WO2019109643A1 - 视频推荐方法、装置、计算机设备和存储介质 - Google Patents
视频推荐方法、装置、计算机设备和存储介质 Download PDFInfo
- Publication number
- WO2019109643A1 WO2019109643A1 PCT/CN2018/096177 CN2018096177W WO2019109643A1 WO 2019109643 A1 WO2019109643 A1 WO 2019109643A1 CN 2018096177 W CN2018096177 W CN 2018096177W WO 2019109643 A1 WO2019109643 A1 WO 2019109643A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- video
- target
- long
- key frame
- feature
- 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
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
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/482—End-user interface for programme selection
- H04N21/4826—End-user interface for programme selection using recommendation lists, e.g. of programmes or channels sorted out according to their score
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from 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
- H04N21/43—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
- H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
- H04N21/4312—Generation of visual interfaces for content selection or interaction; Content or additional data rendering involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations
-
- 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
- H04N21/47—End-user applications
- H04N21/482—End-user interface for programme selection
- H04N21/4828—End-user interface for programme selection for searching programme 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]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/488—Data services, e.g. news ticker
- H04N21/4882—Data services, e.g. news ticker for displaying messages, e.g. warnings, reminders
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/60—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
Definitions
- the present application relates to the field of video processing technologies, and in particular, to a video recommendation method, apparatus, computer device, and storage medium.
- short videos are easy to watch at any time because of their short and refined features. Therefore, under this kind of user demand, short video technology has developed rapidly.
- the short video is obtained based on the long video clip. After watching the short video, the user hopes to know the long video intercepted by the short video. However, in the prior art, the user can only manually query the relevant long video through the title of the short video. If the title of the short video does not have any long video related information, the user cannot find the related long video.
- the present application aims to solve at least one of the technical problems in the related art to some extent.
- the first object of the present application is to propose a video recommendation method for recommending a target long video intercepted by a short video to a user, thereby avoiding a process of manual search by a user.
- a second object of the present application is to propose a video recommendation device.
- a third object of the present application is to propose a computer device.
- a fourth object of the present application is to propose a non-transitory computer readable storage medium.
- a fifth object of the present application is to propose a computer program product.
- the first aspect of the present application provides a video recommendation method, including:
- the target long video is recommended to the user.
- the video recommendation method in the embodiment of the present application after acquiring the short video of the target viewed by the user, according to the video fingerprint feature of the target short video and the video fingerprint feature of the candidate long video, the target short video is captured from the candidate long video.
- the target long video and then recommend the target long video to the user.
- the method of recognizing the target long video intercepted by the target short video from the candidate long video according to the video fingerprint feature is recognized even if the title of the target short video does not carry any long video related information.
- the long-distance video captured by the user is taken out.
- the process of manually querying by the user is avoided, and the technical problem of recognizing the long video operation intercepted by the short video in the prior art is not enough.
- the second aspect of the present application provides a video recommendation apparatus, including:
- An acquisition module configured to acquire a short video of a target viewed by a user
- An identification module configured to identify, according to the video fingerprint feature of the target short video and the video fingerprint feature of the candidate long video, from the candidate long video, the target long video intercepted by the short video;
- a recommendation module for recommending the target long video to the user.
- the video recommendation device of the embodiment of the present application after acquiring the short video of the target viewed by the user, according to the video fingerprint feature of the target short video and the video fingerprint feature of the candidate long video, the target short video is captured from the candidate long video.
- the target long video and then recommend the target long video to the user.
- the method of recognizing the target long video intercepted by the target short video from the candidate long video according to the video fingerprint feature is recognized even if the title of the target short video does not carry any long video related information.
- the long-distance video captured by the user is taken out.
- the process of manually querying by the user is avoided, and the technical problem of recognizing the long video operation intercepted by the short video in the prior art is not enough.
- a third aspect of the present application provides a computer device including a memory, a processor, and a computer program stored on the memory and operable on the processor, when the processor executes the program, A video recommendation method as described in the first aspect is implemented.
- a fourth aspect of the present application provides a non-transitory computer readable storage medium having a computer program stored thereon, and the program is implemented by the processor to implement the video recommendation method according to the first aspect. .
- a fifth aspect of the present application provides a computer program product that, when executed by an instruction processor in the computer program product, performs the video recommendation method of the first aspect.
- FIG. 1 is a schematic flowchart of a video recommendation method according to an embodiment of the present application
- 2A is a schematic diagram of a video playback related page
- 2B is a second schematic diagram of a video playback related page
- 2C is a third schematic diagram of a video playback related page
- 2D is a fourth schematic diagram of a video playback related page
- FIG. 3 is a schematic flowchart diagram of another video recommendation method according to an embodiment of the present disclosure.
