WO2019057034A1 - 视频片段的确定方法、装置、存储介质及电子装置 - Google Patents

视频片段的确定方法、装置、存储介质及电子装置 Download PDF

Info

Publication number
WO2019057034A1
WO2019057034A1 PCT/CN2018/106262 CN2018106262W WO2019057034A1 WO 2019057034 A1 WO2019057034 A1 WO 2019057034A1 CN 2018106262 W CN2018106262 W CN 2018106262W WO 2019057034 A1 WO2019057034 A1 WO 2019057034A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
video
playing
period
segment
Prior art date
Application number
PCT/CN2018/106262
Other languages
English (en)
French (fr)
Inventor
李钟伟
Original Assignee
腾讯科技（深圳）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 腾讯科技（深圳）有限公司 filed Critical 腾讯科技（深圳）有限公司
Publication of WO2019057034A1 publication Critical patent/WO2019057034A1/zh
Priority to US16/802,318 priority Critical patent/US11363353B2/en

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]
    • H04N21/40—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
    • H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
    • H04N21/47214—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for content reservation or setting reminders; for requesting event notification, e.g. of sport results or stock market
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/49—Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
    • 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
    • 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
    • H04N21/26603—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 for automatically generating descriptors from content, e.g. when it is not made available by its provider, using content analysis techniques
    • 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
    • H04N21/432—Content retrieval operation from a local storage medium, e.g. hard-disk
    • H04N21/4325—Content retrieval operation from a local storage medium, e.g. hard-disk by playing back content from the storage medium
    • 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
    • H04N21/435—Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
    • 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
    • H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
    • 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
    • H04N21/44224—Monitoring of user activity on external systems, e.g. Internet browsing
    • 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
    • H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
    • H04N21/47205—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for manipulating displayed content, e.g. interacting with MPEG-4 objects, editing locally
    • 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
    • H04N21/84—Generation or processing of descriptive data, e.g. content descriptors
    • 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
    • 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

