WO2017128482A1 - 一种视频预提醒处理的方法、装置以及终端 - Google Patents

一种视频预提醒处理的方法、装置以及终端 Download PDF

Info

Publication number
WO2017128482A1
WO2017128482A1 PCT/CN2016/074843 CN2016074843W WO2017128482A1 WO 2017128482 A1 WO2017128482 A1 WO 2017128482A1 CN 2016074843 W CN2016074843 W CN 2016074843W WO 2017128482 A1 WO2017128482 A1 WO 2017128482A1
Authority
WO
WIPO (PCT)
Prior art keywords
scene
play
target
playing
video
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2016/074843
Other languages
English (en)
French (fr)
Inventor
陈树云
焦凯
曹奕松
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yulong Computer Telecommunication Scientific Shenzhen Co Ltd
Original Assignee
Yulong Computer Telecommunication Scientific Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Yulong Computer Telecommunication Scientific Shenzhen Co Ltd filed Critical Yulong Computer Telecommunication Scientific Shenzhen Co Ltd
Publication of WO2017128482A1 publication Critical patent/WO2017128482A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

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
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/462—Content or additional data management e.g. creating a master electronic programme guide from data received from the Internet and a Head-end or controlling the complexity of a video stream by scaling the resolution or bit-rate based on the client capabilities
    • 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
    • H04N21/44008—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 involving operations for analysing video streams, e.g. detecting features or characteristics in the video 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
    • H04N21/44012—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 involving rendering scenes according to scene graphs, e.g. MPEG-4 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
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/462—Content or additional data management e.g. creating a master electronic programme guide from data received from the Internet and a Head-end or controlling the complexity of a video stream by scaling the resolution or bit-rate based on the client capabilities
    • H04N21/4627—Rights management associated to the content
    • 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
    • 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