- FIG. 4 is a schematic diagram of dividing a first key frame into a plurality of partial regions
- Figure 5 is a schematic view of a coordinate system XY
- FIG. 6 is a schematic structural diagram of a video recommendation apparatus according to an embodiment of the present disclosure.
- FIG. 7 is a schematic structural diagram of another video recommendation apparatus according to an embodiment of the present application.
- FIG. 8 illustrates a block diagram of an exemplary computer device suitable for use in implementing embodiments of the present application.
- FIG. 1 is a schematic flowchart diagram of a video recommendation method according to an embodiment of the present application.
- the short video clip taken by the long video is a very effective way of spreading, which enables the long video of the film and television drama to be transmitted in the form of short video.
- some users need to know more about which ministerial video the short video is from.
- the embodiment of the present application provides a video recommendation method, which not only captures the target long video intercepted by the target short video viewed by the user, but also recommends the target long video to the user.
- the video recommendation method includes the following steps:
- Step 101 Acquire a short video of the target viewed by the user.
- the content of the target short video viewed by the user is acquired, where the content includes the identifier, image and audio of the target short video.
- Step 102 According to the video fingerprint feature of the target short video and the video fingerprint feature of the candidate long video, identify, from the candidate long video, the target long video intercepted by the target short video.
- the server performing the method of the embodiment has obtained the video fingerprint features of the plurality of candidate long videos in advance, so that the candidate long video whose video fingerprint features match each other can be queried according to the video fingerprint feature of the target short video, as the target long video.
- the video fingerprint feature is used to describe the content of the video, when the target short video is intercepted from the target long video, the contents of the two are similar, so that the video fingerprint features should also match each other.
- the target long video captured by the target short video is identified according to the video fingerprint feature, and has high accuracy.
- the video fingerprint feature includes the image feature and the audio feature.
- the feature is extracted after the key frame is extracted from the video.
- the method for acquiring the video fingerprint feature is described in detail in the following embodiments. Narration.
- step 103 the target long video is recommended to the user.
- the prompt information of the target long video is displayed.
- the prompt information herein may include at least one of an identifier of the target long video, a resource link of the target long video, and an identifier of the long video set to which the target long video belongs.
- the identifier of the target long video may specifically be the title of the target long video.
- the target long video may be a certain episode of the TV series, so that the long video collection to which the target long video belongs is specifically the title of the drama.
- the target short video is intercepted from a certain episode of the TV series, and the target short video is captured from the episode n of the TV series A.
- the prompt information can be displayed "excerpted from "TV drama A”, click to view the complete episode", the prompt information is also You can further display the specific episodes, such as "Excerpt from Episode n of TV Series A, click to view the full episode.”
- the play page for playing the target long video is displayed to play the target long video.
- the target operation may specifically be an operation for triggering a jump to a play page of the target long video.
- the hovering control is displayed on the play page.
- the floating control is used to display the prompt information of the target long video and respond to the target operation performed by the user.
- a part of the display area is used to play the target short video in the play page, that is, a non-full screen mode
- another part of the display area is displayed in the play page to display the Prompt message.
- the video recommendation method will be described in detail from the perspective of user operation in conjunction with the video playback related page diagrams of FIG. 2A to FIG. 2D.
- the user selects the second short video in the list in the playlist page as shown in FIG. 2A as the target short video. Specifically, the user can select from the second short video thumbnail or the title on the right side of the thumbnail to jump from the playlist page shown in FIG. 2A to the target short video as shown in FIG. 2B. Play the page to play the short video.
- FIG. 2B there is a display area for playing the short video of the target, and another display area is arranged below the display area, and another display area may be used to display the prompt information, and another display area It can be located below the display area used to play the short video of the target.
- the prompt information displayed in the other display area carries the resource link of the target long video.
- the playback page shown in FIG. 2B uses a non-full-screen playback mode to play the target short video.
- the full-screen playback mode as shown in FIG. 2C is obtained.
- the prompt information of the long video of the panel may be displayed in a floating control manner in the page shown in FIG. 2C, and when the user clicks on the floating control, the jump to the target length as shown in FIG. 2D is performed.
- the video playback page plays the target long video.
- the target long video captured by the target short video is identified from the candidate long video. And then recommend the target long video to the user.
- the method of recognizing the target long video intercepted by the target short video from the candidate long video according to the video fingerprint feature is recognized even if the title of the target short video does not carry any long video related information.
- the long-distance video captured by the user is taken out. At the same time, since the target long video is actively recommended to the user, the process of manually querying by the user is avoided, and the technical problem of recognizing the long video operation intercepted by the short video in the prior art is not enough.