Definitions

  • the present application relates to the field of the Internet, and in particular, to a method, an apparatus, a storage medium, and an electronic device for determining a video segment.
  • OTT is an abbreviation of “Over The Top”, which means to provide users with various application services through the Internet.
  • This application is different from the communication service provided by the current carrier. It uses the operator's network, and the service can be used by the operator. Provided by a third party.
  • Step 11 After the video editor receives the video content, the video content is completely viewed first;
  • Step 12 The editor determines, according to personal experience, which part of the video segment may trigger a hot topic (ie, determines a required video segment), and manually marks the segment location (corresponding video duration position);
  • Step 13 the editor manually records the marked hot spot location information into the video media asset system, and the system can provide a service for reading the corresponding hotspot location according to the video ID (ie, VID);
  • step 14 according to the needs of the business scenario, the annotation information is displayed when the video is played.
  • the embodiment of the present application provides a method, an apparatus, a storage medium, and an electronic device for determining a video segment, so as to at least solve the technical problem that the efficiency of determining a video segment required in a video is low in the related art.
  • a method for determining a video segment comprising: acquiring an operation record of a target video, each operation record for indicating a first play time and a target video at the first play time An operation performed, the first playing time is a playing time of the target video; the number of operations belonging to the target type that have been performed on the target video at each playing time of the target video is obtained from the operation record; according to the quantity in the target video Determining the target segment, the ratio between the total number of operations belonging to the target type that have been performed on the target video at the playback time within the target segment and the duration of the target segment is at least greater than the operation of the target type that has been performed on the target video. The ratio between the total number and the duration of the target video.
  • a device for determining a video segment comprising one or more processors, and one or more memories storing program units, wherein the program units are executed by the processor
  • the program unit includes: a first obtaining unit configured to acquire an operation record of the target video, each operation record for indicating a first playing time and an operation performed on the target video at the first playing time, the first playing The moment is a play time of the target video; the second acquisition unit is configured to acquire, from the operation record, the number of operations belonging to the target type that have been performed on the target video at each play time of the target video; the determining unit is set to Determining the target segment in the target video according to the quantity, the ratio between the total number of operations belonging to the target type that have been performed on the target video at the playback time within the target segment and the duration of the target segment is at least greater than the execution of the target video The ratio between the total number of operations of the target type and the duration of the target video.
  • the second obtaining unit includes: a first acquiring module, configured to obtain a first operation record from the plurality of operation records, wherein the first operation record is used to indicate that the target video has been executed at the first playing time The operation of the type; the first determining module is configured to determine the number of operations of the target type that has been performed on the target video at each play time of the target video according to the first play time recorded in all the first operation records.
  • the first obtaining module is further configured to: acquire an operation record in the plurality of operation records; and when the operation identifier recorded in the acquired operation record is used to indicate the operation of the target type, the operation record to be acquired Recorded as the first operational record.
  • the determining unit includes: a second acquiring module, configured to acquire an operation density of the target playing period in the target video, where the target playing period is a playing period in which any one of the target videos has a first playing time, the operating density a ratio between a total number of operations belonging to the target type that has been executed within the target playing period and the first threshold; a second determining module configured to determine that the operating density of the target playing period is greater than the second threshold
  • the video segment in which the target playing period is located is a target segment, wherein the second threshold is greater than or equal to a ratio between the total number of operations belonging to the target type that have been performed on the target video and the duration of the target video.
  • the second determining module is further configured to: when the target playing period is multiple, set all the target playing periods to the pending status, Performing the following operations on the target playing period until all the target playing periods are in the processed state: the currently processed target playing period is recorded as the first playing period; in the case where there is the target playing period crossing the first playing period, The target playing period and the first playing period in which the first playing period intersects are merged into the second playing period, and the second playing period is taken as the target playing period in the to-be-processed state; in the first playing period and the adjacent target playing period In a case where the time interval is less than the third threshold, the first play period, the adjacent target play period, and the time interval are merged into the third play period, and the third play period is taken as the target play period in the to-be-processed state; The time interval between the first play period and the adjacent target play period is not less than a third threshold In the case, the first
  • the second determining module is further configured to modify the target segment in the following manner: the video frame where the starting playback time of the target segment is not critical In the case of a frame, the first play time at which the key frame closest to the start play time of the target segment is located is the start play time of the target segment; the video frame where the end play time of the target segment is not the key frame Next, the second play time at which the key frame closest to the end play time of the target segment is located is the end play time of the target segment.
  • the first playing time is earlier than the starting playing time of the target segment before the correction; and the second playing time is the ending playing time of the target segment before the correction.
  • the second obtaining module is further configured to acquire an operation density of the plurality of target playing periods in the target video, wherein the starting playing moments of the adjacent two target playing periods are separated by one unit time.
  • the determining unit is further configured to perform at least one of: sending the indication information to the terminal when the terminal plays the target video, where the indication information is used to indicate the terminal pair The target segment is identified; when receiving the request to play the target video, the indication information is sent to the terminal; in the case where there are multiple target segments, the plurality of target segments are combined into one video.
  • the number of operations belonging to the target type that have been performed on the target video at each play time of the target video is obtained from the acquired operation record; the target video is executed according to the play time in the target segment.
  • the ratio between the total number of operations belonging to the target type and the duration of the target segment is at least greater than the ratio between the total number of operations of the target type that have been performed on the target video and the duration of the target video, in the target video.
  • FIG. 1 is a schematic diagram of a hardware environment of a method for determining a video segment according to an embodiment of the present application
  • FIG. 2 is a flowchart of a method for determining an optional video segment according to an embodiment of the present application
  • FIG. 3 is a schematic diagram of an optional video playback timeline according to an embodiment of the present application.
  • FIG. 4 is a schematic diagram of an optional video annotation according to an embodiment of the present application.
  • FIG. 5 is a flowchart of a method for determining another optional video segment according to an embodiment of the present application.
  • FIG. 6 is a schematic diagram of an apparatus for determining an optional video segment according to an embodiment of the present application.
  • FIG. 7 is a schematic diagram of another optional video segment determining apparatus according to an embodiment of the present application.
  • FIG. 8 is a structural block diagram of an electronic device according to an embodiment of the present application.
  • a method embodiment of a method for determining a video segment is provided.
  • the method for determining the video segment may be applied to a hardware environment formed by the server 102 and the terminal 104 as shown in FIG. 1.
  • the server 102 is connected to the terminal 104 through a network.
  • the network includes but is not limited to a wide area network, a metropolitan area network, or a local area network.
  • the terminal 104 is not limited to a PC, a mobile phone, a tablet, or the like.
  • the method for determining the video clip of the embodiment of the present application may be performed by the server 102, or may be performed by the server 102 and the terminal 104 in common.
  • the method for determining the video segment of the terminal 104 in the embodiment of the present application may also be performed by a client installed on the terminal.
  • the program code corresponding to the method of the embodiment of the present application may be directly executed on the server.
  • the terminal When the determining method of the video segment of the embodiment of the present application is performed by the server and the terminal together, the terminal sends the operation record to the server, and at this time, the program code corresponding to the method of the embodiment of the present application is executed by the server, and the processing is performed. The results are fed back to the terminal.
  • the method may include the following steps:
  • Step S202 The server acquires an operation record of the target video, where each operation record is used to indicate a first play time and an operation performed on the target video at the first play time, where the first play time is a play time of the target video.
  • the running water information includes the user ID, the playing time of the video during operation, the type of operation, and the content of the operation. At least the playback time and operation type of the video during operation.
  • Step S204 The server acquires, from the operation record, the number of operations belonging to the target type that have been performed on the target video at each play time of the target video.
  • the operation of the target type described above may determine which types of operations belong to the target type according to the type of the target segment to be determined. For example, if the target segment to be determined refers to the hot video segment, then the operation of the target type is used to represent Hot-related operations, such as publishing a barrage, chat operation, participation interaction, video screenshots, etc.; for example, the target segment to be determined refers to the segment that is completely played, then the operation of the target type refers to the representation of the complete playback.
  • the operation such as a fast forward operation, a fast reverse operation, a drag operation, and the like performed on the playback progress bar; the target segment to be determined may also be a highlight segment, a key segment, and the like.
  • Step S206 the server determines the target segment according to the quantity in the target video, and the ratio between the total number of operations belonging to the target type that has been performed on the target video in the target segment and the duration of the target segment is at least greater than the target video. The ratio of the total number of operations belonging to the target type that have been executed to the duration of the target video.
  • the corresponding user behavior (that is, the operation indicated by the operation record) is analyzed by big data, and the user is analyzed at each play time of the entire target video.
  • the behavior data that is, the number of operations performed
  • the desired target segment that is, a video segment with a denser and continuous number of operations
  • the server acquires, from the acquired operation record, the number of operations belonging to the target type that have been performed on the target video at each play time of the target video; the server targets the target according to the play time in the target segment.
  • the ratio between the total number of operations of the target type that the video has performed and the duration of the target segment is at least greater than the ratio of the total number of operations belonging to the target type that have been performed by the target video to the duration of the target video, Determining the target segment that satisfies the requirement in the target video can solve the technical problem of determining the efficiency of the video segment required in the video in the related art, thereby improving the efficiency of determining the target segment satisfying the demand in the target video.
  • Technical effects are possible to solve the technical problem of determining the efficiency of the video segment required in the video in the related art, thereby improving the efficiency of determining the target segment satisfying the demand in the target video.
  • step S202 when acquiring the operation record of the target video, the following two acquisition modes are included, but not limited to:
  • Method 1 The server periodically reads the pre-saved operation record.
  • the server saves the operation record sent by the terminal in real time to the database.
  • the server according to the video identifier of the target video (such as video) ID) reads the operation record of the target video in a certain period of time from the database to count the target segment (such as a hot video segment).
  • the server can periodically perform statistics (that is, periodically triggering the target video) The operation records this step) to periodically update the hotspot video clip.
  • Manner 2 The server obtains the operation record uploaded by the terminal in real time, and the server receives the operation record fed back by the terminal in real time, and performs real-time calculation on the operation record to determine the hot spot video segment of the current time period.
  • step S204 the number of operations belonging to the target type that have been performed on the target video at each playback time of the target video is acquired from the operation record.
  • the pre-storing operation record (such as reading the operation record in a certain period before the current time) is equivalent to the calculation of the number of features in the previous time period (such as whether it is a hot spot).
  • the operation record uploaded by the real-time terminal of the second mode it is equivalent to calculating the feature of the current time (such as whether it is a hot spot) in real time.
  • the embodiment of the present application provides the following acquisition methods:
  • step S2042 the server first filters all the operation records, and obtains a valid first operation record from the plurality of operation records, where the first operation record is used to indicate that the target type has been operated on the target video at the first playback time.
  • the server may perform step S2042 to step S2044 in a single thread or in multiple threads.
  • the server performs the following operations on each thread: acquiring one operation record in the plurality of operation records; and recording the operation identifier in the acquired operation record
  • the acquired operation record is recorded as the first operation record.
  • step S2044 the server determines the number of operations of the target type that the target video has been executed at each play time of the target video according to the first play time recorded in all the first operation records.
  • the server may first initialize the number of operations of the target type that the target video has performed at each play time of the target video, that is, record the number as 0; then acquire each first operation record one by one (or Step S2042, when filtering a first operation record, reading the playback time recorded in the first operation record (ie, the first playback time), and performing an operation of adding 1 to the number corresponding to the playback time; repeating the above operation Until all the first operation records are counted, the number of operations of the target type at each play time of the target video is obtained.
  • the server determines the target segment in the target video according to the quantity, between the total number of operations belonging to the target type that have been performed on the target video at the playing time in the target segment and the duration of the target segment.
  • the ratio is at least greater than the ratio between the total number of operations belonging to the target type that have been performed on the target video and the duration of the target video.
  • Step S2062 The server acquires an operation density of the target playing period in the target video, where the target playing period is a playing period in which any one of the target video plays the first threshold, and the operation density is an operation belonging to the target type that has been executed in the target playing period. The ratio between the total number and the first threshold.
  • the target playing period at this time may be a fixed value (that is, the first threshold, such as 1 second, 5 seconds, 10 seconds, 1 minute), and the target obtained at the initial time.
  • the video can be obtained according to a certain time interval (such as one unit time, such as 1 second, 1 minute, etc.) between the initial playing times of two adjacent target playing periods, that is, multiple target playbacks are obtained.
  • the time period is then calculated for the operational density of multiple target playback periods in the target video.
  • the first threshold is 5 unit time (such as seconds, 10 seconds, minutes, etc.), and the first target playing period A corresponds to the 0th to the 5th playing time.
  • the second target playing period B corresponds to the 1st to 6th playing times, the third target playing period C corresponds to the 2nd to 7th playing times, and so on, and each target playing period is determined.
  • the total number of operations in each playing time of each target playing period is counted, and the ratio between the total number and the first threshold (ie, the operating density) is calculated.
  • Step S2064 The server determines that the video segment where the target playing period is located is the target segment if the operation density of the target playing period is greater than the second threshold, and the second threshold is greater than or equal to the total number of operations belonging to the target type that have been performed on the target video. The ratio to the duration of the target video.
  • determining the video segment in which the target playing period is located as the target segment may have two meanings: one is directly to the target playing period.
  • the starting play time is the start play time
  • the video clip whose end play time is the end play time of the target play period is the target clip
  • the second is that the target clip includes at least the video clip where the target play period is located.
  • determining that the video segment in which the target playing period is located as the target segment includes: in the case that the target playing period is multiple, all the target playing with the operating density greater than the second threshold is played.
  • the time period (the periods A, B, C, D, F shown in FIG. 3) is set to be saved in the to-be-processed state (the target playing periods in steps S20642 to S20648 are all operating densities greater than the second threshold) Play time period), perform the following operations on the target play time period until all target play time periods are in the processed state:
  • step S20642 the server takes out one of the to-be-processed sets as the current process, and records the currently-processed target playing period as the first playing period, for example, the taken-out target playing period B is recorded as the first playing period.
  • Step S20644 the server compares the first play period B with the elements in the set to be processed (such as the periods A, C, D, F), and in the case that there is a target play period that intersects with the first play period, The target playing period and the first playing period in which the playing period intersects are merged into the second playing period, and the second playing period is taken as the target playing period in the to-be-processed state, such as the period A intersecting the period B, and the period A and the period B are merged The merge corresponds to the 0th to 6th play time.
  • the elements in the set to be processed such as the periods A, C, D, F
  • the first playback period that is taken out next time is the above-mentioned combined target playback period (the above corresponds to the 0th to the 6th playback time)
  • Step S20646 in a case where the time interval between the first playing period and the adjacent target playing period is less than the third threshold, the server merges the first playing period, the adjacent target playing period, and the time interval into the third playing period. And the third play period is taken as the target play period in the pending state.
  • the third threshold value described above can be set according to actual needs, such as setting to 5 unit time.
  • the period G and the period F are not merged.
  • Step S20648 in a case where the time interval between the first playing period and the adjacent target playing period is not less than the third threshold, the server sets the first playing period as the target playing period in the processed state, and will be in the already The video clip in which the target playback period of the processing state is located is used as a target segment.
  • the time period G may be set to the target playback time period in the processed state, and the video segment in which the time period G is located as one target segment.
  • Step S2066 after determining that the video segment in which the target playing period is located is the target segment, the server may modify the target segment in the following manner:
  • Step S20662 in a case where the video frame where the start playing time of the target segment is not a key frame, the server plays the first playing time of the key frame closest to the starting playing time of the target segment as the starting of the target segment. time.
  • the key frame described above refers to the frame in which the key action of the character or object movement or change is located.
  • step S20664 if the video frame in which the end of the target segment is played is not a key frame, the server sets the second play time of the key frame closest to the end play time of the target segment as the end play time of the target segment.
  • the first playing time is earlier than the starting playing time of the target segment before the correction; and the second playing time is later than the ending playing time of the target segment before the correction.
