WO2018171325A1 - 一种视频热点片段提取方法、用户设备和服务器 - Google Patents

一种视频热点片段提取方法、用户设备和服务器 Download PDF

Info

Publication number
WO2018171325A1
WO2018171325A1 PCT/CN2018/073852 CN2018073852W WO2018171325A1 WO 2018171325 A1 WO2018171325 A1 WO 2018171325A1 CN 2018073852 W CN2018073852 W CN 2018073852W WO 2018171325 A1 WO2018171325 A1 WO 2018171325A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
user group
segment
server
hotspot
Prior art date
Application number
PCT/CN2018/073852
Other languages
English (en)
French (fr)
Inventor
周鹏飞
谭银燕
汪芳山
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Priority to US16/495,175 priority Critical patent/US11265624B2/en
Publication of WO2018171325A1 publication Critical patent/WO2018171325A1/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
    • H04N21/25—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
    • 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]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/85—Assembly of content; Generation of multimedia applications
    • H04N21/854—Content authoring
    • H04N21/8549—Creating video summaries, e.g. movie trailer
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/73—Querying
    • G06F16/735—Filtering based on additional data, e.g. user or group profiles
    • 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
    • H04N21/236—Assembling of a multiplex stream, e.g. transport stream, by combining a video stream with other content or additional data, e.g. inserting a URL [Uniform Resource Locator] into a video stream, multiplexing software data into a video stream; Remultiplexing of multiplex streams; Insertion of stuffing bits into the multiplex stream, e.g. to obtain a constant bit-rate; Assembling of a packetised elementary stream
    • H04N21/23614—Multiplexing of additional data and video streams
    • 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
    • H04N21/25—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
    • H04N21/266—Channel or content management, e.g. generation and management of keys and entitlement messages in a conditional access system, merging a VOD unicast channel into a multicast channel
    • H04N21/2668—Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles
    • 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
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/4302—Content synchronisation processes, e.g. decoder synchronisation
    • H04N21/4307—Synchronising the rendering of multiple content streams or additional data on devices, e.g. synchronisation of audio on a mobile phone with the video output on the TV screen
    • H04N21/43074—Synchronising the rendering of multiple content streams or additional data on devices, e.g. synchronisation of audio on a mobile phone with the video output on the TV screen of additional data with content streams on the same device, e.g. of EPG data or interactive icon with a TV program
    • 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
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
    • H04N21/44204—Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched
    • 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
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
    • H04N21/44213—Monitoring of end-user related 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
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
    • H04N21/44213—Monitoring of end-user related data
    • H04N21/44222—Analytics of user selections, e.g. selection of programs or purchase activity
    • 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
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. 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]
    • H04N21/40—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
    • H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
    • H04N21/4755—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for defining user preferences, e.g. favourite actors or genre
    • 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
    • H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
    • H04N21/4756—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for rating content, e.g. scoring a recommended movie
    • 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
    • H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
    • H04N21/4758—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for providing answers, e.g. voting
    • 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
    • H04N21/4882—Data services, e.g. news ticker for displaying messages, e.g. warnings, reminders
    • 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
    • H04N21/4886—Data services, e.g. news ticker for displaying a ticker, e.g. scrolling banner for news, stock exchange, weather 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]
    • H04N21/60—Network structure or processes for video distribution between server and client or between remote clients; Control signalling between clients, server and network components; Transmission of management data between server and client, e.g. sending from server to client commands for recording incoming content stream; Communication details between server and client 
    • H04N21/65—Transmission of management data between client and server
    • H04N21/658—Transmission by the client directed to the server
    • H04N21/6582—Data stored in the client, e.g. viewing habits, hardware capabilities, credit card number
    • 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]
    • H04N21/60—Network structure or processes for video distribution between server and client or between remote clients; Control signalling between clients, server and network components; Transmission of management data between server and client, e.g. sending from server to client commands for recording incoming content stream; Communication details between server and client 
    • H04N21/65—Transmission of management data between client and server
    • H04N21/658—Transmission by the client directed to the server
    • H04N21/6587—Control parameters, e.g. trick play commands, viewpoint selection
    • 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
    • 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
    • H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
    • H04N21/845—Structuring of content, e.g. decomposing content into time segments
    • H04N21/8456—Structuring of content, e.g. decomposing content into time segments by decomposing the content in the time domain, e.g. in time segments