- FIG. 3 is a schematic flowchart of another video recommendation method provided by the embodiment of the present application.
- the video recommendation method may include the following steps:
- step 201 a feature index library is established.
- image feature extraction is performed according to multiple local regions in the first key frame to obtain image features of the first key frame;
- the feature index library is established for each image feature of the first key frame.
- the feature index library mainly stores image features of each first key frame in each candidate long video.
- the target short video may be obtained by editing a complete frame picture from the target long video, and then performing video synthesis on the complete frame picture, and possibly, after capturing the complete frame picture, taking a part of the frame picture, For example, the central area is to cut off unnecessary pictures in the complete frame picture, such as subtitles below the frame picture, flags at the four corners of the frame picture, and the like.
- each of the first key frames may be divided into a plurality of partial regions, where the size of the local regions may be according to the processing capability of the server performing the method of the embodiment, and the processing capability is strong. Then, each of the first key frames may be divided into a plurality of local regions, and the number of pixels included may be correspondingly small.
- the first key frame is divided into a plurality of partial regions. As shown in FIG. 4, each local region may have no overlapping portion. In another possible implementation manner, The adjacent partial regions may have overlapping portions, which are not limited in this embodiment.
- Each local area of the first key frame is subjected to feature extraction, and image features of each partial area are used as image features of the first key frame.
- the feature index library stores not only image features of the first key frame but also corresponding audio features. As a possible implementation manner, for each first key frame, extracting a piece of audio that is similar to the playing time of the first key frame, and performing feature extraction on the extracted audio to obtain an audio feature of the first key frame.
- Step 202 Acquire a short video of the target viewed by the user, and perform video fingerprint feature extraction on the target short video.
- each second key frame after extracting the image features of the second key frame, for each second key frame, extracting a piece of audio that is similar to the second key frame playing time, and performing the extracted audio. Feature extraction to obtain audio features of the second key frame.
- the image features and audio features of each of the second key frames are thus used as video fingerprint features of the target short video.
- Step 203 In the feature index library, query the first key frame of the image feature matching according to the image features of the plurality of second key frames in the target short video to obtain the target first key frame matched by each second key frame. .
- each key frame is compared with each second key frame in the feature index library to determine a target first key frame that each second key frame matches.
- the determined target first key frame is multiple, and may belong to different candidate long videos.
- Step 204 Determine a target long video from each candidate long video according to a playing time of each target first key frame belonging to the same candidate long video and a playing time of each second key frame in the target short video.
- the playing time of each target first key frame of the target long video matches the playing time of each second key frame in the target short video.
- the target short video includes a plurality of second key frames arranged in order according to the playing time
- the candidate long video includes a plurality of target first key frames arranged in order according to the playing time.
- two playing intervals can be calculated. If the candidate long video is the desired target long video, the playing interval should match the two second keys in the candidate long video.
- the playback interval between the two target first key frames of the frame is the same. It should be noted that the agreement here refers to the agreement within a certain error range.
- the playing time of the plurality of second key frames in the target short video is taken as the vertical axis Y
- the playing time of the plurality of target first key frames in the candidate long video As the horizontal axis X, the coordinate system XY is established.
- the playback time of the target first key frame that matches each other is taken as the x value
- the playback time of the second key frame is taken as the y value
- the (x, y) coordinate point is drawn in the coordinate system XY.
- each coordinate point is connected, and whether the candidate long video is the target long video is determined according to whether the connection between the coordinate points approaches a linear relationship whose slope is equal to 1. If the candidate long video is the desired target long video, the connection between the coordinate points should approach a linear relationship.
- step 206 the target long video is recommended to the user.
- the target long video captured by the target short video is identified from the candidate long video. And then recommend the target long video to the user.
- the method of recognizing the target long video intercepted by the target short video from the candidate long video according to the video fingerprint feature is recognized even if the title of the target short video does not carry any long video related information.
- the long-distance video captured by the user is taken out. At the same time, since the target long video is actively recommended to the user, the process of manually querying by the user is avoided, and the technical problem of recognizing the long video operation intercepted by the short video in the prior art is not enough.
- the desired target long video can be more accurately recognized, and the situation that the target long video cannot be recognized due to the short video capturing only a part of the frame image is avoided. .
- the present application also proposes a video recommendation apparatus.
- FIG. 6 is a schematic structural diagram of a video recommendation apparatus according to an embodiment of the present disclosure.
- the video recommendation device includes an acquisition module 61, an identification module 62, and a recommendation module 63.
- the obtaining module 61 is configured to acquire a short video of the target viewed by the user.
