.
  • the user personality tag includes the label related to the viewing habit and the interaction habit of the target pushing user, thereby enriching the content of the user's personalized tag, and more fully reflecting the preference of the target pushing user.
  • the second history record includes a second historical viewing record and a second viewing interaction record of the barrage author;
  • the second historical viewing record includes a video that the barrage author has watched. , including movies, short films, TV series, entertainment programs, etc., as well as the viewing time, duration, etc. of these videos;
  • the second viewing interaction record refers to the process of watching the video or using video software and video websites by the barrage author. Some interactions, such as creating an album of interest to you, praising the video, commenting, etc.
  • the author personality tag obtaining module 303 is specifically configured to:
  • the author of the barrage author is separately analyzed to view the recording personality tag and the author interaction record personality tag;
  • the author viewing the recording personality tag is from the second historical viewing record
  • a user personality tag including the author viewing record personality tag, the author interaction record personality tag, and the author tag is obtained.
  • the author personality tag includes the viewing habits of the barrage author, the interaction habits, and the tags related to the author itself, thereby enriching the content of the author's personality tag, and more fully reflecting the barrage author. The preference.
  • the target pushes the first history of the user
  • the viewing record includes the video that the target push user viewed;
  • the first viewing interaction record includes an album created by the target push user, a published comment, and a praised user;
  • the user personality tag obtaining module 302 is specifically configured to:
  • the viewed video may be a video that has been viewed during a preset period, for example, a video that has been viewed within 30 days, and for accuracy, a video may be selected for a longer period of time, but may be given later.
  • the video of the time is weighted with a large weight, giving the video of the earlier time a small weight to highlight the target point of interest of the user at the current stage;
  • the video tag includes the tag for the target push user and other users for it
  • the label that is marked, that is, the label that all users put on, may also include a type label that the service provider pre-applies to the video, such as a palace, a science fiction, a funny class, etc.;
  • the first preset frequency may be preset , or it can be user-defined, for example, 5 times within 30 days;
  • the album here refers to the albums that users create themselves according to the type they are interested in, such as American comedy, Korean soap operas, etc. Since the album created by the user can better reflect the user's interest, the target can be pushed to the user.
  • the label of the created album is used as a personalized standard for pushing the user's account, for example, increasing the weight of the user's personalized album label; in addition, according to the morning and evening of the album creation date and the morning and evening of the update date, the corresponding user can also be given accordingly. Personality album labels with different weights;
  • the published comment may be a comment published within a preset period, such as Comments published within 30 days, for accuracy, you can choose a comment for a longer period of time, but you can give the later comments a larger weight, and give the earlier comments a small weight to highlight the target push.
  • the user's current point of interest; the second preset frequency may be preset or user-defined, for example, 2 times within 30 days;
  • the user who is praised by the target push user is a self-character tag, which is derived from the type of content that is published, and may include the viewed video, the created album, the published comment, or may include the target push.
  • a user personality tag including the user personality video tag, the user personality album tag, the user personality comment tag, and the user personality appreciation tag is obtained.
  • the user personalized tag includes a specific tag that can better reflect the user's preference, thereby enriching the content of the user's personalized tag, and more fully reflecting the preference of the target pushing user.
  • the second viewing history of the barrage author includes a video viewed by the barrage author, the second viewing interaction record including an album created by the barrage author, published User comments and praised users;
  • the author tags tagged by other users include a personality tag and a work tag, the personality tag being the barr author's own tag, and the work tag is the work of the barrage author
  • the label, the personalized label and the work label may be labels labeled by the barrage author himself or by other users to the barrage author;
  • the author personality tag obtaining module 303 is specifically configured to:
  • the viewed video may be a video that has been viewed during a preset period, for example, a video that has been viewed within 30 days, and for accuracy, a video may be selected for a longer period of time, but may be given later.
  • the video of time is weighted with a small weight to give the video of the earlier time a small weight to highlight the current point of interest of the barrage author; the video tag includes the tag for the barrage author and other users for it.
  • the labeled label may also include a type label that the service provider pre-applies to the video, such as a palace class, a science fiction class, a funny class, etc.;
  • the third preset frequency may be preset It can also be customized by the barrage author, for example, 5 times within 30 days, which may or may not be equal to the first preset frequency as needed;
  • the album here refers to the album created by the barrage author according to the type he is interested in, such as American comedy, Korean soap opera, etc., because the album created by the barrage author can better reflect the interest of the barrage author. Therefore, the label of the album created by the barrage author can be used as the personalization standard of the account of the barrage author, for example, to increase the weight of the author's personalized album label; in addition, according to the morning and evening of the album creation date and the morning and evening of the update date, Correspondingly, as a standard that gives the corresponding author's personalized album labels different weights;
  • the published comment may be a comment published within a preset period, for example, a comment published within 30 days, and for accuracy, a comment may be selected for a longer period of time, but a later comment may be given accordingly With a large weight, the earlier comments are given a small weight to highlight the current point of interest of the barrage author;
  • the second preset frequency can It is pre-set, or it can be customized by the barrage author, for example, it appears twice in 30 days, and it can be equal to or equal to the second preset frequency as needed;
  • the same user who is praised by the barrage author is a self-character tag, derived from the type of content he publishes, and may include videos that have been viewed, created albums, published comments, or a label tagged by other users, including the author of the barrage, or a tag that the user himself is playing for himself;
  • An author personality tag including the author's personalized video tag, the author's personalized album tag, the author's personalized review tag, the author's personalized appreciation tag, the personality tag, and the work tag is obtained.
  • the author of the barrage is a celebrity or a star
  • the barrage made by the barrage is usually invited by the operator, and therefore, the author's personality tag of this type of barrage author also includes the operator.
  • the author's personality tag of this type of barrage author also includes the operator.
  • pre-defined author tags such as comic actor may be given the label "traditional Chinese humor” and “cross talk”, while young actor may be given the label “youth” and "avant-garde”.
  • the author's personality tag includes a specific tag that can better reflect the preferences of the barrage author, thereby enriching the content of the author's personality tag, and more fully reflecting the preferences of the barrage author.
  • the tag matching module 304 is specifically configured to:
  • the number threshold may be two or more, and of course, it may be preset or user-defined as needed.
  • the barrage pushing module 305 is specifically configured to:
  • the sorted barrage is sequentially pushed to the target push user.
  • the number of identical personality tags of the matching screen authors A, B, and C and the target push user are 5, 4, and 3 respectively.
  • the barrage made by the barrage author A is first pushed, and then the barrage is pushed.
  • the barrage made by the author B finally pushes the barrage made by the barrage author C, but when the barrage of the three appears at the same or the same time point, the barrage is pushed in the order of A to B and then C, so that Make the barrage push more targeted.
  • all user personalized tags can be sorted according to the weight of the user's personalized tag, and then the weights of the user's personalized tag and the user's personalized tag are sorted according to the weight of the user's personalized tag, and the top priority is ranked. Push to the target to push the user.
  • the user personality tag includes a, b, and c, and the weights are 0.5, 0.3, and 0.2, respectively, and the author's personality tag of the barrage author A is a, d, and the author's personality tag of the barrage author B is b, e, and the barrage The author's author's personality tag is c, f.
  • the preset number threshold is 1, the barrage authors A, B, C and the target push user are all successfully matched.
  • a ⁇ a ⁇ 0.5, respectively. B ⁇ b ⁇ 0.3, C ⁇ c ⁇ 0.2 therefore, when pushing, the user pushes the bullet bar to the target in the order of A to B and then C. In this way, the pertinence of the barrage push can be further improved.
  • the barrage pushing module 305 is specifically configured to:
  • the text barrage closer to the video theme can be preferentially pushed, which reduces the irrigation content.
  • the barrage pushing module 305 is specifically configured to:
  • the audio barr corresponding to the successfully matched text content is preferentially pushed to the target push user.
  • the audio barrage closer to the video theme is preferentially pushed, and the watering content is reduced.
  • the barrage pushing device 4 includes a processor 41, a memory 42, and a bus system 43. .
  • the processor 41 and the memory 42 are connected by a bus system 43 for storing instructions, and the processor 41 is configured to execute the instructions stored by the memory 42 for:
  • the barrage of the video corresponding to the successful author's personality tag is preferentially pushed to the target push user.
  • the memory 42 of the barrage pushing device 4 may be a non-transitory computer readable storage medium for storing computer executable instructions that, when executed by one or more processors, may cause The processor performs the steps of the above method embodiments, such as steps 101 to 106 as described in FIG. 1, or steps 201 to 220 as described in FIG. 2, or may cause the processor to perform the functions of the modules of the above device embodiments, such as The functions of the modules 301 to 306 as shown in FIG. 3 may also be stored and/or transmitted in any non-transitory computer readable storage medium for use by the instruction execution system, apparatus or device, or in combination.
  • Non-transitory computer readable storage medium can be any medium that tangibly contains or stores computer-executable instructions, which can be used by an instruction execution system, device, or system Or use in conjunction with an instruction execution system, device, or device.
  • Non-transitory computer readable storage media may include, but are not limited to, magnetic, optical, and/or semiconductor storage devices. Examples of such storage devices include magnetic disks, CD-ROM based on CD, DVD or Blu-ray technology, and persistent solid-state memories (such as flash memory, solid state drives, etc.).
  • the processor 41 may be a central processing unit ("Central Processing Unit” (referred to as "CPU”).
  • CPU Central Processing Unit
  • the processor 41 can also be His general purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs) or other programmable logic devices, discrete or transistor logic devices, discrete hardware components, and the like.
  • DSPs digital signal processors
  • ASICs application specific integrated circuits
  • FPGAs off-the-shelf programmable gate arrays
  • the general purpose processor may be a microprocessor or the processor or any conventional processor or the like.
  • the bus system 43 may include a power bus, a control bus, a status signal bus, and the like in addition to the data bus. However, for clarity of description, various buses are labeled as the bus system 43 in the figure.
  • the barrage pushing device is not limited to the components and configurations of FIG. 4, and may include other or additional components in various configurations.
  • each step of the above method or each module of the device may be completed by an integrated logic circuit of hardware in the processor 41 or an instruction in the form of software.
  • the modules of the steps or apparatus of the method disclosed in the embodiments of the present application may be directly embodied as hardware processor execution completion. Or complete with a combination of hardware and software modules in the processor.
  • the software module can be located in a conventional storage medium such as random access memory, flash memory, read only memory, programmable read only memory or electrically erasable programmable memory, registers, and the like.
  • the storage medium is located in the memory 42, and the processor 41 reads the information in the memory 42 and performs the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.
  • the barrage pushing device provided by the embodiment of the invention can extract the user personality tag representing the personal preference from the first history record of the target pushing user, and match the user personality tag with the author personality tag of the barrage author.
  • the barrage made by the matching successful barrage is preferentially pushed to the target push user, so that it can see or hear the barrage that is more likely to be of interest, rather than just pushing the user to play the generalized barrage to the target, thereby Improve the targeting of the barrage playback and enhance the user experience.
  • DRAM dynamic RAM