Definitions

  • the present application relates to the field of communications technologies, and in particular, to a video hotspot segment extracting method, user equipment, and server.
  • the hotspot segment can be extracted and identified based on the number of the barrage in the video and the threshold value, and the second is based on the user's operation information on the video player to obtain the user's current The preference of the clip in the video, for example, by the fast forward and rewind operation to determine whether the user likes the clip, thereby extracting and identifying the hot clip.
  • the displayed content of the page where the video is located is the same, that is, the identified hotspot segments are the same.
  • different video groups, clips, or video links that users of different age groups, genders, educational backgrounds, and regions may like to watch may be different, so that different video groups need to access different video hotspots.
  • the above method is more efficient than manual editing of hotspot segments, it cannot extract video hotspot segments that different user groups want to watch for different user groups, so that the accuracy of the user accessing the hotspot segments is low, and the user belongs to certain user groups. Hotspot clips cannot be extracted and rendered to the user.
  • the embodiment of the present invention provides a method for extracting a video hotspot segment, a user equipment, and a server, which can solve the problem that the accuracy of the user accessing the hot spot is low and some hot clips cannot be extracted and presented to the user.
  • a method for extracting a video hotspot segment including: dividing a user into a plurality of user groups according to attribute information of the user, and then operating information according to each user group of the plurality of user groups when viewing the video content, Obtaining a hotspot segment of each user group to watch the video content, and then acquiring a tag corresponding to the hot spot segment of each user group according to the hot spot segment of each user group viewing the video content, and labeling the hot spot segment corresponding to each user group User equipment sent to the appropriate user community.
  • the embodiment of the present application can extract and present personalized hotspot segments according to multiple user groups, which can improve the accuracy of the user accessing the hotspot segments, and simultaneously presents the same hotspot segment to all users in the prior art.
  • Embodiments of the present application can extract and present hidden hotspot segments belonging to certain user groups.
  • the server divides the user into multiple user groups according to the attribute information of the user, including: the server analyzes the attribute information of the user according to the clustering algorithm, so as to divide the user into multiple user groups;
  • the class algorithm analyzes the attribute information of the user to divide the user into multiple user groups, and the method may include: the server constructs the attribute vector of the user according to the attribute information of the user, and obtains the Euclidean distance between the attribute vector of the user and the cluster center, according to the European The distance is divided into clusters where the nearest cluster center of the Euclidean distance is located, and each cluster corresponds to a user group.
  • the user can be divided into a plurality of user groups according to attributes, so as to find a hot spot piece that each user group likes to watch for each user group.
  • the attributes here can be varied, for example, the age, gender, and occupation of the user.
  • the user's operation information is data that the user feeds back to the video content
  • the feedback data may include explicit feedback or implicit feedback of the user on the video content
  • the explicit feedback may be, for example, the user's viewing of the video content.
  • the real-time barrage comment of the video clip, the implicit feedback can be, for example, the user's operation on the video player, whether to drag the progress bar back and forth or click the fast forward and rewind button, and click, browse and collect the online video content, etc.
  • the server can obtain hotspot segments corresponding to each user group for multiple user groups.
  • the server obtains a barrage comment threshold of the hotspot segment of the user group according to the operation information of the user group, and the server obtains the user group to the video content for each user group.
  • the ratio of the number of historical barrage comments to the number of video segments of the video content, and then the product of the ratio and the preset coefficient, the product is the barrage review threshold of the hotspot segment of the user group; the server is based on the barrage review threshold and the
  • the operation information of the user group obtains the hotspot segment of the user group: for each user group, the server determines that the video group has any number of barrage comments on any video segment of the video content that is greater than the barrage comment threshold, and any video segment Identify hotspots for the user community. That is, when the number of barrage comments of a certain video segment for each video segment is greater than the average number of barrows for each video segment of the user segment, the video segment is determined to be a hotspot segment of the user group.
  • the server obtains a label corresponding to a hotspot segment of each user group according to a hotspot segment of each user group viewing the video content: the key of the server constructing the hotspot segment for the hotspot segment of each user group
  • the word vocabulary, the keyword vocabulary includes the keywords of the barrage comment of the hot spot segment, and then the word frequency of each word in the keyword vocabulary is counted, the keyword with the highest word frequency is determined, the keyword with the highest word frequency and the user group are The start and end time of the hot spot comment is determined as the tag of the hot spot.
  • the hotspot segments that are of interest to each user group can be accurately located according to the keywords and the labels of the hotspot segments, so that the hotspot segments between the user groups present personality. It does not make the labels of the same hotspots available to each user group.
  • the server obtains the heat contribution threshold of the hotspot segment of the user group according to the operation information of the user group for each user group. Including: For each user group, the server obtains the duration of each type of operation for each user, including fast forward, fast reverse, forward drag, and backward drag; for each user group The user, the server obtains a heat contribution value of each operation type of the user, and the heat contribution value is a product of a duration of the operation type and a weighted value of the operation type, and a duration of the video segment corresponding to the operation type.
  • the server obtains a heat contribution threshold of the hotspot segment of the user group, and the heat contribution threshold is a ratio of the total heat contribution value of the user group to the number of video segments of the video content, and then the preset coefficient Product; for each user group, the server contributes a threshold based on heat and the user group
  • Obtaining the hotspot segment of the user group includes: for each user group, the server obtains a sum of the heat contribution values of the video segments of the video content of the user group, and the video segment whose sum of the heat contribution values is greater than the heat contribution threshold Identify the hotspots for this user group.
  • each user group is obtained.
  • different hotspot segments can be presented for each user group, which can improve the accuracy of the user accessing the hot spot segment, and extract the hidden hotspot segments belonging to certain user groups.
  • the server obtains, according to the hotspot segment of the video content of each user group, the tags corresponding to the hotspot segments of each user group: for each hotspot segment of the user group, the server groups the user group The earliest time point and the latest time point in each time point of the player operation when the hot spot is played are determined as the tags of the hot spot. Therefore, each user group can quickly locate the hotspot segments of interest to each user group according to the labels of the hotspot segments corresponding to each user group.
  • the method further includes: the server receiving the attribute information of the user sent by the user equipment.
  • the attribute information may be obtained from the registration information of the user in the user equipment or obtained from the registration information of the user in the client, or may be obtained by other means, which is not limited in this application.
  • a method for extracting a video hotspot segment including: the user equipment sends the attribute information of the user to the server; the user equipment receives the label of the hot spot segment of the video content sent by the server, and displays the hot spot according to the label in the display portion of the video content.
  • the label of the clip When viewing the video content, the user also sends the operation information and the service data of the user when viewing the video content to the server.
  • the service data can be expressed in a time series format, and each service data can include a session ID (Session ID) and a user account.
  • a server comprising: a classification unit, configured to divide a user into a plurality of user groups according to attribute information of the user; and an obtaining unit, configured to each user group of the plurality of user groups divided according to the classification unit The operation information when the video content is viewed, the hotspot segment of the video content is obtained by each user group, and the obtaining unit is further configured to acquire the hotspot corresponding to each user group according to the hot spot segment of the video content of each user group acquired by the obtaining unit.
  • a labeling unit configured to send, by the acquiring unit, a label of the hotspot segment corresponding to each user group to the user equipment of the corresponding user group.
  • the classification unit is configured to: analyze the attribute information of the user according to the clustering algorithm to divide the user into multiple user groups; the classification unit is specifically configured to: construct the attribute of the user according to the attribute information of the user. Vector; obtains the Euclidean distance between the attribute vector of the user and the cluster center; divides the user into clusters corresponding to the nearest cluster center of Euclidean distance according to the Euclidean distance, and each cluster corresponds to a user group.
  • the obtaining unit is configured to: for each user group, obtain a barrage comment threshold or a heat contribution threshold of the hotspot segment of the user group according to the operation information of the user group; for each user group, according to The barrage review threshold and the operation information of the user group obtain the hotspot segment of the user group, or obtain the hotspot segment of the user group according to the heat contribution threshold and the operation information of the user group.
  • the obtaining unit is configured to: for each user group, obtain a ratio of the number of historical barrage comments of the user group to the video content and the number of video segments of the video content, and obtain the ratio and the preset.
  • the product of the coefficient, the product is the barrage comment threshold of the hotspot segment of the user group; for each user group, when the user group determines that the number of barrage comments for any video segment of the video content is greater than the barrage comment threshold, A video clip is determined as a hotspot segment of the user community.
  • the acquisition unit is configured to: for each user group, obtain the duration of each operation type of each user, the operation types include fast forward, fast reverse, forward drag, and backward drag
  • the operation types include fast forward, fast reverse, forward drag, and backward drag
  • For each user in each user group obtain the heat contribution value of each operation type of the user, and the heat contribution value is the product of the duration of the operation type and the weighted value of the operation type, and then The ratio of the length of the video segment corresponding to the operation type; for each user group, the popularity contribution threshold of the hotspot segment of the user group is obtained, and the heat contribution threshold is the total heat contribution value of the user group and the number of video segments of the video content.
  • a ratio which is a product of a preset coefficient
  • a user equipment including: a sending unit, configured to send attribute information of a user to a server; a receiving unit, configured to receive a label of a hot spot segment of the video content sent by the server; and a display unit configured to be in accordance with the label The display portion of the video content displays the label of the hotspot clip.
  • the tag includes a keyword of the hot spot segment and a start and end time of the user group to which the user belongs, or the tag includes a time point of the user group to which the user belongs to the player when the hot spot is played. The earliest time point and the latest time point.
  • an embodiment of the present application provides a computer storage medium for storing computer software instructions used by the Internet of Things server, including a program designed to perform the above aspects.
  • an embodiment of the present application provides a computer storage medium for storing computer software instructions used by the server, including a program designed to perform the above aspects.
  • An embodiment of the present application provides a method for extracting a video hotspot segment, a user equipment, and a server.
  • the server divides the user into multiple user groups according to the attribute information of the user, and then, according to each user group of the multiple user groups, when watching the video content.
  • the operation information obtains a hot spot segment of each user group to watch the video content, and then obtains a label corresponding to the hot spot segment of each user group according to the hot spot segment of each user group viewing the video content, and corresponds to each user group.
  • the label of the hot spot is sent to the user equipment of the corresponding user group.
  • the embodiment of the present application can extract and present personalized hotspot segments for each user group according to multiple user groups, which can improve the accuracy of the user accessing the hotspot segments, and simultaneously present to all users in the prior art.
  • the embodiment of the present application can extract and present the covered hotspot segments belonging to certain user groups.
  • FIG. 1 is a schematic diagram of a system architecture provided by an embodiment of the present application.
  • FIG. 2 is a schematic diagram of functional modules of a system architecture according to an embodiment of the present disclosure
  • FIG. 3 is a schematic flowchart of a method for extracting a video hotspot segment according to an embodiment of the present disclosure
  • FIG. 4 is a schematic diagram of displaying different hotspot segments for each user group according to an embodiment of the present application
  • FIG. 5 is a schematic diagram of displaying different hotspot segments for each user group according to an embodiment of the present application.
  • FIG. 6 is a schematic flowchart of a method for extracting a video hotspot segment according to an embodiment of the present disclosure
  • FIG. 8 is a schematic diagram of displaying different hotspot segments for each user group according to an embodiment of the present application.
  • FIG. 9 is a schematic structural diagram of a server according to an embodiment of the present application.
  • FIG. 10 is a schematic structural diagram of a server according to an embodiment of the present application.
  • FIG. 11 is a schematic structural diagram of a user equipment according to an embodiment of the present disclosure.
  • FIG. 12 is a schematic structural diagram of a user equipment according to an embodiment of the present disclosure.
  • the application scenario of the user equipment (User Equipment, UE) of different user groups presents different hotspot segments to the user, and implements personalized presentation of hotspot segments of different user groups.
  • the system architecture of the present application may include user equipment and a server. There may be multiple user equipments, and different method flows may be performed between the servers. As shown in FIG. 1 , the system architecture includes multiple user equipments, server 1 and server 2. Schematic diagram of the architecture.
  • the user equipment can be any of the following with a display screen, and the user equipment can be static or mobile.
  • User equipment may include, but is not limited to, a personal computer, a laptop computer, a tablet computer, a netbook, a mobile terminal, a handheld device, a cordless device, a cordless device, a mobile terminal (Mobile terminal), a handheld device (Handheld), and a cordless device. Telephone (Cordless Phone), smart watches, smart glasses, etc.
  • the server 1 and the server 2 may be a physical cluster server or a virtual cloud server or the like.
  • each user equipment 0 may include a data collection/transmission module 01 and a presentation module 02, and the server 1
  • the data receiving/storing module 11 and the data sending module 12 may be included.
  • the server 2 may include a historical data acquiring module 21, a user classification module 22, a hotspot segment obtaining module 23, a label extracting module 24, and a data transmitting module 25.
  • the data collection/transmission module 01 and the presentation module 02 can be implemented in an application of a client device different from the user equipment.
  • the data collection/transmission module 01 in the client may be used to collect attribute information of the user who views the video content and send it to the server 1.
  • the data receiving/storing module 11 in the server 1 may be used to receive and store the received data from each client.
  • the attribute information of the plurality of users viewing the video content, and the attribute information of the aggregated user is sent to the server 2 through the data sending module 12, and the historical data obtaining module 21 in the server 2 is configured to receive attribute information of the plurality of users, the user
  • the classification module 22 is configured to classify a plurality of users according to the attribute information of the plurality of users, and obtain a plurality of user groups.
  • the hotspot segment obtaining module 23 is configured to acquire each user according to the operation information of the video content according to the video content of each user group.
  • the tag extracting module 24 is configured to obtain tags of the hotspot segments corresponding to each user group according to the hotspot segments of each user group, and send the tags of the hotspot segments of each user group to the data sending module 25.
  • Server 1 the data receiving/storing module 11 in the server 1 receives each user group After the label of the hot spot of the body, the user equipment of the user who views the video content receives the label of the hot spot sent by the server 1 through the data sending module 12, and the hot spot presented by the rendering module in the user equipment of different user groups.
  • the tags of the segments are different, so that some hidden hotspot segments belonging to certain user groups can be extracted, and the accuracy of accessing the hotspot segments by different user groups is improved.
  • the functions of the server 1 and the server 2 can be clustered in one server.
  • An embodiment of the present application provides a method for extracting a video hotspot segment. As shown in FIG. 3, the method includes:
  • the user equipment sends the attribute information of the user to the server 1.
  • the user equipment that sends the attribute information here can be understood as the registration information of the user in the client, or other registration information of the user, including the user identification (ID), age, gender, and occupation.
  • the attribute information of different users can be The same, can also be different.
  • the user ID may be an account that the user registers with the client, and may be, for example, a mobile phone number, or a mailbox, or a character string. This step can be performed by the above data collection/transmission module 01.
  • the server 1 receives and stores the attribute information of the user, and sends the attribute information of the user to the server 2.
  • the server 1 When receiving the attribute information of each user equipment user, the server 1 aggregates the attribute information of the received different users, and may be executed by the data receiving/storing module 11 , and then the aggregated attribute information of each user is sent through the data. Module 12 is sent to server 2.
  • the attribute information of the server 2 receiving each user can be executed by the above-described history data acquisition module 21.
  • the attribute information of the user after the aggregation of the server 1 is as shown in Table 1.
  • the server 2 may classify the user by using a clustering algorithm according to the attribute information of the user.
  • server 2 uses a K-Means clustering algorithm.
  • the K-Means clustering algorithm is taken as an example below.
  • the attribute vector of the user can be constructed as: [age, gender, occupation], wherein the age attribute can directly be the value of the corresponding bit of the attribute vector of the user, and the "male” attribute in the gender attribute can be the value of the corresponding bit of the attribute vector of the user.
  • the "female” property may have a value of 0 in the corresponding bit of the user attribute vector, and the value of the corresponding position of the professional attribute in the attribute vector of the user may be the value of the word frequency vector of the professional attribute.
  • the construction process of the professional attribute word frequency vector can be: 1 construct a vocabulary: construct a vocabulary by using all the words appearing in the professional attribute, for example, the vocabulary can be [student, civil servant, engineer, nurse, teacher, lawyer]; 2 construct word frequency vector : The word frequency of each user's occupational attribute in the vocabulary is used as the value of the corresponding bit of the word frequency vector, and the length of the word frequency vector is the vocabulary length.
  • the age is 10 years old, the gender is male, and the occupation is student. Then the value of the age attribute in the attribute vector of the user is 10, the value of the gender attribute is 1, and the occupation is in the vocabulary. The first one, that is, the student's word frequency is 1, and the remaining word frequency has a value of 0, then the value of the word frequency vector corresponding to the user's professional attribute is [1, 0, 0, 0, 0, 0].
  • the server 2 acquires the Euclidean distance of the attribute vector of the user and the cluster center.
  • Server 2 can randomly specify the user IDs of the three cluster centers of K-Means as 001, 007, and 015, respectively, and then calculate the attribute vector of each user and the Euclidean of each cluster center according to the preset Euclidean distance formula. distance.
  • the Euclidean distance of 0,0] is:
  • the server 1 can obtain the video content of each user group according to the operation information of each user group in the plurality of user groups when watching the video content.
  • the specific implementation manner of the hotspot segment may be: for each user group, the server 2 obtains the barrage comment threshold of the hotspot segment of the user group according to the operation information of the user group, and then according to the barrage comment threshold and the user group The operation information acquires a hot spot of the user group.