  • the method provided in the foregoing steps S202 to S206 of the embodiment of the present application can be applied to service scenarios such as video trailers and hotspot operations, such as hotspot video annotation in hotspot operations, and can automatically mark the video highlights based on big data mining. And interception.
  • the program captures the user's active behavior by collecting video, such as publishing the behavior data such as the barrage, jumping watch, and video screenshots. Through data statistics and mining techniques, the hot spot of the labeled video is automatically found, and then the highlight is distributed according to the distribution of the hotspot. Interception.
  • the hot video annotation shown in FIG. 4 is taken as an example for details:
  • step S21 the user usage behavior (that is, the operation belonging to the target type) is sorted on the product, which is related to the degree of the content of the video content (such as posting a barrage, jumping watching, video screenshot, etc.).
  • the specification definition of the behavior reporting operation record (including user ID, operation time, video ID, viewing node, behavior type, etc.) is pre-designed, and data management is performed, and data reporting is performed in the scenario timing corresponding to the application client. .
  • step S22 the application performs operation record data reporting, and the application ensures that the data is completely reported to the data storage platform database of the back-end server according to the contract according to the definition requirements of the reported product.
  • Step S23 After the back-end server collects the user behavior data, based on the common behavior operation of the massive users, the data identification model is used to calculate the relevant identification information of the highlights of each video by using the data statistical model. After the relevant identification information is obtained, the backend server may directly intercept the relevant sub-segments or screenshots for sharing and dissemination; or may synchronize related information to the client player for applying the hotspot identification and fast jump of the playing scene.
  • the highlight identifier obtained by the client may be provided by the server to the application front end by means of an online service.
  • the front-end application can obtain the relevant highlight identification information through the video ID.
  • the server when the terminal plays the target video, the server sends the indication information to the terminal, and the indication information indicates that the terminal identifies the target segment, performs display identification or label data, or sends the indication information to the terminal when receiving the request for playing the target video.
  • step S25 after the front end obtains the identification information, in the video playing scene, after the user clicks on the player, the identification information of the highlight piece can be displayed in the place where the progress bar is played. When interacting, you can quickly jump to the playback position of the highlights to meet the user's desire to quickly view the exciting content.
  • the solution replaces the manual processing method in the related technology by means of automatic interception by the server.
  • video playback terminals such as Android phones, iPhones, PCs, WEBs, TVs, etc.
  • streaming information such as posting a barrage, participating in interactive interactions, jumping watching progress, video screenshots, etc.
  • the background receives the report information (that is, the operation record) and then enters the database to the big data storage platform; the big data platform receives the report.
  • the recording according to the behavior meaning of each reported action representative and the distribution of the action time, the start and stop signs of the video highlights are calculated.
  • the target segment can be calculated in real time to display the target segment as a hot spot in real time, and the target segment can be calculated according to a certain segment or all historical user behavior data to update the previous calculated hot spot segment.
  • the present application also provides a preferred embodiment, which is described in detail by taking a highlight video collection as shown in FIG. 5 as an example:
  • step S502 the user behavior data collection logic is pre-buried in the front-end client, and the operation record of the user usage behavior is reported by the client.
  • step S504 the data warehouse stores the data reported by the client front end to the big data platform, and performs data conversion and cleaning, and performs filtering processing to obtain data of operations belonging to the target type for use in subsequent computing services.
  • Step S506 the statistical modeling calculation service: according to the granularity of the video identification VID, all the reporting records related to each VID are divided and summarized; for the reporting time of each VID, a density-based clustering algorithm is used to classify the large categories and find the highlights. The area where it is located; then through the normal distribution method, find the middle position of the area as the separation point of the edge of the segment; combined with the interval distribution of the cluster, and the relationship of the separation points, the combination of the two sides gives the starting and ending position of each highlight .
  • step S508 since the video adopts compression technology, the start and stop positions acquired in the previous step may not directly correspond to one clear and complete image frame.
  • the starting and ending positions of the clip can be optimized to adjust the starting and ending position of the video clip to the most recent key frame as the final clip edge position.
  • Step S510 After obtaining the start and end position of the segment, the system may import related information of the video highlight into the online system for use in each service scenario.
  • step S512 the relevant segment content is directly intercepted, and the content is created as a highlight video highlight, and the sharing is directly transmitted.
  • the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, by hardware, but in many cases, the former is A better implementation.
  • the technical solution of the embodiments of the present application may be embodied in the form of a software product in essence or in the form of a software product stored in a storage medium (such as ROM/RAM, disk).
  • the optical disc includes a plurality of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method described in the various embodiments of the present application.
  • FIG. 6 is a schematic diagram of an apparatus for determining an optional video clip according to an embodiment of the present application.
  • the apparatus may include one or more processors, and one or more memories storing program units.
  • the program unit is executed by a processor, and the program unit includes: a first obtaining unit 62, a second obtaining unit 64, and a determining unit 66.
  • the first obtaining unit 62 is configured to acquire an operation record of the target video, where each operation record is used to indicate a first play time and an operation that has been performed on the target video at the first play time, where the first play time is the target video A play moment.
  • the running water information includes the user ID, the playing time of the video during operation, the type of operation, and the content of the operation. At least the playback time and operation type of the video during operation.
  • the second obtaining unit 64 is configured to acquire, from the operation record, the number of operations belonging to the target type that have been performed on the target video at each playback time of the target video.
  • the operation of the target type described above may determine which types of operations belong to the target type according to the type of the target segment to be determined. For example, if the target segment to be determined refers to the hot video segment, then the operation of the target type is used to represent Hot-related operations, such as publishing a barrage, chat operation, participation interaction, video screenshots, etc.; for example, the target segment to be determined refers to the segment that is completely played, then the operation of the target type refers to the representation of the complete playback.
  • the operation such as a fast forward operation, a fast reverse operation, a drag operation, and the like performed on the playback progress bar; the target segment to be determined may also be a highlight segment, a key segment, and the like.
  • the determining unit 66 is configured to determine the target segment in the target video according to the quantity, and the ratio between the total number of operations belonging to the target type that have been performed on the target video at the playing time in the target segment and the duration of the target segment is at least greater than The ratio between the total number of operations belonging to the target type that have been performed on the target video and the duration of the target video.
  • the corresponding user behavior (that is, the operation indicated by the operation record) is analyzed by big data, and the user is analyzed at each play time of the entire target video.
  • the behavior data that is, the number of operations performed
  • the desired target segment that is, a video segment with a denser and continuous number of operations
  • first obtaining unit 62 in this embodiment may be configured to perform step S202 in the embodiment of the present application.
  • the second obtaining unit 64 in this embodiment may be configured to perform the example in the embodiment of the present application.
  • the determining unit 66 in this embodiment may be configured to perform step S206 in the embodiment of the present application.
  • the foregoing modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the contents disclosed in the foregoing embodiments. It should be noted that the foregoing module may be implemented in a hardware environment as shown in FIG. 1 as part of the device, and may be implemented by software or by hardware.
  • the target segment that satisfies the requirement can solve the technical problem of determining the efficiency of the video segment required in the video in the related art, and further improve the technical effect of determining the target segment satisfying the demand in the target video.
  • the second obtaining unit includes: a first obtaining module 642, configured to obtain a first operation record from the plurality of operation records, wherein the first operation record is used to indicate that the first operation is performed.
  • the target type of operation has been performed on the target video at a time;
  • the first determining module 644 is configured to determine, according to the first play time recorded in all the first operation records, the target type that has been executed on the target video at each play time of the target video. The number of operations.
  • the first acquiring module acquires one of the plurality of operation records; and when the operation identifier recorded in the acquired operation record is used to indicate the operation of the target type, the acquired operation record is recorded as the first operation record.
  • the determining unit includes: a second acquiring module, configured to acquire an operation density of the target playing period in the target video, where the target playing period is a playing period in which any one of the target videos has a first playing time, the operating density a ratio between a total number of operations belonging to the target type that has been executed within the target playing period and the first threshold; a second determining module configured to determine that the operating density of the target playing period is greater than the second threshold
  • the video segment in which the target playing period is located is a target segment, wherein the second threshold is greater than or equal to a ratio between the total number of operations belonging to the target type that have been performed on the target video and the duration of the target video.
  • the second acquiring module described above is further configured to acquire an operation density of a plurality of target playing periods in the target video, wherein the starting playing times of the adjacent two target playing periods are separated by one unit time.
  • the second determining module described above is further configured to set all the target playing periods as the to-be-processed state in the case where the target playing period is plural, and perform the following operations on the target playing period until all the target playing periods are in the processed state:
  • the target playing period and the first playing period that intersect the first playing period are merged into the second playing period, and the second playing period is regarded as being in a pending state Target playback time period;
  • the first play period, the adjacent target play period, and the time interval are merged into the third play period, and the first The three play period is the target play period in a pending state;
  • the first play period is set to the target play period in the processed state, and the target in the processed state is set The video clip where the play time slot is located as a target clip.
  • the determining unit is further configured to modify the target segment in the following manner:
  • the first play time at which the key frame closest to the start play time of the target segment is located is the start play time of the target segment
  • the second play time at which the key frame closest to the end play time of the target segment is located is the end play time of the target segment.
  • the first playing time is earlier than the starting playing time of the target segment before the correction; the second playing time is later than the ending playing time of the target segment before the correction.
  • the determining unit is further configured to perform at least one of: sending the indication information to the terminal when the terminal plays the target video, where the indication information is used to indicate the terminal pair The target segment is identified; when receiving the request to play the target video, the indication information is sent to the terminal; in the case where there are multiple target segments, the plurality of target segments are combined into one video.
  • the technical solution of the embodiment of the present application replaces the manual processing mode in the related art by means of automatic interception by the server.
  • the video editing receives the content medium to be online, the video hotspot segment is not required to be marked and recorded, and the video is first reviewed.
  • the video playback terminal such as Android mobile phone, iphone mobile phone, PC, WEB, TV and other video clients
  • can watch the user's viewing actions such as publishing a barrage, participating in interactive activities, jumping watching progress, video screenshots).
  • the flow information (including the user ID, operation time, operation type, operation content and other information fields) is identified and extracted and reported, and the report information (that is, the operation record) is received in the background and then stored in the big data storage platform; After receiving the report record, the data platform calculates the start and stop mark of the video highlight according to the behavior meaning of each report action representative and the distribution of the action time.
  • the target segment can be calculated in real time to display the target segment as a hot spot in real time, and the target segment can be calculated according to a certain segment or all historical user behavior data to update the previous calculated hot spot segment.
  • the above modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the contents disclosed in the above embodiments. It should be noted that the foregoing module may be implemented in a hardware environment as shown in FIG. 1 as part of the device, and may be implemented by software or by hardware, where the hardware environment includes a network environment.
  • an electronic device for implementing the above method for determining a video segment which may be a server or a terminal.
  • FIG. 8 is a structural block diagram of an electronic device according to an embodiment of the present application.
  • the electronic device is a terminal.
  • the terminal may include: one or more (only FIG. 8 A processor 801, a memory 803, and a transmission device 805 (such as the transmitting device in the above embodiment) are shown.
  • the terminal may further include an input/output device 807.
  • the memory 803 can be configured to store a software program and a module, such as a method for determining a video segment in the embodiment of the present application and a program instruction/module corresponding to the device, and the processor 801 runs the software program and the module stored in the memory 803. Thus, various functional applications and data processing are performed, that is, the method of determining the video segment described above is implemented.
  • Memory 803 can include high speed random access memory, and can also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid state memory. In some examples, memory 803 can further include memory remotely located relative to processor 801, which can be connected to the terminal over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the transmission device 805 described above is arranged to receive or transmit data via a network, and can also be used for data transmission between the processor and the memory. Specific examples of the above network may include a wired network and a wireless network.
  • the transmission device 805 includes a Network Interface Controller (NIC) that can be connected to other network devices and routers via a network cable to communicate with the Internet or a local area network.
  • the transmission device 805 is a Radio Frequency (RF) module for communicating wirelessly with the Internet.
  • NIC Network Interface Controller
  • RF Radio Frequency
  • the memory 803 is set to store an application.
  • the processor 801 can call the application stored in the memory 803 through the transmission device 805 to perform the following steps: acquiring an operation record of the target video, each operation record is used to indicate the first play time and the target video has been at the first play time.
  • An operation performed is a playing time of the target video; and the number of operations belonging to the target type that have been performed on the target video at each playing time of the target video is obtained from the operation record; according to the quantity in the target video Determining the target segment, the ratio between the total number of operations belonging to the target type that have been performed on the target video at the playback time within the target segment and the duration of the target segment is at least greater than the total of operations belonging to the target type that have been performed on the target video The ratio between the quantity and the duration of the target video.
  • the processor 801 is further configured to perform the steps of: recording the currently processed target playing period as the first playing period; and in the case of the target playing period intersecting the first playing period, intersecting with the first playing period
  • the target playing period and the first playing period are merged into the second playing period, and the second playing period is taken as the target playing period in the to-be-processed state;
  • the time interval between the first playing period and the adjacent target playing period is less than the In the case of three thresholds, the first play period, the adjacent target play period, and the time interval are merged into a third play period, and the third play period is taken as the target play period in the to-be-processed state;
  • the first playing period is set to the target playing period in the processed state, and the video clip in which the target playing period in the processed state is located As a target segment.
  • the number of operations belonging to the target type that have been performed on the target video at each play time of the target video is obtained from the acquired operation record; and the target video has been executed according to the play time in the target segment.
  • the ratio between the total number of operations belonging to the target type and the duration of the target segment is at least greater than the ratio between the total number of operations belonging to the target type that have been performed by the target video and the duration of the target video, in the target video.
  • the structure shown in FIG. 8 is only illustrative, and the terminal can be a smart phone (such as an Android mobile phone, an iOS mobile phone, etc.), a tablet computer, a palm computer, and a mobile Internet device (MID). Terminal equipment such as PAD.
  • FIG. 8 does not limit the structure of the above electronic device.
  • the terminal may also include more or less components (such as a network interface, display device, etc.) than shown in FIG. 8, or have a different configuration than that shown in FIG.
  • Embodiments of the present application also provide a storage medium.
  • the foregoing storage medium may be used to execute program code of a method for determining a video segment.
  • the foregoing storage medium may be located on at least one of the plurality of network devices in the network shown in the foregoing embodiment.
  • the storage medium is arranged to store program code for performing the following steps:
  • S31 Obtain an operation record of the target video, where each operation record is used to indicate a first play time and an operation performed on the target video at the first play time, where the first play time is a play time of the target video;
  • S33 Determine a target segment according to the quantity in the target video, and a ratio between a total number of operations belonging to the target type that has been performed on the target video in the target segment and a duration of the target segment is at least greater than that performed on the target video. The ratio of the total number of operations belonging to the target type to the duration of the target video.
  • the storage medium is further arranged to store program code for performing the following steps:
  • the foregoing storage medium may include, but not limited to, a USB flash drive, a Read-Only Memory (ROM), a Random Access Memory (RAM), a mobile hard disk, and a magnetic memory.
  • ROM Read-Only Memory
  • RAM Random Access Memory
  • a mobile hard disk e.g., a hard disk
  • magnetic memory e.g., a hard disk
  • the integrated unit in the above embodiment if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in the above-described computer readable storage medium.
  • the technical solution of the embodiments of the present application may be embodied in the form of a software product in the form of a software product in essence or in a part contributing to the related art, and the computer software product is stored in a storage medium.
  • a number of instructions are included to cause one or more computer devices (which may be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present application.
  • the disclosed client may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, unit or module, and may be electrical or otherwise.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the number of operations belonging to the target type that have been performed on the target video at each play time of the target video is obtained from the acquired operation record; and the target video has been executed according to the play time in the target segment.
  • the ratio between the total number of operations belonging to the target type and the duration of the target segment is at least greater than the ratio between the total number of operations belonging to the target type that have been performed by the target video and the duration of the target video, in the target video.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Social Psychology (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Computer Security & Cryptography (AREA)
  • Computing Systems (AREA)
  • Human Computer Interaction (AREA)
  • Business, Economics & Management (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • Television Signal Processing For Recording (AREA)