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Computer Graphics (AREA)
  • Computing Systems (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本发明实施例公开了一种弹幕推送方法及装置，其中，方法包括：接收目标推送用户的对所收看视频的弹幕获取请求；获取所述目标推送用户的第一历史记录，并根据所述第一历史记录分析得到目标推送用户的用户个性标签；获取所述视频的至少一个弹幕作者的第二历史记录和/或其被其他用户打上的作者标签；根据所述弹幕作者各自的第二历史记录和/或其作者标签，分别分析得到所述弹幕作者各自的作者个性标签；将所述目标推送用户的用户个性标签与所述弹幕作者的作者个性标签进行匹配；将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕，优先推送给所述目标推送用户。本发明实施例提出的弹幕推送方法及装置，能够向目标用户优先推送其感兴趣的弹幕。

Description

弹幕推送方法及装置
本申请要求于2016年3月21日提交中国专利局、申请号为201610162782.8、发明名称为“弹幕推送方法及装置”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】
本发明实施例涉及数据统计与处理技术领域，特别是指一种弹幕推送方法及装置。
【背景技术】
现有技术中的弹幕技术，通过将同一时间节点的用户的文字评论同时显示在用户正在观看的视频画面上。
目前的弹幕技术，包括文字弹幕和音频弹幕(简称音弹)；其中，文字弹幕通过用户打字进行评论，评论的内容在视频播放的过程中同时会显示在视频画面上，而音频弹幕则是通过用户录音进行评论，录下的评论音频在视频播放的过程中同时会在相应时间节点进行播放。
但是目前的文字弹幕技术，对用户的评论内容不加区分显示在播放界面上，并在评论到达一定数量后清空之前的评论内容，通过这种方式往往显示的大多数评论都是灌水内容，并不是用户真正感兴趣的。另外由于个性化的评判标准不同，应用的信息平台不同，因此显示文字弹幕时如何使用户看到他感兴趣的评论内容，成为主要问题。
而目前的音频弹幕技术，由于音弹在播放时用户更喜欢听到其感兴趣的内容，不想听到灌水内容，影响其视听感受，但是由于个性化的评判标准不同，应用的信息平台不同，因此播放音弹时如何使用户 听到他感兴趣的音弹评论内容，成为主要问题。
【发明内容】
有鉴于此，本发明实施例的目的在于提出一种弹幕推送方法及装置，能够向目标用户优先推送其感兴趣的弹幕，可广泛应用于手机、平板电脑、电视、计算机、及车载系统等终端。
基于上述目的本发明实施例提供的弹幕推送方法，包括：
接收目标推送用户的对所收看视频的弹幕获取请求；
获取所述目标推送用户的第一历史记录，并根据所述第一历史记录分析得到目标推送用户的用户个性标签；
获取所述视频的至少一个弹幕作者的第二历史记录和/或其被其他用户打上的作者标签；
根据所述弹幕作者各自的第二历史记录和/或其作者标签，分别分析得到所述弹幕作者各自的作者个性标签；
将所述目标推送用户的用户个性标签与所述弹幕作者的作者个性标签进行匹配；
将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕，优先推送给所述目标推送用户。
本发明实施例的另一方面还公开了一种弹幕推送装置，包括：
弹幕获取请求接收模块，用于接收目标推送用户对所收看视频的弹幕获取请求；
用户个性标签获取模块，用于获取所述目标推送用户的第一历史记录，并根据所述第一历史记录分析得到目标推送用户的用户个性标签；
作者个性标签获取模块，用于获取所述视频的至少一个弹幕作者的第二历史记录和/或其被其他用户打上的作者标签；以及，根据所述弹幕作者各自的第二历史记录和/或其作者标签，分别分析得到所述弹幕作者各自的作者个性标签；
标签匹配模块，用于将所述目标推送用户的用户个性标签与所述弹幕作者的作者个性标签进行匹配；
弹幕推送模块，用于将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕，优先推送给所述目标推送用户。
本发明另一方面还提供一种弹幕推送装置，包括：处理器、存储器、总线系统，
所述处理器和所述存储器通过所述总线系统相连，
所述存储器用于存储指令，
所述处理器用于执行所述存储器存储的指令，用于：
接收目标推送用户对所收看视频的弹幕获取请求；
获取所述目标推送用户的第一历史记录，并根据所述第一历史记录分析得到目标推送用户的用户个性标签；
获取所述视频的至少一个弹幕作者的第二历史记录和/或其被其他用户打上的作者标签；
根据所述弹幕作者各自的第二历史记录和/或其作者标签，分别分析得到所述弹幕作者各自的作者个性标签；
将所述目标推送用户的用户个性标签与所述弹幕作者的作者个性标签进行匹配；
将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕，优先推送给所述目标推送用户。
本发明另一方面还提供一种计算机可读存储介质，用于存储计算 机可执行指令，当所述指令由一个或多个处理器执行时，用于执行前述的方法。
从上面所述可以看出，本发明实施例提供的弹幕推送方法及装置，能够从目标推送用户的第一历史记录中提取出代表其个人喜好的用户个性标签，将其用户个性标签与弹幕作者的作者个性标签进行匹配，将匹配成功的弹幕作者所做的弹幕优先推送给目标推送用户，从而使其看到或听到其更有可能感兴趣的弹幕，而不仅仅是向目标推送用户泛泛播放弹幕，从而提高了弹幕播放的针对性，提升了用户体验。
【附图说明】
图1为本发明实施例提供的弹幕推送方法的一个实施例的流程示意图；
图2为本发明实施例提供的弹幕推送方法的另一个实施例的流程示意图；
图3为本发明实施例提供的弹幕推送装置实施例的模块结构示意图；
图4所示，为本发明实施例提供的弹幕推送装置4实施例的结构示意框图。
【具体实施方式】
为使本发明的目的、技术方案和优点更加清楚明白，以下结合具体实施例，并参照附图，对本发明进一步详细说明。
需要说明的是，本发明实施例中所有使用“第一”和“第二”的表述均是为了区分两个相同名称非相同的实体或者非相同的参量，可见“第一”“第二”仅为了表述的方便，不应理解为对本发明实施例的限定， 后续实施例对此不再一一说明。
本发明实施例的第一个方面，提供了一种能够向目标用户优先推送其感兴趣的弹幕的弹幕推送方法。如图1所示，为本发明提供的弹幕推送方法的一个实施例的流程示意图。
所述弹幕推送方法，应用于服务器，包括以下步骤：
步骤101：接收目标推送用户对所收看视频的弹幕获取请求；通常情况下，所述弹幕获取请求是在用户打开所述视频的播放界面时，用户的终端自动向服务器发出的，用于请求服务器向其推送与所述视频相关的弹幕(包括文字弹幕和音频弹幕)；但是，也不排除该弹幕获取请求是用户自己手动发出的，例如点击获取弹幕的按钮才发出弹幕获取请求；
步骤102：获取所述目标推送用户的第一历史记录，并根据所述第一历史记录分析得到目标推送用户的用户个性标签；所述第一历史记录可包括有关于所述目标推送用户的任意的历史操作记录，例如历史观看记录、创建的专辑等等；所述用户个性标签为从所述第一历史记录中能够分析得到的、可以代表所述目标推送用户个性与喜好的标签，通常情况下，所述用户个性标签中的标签数量为至少两个；
步骤103：获取所述视频的至少一个弹幕作者的第二历史记录和/或其被其他用户打上的作者标签；同样的，所述第二历史记录可包括有关于所述弹幕作者的任意的历史操作记录，例如历史观看记录、创建的专辑等等；
步骤104：根据所述弹幕作者各自的第二历史记录和/或其作者标签，分别分析得到所述弹幕作者各自的作者个性标签；所述作者个性标签为从所述第二历史记录中能够分析得到的、可以代表所述弹幕作者的个性与喜好的标签，通常情况下，所述作者个性标签中的标签 数量为至少两个；
步骤105：按照预设的匹配规则，将所述目标推送用户的用户个性标签与所述弹幕作者的作者个性标签进行匹配；
步骤106：将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕，优先推送给所述目标推送用户。