Definitions

  • the present invention relates to the field of Internet technologies, and in particular, to a method, an apparatus, and a terminal for video pre-alert processing.
  • film and television works become more diverse and more diverse.
  • interspersed scenes such as blood, violence, pornography, horror, etc.
  • These interspersed scenes are not acceptable to all viewers.
  • special viewing groups such as the elderly, children, special patients, etc. who do not want to watch these special interspersed scenes.
  • the technical problem to be solved by the embodiments of the present invention is to provide a method, a device, and a terminal for the video pre-alert processing, which can automatically and intelligently remind the special interspersed scenes in the video according to the actual needs of the user, and improve the video pre-preparation. Remind the practicality and convenience of processing.
  • an embodiment of the present invention provides a method for video pre-alert processing, the method include:
  • the currently played video is obtained, and a scene feature table is generated for the video, where the scene feature table includes a play scene obtained by classifying and identifying the scene segment in the video;
  • the pre-alert processing is performed according to the time description information associated with the target playing scene in the scene feature table.
  • the generating a scene feature table for the video includes:
  • a scene feature table is generated according to the obtained playback time of each play scene and the frame image.
  • the scene feature table includes at least one play scene and time description information corresponding to the play scene, where the time description information includes a start play time and an end play time of playing the play scene.
  • the video includes a current playing time
  • the pre-alert processing is performed according to the time description information associated with the target playing scene in the scene feature table during the playing of the video, :
  • the method further includes:
  • the received operation instruction is a play instruction for instructing to play the target playing scene, And continuing to play the target playing scene in response to the playing instruction;
  • the received operation instruction is a skip instruction for indicating that the target play scene is not to be played, skipping the target play scene in response to the skip instruction, ending playback corresponding to the target play scene The time begins to continue playing the video.
  • the method before the performing the corresponding operation processing on the target play scenario according to the operation instruction, the method further includes:
  • an embodiment of the present invention provides an apparatus for video pre-alert processing, where the apparatus includes:
  • Obtaining a generating module configured to: when a video playing event is detected, acquire a currently played video, and generate a scene feature table for the video, where the scene feature table includes playing the segmentation and recognition of the scene segment in the video. Scenes;
  • a determining module configured to determine, from a scene feature table generated by the acquiring and generating module, a target playing scene that needs to perform a pre-alert processing
  • the reminding processing module is configured to perform pre-alert processing according to the time description information associated with the target playing scene in the scene feature table during the playing of the video.
  • the obtaining and generating module includes:
  • An acquiring unit configured to acquire each frame image in the video, and a play time corresponding to each frame image
  • a matching unit configured to perform feature matching on the image of each frame and a preset image in multiple scenes, and obtain a corresponding playing scene according to the matching result and the preset scene;
  • a generating unit configured to generate a scene feature table according to the obtained playing time of each playing scene and the frame image.
  • the scene feature table includes at least one play scene and time description information corresponding to the play scene, where the time description information includes a start play time of playing the play scene, and End playback time.
  • the device further includes:
  • a sorting module configured to sort the target play scene according to a start play time, an end play time, and a current play time corresponding to the target play scene in the feature information table;
  • the determining module is further configured to determine, according to the sorting result of the sorting module, a play order of the target play scene, so as to perform pre-alert according to the play sequence and time description information associated with the target play scene. deal with.
  • the device further includes:
  • a receiving processing module configured to receive an operation instruction about the target playing scene, and perform corresponding operation processing on the target playing scene according to the operation instruction;
  • the receiving processing module is configured to: if the received operation instruction is a play instruction for instructing to play the target playing scene, continue to play the target playing scene in response to the playing instruction; or
  • the receiving processing module is configured to: if the received operation instruction is a skip instruction for indicating that the target playing scene is not to be played, skip the target playing scene in response to the skip instruction, and The end playing time corresponding to the target playing scene begins to continue playing the video.
  • the device further includes:
  • Obtaining a verification module configured to obtain permission verification information for indicating whether the right to play the target playing scene, and verifying whether the right verification information has the right to play the target playing scene; The module verifies the right to notify the receiving processing module.
  • an embodiment of the present invention further provides a terminal, where the terminal includes a processor and a memory, wherein the memory stores a set of program codes, and the processor is configured to invoke the storage in the memory.
  • Program code to do the following:
  • the currently played video is obtained, and a scene feature table is generated for the video, where the scene feature table includes a play scene obtained by classifying and recognizing the scene segment in the video;
  • the scene feature table includes a play scene obtained by classifying and recognizing the scene segment in the video;
  • the target play scene that needs to perform the pre-alert process is determined; during the play of the video, the pre-alert process is performed according to the time description information associated with the target play scene in the scene feature table.
  • the processor is further configured to acquire each frame image in the video, and Determining a play time corresponding to each frame image; performing feature matching on each frame image and a preset image in multiple scenes, and obtaining a corresponding play scene according to the matching result and the preset scene;
  • a scene feature table is generated by playing time of the scene and the frame image.
  • the processor is further configured to: the scene feature table includes at least one play scene, and time description information corresponding to the play scene, where the time description information includes playing the play scene. Start time and end play time.
  • the processor is further configured to sort the target play scene according to a start play time, an end play time, and the current play time corresponding to the target play scene in the feature information table; And determining, according to the sorting result of the sorting, a play order of the target play scene, so as to perform pre-alert processing according to the play order and time description information associated with the target play scene.
  • the processor is further configured to receive an operation instruction about the target playing scene, and perform corresponding operation processing on the target playing scene according to the operation instruction; specifically: if the received The operation instruction is a play instruction for instructing to play the target play scene, and then the target play scene is continued to be played in response to the play instruction; or, if the received operation instruction is used to indicate that the target is not played When the skip instruction of the scene is played, the target play scene is skipped in response to the skip instruction, and the video is resumed from the end play time corresponding to the target play scene.
  • the operation instruction is a play instruction for instructing to play the target play scene, and then the target play scene is continued to be played in response to the play instruction; or, if the received operation instruction is used to indicate that the target is not played
  • the target play scene is skipped in response to the skip instruction, and the video is resumed from the end play time corresponding to the target play scene.
  • the processor is further configured to acquire permission verification information for indicating whether the user has the right to play the target playing scene, and verify whether the rights verification information has the right to play the target playing scene. And if the right is, performing the corresponding operation processing on the target playing scene according to the operation instruction.
  • the embodiment of the present invention can perform pre-alert processing on a specific playing scene existing in the video according to the actual needs of the user, and automatically and intelligently perform the reminding of the specific playing scene, thereby avoiding the user unprepared to watch these special interspersed scenes.
  • the psychological and physiological impacts and injuries have improved the practicality and convenience of video pre-alert handling.
  • the embodiment of the present invention can perform pre-alert processing on a specific playing scene existing in the video according to the actual needs of the user, and automatically and intelligently perform the reminding of the specific playing scene, thereby avoiding the user unprepared to watch these special interspersed scenes.
  • Psychological and physical shocks and injuries have improved the video pre- Remind the practicality and convenience of processing.
  • FIG. 1 is a schematic flowchart of a video pre-alert processing method according to an embodiment of the present invention
  • FIG. 2 is a schematic flowchart diagram of another video pre-alert processing method according to an embodiment of the present invention.
  • FIG. 3 is a schematic flowchart diagram of another video pre-alert processing method according to an embodiment of the present invention.
  • FIG. 4 is a schematic structural diagram of a video pre-alert processing device according to an embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of another video pre-alert processing apparatus according to an embodiment of the present invention.
  • FIG. 6 is a schematic structural diagram of a terminal according to an embodiment of the present invention.
  • the embodiment of the invention provides a method, a device and a terminal for the video pre-alert processing, in order to quickly search for keywords and obtain the result information that the user most wants, which is simple in operation and high in efficiency.
  • FIG. 1 is a schematic flowchart of a video pre-alert processing method according to an embodiment of the present invention.
  • the method of the embodiment of the present invention can be applied to a terminal with a communication network function, such as a smart phone, a tablet computer, a smart wearable device, and the like, and can be implemented by a processor of the communication terminal.
  • the method of the embodiment of the invention further includes the following steps.
  • the scene feature table includes a play scene obtained by classifying and recognizing the scene segment in the video.
  • the communication terminal when the communication terminal detects that the user uses the communication terminal to perform video playback, the communication terminal may detect and acquire the video currently played by the user, and generate a corresponding scene feature table according to the video.
  • the feature table includes a play scene obtained by classifying the scene segments in the video.
  • the communication terminal may dynamically adopt a specific frame number image in the video, that is, a frame image in the video, and the communication terminal may further determine a play time of the frame image.
  • the image of tens of frames is usually included in the 1s video, and the frame image corresponding to the beginning, middle, and end in the 1s video can represent all the information included in the 1s video. That is, the communication terminal may separately collect the frame images corresponding to the sampling moments by using the three time points of the start, the middle, and the end of the 1s video as the sampling time, for example, taking a 1s video segment between 4s and 5s as an example.
  • the communication terminal may collect three frame images corresponding to the three times of 4s, 4.5s, and 5s through the information collection area in the terminal, the image processor, or other modules for image acquisition of the terminal, the three frames.
  • the frame image can represent all the information of the video segment of 4s-5s; thus, the communication terminal can complete the collection of the image of each frame of the video, and the communication terminal can further determine the frame according to the sampling moment.
  • the playback time corresponding to the image.
  • the difference between each frame image collected at a low sampling rate is relatively large, and then the sampling time of the frame image acquisition can be dynamically adjusted, as described above.
  • the difference between the three frames of 4s, 4.5s, and 5s is relatively large.
  • the communication terminal can reselect several (such as 3) from 4s-4.5s and 4.5s-5s.
  • the frame image is collected at the sampling time until the difference between the frames of the frames collected by the communication terminal in the time period is not large.
  • the communication terminal may perform feature information matching on the frame images corresponding to the 4s, 4.5s, and 5s, to obtain a first matching degree (that is, compare the similarity of the three frame images), if The first matching degree exceeds a preset first threshold (such as 80%), then the table It is shown that the difference between the three frame images is not large; if the first matching degree does not exceed the preset first threshold, it indicates that the difference between the three frame images is large/difference.
  • the preset matching degree threshold may be set in the communication terminal by the user/system customization, which is not limited in the embodiment of the present invention.
  • the communication terminal may match the collected image of each frame with the image of each scene in the preset scene library set by the user or the system in the communication terminal to obtain the second matching degree;
  • the second matching degree exceeds a second preset threshold set by the user/system customization in the communication terminal, and the communication terminal may classify each frame image according to the preset scene set by the user/system customization.
  • the communication terminal may further generate a scene feature table according to the obtained play scenes and the play time corresponding to the frame images, where The scene feature table includes at least one play scene, and time description information corresponding to the play scene, where the time description information may include a play time corresponding to the frame image, and may further include playing a start play time of the play scene. And end the play time.
  • the user/system sets a template image of four preset scenes of violence, blood, pornography, and scare in a specific scene library in the communication terminal.
  • the communication terminal detects that user A clicks to play video A, the communication terminal will acquire the video.
  • Feature information feature information corresponding to the template image
  • the communication terminal compares the feature information corresponding to the frame image and the feature information of the template image to obtain a similarity; Determining, by the communication terminal, whether the similarity exceeds a third threshold (such as 85%, etc.) of the similarity of the user/system in the communication terminal; if not, the communication terminal performs each frame image.
  • a third threshold such as 85%, etc.
  • the image and the play time corresponding to the frame image are generated, and the communication terminal is further configured to: according to the four play scenes corresponding to the four preset scenes, and the frame image in the play scene,
  • the scene feature table is generated by the play time corresponding to the frame image.
  • the scene feature table may include four play scenes corresponding to the four preset scenes, a start play time of playing the play scene, and an end play time.
  • a scene feature table generated according to the video A is exemplarily given as shown in Table 1 below.
  • the scene feature table includes play videos of four scenes of violence, blood, pornography, and fright, and a play start time and an end time of each play video in each scene.
  • the communication terminal may determine, from the scene feature table generated in S101, a target play scene that needs to perform pre-alert processing.
  • the communication terminal may traverse the scene feature table generated by S101 to obtain a target play scene, and the scene feature table generated in Table 1 on the map, and the communication terminal may traverse the scene feature table shown in Table 1.
  • Obtaining 7 playback scenes that need to perform pre-alert processing namely, one play scene in a violent scene, three play scenes in a bloody scene, one play scene in a pornographic scene, and two play scenes in a scary scene;
  • the user may customize a play scene or a play scene identifier (such as a scene name, a scene screen, etc.) in which the user wants to perform pre-alert processing in the communication terminal, and the communication terminal may determine whether the scene feature table is in the scene.
  • the communication terminal uses the play scene as a target play scene that needs to perform pre-alert processing. If the user sets only the reminder to the bloody scene in the communication terminal, the communication terminal may determine whether the scene feature table exists and is in accordance with the bloody scene that the user needs to remind according to the setting on the communication terminal. a play scene corresponding to the bloody scene; if yes, extracting three play scenes corresponding to the bloody scene from the scene feature table as a target play scene that needs to perform pre-alert processing.
  • the communication terminal may further sort the target play scene according to the start play time and the end play time in the target play scene in the scene feature table, and the sorting result of the communication terminal according to the sorting Determining a play order for playing the target play scene, the communication terminal may perform pre-alert processing on the target play scene according to the play sequence; the communication terminal may also acquire a current current video of the user currently playing the video. The playing terminal may further sort the target playing scene according to the initial playing time, the ending playing time, and the current playing time corresponding to the playing scene, and the communication terminal performs the sorting result according to the sorting.
  • the target playing scene performs pre-alert processing, wherein the sorting may be sorted according to time, sorted according to playing time length, or sorted according to priority of a user/system customized playing scene, or sorted according to other methods.
  • the embodiment of the invention is not limited.
  • the communication terminal can detect and acquire the current user. Playing the current playing time of the video at 40:00; the communication terminal starts playing and ending playback according to the current playing time and the target playing scene (ie, 3 playing scenes in a bloody scene) Time chronologically sorting the target playing scenes, and determining the order in which the target playing scenes are played, that is, the target playing scene in which the target playing scene is the first pre-alert processing is 48:22-49:36.
  • the communication terminal may perform pre-alert processing on the target playing scene according to the playing sequence, that is, the communication terminal may according to the The initial playing time of the target playing scene selects a target playing scene that is played most recently from the current playing time to perform pre-alert processing.
  • the communication terminal in the process of playing the video, may perform pre-alert processing according to the time description information associated with the target play scene in the scene feature table.
  • the user/system may customize a preset reminding time for reminding the target scene in the communication terminal, such as setting a reminder for 1 minute before playing the target playing scene.
  • the video is played to 1 minute before the start playing time of the target playing scene, and a prompt message for reminding whether to play the target playing scene is sent.
  • the communication terminal may send prompt information for prompting whether to play the bloody scene;
  • the communication terminal may send Prompting whether to play the prompt information of the bloody scene.
  • the communication terminal may prompt the user to play the target playing scene by sending voice information, or the communication terminal may display the subtitle on the display screen to prompt the user whether to play the target playing scene, or the communication terminal The user is prompted to play the target playing scene in a vibrating manner, or the communication terminal prompts the user to play the target playing scene in other prompting manners, which is not limited in the embodiment of the present invention.
  • the user may perform selection according to the prompt information sent by the communication terminal for prompting whether to play the target play scene.
  • the communication terminal may detect and acquire an operation instruction that is sent by the user according to the prompt information to indicate that the target playback scene is played, and performs a playback operation on the target playback scene according to the operation instruction.
  • the communication terminal plays the target with the target according to the play instruction (that is, responds to the play instruction).
  • the target play scene is continued to be played;
  • the operation instruction is a skip instruction for indicating that the target play scene is not to be played, the communication terminal according to the skip instruction (that is, in response to the skip instruction), when the initial play time corresponding to the target play scene is played, skip the target play scene, and continue from the end play time corresponding to the target play scene. Play the video.