Abstract

本申请实施例公开了一种视频片段的确定方法、装置、存储介质及电子装置。其中，该方法包括：获取目标视频的操作记录，每条操作记录用于指示第一播放时刻和在第一播放时刻对目标视频已执行的一个操作，第一播放时刻为目标视频的一个播放时刻；从操作记录中获取目标视频的每个播放时刻上对目标视频已执行的属于目标类型的操作的数量；根据数量在目标视频中确定目标片段，在目标片段内的播放时刻上对目标视频已执行的属于目标类型的操作的总数量与目标片段的时长之间的比值至少大于对目标视频已执行的属于目标类型的操作的总数量与目标视频的时长之间的比值。本申请实施例解决了相关技术中确定视频中需要的视频片段的效率较低的技术问题。

Description

视频片段的确定方法、装置、存储介质及电子装置
本申请要求于2017年09月21日提交中国专利局、申请号为201710862009.7、发明名称“视频片段的确定方法和装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及互联网领域，具体而言，涉及一种视频片段的确定方法、装置、存储介质及电子装置。
背景技术
OTT是“Over The Top”的缩写，是指通过互联网向用户提供各种应用服务，这种应用和目前运营商所提供的通信业务不同，它利用运营商的网络，而服务可由运营商之外的第三方提供。
在视频服务业务中，对视频中的精彩片段进行标注是一个非常重要的服务，在相关技术中，采用如下方式进行视频的人工标注：
步骤11，视频编辑者收到视频内容后，先完整观看一遍视频内容；
步骤12，编辑者根据个人经验，判断哪部分视频片段可能引发热点话题(即确定需要的视频片段)，并手工对该片段位置(对应的视频时长位置)进行标注；
步骤13，编辑者手工将标注的热点位置信息录入到视频媒资系统，该系统可以提供根据视频ID(即VID)读取对应热点位置的服务；
步骤14，根据业务场景需求，在播放视频时显示标注信息。
在上述视频标注方式中，存在如下问题：
(1)依赖于人工标注，标注的工作量和成本很高，标注的效率较低。
(2)对视频片段的精彩程度、或话题引爆可能性的判断，完全依赖于个人经验判断，对个人能力要求较高，故存在截取的视频片段和用户真实兴趣点不匹配的风险。
(3)人工标注偏向一次性工作，基于人力和成本等原因，标注完一次后基本就保持不变，难以适应在视频播出过程出现热点轮换等动态情况。
针对相关技术中确定视频中需要的视频片段的效率较低的技术问题，目前尚未提出有效的解决方案。
发明内容
本申请实施例提供了一种视频片段的确定方法、装置、存储介质及电子装置，以至少解决相关技术中确定视频中需要的视频片段的效率较低的技术问题。
根据本申请实施例的一个方面，提供了一种视频片段的确定方法，该方法包括：获取目标视频的操作记录，每条操作记录用于指示第一播放时刻和在第一播放时刻对目标视频已执行的一个操作，第一播放时刻为目标视频的一个播放时刻；从操作记录中获取目标视频的每个播放时刻上对目标视频已执行的属于目标类型的操作的数量；根据数量在目标视频中确定目标片段，在目标片段内的播放时刻上对目标视频已执行的属于目标类型的操作的总数量与目标片段的时长之间的比值至少大于对目标视频已执行的属于目标类型的操作的总数量与目标视频的时长之间的比值。
根据本申请实施例的另一方面，还提供了一种视频片段的确定装置，该装置包括一个或多个处理器，以及一个或多个存储程序单元的存储器，其中，程序单元由处理器执行，该程序单元包括：第一获取单元，被设置为获取目标视频的操作记录，每条操作记录用于指示第一播放时刻和在第一播放时刻对目标视频已执行的一个操作，第一播放时刻为目标视频的一个播放时刻；第二获取单元，被设置为从操作记录中获取目标视频的每个播放时刻上对目标视频已执行的属于目标类型的操作的数量；确定单元， 被设置为根据数量在目标视频中确定目标片段，在目标片段内的播放时刻上对目标视频已执行的属于目标类型的操作的总数量与目标片段的时长之间的比值至少大于对目标视频已执行的属于目标类型的操作的总数量与目标视频的时长之间的比值。
可选地，第二获取单元包括：第一获取模块，被设置为从多条操作记录中获取第一操作记录，其中，第一操作记录用于指示在第一播放时刻对目标视频已执行目标类型的操作；第一确定模块，被设置为根据所有第一操作记录中记录的第一播放时刻确定目标视频的每个播放时刻上对目标视频已执行的目标类型的操作的数量。
可选地，第一获取模块还被设置为：获取多条操作记录中的一条操作记录；在获取的操作记录中记录的操作标识用于指示目标类型的操作的情况下，将获取的操作记录记为第一操作记录。
可选地，确定单元包括：第二获取模块，被设置为获取目标视频中目标播放时段的操作密度，其中，目标播放时段为目标视频中任意一个播放时长为第一阈值的播放时段，操作密度为在目标播放时段内已执行的属于目标类型的操作的总数量与第一阈值之间的比值；第二确定模块，被设置为在目标播放时段的操作密度大于第二阈值的情况下，确定目标播放时段所在的视频片段为目标片段，其中，第二阈值大于等于对目标视频已执行的属于目标类型的操作的总数量与目标视频的时长之间的比值。
可选地，在目标播放时段的操作密度大于第二阈值的情况下，第二确定模块还被设置为：在目标播放时段为多个的情况下，将所有目标播放时段设置为待处理状态，对目标播放时段执行以下操作，直到所有目标播放时段处于已处理状态：将当前处理的目标播放时段记为第一播放时段；在存在与第一播放时段交叉的目标播放时段的情况下，将与第一播放时段交叉的目标播放时段和第一播放时段合并为第二播放时段，并将第二播放时段作为处于待处理状态的目标播放时段；在第一播放时段与相邻的目标播放时段之间的时间间隔小于第三阈值的情况下，将第一播放时段、相邻的 目标播放时段以及时间间隔合并为第三播放时段，并将第三播放时段作为处于待处理状态的目标播放时段；在第一播放时段与相邻的目标播放时段之间的时间间隔不小于第三阈值的情况下，将第一播放时段设置为处于已处理状态的目标播放时段，并将处于已处理状态的目标播放时段所在的视频片段作为一个目标片段。
可选地，第二确定模块在确定目标播放时段所在的视频片段为目标片段之后，还被设置为对目标片段采用如下方式进行修正：在目标片段的起始播放时刻所在的视频帧不为关键帧的情况下，将距离目标片段的起始播放时刻最近的关键帧所在的第一播放时刻作为目标片段的起始播放时刻；在目标片段的结束播放时刻所在的视频帧不为关键帧的情况下，将距离目标片段的结束播放时刻最近的关键帧所在的第二播放时刻作为目标片段的结束播放时刻。
可选地，第一播放时刻为早于修正前的目标片段的起始播放时刻；第二播放时刻为晚于修正前的目标片段的结束播放时刻。
可选地，第二获取模块还被设置为获取目标视频中多个目标播放时段的操作密度，其中，相邻的两个目标播放时段的起始播放时刻之间间隔一个单位时间。
可选地，确定单元在根据数量在目标视频中确定目标片段之后，还被设置为执行以下至少之一：在终端播放目标视频时，发送指示信息至终端，其中，指示信息用于指示终端对目标片段进行标识；在接收到播放目标视频的请求时，发送指示信息至终端；在目标片段为多个的情况下，将多个目标片段合并为一个视频。
在本申请实施例中，从获取的操作记录中获取目标视频的每个播放时刻上对目标视频已执行的属于目标类型的操作的数量；根据在目标片段内的播放时刻上对目标视频已执行的属于目标类型的操作的总数量与目标片段的时长之间的比值至少大于对目标视频已执行的属于目标类型的操作的总数量与目标视频的时长之间的比值这一原则，在目标视频中确定出 满足需求的目标片段，可以解决了相关技术中确定视频中需要的视频片段的效率较低的技术问题，进而达到了提高在目标视频中确定出满足需求的目标片段的效率的技术效果。
附图说明
此处所说明的附图用来提供对本申请的进一步理解，构成本申请的一部分，本申请的示意性实施例及其说明用于解释本申请实施例，并不构成对本申请实施例的不当限定。在附图中：
图1是根据本申请实施例的视频片段的确定方法的硬件环境的示意图；
图2是根据本申请实施例的一种可选的视频片段的确定方法的流程图；
图3是根据本申请实施例的一种可选的视频播放时间轴的示意图；
图4是根据本申请实施例的一种可选的进行视频标注的示意图；
图5是根据本申请实施例的另一种可选的视频片段的确定方法的流程图；
图6是根据本申请实施例的一种可选的视频片段的确定装置的示意图；
图7是根据本申请实施例的另一种可选的视频片段的确定装置的示意图；
以及
图8是根据本申请实施例的一种电子装置的结构框图。
具体实施方式
为了使本技术领域的人员更好地理解本申请实施例中的方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分的实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本申请实施例保 护的范围。
需要说明的是，本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
根据本申请实施例的一个方面，提供了一种视频片段的确定方法的方法实施例。
可选地，在本实施例中，上述视频片段的确定方法可以应用于如图1所示的由服务器102和终端104所构成的硬件环境中。如图1所示，服务器102通过网络与终端104进行连接，上述网络包括但不限于：广域网、城域网或局域网，终端104并不限定于PC、手机、平板电脑等。本申请实施例的视频片段的确定方法可以由服务器102来执行，还可以是由服务器102和终端104共同执行。其中，终端104执行本申请实施例的视频片段的确定方法也可以是由安装在其上的客户端来执行。
当本申请实施例的视频片段的确定方法由服务器来单独执行时，直接在服务器上来执行与本申请实施例的方法对应的程序代码即可。
当本申请实施例的视频片段的确定方法由服务器和终端共同来执行时，由终端发送操作记录至服务器，此时，由服务器来执行与本申请实施例的方法对应的程序代码，并将处理的结果反馈给终端。
下面以在服务器上来执行与本申请实施例的方法对应的程序代码为例详述本申请的实施例，图2是根据本申请实施例的一种可选的视频片段 的确定方法的流程图，如图2所示，该方法可以包括以下步骤：
步骤S202，服务器获取目标视频的操作记录，每条操作记录用于指示第一播放时刻和在第一播放时刻对目标视频已执行的一个操作，第一播放时刻为目标视频的一个播放时刻。
在上述操作记录中可包括两个部分的信息，其一是操作动作(如发表弹幕、聊天操作、参与互动、跳跃观看进度、视频截图等)、其二是操作动作的相关信息(也即流水信息，包括用户ID、操作时视频的播放时刻、操作类型、操作内容等信息)。至少包括其中的操作时视频的播放时刻和操作类型。
步骤S204，服务器从操作记录中获取目标视频的每个播放时刻上对目标视频已执行的属于目标类型的操作的数量。
上述的目标类型的操作可根据需要确定的目标片段的类型来确定哪些类型的操作属于目标类型的操作，例如，需要确定的目标片段是指热点视频片段，那么目标类型的操作就是指用于表示热点相关的操作，如发表弹幕、聊天操作、参与互动、视频截图等；再如，需要确定的目标片段是指被完整播放的片段，那么目标类型的操作就是指用于表示完整播放相关的操作，如对播放进度条执行的快进操作、快退操作、拖动操作等；需要确定的目标片段还可以是精彩片段、重点片段等。
步骤S206，服务器根据数量在目标视频中确定目标片段，在目标片段内的播放时刻上对目标视频已执行的属于目标类型的操作的总数量与目标片段的时长之间的比值至少大于对目标视频已执行的属于目标类型的操作的总数量与目标视频的时长之间的比值。
在上述步骤中，可根据需要(也即什么类型的目标片段)，对相应的用户行为(也即操作记录指示的操作)进行大数据分析，分析出用户在整个目标视频的每个播放时刻的行为数据(即执行操作的数量)，从而可根据用户的行为数据确定出需要的目标片段(也即操作的数量较密集且连续 的一个视频片段)。
通过上述步骤S202至步骤S206，服务器从获取的操作记录中获取目标视频的每个播放时刻上对目标视频已执行的属于目标类型的操作的数量；服务器根据在目标片段内的播放时刻上对目标视频已执行的属于目标类型的操作的总数量与目标片段的时长之间的比值至少大于对目标视频已执行的属于目标类型的操作的总数量与目标视频的时长之间的比值这一原则，在目标视频中确定出满足需求的目标片段，可以解决了相关技术中确定视频中需要的视频片段的效率较低的技术问题，进而达到提高在目标视频中确定出满足需求的目标片段的效率的技术效果。
下面结合步骤S202至步骤S206从技术侧进一步详述本申请的实施例。
在步骤S202提供的技术方案中，在获取目标视频的操作记录时，包括但不局限于如下两种获取方式：
方式一：服务器定时读取预先保存的操作记录，在终端播放目标视频时，服务器保存终端实时发送的操作记录至数据库，在获取目标视频的操作记录时，服务器根据目标视频的视频标识(如视频ID)从数据库中读取一定时间段内的目标视频的操作记录，以统计出目标片段(如热点视频片段)，在统计目标片段时，服务器可以定期进行统计(也即定期触发获取目标视频的操作记录这一步骤)，从而定期更新热点视频片段。
方式二：服务器实时获取终端上传的操作记录，服务器实时接收终端反馈的操作记录，通过对操作记录进行实时计算，确定当前时段的热点视频片段。
在步骤S204提供的技术方案中，从操作记录中获取目标视频的每个播放时刻上对目标视频已执行的属于目标类型的操作的数量。
由于获取操作记录的方式不同，那么“从操作记录中获取目标视频的每个播放时刻上对目标视频已执行的属于目标类型的操作的数量”中数量的含义也有所不同，具体实践本申请实施例的方法时可以根据需求进行选择：
对于方式一的定时读取预先保存的操作记录(如读取当前时刻前某个时段内的操作记录)，其相当于计算出的是数量是之前的某个时段内的特征(如是否为热点)。
对于方式二的实时获取终端上传的操作记录，其相当于是实时计算出当前时刻的特征(如是否为热点)。
对于如何从操作记录中获取目标视频的每个播放时刻上对目标视频已执行的属于目标类型的操作的数量，本申请实施例提供了如下的获取方式：
步骤S2042，服务器首先对所有的操作记录进行过滤，从多条操作记录中获取有效的第一操作记录，第一操作记录用于指示在第一播放时刻对目标视频已执行目标类型的操作。