  • the server 1 may obtain historical barrage comment information of each video content collected by each user who collects the registration information from the client of the user equipment, where the historical barrage comment information may be within a preset time period after the video content is online.
  • the barrage comments information, and then the barrage comment information of the video content in the preset time period is sent to the server 2 by each user group.
  • the historical bullet review information may include a video ID of the video content commented by each user ID, a video clip ID, a play time point when the video is commented, and a barrage comment.
  • the user's commentary on the barrage of the Spring Festival Gala can be as shown in Table 5.
  • each user in the final divided user group in step 303 does not necessarily comment on the Spring Festival Gala video, and in step 304, only the historical barrage comment information of the user who comments on the Spring Festival Gala video is extracted. It is also possible for the same user to make multiple comments on the same video content.
  • the server 2 obtains a ratio of the number of historical barrage comments of the user group to the video content and the number of video segments of the video content, and then obtains the product of the ratio and the preset coefficient, where the product is the user.
  • the barrage comment threshold for a hot segment of the group For each user group, the server 2 obtains a ratio of the number of historical barrage comments of the user group to the video content and the number of video segments of the video content, and then obtains the product of the ratio and the preset coefficient, where the product is the user.
  • the barrage comment threshold for a hot segment of the group is the user.
  • the historical barrage comment information of the video content is grouped, that is, regardless of which video segment the user has commented on, the user's historical barrage comment information is divided into the user.
  • the user group to which it belongs For example, User 001's video content of the Spring Festival Gala Video ID is very cute in the 10.11s comment of the video content, then this barrage comment can be divided into the user group userGroup1 where the user ID 001 is located, so the grouped post-screen comment
  • the information can be as shown in Table 6.
  • the server 2 determines that the video group determines any video segment as a hotspot segment of the user group when the number of barrage comments of any video segment of the video content is greater than the barrage review threshold.
  • the video segment is determined to be the user group watching the video content.
  • Hot clips For example, the user group user group1 has 3 comments on the Tfboys video clip, the user group 1 has a threshold of 1.7, and the bullet comment number is 3 is greater than the threshold 1.7. Then the Tfboys video clip is the hot spot of the user group1.
  • the hotspot segments of each user group corresponding to Table 7 above can be as shown in Table 8:
  • Steps 304-306 can be performed by the hot spot segment acquisition module 23 described above.
  • the server 2 acquires a label corresponding to the hot spot segment of each user group according to the hot spot segment of the video content viewed by each user group, and sends the label of the hot spot segment of each user group to the server 1.
  • the server 2 may construct a keyword vocabulary of the hotspot segment, the keyword vocabulary includes keywords of the barrage comment of the hot spot segment, and then count the word frequency of each word in the keyword vocabulary. The keyword with the highest word frequency is determined, and the keyword with the highest word frequency and the start and end time of the user group for the hot spot segment are determined as the label of the hot spot.
  • the server 2 can extract the keywords of each barrage comment using the Java word segmentation HanLP.
  • the keywords extracted by HanLP can be: cute and Tfboys, so that the keywords extracted from each barrage comment of each user group can be as shown in Table 9. Then, according to the keywords of each barrage comment, the keyword vocabulary of each user group is constructed.
  • all the keywords corresponding to user group1 are: cute, Tfboys, singing, good, growing up, then user
  • the keyword vocabulary corresponding to Group1 can be: [cute, Tfboys, singing, good, growing up], and then, server 2 counts the word frequency of each word in the keyword vocabulary of each user group, for example, in the above keyword vocabulary
  • “Tfboys” appears 3 times, and other keywords appear once
  • the word frequency vector corresponding to user group1 is: [1,3,1,1,1]
  • the word frequency is determined according to the word frequency vector.
  • the highest keyword is “Tfboys”, and the user group’s start and end time for the hot spot TFboys is 10.11-105.45. Therefore, the hot spot of user group1 can be labeled “Tfboys” and 10.11-105.45.
  • This step can be performed by the tag extraction module 24 described above.
  • the server 1 saves a label of a hot spot segment of each user group, and sends a label corresponding to the hot spot segment of each user group to the user equipment of the corresponding user group.
  • the server 1 After the server 1 obtains the label of the hotspot segment of each user group, if the user in the registration information saved in the server 1 views the video content, the server 1 may send the label of the hot spot segment of the video content to the corresponding content of the viewing video content.
  • the user equipment displays a label of the hot spot segment according to the label in the display portion of the video content.
  • the server 1 can receive the label of the hotspot segment of the video content.
  • the user device personalizes the hotspot segment according to the received tag.
  • the user equipment may mark a start time of the hot spot segment of the play time axis according to the start and end time of the hot spot segment of the user group. And according to the start and stop time in the hot spot segment of the playing time axis to distinguish the color label of the non-hot spot, for example, as shown in FIG. 4, FIG. 4 is a hot spot when watching the video of the Spring Festival Gala according to each user group shown in Table 9. Fragment.
  • the user equipment may display the start and end time of the hotspot segment comment and the keyword to the user group in the form of a list in the video display area according to the user group.
  • the hotspot segment may have more than one hot segment displayed by the same user group.
  • the hotspot segment list presented to user group1 is as shown in Figure (1) in Figure 5
  • the hotspot segment list presented to user Group2 is presented to user group3 as shown in Figure (2) in Figure 5.
  • the hot spot segment list is shown in Figure (3) in Figure 5.
  • This step can be performed by the presentation module 02 described above.
  • embodiments of the present application can extract and present personalized hotspot segments according to multiple user groups, which can improve the accuracy of the user accessing the hotspot segments, and simultaneously presents the same hotspot to all users in the prior art. Fragments, embodiments of the present application can extract and present masked hotspot segments belonging to certain user groups.
  • An embodiment of the present application provides a method for extracting a video hotspot segment, as shown in FIG. 6, including:
  • the user equipment sends the attribute information of the user to the server 1.
  • the server 1 receives and stores the attribute information of the user, and sends the attribute information of the user to the server 2.
  • the server 2 divides the user into multiple user groups according to the attribute information of the user.
  • steps 601-603 For the implementation of steps 601-603, refer to steps 301-303 above.
  • the server 1 plays the video content from the player acquired by the user equipment, the historical operation information of the player for each user group is sent to the server 2.
  • the user's operation information on the player can be divided into: fast forward, forward drag, fast reverse, backward drag, and the like. If the user performs fast forward or forward drag operation on certain video segments of the video content, indicating that the user is not interested in the video segment, the server 1 can record the action name of the fast forward operation or the forward drag operation, and the action start time point. The end time of the action and the duration of the video clip, and obtain the duration of the action of the fast forward operation or the forward drag operation. For example, if the user fast forwards for 10s or drags forward for 10s, it is recorded as -10s, indicating The fast forward operation or the forward drag operation has a negative contribution to the heat contribution value of the video clip.
  • the server 1 may record the action name and action of the rewind operation or the backward drag operation.
  • the start time point, the action end time point, and the duration of the video clip and obtain the action duration span of the rewind operation or the backward drag operation, for example, for rewinding 10 or dragging backward 10s, then remember It is +10s, indicating that the rewind operation or the backward drag operation has a positive contribution to the heat contribution value of the video clip.
  • This embodiment of the present application is still described by taking the player to play the Spring Festival Gala as an example.
  • the server obtains the duration of each operation type according to the start and end time of each operation type when the user plays the video content in the user group, for example, Table 10
  • the historical operation information for the player when the user recorded by the server 1 in the preset time period views the video clips of the Spring Festival Gala.
  • the server 2 obtains a threshold of the hotspot segment of the user group according to historical operation information of the player group.
  • the server 2 can group the historical operation information of the player according to different user groups.
  • the user When a user performs a player operation on which video segment, the user is divided into the user group where the user is located. For example, the ID user's Tfboys performance video clip in the Spring Festival Gala video starts the fast forward operation at 10.11s to end the operation at 12.11, then the operation information is divided into user group1, for example, the grouping of each user group.
  • Table 4 as shown in Table 10, when the user views the historical operation information of the player during the Spring Festival Gala, the situation in which the historical operation information of the player is grouped can be as shown in Table 11.
  • Hot A (t A , T v ) K A *t A /T v
  • Hot A represents the heat contribution value of the fast forward operation
  • t A represents fast.
  • the duration is fast, the duration of this type of operation
  • T v represents the duration of the corresponding video segment
  • K A is the weight of the type of operation such as fast forward, and the range can be (0 to 1).
  • Hot B represents the heat contribution value of the forward drag operation
  • t B indicates the length of dragging forward, that is, the duration of dragging this type of operation forward
  • T v indicates the duration of the corresponding video clip
  • K B is the weighting value of the type of operation such as dragging forward, which can be dragged forward It means that the user's annoyance to video content is more intense than fast forward, so K B ⁇ K A , K B can range from (0 to 1).
  • Hot c (t c , T v ) K c *t c /T v
  • Hot c represents the heat contribution value of the rewind operation
  • t c represents the retreat
  • the duration that is, the duration of this type of operation is retired
  • T v represents the duration of the corresponding video segment
  • K c represents the weighted value of the type of operation such as rewind, the range (0 to 1).
  • Hot D represents the heat contribution value of the backward drag operation
  • t D indicates the length of dragging backwards, that is, the duration of dragging this type of operation backwards
  • T v indicates the duration of the corresponding video clip
  • K D is the weighting value of such operation type of dragging backwards, as it can be dragged backwards It means that the user likes the video content more strongly than the fast rewind, so K D ⁇ K C , K D can range from (0 to 1).
  • the total heat contribution value of each user group can be obtained, and the total heat contribution value of each user group can be expressed as That is, the sum of the heat contribution values of the user group to the player operation.
  • U represents a collection of player operations for any user group
  • Hot i is one of Hot A , Hot B , Hot c , and Hot D.
  • the product of the total heat contribution value of the user group and the number of video segments of the video content, and the product of the preset coefficient may be expressed as a heat contribution threshold of the hot spot of the video content of the user group, that is, a hotspot of the user group.
  • the heat contribution threshold of the segment (the total heat contribution value of the user group / the number of video segments) * C
  • C represents the preset coefficient.
  • the heat contribution threshold of the hotspot segment of each user group can be as shown in Table 12.
  • the server 2 acquires a hotspot segment of the user group according to the heat contribution threshold and the user group to the historical operation information of the player.
  • the video segment may be determined to be a hot segment of the user group. That is to say, for each user group, the server obtains the sum of the heat contribution values of the user groups to the video segments of the video content, and determines the video segments whose sum of the heat contribution values are greater than the heat contribution threshold as the hotspot segments of the user group.
  • the server 2 determines, as the hotspot segment, the earliest time point and the latest time point of each time point of the player operation when the hot spot segment is played.
  • the server 1 receives the label of the hotspot segment corresponding to each user group sent by the server 2 and saves the label, and sends the label corresponding to the hot spot segment of each user group to the user equipment of the corresponding user group.
  • the server 1 After the server 1 obtains the label of the hot spot segment when each user group views the video content, if the user in the registration information saved in the server 1 views the video content, the server 1 may send the label of the hot spot segment of the video content to the label View the user device of the corresponding user group of the video content.
  • the user equipment displays a label of the hot spot segment according to the label in the display portion of the video content.
  • the user equipment may select the earliest time point and the latest time point in each time point of the player operation according to the user group, and the earliest hot spot segment in the playing time axis.
  • the dot is marked with a dot, and the color segment of the non-hotspot segment is distinguished according to the hot spot segment of the earliest time point and the latest time point.
  • FIG. 7 is a group of users according to Table 13. Watch the hot clips of the Spring Festival Gala video.
  • the embodiment of the present application can extract and present personalized hotspot segments for each user group according to each user group, which can improve the accuracy of the user accessing the hot spot segments, and simultaneously, compared with all users in the prior art.
  • the embodiment of the present application can extract and present the covered hotspot segments belonging to certain user groups.
  • the embodiment of the present invention may divide a function module into a server, a user equipment, and the like according to the foregoing method.
  • each function module may be divided according to each function, or two or more functions may be integrated into one processing module.
  • the above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of the module in the embodiment of the present invention is schematic, and is only a logical function division, and the actual implementation may have another division manner.
  • FIG. 9 shows a possible structural diagram of the server involved in the above embodiment, and the server 90
  • the method includes: a classification unit 901, an acquisition unit 902, a transmission unit 903, and a reception unit 904.
  • the classification unit 901 is configured to support the server to execute the process 303 in FIG. 3, the process 603 in FIG. 6, the obtaining unit 303 is configured to support the server to execute the processes 304, 305, 306 in FIG. 3, the processes 605, 606 in FIG. 607;
  • the sending unit 903 is configured to execute the processes 307, 309 in FIG. 3, the process 604 in FIG.
  • the receiving unit 904 is configured to support the server to execute the process 302 in FIG. 3, the processes 602, 608 in FIG. All the related content of the steps involved in the foregoing method embodiments may be referred to the functional descriptions of the corresponding functional modules, and details are not described herein again.
  • a possible schematic diagram of the server 1 and the server 2 involved in the above embodiment may be as shown in FIG. 2.
  • the data sending module 12 and the historical data obtaining module 21 can be used to support the server 1 to perform the process 302 in FIG. 3, and the steps 602 and 604 in FIG. 6, the user classification module 22 can be used to support the server 2 to execute in FIG. Process 303 and step 603 in FIG. 6, hotspot segment acquisition module 23 may perform processes 304-306 in FIG. 3, and steps 605 and 606 in FIG. 6, tag extraction module 24 may perform process 307 in FIG. 3 and
  • the data transmitting module 25 can perform the process 308 of FIG. 3, and the step 608 of FIG. 6, the data transmitting module 12 can perform the process 309 of FIG. 3, and the step 608 of FIG.
  • the server 1 and the server 2 may further include a storage module (not shown in FIG. 2) for storing program codes and data of the server 1 and the server 2.
  • the user classification module 22, the hotspot fragment extraction module 23, and the label extraction module 24 may be processors or controllers, such as a central processing unit (CPU), a general purpose processor, and a digital signal processor (Digital Signal). Processor, DSP), Application-Specific Integrated Circuit (ASIC), Field Programmable Gate Array (FPGA) or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It is possible to implement or carry out the various illustrative logical blocks, modules and circuits described in connection with the present disclosure.
  • the processor may also be a combination of computing functions, for example, including one or more microprocessor combinations, a combination of a DSP and a microprocessor, and the like.
  • the historical data acquisition module 21, the data transmission optical module 25, the data transmission module 12, and the data reception module 11 may be a transceiver, a transceiver circuit, a communication interface, or the like.
  • the data storage module 11 can be a memory.
  • the hotspot fragment extraction module 23, and the label extraction module 24 are processors
  • the historical data acquisition module 21, the data transmission optical module 25, the data transmission module 12, and the data receiving module 11 are transceivers
  • the data storage module 11 is In the case of the memory, if the functions of the server 1 and the server 2 are clustered in one server, the server involved in the embodiment of the present invention may be the server shown in FIG.
  • the server 10 includes a processor 1012, a transceiver 1013, a memory 1011, and a bus 1014.
  • the transceiver 1013, the processor 1012, and the memory 1011 are connected to each other through a bus 1014.
  • the bus 1014 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. Wait.
  • PCI Peripheral Component Interconnect
  • EISA Extended Industry Standard Architecture
  • Wait The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one thick line is shown in FIG. 10, but it does not mean that there is only one bus or one type of bus.
  • FIG. 2 shows a possible structural diagram of the user equipment involved in the above embodiment.
  • the user equipment 0 includes a data collection/transmission module 01 and a presentation module 02.
  • the data collection/transmission module 01 is configured to support the user equipment to perform the process 301 in FIG. 3, the process 601 in FIG. 6, and the presentation module 02 user performs the process 310 in FIG. 3, the process 609 in FIG.
  • the data collection/transmission module 01 is for supporting communication between the user equipment and other network entities, such as communication with the functional modules or network entities shown in Figures 2, 3, and 6.
  • the user equipment 0 may further include a storage module 03 and a processing module 04 (not shown) for storing program codes and data of the user equipment, and the processing module 04 is for controlling and managing the actions of the user equipment.
  • the processing module 04 can be a processor or a controller, such as a central processing unit CPU, a general purpose processor, a digital signal processor DSP, an application specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic device, and a transistor. Logic device, hardware component, or any combination thereof. It is possible to implement or carry out the various illustrative logical blocks, modules and circuits described in connection with the present disclosure.
  • the processor may also be a combination of computing functions, for example, including one or more microprocessor combinations, a combination of a DSP and a microprocessor, and the like.
  • the data collection/transmission module 01 may be a transceiver, a transceiver circuit, a communication interface, or the like.
  • the storage module 03 can be a memory
  • the presentation module 02 can be a display or a display screen or the like.
  • the processing module 04 is a processor
  • the data collection/transmission module 01 is a transceiver
  • the storage module 03 is a memory
  • the presentation module is a display
  • the user equipment involved in the embodiment of the present invention may be the user equipment shown in FIG.
  • the user equipment 122 includes a processor 1212, a transceiver 1213, a memory 1211, a display 1215, and a bus 1214.
  • the transceiver 1213, the processor 1212, the display 1215, and the memory 1211 are connected to each other through a bus 1214.
  • the bus 1214 may be a peripheral component interconnect standard PCI bus or an extended industry standard structure EISA bus.
  • the bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one thick line is shown in Figure 12, but it does not mean that there is only one bus or one type of bus.
  • the steps of a method or algorithm described in connection with the present disclosure may be implemented in a hardware, or may be implemented by a processor executing software instructions.
  • the software instructions may be composed of corresponding software modules, which may be stored in a random access memory (RAM), a flash memory, a read only memory (ROM), an erasable programmable read only memory ( Erasable Programmable ROM (EPROM), electrically erasable programmable read only memory (EEPROM), registers, hard disk, removable hard disk, compact disk read only (CD-ROM) or any other form of storage medium known in the art.
  • An exemplary storage medium is coupled to the processor to enable the processor to read information from, and write information to, the storage medium.
  • the storage medium can also be an integral part of the processor.
  • the processor and the storage medium can be located in an ASIC. Additionally, the ASIC can be located in a core network interface device.
  • the processor and the storage medium may also exist as discrete components in the core network interface device.
  • the functions described herein can be implemented in hardware, software, firmware, or any combination thereof.
  • the functions may be stored in a computer readable medium or transmitted as one or more instructions or code on a computer readable medium.
  • Computer readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one location to another.
  • a storage medium may be any available media that can be accessed by a general purpose or special purpose computer.