从上述实施例可以看出，本发明实施例提供的弹幕推送方法，能够从目标推送用户的第一历史记录中提取出代表其个人喜好的用户个性标签，将其用户个性标签与弹幕作者的作者个性标签进行匹配，将匹配成功的弹幕作者所做的弹幕优先推送给目标推送用户，从而使其看到或听到其更有可能感兴趣的弹幕，而不仅仅是向目标推送用户泛泛播放弹幕，从而提高了弹幕播放的针对性，提升了用户体验。
进一步的，在一些可选实施方式中，所述第一历史记录包括所述目标推送用户的第一历史观看记录和第一观看互动记录；所述第一历史观看记录包括目标推送用户曾经观看过的视频，包括电影、短片、电视剧、娱乐节目等等，以及，这些视频的观看时间、时长等等；所述第一观看互动记录是指目标推送用户在观看视频或使用视频软件、视频网站的过程中所进行的一些互动操作，例如创建自己感兴趣的专辑、为视频点赞、评论等等；
所述根据所述第一历史记录分析得到目标推送用户的用户个性标签的步骤包括：
从所述第一历史观看记录和第一观看互动记录中，分别分析得到目标推送用户的用户观看记录个性标签和用户互动记录个性标签；所述用户观看记录个性标签是从第一历史观看记录中分析得到的跟用户观看习惯有关的标签，所述用户互动记录个性标签是从第一观看互动记录中分析得到的跟用户的互动习惯有关的标签；
得到包括所述用户观看记录个性标签和用户互动记录个性标签的用户个性标签。
通过上述实施例，使得所述用户个性标签中包含了目标推送用户的观看习惯和互动习惯有关的标签，从而丰富了用户个性标签的内容，能够更加全面地体现目标推送用户的喜好。
在另一些可选实施方式中，所述第二历史记录包括所述弹幕作者的第二历史观看记录和第二观看互动记录；所述第二历史观看记录包括弹幕作者曾经观看过的视频，包括电影、短片、电视剧、娱乐节目等等，以及，这些视频的观看时间、时长等等；所述第二观看互动记录是指弹幕作者在观看视频或使用视频软件、视频网站的过程中所进行的一些互动操作，例如创建自己感兴趣的专辑、为视频点赞、评论等等；
所述根据所述弹幕作者各自的第二历史记录及其作者标签，分别分析得到所述弹幕作者各自的作者个性标签的步骤包括：
从所述第二历史观看记录和第二观看互动记录中，分别分析得到弹幕作者的作者观看记录个性标签和作者互动记录个性标签；所述作者观看记录个性标签是从第二历史观看记录中分析得到的跟弹幕作者观看习惯有关的标签，所述作者互动记录个性标签是从第二观看互动记录中分析得到的跟弹幕作者的互动习惯有关的标签；
得到包括所述作者观看记录个性标签、作者互动记录个性标签和作者标签的作者个性标签。
通过上述实施例，使得所述作者个性标签中包含了弹幕作者的观看习惯、互动习惯有关的以及与作者本身有关的标签，从而丰富了作者个性标签的内容，能够更加全面地体现弹幕作者的喜好。
较佳的，在一些可选实施方式中，所述目标推送用户的第一历史 观看记录包括所述目标推送用户观看过的视频；所述第一观看互动记录包括所述目标推送用户创建的专辑、发表过的评论和赞过的用户；
所述根据所述第一历史记录分析得到目标推送用户的用户个性标签的步骤具体还可包括以下步骤：
获取所述目标推送用户观看过的视频的视频标签，从所述视频标签中提取出出现频率高于第一预设频率的视频标签作为用户个性视频标签；
这里，所述观看过的视频可以是在预设期间内被观看过的视频，例如30天内观看过的视频，为了准确性，可以选择更长时间段内的视频，但可相应地赋予较晚时间的视频以大的权重，赋予较早时间的视频以小的权重，以凸显目标推送用户现阶段的兴趣点；所述视频标签包括所述目标推送用户为其打上的标签和其他用户为其打上的标签，即所有用户打上的标签，还可包括服务提供商预先给视频所打上的类型标签，例如宫斗类、科幻类、搞笑类等；所述第一预设频率可以是预先设定的，也可以是用户自定义的，例如30天内出现5次；
根据所述目标推送用户所创建的专辑，提取出专辑标签作为用户个性专辑标签；
这里的专辑是指用户根据自己感兴趣的类型而自行创建的专辑，例如美式喜剧、韩式肥皂剧，等等，由于用户自行创建的专辑更能体现用户的兴趣点所在，因此可以令目标推送用户所创建的专辑的标签作为目标推送用户的账号的个性化的标准，例如提高用户个性专辑标签所占权重；此外，根据专辑创建日期的早晚以及更新日期的早晚，也可以相应地作为赋予相应用户个性专辑标签以不同权重的标准；
获取所述目标推送用户发表过的评论，从所述评论中提取出出现频率高于第二预设频率的评论标签作为用户个性评论标签；
这里，所述发表过的评论可以是在预设期间内发表的评论，例如30天内发表的评论，为了准确性，可以选择更长时间段内的评论，但可相应地赋予较晚时间的评论以大的权重，赋予较早时间的评论以小的权重，以凸显目标推送用户现阶段的兴趣点；所述第二预设频率可以是预先设定的，也可以是用户自定义的，例如30天内出现2次；
获取所述目标推送用户赞过的用户的用户标签，将其作为用户个性赞赏标签；
这里，被目标推送用户赞过的用户是有自我性格的标签的，来源于其发表的内容类型，同样的可以包括看过的视频、创建的专辑、发表过的评论，也可以是包括目标推送用户在内的其他用户为其打的标签或该用户本身为自己所打的标签；
得到包括所述用户个性视频标签、用户个性专辑标签、用户个性评论标签和用户个性赞赏标签的用户个性标签。
通过上述实施例，使得所述用户个性标签中包含了更加能够体现目标推送用户喜好的具体的标签，从而丰富了用户个性标签的内容，能够更加全面地体现目标推送用户的喜好。
在另一些可选实施方式中，所述弹幕作者的第二观看历史记录包括所述弹幕作者观看过的视频，所述第二观看互动记录包括所述弹幕作者创建的专辑、发表过的评论和赞过的用户；所述被其他用户打上的作者标签包括个性标签和作品标签，所述个性标签为所述弹幕作者自己的标签，所述作品标签为所述弹幕作者的作品的标签，所述个性标签和作品标签都可以是弹幕作者本人给自己打的标签或其他用户给弹幕作者打的标签；
所述根据所述弹幕作者各自的第二历史记录及其作者标签，分别分析得到所述弹幕作者各自的作者个性标签的步骤还可包括以下步 骤：
获取所述弹幕作者观看过的视频的视频标签，从所述视频标签中提取出出现频率高于第三预设频率的视频标签作为作者个性视频标签；
这里，所述观看过的视频可以是在预设期间内被观看过的视频，例如30天内观看过的视频，为了准确性，可以选择更长时间段内的视频，但可相应地赋予较晚时间的视频以大的权重，赋予较早时间的视频以小的权重，以凸显弹幕作者现阶段的兴趣点；所述视频标签包括所述弹幕作者为其打上的标签和其他用户为其打上的标签，即所有用户打上的标签，还可包括服务提供商预先给视频所打上的类型标签，例如宫斗类、科幻类、搞笑类等；所述第三预设频率可以是预先设定的，也可以是弹幕作者自定义的，例如30天内出现5次，根据需要，其可以与第一预设频率相等也可以不等；
根据所述弹幕作者创建的专辑，提取出专辑标签作为作者个性专辑标签；
这里的专辑是指弹幕作者根据自己感兴趣的类型而自行创建的专辑，例如美式喜剧、韩式肥皂剧，等等，由于弹幕作者自行创建的专辑更能体现弹幕作者的兴趣点所在，因此可以令弹幕作者所创建的专辑的标签作为弹幕作者的账号的个性化的标准，例如提高作者个性专辑标签所占权重；此外，根据专辑创建日期的早晚以及更新日期的早晚，也可以相应地作为赋予相应作者个性专辑标签以不同权重的标准；
获取所述弹幕作者发表过的评论，从所述评论中提取出出现频率高于第四预设频率的评论标签作为作者个性评论标签；
这里，所述发表过的评论可以是在预设期间内发表的评论，例如 30天内发表的评论，为了准确性，可以选择更长时间段内的评论，但可相应地赋予较晚时间的评论以大的权重，赋予较早时间的评论以小的权重，以凸显弹幕作者现阶段的兴趣点；所述第二预设频率可以是预先设定的，也可以是弹幕作者自定义的，例如30天内出现2次，根据需要，其可以与第二预设频率相等也可以不等；
获取所述弹幕作者赞过的用户的用户标签，将其作为作者个性赞赏标签；
这里，同样的，被弹幕作者赞过的用户是有自我性格的标签的，来源于其发表的内容类型，同样的可以包括看过的视频、创建的专辑、发表过的评论，也可以是包括弹幕作者在内的其他用户为其打的标签或该用户本身为自己所打的标签；
得到包括所述作者个性视频标签、作者个性专辑标签、作者个性评论标签、作者个性赞赏标签、个性标签和作品标签的作者个性标签。