可选地，服务器可以单线程或者多线程的执行步骤S2042至步骤S2044。在执行步骤S2042的从多条操作记录中获取第一操作记录时，服务器在每个线程上执行如下操作：获取多条操作记录中的一条操作记录；在获取的操作记录中记录的操作标识用于指示目标类型的操作(如发表弹幕、聊天操作、参与互动、视频截图等)的情况下，将获取的操作记录记为第一操作记录。
步骤S2044，服务器根据所有第一操作记录中记录的第一播放时刻确定目标视频的每个播放时刻上对目标视频已执行的目标类型的操作的数量。
可选地，服务器可先对目标视频的每个播放时刻上对目标视频已执行的目标类型的操作的数量进行初始化，也即将数量记为0；然后逐个获取 每个第一操作记录(或者在步骤S2042的过滤出一个第一操作记录时)，读取该第一操作记录中记录的播放时刻(即第一播放时刻)，并对该播放时刻对应的数量执行加1的操作；重复上述操作直至将所有第一操作记录统计完毕，得到目标视频的每个播放时刻上为目标类型的操作的数量。
在步骤S206提供的技术方案中，服务器根据数量在目标视频中确定目标片段，在目标片段内的播放时刻上对目标视频已执行的属于目标类型的操作的总数量与目标片段的时长之间的比值至少大于对目标视频已执行的属于目标类型的操作的总数量与目标视频的时长之间的比值。步骤S206提供的实施例可通过如下的步骤实现：
步骤S2062，服务器获取目标视频中目标播放时段的操作密度，目标播放时段为目标视频中任意一个播放时长为第一阈值的播放时段，操作密度为在目标播放时段内已执行的属于目标类型的操作的总数量与第一阈值之间的比值。
在获取目标视频中目标播放时段的操作密度时，此时的目标播放时段可以为一个固定值(也即第一阈值，如1秒、5秒、10秒、1分钟)，初始时获取的目标视频可以按照某个特定时间间隔(如相邻的两个目标播放时段的起始播放时刻之间间隔一个单位时间，如1秒、1分钟等)来获取，也即得到的是多个目标播放时段，然后再计算目标视频中多个目标播放时段的操作密度。
如图3所示的播放时间轴，以第一阈值为5个单位时间(如秒、10秒、分等)为例，第一个目标播放时段A对应于第0至第5个播放时刻，第二个目标播放时段B对应于第1至第6个播放时刻，第三个目标播放时段C对应于第2至第7个播放时刻，依次类推，确定各个目标播放时段。
在确定了各个目标播放时段之后，统计每个目标播放时段各个播放时刻内的操作总数量，并计算总数量与第一阈值之间的比值(也即操作密度)。
步骤S2064，服务器在目标播放时段的操作密度大于第二阈值的情况下，确定目标播放时段所在的视频片段为目标片段，第二阈值大于等于对目标视频已执行的属于目标类型的操作的总数量与目标视频的时长之间的比值。
可选地，“在目标播放时段的操作密度大于第二阈值的情况下，确定目标播放时段所在的视频片段为目标片段”可以有两个方面的含义：其一是直接将以目标播放时段的起始播放时刻为起始播放时刻，并以目标播放时段的结束播放时刻为结束播放时刻的视频片段为目标片段；第二个则是目标片段至少包括该目标播放时段所在的视频片段。下面对第二种进行详述：
在目标播放时段的操作密度大于第二阈值的情况下，确定目标播放时段所在的视频片段为目标片段包括：在目标播放时段为多个的情况下，将所有操作密度大于第二阈值的目标播放时段(如图3所示的时段A、B、C、D、F)设置为待处理状态保存至待处理集合中(步骤S20642至步骤S20648中的目标播放时段均为操作密度大于第二阈值的播放时段)，对目标播放时段执行以下操作，直到所有目标播放时段处于已处理状态：
步骤S20642，服务器每次处理时从待处理集合中取出一个作为当前处理的，将当前处理的目标播放时段记为第一播放时段，如将取出的目标播放时段B记为第一播放时段。
步骤S20644，服务器将第一播放时段B与待处理集合中的元素(如时段A、C、D、F)比较，在存在与第一播放时段交叉的目标播放时段的情况下，将与第一播放时段交叉的目标播放时段和第一播放时段合并为第二播放时段，并将第二播放时段作为处于待处理状态的目标播放时段，如时段A与时段B交叉，将时段A和时段B合并，合并后对应于第0至第6个播放时刻。
若下一次取出的第一播放时段为上述合并后的目标播放时段(上述对应于第0至第6个播放时刻)，则继续判断是否有与之交叉的目标播放时 段，可以看出其与时段C交叉，则进行合并，合并后依然与时段D交叉，则继续合并，得到的目标播放时段记为G(对应于第0至第8个播放时刻)。
步骤S20646，在第一播放时段与相邻的目标播放时段之间的时间间隔小于第三阈值的情况下，服务器将第一播放时段、相邻的目标播放时段以及时间间隔合并为第三播放时段，并将第三播放时段作为处于待处理状态的目标播放时段。
上述的第三阈值可根据实际需要进行设定，如设定为5个单位时间。
由于时段G和时段F之间的时间间隔(时段G的结束播放时刻与时段F的起始播放时刻之间的间隔)不小于第三阈值5，则不合并时段G和时段F。
步骤S20648，在第一播放时段与相邻的目标播放时段之间的时间间隔不小于第三阈值的情况下，服务器将第一播放时段设置为处于已处理状态的目标播放时段，并将处于已处理状态的目标播放时段所在的视频片段作为一个目标片段。
由于相邻的时段G和时段F之间的时间间隔不小于第三阈值5，则可以将时段G设置为处于已处理状态的目标播放时段，并将时段G所在的视频片段作为一个目标片段。
步骤S2066，在确定目标播放时段所在的视频片段为目标片段之后，服务器可对目标片段采用如下方式进行修正：
步骤S20662，在目标片段的起始播放时刻所在的视频帧不为关键帧的情况下，服务器将距离目标片段的起始播放时刻最近的关键帧所在的第一播放时刻作为目标片段的起始播放时刻。
上述的关键帧指角色或者物体运动或变化中的关键动作所处的那一帧。
步骤S20664，在目标片段的结束播放时刻所在的视频帧不为关键帧 的情况下，服务器将距离目标片段的结束播放时刻最近的关键帧所在的第二播放时刻作为目标片段的结束播放时刻。
可选地，上述的第一播放时刻为早于修正前的目标片段的起始播放时刻；第二播放时刻为晚于修正前的目标片段的结束播放时刻。
本申请实施例的上述步骤S202至步骤S206所提供的方法可应用于视频花絮、热点运营等业务场景下，例如应用于热点运营中的热点视频标注，可基于大数据挖掘的视频精彩片段自动标注和截取。该方案通过采集视频观看用户的主动行为，如发表弹幕、跳跃观看、视频截图等行为数据，通过数据统计和挖掘等技术，自动发现标注视频的热点部分，再根据热点的分布情况进行精彩片段的截取。
作为一种可选的实施例，下面以如图4所示的热点视频标注为例进行详述：
步骤S21，在产品上梳理哪些用户使用行为(也即属于目标类型的操作)，与视频内容的精彩程度相关(如发表弹幕、跳跃观看、视频截图等行为)。对这些行为，预先设计好行为上报操作记录的规范定义(包括用户ID，操作时间、视频ID，观看节点、行为类型等)，并进行数据打点，在应用客户端对应的场景时机下进行数据上报。
步骤S22，应用进行操作记录数据上报，应用按照上报产品的定义要求，确保数据按约定完整上报到后端服务器的数据存储平台数据库。
步骤S23，后端服务器收集到用户行为数据后，基于海量用户的共同行为操作，通过数据建模或规则统计的方式，利用数据统计模型计算得到各个视频的精彩片段所在的相关标识信息。得到相关标识信息后，后端服务器可以直接截取相关子片段或截图，用于分享传播；也可以将相关信息同步给客户端播放器，用于应用播放场景的热点标识和快速跳转等。
步骤S24，客户端获取到的精彩片段标识，可以通过在线服务的方式，由服务器提供给应用前端调用。前端应用通过视频ID，就可以获取到相关精彩片段标识信息。
如在终端播放目标视频时，服务器发送指示信息至终端，通过指示信息指示终端对目标片段进行标识，进行显示标识或者标注数据；或者在接收到播放目标视频的请求时，发送指示信息至终端。
步骤S25，前端获取到标识信息后，在视频播放场景下，用户点击拉起播放器后，可以在播放进度条的地方，展示精彩片断的标识打点信息。进行交互时，可以快速跳转至精彩片段的播放位置，满足用户快速观看精彩内容的诉求。
该方案以服务器自动截取的方式替代相关技术中的人工处理方式，当视频编辑收到即将上线的内容介质时，不需进行视频热点片段的标注和记录，先完成视频的审核上架即可；内容上架后，视频播放终端(如安卓手机、iphone手机、PC、WEB、TV等视频客户端)对用户的观影动作(比如发表弹幕、参与互动、跳跃观看进度、视频截图等)的流水信息(包括用户ID、操作时间、操作类型、操作内容等信息字段)进行识别提取并上报，后台收到上报信息(也即操作记录)后入库到大数据存储平台上；大数据平台收到上报记录后，根据各上报动作代表的行为意义和动作时间的分布情况，计算得到视频精彩片段的起止标识。通过该方案，至少可以达到如下效果：
(1)不用依赖于人工选取待标注的目标片段，视频片段的选取和标注均通过服务器自动运行，标注的效率较高。
(2)对视频片段的精彩程度、或话题引爆可能性的判断，完全依赖于用户行为大数据进行判断，和用户真实兴趣点匹配度非常高。
(3)不同于人工标注偏向一次性工作(出于人力和成本等原因，标注完一次后基本就保持不变)，难以适应在视频播出过程出现热点轮换等 动态情况，在本申请实施例的技术方案中可以实时计算出目标片段，以实时显示作为热点的目标片段，也可以根据某一段或者所有历史用户行为数据定时进行目标片段的计算，以对前一次的计算出的热点片段进行更新。
本申请还提供了一种优选实施例，该优选实施例以如图5所示的制作精彩视频集锦为例进行详述：
步骤S502，在前端客户端预埋用户行为数据收集逻辑，由客户端上报用户使用行为的操作记录。
步骤S504，数据仓库将客户端前端上报的数据入库到大数据平台，通过对数据进行转换清洗，过滤处理得到属于目标类型的操作的数据，以用于后续的计算服务。
步骤S506，统计建模计算服务：按照视频标识VID的粒度，划分汇总各VID相关的所有上报记录；对各VID的上报记录时机，采用基于密度的聚类算法，划分出大类，找到精彩片段的所在区域；然后再通过正态分布法，找出该区域的中间位置，作为片段边沿的分隔点；结合聚类的区间分布，以及分隔点的关系，两两结合得到各精彩片段的起止位置。
步骤S508，由于视频采用压缩技术，前一步骤中获取到的起止位置可能无法直接对应到1个清晰完整的图像画面。为获得更好的视频画质，可对片段的起止位置再进行优化，将视频片段的起止位置调整到前后最近的关键帧上，作为最终的片段边沿位置。
步骤S510，获取到片段的起止位置后，系统可以将视频精彩片段的相关信息导入到在线系统，供各业务场景使用。
步骤S512，直接截取出相关片段内容，制作为一个精彩视频集锦，直接进行分享传播。
在本申请实施例的技术方案中，引入大数据统计和数据挖掘技术，基 于用户主动的共同行为，机器自动发现标识视频的精彩内容，减少对编辑运营经验的依赖；由机器完全自动化运行，替代现有人工处理方式，降低了成本并提升了处理效率。
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请实施例并不受所描述的动作顺序的限制，因为依据本申请实施例，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本申请实施例所必须的。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到根据上述实施例的方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请实施例的技术方案本质上或者说对相关技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，或者网络设备等)执行本申请各个实施例所述的方法。
根据本申请实施例的另一个方面，还提供了一种用于实施上述视频片段的确定方法的视频片段的确定装置。图6是根据本申请实施例的一种可选的视频片段的确定装置的示意图，如图6所示，该装置可以包括一个或多个处理器，以及一个或多个存储程序单元的存储器，其中，程序单元由处理器执行，该程序单元包括：第一获取单元62、第二获取单元64以及确定单元66。
第一获取单元62，被设置为获取目标视频的操作记录，每条操作记录用于指示第一播放时刻和在第一播放时刻对目标视频已执行的一个操作，第一播放时刻为目标视频的一个播放时刻。
在上述操作记录中可包括两个部分的信息，其一是操作动作(如发表弹幕、聊天操作、参与互动、跳跃观看进度、视频截图等)、其二是操作动作的相关信息(也即流水信息，包括用户ID、操作时视频的播放时刻、操作类型、操作内容等信息)。至少包括其中的操作时视频的播放时刻和操作类型。
第二获取单元64，被设置为从操作记录中获取目标视频的每个播放时刻上对目标视频已执行的属于目标类型的操作的数量。
上述的目标类型的操作可根据需要确定的目标片段的类型来确定哪些类型的操作属于目标类型的操作，例如，需要确定的目标片段是指热点视频片段，那么目标类型的操作就是指用于表示热点相关的操作，如发表弹幕、聊天操作、参与互动、视频截图等；再如，需要确定的目标片段是指被完整播放的片段，那么目标类型的操作就是指用于表示完整播放相关的操作，如对播放进度条执行的快进操作、快退操作、拖动操作等；需要确定的目标片段还可以是精彩片段、重点片段等。
确定单元66，被设置为根据数量在目标视频中确定目标片段，在目标片段内的播放时刻上对目标视频已执行的属于目标类型的操作的总数量与目标片段的时长之间的比值至少大于对目标视频已执行的属于目标类型的操作的总数量与目标视频的时长之间的比值。
在上述步骤中，可根据需要(也即什么类型的目标片段)，对相应的用户行为(也即操作记录指示的操作)进行大数据分析，分析出用户在整个目标视频的每个播放时刻的行为数据(即执行操作的数量)，从而可根据用户的行为数据确定出需要的目标片段(也即操作的数量较密集且连续的一个视频片段)。
需要说明的是，该实施例中的第一获取单元62可以被设置为执行本申请实施例中的步骤S202，该实施例中的第二获取单元64可以被设置为执行本申请实施例中的步骤S204，该实施例中的确定单元66可以被设置为执行本申请实施例中的步骤S206。