Abstract

本申请实施例公开了一种视频热点片段提取方法、用户设备和服务器，涉及通信领域，能够解决用户访问热点片段准确度低以及某些热点片段无法提取和对用户呈现的问题。服务器根据用户的属性信息将用户分为多个用户群体，根据多个用户群体中每个用户群体在观看视频内容时的操作信息，获取每个用户群体观看视频内容的热点片段，再根据每个用户群体观看视频内容的热点片段获取对应于每个用户群体的热点片段的标签，并将对应于每个用户群体的热点片段的标签发送给相应的用户群体的用户设备。本申请实施例用于向不同的用户群体呈现不同的热点片段。

Description

一种视频热点片段提取方法、用户设备和服务器
本申请要求于2017年3月21日提交中国专利局、申请号为201710171580.4，发明名称为“一种视频热点片段提取方法、用户设备和服务器”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
本申请涉及通信技术领域，尤其涉及一种视频热点片段提取方法、用户设备和服务器。
背景技术
随着互联网的快速发展，在线网络视频观看受到越来越多用户的喜爱。传统的视频门户网站，可以通过后台编辑节目的个人喜好引导用户观看该视频，每次视频上线之前，会通过人工在线观看数遍视频后，筛选出视频的热点片段并拟出醒目的标题标注在进度条上。
目前，相对于人工编辑热点片段更有效的方法有两种，一是可以基于视频中弹幕数量与阈值的大小提取并标识热点片段，二是基于用户对视频播放器的操作信息获取用户对当前视频中的片段的喜好，例如通过快进快退的操作确定用户是否喜欢该片段，以此提取并标识热点片段。
但是，这样一来，所有用户观看同一视频时，视频所在的页面的显示内容都相同，即标识的热点片段均相同。而实际上，不同的年龄段、性别、教育背景以及地域等的用户群体喜欢观看的视频题材、片段或视频环节等可能都不相同，使得不同的用户群体所需访问的视频热点片段也不相同，上述方法虽然相对于人工编辑热点片段效率高，但是不能针对不同用户群体提取不同用户群体所想要观看的视频热点片段，使得用户访问热点片段的准确度低，也会使得属于某些用户群体的热点片段无法提取和对用户呈现。
发明内容
本申请实施例提供一种视频热点片段提取方法、用户设备和服务器，能够解决用户访问热点片段准确度低以及某些热点片段无法提取和对用户呈现的问题。
一方面，提供一种视频热点片段的提取方法，包括：服务器根据用户的属性信息将用户分为多个用户群体，再根据多个用户群体中每个用户群体在观看视频内容时的操作信息，获取每个用户群体观看视频内容的热点片段，进而根据每个用户群体观看视频内容的热点片段获取对应于每个用户群体的热点片段的标签，并将对应于每个用户群体的热点片段的标签发送给相应的用户群体的用户设备。这样，本申请实施例可以按照多个用户群体，提取和呈现个性化的热点片段，可以提高用户访问热点片段的准确度，同时，相对于现有技术中给所有用户呈现的为同一热点片段，本申请实施例可以提取和呈现出被掩盖的属于某些用户群体的热点片段。
在一种可能的设计中，服务器根据用户的属性信息将用户分为多个用户群体包括：服务 器根据聚类算法对用户的属性信息进行分析，以将用户分为多个用户群体；服务器根据聚类算法对用户的属性信息进行分析，以将用户分为多个用户群体可以包括：服务器根据用户的属性信息构建用户的属性向量，获取用户的属性向量与聚类中心的欧氏距离，根据欧氏距离将用户划分至欧氏距离最近的聚类中心所在的簇，每个簇对应一个用户群体。于是，在本申请中，可以将用户按照属性分为多个用户群体，以便为每个用户群体找寻每个用户群体喜欢观看的热点片段。这里的属性可以由多种，例如可以为用户的年龄、性别以及职业等。
在一种可能的设计中，服务器根据多个用户群体中每个用户群体在观看视频内容时的操作信息，获取每个用户群体观看视频内容的热点片段包括：对于每个用户群体，服务器根据该用户群体的操作信息获取该用户群体的热点片段的弹幕评论阈值或热度贡献阈值；对于每个用户群体，服务器根据弹幕评论阈值以及该用户群体的操作信息获取该用户群体的热点片段，或服务器根据热度贡献阈值以及该用户群体的操作信息获取该用户群体的热点片段。在本申请中，用户的操作信息即用户对观看视频内容反馈的数据，该反馈数据可以包括用户对视频内容的显性反馈或隐性反馈，显性反馈例如可以是用户对观看的视频内容的视频片段的实时弹幕评论，隐性反馈例如可以是用户对视频播放器的操作，是否前后拖动进度条或点击快进快退按钮，以及对在线视频内容的点击、浏览和收藏等，用以体现用户对视频内容的喜爱程度，使得服务器可以为多个用户群体获取到每个用户群体对应的热点片段。
在一种可能的设计中，对于每个用户群体，服务器根据该用户群体的操作信息获取该用户群体的热点片段的弹幕评论阈值包括：对于每个用户群体，服务器获取该用户群体对视频内容的历史弹幕评论的数量与视频内容的视频片段的数量的比值，再获取比值与预设系数的乘积，乘积为该用户群体的热点片段的弹幕评论阈值；服务器根据弹幕评论阈值以及该用户群体的操作信息获取该用户群体的热点片段包括：对于每个用户群体，服务器确定该用户群体对视频内容的任一视频片段的弹幕评论数大于弹幕评论阈值时，将任一视频片段确定为用户群体的热点片段。也即每个用户群体对于某个视频片段的弹幕评论数量大于了该用户群体的对每个视频片段的平均弹幕数量时，确定该视频片段为该用户群体的热点片段。
在一种可能的设计中，服务器根据每个用户群体观看视频内容的热点片段获取对应于每个用户群体的热点片段的标签包括：对于每个用户群体的热点片段，服务器构建该热点片段的关键词词表，关键词词表包括该热点片段的弹幕评论的关键词，再统计关键词词表中各词的词频，确定词频最高的关键词，将词频最高的关键词以及该用户群体对该热点片段评论的起止时间确定为该热点片段的标签。于是，在用户设备侧，可以在每个用户群体观看视频内容时，可以根据关键词以及热点片段的标签准确定位到每个用户群体感兴趣的热点片段，使得用户群体之间的热点片段呈现个性化，也不会使得每个用户群体都获取到的是相同的热点片段的标签。
在一种可能的设计中，如果用户群体的操作信息为用户为播放器的历史操作信息，那么对于每个用户群体，服务器根据该用户群体的操作信息获取该用户群体的热点片段的热度贡献阈值包括：对于每个用户群体，服务器获取每个用户的每种操作类型的持续时间，操作类型包括快进、快退、向前拖动以及向后拖动；对于每个用户群体中的每个用户，服务器获取该用户的每种操作类型的热度贡献值，热度贡献值为该种操作类型的持续时间与该种操作类型的加权值的乘积，再与该种操作类型对应的视频片段时长的比值；对于每个用户群体，服务器获取该用户群体的热点片段的热度贡献阈值，热度贡献阈值为该用户群体的总热度贡献值与视频内容的视频片段的数量的比值，再与预设系数的乘积；对于每个用户群体，服务器 根据热度贡献阈值以及该用户群体的操作信息获取该用户群体的热点片段包括：对于每个用户群体，服务器获取该用户群体对视频内容的各视频片段的热度贡献值的和，将热度贡献值的和大于热度贡献阈值的视频片段确定为该用户群体的热点片段。由于用户在视频片段播放时对播放器的快进、快退、向前拖动以及向后拖动都可以反馈出该用户对该视频片段的感兴趣程度，那么在获取到每个用户群体的热点片段后，可以为每个用户群体呈现不同的热点片段，可以提高用户访问热点片段的准确度，并提取出被掩盖的属于某些用户群体的热点片段。
在一种可能的设计中，服务器根据每个用户群体观看视频内容的热点片段获取对应于每个用户群体的热点片段的标签包括：对于每个用户群体的热点片段，服务器将该用户群体在该热点片段播放时对播放器操作的各时间点中的最早时间点和最晚时间点确定为热点片段的标签。于是，每个用户群体就可以根据每个用户群体对应的热点片段的标签快速定位到每个用户群体感兴趣的热点片段。
在一种可能的设计中，在服务器根据观看视频内容的用户的属性信息将用户分为不同的用户群体之前，该方法还包括：服务器接收用户设备发送的用户的属性信息。该属性信息可以从用户在用户设备中的注册信息中获取或者从用户在客户端中的注册信息获取，也可以通过其他方式获取，本申请不做限定。
另一方面，提供一种视频热点片段的提取方法，包括：用户设备向服务器发送用户的属性信息；用户设备接收服务器发送的视频内容的热点片段的标签，根据标签在视频内容的显示部分显示热点片段的标签。用户在观看视频内容时，同时也将用户在观看视频内容时的操作信息以及业务数据也发送给服务器，业务数据可以表示为时序形式，每条业务数据可以包括会话标识(Session ID)、用户账号、视频播放起始时间、视频结束时间、播放类型、视频类型、视频ID等，这样，服务器可以根据用户的属性信息以及用户在观看视频内容的操作信息以及业务数据获取每个用户群体观看视频内容的热点片段，并获取每个用户群体的热点片段的标签发送给用户设备，于是，每个用户群体的用户设备可以呈现个性化的热点片段的标签，提升用户访问热点片段的准确度，可呈现出了被掩盖的属于某些用户群体的热点片段。
在一种可能的设计中，标签包括热点片段的关键词以及用户所属的用户群体对热点片段评论的起止时间，或标签包括用户所属的用户群体在热点片段播放时对播放器操作的各时间点中的最早时间点和最晚时间点。
再一方面，提供一种服务器，包括：分类单元，用于根据用户的属性信息将用户分为多个用户群体；获取单元，用于根据分类单元划分的多个用户群体中每个用户群体在观看视频内容时的操作信息，获取每个用户群体观看视频内容的热点片段；获取单元，还用于根据获取单元获取的每个用户群体观看视频内容的热点片段获取对应于每个用户群体的热点片段的标签；发送单元，用于将获取单元获取的对应于每个用户群体的热点片段的标签发送给相应的用户群体的用户设备。
在一种可能的设计中，分类单元用于：根据聚类算法对用户的属性信息进行分析，以将用户分为多个用户群体；分类单元具体用于：根据用户的属性信息构建用户的属性向量；获取用户的属性向量与聚类中心的欧氏距离；根据欧氏距离将用户划分至欧氏距离最近的聚类中心所在的簇，每个簇对应一个用户群体。
在一种可能的设计中，获取单元用于：对于每个用户群体，根据该用户群体的操作信息获取该用户群体的热点片段的弹幕评论阈值或热度贡献阈值；对于每个用户群体，根据弹幕 评论阈值以及该用户群体的操作信息获取该用户群体的热点片段，或根据热度贡献阈值以及该用户群体的操作信息获取该用户群体的热点片段。
在一种可能的设计中，获取单元用于：对于每个用户群体，获取该用户群体对视频内容的历史弹幕评论的数量与视频内容的视频片段的数量的比值，再获取比值与预设系数的乘积，乘积为该用户群体的热点片段的弹幕评论阈值；对于每个用户群体，确定该用户群体对视频内容的任一视频片段的弹幕评论数大于弹幕评论阈值时，将任一视频片段确定为用户群体的热点片段。
在一种可能的设计中，对于每个用户群体的热点片段，构建该热点片段的关键词词表，关键词词表包括该热点片段的弹幕评论的关键词；对于每个用户群体的热点片段，统计关键词词表中各词的词频，确定词频最高的关键词，将词频最高的关键词以及该用户群体对该热点片段评论的起止时间确定为该热点片段的标签。
在一种可能的设计中，获取单元用于：对于每个用户群体，获取每个用户的每种操作类型的持续时间，操作类型包括快进、快退、向前拖动以及向后拖动；对于每个用户群体中的每个用户，获取该用户的每种操作类型的热度贡献值，热度贡献值为该种操作类型的持续时间与该种操作类型的加权值的乘积，再与该种操作类型对应的视频片段时长的比值；对于每个用户群体，获取该用户群体的热点片段的热度贡献阈值，热度贡献阈值为该用户群体的总热度贡献值与视频内容的视频片段的数量的比值，再与预设系数的乘积；对于每个用户群体，获取该用户群体对视频内容的各视频片段的热度贡献值的和，将热度贡献值的和大于热度贡献阈值的视频片段确定为该用户群体的热点片段。
在一种可能的设计中，获取单元用于：对于每个用户群体的热点片段，将该用户群体在该热点片段播放时对播放器操作的各时间点中的最早时间点和最晚时间点确定为热点片段的标签。
在一种可能的设计中，还包括接收单元，用于接收用户设备发送的用户的属性信息。
又一方面，提供一种用户设备，包括：发送单元，用于向服务器发送用户的属性信息；接收单元，用于接收服务器发送的视频内容的热点片段的标签；显示单元，用于根据标签在视频内容的显示部分显示热点片段的标签。
在一种可能的设计中，标签包括热点片段的关键词以及用户所属的用户群体对热点片段评论的起止时间，或标签包括用户所属的用户群体在热点片段播放时对播放器操作的各时间点中的最早时间点和最晚时间点。
又一方面，本申请实施例提供了一种计算机存储介质，用于储存为上述物联网服务器所用的计算机软件指令，其包含用于执行上述方面所设计的程序。
又一方面，本申请实施例提供了一种计算机存储介质，用于储存为上述服务器所用的计算机软件指令，其包含用于执行上述方面所设计的程序。
本申请实施例提供一种视频热点片段的提取方法、用户设备和服务器，服务器根据用户的属性信息将用户分为多个用户群体，再根据多个用户群体中每个用户群体在观看视频内容时的操作信息，获取每个用户群体观看视频内容的热点片段，进而根据每个用户群体观看视频内容的热点片段获取对应于每个用户群体的热点片段的标签，并将对应于每个用户群体的热点片段的标签发送给相应的用户群体的用户设备。这样，本申请实施例可以按照多个用户群体，为每个用户群体提取和呈现个性化的热点片段，可以提高用户访问热点片段的准确度，同时，相对于现有技术中给所有用户呈现的为同一热点片段，本申请实施例可以提取和呈现 出被掩盖的属于某些用户群体的热点片段。
附图说明
图1为本申请实施例提供的一种系统架构的示意图；
图2为本申请实施例提供的一种系统架构的功能模块的示意图；
图3为本申请实施例提供的一种视频热点片段的提取方法的流程示意图；
图4为本申请实施例提供的一种为每个用户群体展现不同的热点片段的示意图；
图5为本申请实施例提供的一种为每个用户群体展现不同的热点片段的示意图；
图6为本申请实施例提供的一种视频热点片段的提取方法的流程示意图；
图7为本申请实施例提供的一种为每个用户群体展现不同的热点片段的示意图；
图8为本申请实施例提供的一种为每个用户群体展现不同的热点片段的示意图；
图9为本申请实施例提供的一种服务器的结构示意图；
图10为本申请实施例提供的一种服务器的结构示意图；
图11为本申请实施例提供的一种用户设备的结构示意图；
图12为本申请实施例提供的一种用户设备的结构示意图。
具体实施方式
本申请实施例可以应用在不同用户群体的用户设备(User Equipment，UE)向用户呈现不同的热点片段的应用场景，实现不同用户群体的热点片段的个性化呈现。
本申请的系统架构可以包括用户设备和服务器，用户设备可以有多个，服务器之间可以交互执行不同的方法流程，如图1所示为系统架构包括多个用户设备、服务器1和服务器2的架构示意图。用户设备可以为具有显示屏的以下任意一种，并且用户设备可以是静态的，也可以是移动的。用户设备可以包括但不限于：个人电脑(Personal Computer)、膝上型电脑(Laptop Computer)、平板电脑(Tablet Computer)、上网本(Netbook)、移动终端(Mobile Terminal)、手持设备(Handheld)、无绳电话(Cordless Phone)、智能手表以及智能眼镜等。服务器1和服务器2可以是物理集群服务器或者虚拟云服务器等。
在本申请实施例中，如图2所示，在系统架构包括用户设备0、服务器1和服务器2的情况下，每个用户设备0可以包括数据收集/发送模块01和呈现模块02，服务器1可以包括数据接收/存储模块11和数据发送模块12，服务器2可以包括历史数据获取模块21、用户分类模块22、热点片段获取模块23、标签提取模块24以及数据发送模块25。其中，数据收集/发送模块01和呈现模块02可以在用户设备不同的客户端的应用程序中实现。客户端中的数据收集/发送模块01可以用于收集观看视频内容的用户的属性信息并发送给服务器1，服务器1中的数据接收/存储模块11可以用于从各个客户端接收并存储接收到的观看视频内容的多个用户的属性信息，并汇聚得到的用户的属性信息通过数据发送模块12发送给服务器2，服务器2中的历史数据获取模块21用于接收多个用户的属性信息，用户分类模块22用于根据多个用户的属性信息对多个用户分类，得到多个用户群体，热点片段获取模块23用于根据每个用户群体观看视频内容时对视频内容的操作信息获取每个用户群体的热点片段，标签提取模块24用于根据每个用户群体的热点 片段获取对应于每个用户群体的热点片段的标签，并将每个用户群体的热点片段的标签通过数据发送模块25发送给服务器1，服务器1中的数据接收/存储模块11在接收到每个用户群体的热点片段的标签后，之后观看该视频内容的用户的用户设备会接收到服务器1通过2数据发送模块12发送的热点片段的标签，不同用户群体的用户设备中的呈现模块所呈现的热点片段的标签不同，这样，能够提取到某些被掩盖的属于某些用户群体的热点片段，提高不同的用户群体访问热点片段的准确度。当然，如果系统架构有一个服务器时，该服务器1和服务器2的功能可以集群在一个服务器中。
下面以各用户群体对视频内容的操作信息为历史弹幕评论信息为例进行说明。本申请实施例提供一种视频热点片段的提取方法，如图3所示，该方法包括：
301、用户设备向服务器1发送用户的属性信息。
这里发送属性信息的用户设备可以理解为用户在客户端中的注册信息，也可以是用户的其他注册信息，包括用户标识(Identification，ID)、年龄、性别和职业等，不同用户的属性信息可以相同，也可以不同。用户ID可以是用户注册该客户端的账号，例如可以是手机号、或邮箱、或字符串等。该步骤可以由上述数据收集/发送模块01执行。