此外，当所述弹幕作者为名人、明星时，其所做的弹幕通常是运营商邀请其所作，因此，这种类型的弹幕作者的所述作者个性标签中还包括所述运营商为其预设的作者标签，例如相声演员可能被赋予“传统中式幽默”“相声”等标签，而年轻男演员则可能被赋予“青春”“前卫”等标签。
通过上述实施例，使得所述作者个性标签中包含了更加能够体现弹幕作者喜好的具体的标签，从而丰富了作者个性标签的内容，能够更加全面地体现弹幕作者的喜好。
进一步的，在一些可选实施方式中，所述将所述目标推送用户的用户个性标签与所述弹幕作者的作者个性标签进行匹配的步骤包括：
将所述目标推送用户的用户个性标签与所述弹幕作者的作者个性标签进行一一对比；
当所述弹幕作者的作者个性标签与所述目标推送用户的用户个性标签的相同数量大于等于预设数量阈值时，则判定所述弹幕作者的作者个性标签与所述目标推送用户的用户个性标签相匹配；所述预设数量阈值可以是两个或以上，当然也可以根据需要进行预先设定或用户自定义设定。
在另一些可选实施方式中，所述将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕，优先推送给所述目标推送用户的步骤包括：
根据与所述目标推送用户的用户个性标签匹配数量的多少，依照数量从多到少的顺序，将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕进行排序；
将排序完成的弹幕依次推送给所述目标推送用户。
例如，匹配成功的弹幕作者A、B、C与目标推送用户的相同个性标签数量分别为5、4、3个，此时，则先推送弹幕作者A所作的弹幕，再推送弹幕作者B所作的弹幕，最后推送弹幕作者C所作的弹幕，但三者的弹幕在相近或相同时间点出现时，则按照A到B再到C的顺序依次推送弹幕，这样，使得弹幕推送更有针对性。
此外，还可以根据用户个性标签的权重大小，将所有用户个性标签进行排序，然后再根据作者个性标签与用户个性标签相同的标签作为用户个性标签时所占权重进行排序，将排名靠前的优先推送给目标推送用户。
例如，用户个性标签包括a、b、c，权重分别是0.5、0.3、0.2，而弹幕作者A的作者个性标签为a、d，弹幕作者B的作者个性标签为b、e，弹幕作者C的作者个性标签为c、f，假设预设数量阈值为1，则弹幕作者A、B、C与目标推送用户均匹配成功，按照相同标签的 权重，分别是A→a→0.5，B→b→0.3，C→c→0.2，因此，推送时则按照A到B再到C的顺序依次向目标推送用户推送弹幕；这样，能够进一步提高弹幕推送的针对性。
较佳的，在一些可选实施方式中，当所述弹幕作者为所述视频所作的弹幕为文字弹幕时，所述将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕，优先推送给所述目标推送用户的步骤还包括：
将匹配成功的弹幕作者为所述视频所作的文字弹幕的文字内容与所述视频的标签进行匹配；
将匹配成功的文字内容所对应的文字弹幕优先推送给所述目标推送用户。
通过上述实施例，使得更加贴近视频主题的文字弹幕得以优先推送，减少了灌水内容。
在另一些可选实施方式中，当所述弹幕作者为所述视频所作的弹幕为音频弹幕时，所述将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕，优先推送给所述目标推送用户的步骤还包括：
将匹配成功的弹幕作者为所述视频所作的音频弹幕的音频内容转换为文字内容；
将转换得到的文字内容与所述视频的标签进行匹配；
将匹配成功的文字内容所对应的音频弹幕优先推送给所述目标推送用户。
通过上述实施例，使得更加贴近视频主题的音频弹幕得以优先推送，减少了灌水内容。
本发明实施例还提供了所述弹幕推送方法的另一个实施例。如图2所示，为本发明提供的弹幕推送方法的另一个实施例的流程示意图。
所述弹幕推送方法，包括以下步骤：
步骤201：接收目标推送用户的对所收看视频的弹幕获取请求；
步骤202：获取所述目标推送用户观看过的视频的视频标签，从所述视频标签中提取出出现频率高于第一预设频率的视频标签作为用户个性视频标签；
步骤203：根据所述目标推送用户创建的专辑，提取出专辑标签作为用户个性专辑标签；
步骤204：获取所述目标推送用户发表过的评论，从所述评论中提取出出现频率高于第二预设频率的评论标签作为用户个性评论标签；
步骤205：获取所述目标推送用户赞过的用户的用户标签，将其作为用户个性赞赏标签；
步骤206：得到包括所述用户个性视频标签、用户个性专辑标签、用户个性评论标签和用户个性赞赏标签的用户个性标签；
步骤207：获取所述弹幕作者观看过的视频的视频标签，从所述视频标签中提取出出现频率高于第三预设频率的视频标签作为作者个性视频标签；
步骤208：根据所述弹幕作者创建的专辑，提取出专辑标签作为作者个性专辑标签；
步骤209：获取所述弹幕作者发表过的评论，从所述评论中提取出出现频率高于第四预设频率的评论标签作为作者个性评论标签；
步骤210：获取所述弹幕作者赞过的用户的用户标签，将其作为作者个性赞赏标签；
步骤211：得到包括所述作者个性视频标签、作者个性专辑标签、作者个性评论标签、作者个性赞赏标签、个性标签和作品标签的作者 个性标签。
步骤212：将所述目标推送用户的用户个性标签与所述弹幕作者的作者个性标签进行一一对比；
步骤213：当所述弹幕作者的作者个性标签与所述目标推送用户的用户个性标签的相同数量大于等于预设数量阈值时，则判定所述弹幕作者的作者个性标签与所述目标推送用户的用户个性标签相匹配；
步骤214：根据与所述目标推送用户的用户个性标签匹配数量的多少，依照数量从多到少的顺序，将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕进行排序；
步骤215：判定弹幕类型；
步骤216：当所述弹幕作者为所述视频所作的弹幕为文字弹幕时，将排序完成的弹幕作者为所述视频所作的文字弹幕的文字内容与所述视频的标签进行匹配；
步骤217：将匹配成功的文字内容所对应的文字弹幕优先推送给所述目标推送用户；
步骤218：当所述弹幕作者为所述视频所作的弹幕为音频弹幕时，将排序完成的的弹幕作者为所述视频所作的音频弹幕的音频内容转换为文字内容；
步骤219：将转换得到的文字内容与所述视频的标签进行匹配；
步骤220：将匹配成功的文字内容所对应的音频弹幕优先推送给所述目标推送用户。
从上述实施例可以看出，本发明实施例提供的弹幕推送方法，能够从目标推送用户的第一历史记录中提取出代表其个人喜好的用户个性标签，将其用户个性标签与弹幕作者的作者个性标签进行匹配，将匹配成功的弹幕作者所做的弹幕优先推送给目标推送用户，从而使 其看到或听到其更有可能感兴趣的弹幕，而不仅仅是向目标推送用户泛泛播放弹幕，从而提高了弹幕播放的针对性，提升了用户体验。
本发明实施例的第二个方面，提供了一种能够向目标用户优先推送其感兴趣的弹幕的弹幕推送装置。如图3所示，为本发明提供的弹幕推送装置实施例的模块结构示意图。
所述弹幕推送装置3，包括：
弹幕获取请求接收模块301，用于接收目标推送用户的对所收看视频的弹幕获取请求；通常情况下，所述弹幕获取请求是在用户打开所述视频的播放界面时，用户的终端自动向服务器发出的，用于请求服务器向其推送与所述视频相关的弹幕(包括文字弹幕和音频弹幕)；但是，也不排除该弹幕获取请求是用户自己手动发出的，例如点击获取弹幕的按钮才发出弹幕获取请求；
用户个性标签获取模块302，用于获取所述目标推送用户的第一历史记录，并根据所述第一历史记录分析得到目标推送用户的用户个性标签；所述第一历史记录可包括有关于所述目标推送用户的任意的历史操作记录，例如历史观看记录、创建的专辑等等；所述用户个性标签为从所述第一历史记录中能够分析得到的、可以代表所述目标推送用户个性与喜好的标签，通常情况下，所述用户个性标签中的标签数量为至少两个；
作者个性标签获取模块303，用于获取所述视频的至少一个弹幕作者的第二历史记录和/或其被其他用户打上的作者标签；以及，根据所述弹幕作者各自的第二历史记录和/或其作者标签，分别分析得到所述弹幕作者各自的作者个性标签；同样的，所述第二历史记录可包括有关于所述弹幕作者的任意的历史操作记录，例如历史观看记录、 创建的专辑等等；所述作者个性标签为从所述第二历史记录中能够分析得到的、可以代表所述弹幕作者的个性与喜好的标签，通常情况下，所述作者个性标签中的标签数量为至少两个；