此处需要说明的是，上述模块与对应的步骤所实现的示例和应用场景相同，但不限于上述实施例所公开的内容。需要说明的是，上述模块作为装置的一部分可以运行在如图1所示的硬件环境中，可以通过软件实现，也可以通过硬件实现。
通过上述模块，从获取的操作记录中获取目标视频的每个播放时刻上对目标视频已执行的属于目标类型的操作的数量；根据在目标片段内的播放时刻上对目标视频已执行的属于目标类型的操作的总数量与目标片段的时长之间的比值至少大于对目标视频已执行的属于目标类型的操作的总数量与目标视频的时长之间的比值这一原则，在目标视频中确定出满足需求的目标片段，可以解决了相关技术中确定视频中需要的视频片段的效率较低的技术问题，进而达到提高在目标视频中确定出满足需求的目标片段的效率的技术效果。
可选地，如图7所示，第二获取单元包括：第一获取模块642，被设置为从多条操作记录中获取第一操作记录，其中，第一操作记录用于指示在第一播放时刻对目标视频已执行目标类型的操作；第一确定模块644，被设置为根据所有第一操作记录中记录的第一播放时刻确定目标视频的每个播放时刻上对目标视频已执行的目标类型的操作的数量。
上述的第一获取模块获取多条操作记录中的一条操作记录；在获取的操作记录中记录的操作标识用于指示目标类型的操作的情况下，将获取的操作记录记为第一操作记录。
可选地，确定单元包括：第二获取模块，被设置为获取目标视频中目标播放时段的操作密度，其中，目标播放时段为目标视频中任意一个播放时长为第一阈值的播放时段，操作密度为在目标播放时段内已执行的属于目标类型的操作的总数量与第一阈值之间的比值；第二确定模块，被设置为在目标播放时段的操作密度大于第二阈值的情况下，确定目标播放时段所在的视频片段为目标片段，其中，第二阈值大于等于对目标视频已执行的属于目标类型的操作的总数量与目标视频的时长之间的比值。
上述的第二获取模块还被设置为获取目标视频中多个目标播放时段的操作密度，其中，相邻的两个目标播放时段的起始播放时刻之间间隔一个单位时间。
上述的第二确定模块还被设置为在目标播放时段为多个的情况下，将所有目标播放时段设置为待处理状态，对目标播放时段执行以下操作，直到所有目标播放时段处于已处理状态：
将当前处理的目标播放时段记为第一播放时段；
在存在与第一播放时段交叉的目标播放时段的情况下，将与第一播放时段交叉的目标播放时段和第一播放时段合并为第二播放时段，并将第二播放时段作为处于待处理状态的目标播放时段；
在第一播放时段与相邻的目标播放时段之间的时间间隔小于第三阈值的情况下，将第一播放时段、相邻的目标播放时段以及时间间隔合并为第三播放时段，并将第三播放时段作为处于待处理状态的目标播放时段；
在第一播放时段与相邻的目标播放时段之间的时间间隔不小于第三阈值的情况下，将第一播放时段设置为处于已处理状态的目标播放时段，并将处于已处理状态的目标播放时段所在的视频片段作为一个目标片段。
可选地，确定单元在确定目标播放时段所在的视频片段为目标片段之后，还被设置为对目标片段采用如下方式进行修正：
在目标片段的起始播放时刻所在的视频帧不为关键帧的情况下，将距离目标片段的起始播放时刻最近的关键帧所在的第一播放时刻作为目标片段的起始播放时刻；
在目标片段的结束播放时刻所在的视频帧不为关键帧的情况下，将距离目标片段的结束播放时刻最近的关键帧所在的第二播放时刻作为目标片段的结束播放时刻。
上述的第一播放时刻为早于修正前的目标片段的起始播放时刻；第二 播放时刻为晚于修正前的目标片段的结束播放时刻。
可选地，确定单元在根据数量在目标视频中确定目标片段之后，还被设置为执行以下至少之一：在终端播放目标视频时，发送指示信息至终端，其中，指示信息用于指示终端对目标片段进行标识；在接收到播放目标视频的请求时，发送指示信息至终端；在目标片段为多个的情况下，将多个目标片段合并为一个视频。
本申请实施例的技术方案以服务器自动截取的方式替代相关技术中的人工处理方式，当视频编辑收到即将上线的内容介质时，不需进行视频热点片段的标注和记录，先完成视频的审核上架即可；内容上架后，视频播放终端(如安卓手机、iphone手机、PC、WEB、TV等视频客户端)对用户的观影动作(比如发表弹幕、参与互动、跳跃观看进度、视频截图等)的流水信息(包括用户ID、操作时间、操作类型、操作内容等信息字段)进行识别提取并上报，后台收到上报信息(也即操作记录)后入库到大数据存储平台上；大数据平台收到上报记录后，根据各上报动作代表的行为意义和动作时间的分布情况，计算得到视频精彩片段的起止标识。通过该方案，至少可以达到如下效果：
(1)不用依赖于人工选取待标注的目标片段，视频片段的选取和标注均通过服务器自动运行，标注的效率较高。
(2)对视频片段的精彩程度、或话题引爆可能性的判断，完全依赖于用户行为大数据进行判断，和用户真实兴趣点匹配度非常高。
(3)不同于人工标注偏向一次性工作(出于人力和成本等原因，标注完一次后基本就保持不变)，难以适应在视频播出过程出现热点轮换等动态情况，在本申请实施例的技术方案中可以实时计算出目标片段，以实时显示作为热点的目标片段，也可以根据某一段或者所有历史用户行为数据定时进行目标片段的计算，以对前一次的计算出的热点片段进行更新。
此处需要说明的是，上述模块与对应的步骤所实现的示例和应用场景 相同，但不限于上述实施例所公开的内容。需要说明的是，上述模块作为装置的一部分可以运行在如图1所示的硬件环境中，可以通过软件实现，也可以通过硬件实现，其中，硬件环境包括网络环境。
根据本申请实施例的另一个方面，还提供了一种用于实施上述视频片段的确定方法的电子装置，该电子装置可以是服务器或终端。
图8是根据本申请实施例的一种电子装置的结构框图，下面以该电子装置是终端为例来进行说明，如图8所示，该终端可以包括：一个或多个(图8中仅示出一个)处理器801、存储器803、以及传输装置805(如上述实施例中的发送装置)，如图8所示，该终端还可以包括输入输出设备807。
其中，存储器803可被设置为存储软件程序以及模块，如本申请实施例中的视频片段的确定方法和装置对应的程序指令/模块，处理器801通过运行存储在存储器803内的软件程序以及模块，从而执行各种功能应用以及数据处理，即实现上述的视频片段的确定方法。存储器803可包括高速随机存储器，还可以包括非易失性存储器，如一个或者多个磁性存储装置、闪存、或者其他非易失性固态存储器。在一些实例中，存储器803可进一步包括相对于处理器801远程设置的存储器，这些远程存储器可以通过网络连接至终端。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
上述的传输装置805被设置为经由一个网络接收或者发送数据，还可以用于处理器与存储器之间的数据传输。上述的网络具体实例可包括有线网络及无线网络。在一个实例中，传输装置805包括一个网络适配器(Network Interface Controller，NIC)，其可通过网线与其他网络设备与路由器相连从而可与互联网或局域网进行通讯。在一个实例中，传输装置805为射频(Radio Frequency，RF)模块，其用于通过无线方式与互联网进行通讯。
其中，具体地，存储器803被设置为存储应用程序。
处理器801可以通过传输装置805调用存储器803存储的应用程序，以执行下述步骤：获取目标视频的操作记录，每条操作记录用于指示第一播放时刻和在第一播放时刻对目标视频已执行的一个操作，第一播放时刻为目标视频的一个播放时刻；从操作记录中获取目标视频的每个播放时刻上对目标视频已执行的属于目标类型的操作的数量；根据数量在目标视频中确定目标片段，在目标片段内的播放时刻上对目标视频已执行的属于目标类型的操作的总数量与目标片段的时长之间的比值至少大于对目标视频已执行的属于目标类型的操作的总数量与目标视频的时长之间的比值。
处理器801还被设置为执行下述步骤：将当前处理的目标播放时段记为第一播放时段；在存在与第一播放时段交叉的目标播放时段的情况下，将与第一播放时段交叉的目标播放时段和第一播放时段合并为第二播放时段，并将第二播放时段作为处于待处理状态的目标播放时段；在第一播放时段与相邻的目标播放时段之间的时间间隔小于第三阈值的情况下，将第一播放时段、相邻的目标播放时段以及时间间隔合并为第三播放时段，并将第三播放时段作为处于待处理状态的目标播放时段；在第一播放时段与相邻的目标播放时段之间的时间间隔不小于第三阈值的情况下，将第一播放时段设置为处于已处理状态的目标播放时段，并将处于已处理状态的目标播放时段所在的视频片段作为一个目标片段。
采用本申请实施例，从获取的操作记录中获取目标视频的每个播放时刻上对目标视频已执行的属于目标类型的操作的数量；根据在目标片段内的播放时刻上对目标视频已执行的属于目标类型的操作的总数量与目标片段的时长之间的比值至少大于对目标视频已执行的属于目标类型的操作的总数量与目标视频的时长之间的比值这一原则，在目标视频中确定出满足需求的目标片段，可以解决了相关技术中确定视频中需要的视频片段的效率较低的技术问题，进而达到了提高在目标视频中确定出满足需求的目标片段的效率的技术效果。
可选地，本实施例中的具体示例可以参考上述实施例中所描述的示例，本实施例在此不再赘述。
本领域普通技术人员可以理解，图8所示的结构仅为示意，终端可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌上电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。图8其并不对上述电子装置的结构造成限定。例如，终端还可包括比图8中所示更多或者更少的组件(如网络接口、显示装置等)，或者具有与图8所示不同的配置。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令终端设备相关的硬件来完成，该程序可以存储于一计算机可读存储介质中，存储介质可以包括：闪存盘、只读存储器(Read-Only Memory，ROM)、随机存取器(Random Access Memory，RAM)、磁盘或光盘等。
本申请的实施例还提供了一种存储介质。可选地，在本实施例中，上述存储介质可以用于执行视频片段的确定方法的程序代码。
可选地，在本实施例中，上述存储介质可以位于上述实施例所示的网络中的多个网络设备中的至少一个网络设备上。
可选地，在本实施例中，存储介质被设置为存储用于执行以下步骤的程序代码：
S31，获取目标视频的操作记录，每条操作记录用于指示第一播放时刻和在第一播放时刻对目标视频已执行的一个操作，第一播放时刻为目标视频的一个播放时刻；
S32，从操作记录中获取目标视频的每个播放时刻上对目标视频已执行的属于目标类型的操作的数量；
S33，根据数量在目标视频中确定目标片段，在目标片段内的播放时刻上对目标视频已执行的属于目标类型的操作的总数量与目标片段的时 长之间的比值至少大于对目标视频已执行的属于目标类型的操作的总数量与目标视频的时长之间的比值。
可选地，存储介质还被设置为存储用于执行以下步骤的程序代码：
S41，将当前处理的目标播放时段记为第一播放时段；
S42，在存在与第一播放时段交叉的目标播放时段的情况下，将与第一播放时段交叉的目标播放时段和第一播放时段合并为第二播放时段，并将第二播放时段作为处于待处理状态的目标播放时段；
S43，在第一播放时段与相邻的目标播放时段之间的时间间隔小于第三阈值的情况下，将第一播放时段、相邻的目标播放时段以及时间间隔合并为第三播放时段，并将第三播放时段作为处于待处理状态的目标播放时段；
S44，在第一播放时段与相邻的目标播放时段之间的时间间隔不小于第三阈值的情况下，将第一播放时段设置为处于已处理状态的目标播放时段，并将处于已处理状态的目标播放时段所在的视频片段作为一个目标片段。
可选地，本实施例中的具体示例可以参考上述实施例中所描述的示例，本实施例在此不再赘述。
可选地，在本实施例中，上述存储介质可以包括但不限于：U盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
上述实施例中的集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在上述计算机可读取的存储介质中。基于这样的理解，本申请实施例的技术方案本质上或者说对相关技术做出 贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在存储介质中，包括若干指令用以使得一台或多台计算机设备(可为个人计算机、服务器或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。
在本申请的上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。
在本申请所提供的几个实施例中，应该理解到，所揭露的客户端，可通过其它的方式实现。其中，以上所描述的装置实施例仅仅是示意性的，例如所述单元的划分，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，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，单元或模块的间接耦合或通信连接，可以是电性或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
以上所述仅是本申请的优选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本申请实施例原理的前提下，还可以做出若干改进和润饰，这些改进和润饰也应视为本申请实施例的保护范围。
工业实用性
通过本申请实施例，从获取的操作记录中获取目标视频的每个播放时 刻上对目标视频已执行的属于目标类型的操作的数量；根据在目标片段内的播放时刻上对目标视频已执行的属于目标类型的操作的总数量与目标片段的时长之间的比值至少大于对目标视频已执行的属于目标类型的操作的总数量与目标视频的时长之间的比值这一原则，在目标视频中确定出满足需求的目标片段，可以解决了相关技术中确定视频中需要的视频片段的效率较低的技术问题，进而达到了提高在目标视频中确定出满足需求的目标片段的效率的技术效果。