302、服务器1接收并存储用户的属性信息，并将用户的属性信息发送给服务器2。
服务器1在接收到各个用户设备用户的属性信息时，对接收到的不同用户的属性信息进行汇总，可以由上述数据接收/存储模块11执行，而后将汇总后的各个用户的属性信息通过数据发送模块12发送给服务器2。服务器2接收各个用户的属性信息可以由上述历史数据获取模块21执行。例如服务器1汇总后的用户的属性信息如表1所示。
表1用户属性信息
用户ID 年龄 性别 职业 XX(可扩展) ……
001 10 男 学生    
002 8 女 学生    
003 12 女 学生    
004 22 男 学生    
005 50 男 公务员    
006 9 女 学生    
007 25 男 工程师    
008 27 女 护士    
009 26 男 工程师    
010 23 男 学生    
011 21 女 学生    
012 44 女 教师    
013 11 男 学生    
014 25 男 律师    
015 47 男 公务员    
016 49 女 教师    
303、服务器2根据用户的属性信息将用户分为多个用户群体。该步骤可以由上述用户分类模块22执行。
一种可能的实现方式为：服务器2可以简单的根据用户的年龄和性别等属性对用户进行分类、例如服务器2可以根据年龄的划分将用户分为：儿童用户观看群体、年轻人 用户观看群体以及中老年用户观看群体。
另一种可能的实现方式可以为：服务器2可以根据用户的属性信息，采用聚类算法对用户进行分类。例如服务器2采用K-Means聚类算法。下面以K-Means聚类算法为例进行说明。
1)服务器2根据用户的属性信息构建用户的属性向量。
例如用户的属性向量可以构建为：[年龄，性别，职业]，其中年龄属性可以直接作为用户的属性向量对应位的值，性别属性中的“男”性可以在用户的属性向量对应位的值为1，“女”性可以在用户属性向量对应位的值为0，职业属性在用户的属性向量对应位的值可以为职业属性的词频向量的值。这里职业属性词频向量构建过程可以为：①构建词表：利用职业属性中所有出现的词构建词表，例如词表可以为[学生，公务员，工程师，护士，教师，律师]；②构建词频向量：将每个用户的职业属性在词表中各词的词频，作为词频向量对应位的值，词频向量的长度即为词表长度。
表1中汇总的用户的属性信息对应的用户的属性向量可以如表2所示。
表2用户的属性向量
用户ID 年龄 性别 职业 用户属性向量
001 10 男 学生 [10,1,1,0,0,0,0,0]
002 8 女 学生 [8,0,1,0,0,0,0,0]
003 12 女 学生 [12,0,1,0,0,0,0,0]
004 22 男 学生 [22,1,1,0,0,0,0,0]
005 50 男 公务员 [50,1,0,1,0,0,0,0]
006 9 女 学生 [9,0,1,0,0,0,0,0]
007 25 男 工程师 [25,1,0,0,1,0,0,0]
008 27 女 护士 [27,0,0,0,0,1,0,0]
009 26 男 工程师 [26,1,0,0,1,0,0,0]
010 23 男 学生 [23,1,1,0,0,0,0,0]
011 21 女 学生 [21,0,1,0,0,0,0,0]
012 44 女 教师 [44,0,0,0,0,0,1,0]
013 11 男 学生 [11,1,1,0,0,0,0,0]
014 25 男 律师 [25,1,0,0,0,0,0,1]
015 47 男 公务员 [47,1,0,1,0,0,0,0]
016 49 女 教师 [49,0,0,0,0,0,1,0]
以ID为001的用户来说，其年龄为10岁，性别为男，职业为学生，那么该用户的属性向量中的年龄属性的值为10，性别属性的值为1，职业在词表的第一位，即学生的词频为1，其余词频的值为0，那么该用户的职业属性对应的词频向量的值为[1,0,0,0,0,0]。
2)服务器2获取用户的属性向量与聚类中心的欧氏距离。
服务器2可以先随机指定K-Means的3个聚类中心的用户ID分别为001、007和015，而后按照预设的欧氏距离公式，计算各用户的属性向量与各聚类中心的欧氏距离。例如用户ID为002的用户属性向量[8,0,1,0,0,0,0,0]与聚类中心ID为001的用户的属性向量[8,0,1,0,0,0,0,0]的欧氏距离为：
Figure PCTCN2018073852-appb-000001
按照这种计算方式，各用户的属性向量与各聚类中心的欧氏距离可以如表3所示。
表3用户的属性向量与聚类中心的欧氏距离
Figure PCTCN2018073852-appb-000002
这样，根据上述计算得到的每个用户的属性向量与各聚类中心的欧氏距离，将各用户划分至距离最近的聚类中心所在的簇，每个簇对应一个用户群体。例如ID 002的用户到聚类中心[用户ID 001]的欧氏距离为2.2，到聚类中心[用户ID 007]的欧氏距离为17.1，到聚类中心[用户ID 015]的欧氏距离为39.0，因此将ID 002的用户划分至聚类中心[用户ID 001]所在的簇，即ID 002的用户属于[用户ID 001]所在的用户群体user Group1。于是，聚类后的3个用户群体(userGroup1、usergroup2以及usergroup3)可以如下表4所示。
表4聚类得到的各用户群体
Figure PCTCN2018073852-appb-000003
而后，在服务器2根据用户的属性信息将用户分为多个用户群体之后，服务器1可以根据多个用户群体中每个用户群体在观看视频内容时的操作信息，获取每个用户群体观看视频内容的热点片段，其具体实现方式可以为：对于每个用户群体，服务器2根据该用户群体的操作信息获取该用户群体的热点片段的弹幕评论阈值，而后根据弹幕评论阈值以及该用户群体的操作信息获取该用户群体的热点片段。
下面以每个用户群体对视频内容的操作信息为用户对视频内容的历史弹幕评论信息为例继续进行说明。
304、服务器1将从用户设备获取的每个用户群体对视频内容的历史弹幕评论信息发送给服务器2。
服务器1可以从用户设备的客户端获取采集到注册信息的各个用户在对各个视频内容的历史弹幕评论信息，这里的历史弹幕评论信息可以是视频内容在上线之后的预设时间段内的弹幕评论信息，而后将每个用户群体对该视频内容在预设时间段内的弹幕评论信息发送给服务器2。其中，历史弹幕评论信息可以包括每个用户ID评论的视频内容的视频ID、视频片段ID、对视频进行评论时的播放时间点以及弹幕评论。以每个用户群体观看春节联欢晚会视频的弹幕评论信息为例，用户对春节联欢晚会的弹幕评论信息可以如表5所示。
表5用户观看春节联欢晚会视频的弹幕评论信息
Figure PCTCN2018073852-appb-000004
需要说明的是，步骤303中最终划分的用户群体中的每个用户不一定都会对春节联欢晚会视频进行评论，步骤304这里只提取对春节联欢晚会视频进行评论的用户的历史弹幕评论信息，同一个用户也有可能对同一视频内容进行多次评论。
305、对于每个用户群体，服务器2获取用户群体对视频内容的历史弹幕评论的数量与视频内容的视频片段的数量的比值，再获取该比值与预设系数的乘积，该乘积为该用户群体的热点片段的弹幕评论阈值。
按照步骤303中划分的每个用户群体，将对视频内容的历史弹幕评论信息进行分组，即一个用户不论对哪个视频片段进行了评论，都会将该用户的历史弹幕评论信息划分至该用户所属的用户群体。例如用户001对春节联欢晚会视频ID的视频内容在视频内容的10.11s评论为Tfboys好可爱，那么这条弹幕评论可以分到用户ID 001所在的用户群体userGroup1中，于是分组后的弹幕评论信息可以如表6所示。
表6分组后的弹幕评论信息
Figure PCTCN2018073852-appb-000005
Figure PCTCN2018073852-appb-000006
按照分组后的弹幕评论信息，对于每个用户群体，可以获取用户群体对视频内容的历史弹幕评论的数量与视频内容的视频片段的数量的比值，再获取该比值与预设系数的乘积，该乘积为用户群体观看视频内容的热点片段的弹幕评论阈值，预设系数可以为超参，可以根据对热点片段的热点强度需求设置。例如按照表6来说，取预设系数为1，user Group1观看视频内容的热点片段的弹幕评论阈值＝5/3＝1.7，user Group2观看视频内容的热点片段的弹幕评论阈值＝7/3＝2.3，user Group3观看视频内容的热点片段的弹幕评论阈值＝4/3＝1.3，如表7所示。
表7每个用户群体的热点片段的阈值
Figure PCTCN2018073852-appb-000007
Figure PCTCN2018073852-appb-000008
306、对于每个用户群体，服务器2确定该用户群体对视频内容的任一视频片段的弹幕评论数大于弹幕评论阈值时，将任一视频片段确定为用户群体的热点片段。
也就是说，对于任一用户群体，如果用户群体对同一视频片段的弹幕评论数量大于该用于群体的热点片段的弹幕评论阈值，则将该视频片段确定为该用户群体观看视频内容的热点片段。例如用户群体user Group1对Tfboys视频片段的弹幕评论数为3，user Group1的热点片段的阈值为1.7，弹幕评论数为3大于阈值1.7，那么Tfboys视频片段为user Group1的热点片段，以此类推，上述表7对应的每个用户群体的热点片段可以如表8所示：
表8每个用户群体的热点片段
Figure PCTCN2018073852-appb-000009
Figure PCTCN2018073852-appb-000010
步骤304-306可以由上述热点片段获取模块23执行。
307、服务器2根据每个用户群体观看视频内容的热点片段获取对应于每个用户群体的热点片段的标签，并将每个用户群体的热点片段的标签发送给服务器1。
对于每个用户群体的热点片段，服务器2可以构建该热点片段的关键词词表，关键词词表包括该热点片段的弹幕评论的关键词，而后统计关键词词表中各词的词频，确定词频最高的关键词，将词频最高的关键词以及该用户群体对该热点片段评论的起止时间确定为该热点片段的标签。
其中，服务器2可以采用Java分词包HanLP提取每条弹幕评论的关键词。例如对于弹幕评论“Tfboys好可爱”，通过HanLP提取出的关键词可以为：可爱和Tfboys，这样，每个用户群体的每条弹幕评论提取出的关键词可以如表9所示。而后，根据每条弹幕评论的关键词构建每个用户群体的关键词词表，如表9所示，user Group1对应的所有关键词为：可爱，Tfboys，歌唱，不错，长大，则user Group1对应的关键词词表可以为：[可爱，Tfboys，歌唱，不错，长大]，进而，服务器2统计各用户群体的关键词词表中各词的词频，例如，在上述关键词词表中，user Group1对应的关键词中“Tfboys”出现3次，其他关键词出现一次，那么user Group1对应的词频向量为：[1,3,1,1,1]，根据该词频向量，确定词频最高的关键词为“Tfboys”，再加上用户群体对热点片段TFboys表演评论的起止时间为10.11-105.45，因此，user Group1的热点片段的标签可以为“Tfboys”以及10.11-105.45。
表9关键词词表、对应的词频以及词频最高的关键词
Figure PCTCN2018073852-appb-000011
Figure PCTCN2018073852-appb-000012
该步骤可以由上述标签提取模块24执行。
308、服务器2将每个用户群体的热点片段的标签发送给服务器1。该步骤可以由上述数据发送模块25执行。
309、服务器1保存每个用户群体的热点片段的标签，并将对应于每个用户群体的热点片段的标签发送给相应的用户群体的用户设备。
在服务器1获取到每个用户群体的热点片段的标签后，如果在服务器1中保存的注册信息中的用户观看视频内容时，服务器1可以将视频内容的热点片段的标签发送给观看视频内容相应的用户群体的用户设备。该步骤可以由数据发送模块12执行。
310、用户设备根据标签在视频内容的显示部分显示热点片段的标签。
例如用户设备要播放视频内容时，从服务器1可以接收到该视频内容的热点片段的标签。用户设备根据接收到的标签个性化呈现热点片段。
在一种可能的实现方式中，对于每个用户群体的热点片段，用户设备可以根据该用户群体对该热点片段评论的起止时间,在播放时间轴的该热点片段的起始时间处打上圆点，并根据起止时间在播放时间轴的热点片段区间以区分非热点片段的颜色标注，例如可以如图4所示，图4为根据表9展示的每个用户群体观看春节联欢晚会视频时的热点片段。
在另一种可能的实现方式，对于每个用户群体的热点片段，用户设备可以在视频显示区域中以列表的形式，按照该用户群体对该热点片段评论的起止时间以及关键词向用户群体展示该热点片段，同一个用户群体所被展示的热点片段可能不止一个。按照表9的举例，呈现给user Group1的热点片段列表如图5中的图(1)所示，呈现给user Group2的热点片段列表如图5中的图(2)所示，呈现给user Group3的热点片段列表如图5中的图(3)所示。
该步骤可以由上述呈现模块02执行。
这样一来，本申请实施例可以按照多个用户群体，提取和呈现个性化的热点片段，可以提高用户访问热点片段的准确度，同时，相对于现有技术中给所有用户呈现的为同一热点片段，本申请实施例可以提取和呈现出被掩盖的属于某些用户群体的热点片段。
下面再以每个用户群体对视频内容的操作信息为用户对播放器的历史操作信息为例进行说明。本申请实施例提供一种视频热点片段的提取方法，如图6所示，包括：
601、用户设备向服务器1发送用户的属性信息。
602、服务器1接收并存储用户的属性信息，并将用户的属性信息发送给服务器2。
603、服务器2根据用户的属性信息将用户分为多个用户群体。
步骤601-603的实现方式可以参见上述步骤301-303。
604、服务器1将从用户设备获取的播放器播放视频内容时，每个用户群体对播放器的历史操作信息发送给服务器2。
用户对播放器的操作信息可以分为：快进、向前拖动、快退、向后拖动等。如果用户对视频内容的某些视频片段进行快进或向前拖动操作，表示用户对视频片段不感兴趣，服务器1可以记录快进操作或向前拖动操作的动作名称、动作起始时间点、动作结束时间点以及该视频片段时长，并获取该快进操作或向前拖动操作的动作持续时间跨度，例如，用户快进了10s或向前拖动10s，则记为-10s，表示快进操作或向前拖动操作对视频片段的热度贡献值具有负的贡献。如果用户对视频内容的某些视频片段进行快退或向后拖动操作，表示用户对视频片段感兴趣，想重复观看，服务器1可以记录快退操作或向后拖动操作的动作名称、动作起始时间点、动作结束时间点以及该视频片段时长，并获取该快退操作或向后拖动操作的动作持续时间跨度，例如，用于快退了10或向后拖动10s，则记为+10s，表示快退操作或向后拖动操作对视频片段的热度贡献值具有正的贡献。
本申请的这一实施例仍然以播放器播放春节联欢晚会为例进行说明。对于观看春节联欢晚会这一视频内容的每个用户群体，服务器根据该用户群体中的每个用户对播放视频内容时的每种操作类型的起止时间获取每种操作类型的持续时间，例如表10为服务器1在预设时间段内记录的用户观看春节联欢晚会的各个视频片段时对播放器的历史操作信息。
表10用户观看春节联欢晚会时对播放器的历史操作信息
Figure PCTCN2018073852-appb-000013
Figure PCTCN2018073852-appb-000014
605、对于每个用户群体，服务器2根据该用户群体对播放器的历史操作信息获取该用户群体的热点片段的阈值。
服务器2可以根据不同的用户群体，对播放器的历史操作信息进行分组，一个用户不论对哪个视频片段进行了播放器的操作，该用户都会被划分至该用户所在的用户群体。例如ID的用户对春节联欢晚会视频中的Tfboys表演视频片段在10.11s时开始进行快进操作至12.11时结束操作，那么这条操作信息就会被划分至user Group1中，例如各用户群体的分组如表4所示，用户观看春节联欢晚会时对播放器的历史操作信息如表10所示，那么将对播放器的历史操作信息分组后的情况可以如表11所示。
表11对播放器的历史操作信息的分组
Figure PCTCN2018073852-appb-000015
Figure PCTCN2018073852-appb-000016
而后，根据每个用户群体中每个用户对播放器的操作信息获取该用户群体的热点片段的热度贡献阈值。由于播放视频片段时用户对播放器的不同操作信息能够反映出用户对该视频片段内容的喜好与否，因此，可以用播放视频片段时用户对播放器的不同操作信息来衡量视频片段的热度值。在本申请实施例中，每个用户的每种操作类型的热度贡献可以用热度贡献值的公式来计算。对于每个用户群体中的每个用户，每种操作类型的热度贡献值可以为操作类型的持续时间与操作类型的加权值的乘积，再与操作类型对应的视频片段时长的比值。