  • the communication terminal may further obtain permission verification information for indicating whether the user has the right to play the target playing scene, and verify whether the rights verification information has the right to play the target playing scene, if the communication terminal If it is verified that the target playing scene is played, the playback operation of the target playing scene is performed according to the operation instruction.
  • the user may customize verification reference information (such as fingerprint information, password information, facial feature information, and the like) for performing authority verification on the target playing scene in the communication terminal, where the communication terminal is In the process of performing pre-alert processing on the target playing video, prompt information for prompting the user to input the right verification information may also be simultaneously sent, and the communication terminal acquires the user according to the Determining the authority verification information returned by the prompt information, the communication terminal verifies whether the similarity between the authority verification information and the preset verification reference information exceeds a preset fourth threshold, and if yes, the communication terminal according to the obtained location The operation instruction performs a playback operation process on the target play video.
  • verification reference information such as fingerprint information, password information, facial feature information, and the like
  • the preset first threshold, the preset second threshold, the preset third threshold, and the preset fourth threshold may be preset thresholds set by a user or a system, and the preset threshold.
  • the embodiments may be the same or different, and are not limited in the embodiment of the present invention.
  • the embodiment of the present invention can perform pre-alert processing on a specific playing scene existing in the video according to the actual needs of the user, and automatically and intelligently perform the reminding of the specific playing scene, thereby avoiding the user unprepared to watch these special interspersed scenes.
  • the psychological and physiological impacts and injuries have improved the practicality and convenience of video pre-alert handling.
  • FIG. 2 is a schematic flowchart of another video pre-alert processing method according to an embodiment of the present invention.
  • the method in the embodiment of the present invention can be applied to a communication network function, such as a smart phone, a tablet computer, and a smart wearable device.
  • the terminals can be specifically implemented by the processors of these communication terminals.
  • the method of the embodiment of the invention further includes the following steps.
  • S203 Perform feature matching on the image of each frame and a preset image in multiple scenes, and obtain a corresponding playing scene according to the matching result and the preset scene; wherein the playing scene is in the video.
  • the scene fragments are classified.
  • S204 Generate a scene feature table according to the obtained play time of each play scene and the frame image, where the scene feature table includes at least one play scene and time description information corresponding to the play scene, the time description information The start play time and the end play time of playing the play scene are included.
  • the communication terminal when the communication terminal detects that the user uses the communication terminal to perform video playback, the communication terminal may detect and acquire the video currently played by the user, and generate a corresponding scene feature table according to the video.
  • the feature table includes a play scene for classifying and identifying the scene segments in the video.
  • the communication terminal may dynamically adopt a specific frame number image in the video, that is, a frame image in the video, and the communication terminal may further determine a play time of the frame image.
  • the image of tens of frames is usually included in the 1s video, and the frame image corresponding to the beginning, middle, and end in the 1s video can represent all the information included in the 1s video. That is, the communication terminal may separately collect the frame images corresponding to the sampling moments by using the three time points of the start, the middle, and the end of the 1s video as the sampling time, for example, taking a 1s video segment between 4s and 5s as an example.
  • the communication terminal may collect three frame images corresponding to the three times of 4s, 4.5s, and 5s through the information collection area in the terminal, the image processor, or other modules for image acquisition of the terminal, the three frames.
  • the frame image can represent all the information of the video segment of 4s-5s; thus, the communication terminal can complete the collection of the image of each frame of the video, and the communication terminal can further determine the frame according to the sampling moment.
  • the playback time corresponding to the image.
  • the difference between each frame image collected at a low sampling rate is relatively large, and then the sampling time of the frame image acquisition can be dynamically adjusted, as described above.
  • the difference between the three frames of 4s, 4.5s, and 5s is relatively large.
  • the communication terminal can reselect several (such as 3) from 4s-4.5s and 4.5s-5s.
  • the frame image is collected at the sampling time until the difference between the frames of the frames collected by the communication terminal in the time period is not large.
  • the communication terminal may perform feature information matching on the frame images corresponding to the 4s, 4.5s, and 5s, to obtain a first matching degree (that is, compare the similarity of the three frame images), if If the first matching degree exceeds the preset first threshold (for example, 80%), the difference between the three frame images is not large; if the first matching degree does not exceed the preset first threshold, It means that the difference between the three frame images is large/difference.
  • the preset matching degree threshold may be set in the communication terminal by the user/system customization, which is not limited in the embodiment of the present invention.
  • the communication terminal may match the collected image of each frame with the image of each scene in the preset scene library set by the user or the system in the communication terminal to obtain the second matching degree;
  • the second matching degree exceeds a second preset threshold set by the user/system customization in the communication terminal, and the communication terminal may classify each frame image according to the preset scene set by the user/system customization.
  • the communication terminal may further generate a scene feature table according to the obtained play scenes and the play time corresponding to the frame images, where
  • the scene feature table includes at least one a play scene, time description information corresponding to the play scene, the time description information may include a play time corresponding to the frame image, and may further include playing a start play time and an end play time of the play scene.
  • the communication terminal may further sort the target play scene according to the start play time and the end play time in the target play scene in the scene feature table, where the communication terminal is configured according to the The sorting result of the sorting determines a play order for playing the target play scene, and the communication terminal may perform pre-alert processing on the target play scene according to the play order; the communication terminal may also acquire the current user Playing the current playing time of the video, the communication terminal may further sort the target playing scene according to the initial playing time, the ending playing time, and the current playing time corresponding to the playing scene, where the communication terminal is The sorting result of the sorting performs pre-alert processing on the target playing scene, wherein the sorting may be sorted according to time, sorted according to playing time length, or sorted according to priority of a user/system customized playing scene, or The sorting according to other manners is not limited in the embodiment of the present invention. .
  • the pre-alarm processing manner includes a voice reminder, a subtitle reminder, and a vibration. One or more combinations of reminders.
  • the received operation instruction is a play instruction for instructing to play the target play scene, continue to play the target play scene in response to the play instruction.
  • the received operation instruction is a skip instruction for indicating that the target play scene is not to be played, skipping the target play scene in response to the skip instruction, corresponding to the target play scene.
  • the playback time begins to continue playing the video.
  • step S210 and step S209 are performed in step S209 according to the operation.
  • the embodiment of the present invention can perform pre-alert processing on a specific playing scene existing in the video according to the actual needs of the user, and automatically and intelligently perform the reminding of the specific playing scene, thereby avoiding the user unprepared to watch these special interspersed scenes.
  • the psychological and physiological impacts and injuries have improved the practicality and convenience of video pre-alert handling.
  • FIG. 3 is a schematic flowchart of another video pre-alert processing method according to an embodiment of the present invention.
  • the communication terminal may further obtain permission verification information (such as fingerprint information, password information, facial feature information, and the like) for indicating whether the user has the right to play the target playing scene, and verify the Whether the rights verification information has the right to play the target playing scene. If the communication terminal verifies that the target playing scene is authorized to play, step S209 is continued; otherwise, step S303 is performed.
  • permission verification information such as fingerprint information, password information, facial feature information, and the like
  • the parents at home can encrypt certain specific playing scenes (such as violent, bloody, pornographic and other playing scenes) on the home computer, and obtain initial verification information for verifying the rights of the specific playing scenes.
  • specific playing scenes such as violent, bloody, pornographic and other playing scenes
  • the computer can perform the above steps S201-S208, when the computer detects that the video is played to the preset reminder time or plays to the
  • the computer may send prompt information for prompting the user to input the right authority verification information for verifying the target playing scene, or directly display the corresponding right authority verification on the real interface.
  • the information input interface the user returns the authority verification information according to the prompt information, or inputs the corresponding authority verification information on the authority verification information input interface; the computer can detect and acquire the authority verification information input by the user; The computer compares the authority verification information with the preset initial verification information. Comparing, the computer compares the similarity obtained by the similarity with the user/system in the computer.
  • the preset threshold eg, 80%
  • step S209 is performed; otherwise, step S303 is performed.
  • the embodiment of the present invention can perform pre-alert processing on a specific playing scene existing in the video according to the actual needs of the user, and automatically and intelligently perform the reminding of the specific playing scene, thereby avoiding the user unprepared to watch these special interspersed scenes.
  • the psychological and physiological impacts and injuries have improved the practicality and convenience of video pre-alert handling.
  • FIG. 4 is a schematic structural diagram of a video pre-alert processing device according to an embodiment of the present invention.
  • the device in the embodiment of the present invention may be set in a communication network function such as a smart phone, a tablet computer, or a smart wearable device.
  • the device 4 includes:
  • the obtaining module 40 is configured to: when the video playing event is detected, acquire the currently played video, and generate a scene feature table for the video, where the scene feature table includes used for classifying and identifying the scene segment in the video. The resulting playback scene;
  • a determining module 41 configured to determine, from the scene feature table generated by the acquiring and generating module 40, a target playing scene that needs to perform pre-alert processing
  • the reminding processing module 42 is configured to perform pre-alert processing according to the time description information associated with the target playing scene in the scene feature table during the playing of the video.
  • the acquisition generation module 40 when the acquisition and generation module 40 detects the video playback event, acquires the currently played video, and generates a scene feature table for the video, where the scene feature table includes the video.
  • the scene segment in the segment performs the classification and recognition of the playback scene;
  • the determining module 41 determines, from the scene feature table generated by the acquisition generation module 40, the target playback scenario that needs to perform the pre-alert processing; during the playback of the video, the reminder
  • the processing module 42 performs pre-alert processing according to the time description information associated with the target playing scene determined by the determining module 41 in the scene feature table generated by the acquiring and generating module 40.
  • the embodiment of the present invention can perform pre-alert processing on a specific playing scene existing in the video according to the actual needs of the user, and automatically and intelligently perform the reminding of the specific playing scene, thereby avoiding the user unprepared to watch these special interspersed scenes.
  • the psychological and physiological impacts and injuries have improved the practicality and convenience of video pre-alert handling.
  • FIG. 5 is a schematic structural diagram of a video pre-alert processing device according to an embodiment of the present invention.
  • the device in the embodiment of the present invention may be set in, for example, a smart phone, a tablet computer, and a smart wearable device.
  • the terminal with a communication network function such as the device, the device 5 includes the above-mentioned acquisition and generation module 40, the determination module 41, and the reminder processing module 42, and further includes:
  • the obtaining and generating module 40 includes:
  • the acquiring unit 400 is configured to acquire each frame image in the video, and a play time corresponding to each frame image;
  • the matching unit 401 is configured to perform feature matching on the image of each frame and the image in the preset multiple scenes, and obtain a corresponding playing scene according to the matching result and the preset scene;
  • the generating unit 402 is configured to generate a scene feature table according to the obtained playing time of each playing scene and the frame image.
  • the scene feature table generated by the acquiring and generating module 40 includes at least one playing scene and time description information corresponding to the playing scene, where the time description information includes playing the playing scene. Start time and end play time.
  • the video includes a current playing time
  • the device further includes:
  • the sorting module 43 is configured to sort the target play scene according to the initial play time, the end play time, and the current play time corresponding to the target play scene in the feature information table;
  • the determining module 41 is further configured to determine, according to the sorting result of the sorting module, a play order of the target play scene, to perform pre-preparation according to the play order and time description information associated with the target play scene. Reminder processing.
  • the device further includes:
  • the receiving processing module 44 is configured to receive an operation instruction about the target playing scene, and perform corresponding operation processing on the target playing scene according to the operation instruction;
  • the receiving processing module 44 is configured to: if the received operation instruction is a play instruction for instructing to play the target playing scene, continue to play the target playing scene in response to the playing instruction; or
  • the receiving processing module 44 is specifically configured to: if the received operation instruction is a skip instruction for indicating that the target playing scene is not to be played, skip the target playing scene in response to the skip instruction, The end playing time corresponding to the target playing scene begins to continue playing the video.
  • the device further includes:
  • the obtaining verification module 45 is configured to obtain permission verification information for indicating whether the user has the right to play the target playing scene, and verify whether the right verification information has the right to play the target playing scene; The verification module 45 verifies the right to notify the receiving processing module 44.
  • the embodiment of the present invention can perform pre-alert processing on a specific playing scene existing in the video according to the actual needs of the user, and automatically and intelligently perform the reminding of the specific playing scene, thereby avoiding the user unprepared to watch these special interspersed scenes.
  • the psychological and physiological impacts and injuries have improved the practicality and convenience of video pre-alert handling.
  • FIG. 6 is a schematic structural diagram of a terminal according to an embodiment of the present invention.
  • the terminal may be a device with a communication network function, such as a smart phone, a tablet computer, or a smart wearable device.
  • the terminal in the embodiment of the present invention may include a display screen, a button, a speaker, a pickup, and the like.
  • the processor 502 can call the code stored in the memory 503 via the bus 501 to perform related functions.
  • the processor 502 is configured to: when a video play event is detected, acquire a currently played video, and generate a scene feature table for the video, where the scene feature table includes classifying and identifying the scene segment in the video. a play scene in which the target play scene needs to be executed, and a time description information associated with the target play scene in the scene feature table during the play of the video; Pre-alert processing.
  • the processor 502 is further configured to acquire each frame image in the video, and a play time corresponding to each frame image; and display the image of each frame with a preset image in multiple scenes Feature matching is performed, and corresponding play scenes are obtained according to the matching result and the preset scene; and the scene feature table is generated according to the obtained play scenes and the play time of the frame images.
  • the processor 502 is further configured to: the scene feature table includes at least one play scene, and time description information corresponding to the play scene, where the time description information includes playing the play scene. Start play time and end play time.
  • the processor 502 is further configured to: target the target according to the initial play time, the end play time, and the current play time corresponding to the target play scene in the feature information table.
  • the playing scenes are sorted; the playing order of the target playing scenes is determined according to the sorting result of the sorting, so that the pre-alert processing is performed according to the playing order and the time description information associated with the target playing scene.
  • the processor 502 is further configured to receive an operation instruction about the target playing scene, and perform corresponding operation processing on the target playing scene according to the operation instruction; specifically: if the received The operation instruction is a play instruction for instructing to play the target play scene, and then the target play scene is continued to be played in response to the play instruction; or, if the received operation instruction is for indicating that the play is not to be played
  • the skip instruction of the target play scene skips the target play scene in response to the skip instruction, and continues to play the video from the end play time corresponding to the target play scene.
  • the processor 502 is further configured to obtain permission verification information for indicating whether the right to play the target playing scene, and verify whether the right verification information has the right to perform the target playing scene. Playing, if the right is, performing the corresponding operation processing on the target playing scene according to the operation instruction.
  • the embodiment of the present invention can perform pre-alert processing on a specific playing scene existing in the video according to the actual needs of the user, and automatically and intelligently perform the reminding of the specific playing scene, thereby avoiding the user unprepared to watch these special interspersed scenes.
  • the psychological and physiological impacts and injuries have improved the practicality and convenience of video pre-alert handling.
  • the embodiment of the present invention further provides a computer storage medium, wherein the computer storage medium can store a program, and the program includes some or all of the steps of the operation method of any of the audio playback applications described in the foregoing method embodiments.
  • the disclosed device may be It's way to achieve it.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, 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, device or unit, 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 invention 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 integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • the technical solution of the present invention which is essential or contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product stored in a storage medium.
  • a number of instructions are included to cause a computer device (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 invention.
  • the foregoing storage medium includes: a U disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, and the like. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Human Computer Interaction (AREA)
  • Computer Security & Cryptography (AREA)
  • Business, Economics & Management (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Television Signal Processing For Recording (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