Claims (14)

  1. 一种视频片段的确定方法，包括：
    获取目标视频的操作记录，其中，每条所述操作记录用于指示第一播放时刻和在所述第一播放时刻对所述目标视频已执行的一个操作，所述第一播放时刻为所述目标视频的一个播放时刻；
    从所述操作记录中获取所述目标视频的每个播放时刻上对所述目标视频已执行的属于目标类型的操作的数量；
    根据所述数量在所述目标视频中确定目标片段，其中，在所述目标片段内的播放时刻上对所述目标视频已执行的属于目标类型的操作的总数量与所述目标片段的时长之间的比值至少大于对所述目标视频已执行的属于所述目标类型的操作的总数量与所述目标视频的时长之间的比值。
  2. 根据权利要求1所述的方法，其中，从所述操作记录中获取所述目标视频的每个播放时刻上对所述目标视频已执行的属于目标类型的操作的数量包括：
    从多条所述操作记录中获取第一操作记录，其中，所述第一操作记录用于指示在所述第一播放时刻对所述目标视频已执行所述目标类型的操作；
    根据所有所述第一操作记录中记录的所述第一播放时刻确定所述目标视频的每个播放时刻上对所述目标视频已执行的所述目标类型的操作的数量。
  3. 根据权利要求2所述的方法，其中，从多条所述操作记录中获取第一操作记录包括：
    获取多条所述操作记录中的一条所述操作记录；
    在获取的所述操作记录中记录的操作标识用于指示所述目标类型的操作的情况下，将获取的所述操作记录记为所述第一操作记录。
  4. 根据权利要求1至3中任一项所述的方法，其中，根据所述数量在所述目标视频中确定目标片段包括：
    获取所述目标视频中目标播放时段的操作密度，其中，所述目标播放时段为所述目标视频中任意一个播放时长为第一阈值的播放时段，所述操作密度为在所述目标播放时段内已执行的属于所述目标类型的操作的总数量与所述第一阈值之间的比值；
    在所述目标播放时段的操作密度大于第二阈值的情况下，确定所述目标播放时段所在的视频片段为所述目标片段，其中，所述第二阈值大于等于对所述目标视频已执行的属于所述目标类型的操作的总数量与所述目标视频的时长之间的比值。
  5. 根据权利要求4所述的方法，其中，在所述目标播放时段的操作密度大于第二阈值的情况下，确定所述目标播放时段所在的视频片段为所述目标片段包括：在所述目标播放时段为多个的情况下，将所有所述目标播放时段设置为待处理状态，对所述目标播放时段执行以下操作，直到所有所述目标播放时段处于已处理状态：
    将当前处理的所述目标播放时段记为第一播放时段；
    在存在与所述第一播放时段交叉的所述目标播放时段的情况下，将与所述第一播放时段交叉的所述目标播放时段和所述第一播放时段合并为第二播放时段，并将所述第二播放时段作为处于待处理状态的所述目标播放时段；
    在所述第一播放时段与相邻的所述目标播放时段之间的时间间隔小于第三阈值的情况下，将所述第一播放时段、相邻的所述目标播放时段以及所述时间间隔合并为第三播放时段，并将所述第三播放时段作为处于待处理状态的所述目标播放时段；
    在所述第一播放时段与相邻的所述目标播放时段之间的时间间隔不小于所述第三阈值的情况下，将所述第一播放时段设置为处于已处理状态的所述目标播放时段，并将处于已处理状态的所述目标播放时段所在的视频片段作为一个所述目标片段。
  6. 根据权利要求4所述的方法，其中，在确定所述目标播放时段所在的视频片段为所述目标片段之后，所述方法还包括对所述目标片段采用如下方式进行修正：
    在所述目标片段的起始播放时刻所在的视频帧不为关键帧的情况下，将距离所述目标片段的起始播放时刻最近的关键帧所在的第一播放时刻作为所述目标片段的起始播放时刻；
    在所述目标片段的结束播放时刻所在的视频帧不为关键帧的情况下，将距离所述目标片段的结束播放时刻最近的关键帧所在的第二播放时刻作为所述目标片段的结束播放时刻。
  7. 根据权利要求6所述的方法，其中，
    所述第一播放时刻为早于修正前的所述目标片段的起始播放时刻；
    所述第二播放时刻为晚于修正前的所述目标片段的结束播放时刻。
  8. 根据权利要求4所述的方法，其中，获取所述目标视频中目标播放时段的操作密度包括：
    获取所述目标视频中多个所述目标播放时段的操作密度，其中，相邻的两个所述目标播放时段的起始播放时刻之间间隔一个单位时间。
  9. 根据权利要求1所述的方法，其中，在根据所述数量在所述目标视频中确定目标片段之后，所述方法还包括以下至少之一：
    在终端播放所述目标视频时，发送指示信息至所述终端，其中，所述指示信息用于指示所述终端对所述目标片段进行标识；
    在接收到播放所述目标视频的请求时，发送所述指示信息至所述终端；
    在所述目标片段为多个的情况下，将多个所述目标片段合并为一个视频。
  10. 一种视频片段的确定装置，包括一个或多个处理器，以及一个或多个存储程序单元的存储器，其中，所述程序单元由所述处理器执行，所述程序单元包括：
    第一获取单元，被设置为获取目标视频的操作记录，其中，每条所述操作记录用于指示第一播放时刻和在所述第一播放时刻对所述目标视频已执行的一个操作，所述第一播放时刻为所述目标视频的一个播放时刻；
    第二获取单元，被设置为从所述操作记录中获取所述目标视频的每个播放时刻上对所述目标视频已执行的属于目标类型的操作的数量；
    确定单元，被设置为根据所述数量在所述目标视频中确定目标片段，其中，在所述目标片段内的播放时刻上对所述目标视频已执行的属于目标类型的操作的总数量与所述目标片段的时长之间的比值至少大于对所述目标视频已执行的属于所述目标类型的操作的总数量与所述目标视频的时长之间的比值。
  11. 根据权利要求10所述的装置，其中，所述第二获取单元包括：
    第一获取模块，被设置为从多条所述操作记录中获取第一操作记录，其中，所述第一操作记录用于指示在所述第一播放时刻对所述目标视频已执行所述目标类型的操作；
    第一确定模块，被设置为根据所有所述第一操作记录中记录的所述第一播放时刻确定所述目标视频的每个播放时刻上对所述目标视频已执行的所述目标类型的操作的数量。
  12. 根据权利要求10至11中任一项所述的装置，其中，所述确定单元包括：
    第二获取模块，被设置为获取所述目标视频中目标播放时段的操作密度，其中，所述目标播放时段为所述目标视频中任意一个播放时长为第一阈值的播放时段，所述操作密度为在所述目标播放时段内已 执行的属于所述目标类型的操作的总数量与所述第一阈值之间的比值；
    第二确定模块，被设置为在所述目标播放时段的操作密度大于第二阈值的情况下，确定所述目标播放时段所在的视频片段为所述目标片段，其中，所述第二阈值大于等于对所述目标视频已执行的属于所述目标类型的操作的总数量与所述目标视频的时长之间的比值。
  13. 一种存储介质，所述存储介质包括存储的程序，其中，所述程序运行时执行上述权利要求1至9任一项中所述的方法。
  14. 一种电子装置，包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，其特征在于，所述处理器通过所述计算机程序执行上述权利要求1至9任一项中所述的方法。
PCT/CN2018/106262 2017-09-21 2018-09-18 视频片段的确定方法、装置、存储介质及电子装置 WO2019057034A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US16/802,318 US11363353B2 (en) 2017-09-21 2020-02-26 Video highlight determination method and apparatus, storage medium, and electronic device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710862009.7A CN109547859B (zh) 2017-09-21 2017-09-21 视频片段的确定方法和装置
CN201710862009.7 2017-09-21