例如对于快进操作，其热度贡献值的公式可以表示为：Hot A(t A,T v)＝K A*t A/T v，Hot A表示快进操作的热度贡献值，t A表示快进时长，即快进这种操作类型的持续时间，T v表示对应的视频片段时长，K A为快进这类操作类型的加权值,范围可以为(0～1)。对于向前拖动操作，其热度贡献值的公式可以表示为：Hot B(t B,T v)＝K B*t B/T v，Hot B表示向前拖动操作的热度贡献值，t B表示向前拖动时长，即向前拖动这种操作类型的持续时间，T v表示对应视频片段时长，K B为向前拖动这类操作类型的加权值，由于向前拖动可以表示用户对视频内容的讨厌程度比快进更强烈，故K B≥K A，K B的范围可以为(0～1)。对于快退操作，其热度贡献值的公式可以表示为：Hot c(t c,T v)＝K c*t c/T v，Hot c表示快退操作的热度贡献值，t c表示快退时长，即快退这种操作类型的持续时间，T v表示对应视频片段时长，K c表示快退这类操作类型的加权值,范围(0～1)。对于向后拖动操作，其热度贡献值的公式可以表示为：Hot D(t D,T v)＝K D*t D/T v，Hot D表示向后拖动操作的热度贡献值，t D表示向后拖动时长，即向后拖动这种操作类型的持续时间，T v表示对应视频片段时长，K D为向后拖动这类操作类型的加权值,由于向后拖动可以表示用户对视频内容的喜欢程度比快退更强烈，故K D≥K C，K D的范围可以为(0～1)。
按照上述各操作类型的热度贡献值的计算方式，可以获取每个用户群体的总热度贡献值，这里将每个用户群体的总热度贡献值可以表示为
Figure PCTCN2018073852-appb-000017
即该用户群体对播放器操作的热度贡献值之和。其中U表示任一用户群体对播放器操作的集合，Hot i为Hot A、Hot B、Hot c、Hot D中的一种。而后，可以将用户群体的总热度贡献值与视频内容的视频片段的数量的比值，再与预设系数的乘积表示为该用户群体观看视频内容的热点片段的热度贡献阈值，即用户群体的热点片段的热度贡献阈值＝(用户群体的总热度贡献值/视频片段数)*C，C表示预设系数。
如果将上述公式中的C、K A、K B、t c、K D的取值均取为1，按照表11中的情况，那么user Group1的热点片段的阈值
＝(Hot A(-2,250)+Hot C(20,250)+Hot D(50,250)+Hot A(-10,300)+Hot B(-20,280))/3＝(-2*K A/250+20*K C/250+50*K D/250-10*K A/300-20*K B/280)/3＝0.056；
user Group2的热点片段的阈值
＝(Hot B(-30,250)+Hot D(40,300)+Hot C(10,300)+Hot D(35,300)+Hot C(30,300)+Hot A(-6,300)+Hot B(-30,280))/3
＝(-30*K B/250+40*K D/300+10*K C/300+35*K D/300+30*K C/300-6*K A/300-30*K B/280)/3＝0.045
user Group3的热点片段的阈值
＝(Hot A(-8,250)+Hot B(-40,300)+Hot D(40,280)+Hot C(30,280))/3
＝(-8*K A/250-40*K B/300+40*K D/280+30*K C/280)/3＝0.085
于是，每个用户群体的热点片段的热度贡献阈值可以如表12所示。
表12每个用户群体的热点片段的热度贡献阈值
Figure PCTCN2018073852-appb-000018
606、服务器2根据热度贡献阈值以及用户群体对对播放器的历史操作信息获取用户群体的热点片段。
如果某一用户群体对某一视频片段的热度贡献值大于该用户群体的热点片段的热度贡献阈值，可以确定该视频片段为该用户群体的热点片段。也就是说，对于每个用户群体，服务器获取用户群体对视频内容的各视频片段的热度贡献值的和，将热度贡献值的和大于热度贡献阈值的视频片段确定为用户群体的热点片段。
例如按照表12中的情况，在各权值取为1的情况下，user Group1对Tfboys表演的视频片段的总的热度贡献值
＝Hot A(-2,250)+Hot C(20,250)+Hot D(50,250)
＝-2*K A/250+20*K C/250+50*K D/250＝0.272
user Group1对周杰伦表演的视频片段的总的热度贡献值
＝HotA(-10,300)＝-10*KA/300＝-0.033
userGroup 1对宋祖英表演的视频片段总的热度贡献值
＝Hot B(-20,280)＝-20*K B/280＝-0.071
user Group2对Tfboys表演的视频片段的总的热度贡献值
＝Hot B(-30,250)＝-30*K B/250＝-0.12
user Group2对周杰伦表演的视频片段的总的热度贡献值
＝Hot D(40,300)+Hot C(10,300)+Hot D(35,300)+Hot C(30,300)+Hot A(-6,300)
＝40*K D/300+10*K C/300+35*K D/300+30*K C/300-6*K A/300＝0.363
userGroup2对宋祖英表演的视频片段总的热度贡献值
＝Hot B(-30,280)＝-30*K B/280＝-0.107
user Group3对Tfboys表演的视频片段的总的热度贡献值
＝Hot A(-8,250)＝-8*K A/250＝-0.032
user Group3对周杰伦表演的视频片段的总的热度贡献值
＝Hot B(-40,300)＝-40*K B/300＝-0.133
userGroup 3对宋祖英表演的视频片段总的热度贡献值
＝Hot D(40,280)+Hot C(30,280)＝40*K D/280+30*K C/280＝0.25
由于userGroup1对TFboys表演片段的总的热度贡献值为0.272，而userGroup1的热点片段的热度贡献阈值为0.056，因为热度贡献值0.272>热度贡献阈值0.056，故TFboys表演片段属于userGroup1的热点片段。按照这种方式，每个用户群体对应的热点片段可以如表13所示。
表13每个用户群体的热点片段
Figure PCTCN2018073852-appb-000019
Figure PCTCN2018073852-appb-000020
607、对于每个用户群体的热点片段，服务器2将该用户群体在该热点片段播放时对播放器操作的各时间点中的最早时间点和最晚时间点确定为热点片段的标签。
对于每个用户群体的热点片段，标签中的最早时间点为该用户群体对该热点片段的操作中在时间上最先一次操作的时间点，最晚时间点为该用户群体对该热点片段的操作中在时间上最后一次操作的时间点。
按照表13中的情况，例如对于userGroup1的热点片段，用户001的动作起始时间点10.11s为最早时间点，用户002的动作起始时间点105.45s为最晚时间点，那么userGroup1的热点片段的标签为(10.11s，105.45s)。对于userGroup2的热点片段，用于007的动作结束时间点310.54s为最早时间点，用户011的动作结束时间点513.49s为最晚时间点，那么userGroup2的热点片段的标签为(310.54s，513.49s)。对于userGroup3的热点片段，用于015的动作结束时间点740.53为最早时间点，用户016的动作起始时间点850.25为最晚时间点，那么userGroup3的热点片段的标签为(740.53，850.25)。
608、服务器1接收服务器2发送的对应于每个用户群体的热点片段的标签并保存，并将对应于每个用户群体的热点片段的标签发送给相应的用户群体的用户设备。
在服务器1获取到每个用户群体观看视频内容时的热点片段的标签后，如果在服务器1中保存的注册信息中的用户观看视频内容时，服务器1可以将视频内容的热点片段的标签发送给观看视频内容相应的用户群体的用户设备。
609、用户设备根据标签在视频内容的显示部分显示热点片段的标签。
在一种可能的实现方式中，对于每个用户群体，用户设备可以根据该用户群体对播放器操作的各时间点中的最早时间点和最晚时间点,在播放时间轴的热点片段的最早时间点处打上圆点，并根据最早时间点和最晚时间点的热点片段区间以区分非热点片段的颜色标注，例如可以如图7所示，图7为根据表13展示的每个用户群体观看春节联欢晚会视频时的热点片段。
在另一种可能的实现方式中，对于每个用户群体，用户设备可以在视频显示区域中以列表的形式，按照该用户群体对播放器操作的各时间点中的最早时间点和最晚时间点向用户群体展示热点片段，同一个用户群体所被展示的热点片段可能不止一个。按照表13的举例，呈现给user Group1的热点片段列表如图8中的图(1)所示，呈现给user Group2的热点片段列表如图8中的图(2)所示，呈现给user Group3的热点片段列表如图8中的图(3)所示。
这样一来，本申请实施例可以按照每个用户群体，为每个用户群体提取和呈现个性化的热点片段，可以提高用户访问热点片段的准确度，同时，相对于现有技术中给所有用户呈现的为同一热点片段，本申请实施例可以提取和呈现出被掩盖的属于某些用户群体的热点片段。
上述主要从各个网元之间交互的角度对本发明实施例提供的方案进行了介绍。可以理解的是，各个网元，例如服务器、用户设备等为了实现上述功能，其包含了执行各个功能相应的硬件结构和/或软件模块。本领域技术人员应该很容易意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，本发明能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。；
本发明实施例可以根据上述方法示例对服务器、用户设备等进行功能模块的划分，例如，可以对应各个功能划分各个功能模块，也可以将两个或两个以上的功能集成在一个处理模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。需要说明的是，本发明实施例中对模块的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。
在采用对应各个功能划分各个功能模块的情况下，如果服务器1和服务器2的功能集群在一个服务器中，图9示出了上述实施例中所涉及的服务器的一种可能的结构示意图，服务器90包括：分类单元901，获取单元902，发送单元903以及接收单元904。分类单元901用于支持服务器执行图3中的过程303，图6中的过程603，获取单元303用于支持服务器执行图3中的过程304、305、306，图6中的过程605、606、607；发送单元903用于执行图3中的过程307、309，图6中的过程604，接收单元904用于支持服务器执行图3中的过程302，图6中的过程602、608。其中，上述方法实施例涉及的各步骤的所有相关内容均可以援引到对应功能模块的功能描述，在此不再赘述。
在采用集成的单元的情况下，上述实施例中所涉及的服务器1和服务器2的一种可能的结构示意图可以如图2所示。例如，数据发送模块12和历史数据获取模块21可以用于支持服务器1执行图3中的过程302，以及图6中的步骤602和604，用户分类模块22可以用于支持服务器2执行图3中的过程303以及图6中的步骤603，热点片段获取模块23可以执行图3中的过程304-306，以及图6中的步骤605和606，标签提取模块24可以执行图3中的 过程307以及图6中的步骤607，数据发送模块25可以执行图3中的过程308，以及图6中的步骤608，数据发送模块12可以执行图3中的过程309,以及图6中的步骤608。服务器1和服务器2还可以包括存储模块(图2中未示出)，存储模块用于存储服务器1和服务器2的程序代码和数据。
其中，用户分类模块22、热点片段提取模块23以及标签提取模块24可以是处理器或控制器，例如可以是中央处理器(Central Processing Unit，CPU)，通用处理器，数字信号处理器(Digital Signal Processor，DSP)，专用集成电路(Application-Specific Integrated Circuit，ASIC)，现场可编程门阵列(Field Programmable Gate Array，FPGA)或者其他可编程逻辑器件、晶体管逻辑器件、硬件部件或者其任意组合。其可以实现或执行结合本发明公开内容所描述的各种示例性的逻辑方框，模块和电路。所述处理器也可以是实现计算功能的组合，例如包含一个或多个微处理器组合，DSP和微处理器的组合等等。历史数据获取模块21、数据发送光模块25、数据发送模块12以及数据接收模块11可以是收发器、收发电路或通信接口等。数据存储模块11可以是存储器。
当用户分类模块22、热点片段提取模块23以及标签提取模块24为处理器，历史数据获取模块21、数据发送光模块25、数据发送模块12以及数据接收模块11为收发器，数据存储模块11为存储器时，如果服务器1和服务器2的功能集群在一个服务器中，本发明实施例所涉及的服务器可以为图10所示的服务器。
参阅图10所示，该服务器10包括：处理器1012、收发器1013、存储器1011以及总线1014。其中，收发器1013、处理器1012以及存储器1011通过总线1014相互连接；总线1014可以是外设部件互连标准(Peripheral Component Interconnect，PCI)总线或扩展工业标准结构(Extended Industry Standard Architecture，EISA)总线等。所述总线可以分为地址总线、数据总线、控制总线等。为便于表示，图10中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
在采用对应各个功能划分各个功能模块的情况下，图11示出了上述实施例中所涉及的用户设备的一种可能的结构示意图，用户设备111包括：发送单元1111、接收单元1112和显示单元1113。发送单元1111用于支持用户设备执行图3中的过程301、图6中的过程601，接收单元1112用于支持用户设备执行图3中的过程309，图6中的过程608；显示单元1113用于支持用户设备执行图3中的过程310，图6中的过程609。其中，上述方法实施例涉及的各步骤的所有相关内容均可以援引到对应功能模块的功能描述，在此不再赘述。
在采用集成的单元的情况下，图2示出了上述实施例中所涉及的用户设备的一种可能的结构示意图。用户设备0包括：数据收集/发送模块01和呈现模块02。例如，数据收集/发送模块01用于支持用户设备执行图3中的过程301、图6中的过程601，呈现模块02用户执行图3中的过程310，图6中的过程609。数据收集/发送模块01用于支持用户设备与其他网络实体的通信，例如与图2、图3、图6中示出的功能模块或网络实体之间的通信。用户设备0还可以包括存储模块03和处理模块04(图中未示出)，存储模块03用于存储用户设备的程序代码和数据，处理模块04用于对用户设备的动作进行控制管理。
其中，处理模块04可以是处理器或控制器，例如可以是中央处理器CPU，通用处理器，数字信号处理器DSP，专用集成电路ASIC，现场可编程门阵列FPGA或者其他可编程逻辑器件、晶体管逻辑器件、硬件部件或者其任意组合。其可以实现或执行结合本发明 公开内容所描述的各种示例性的逻辑方框，模块和电路。所述处理器也可以是实现计算功能的组合，例如包含一个或多个微处理器组合，DSP和微处理器的组合等等。数据收集/发送模块01可以是收发器、收发电路或通信接口等。存储模块03可以是存储器，呈现模块02可以是显示器或显示屏等。
当处理模块04为处理器，数据收集/发送模块01为收发器，存储模块03为存储器，呈现模块为显示器时，本发明实施例所涉及的用户设备可以为图12所示的用户设备。
参阅图12所示，该用户设备122包括：处理器1212、收发器1213、存储器1211、显示器1215以及总线1214。其中，收发器1213、处理器1212、显示器1215以及存储器1211通过总线1214相互连接；总线1214可以是外设部件互连标准PCI总线或扩展工业标准结构EISA总线等。所述总线可以分为地址总线、数据总线、控制总线等。为便于表示，图12中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
结合本发明公开内容所描述的方法或者算法的步骤可以硬件的方式来实现，也可以是由处理器执行软件指令的方式来实现。软件指令可以由相应的软件模块组成，软件模块可以被存放于随机存取存储器(Random Access Memory，RAM)、闪存、只读存储器(Read Only Memory，ROM)、可擦除可编程只读存储器(Erasable Programmable ROM，EPROM)、电可擦可编程只读存储器(Electrically EPROM，EEPROM)、寄存器、硬盘、移动硬盘、只读光盘(CD-ROM)或者本领域熟知的任何其它形式的存储介质中。一种示例性的存储介质耦合至处理器，从而使处理器能够从该存储介质读取信息，且可向该存储介质写入信息。当然，存储介质也可以是处理器的组成部分。处理器和存储介质可以位于ASIC中。另外，该ASIC可以位于核心网接口设备中。当然，处理器和存储介质也可以作为分立组件存在于核心网接口设备中。
本领域技术人员应该可以意识到，在上述一个或多个示例中，本发明所描述的功能可以用硬件、软件、固件或它们的任意组合来实现。当使用软件实现时，可以将这些功能存储在计算机可读介质中或者作为计算机可读介质上的一个或多个指令或代码进行传输。计算机可读介质包括计算机存储介质和通信介质，其中通信介质包括便于从一个地方向另一个地方传送计算机程序的任何介质。存储介质可以是通用或专用计算机能够存取的任何可用介质。
以上所述的具体实施方式，对本发明的目的、技术方案和有益效果进行了进一步详细说明，所应理解的是，以上所述仅为本发明的具体实施方式而已，并不用于限定本发明的保护范围，凡在本发明的技术方案的基础之上，所做的任何修改、等同替换、改进等，均应包括在本发明的保护范围之内。