标签匹配模块304，用于将所述目标推送用户的用户个性标签与所述弹幕作者的作者个性标签进行匹配；
弹幕推送模块305，用于将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕，优先推送给所述目标推送用户。
从上述实施例可以看出，本发明实施例提供的弹幕推送装置，能够从目标推送用户的第一历史记录中提取出代表其个人喜好的用户个性标签，将其用户个性标签与弹幕作者的作者个性标签进行匹配，将匹配成功的弹幕作者所做的弹幕优先推送给目标推送用户，从而使其看到或听到其更有可能感兴趣的弹幕，而不仅仅是向目标推送用户泛泛播放弹幕，从而提高了弹幕播放的针对性，提升了用户体验。
进一步的，在一些可选实施方式中，所述第一历史记录包括所述目标推送用户的第一历史观看记录和第一观看互动记录；所述第一历史观看记录包括目标推送用户曾经观看过的视频，包括电影、短片、电视剧、娱乐节目等等，以及，这些视频的观看时间、时长等等；所述第一观看互动记录是指目标推送用户在观看视频或使用视频软件、视频网站的过程中所进行的一些互动操作，例如创建自己感兴趣的专辑、为视频点赞、评论等等；
所述用户个性标签获取模块302，具体用于：
从所述第一历史观看记录和第一观看互动记录中，分别分析得到目标推送用户的用户观看记录个性标签和用户互动记录个性标签；所述用户观看记录个性标签是从第一历史观看记录中分析得到的跟用户观看习惯有关的标签，所述用户互动记录个性标签是从第一观看互 动记录中分析得到的跟用户的互动习惯有关的标签；
得到包括所述用户观看记录个性标签和用户互动记录个性标签的用户个性标签。
通过上述实施例，使得所述用户个性标签中包含了目标推送用户的观看习惯和互动习惯有关的标签，从而丰富了用户个性标签的内容，能够更加全面地体现目标推送用户的喜好。
在另一些可选实施方式中，所述第二历史记录包括所述弹幕作者的第二历史观看记录和第二观看互动记录；所述第二历史观看记录包括弹幕作者曾经观看过的视频，包括电影、短片、电视剧、娱乐节目等等，以及，这些视频的观看时间、时长等等；所述第二观看互动记录是指弹幕作者在观看视频或使用视频软件、视频网站的过程中所进行的一些互动操作，例如创建自己感兴趣的专辑、为视频点赞、评论等等；
所述作者个性标签获取模块303，具体用于：
从所述第二历史观看记录和第二观看互动记录中，分别分析得到弹幕作者的作者观看记录个性标签和作者互动记录个性标签；所述作者观看记录个性标签是从第二历史观看记录中分析得到的跟弹幕作者观看习惯有关的标签，所述作者互动记录个性标签是从第二观看互动记录中分析得到的跟弹幕作者的互动习惯有关的标签；
得到包括所述作者观看记录个性标签、作者互动记录个性标签和作者标签的用户个性标签。
通过上述实施例，使得所述作者个性标签中包含了弹幕作者的观看习惯、互动习惯有关的以及与作者本身有关的标签，从而丰富了作者个性标签的内容，能够更加全面地体现弹幕作者的喜好。
较佳的，在一些可选实施方式中，所述目标推送用户的第一历史 观看记录包括所述目标推送用户观看过的视频；所述第一观看互动记录包括所述目标推送用户创建的专辑、发表过的评论和赞过的用户；
所述用户个性标签获取模块302，具体用于：
获取所述目标推送用户观看过的视频的视频标签，从所述视频标签中提取出出现频率高于第一预设频率的视频标签作为用户个性视频标签；
这里，所述观看过的视频可以是在预设期间内被观看过的视频，例如30天内观看过的视频，为了准确性，可以选择更长时间段内的视频，但可相应地赋予较晚时间的视频以大的权重，赋予较早时间的视频以小的权重，以凸显目标推送用户现阶段的兴趣点；所述视频标签包括所述目标推送用户为其打上的标签和其他用户为其打上的标签，即所有用户打上的标签，还可包括服务提供商预先给视频所打上的类型标签，例如宫斗类、科幻类、搞笑类等；所述第一预设频率可以是预先设定的，也可以是用户自定义的，例如30天内出现5次；
根据所述目标推送用户创建的专辑，提取出专辑标签作为用户个性专辑标签；
这里的专辑是指用户根据自己感兴趣的类型而自行创建的专辑，例如美式喜剧、韩式肥皂剧，等等，由于用户自行创建的专辑更能体现用户的兴趣点所在，因此可以令目标推送用户所创建的专辑的标签作为目标推送用户的账号的个性化的标准，例如提高用户个性专辑标签所占权重；此外，根据专辑创建日期的早晚以及更新日期的早晚，也可以相应地作为赋予相应用户个性专辑标签以不同权重的标准；
获取所述目标推送用户发表过的评论，从所述评论中提取出出现频率高于第二预设频率的评论标签作为用户个性评论标签；
这里，所述发表过的评论可以是在预设期间内发表的评论，例如 30天内发表的评论，为了准确性，可以选择更长时间段内的评论，但可相应地赋予较晚时间的评论以大的权重，赋予较早时间的评论以小的权重，以凸显目标推送用户现阶段的兴趣点；所述第二预设频率可以是预先设定的，也可以是用户自定义的，例如30天内出现2次；
获取所述目标推送用户赞过的用户的用户标签，将其作为用户个性赞赏标签；
这里，被目标推送用户赞过的用户是有自我性格的标签的，来源于其发表的内容类型，同样的可以包括看过的视频、创建的专辑、发表过的评论，也可以是包括目标推送用户在内的其他用户为其打的标签或该用户本身为自己所打的标签；
得到包括所述用户个性视频标签、用户个性专辑标签、用户个性评论标签和用户个性赞赏标签的用户个性标签。
通过上述实施例，使得所述用户个性标签中包含了更加能够体现目标推送用户喜好的具体的标签，从而丰富了用户个性标签的内容，能够更加全面地体现目标推送用户的喜好。
在另一些可选实施方式中，所述弹幕作者的第二观看历史记录包括所述弹幕作者观看过的视频，所述第二观看互动记录包括所述弹幕作者创建的专辑、发表过的评论和赞过的用户；所述被其他用户打上的作者标签包括个性标签和作品标签，所述个性标签为所述弹幕作者自己的标签，所述作品标签为所述弹幕作者的作品的标签，所述个性标签和作品标签都可以是弹幕作者本人给自己打的标签或其他用户给弹幕作者打的标签；
所述作者个性标签获取模块303，具体用于：
获取所述弹幕作者观看过的视频的视频标签，从所述视频标签中提取出出现频率高于第三预设频率的视频标签作为作者个性视频标 签；
这里，所述观看过的视频可以是在预设期间内被观看过的视频，例如30天内观看过的视频，为了准确性，可以选择更长时间段内的视频，但可相应地赋予较晚时间的视频以大的权重，赋予较早时间的视频以小的权重，以凸显弹幕作者现阶段的兴趣点；所述视频标签包括所述弹幕作者为其打上的标签和其他用户为其打上的标签，即所有用户打上的标签，还可包括服务提供商预先给视频所打上的类型标签，例如宫斗类、科幻类、搞笑类等；所述第三预设频率可以是预先设定的，也可以是弹幕作者自定义的，例如30天内出现5次，根据需要，其可以与第一预设频率相等也可以不等；
根据所述弹幕作者创建的专辑，提取出专辑标签作为作者个性专辑标签；
这里的专辑是指弹幕作者根据自己感兴趣的类型而自行创建的专辑，例如美式喜剧、韩式肥皂剧，等等，由于弹幕作者自行创建的专辑更能体现弹幕作者的兴趣点所在，因此可以令弹幕作者所创建的专辑的标签作为弹幕作者的账号的个性化的标准，例如提高作者个性专辑标签所占权重；此外，根据专辑创建日期的早晚以及更新日期的早晚，也可以相应地作为赋予相应作者个性专辑标签以不同权重的标准；
获取所述弹幕作者发表过的评论，从所述评论中提取出出现频率高于第四预设频率的评论标签作为作者个性评论标签；
这里，所述发表过的评论可以是在预设期间内发表的评论，例如30天内发表的评论，为了准确性，可以选择更长时间段内的评论，但可相应地赋予较晚时间的评论以大的权重，赋予较早时间的评论以小的权重，以凸显弹幕作者现阶段的兴趣点；所述第二预设频率可以 是预先设定的，也可以是弹幕作者自定义的，例如30天内出现2次，根据需要，其可以与第二预设频率相等也可以不等；
获取所述弹幕作者赞过的用户的用户标签，将其作为作者个性赞赏标签；
这里，同样的，被弹幕作者赞过的用户是有自我性格的标签的，来源于其发表的内容类型，同样的可以包括看过的视频、创建的专辑、发表过的评论，也可以是包括弹幕作者在内的其他用户为其打的标签或该用户本身为自己所打的标签；
得到包括所述作者个性视频标签、作者个性专辑标签、作者个性评论标签、作者个性赞赏标签、个性标签和作品标签的作者个性标签。