本发明实施例提供了一种视频预提醒处理的方法、装置以及终端，其中，所述方法包括：当检测到视频播放事件时，获取当前播放的视频，并为所述视频生成场景特征表，所述场景特征表包括对所述视频中的场景片段进行分类识别得到的播放场景；从所述场景特征表中确定出需要执行预提醒处理的目标播放场景；在所述视频的播放过程中，根据所述场景特征表中与所述目标播放场景关联的时间描述信息进行预提醒处理。采用本发明，可根据用户的实际需求自动地、智能地对视频中存在特殊穿插场景进行提醒，避免了用户毫无准备下观看这些特殊穿插场景带来的心理、生理上的冲击和伤害，提升了视频预提醒处理的实用性和方便快捷性。

Description

一种视频预提醒处理的方法、装置以及终端
本申请要求于2016年01月28日提交中国专利局，申请号为201610061655.9、发明名称为“一种视频预提醒处理的方法、装置以及终端”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及互联网技术领域，尤其涉及一种视频预提醒处理的方法、装置以及终端。
背景技术
随着人们精神需求的提高，影视作品变得越来越多元、种类越来越多了。然而相当多的影视作品中包含诸如血腥、暴力、色情、恐怖等穿插场景，这些穿插场景并非是所有观众能够接受的。例如存在一些特殊观看群体(如老人、儿童、特殊患者等)，他们不想观看这些特殊的穿插场景。
现有常见的两种视频处理技术方案，一种视频处理方案为相关机构对影视作品进行评级，不同级别对应的影视作品适合不同年龄阶段的人们观看，并在整部影视作品播放前进行提醒；另一种视频处理方案为相关机构对影视作品进行审核，不能通过审核的影视作品不允许人们观看。在实践中发现，上述两种视频处理方案都是针对整部视频进行处理的，人们只能选择对整部视频进行播放或者不播放，不能满足用户的实际需求。且目前，网络上的视频资源大多没经过严格的审核，仍存在一些不和谐的特殊场景，人们还是能够观看到这些特殊场景；另外，针对一些特殊观看群体而言，他们在毫无防备地观看这些特殊场景时，可能会带来心理或者生理上的冲击、伤害。
发明内容
本发明实施例所要解决的技术问题在于，提供一种视频预提醒处理的方法、装置以及终端，可根据用户的实际需求自动地、智能地对视频中存在特殊穿插场景进行提醒，提升了视频预提醒处理的实用性和方便快捷性。
一方面，本发明实施例公开提供了一种视频预提醒处理的方法，所述方法 包括：
当检测到视频播放事件时，获取当前播放的视频，并为所述视频生成场景特征表，所述场景特征表包括对所述视频中的场景片段进行分类识别得到的播放场景；
从所述场景特征表中确定出需要执行预提醒处理的目标播放场景；
在所述视频的播放过程中，根据所述场景特征表中与所述目标播放场景关联的时间描述信息进行预提醒处理。
其中可选地，所述为所述视频生成场景特征表，包括：
获取所述视频中的各个帧图像，以及所述各个帧图像对应的播放时间；
将所述各个帧图像与预设的多个场景下的图像进行特征匹配，并根据匹配结果和预设的场景，得到对应的播放场景；
根据得到的各个播放场景和帧图像的播放时间，生成场景特征表。
其中可选地，
所述场景特征表包括至少一个播放场景、以及与所述播放场景对应的时间描述信息，其中，所述时间描述信息包括播放所述播放场景的起始播放时间和结束播放时间。
其中可选地，所述视频包括当前播放时间，所述在所述视频的播放过程中，根据所述场景特征表中与所述目标播放场景关联的时间描述信息进行预提醒处理之前，还包括：
根据所述特征信息表中与所述目标播放场景对应的起始播放时间、结束播放时间和所述当前播放时间对所述目标播放场景进行排序；
根据所述进行排序的排序结果确定出所述目标播放场景的播放顺序，以便根据所述播放顺序和与所述目标播放场景关联的时间描述信息进行预提醒处理。
其中可选地，所述根据所述场景特征表中与所述目标播放场景关联的时间描述信息进行预提醒处理之后，还包括：
接收关于所述目标播放场景的操作指令，并根据所述操作指令对所述目标播放场景进行对应的操作处理；其具体包括：
若接收到的所述操作指令为用于指示播放所述目标播放场景的播放指令， 则响应所述播放指令继续播放所述目标播放场景；或者，
若接收到的所述操作指令为用于指示不播放所述目标播放场景的跳过指令，则响应所述跳过指令跳过所述目标播放场景，从与所述目标播放场景对应的结束播放时间开始继续播放所述视频。
其中可选地，所述根据所述操作指令对所述目标播放场景进行对应的操作处理之前，还包括：
获取用于指示是否有权对所述目标播放场景进行播放的权限验证信息，并验证所述权限验证信息是否有权对所述目标播放场景进行播放；
若有权，则执行所述根据所述操作指令对所述目标播放场景进行对应的操作处理。
另一方面，本发明实施例公开提供了一种视频预提醒处理的装置，所述装置包括：
获取生成模块，用于当检测到视频播放事件时，获取当前播放的视频，并为所述视频生成场景特征表，所述场景特征表包括对所述视频中的场景片段进行分类识别得到的播放场景；
确定模块，用于从所述获取生成模块生成的场景特征表中确定出需要执行预提醒处理的目标播放场景；
提醒处理模块，用于在所述视频的播放过程中，根据所述场景特征表中与所述目标播放场景关联的时间描述信息进行预提醒处理。
其中可选地，所述获取生成模块包括：
获取单元，用于获取所述视频中的各个帧图像，以及所述各个帧图像对应的播放时间；
匹配单元，用于将所述各个帧图像与预设的多个场景下的图像进行特征匹配，并根据匹配结果和预设的场景，得到对应的播放场景；
生成单元，用于根据得到的各个播放场景和帧图像的播放时间，生成场景特征表。
其中可选地，
所述场景特征表包括至少一个播放场景、以及与所述播放场景对应的时间描述信息，其中，所述时间描述信息包括播放所述播放场景的起始播放时间和 结束播放时间。
其中可选地，所述装置还包括：
排序模块，用于根据所述特征信息表中与所述目标播放场景对应的起始播放时间、结束播放时间和所述当前播放时间对所述目标播放场景进行排序；
所述确定模块，还用于根据所述排序模块进行排序的排序结果确定出所述目标播放场景的播放顺序，以便根据所述播放顺序和与所述目标播放场景关联的时间描述信息进行预提醒处理。
其中可选地，所述装置还包括：
接收处理模块，用于接收关于所述目标播放场景的操作指令，并根据所述操作指令对所述目标播放场景进行对应的操作处理；其具体包括：
所述接收处理模块，具体用于若接收到的所述操作指令为用于指示播放所述目标播放场景的播放指令，则响应所述播放指令继续播放所述目标播放场景；或者，
所述接收处理模块，具体用于若接收到的所述操作指令为用于指示不播放所述目标播放场景的跳过指令，则响应所述跳过指令跳过所述目标播放场景，从与所述目标播放场景对应的结束播放时间开始继续播放所述视频。
其中可选地，所述装置还包括：
获取验证模块，用于获取用于指示是否有权对所述目标播放场景进行播放的权限验证信息，并验证所述权限验证信息是否有权对所述目标播放场景进行播放；若所述获取验证模块验证到有权，则通知所述接收处理模块。
再一方面，本发明实施例还公开提供了一种终端，所述终端包括处理器和存储器，其中，所述存储器中存储一组程序代码，且所述处理器用于调用所述存储器中存储的程序代码，用于执行以下操作：
当检测到视频播放事件时，获取当前播放的视频，并为所述视频生成场景特征表，所述场景特征表包括对所述视频中的场景片段进行分类识别得到的播放场景；从所述场景特征表中确定出需要执行预提醒处理的目标播放场景；在所述视频的播放过程中，根据所述场景特征表中与所述目标播放场景关联的时间描述信息进行预提醒处理。
进一步可选地，所述处理器还用于获取所述视频中的各个帧图像，以及所 述各个帧图像对应的播放时间；将所述各个帧图像与预设的多个场景下的图像进行特征匹配，并根据匹配结果和预设的场景，得到对应的播放场景；根据得到的各个播放场景和帧图像的播放时间，生成场景特征表。
进一步可选地，所述处理器还用于所述场景特征表包括至少一个播放场景、以及与所述播放场景对应的时间描述信息，其中，所述时间描述信息包括播放所述播放场景的起始播放时间和结束播放时间。
进一步可选地，所述处理器还用于根据所述特征信息表中与所述目标播放场景对应的起始播放时间、结束播放时间和所述当前播放时间对所述目标播放场景进行排序；根据所述进行排序的排序结果确定出所述目标播放场景的播放顺序，以便根据所述播放顺序和与所述目标播放场景关联的时间描述信息进行预提醒处理。
进一步可选地，所述处理器还用于接收关于所述目标播放场景的操作指令，并根据所述操作指令对所述目标播放场景进行对应的操作处理；其具体包括：若接收到的所述操作指令为用于指示播放所述目标播放场景的播放指令，则响应所述播放指令继续播放所述目标播放场景；或者，若接收到的所述操作指令为用于指示不播放所述目标播放场景的跳过指令，则响应所述跳过指令跳过所述目标播放场景，从与所述目标播放场景对应的结束播放时间开始继续播放所述视频。
进一步可选地，所述处理器还用于获取用于指示是否有权对所述目标播放场景进行播放的权限验证信息，并验证所述权限验证信息是否有权对所述目标播放场景进行播放；若有权，则执行所述根据所述操作指令对所述目标播放场景进行对应的操作处理。
本发明实施例可根据用户的实际需求对视频中的存在的特定播放场景进行预提醒处理，自动地、智能地进行特定播放场景的提醒，避免了用户毫无准备下观看这些特殊穿插场景带来的心理、生理上的冲击和伤害，提升了视频预提醒处理的实用性和方便快捷性。
本发明实施例可根据用户的实际需求对视频中的存在的特定播放场景进行预提醒处理，自动地、智能地进行特定播放场景的提醒，避免了用户毫无准备下观看这些特殊穿插场景带来的心理、生理上的冲击和伤害，提升了视频预 提醒处理的实用性和方便快捷性。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本发明实施例的一种视频预提醒处理方法的流程示意图；
图2是本发明实施例的另一种视频预提醒处理方法的流程示意图；
图3是本发明实施例的另一种视频预提醒处理方法的流程示意图；
图4是本发明实施例的一种视频预提醒处理装置的结构示意图；
图5是本发明实施例的另一种视频预提醒处理装置的结构示意图；
图6是本发明实施例的一种终端的结构示意图。
具体实施方式
本发明实施例提供了一种视频预提醒处理的方法、装置及终端，以期可以对关键词进行快速搜索，获取用户最想得到的结果信息，操作简单，效率高。
为了使本技术领域的人员更好地理解本发明方案，下面将结合本发明实施例中的附图，对本发明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发明一部分的实施例，而不是全部的实施例。基于本发明中的实施例，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，都应当属于本发明保护的范围。
本发明的说明书和权利要求书及上述附图中的术语“第一”、“第二”和“第三”等是用于区别不同对象，而非用于描述特定顺序。此外，术语“包括”以及它们任何变形，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、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其它步骤或单元。
请参见图1，是本发明实施例的一种视频预提醒处理方法的流程示意图， 本发明实施例的所述方法可以应用在诸如智能手机、平板电脑、智能可穿戴设备等带通信网络功能的终端中，具体可由这些通信终端的处理器来实现。本发明实施例的所述方法还包括如下步骤。
S101、当检测到视频播放事件时，获取当前播放的视频，并为所述视频生成场景特征表，所述场景特征表包括对所述视频中的场景片段进行分类识别得到的播放场景。
本发明实施例中，当通信终端检测到用户使用本通信终端进行视频播放时，所述通信终端可以检测并获取用户当前播放的视频，并根据所述视频生成相应的场景特征表，所述场景特征表包括对所述视频中的场景片段进行分类识别得到的播放场景。
具体实现中，所述通信终端可以动态采取所述视频中的特定帧数图像，也即是所述视频中的帧图像，所述通信终端还可以确定所述帧图像的播放时间。可以理解的，1s视频中通常包括了几十帧的图像，1s视频中的开始、中间、结束对应的帧图像可以代表这1s视频包括的所有信息。也即是，所述通信终端可以将1s视频的开始、中间、结束这三个时间点作为采样时刻分别采集所述采样时刻对应的帧图像，如以4s-5s之间的1s视频片段为例，所述通信终端可以通过本终端中的信息采集区、图像处理器或者本终端其他的用于图像采集的模块采集4s、4.5s、5s这三个时刻对应的三个帧图像，这三个帧图像就可以代表4s-5s这个视频片段的所有信息；以此，所述通信终端可以完成对所述视频的各个帧图像的采集，所述通信终端还可以根据所述采样时刻确定所述帧图像对应的播放时间。