Claims (20)

  1. 一种视频热点片段的提取方法，其特征在于，包括：
    服务器根据用户的属性信息将所述用户分为多个用户群体；
    所述服务器根据所述多个用户群体中每个用户群体在观看视频内容时的操作信息，获取所述每个用户群体观看所述视频内容的热点片段；
    所述服务器根据所述每个用户群体观看所述视频内容的热点片段获取对应于所述每个用户群体的热点片段的标签，并将所述对应于所述每个用户群体的热点片段的标签发送给相应的用户群体的用户设备。
  2. 根据权利要求1所述的方法，其特征在于，所述服务器根据用户的属性信息将所述用户分为多个用户群体包括：
    所述服务器根据聚类算法对所述用户的属性信息进行分析，以将所述用户分为所述多个用户群体；
    所述服务器根据聚类算法对所述用户的属性信息进行分析，以将所述用户分为所述多个用户群体包括：
    所述服务器根据所述用户的属性信息构建所述用户的属性向量；
    所述服务器获取所述用户的属性向量与聚类中心的欧氏距离；
    所述服务器根据所述欧氏距离将所述用户划分至欧氏距离最近的聚类中心所在的簇，每个簇对应一个用户群体。
  3. 根据权利要求1或2所述的方法，其特征在于，所述服务器根据所述多个用户群体中每个用户群体在观看视频内容时的操作信息，获取所述每个用户群体观看所述视频内容的热点片段包括：
    对于所述每个用户群体，所述服务器根据该用户群体的操作信息获取该用户群体的热点片段的弹幕评论阈值或热度贡献阈值；
    对于所述每个用户群体，所述服务器根据所述弹幕评论阈值以及该用户群体的操作信息获取该用户群体的热点片段，或所述服务器根据所述热度贡献阈值以及该用户群体的操作信息获取该用户群体的热点片段。
  4. 根据权利要求3所述的方法，其特征在于，所述对于所述每个用户群体，所述服务器根据该用户群体的操作信息获取该用户群体的热点片段的弹幕评论阈值包括：
    对于所述每个用户群体，所述服务器获取该用户群体对所述视频内容的历史弹幕评论的数量与所述视频内容的视频片段的数量的比值，再获取所述比值与预设系数的乘积，所述乘积为该用户群体的热点片段的弹幕评论阈值；
    所述服务器根据所述弹幕评论阈值以及该用户群体的操作信息获取该用户群体的热点片段包括：
    对于所述每个用户群体，所述服务器确定该用户群体对所述视频内容的任一视频片段的弹幕评论数大于所述弹幕评论阈值时，将所述任一视频片段确定为所述用户群体的热点片段。
  5. 根据权利要求4所述的方法，其特征在于，所述服务器根据所述每个用户群体观看所述视频内容的热点片段获取对应于所述每个用户群体的热点片段的标签包括：
    对于所述每个用户群体的热点片段，所述服务器构建该热点片段的关键词词表，所述关键词词表包括该热点片段的弹幕评论的关键词；
    对于所述每个用户群体的热点片段，所述服务器统计所述关键词词表中各词的词频，确定词频最高的关键词，将所述词频最高的关键词以及该用户群体对该热点片段评论的起止时间确定为该热点片段的标签。
  6. 根据权利要求3所述的方法，其特征在于，所述对于所述每个用户群体，所述服务器根据该用户群体的操作信息获取该用户群体的热点片段的热度贡献阈值包括：
    对于所述每个用户群体，所述服务器获取每个用户的每种操作类型的持续时间，所述操作类型包括快进、快退、向前拖动以及向后拖动；
    对于所述每个用户群体中的每个用户，所述服务器获取该用户的每种操作类型的热度贡献值，所述热度贡献值为该种操作类型的持续时间与该种操作类型的加权值的乘积，再与该种操作类型对应的视频片段时长的比值；
    对于所述每个用户群体，所述服务器获取该用户群体的热点片段的热度贡献阈值，所述热度贡献阈值为该用户群体的总热度贡献值与所述视频内容的视频片段的数量的比值，再与预设系数的乘积；
    对于所述每个用户群体，所述服务器根据所述热度贡献阈值以及该用户群体的操作信息获取该用户群体的热点片段包括：
    对于所述每个用户群体，所述服务器获取该用户群体对所述视频内容的各视频片段的热度贡献值的和，将所述热度贡献值的和大于所述热度贡献阈值的视频片段确定为该用户群体的热点片段。
  7. 根据权利要求6所述的方法，其特征在于，所述服务器根据所述每个用户群体观看所述视频内容的热点片段获取对应于所述每个用户群体的热点片段的标签包括：
    对于所述每个用户群体的热点片段，所述服务器将该用户群体在该热点片段播放时对所述播放器操作的各时间点中的最早时间点和最晚时间点确定为所述热点片段的标签。
  8. 根据权利要求1-7任一项所述的方法，其特征在于，在所述服务器根据观看视频内容的用户的属性信息将所述用户分为不同的用户群体之前，所述方法还包括：
    所述服务器接收用户设备发送的所述用户的属性信息。
  9. 一种视频热点片段的提取方法，其特征在于，包括：
    用户设备向服务器发送用户的属性信息；
    所述用户设备接收所述服务器发送的视频内容的热点片段的标签，根据所述标签在所述视频内容的显示部分显示所述热点片段的标签。
  10. 根据权利要求9所述的方法，其特征在于，所述标签包括所述热点片段的关键词以及所述用户所属的用户群体对所述热点片段评论的起止时间，或所述标签包括所述用户所属的用户群体在所述热点片段播放时对所述播放器操作的各时间点中的最早时间点和最晚时间点。
  11. 一种服务器，其特征在于，包括：
    分类单元，用于根据用户的属性信息将所述用户分为多个用户群体；
    获取单元，用于根据所述分类单元划分的所述多个用户群体中每个用户群体在观看视频内容时的操作信息，获取所述每个用户群体观看所述视频内容的热点片段；
    所述获取单元，还用于根据所述获取单元获取的所述每个用户群体观看所述视频内容的热点片段获取对应于所述每个用户群体的热点片段的标签；
    发送单元，用于将所述获取单元获取的所述对应于所述每个用户群体的热点片段的标签 发送给相应的用户群体的用户设备。
  12. 根据权利要求11所述的服务器，其特征在于，所述分类单元用于：根据聚类算法对所述用户的属性信息进行分析，以将所述用户分为所述多个用户群体；
    所述分类单元具体用于：
    根据所述用户的属性信息构建所述用户的属性向量；
    获取所述用户的属性向量与聚类中心的欧氏距离；
    根据所述欧氏距离将所述用户划分至欧氏距离最近的聚类中心所在的簇，每个簇对应一个用户群体。
  13. 根据权利要求11或12所述的服务器，其特征在于，所述获取单元用于：
    对于所述每个用户群体，根据该用户群体的操作信息获取该用户群体的热点片段的弹幕评论阈值或热度贡献阈值；
    对于所述每个用户群体，根据所述弹幕评论阈值以及该用户群体的操作信息获取该用户群体的热点片段，或根据所述热度贡献阈值以及该用户群体的操作信息获取该用户群体的热点片段。
  14. 根据权利要求13所述的服务器，其特征在于，所述获取单元用于：
    对于所述每个用户群体，获取该用户群体对所述视频内容的历史弹幕评论的数量与所述视频内容的视频片段的数量的比值，再获取所述比值与预设系数的乘积，所述乘积为该用户群体的热点片段的弹幕评论阈值；
    对于所述每个用户群体，确定该用户群体对所述视频内容的任一视频片段的弹幕评论数大于所述弹幕评论阈值时，将所述任一视频片段确定为所述用户群体的热点片段。
  15. 根据权利要求14所述的服务器，其特征在于，所述获取单元用于：
    对于所述每个用户群体的热点片段，构建该热点片段的关键词词表，所述关键词词表包括该热点片段的弹幕评论的关键词；
    对于所述每个用户群体的热点片段，统计所述关键词词表中各词的词频，确定词频最高的关键词，将所述词频最高的关键词以及该用户群体对该热点片段评论的起止时间确定为该热点片段的标签。
  16. 根据权利要求13所述的服务器，其特征在于，所述获取单元用于：
    对于所述每个用户群体，获取每个用户的每种操作类型的持续时间，所述操作类型包括快进、快退、向前拖动以及向后拖动；
    对于所述每个用户群体中的每个用户，获取该用户的每种操作类型的热度贡献值，所述热度贡献值为该种操作类型的持续时间与该种操作类型的加权值的乘积，再与该种操作类型对应的视频片段时长的比值；
    对于所述每个用户群体，获取该用户群体的热点片段的热度贡献阈值，所述热度贡献阈值为该用户群体的总热度贡献值与所述视频内容的视频片段的数量的比值，再与预设系数的乘积；
    对于所述每个用户群体，获取该用户群体对所述视频内容的各视频片段的热度贡献值的和，将所述热度贡献值的和大于所述热度贡献阈值的视频片段确定为该用户群体的热点片段。
  17. 根据权利要求16所述的服务器，其特征在于，所述获取单元用于：
    对于所述每个用户群体的热点片段，将该用户群体在该热点片段播放时对所述播放器操 作的各时间点中的最早时间点和最晚时间点确定为所述热点片段的标签。
  18. 根据权利要求11-17任一项所述的服务器，其特征在于，还包括接收单元，用于接收用户设备发送的所述用户的属性信息。
  19. 一种用户设备，其特征在于，包括：
    发送单元，用于向服务器发送用户的属性信息；
    接收单元，用于接收所述服务器发送的视频内容的热点片段的标签；
    显示单元，用于根据所述标签在所述视频内容的显示部分显示所述热点片段的标签。
  20. 根据权利要求19所述的用户设备，其特征在于，所述标签包括所述热点片段的关键词以及所述用户所属的用户群体对所述热点片段评论的起止时间，或所述标签包括所述用户所属的用户群体在所述热点片段播放时对所述播放器操作的各时间点中的最早时间点和最晚时间点。
PCT/CN2018/073852 2017-03-21 2018-01-23 一种视频热点片段提取方法、用户设备和服务器 WO2018171325A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US16/495,175 US11265624B2 (en) 2017-03-21 2018-01-23 Hot video clip extraction method, user equipment, and server