此外，当所述弹幕作者为名人、明星时，其所做的弹幕通常是运营商邀请其所作，因此，这种类型的弹幕作者的所述作者个性标签中还包括所述运营商为其预设的作者标签，例如相声演员可能被赋予“传统中式幽默”“相声”等标签，而年轻男演员则可能被赋予“青春”“前卫”等标签。
通过上述实施例，使得所述作者个性标签中包含了更加能够体现弹幕作者喜好的具体的标签，从而丰富了作者个性标签的内容，能够更加全面地体现弹幕作者的喜好。
进一步的，在一些可选实施方式中，所述标签匹配模块304，具体用于：
将所述目标推送用户的用户个性标签与所述弹幕作者的作者个性标签进行一一对比；
当所述弹幕作者的作者个性标签与所述目标推送用户的用户个性标签的相同数量大于等于预设数量阈值时，则判定所述弹幕作者的作者个性标签与所述目标推送用户的用户个性标签相匹配；所述预设 数量阈值可以是两个或以上，当然也可以根据需要进行预先设定或用户自定义设定。
在另一些可选实施方式中，所述弹幕推送模块305，具体用于：
根据与所述目标推送用户的用户个性标签匹配数量的多少，依照数量从多到少的顺序，将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕进行排序；
将排序完成的弹幕依次推送给所述目标推送用户。
例如，匹配成功的弹幕作者A、B、C与目标推送用户的相同个性标签数量分别为5、4、3个，此时，则先推送弹幕作者A所作的弹幕，再推送弹幕作者B所作的弹幕，最后推送弹幕作者C所作的弹幕，但三者的弹幕在相近或相同时间点出现时，则按照A到B再到C的顺序依次推送弹幕，这样，使得弹幕推送更有针对性。
此外，还可以根据用户个性标签的权重大小，将所有用户个性标签进行排序，然后再根据作者个性标签与用户个性标签相同的标签作为用户个性标签时所占权重进行排序，将排名靠前的优先推送给目标推送用户。
例如，用户个性标签包括a、b、c，权重分别是0.5、0.3、0.2，而弹幕作者A的作者个性标签为a、d，弹幕作者B的作者个性标签为b、e，弹幕作者C的作者个性标签为c、f，假设预设数量阈值为1，则弹幕作者A、B、C与目标推送用户均匹配成功，按照相同标签的权重，分别是A→a→0.5，B→b→0.3，C→c→0.2，因此，推送时则按照A到B再到C的顺序依次向目标推送用户推送弹幕；这样，能够进一步提高弹幕推送的针对性。
较佳的，在一些可选实施方式中，当所述弹幕作者为所述视频所作的弹幕为文字弹幕时，所述弹幕推送模块305，具体用于：
将匹配成功的弹幕作者为所述视频所作的文字弹幕的文字内容与所述视频的标签进行匹配；
将匹配成功的文字内容所对应的文字弹幕优先推送给所述目标推送用户；
通过上述实施例，使得更加贴近视频主题的文字弹幕得以优先推送，减少了灌水内容。
在另一些可选实施方式中，当所述弹幕作者为所述视频所作的弹幕为音频弹幕时，所述弹幕推送模块305，具体用于：
将匹配成功的弹幕作者为所述视频所作的音频弹幕的音频内容转换为文字内容；
将转换得到的文字内容与所述视频的标签进行匹配；
将匹配成功的文字内容所对应的音频弹幕优先推送给所述目标推送用户。
通过上述实施例，使得更加贴近视频主题的音频弹幕得以优先推送，减少了灌水内容。
如图4所示，为本发明实施例提供的弹幕推送装置4实施例的结构示意框图,如图4所示，所述弹幕推送装置4包括：处理器41、存储器42、总线系统43。其中，处理器41和存储器42通过总线系统43相连，该存储器42用于存储指令，该处理器41用于执行该存储器42存储的指令，用于：
接收目标推送用户对所收看视频的弹幕获取请求；
获取所述目标推送用户的第一历史记录，并根据所述第一历史记录分析得到目标推送用户的用户个性标签；
获取所述视频的至少一个弹幕作者的第二历史记录和/或其被其他用户打上的作者标签；
根据所述弹幕作者各自的第二历史记录和/或其作者标签，分别分析得到所述弹幕作者各自的作者个性标签；
将所述目标推送用户的用户个性标签与所述弹幕作者的作者个性标签进行匹配；
将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕，优先推送给所述目标推送用户。
在本申请实施例中，弹幕推送装置4的存储器42可以是非易失性计算机可读存储介质，以用于存储计算机可执行指令，该指令当由一个或多个处理器执行时，可以使得处理器执行以上方法实施例的步骤，比如，如图1描述的步骤101至106,或者如图2描述的步骤201至220，或者，可以使得处理器执行以上装置实施例各模块的功能，比如，如图3所示模块301至306的功能，计算机可执行指令也可以在任何非易失性计算机可读存储介质内存储和/或传输，以便由指令执行系统、装置或设备使用，或者结合指令执行系统、装置或设备使用，其中该指令执行系统、装置或设备诸如基于计算机的系统、包含处理器的系统或可以从指令执行系统、装置或设备获取指令并执行该指令的其他系统。出于本文档的目的，“非易失性计算机可读存储介质”可以是有形地包含或存储计算机可执行指令的任何介质，该计算机可执行指令可以用于由指令执行系统、设备或系统使用或者结合指令执行系统、装置或设备使用。非易失性计算机可读存储介质可以包括但不限于磁的、光的和/或半导体存储装置。这些存储装置的示例包括磁盘、基于CD、DVD或蓝光技术的光盘以及持久性固态存储器(诸如，闪存、固态驱动器等)。
应当理解，在本申请实施例中，该处理器41可以是中央处理单元(Centrral Processing Unit，简称为“CPU”)。该处理器41还可以是其 他通用处理器、数字信号处理器(DSP)、专用集成电路(ASIC)、现成可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
该总线系统43除包括数据总线之外，还可以包括电源总线、控制总线和状态信号总线等。但是为了清楚说明起见，在图中将各种总线都标为总线系统43。
在本申请实施例中，弹幕推送装置不限于图4的部件和配置，还可以包括以多种配置形式的其他或附加部件。
在实现过程中，上述方法的各步骤或装置的各模块可以通过处理器41中的硬件的集成逻辑电路或者软件形式的指令完成。结合本申请实施例所公开的方法的步骤或装置的各模块可以直接体现为硬件处理器执行完成。或者用处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器42，处理器41读取存储器42中的信息，结合其硬件完成上述方法的步骤。为避免重复，这里不再详细描述。
本发明实施例提供的弹幕推送装置，能够从目标推送用户的第一历史记录中提取出代表其个人喜好的用户个性标签，将其用户个性标签与弹幕作者的作者个性标签进行匹配，将匹配成功的弹幕作者所做的弹幕优先推送给目标推送用户，从而使其看到或听到其更有可能感兴趣的弹幕，而不仅仅是向目标推送用户泛泛播放弹幕，从而提高了弹幕播放的针对性，提升了用户体验。所属领域的普通技术人员应当理解：以上任何实施例的讨论仅为示例性的，并非旨在暗示本公开的范围(包括权利要求)被限于这些例子；在本发明的思路下，以上实 施例或者不同实施例中的技术特征之间也可以进行组合，步骤可以以任意顺序实现，并存在如上所述的本发明的不同方面的许多其它变化，为了简明它们没有在细节中提供。
另外，为简化说明和讨论，并且为了不会使本发明难以理解，在所提供的附图中可以示出或可以不示出与集成电路(IC)芯片和其它部件的公知的电源/接地连接。此外，可以以框图的形式示出装置，以便避免使本发明难以理解，并且这也考虑了以下事实，即关于这些框图装置的实施方式的细节是高度取决于将要实施本发明的平台的(即，这些细节应当完全处于本领域技术人员的理解范围内)。在阐述了具体细节(例如，电路)以描述本发明的示例性实施例的情况下，对本领域技术人员来说显而易见的是，可以在没有这些具体细节的情况下或者这些具体细节有变化的情况下实施本发明。因此，这些描述应被认为是说明性的而不是限制性的。
尽管已经结合了本发明的具体实施例对本发明进行了描述，但是根据前面的描述，这些实施例的很多替换、修改和变型对本领域普通技术人员来说将是显而易见的。例如，其它存储器架构(例如，动态RAM(DRAM))可以使用所讨论的实施例。
本发明的实施例旨在涵盖落入所附权利要求的宽泛范围之内的所有这样的替换、修改和变型。因此，凡在本发明的精神和原则之内，所做的任何省略、修改、等同替换、改进等，均应包含在本发明的保护范围之内。