可以理解的是，当播放所述视频的画面变化迅速时，低采样率采集到的各个帧图像之间的差异比较大，这时就可以动态调整对帧图像采集的采样时刻，如上述采集到的4s、4.5s、5s这三个帧图像的差异比较大，这时所述通信终端就可以分别从4s-4.5s、4.5s-5s的时间段之间在重新选取几个(如3个)采样时刻再进行帧图像采集，直至所述通信终端在所述时间段中采集到的各个帧图像之间的差异不大为止。具体实现中，所述通信终端可以将4s、4.5s、5s对应采集到的帧图像进行特征信息匹配，得到第一匹配度(也即是，对上述三个帧图像进行相似度比较)，若所述第一匹配度超过预设第一阈值(如80％)，则表 示所述三个帧图像之间的差异不大；若所述第一匹配度不超过所述预设第一阈值，则表示所述三个帧图像之间的差异大/差异明显。所述预设匹配度阈值可以为用户/系统自定义在所述通信终端中设置的，本发明实施例不作限定。
所述通信终端可以将采集到的各个帧图像与用户或者系统自定义在所述通信终端中设置的预设场景库中的各个场景下的图像进行特征信息匹配，得到第二匹配度；若所述第二匹配度超过用户/系统自定义在所述通信终端中设置的第二预设阈值，则所述通信终端可以根据上述用户/系统自定义设置的预设场景将各个帧图像进行分类，得到对应的播放场景，其中所述播放场景包括预设场景下的至少一个帧图像；所述通信终端还可以根据得到的各个播放场景、所述帧图像对应的播放时间生成场景特征表，其中所述场景特征表包括至少一个播放场景、与所述播放场景对应的时间描述信息，所述时间描述信息可以包括所述帧图像对应的播放时间，还可以包括播放所述播放场景的起始播放时间和结束播放时间。
示例性地，用户/系统在通信终端中的特定场景库中设置了暴力、血腥、色情、惊吓四个预设场景的模板图像。现用户A想观看一部为时90分钟的视频A，用户A在通信终端上点击播放视频A，所述通信终端在检测到用户A点击播放视频A时，所述通信终端将获取所述视频A，并采集所述视频A中的各个帧图像，所述帧图像对应的播放时间；所述通信终端将解析采集到的各个帧图像和预设的模板图像，得到与所述帧图像对应的特征信息、与所述模板图像对应的特征信息；所述通信终端将解析得到的所述与所述帧图像对应的特征信息和与所述模板图像的特征信息进行相似度对比，得到相似度；所述通信终端判断得到的相似度是否超过用户/系统在所述通信终端中自定的相似度预设第三阈值(如85％等)，若超过，则所述通信终端将各个帧图像进行预设的暴力、血腥、色情、惊吓四个场景归类，得到四个预设场景下对应的帧图像，所述通信终端还可以根据所述预设场景下的所有帧图像、以及与所述帧图像对应的播放时间生成对应的播放场景；所述通信终端还可以根据与所述四个预设场景对应的四个播放场景、以及所述播放场景下的帧图像、所述帧图像对应的播放时间生成场景特征表；其中，所述场景特征表可以包括与上述四个预设场景对应的四个播放场景、播放所述播放场景的起始播放时间以及结束播放时 间，如下表1示例性地给出根据所述视频A生成的场景特征表。
表1
Figure PCTCN2016074843-appb-000001
如上表1可知，所述场景特征表中包括有暴力、血腥、色情、惊吓这四个场景的播放视频，以及每个场景下的各个播放视频的播放起始时间和结束时间。
S102、从所述场景特征表中确定出需要执行预提醒处理的目标播放场景。
本发明实施例中，所述通信终端可以从S101中生成的所述场景特征表中确定相互需要执行预提醒处理的目标播放场景。
具体实现中，所述通信终端可以直接对S101生成的场景特征表进行遍历，得到目标播放场景，图上表1生成的场景特征表，所述通信终端可以遍历表1所示的场景特征表，得到需要执行预提醒处理的7个播放场景，分别为暴力场景下的1个播放场景、血腥场景下的3个播放场景、色情场景下的1个播放场景、惊吓场景下的2个播放场景；或者，用户可以自定义在所述通信终端中设置用户想要进行预提醒处理的播放场景或者播放场景标识(如场景名称、场景画面等)，所述通信终端可以判断所述场景特征表中是否存在用户自定义的播放场景或者与所述播放场景标识对应的播放场景，若存在，所述通信终端将所述播放场景作为需要进行预提醒处理的目标播放场景。如用户在所述通信终端中设置只设置了对血腥场景进行提醒，所述通信终端可以根据用户在本通信终端上的设置需要提醒的血腥场景，判断所述场景特征表中是否存在与所述血腥场景对应的播放场景；若存在，则从所述场景特征表中提取出与所述血腥场景对应的3个播放场景，作为需要进行预提醒处理的目标播放场景。
所述通信终端还可以根据所述场景特征表中的与所述目标播放场景中的起始播放时间和结束播放时间对所述目标播放场景进行排序，所述通信终端根据所述排序的排序结果确定出对所述目标播放场景进行播放的播放顺序，所述通信终端可以根据所述播放顺序对所述目标播放场景进行预提醒处理；所述通信终端还可以获取用户当前播放所述视频的当前播放时间，所述通信终端还可以根据与所述播放场景对应的起始播放时间和结束播放时间以及当前播放时间对所述目标播放场景进行排序，所述通信终端根据所述排序的排序结果对所述目标播放场景进行预提醒处理，其中，所述排序可以根据时间排序、也可以根据播放时长排序、或者根据用户/系统自定义的播放场景的优先级进行排序，或者根据其他方式进行排序，本发明实施例不作限定。
示例性地，上述示例中若用户A由于时间紧迫只想观看40:00之后的视频，用户A点击打开视频A之后直接拖至40:00开始观看，则所述通信终端可以检测并获取用户当前播放所述视频的当前播放时间40:00；所述通信终端根据所述当前播放时间以及与所述目标播放场景(即是，血腥场景下的3个播放场景)的起始播放时间和结束播放时间对所述目标播放场景进行时间先后顺序排序，确定出播放所述目标播放场景的顺序，即为最先进行预提醒处理的目标播放场景为48:22-49:36时间段的目标播放场景，其次为59:01-60:45时间段的目标播放场景，所述通信终端可以根据所述播放顺序对所述目标播放场景进行预提醒处理，也即是，所述通信终端可以根据与所述目标播放场景的起始播放时间选取距离所述当前播放时间最近播放的目标播放场景进行预提醒处理。
S103、在所述视频的播放过程中，根据所述场景特征表中与所述目标播放场景关联的时间描述信息进行预提醒处理。
本发明实施例中，通信终端在对所述视频进行播放的过程中，所述通信终端可以根据所述场景特征表中与所述目标播放场景关联的时间描述信息进行预提醒处理。
具体实现中，用户/系统可以在所述通信终端中自定义设置对所述目标场景进行提醒的预设提醒时间，如设置在对所述目标播放场景进行播放之前的1分钟进行提醒，当所述视频播放到距离播放所述目标播放场景的起始播放时间之前的1分钟，发送用于提醒是否对所述目标播放场景进行播放的提示信息， 如以上述48:22-49:36时间段的目标播放场景为例，当所述视频播放到48:21时，所述通信终端可以发送用于提示是否播放所述血腥场景的提示信息；可选地，若用户/系统不在所述通信终端中设置预设提醒时间时，当所述通信终端检测到所述视频播放到所述目标播放场景的开始播放时间时，所述通信终端可以发送用于提示是否播放所述血腥场景的提示信息。所述通信终端可以通过发送语音信息来提示用户是否对所述目标播放场景进行播放，或者所述通信终端可以在显示屏上显示字幕来提示用户是否播放所述目标播放场景，或者所述通信终端以震动的方式提示用户是否播放所述目标播放场景，或者所述通信终端以其他的提示方式来提示用户是否播放所述目标播放场景，本发明实施例不作限定。
用户可以根据所述通信终端发送的用于提示是否播放所述目标播放场景提示信息，进行选择。所述通信终端可以检测并获取用户根据所述提示信息发送的用于指示对所述目标播放场景进行播放操作处理的操作指令，并根据所述操作指令对所述目标播放场景进行播放操作处理。
具体实现中，若所述操作指令为用于指示播放所述目标播放场景的播放指令，则所述通信终端根据所述播放指令(也即是响应所述播放指令)在播放到与所述目标播放场景对应的起始播放时间时，继续播放所述目标播放场景；若所述操作指令为用于指示不播放所述目标播放场景的跳过指令，则所述通信终端根据所述跳过指令(也即是响应所述跳过指令)在播放到与所述目标播放场景对应的起始播放时间时，跳过所述目标播放场景，从与所述目标播放场景对应的结束播放时间开始继续播放所述视频。
所述通信终端还可以获取用于指示是否有权对所述目标播放场景进行播放的权限验证信息，并验证所述权限验证信息是否有权对所述目标播放场景进行播放，若所述通信终端验证到有权播放所述目标播放场景，则根据所述操作指令对所述目标播放场景进行播放操作处理。
具体实现中，用户可以自定义在所述通信终端中设置用于对所述目标播放场景进行权限验证的验证参考信息(如指纹信息、密码信息、脸部特征信息等)，所述通信终端在对所述目标播放视频进行预提醒处理的过程中，也可以同时发送用于提示用户输入权限验证信息的提示信息，所述通信终端获取用户根据所 述提示信息返回的权限验证信息，所述通信终端验证所述权限验证信息和预置的验证参考信息的相似度是否超过预设第四阈值，若超过，则所述通信终端根据获取到的所述操作指令对所述目标播放视频进行播放操作处理。
需要说明的是，上述预设第一阈值、上述预设第二阈值、上述预设第三阈值和上述预设第四阈值，可以为用户或系统自定的预设阈值，所述预设阈值可以是相同的，也可以为不同的，本发明实施例不作限定。
本发明实施例可根据用户的实际需求对视频中的存在的特定播放场景进行预提醒处理，自动地、智能地进行特定播放场景的提醒，避免了用户毫无准备下观看这些特殊穿插场景带来的心理、生理上的冲击和伤害，提升了视频预提醒处理的实用性和方便快捷性。
请参见图2，是本发明实施例的另一种视频预提醒处理方法的流程示意图，本发明实施例的所述方法可以应用在诸如智能手机、平板电脑、智能可穿戴设备等带通信网络功能的终端中，具体可由这些通信终端的处理器来实现。本发明实施例的所述方法还包括如下步骤。
S201、当检测到视频播放事件时，获取当前播放的视频；其中，所述视频包括当前播放时间。
S202、获取所述视频中的各个帧图像，以及所述各个帧图像对应的播放时间。
S203、将所述各个帧图像与预设的多个场景下的图像进行特征匹配，并根据匹配结果和预设的场景，得到对应的播放场景；其中，所述播放场景为对所述视频中的场景片段进行分类得到的。
S204、根据得到的各个播放场景和帧图像的播放时间，生成场景特征表；其中，所述场景特征表包括至少一个播放场景、以及与所述播放场景对应的时间描述信息，所述时间描述信息包括播放所述播放场景的起始播放时间和结束播放时间。
本发明实施例中，当通信终端检测到用户使用本通信终端进行视频播放时，所述通信终端可以检测并获取用户当前播放的视频，并根据所述视频生成相应的场景特征表，所述场景特征表包括用于对所述视频中的场景片段进行分类识别得到的播放场景。
具体实现中，所述通信终端可以动态采取所述视频中的特定帧数图像，也即是所述视频中的帧图像，所述通信终端还可以确定所述帧图像的播放时间。可以理解的，1s视频中通常包括了几十帧的图像，1s视频中的开始、中间、结束对应的帧图像可以代表这1s视频包括的所有信息。也即是，所述通信终端可以将1s视频的开始、中间、结束这三个时间点作为采样时刻分别采集所述采样时刻对应的帧图像，如以4s-5s之间的1s视频片段为例，所述通信终端可以通过本终端中的信息采集区、图像处理器或者本终端其他的用于图像采集的模块采集4s、4.5s、5s这三个时刻对应的三个帧图像，这三个帧图像就可以代表4s-5s这个视频片段的所有信息；以此，所述通信终端可以完成对所述视频的各个帧图像的采集，所述通信终端还可以根据所述采样时刻确定所述帧图像对应的播放时间。
可以理解的是，当播放所述视频的画面变化迅速时，低采样率采集到的各个帧图像之间的差异比较大，这时就可以动态调整对帧图像采集的采样时刻，如上述采集到的4s、4.5s、5s这三个帧图像的差异比较大，这时所述通信终端就可以分别从4s-4.5s、4.5s-5s的时间段之间在重新选取几个(如3个)采样时刻再进行帧图像采集，直至所述通信终端在所述时间段中采集到的各个帧图像之间的差异不大为止。具体实现中，所述通信终端可以将4s、4.5s、5s对应采集到的帧图像进行特征信息匹配，得到第一匹配度(也即是，对上述三个帧图像进行相似度比较)，若所述第一匹配度超过预设第一阈值(如80％)，则表示所述三个帧图像之间的差异不大；若所述第一匹配度不超过所述预设第一阈值，则表示所述三个帧图像之间的差异大/差异明显。所述预设匹配度阈值可以为用户/系统自定义在所述通信终端中设置的，本发明实施例不作限定。
所述通信终端可以将采集到的各个帧图像与用户或者系统自定义在所述通信终端中设置的预设场景库中的各个场景下的图像进行特征信息匹配，得到第二匹配度；若所述第二匹配度超过用户/系统自定义在所述通信终端中设置的第二预设阈值，则所述通信终端可以根据上述用户/系统自定义设置的预设场景将各个帧图像进行分类，得到对应的播放场景，其中所述播放场景包括预设场景下的至少一个帧图像；所述通信终端还可以根据得到的各个播放场景、所述帧图像对应的播放时间生成场景特征表，其中所述场景特征表包括至少一 个播放场景、与所述播放场景对应的时间描述信息，所述时间描述信息可以包括所述帧图像对应的播放时间，还可以包括播放所述播放场景的起始播放时间和结束播放时间。
S205、从所述场景特征表中确定出需要执行预提醒处理的目标播放场景。