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710171580.4A CN107105318B (zh) 2017-03-21 2017-03-21 一种视频热点片段提取方法、用户设备和服务器
CN201710171580.4 2017-03-21

Publications (1)

Publication Number Publication Date
WO2018171325A1 true WO2018171325A1 (zh) 2018-09-27

Family

ID=59675408

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/073852 WO2018171325A1 (zh) 2017-03-21 2018-01-23 一种视频热点片段提取方法、用户设备和服务器

Country Status (3)

Country Link
US (1) US11265624B2 (zh)
CN (1) CN107105318B (zh)
WO (1) WO2018171325A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111447505A (zh) * 2020-03-09 2020-07-24 咪咕文化科技有限公司 视频剪辑方法、网络设备及计算机可读存储介质
WO2021164369A1 (zh) * 2020-02-21 2021-08-26 北京百度网讯科技有限公司 提取视频中热点片段的方法以及装置

Families Citing this family (38)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107105318B (zh) 2017-03-21 2021-01-29 华为技术有限公司 一种视频热点片段提取方法、用户设备和服务器
CN110020107A (zh) * 2017-09-08 2019-07-16 北京京东尚科信息技术有限公司 页面展示方法及系统
CN107608792B (zh) * 2017-09-12 2020-09-01 中国联合网络通信集团有限公司 资源调度方法与装置
CN109547859B (zh) * 2017-09-21 2021-12-07 腾讯科技（深圳）有限公司 视频片段的确定方法和装置
CN107809674A (zh) * 2017-09-30 2018-03-16 努比亚技术有限公司 一种基于视频的用户反应获取、处理方法、终端及服务器
CN109729435A (zh) * 2017-10-27 2019-05-07 优酷网络技术（北京）有限公司 视频片段的提取方法及装置
CN108156528A (zh) * 2017-12-18 2018-06-12 北京奇艺世纪科技有限公司 一种视频处理方法及装置
CN108174299B (zh) * 2017-12-28 2021-07-27 北京安云世纪科技有限公司 一种视频的点评数据加载方法及装置
CN108174306B (zh) * 2017-12-28 2021-03-30 北京安云世纪科技有限公司 一种多媒体数据加载方法及终端
CN108307230B (zh) * 2018-02-07 2021-01-22 北京奇艺世纪科技有限公司 一种视频精彩片段的提取方法及装置
CN110245343B (zh) * 2018-03-07 2022-09-09 阿里巴巴（中国）有限公司 弹幕分析方法及装置
CN108959450B (zh) * 2018-06-14 2022-08-26 腾讯科技（深圳）有限公司 一种热门评论确定系统、方法、装置和可读介质
CN109040773A (zh) * 2018-07-10 2018-12-18 武汉斗鱼网络科技有限公司 一种视频改进方法、装置、设备及介质
CN109040796A (zh) * 2018-08-17 2018-12-18 深圳市迅雷网络技术有限公司 内容片段热度的计算方法、影音内容的播放方法及装置
CN109189957B (zh) * 2018-08-30 2022-05-31 维沃移动通信有限公司 一种媒体数据的处理方法及设备
CN109587568A (zh) * 2018-11-01 2019-04-05 北京奇艺世纪科技有限公司 视频播放方法、装置、计算机可读存储介质
CN109933691B (zh) * 2019-02-11 2023-06-09 北京百度网讯科技有限公司 用于内容检索的方法、装置、设备和存储介质
CN110198482B (zh) * 2019-04-11 2022-05-20 华东理工大学 一种视频重点桥段标注方法、终端及存储介质
CN112073817B (zh) * 2019-06-10 2022-08-30 腾讯科技（深圳）有限公司 媒体文件的播放控制方法、装置、电子设备及存储介质
CN110222231B (zh) * 2019-06-11 2022-10-18 成都澳海川科技有限公司 一种视频片段的热度预测方法
CN110751219A (zh) * 2019-10-23 2020-02-04 郑州阿帕斯科技有限公司 一种内容发送方法和装置
CN110968682A (zh) * 2019-11-29 2020-04-07 北京达佳互联信息技术有限公司 评论信息发布方法、装置、客户端、服务器和系统
CN111491189A (zh) * 2019-12-23 2020-08-04 高秀丽 主播计酬信息录入平台
CN111147915B (zh) * 2019-12-30 2022-10-04 咪咕视讯科技有限公司 视频加工方法、服务器和计算机可读存储介质
KR102487794B1 (ko) * 2020-02-21 2023-01-13 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. 비디오 중의 핫스팟 세그먼트를 추출하는 방법, 장치, 전자 기기, 저장 매체, 및 컴퓨터 프로그램 제품
CN111641868A (zh) * 2020-05-27 2020-09-08 维沃移动通信有限公司 预览视频生成方法、装置及电子设备
CN111711839A (zh) * 2020-05-27 2020-09-25 杭州云端文化创意有限公司 一种基于用户互动数值的影片精选展示方法
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
CN111782323B (zh) * 2020-06-29 2021-06-29 掌阅科技股份有限公司 弹幕获取方法、计算设备及计算机存储介质
CN112423110A (zh) * 2020-08-04 2021-02-26 上海哔哩哔哩科技有限公司 直播视频数据生成方法、装置及直播视频播放方法、装置
CN113055741B (zh) * 2020-12-31 2023-05-30 科大讯飞股份有限公司 视频摘要的生成方法、电子设备及计算机可读存储介质
CN112949703A (zh) * 2021-02-23 2021-06-11 广州市百果园信息技术有限公司 视频召回方法、装置及电子设备
CN112969100B (zh) * 2021-03-24 2023-06-30 西安闻泰信息技术有限公司 视频播放控制方法、装置、设备和介质
US11881233B2 (en) * 2021-04-08 2024-01-23 Rovi Guides, Inc. Methods and systems for generating meme content
CN113207014B (zh) * 2021-04-29 2023-05-12 北京百度网讯科技有限公司 直播热点确定方法、装置、电子设备以及存储介质
CN115834927A (zh) * 2021-09-17 2023-03-21 上海哔哩哔哩科技有限公司 弹幕处理方法及装置
WO2023197204A1 (en) * 2022-04-13 2023-10-19 Comcast Cable Communications, Llc Managing transmission resources
CN117014687B (zh) * 2023-09-28 2023-12-08 北京小糖科技有限责任公司 基于用户播放画像的视频定位播放方法、装置

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140189540A1 (en) * 2012-12-31 2014-07-03 DISH Digital L.L.C. Methods and apparatus for providing social viewing of media content
CN104462376A (zh) * 2014-12-09 2015-03-25 北京百度网讯科技有限公司 用于弹幕媒体的信息提供方法及装置
CN104936035A (zh) * 2015-06-19 2015-09-23 腾讯科技（北京）有限公司 一种弹幕处理方法及系统
CN105516821A (zh) * 2015-12-14 2016-04-20 广州弹幕网络科技有限公司 弹幕筛选的方法及装置
CN105847993A (zh) * 2016-04-19 2016-08-10 乐视控股（北京）有限公司 一种分享视频片段的方法及装置
CN106028161A (zh) * 2016-04-29 2016-10-12 乐视控股（北京）有限公司 一种弹幕的生成、呈现方法及其装置、服务器、客户端
CN107105318A (zh) * 2017-03-21 2017-08-29 华为技术有限公司 一种视频热点片段提取方法、用户设备和服务器

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8191097B1 (en) * 1999-04-01 2012-05-29 Comcast Ip Holdings I, Llc Method and apparatus for hierarchical distribution of video content for an interactive information distribution system
JP3663362B2 (ja) * 2001-03-30 2005-06-22 インターナショナル・ビジネス・マシーンズ・コーポレーション インデックス生成装置
US7532607B1 (en) * 2004-11-04 2009-05-12 At&T Intellectual Property Ii, L.P. Ad-hoc IP closed user group networks
US8549497B2 (en) * 2008-05-05 2013-10-01 University Of New Brunswick High-level hypermedia synthesis for adaptive web
CN102487456B (zh) 2009-11-30 2015-06-17 国际商业机器公司 用于提供网络视频访问热度的方法和装置
CN101901619B (zh) * 2010-07-16 2012-10-17 复旦大学 一种基于视频内容缩影的增强用户体验的视频播放器
US9317188B2 (en) * 2013-03-15 2016-04-19 Arris Enterprises, Inc. Devices and methods for providing navigation images associated with adaptive bit rate video content
CN104951479A (zh) * 2014-03-31 2015-09-30 小米科技有限责任公司 视频内容探测方法及装置
CN104410920B (zh) * 2014-12-31 2015-12-30 合一网络技术(北京)有限公司 基于视频分段播放量进行精彩片段标注的方法
CN104869468A (zh) * 2015-04-22 2015-08-26 腾讯科技（北京）有限公司 一种显示弹幕信息的方法和装置
CN104994425B (zh) 2015-06-30 2018-11-23 北京奇艺世纪科技有限公司 一种视频标识方法和装置
US20170169857A1 (en) * 2015-12-15 2017-06-15 Le Holdings (Beijing) Co., Ltd. Method and Electronic Device for Video Play
CN105828116A (zh) * 2016-04-29 2016-08-03 乐视控股（北京）有限公司 广告推送方法及装置
CN106446052A (zh) * 2016-08-31 2017-02-22 北京魔力互动科技有限公司 一种基于用户集合的视频点播节目推荐方法
CN106484858B (zh) * 2016-10-09 2019-12-06 腾讯科技（北京）有限公司 热点内容推送方法和装置
US10390077B2 (en) * 2017-03-15 2019-08-20 The Directv Group, Inc. Collective determination of interesting portions of a media presentation, media tagging and jump playback

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140189540A1 (en) * 2012-12-31 2014-07-03 DISH Digital L.L.C. Methods and apparatus for providing social viewing of media content
CN104462376A (zh) * 2014-12-09 2015-03-25 北京百度网讯科技有限公司 用于弹幕媒体的信息提供方法及装置
CN104936035A (zh) * 2015-06-19 2015-09-23 腾讯科技（北京）有限公司 一种弹幕处理方法及系统
CN105516821A (zh) * 2015-12-14 2016-04-20 广州弹幕网络科技有限公司 弹幕筛选的方法及装置
CN105847993A (zh) * 2016-04-19 2016-08-10 乐视控股（北京）有限公司 一种分享视频片段的方法及装置
CN106028161A (zh) * 2016-04-29 2016-10-12 乐视控股（北京）有限公司 一种弹幕的生成、呈现方法及其装置、服务器、客户端
CN107105318A (zh) * 2017-03-21 2017-08-29 华为技术有限公司 一种视频热点片段提取方法、用户设备和服务器

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021164369A1 (zh) * 2020-02-21 2021-08-26 北京百度网讯科技有限公司 提取视频中热点片段的方法以及装置
EP3890294A4 (en) * 2020-02-21 2021-12-29 Beijing Baidu Netcom Science And Technology Co. Ltd. Method and apparatus for extracting hotspot segment from video
CN111447505A (zh) * 2020-03-09 2020-07-24 咪咕文化科技有限公司 视频剪辑方法、网络设备及计算机可读存储介质
CN111447505B (zh) * 2020-03-09 2022-05-31 咪咕文化科技有限公司 视频剪辑方法、网络设备及计算机可读存储介质

Also Published As

Publication number Publication date
US11265624B2 (en) 2022-03-01
CN107105318B (zh) 2021-01-29
CN107105318A (zh) 2017-08-29
US20210120319A1 (en) 2021-04-22

Similar Documents

Publication Publication Date Title
WO2018171325A1 (zh) 一种视频热点片段提取方法、用户设备和服务器
US11153653B2 (en) Resource recommendation method, device, apparatus and computer readable storage medium
CN107888950B (zh) 一种推荐视频的方法和系统
US10650009B2 (en) Generating news headlines on online social networks
CN104469508B (zh) 基于弹幕信息内容进行视频定位的方法、服务器和系统
US20180190002A1 (en) Automatic video segment selection method and apparatus
WO2019227560A1 (zh) 信息推荐方法、装置、系统、设备及可读存储介质
JP6334696B2 (ja) ハッシュタグおよびコンテンツ提示
WO2018036272A1 (zh) 新闻内容的推送方法、电子装置及计算机可读存储介质
US8583685B2 (en) Determination of category information using multiple stages
WO2016091044A1 (zh) 一种热词推荐方法、装置、系统、设备和计算机存储介质
WO2023051102A1 (zh) 视频推荐方法、装置、设备及介质
WO2017076038A1 (zh) 搜索推荐方法及装置
US20140095308A1 (en) Advertisement distribution apparatus and advertisement distribution method
CN104537000B (zh) 一种用于推送信息的方法和装置
WO2013177372A2 (en) Methods and systems for identifying new computers and providing matching services
US20160210367A1 (en) Transition event detection
CN109241242A (zh) 一种直播间话题推荐方法、装置、服务器及存储介质
CN109168047A (zh) 视频推荐方法、装置、服务器及存储介质
US9436766B1 (en) Clustering of documents for providing content
JP2016206722A (ja) 作成装置、作成方法及び作成プログラム
WO2017156994A1 (zh) 多媒体资源的质量评估方法和装置
WO2018161677A1 (zh) 一种推送消息的方法、装置及存储介质
CN116450881B (zh) 基于用户偏好推荐兴趣分段标签的方法、装置及电子设备
CN109509014B (zh) 一种媒体信息的投放方法和装置

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: 18770837

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18770837

Country of ref document: EP

Kind code of ref document: A1