Claims (12)

  1. 一种弹幕推送方法，其特征在于，包括：
    接收目标推送用户对所收看视频的弹幕获取请求；
    获取所述目标推送用户的第一历史记录，并根据所述第一历史记录分析得到目标推送用户的用户个性标签；
    获取所述视频的至少一个弹幕作者的第二历史记录和/或其被其他用户打上的作者标签；
    根据所述弹幕作者各自的第二历史记录和/或其作者标签，分别分析得到所述弹幕作者各自的作者个性标签；
    将所述目标推送用户的用户个性标签与所述弹幕作者的作者个性标签进行匹配；
    将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕，优先推送给所述目标推送用户。
  2. 根据权利要求1所述的方法，其特征在于，所述第一历史记录包括所述目标推送用户的第一历史观看记录和第一观看互动记录；
    所述根据所述第一历史记录分析得到目标推送用户的用户个性标签的步骤包括：
    从所述第一历史观看记录和第一观看互动记录中，分别分析得到目标推送用户的用户观看记录个性标签和用户互动记录个性标签；
    得到包括所述用户观看记录个性标签和用户互动记录个性标签的用户个性标签；
    和/或，
    所述第二历史记录包括所述弹幕作者的第二历史观看记录和第二观看互动记录；
    所述根据所述弹幕作者各自的第二历史记录和/或其作者标签，分别分析得到所述弹幕作者各自的作者个性标签的步骤包括：
    从所述第二历史观看记录和第二观看互动记录中，分别分析得到弹幕作者的作者观看记录个性标签和作者互动记录个性标签；
    得到包括所述作者观看记录个性标签、作者互动记录个性标签和/或作者标签的作者个性标签。
  3. 根据权利要求2所述的方法，其特征在于，所述目标推送用户的第一历史观看记录包括所述目标推送用户观看过的视频；所述第一观看互动记录包括所述目标推送用户创建的专辑、发表过的评论和赞过的用户；
    所述根据所述第一历史记录分析得到目标推送用户的用户个性标签的步骤具体包括：
    获取所述目标推送用户观看过的视频的视频标签，从所述视频标签中提取出出现频率高于第一预设频率的视频标签作为用户个性视频标签；
    根据所述目标推送用户创建的专辑，提取出专辑标签作为用户个性专辑标签；
    获取所述目标推送用户发表过的评论，从所述评论中提取出出现频率高于第二预设频率的评论标签作为用户个性评论标签；
    获取所述目标推送用户赞过的用户的用户标签，将其作为用户个性赞赏标签；
    得到包括所述用户个性视频标签、用户个性专辑标签、用户个性评论标签和用户个性赞赏标签的用户个性标签；
    和/或，
    所述弹幕作者的第二观看历史记录包括所述弹幕作者观看过的 视频，所述第二观看互动记录包括所述弹幕作者创建的专辑、发表过的评论和赞过的用户；所述被其他用户打上的作者标签包括个性标签和作品标签；
    所述根据所述弹幕作者各自的第二历史记录和/或其作者标签，分别分析得到所述弹幕作者各自的作者个性标签的步骤具体包括：
    获取所述弹幕作者观看过的视频的视频标签，从所述视频标签中提取出出现频率高于第三预设频率的视频标签作为作者个性视频标签；
    根据所述弹幕作者创建的专辑，提取出专辑标签作为作者个性专辑标签；
    获取所述弹幕作者发表过的评论，从所述评论中提取出出现频率高于第四预设频率的评论标签作为作者个性评论标签；
    获取所述弹幕作者赞过的用户的用户标签，将其作为作者个性赞赏标签；
    得到包括所述作者个性视频标签、作者个性专辑标签、作者个性评论标签、作者个性赞赏标签、个性标签、作品标签和/或作者标签的作者个性标签。
  4. 根据权利要求1所述的方法，其特征在于，所述将所述目标推送用户的用户个性标签与所述弹幕作者的作者个性标签进行匹配的步骤包括：
    将所述目标推送用户的用户个性标签与所述弹幕作者的作者个性标签进行一一对比；
    当所述弹幕作者的作者个性标签与所述目标推送用户的用户个性标签的相同数量大于或等于预设数量阈值时，则判定所述弹幕作者的作者个性标签与所述目标推送用户的用户个性标签相匹配；
    和/或，
    所述将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕，优先推送给所述目标推送用户的步骤包括：
    根据与所述目标推送用户的用户个性标签匹配数量的多少，依照数量从多到少的顺序，将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕进行排序；
    将排序完成的弹幕依次推送给所述目标推送用户。
  5. 根据权利要求1所述的方法，其特征在于，当所述弹幕作者为所述视频所作的弹幕为文字弹幕时，所述将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕，优先推送给所述目标推送用户的步骤还包括：
    将匹配成功的弹幕作者为所述视频所作的文字弹幕的文字内容与所述视频的标签进行匹配；
    将匹配成功的文字内容所对应的文字弹幕优先推送给所述目标推送用户；
    和/或，
    当所述弹幕作者为所述视频所作的弹幕为音频弹幕时，所述将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕，优先推送给所述目标推送用户的步骤还包括：
    将匹配成功的弹幕作者为所述视频所作的音频弹幕的音频内容转换为文字内容；
    将转换得到的文字内容与所述视频的标签进行匹配；
    将匹配成功的文字内容所对应的音频弹幕优先推送给所述目标推送用户。
  6. 一种弹幕推送装置，其特征在于，包括：
    弹幕获取请求接收模块，用于接收目标推送用户对所收看视频的弹幕获取请求；
    用户个性标签获取模块，用于获取所述目标推送用户的第一历史记录，并根据所述第一历史记录分析得到目标推送用户的用户个性标签；
    作者个性标签获取模块，用于获取所述视频的至少一个弹幕作者的第二历史记录和/或其被其他用户打上的作者标签；以及，根据所述弹幕作者各自的第二历史记录和/或其作者标签，分别分析得到所述弹幕作者各自的作者个性标签；
    标签匹配模块，用于将所述目标推送用户的用户个性标签与所述弹幕作者的作者个性标签进行匹配；
    弹幕推送模块，用于将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕，优先推送给所述目标推送用户。
  7. 根据权利要求6所述的装置，其特征在于，所述第一历史记录包括所述目标推送用户的第一历史观看记录和第一观看互动记录；
    所述用户个性标签获取模块，具体用于：
    从所述第一历史观看记录和第一观看互动记录中，分别分析得到目标推送用户的用户观看记录个性标签和用户互动记录个性标签；
    得到包括所述用户观看记录个性标签和用户互动记录个性标签的用户个性标签；
    和/或，
    所述第二历史记录包括所述弹幕作者的第二历史观看记录和第二观看互动记录；
    所述作者个性标签获取模块，具体用于：
    从所述第二历史观看记录和第二观看互动记录中，分别分析得到弹幕作者的作者观看记录个性标签和作者互动记录个性标签；
    得到包括所述作者观看记录个性标签、作者互动记录个性标签和/或作者标签的作者个性标签。
  8. 根据权利要求7所述的装置，其特征在于，所述目标推送用户的第一历史观看记录包括所述目标推送用户观看过的视频；所述第一观看互动记录包括所述目标推送用户创建的专辑、发表过的评论和赞过的用户；
    所述用户个性标签获取模块，具体用于：
    获取所述目标推送用户观看过的视频的视频标签，从所述视频标签中提取出出现频率高于第一预设频率的视频标签作为用户个性视频标签；
    根据所述目标推送用户创建的专辑，提取出专辑标签作为用户个性专辑标签；
    获取所述目标推送用户发表过的评论，从所述评论中提取出出现频率高于第二预设频率的评论标签作为用户个性评论标签；
    获取所述目标推送用户赞过的用户的用户标签，将其作为用户个性赞赏标签；
    得到包括所述用户个性视频标签、用户个性专辑标签、用户个性评论标签和用户个性赞赏标签的用户个性标签；
    和/或，
    所述弹幕作者的第二观看历史记录包括所述弹幕作者观看过的视频，所述第二观看互动记录包括所述弹幕作者创建的专辑、发表过的评论和赞过的用户；所述被其他用户打上的作者标签包括个性标签和作品标签；
    所述作者个性标签获取模块，具体用于：
    获取所述弹幕作者观看过的视频的视频标签，从所述视频标签中提取出出现频率高于第三预设频率的视频标签作为作者个性视频标签；
    根据所述弹幕作者创建的专辑，提取出专辑标签作为作者个性专辑标签；
    获取所述弹幕作者发表过的评论，从所述评论中提取出出现频率高于第四预设频率的评论标签作为作者个性评论标签；
    获取所述弹幕作者赞过的用户的用户标签，将其作为作者个性赞赏标签；
    得到包括所述作者个性视频标签、作者个性专辑标签、作者个性评论标签、作者个性赞赏标签、个性标签、作品标签和/或作者标签的作者个性标签。
  9. 根据权利要求6所述的装置，其特征在于，所述标签匹配模块，具体用于：
    将所述目标推送用户的用户个性标签与所述弹幕作者的作者个性标签进行一一对比；
    当所述弹幕作者的作者个性标签与所述目标推送用户的用户个性标签的相同数量大于或等于预设数量阈值时，则判定所述弹幕作者的作者个性标签与所述目标推送用户的用户个性标签相匹配；
    和/或，
    所述弹幕推送模块，具体用于：
    根据与所述目标推送用户的用户个性标签匹配数量的多少，依照数量从多到少的顺序，将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕进行排序；
    将排序完成的弹幕依次推送给所述目标推送用户。
  10. 根据权利要求6所述的装置，其特征在于，当所述弹幕作者为所述视频所作的弹幕为文字弹幕时，所述弹幕推送模块，具体用于：
    将匹配成功的弹幕作者为所述视频所作的文字弹幕的文字内容与所述视频的标签进行匹配；
    将匹配成功的文字内容所对应的文字弹幕优先推送给所述目标推送用户；
    和/或，
    当所述弹幕作者为所述视频所作的弹幕为音频弹幕时，所述弹幕推送模块，具体用于：
    将匹配成功的弹幕作者为所述视频所作的音频弹幕的音频内容转换为文字内容；
    将转换得到的文字内容与所述视频的标签进行匹配；
    将匹配成功的文字内容所对应的音频弹幕优先推送给所述目标推送用户。
  11. 一种弹幕推送装置，其特征在于，包括：处理器、存储器、总线系统，
    所述处理器和所述存储器通过所述总线系统相连，
    所述存储器用于存储指令，
    所述处理器用于执行所述存储器存储的指令，用于：
    接收目标推送用户对所收看视频的弹幕获取请求；
    获取所述目标推送用户的第一历史记录，并根据所述第一历史记录分析得到目标推送用户的用户个性标签；
    获取所述视频的至少一个弹幕作者的第二历史记录和/或其被其 他用户打上的作者标签；
    根据所述弹幕作者各自的第二历史记录和/或其作者标签，分别分析得到所述弹幕作者各自的作者个性标签；
    将所述目标推送用户的用户个性标签与所述弹幕作者的作者个性标签进行匹配；
    将匹配成功的作者个性标签对应的弹幕作者为所述视频所作的弹幕，优先推送给所述目标推送用户。
  12. 一种计算机可读存储介质，其特征在于，用于存储计算机可执行指令，当所述指令由一个或多个处理器执行时，用于执行如权利要求1-5中任一项所述的方法。
PCT/CN2016/089346 2016-03-21 2016-07-08 弹幕推送方法及装置 WO2017161776A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US15/246,738 US20170272800A1 (en) 2016-03-21 2016-08-25 Method for bullet screen pushing and electronic device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610162782.8 2016-03-21
CN201610162782.8A CN105872593A (zh) 2016-03-21 2016-03-21 弹幕推送方法及装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/246,738 Continuation US20170272800A1 (en) 2016-03-21 2016-08-25 Method for bullet screen pushing and electronic device