S206、根据所述特征信息表中与所述目标播放场景对应的起始播放时间、结束播放时间和所述当前播放时间对所述目标播放场景进行排序。
S207、根据所述进行排序的排序结果确定出所述目标播放场景的播放顺序。
本发明实施例中，所述通信终端还可以根据所述场景特征表中的与所述目标播放场景中的起始播放时间和结束播放时间对所述目标播放场景进行排序，所述通信终端根据所述排序的排序结果确定出对所述目标播放场景进行播放的播放顺序，所述通信终端可以根据所述播放顺序对所述目标播放场景进行预提醒处理；所述通信终端还可以获取用户当前播放所述视频的当前播放时间，所述通信终端还可以根据与所述播放场景对应的起始播放时间和结束播放时间以及当前播放时间对所述目标播放场景进行排序，所述通信终端根据所述排序的排序结果对所述目标播放场景进行预提醒处理，其中，所述排序可以根据时间排序、也可以根据播放时长排序、或者根据用户/系统自定义的播放场景的优先级进行排序，或者根据其他方式进行排序，本发明实施例不作限定。
S208、在所述视频的播放过程中，根据所述播放顺序和与所述目标播放场景关联的时间描述信息进行预提醒处理；其中，所述预提醒处理的方式包括语音提醒、字幕提醒、震动提醒中的一种或多种组合。
S209、接收用于指示对所述目标播放场景进行播放操作处理的操作指令，并根据所述操作指令对所述目标播放场景进行播放操作处理。
S210、若接收到的所述操作指令为用于指示播放所述目标播放场景的播放指令，则响应所述播放指令继续播放所述目标播放场景。
S211、若接收到的所述操作指令为用于指示不播放所述目标播放场景的跳过指令，则响应所述跳过指令跳过所述目标播放场景，从与所述目标播放场景对应的结束播放时间开始继续播放所述视频。
需要说明的是，步骤S210和步骤S209是步骤S209执行所述根据所述操 作指令对所述目标播放场景进行播放操作处理的具体实现方式。
本发明实施例可根据用户的实际需求对视频中的存在的特定播放场景进行预提醒处理，自动地、智能地进行特定播放场景的提醒，避免了用户毫无准备下观看这些特殊穿插场景带来的心理、生理上的冲击和伤害，提升了视频预提醒处理的实用性和方便快捷性。
请一并参阅图3，是本发明实施例的另一种视频预提醒处理方法的流程示意图，在上述步骤S209中所述根据所述操作指令对所述目标播放场景进行播放操作处理之前，还包括如下步骤：
S301、获取用于指示是否有权对所述目标播放场景进行播放的权限验证信息。
S302、验证所述权限验证信息是否有权对所述目标播放场景进行播放。
本发明实施例中，所述通信终端还可以获取用于指示是否有权对所述目标播放场景进行播放的权限验证信息(如指纹信息、密码信息、脸部特征信息等)，并验证所述权限验证信息是否有权对所述目标播放场景进行播放，若所述通信终端验证到有权播放所述目标播放场景，则继续执行步骤S209；否则，执行步骤S303。
S303、跳过所述目标播放场景，从与所述目标播放场景对应的结束播放时间开始继续播放所述视频。
示例性地，家里的父母可以在家用电脑上对某些特定的播放场景(如暴力、血腥、色情等播放场景)进行加密，得到用于多所述特定播放场景进行权限验证的初始验证信息(如指纹信息、密码信息等)，当小孩在使用电脑进行视频播放时，所述电脑可以执行上述步骤S201-S208，当所述电脑检测到播放所述视频到预设提醒时间或者播放到所述目标播放场景的起始播放时间时，所述电脑可以发送用于提示用于用户输入对所述目标播放场景进行权限验证的权限验证信息的提示信息，或者直接在现实界面上显示对应的权限验证信息输入界面，用户根据所述提示信息返回权限验证信息，或者在所述权限验证信息输入界面上输入对应的权限验证信息；所述电脑可以检测并获取用户输入的所述权限验证信息；所述电脑将所述权限验证信息与预置的初始验证信息进行相似度比较，所述电脑将所述相似度比较得到的相似度与用户/系统在本电脑中自定 义的预设阈值(如80％)进行比较，若超过所述预设阈值，则执行步骤S209；否则，执行步骤S303。
本发明实施例可根据用户的实际需求对视频中的存在的特定播放场景进行预提醒处理，自动地、智能地进行特定播放场景的提醒，避免了用户毫无准备下观看这些特殊穿插场景带来的心理、生理上的冲击和伤害，提升了视频预提醒处理的实用性和方便快捷性。
请参见图4，是本发明实施例的一种视频预提醒处理装置的结构示意图，本发明实施例的所述装置可以可设置在诸如智能手机、平板电脑、智能可穿戴设备等带通信网络功能的终端中，所述装置4包括：
获取生成模块40，用于当检测到视频播放事件时，获取当前播放的视频，并为所述视频生成场景特征表，所述场景特征表包括用于对所述视频中的场景片段进行分类识别得到的播放场景；
确定模块41，用于从所述获取生成模块40生成的场景特征表中确定出需要执行预提醒处理的目标播放场景；
提醒处理模块42，用于在所述视频的播放过程中，根据所述场景特征表中与所述目标播放场景关联的时间描述信息进行预提醒处理。
本发明实施例中，当获取生成模块40检测到视频播放事件时，所述获取生成模块40获取当前播放的视频，并为所述视频生成场景特征表，所述场景特征表包括对所述视频中的场景片段进行分类识别得到的播放场景；确定模块41从所述获取生成模块40生成的场景特征表中确定出需要执行预提醒处理的目标播放场景；在所述视频的播放过程中，提醒处理模块42根据所述获取生成模块40生成的场景特征表中的与所述确定模块41确定出的目标播放场景关联的时间描述信息进行预提醒处理。
本发明实施例可根据用户的实际需求对视频中的存在的特定播放场景进行预提醒处理，自动地、智能地进行特定播放场景的提醒，避免了用户毫无准备下观看这些特殊穿插场景带来的心理、生理上的冲击和伤害，提升了视频预提醒处理的实用性和方便快捷性。
请参见图5，是本发明实施例的一种视频预提醒处理装置的结构示意图，本发明实施例的所述装置可以可设置在诸如智能手机、平板电脑、智能可穿戴 设备等带通信网络功能的终端中，所述装置5包括上述的获取生成模块40、确定模块41、提醒处理模块42，还包括：
所述获取生成模块40包括：
获取单元400，用于获取所述视频中的各个帧图像，以及所述各个帧图像对应的播放时间；
匹配单元401，用于将所述各个帧图像与预设的多个场景下的图像进行特征匹配，并根据匹配结果和预设的场景，得到对应的播放场景；
生成单元402，用于根据得到的各个播放场景和帧图像的播放时间，生成场景特征表。
其中可选地，所述获取生成模块40中生成的场景特征表包括至少一个播放场景、以及与所述播放场景对应的时间描述信息，其中，所述时间描述信息包括播放所述播放场景的起始播放时间和结束播放时间。
其中可选地，所述视频包括当前播放时间，所述装置还包括：
排序模块43，用于根据所述特征信息表中与所述目标播放场景对应的起始播放时间、结束播放时间和所述当前播放时间对所述目标播放场景进行排序；
所述确定模块41，还用于根据所述排序模块进行排序的排序结果确定出所述目标播放场景的播放顺序，以便根据所述播放顺序和与所述目标播放场景关联的时间描述信息进行预提醒处理。
其中可选地，所述装置还包括：
接收处理模块44，用于接收关于所述目标播放场景的操作指令，并根据所述操作指令对所述目标播放场景进行对应的操作处理；其具体包括：
所述接收处理模块44，具体用于若接收到的所述操作指令为用于指示播放所述目标播放场景的播放指令，则响应所述播放指令继续播放所述目标播放场景；或者，
所述接收处理模块44，具体用于若接收到的所述操作指令为用于指示不播放所述目标播放场景的跳过指令，则响应所述跳过指令跳过所述目标播放场景，从与所述目标播放场景对应的结束播放时间开始继续播放所述视频。
其中可选地，所述装置还包括：
获取验证模块45，用于获取用于指示是否有权对所述目标播放场景进行播放的权限验证信息，并验证所述权限验证信息是否有权对所述目标播放场景进行播放；若所述获取验证模块45验证到有权，则通知所述接收处理模块44。
本发明实施例可根据用户的实际需求对视频中的存在的特定播放场景进行预提醒处理，自动地、智能地进行特定播放场景的提醒，避免了用户毫无准备下观看这些特殊穿插场景带来的心理、生理上的冲击和伤害，提升了视频预提醒处理的实用性和方便快捷性。
再请参见图6，是本发明实施例的一种终端的结构示意图。所述终端可以为智能手机、平板电脑、智能可穿戴设备等带通信网络功能的设备，如图5所示，本发明实施例的所述终端可以包括显示屏、按键、扬声器、拾音器等模块，并且还包括：至少一个总线501、与总线501相连的至少一个处理器502以及与总线501相连的至少一个存储器503，实现通信功能的通信装置505，为通信终端各耗电模块供电的电源装置504。
所述处理器502可通过总线501，调用存储器503中存储的代码以执行相关的功能。
所述处理器502，用于当检测到视频播放事件时，获取当前播放的视频，并为所述视频生成场景特征表，所述场景特征表包括对所述视频中的场景片段进行分类识别得到的播放场景；从所述场景特征表中确定出需要执行预提醒处理的目标播放场景；在所述视频的播放过程中，根据所述场景特征表中与所述目标播放场景关联的时间描述信息进行预提醒处理。
进一步可选地，所述处理器502还用于获取所述视频中的各个帧图像，以及所述各个帧图像对应的播放时间；将所述各个帧图像与预设的多个场景下的图像进行特征匹配，并根据匹配结果和预设的场景，得到对应的播放场景；根据得到的各个播放场景和帧图像的播放时间，生成场景特征表。
进一步可选地，所述处理器502还用于所述场景特征表包括至少一个播放场景、以及与所述播放场景对应的时间描述信息，其中，所述时间描述信息包括播放所述播放场景的起始播放时间和结束播放时间。
进一步可选地，所述处理器502还用于根据所述特征信息表中与所述目标播放场景对应的起始播放时间、结束播放时间和所述当前播放时间对所述目标 播放场景进行排序；根据所述进行排序的排序结果确定出所述目标播放场景的播放顺序，以便根据所述播放顺序和与所述目标播放场景关联的时间描述信息进行预提醒处理。
进一步可选地，所述处理器502还用于接收关于所述目标播放场景的操作指令，并根据所述操作指令对所述目标播放场景进行对应的操作处理；其具体包括：若接收到的所述操作指令为用于指示播放所述目标播放场景的播放指令，则响应所述播放指令继续播放所述目标播放场景；或者，若接收到的所述操作指令为用于指示不播放所述目标播放场景的跳过指令，则响应所述跳过指令跳过所述目标播放场景，从与所述目标播放场景对应的结束播放时间开始继续播放所述视频。
进一步可选地，所述处理器502还用于获取用于指示是否有权对所述目标播放场景进行播放的权限验证信息，并验证所述权限验证信息是否有权对所述目标播放场景进行播放；若有权，则执行所述根据所述操作指令对所述目标播放场景进行对应的操作处理。
本发明实施例可根据用户的实际需求对视频中的存在的特定播放场景进行预提醒处理，自动地、智能地进行特定播放场景的提醒，避免了用户毫无准备下观看这些特殊穿插场景带来的心理、生理上的冲击和伤害，提升了视频预提醒处理的实用性和方便快捷性。
本发明实施例还提供一种计算机存储介质，其中，该计算机存储介质可存储有程序，该程序执行时包括上述方法实施例中记载的任何音频播放应用的操作方法的部分或全部步骤。
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，本发明并不受所描述的动作顺序的限制，因为依据本发明，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发明所必须的。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其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，所揭露的装置，可通过其 它的方式实现。例如，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，装置或单元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，在本发明的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。
所述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，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有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一个存储介质中，包括若干指令用以使得一台计算机设备(可为个人计算机、服务器或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：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。
以上所述，以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的范围。