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/802,318 Continuation US11363353B2 (en) 2017-09-21 2020-02-26 Video highlight determination method and apparatus, storage medium, and electronic device

Publications (1)

Publication Number Publication Date
WO2019057034A1 true WO2019057034A1 (zh) 2019-03-28

Family

ID=65810972

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/106262 WO2019057034A1 (zh) 2017-09-21 2018-09-18 视频片段的确定方法、装置、存储介质及电子装置

Country Status (3)

Country Link
US (1) US11363353B2 (zh)
CN (1) CN109547859B (zh)
WO (1) WO2019057034A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112969100A (zh) * 2021-03-24 2021-06-15 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

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110166817A (zh) * 2019-06-24 2019-08-23 北京奇艺世纪科技有限公司 一种数据缓存方法及相关设备
CN110611841B (zh) * 2019-09-06 2021-07-30 Oppo广东移动通信有限公司 整合方法、终端和可读存储介质
CN111026558B (zh) * 2019-11-25 2020-11-17 上海哔哩哔哩科技有限公司 基于微信小程序的弹幕处理方法和系统
CN112995649B (zh) * 2019-12-13 2024-04-16 青岛海信宽带多媒体技术有限公司 网络终端及网络终端评测方法
CN112383827B (zh) * 2020-11-10 2023-03-31 北京乐学帮网络技术有限公司 一种视频播放控制方法及装置
CN112822504B (zh) * 2020-12-30 2023-07-25 北京达佳互联信息技术有限公司 直播间封面更新方法、装置、电子设备及存储介质
CN113052033A (zh) * 2021-03-15 2021-06-29 深圳软牛科技有限公司 视频精彩度测量方法、装置、设备及存储介质
CN113727201B (zh) * 2021-08-30 2022-08-02 北京字节跳动网络技术有限公司 一种数据处理方法、装置、计算机设备及存储介质
CN113992975B (zh) * 2021-10-13 2023-10-17 咪咕视讯科技有限公司 视频播放方法、装置、设备以及计算机存储介质
CN114630141A (zh) * 2022-03-18 2022-06-14 北京达佳互联信息技术有限公司 视频处理方法及相关设备
CN115412765B (zh) * 2022-08-31 2024-03-26 北京奇艺世纪科技有限公司 视频精彩片段确定方法、装置、电子设备及存储介质
CN116546264A (zh) * 2023-04-10 2023-08-04 北京度友信息技术有限公司 视频处理方法及装置、电子设备和存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103957433A (zh) * 2014-03-31 2014-07-30 深圳市同洲电子股份有限公司 一种视频数据的处理方法、相关设备及系统
CN104994425A (zh) * 2015-06-30 2015-10-21 北京奇艺世纪科技有限公司 一种视频标识方法和装置
CN105939494A (zh) * 2016-05-25 2016-09-14 乐视控股（北京）有限公司 音视频片段提供方法及装置
CN106170104A (zh) * 2016-07-01 2016-11-30 广州华多网络科技有限公司 视频精彩片段的确定方法、装置和服务器
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 (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040197088A1 (en) * 2003-03-31 2004-10-07 Ferman Ahmet Mufit System for presenting audio-video content
US7742111B2 (en) * 2005-05-06 2010-06-22 Mavs Lab. Inc. Highlight detecting circuit and related method for audio feature-based highlight segment detection
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
US9235765B2 (en) * 2010-08-26 2016-01-12 Blast Motion Inc. Video and motion event integration system
US20120324491A1 (en) * 2011-06-17 2012-12-20 Microsoft Corporation Video highlight identification based on environmental sensing
US8566866B1 (en) * 2012-05-09 2013-10-22 Bluefin Labs, Inc. Web identity to social media identity correlation
US9699485B2 (en) * 2012-08-31 2017-07-04 Facebook, Inc. Sharing television and video programming through social networking
US9740984B2 (en) * 2012-08-21 2017-08-22 Disney Enterprises, Inc. Characterizing motion patterns of one or more agents from spatiotemporal data
US9253533B1 (en) * 2013-03-22 2016-02-02 Amazon Technologies, Inc. Scene identification
WO2014182901A1 (en) * 2013-05-08 2014-11-13 Viki, Inc. Timed comments for media
CN104918067A (zh) * 2014-03-12 2015-09-16 乐视网信息技术（北京）股份有限公司 对视频热度进行曲线处理的方法和系统
US10433030B2 (en) * 2014-10-09 2019-10-01 Thuuz, Inc. Generating a customized highlight sequence depicting multiple events
US11146865B2 (en) * 2016-03-03 2021-10-12 Comcast Cable Communications, Llc Determining points of interest in a content item
US10681391B2 (en) * 2016-07-13 2020-06-09 Oath Inc. Computerized system and method for automatic highlight detection from live streaming media and rendering within a specialized media player

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103957433A (zh) * 2014-03-31 2014-07-30 深圳市同洲电子股份有限公司 一种视频数据的处理方法、相关设备及系统
CN104994425A (zh) * 2015-06-30 2015-10-21 北京奇艺世纪科技有限公司 一种视频标识方法和装置
CN105939494A (zh) * 2016-05-25 2016-09-14 乐视控股（北京）有限公司 音视频片段提供方法及装置
CN106170104A (zh) * 2016-07-01 2016-11-30 广州华多网络科技有限公司 视频精彩片段的确定方法、装置和服务器
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 (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112969100A (zh) * 2021-03-24 2021-06-15 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
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

Also Published As

Publication number Publication date
US11363353B2 (en) 2022-06-14
US20200213686A1 (en) 2020-07-02
CN109547859A (zh) 2019-03-29
CN109547859B (zh) 2021-12-07

Similar Documents

Publication Publication Date Title
WO2019057034A1 (zh) 视频片段的确定方法、装置、存储介质及电子装置
US20230410130A1 (en) System and method for providing crowd sourced metrics for network content broadcasters
WO2016054916A1 (zh) 视频内容的推荐、评价方法及装置
CN105872837B (zh) 用户推荐方法及装置
CN109168037B (zh) 视频播放方法和装置
CN103718166B (zh) 信息处理设备、信息处理方法
CN108632676B (zh) 图像的显示方法、装置、存储介质及电子装置
CN108462883B (zh) 一种直播互动方法、装置、终端设备及存储介质
CN103731631B (zh) 一种传输视频图像的方法、装置及系统
CN103945240A (zh) 一种基于视频聚合的视频播放方法及装置
CN104168303A (zh) 一种展示网络直播间的方法和装置
US10237583B1 (en) Execution of cases based on barcodes in video feeds
CN104581407A (zh) 一种视频预览的方法和装置
WO2017161744A1 (zh) 一种视频推荐方法及装置
CN106488253A (zh) 直播视频互动数据处理方法及装置
CN102036058A (zh) 视频监控系统中视频切换的方法、服务器、终端及系统
CN112019905A (zh) 直播回放方法、计算机设备及可读存储介质
CN113301397A (zh) 基于cdn的音视频传输、播放与延时探测方法及设备
WO2023077813A1 (zh) 确定直播间刷量的方法及装置
AU2018275194A1 (en) Temporal placement of a rebuffering event
CN106982391A (zh) 一种信息推送方法、终端、服务器及系统
CN103442264A (zh) 基于视频监测的收视分析方法及系统
CN111193945A (zh) 广告播放处理方法和装置
CN104537011A (zh) 歌唱排名方法及装置
CN106131673A (zh) 用于实现群聊的装置、系统及方法

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: 18858680

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: 18858680

Country of ref document: EP

Kind code of ref document: A1