Publications (1)

Publication Number Publication Date
WO2017161776A1 true WO2017161776A1 (zh) 2017-09-28

Family

ID=56625333

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/089346 WO2017161776A1 (zh) 2016-03-21 2016-07-08 弹幕推送方法及装置

Country Status (2)

Country Link
CN (1) CN105872593A (zh)
WO (1) WO2017161776A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111435496A (zh) * 2019-01-14 2020-07-21 上海汽车集团股份有限公司 一种知识及项目管理方法及装置
CN111708901A (zh) * 2020-06-19 2020-09-25 腾讯科技（深圳）有限公司 多媒体资源推荐方法、装置、电子设备及存储介质
CN112672202A (zh) * 2020-12-28 2021-04-16 广州博冠信息科技有限公司 弹幕处理方法、设备和存储介质
CN116992159A (zh) * 2023-09-27 2023-11-03 江西科技学院 一种内容推荐方法与系统

Families Citing this family (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110380954B (zh) * 2017-04-12 2021-01-15 腾讯科技（深圳）有限公司 数据分享方法和装置，存储介质及电子装置
CN107124451B (zh) * 2017-04-18 2020-09-01 腾讯科技（深圳）有限公司 应用资源的获取方法及装置
CN108933964B (zh) * 2017-05-23 2021-07-27 腾讯科技（深圳）有限公司 一种弹幕显示方法、播放设备及控制终端
CN107396144B (zh) * 2017-06-30 2019-08-02 武汉斗鱼网络科技有限公司 一种弹幕分发方法及装置
CN107835439B (zh) * 2017-10-25 2020-08-14 中国移动通信集团公司 一种弹幕推送方法、电子设备以及计算机可读存储介质
CN109729436B (zh) * 2017-10-31 2021-03-16 腾讯科技（深圳）有限公司 广告弹幕处理方法和装置
CN107948761B (zh) 2017-12-12 2021-01-01 上海哔哩哔哩科技有限公司 弹幕播放控制方法、服务器及弹幕播放控制系统
CN109379636B (zh) * 2018-09-20 2022-06-17 京东方科技集团股份有限公司 弹幕处理方法、装置及系统
CN109688479B (zh) * 2018-12-26 2022-03-01 杭州蓦然认知科技有限公司 一种弹幕显示方法、弹幕显示装置和弹幕显示服务器
CN109756759B (zh) * 2018-12-26 2021-01-15 北京蓦然认知科技有限公司 一种弹幕信息推荐方法和装置
CN110113634A (zh) * 2019-03-22 2019-08-09 厦门理工学院 一种信息互动方法、装置、设备及存储介质
CN110084373B (zh) * 2019-04-22 2021-08-24 腾讯科技（深圳）有限公司 信息处理方法、装置、计算机可读存储介质和计算机设备
CN111444687A (zh) * 2020-03-20 2020-07-24 北京达佳互联信息技术有限公司 一种标签生成方法、装置、服务器及存储介质
CN115379267B (zh) * 2021-05-20 2024-05-28 上海哔哩哔哩科技有限公司 弹幕展示方法及装置
CN115379266B (zh) * 2021-05-20 2024-07-30 上海哔哩哔哩科技有限公司 弹幕展示方法及装置
CN113691838A (zh) * 2021-08-24 2021-11-23 北京快乐茄信息技术有限公司 音频弹幕处理方法及装置、电子设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110058101A1 (en) * 2009-09-03 2011-03-10 Fox Broadcasting Company Method and apparatus for concurrent broadcast of media program and social networking derived information exchange
US20130311395A1 (en) * 2012-05-17 2013-11-21 Yahoo! Inc. Method and system for providing personalized reviews to a user
CN104156390A (zh) * 2014-07-07 2014-11-19 乐视网信息技术（北京）股份有限公司 一种评论推荐方法和系统
CN104754420A (zh) * 2015-03-30 2015-07-01 北京奇艺世纪科技有限公司 一种在多媒体文件播放过程中的弹幕交互方法及装置

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7069308B2 (en) * 2003-06-16 2006-06-27 Friendster, Inc. System, method and apparatus for connecting users in an online computer system based on their relationships within social networks
EP2343866B1 (en) * 2010-01-11 2016-03-30 Vodafone Holding GmbH Network-based system for social interactions between users
WO2015036817A1 (en) * 2013-09-15 2015-03-19 Yogesh Chunilal Rathod Structured updated status, requests, user data & programming based presenting & accessing of connections
CN104731950B (zh) * 2015-03-31 2018-09-28 北京奇艺世纪科技有限公司 一种视频推荐方法和装置
CN105095431A (zh) * 2015-07-22 2015-11-25 百度在线网络技术（北京）有限公司 根据用户的行为信息推送视频的方法和装置
CN105138572B (zh) * 2015-07-27 2019-12-10 百度在线网络技术（北京）有限公司 获取用户标签的关联度权值的方法和装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110058101A1 (en) * 2009-09-03 2011-03-10 Fox Broadcasting Company Method and apparatus for concurrent broadcast of media program and social networking derived information exchange
US20130311395A1 (en) * 2012-05-17 2013-11-21 Yahoo! Inc. Method and system for providing personalized reviews to a user
CN104156390A (zh) * 2014-07-07 2014-11-19 乐视网信息技术（北京）股份有限公司 一种评论推荐方法和系统
CN104754420A (zh) * 2015-03-30 2015-07-01 北京奇艺世纪科技有限公司 一种在多媒体文件播放过程中的弹幕交互方法及装置

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111435496A (zh) * 2019-01-14 2020-07-21 上海汽车集团股份有限公司 一种知识及项目管理方法及装置
CN111435496B (zh) * 2019-01-14 2023-10-03 上海汽车集团股份有限公司 一种知识及项目管理方法及装置
CN111708901A (zh) * 2020-06-19 2020-09-25 腾讯科技（深圳）有限公司 多媒体资源推荐方法、装置、电子设备及存储介质
CN111708901B (zh) * 2020-06-19 2023-10-13 腾讯科技（深圳）有限公司 多媒体资源推荐方法、装置、电子设备及存储介质
CN112672202A (zh) * 2020-12-28 2021-04-16 广州博冠信息科技有限公司 弹幕处理方法、设备和存储介质
CN116992159A (zh) * 2023-09-27 2023-11-03 江西科技学院 一种内容推荐方法与系统
CN116992159B (zh) * 2023-09-27 2023-11-28 江西科技学院 一种内容推荐方法与系统

Also Published As

Publication number Publication date
CN105872593A (zh) 2016-08-17

Similar Documents

Publication Publication Date Title
WO2017161776A1 (zh) 弹幕推送方法及装置
US12079226B2 (en) Approximate template matching for natural language queries
US10102284B2 (en) System and method for generating media bookmarks
KR102436734B1 (ko) 비디오 재생 노드 위치 확정 방법, 장치, 전자 장비, 컴퓨터 판독가능 저장 매체 및 컴퓨터 프로그램
US20190138815A1 (en) Method, Apparatus, User Terminal, Electronic Equipment, and Server for Video Recognition
WO2023051102A1 (zh) 视频推荐方法、装置、设备及介质
US20160378762A1 (en) Methods and systems for identifying media assets
US20170272800A1 (en) Method for bullet screen pushing and electronic device
US20150188960A1 (en) System and method for online media content sharing
WO2019134587A1 (zh) 视频数据处理方法、装置、电子设备和存储介质
CN110168541B (zh) 基于静态和时间知识图消除词语歧义的系统和方法
US11700410B2 (en) Crowd sourced indexing and/or searching of content
US9426411B2 (en) Method and apparatus for generating summarized information, and server for the same
US12086503B2 (en) Audio segment recommendation
WO2022000991A1 (zh) 表情包生成方法及设备、电子设备和介质
US20150156227A1 (en) Synchronize Tape Delay and Social Networking Experience
US20150220516A1 (en) Method and system for providing relevant portions of multi-media based on text searching of multi-media
US20200302933A1 (en) Generation of audio stories from text-based media
US11729480B2 (en) Systems and methods to enhance interactive program watching
US11570523B1 (en) Systems and methods to enhance interactive program watching
CN115734045B (zh) 一种视频播放方法、装置、设备及存储介质
JP2018081389A (ja) 分類検索システム

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

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

Ref document number: 16895126

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 16895126

Country of ref document: EP

Kind code of ref document: A1