Claims (18)

  1. 一种视频预提醒处理的方法，其特征在于，所述方法包括：
    当检测到视频播放事件时，获取当前播放的视频，并为所述视频生成场景特征表，所述场景特征表包括对所述视频中的场景片段进行分类识别得到的播放场景；
    从所述场景特征表中确定出需要执行预提醒处理的目标播放场景；
    在所述视频的播放过程中，根据所述场景特征表中与所述目标播放场景关联的时间描述信息进行预提醒处理。
  2. 如权利要求1所述的方法，其特征在于，所述为所述视频生成场景特征表，包括：
    获取所述视频中的各个帧图像，以及所述各个帧图像对应的播放时间；
    将所述各个帧图像与预设的多个场景下的图像进行特征匹配，并根据匹配结果和预设的场景，得到对应的播放场景；
    根据得到的各个播放场景和帧图像的播放时间，生成场景特征表。
  3. 如权利要求2所述的方法，其特征在于，所述场景特征表包括至少一个播放场景、以及与所述播放场景对应的时间描述信息，其中，所述时间描述信息包括播放所述播放场景的起始播放时间和结束播放时间。
  4. 如权利要求3所述的方法，所述视频包括当前播放时间，其特征在于，所述在所述视频的播放过程中，根据所述场景特征表中与所述目标播放场景关联的时间描述信息进行预提醒处理之前，还包括：
    根据所述特征信息表中与所述目标播放场景对应的起始播放时间、结束播放时间和所述当前播放时间对所述目标播放场景进行排序；
    根据所述进行排序的排序结果确定出所述目标播放场景的播放顺序，以便根据所述播放顺序和与所述目标播放场景关联的时间描述信息进行预提醒处理。
  5. 如权利要求3所述的方法，其特征在于，所述根据所述场景特征表中与所述目标播放场景关联的时间描述信息进行预提醒处理之后，还包括：
    接收关于所述目标播放场景的操作指令，并根据所述操作指令对所述目标播放场景进行对应的操作处理；其具体包括：
    若接收到的所述操作指令为用于指示播放所述目标播放场景的播放指令，则响应所述播放指令继续播放所述目标播放场景；或者，
    若接收到的所述操作指令为用于指示不播放所述目标播放场景的跳过指令，则响应所述跳过指令跳过所述目标播放场景，从与所述目标播放场景对应的结束播放时间开始继续播放所述视频。
  6. 如权利要求5所述的方法，其特征在于，所述根据所述操作指令对所述目标播放场景进行对应的操作处理之前，还包括：
    获取用于指示是否有权对所述目标播放场景进行播放的权限验证信息，并验证所述权限验证信息是否有权对所述目标播放场景进行播放；
    若有权，则执行所述根据所述操作指令对所述目标播放场景进行对应的操作处理。
  7. 一种视频预提醒处理的装置，其特征在于，所述装置包括：
    获取生成模块，用于当检测到视频播放事件时，获取当前播放的视频，并为所述视频生成场景特征表，所述场景特征表包括对所述视频中的场景片段进行分类识别得到的播放场景；
    确定模块，用于从所述获取生成模块生成的场景特征表中确定出需要执行预提醒处理的目标播放场景；
    提醒处理模块，用于在所述视频的播放过程中，根据所述场景特征表中与所述目标播放场景关联的时间描述信息进行预提醒处理。
  8. 如权利要求7所述的装置，其特征在于，所述获取生成模块包括：
    获取单元，用于获取所述视频中的各个帧图像，以及所述各个帧图像对应的播放时间；
    匹配单元，用于将所述各个帧图像与预设的多个场景下的图像进行特征匹配，并根据匹配结果和预设的场景，得到对应的播放场景；
    生成单元，用于根据得到的各个播放场景和帧图像的播放时间，生成场景特征表。
  9. 如权利要求8所述的装置，其特征在于，所述场景特征表包括至少一个播放场景、以及与所述播放场景对应的时间描述信息，其中，所述时间描述信息包括播放所述播放场景的起始播放时间和结束播放时间。
  10. 如权利要求9所述的装置，所述视频包括当前播放时间，其特征在于，所述装置还包括：
    排序模块，用于根据所述特征信息表中与所述目标播放场景对应的起始播放时间、结束播放时间和所述当前播放时间对所述目标播放场景进行排序；
    所述确定模块，还用于根据所述排序模块进行排序的排序结果确定出所述目标播放场景的播放顺序，以便根据所述播放顺序和与所述目标播放场景关联的时间描述信息进行预提醒处理。
  11. 如权利要求9所述的装置，其特征在于，所述装置还包括：
    接收处理模块，用于接收关于所述目标播放场景的操作指令，并根据所述操作指令对所述目标播放场景进行对应的操作处理；其具体包括：
    所述接收处理模块，具体用于若接收到的所述操作指令为用于指示播放所述目标播放场景的播放指令，则响应所述播放指令继续播放所述目标播放场景；或者，
    所述接收处理模块，具体用于若接收到的所述操作指令为用于指示不播放所述目标播放场景的跳过指令，则响应所述跳过指令跳过所述目标播放场景，从与所述目标播放场景对应的结束播放时间开始继续播放所述视频。
  12. 如权利要求11所述的装置，其特征在于，所述装置还包括：
    获取验证模块，用于获取用于指示是否有权对所述目标播放场景进行播放的权限验证信息，并验证所述权限验证信息是否有权对所述目标播放场景进行播放；若所述获取验证模块验证到有权，则通知所述接收处理模块。
  13. 一种终端，其特征在于，所述终端包括处理器和存储器，其中，所述存储器中存储一组程序代码，且所述处理器用于调用所述存储器中存储的程序 代码，用于执行以下操作：
    当检测到视频播放事件时，获取当前播放的视频，并为所述视频生成场景特征表，所述场景特征表包括对所述视频中的场景片段进行分类识别得到的播放场景；
    从所述场景特征表中确定出需要执行预提醒处理的目标播放场景；
    在所述视频的播放过程中，根据所述场景特征表中与所述目标播放场景关联的时间描述信息进行预提醒处理。
  14. 如权利要求13所述的终端，其特征在于，所述处理器为所述视频生成场景特征表，包括：
    获取所述视频中的各个帧图像，以及所述各个帧图像对应的播放时间；
    将所述各个帧图像与预设的多个场景下的图像进行特征匹配，并根据匹配结果和预设的场景，得到对应的播放场景；
    根据得到的各个播放场景和帧图像的播放时间，生成场景特征表。
  15. 如权利要求14所述的终端，其特征在于，所述场景特征表包括至少一个播放场景、以及与所述播放场景对应的时间描述信息，其中，所述时间描述信息包括播放所述播放场景的起始播放时间和结束播放时间。
  16. 如权利要求15所述的方法，所述视频包括当前播放时间，其特征在于，所述处理器在所述视频的播放过程中，根据所述场景特征表中与所述目标播放场景关联的时间描述信息进行预提醒处理之前，还执行以下操作：
    根据所述特征信息表中与所述目标播放场景对应的起始播放时间、结束播放时间和所述当前播放时间对所述目标播放场景进行排序；
    根据所述进行排序的排序结果确定出所述目标播放场景的播放顺序，以便根据所述播放顺序和与所述目标播放场景关联的时间描述信息进行预提醒处理。
  17. 如权利要求15所述的方法，其特征在于，所述处理器在根据所述场景特征表中与所述目标播放场景关联的时间描述信息进行预提醒处理之后，还执行以下操作：
    接收关于所述目标播放场景的操作指令，并根据所述操作指令对所述目标播放场景进行对应的操作处理；其具体包括：
    若接收到的所述操作指令为用于指示播放所述目标播放场景的播放指令，则响应所述播放指令继续播放所述目标播放场景；或者，
    若接收到的所述操作指令为用于指示不播放所述目标播放场景的跳过指令，则响应所述跳过指令跳过所述目标播放场景，从与所述目标播放场景对应的结束播放时间开始继续播放所述视频。
  18. 如权利要求17所述的方法，其特征在于，所述处理器在根据所述操作指令对所述目标播放场景进行对应的操作处理之前，还执行以下操作：
    获取用于指示是否有权对所述目标播放场景进行播放的权限验证信息，并验证所述权限验证信息是否有权对所述目标播放场景进行播放；
    若有权，则执行所述根据所述操作指令对所述目标播放场景进行对应的操作处理。
PCT/CN2016/074843 2016-01-28 2016-02-29 一种视频预提醒处理的方法、装置以及终端 Ceased WO2017128482A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610061655.9A CN105744355A (zh) 2016-01-28 2016-01-28 一种视频预提醒处理的方法、装置以及终端
CN201610061655.9 2016-01-28

Publications (1)

Publication Number Publication Date
WO2017128482A1 true WO2017128482A1 (zh) 2017-08-03

Family

ID=56246991

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/074843 Ceased WO2017128482A1 (zh) 2016-01-28 2016-02-29 一种视频预提醒处理的方法、装置以及终端

Country Status (2)

Country Link
CN (1) CN105744355A (zh)
WO (1) WO2017128482A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110580303A (zh) * 2018-05-21 2019-12-17 谷林娜 一种穴位按摩视频的生成方法及装置
CN111475675A (zh) * 2020-04-07 2020-07-31 深圳市超高清科技有限公司 视频处理系统
CN114363683A (zh) * 2020-10-14 2022-04-15 深圳市万普拉斯科技有限公司 图像显示方法、装置、计算机设备和存储介质
CN115981195A (zh) * 2022-12-07 2023-04-18 慕思健康睡眠股份有限公司 智能床垫的控制方法及装置、智能床垫、存储介质

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107911744B (zh) * 2017-12-04 2020-07-03 微鲸科技有限公司 播放管控方法及装置
CN110475121B (zh) * 2018-05-10 2022-02-11 腾讯科技（深圳）有限公司 一种视频数据处理方法、装置以及相关设备
CN109120949B (zh) * 2018-09-30 2021-07-23 武汉斗鱼网络科技有限公司 视频集合的视频消息推送方法、装置、设备及存储介质
CN111385642A (zh) * 2018-12-29 2020-07-07 阿里巴巴集团控股有限公司 媒体信息的处理方法、装置、服务器、设备及存储介质
CN110062271B (zh) * 2019-04-28 2022-03-04 腾讯科技(成都)有限公司 场景切换方法、装置、终端及存储介质
CN110381364A (zh) * 2019-06-13 2019-10-25 北京奇艺世纪科技有限公司 视频数据处理方法、装置、计算机设备和存储介质
CN110856013A (zh) * 2019-11-19 2020-02-28 珠海格力电器股份有限公司 识别视频中关键片段的方法、系统和存储介质
CN111143612B (zh) * 2019-12-27 2023-06-27 广州市百果园信息技术有限公司 视频审核模型训练方法、视频审核方法及相关装置
CN111416997B (zh) * 2020-03-31 2022-11-08 百度在线网络技术（北京）有限公司 视频播放方法、装置、电子设备和存储介质
CN111797752B (zh) * 2020-06-29 2024-08-02 广州市百果园信息技术有限公司 违规视频检测方法、装置、设备及存储介质
CN112423077A (zh) * 2020-10-15 2021-02-26 深圳Tcl新技术有限公司 视频播放方法、装置、设备和存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101739228A (zh) * 2008-11-20 2010-06-16 辉达公司 用于防止不想要内容显示的系统,方法和计算机程序产品
CN103167361A (zh) * 2011-12-19 2013-06-19 汤姆森特许公司 处理视听内容的方法及对应设备
CN103473340A (zh) * 2013-09-23 2013-12-25 江苏刻维科技信息有限公司 基于视频图像的互联网多媒体内容的分类方法
US20150033249A1 (en) * 2005-11-14 2015-01-29 Rovi Guides, Inc. Media control system with viewer rewards
CN104602134A (zh) * 2015-01-16 2015-05-06 乐视致新电子科技（天津）有限公司 智能电视的节目提醒的控制方法及装置
US20150365725A1 (en) * 2014-06-11 2015-12-17 Rawllin International Inc. Extract partition segments of personalized video channel
CN105227973A (zh) * 2014-06-27 2016-01-06 中兴通讯股份有限公司 基于场景识别的信息推荐方法及装置

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100672406B1 (ko) * 2002-07-22 2007-01-23 엘지전자 주식회사 특정 프로그램에 대한 시청허가 장치 및 그 방법
US20090288112A1 (en) * 2008-05-13 2009-11-19 Porto Technology, Llc Inserting advance content alerts into a media item during playback
CN102447818A (zh) * 2010-09-30 2012-05-09 上海维阔信息技术有限公司 视频版权保护和分级观看的播放方法
CN102236796B (zh) * 2011-07-13 2014-01-22 Tcl集团股份有限公司 数字视频不良内容的分类方法和系统
US9432730B2 (en) * 2012-12-26 2016-08-30 Huawei Technologies Co., Ltd. Multimedia file playback method and apparatus
CN104240224B (zh) * 2013-06-20 2018-04-27 富泰华工业（深圳）有限公司 视频分析系统及方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150033249A1 (en) * 2005-11-14 2015-01-29 Rovi Guides, Inc. Media control system with viewer rewards
CN101739228A (zh) * 2008-11-20 2010-06-16 辉达公司 用于防止不想要内容显示的系统,方法和计算机程序产品
CN103167361A (zh) * 2011-12-19 2013-06-19 汤姆森特许公司 处理视听内容的方法及对应设备
CN103473340A (zh) * 2013-09-23 2013-12-25 江苏刻维科技信息有限公司 基于视频图像的互联网多媒体内容的分类方法
US20150365725A1 (en) * 2014-06-11 2015-12-17 Rawllin International Inc. Extract partition segments of personalized video channel
CN105227973A (zh) * 2014-06-27 2016-01-06 中兴通讯股份有限公司 基于场景识别的信息推荐方法及装置
CN104602134A (zh) * 2015-01-16 2015-05-06 乐视致新电子科技（天津）有限公司 智能电视的节目提醒的控制方法及装置

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110580303A (zh) * 2018-05-21 2019-12-17 谷林娜 一种穴位按摩视频的生成方法及装置
CN110580303B (zh) * 2018-05-21 2023-09-12 谷林娜 一种穴位按摩视频的生成方法及装置
CN111475675A (zh) * 2020-04-07 2020-07-31 深圳市超高清科技有限公司 视频处理系统
CN111475675B (zh) * 2020-04-07 2023-03-24 深圳市超高清科技有限公司 视频处理系统
CN114363683A (zh) * 2020-10-14 2022-04-15 深圳市万普拉斯科技有限公司 图像显示方法、装置、计算机设备和存储介质
CN115981195A (zh) * 2022-12-07 2023-04-18 慕思健康睡眠股份有限公司 智能床垫的控制方法及装置、智能床垫、存储介质

Also Published As

Publication number Publication date
CN105744355A (zh) 2016-07-06

Similar Documents

Publication Publication Date Title
WO2017128482A1 (zh) 一种视频预提醒处理的方法、装置以及终端
TWI717146B (zh) 圖像處理方法及裝置、電子設備和儲存介質
JP6474393B2 (ja) 顔アルバムに基づく音楽再生方法、装置および端末デバイス
CN102710991B (zh) 信息处理设备、信息处理方法和程序
CN108370447B (zh) 内容处理装置及其内容处理方法、服务器
WO2020134527A1 (zh) 人脸识别的方法及装置
CN103905904B (zh) 播放多媒体文件的方法及装置
KR101895846B1 (ko) 소셜 네트워킹 툴들과의 텔레비전 기반 상호작용의 용이화
CN105611382A (zh) 产生概要内容的电子设备及其方法
JP2022524672A (ja) 情報認識方法及び装置、システム、電子機器、記憶媒体並びにコンピュータプログラム
CN105825112A (zh) 移动终端的解锁方法及装置
WO2011026397A1 (zh) 图像提示方法及数码相框
CN108933929A (zh) 一种视频监测方法及安防侦测设备
CN114612986A (zh) 检测方法、装置、电子设备及存储介质
CN111654748A (zh) 限制级画面检测方法、装置、显示设备和可读存储介质
US12216708B2 (en) Digital media authentication
US10904586B2 (en) Methods, systems, and media for detecting and transforming rotated video content items
CN109840406B (zh) 活体验证方法、装置和计算机设备
CN107851129B (zh) 信息处理装置、信息处理方法和程序
WO2017092328A1 (zh) 一种智能电视的用户数据区分方法和装置
CN109151599B (zh) 视频处理方法和装置
WO2016058540A1 (zh) 身份验证方法、装置和存储介质
US20160328474A1 (en) Data recording and data recording apparatus
CN114302231A (zh) 视频处理方法及装置、电子设备和存储介质
KR20150023492A (ko) 동기화된 영화 요약

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: 16887366

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: 16887366

Country of ref document: EP

Kind code of ref document: A1