- the identification module 62 is configured to identify, according to the video fingerprint feature of the target short video and the video fingerprint feature of the candidate long video, from the candidate long video, the target long video intercepted by the short video.
- the recommendation module 63 is configured to recommend the target long video to the user.
- the recommendation module 63 is specifically configured to display prompt information of the target long video on a play page for playing the target short video, where the prompt information includes an identifier and a location of the target long video. At least one of a resource link of the target long video and an identifier of the long video set to which the target long video belongs.
- a hovering control is displayed on the play page; wherein the hovering control is used to display the target A long video prompt message and respond to the user's target action.
- a part of the display area is used to play the target short video in the play page, another part of the display area is used to display the prompt information in the play page.
- the recommendation module 63 is further configured to display, when the user performs a target operation on the prompt information of the target long video, to display the target long video. Play page to play the target long video.
- FIG. 7 is a schematic structural diagram of another video recommendation device according to an embodiment of the present application, as shown in FIG.
- the video recommendation device further includes: an establishing module 71.
- the establishing module 71 is configured to: before acquiring the feature index library, extract the first key frame according to the image content of the plurality of candidate long videos to obtain a plurality of first key frames of each candidate long video; and for each candidate long video Image feature extraction is performed according to each of the plurality of local regions in the first key frame to obtain image features of the first key frame; and each first key frame according to each of the plurality of candidate long videos Image features to build the feature index library.
- the identification module 62 includes an acquisition unit 621, an extraction unit 622, and a search unit 623.
- the obtaining unit 621 is configured to acquire a feature index library, where the feature index library includes video fingerprint features of the plurality of candidate long videos, wherein the video fingerprint feature includes image features and/or audio features.
- the extracting unit 622 is configured to extract a video fingerprint feature of the target short video for the target short video.
- the extracting unit 622 is specifically configured to: extract, according to the image content of the target short video, a plurality of second key frames of the target short video; and extract, for each second key frame of the target short video, The image feature of the second key frame serves as a video fingerprint feature of the target short video.
- the searching unit 623 is configured to search, according to the feature index library, a candidate long video whose video fingerprint feature matches the target short video as the target long video.
- the searching unit 623 is specifically configured to: in the feature index library, query the first key frame of the image feature matching according to image features of the plurality of second key frames in the target short video to obtain each second a target first key frame matched by the key frame; a play time of each target first key frame belonging to the same candidate long video, and a play time of each second key frame in the target short video, from each candidate long video Determining a target long video; playing time of each target first key frame of the target long video matches a playing time of each second key frame in the target short video.
- the target long video is captured from the candidate long video.
- the video which in turn recommends the target long video to the user.
- the method of recognizing the target long video intercepted by the target short video from the candidate long video according to the video fingerprint feature is recognized even if the title of the target short video does not carry any long video related information.
- the long-distance video captured by the user is taken out.
- the process of manually querying by the user is avoided, and the technical problem of recognizing the long video operation intercepted by the short video in the prior art is not enough.
- the present application further provides a computer device, including a memory, a processor, and a computer program stored on the memory and operable on the processor, when the processor executes the program, implementing the foregoing The video recommendation method described.
- the present application also proposes a non-transitory computer readable storage medium having stored thereon a computer program that, when executed by the processor, implements the video recommendation method as described above.
- the present application also proposes a computer program product that, when executed by an instruction processor in the computer program product, performs the video recommendation method as described above.
- FIG. 8 illustrates a block diagram of an exemplary computer device suitable for use in implementing embodiments of the present application.
- the computer device 12 shown in FIG. 8 is merely an example and should not impose any limitation on the function and scope of use of the embodiments of the present application.
- computer device 12 is embodied in the form of a general purpose computing device.
- Components of computer device 12 may include, but are not limited to, one or more processors or processing units 16, system memory 28, and bus 18 that connects different system components, including system memory 28 and processing unit 16.
- Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of a variety of bus structures.
- these architectures include, but are not limited to, an Industry Standard Architecture (hereinafter referred to as ISA) bus, a Micro Channel Architecture (MAC) bus, an enhanced ISA bus, and video electronics.
- ISA Industry Standard Architecture
- MAC Micro Channel Architecture
- VESA Video Electronics Standards Association
- PCI Peripheral Component Interconnection
- Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including both volatile and nonvolatile media, removable and non-removable media.
- Memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30 and/or cache memory 32.
- Computer device 12 may further include other removable/non-removable, volatile/non-volatile computer system storage media.
- storage system 34 may be used to read and write non-removable, non-volatile magnetic media (not shown in Figure 8, commonly referred to as "hard disk drives").
- a disk drive for reading and writing to a removable non-volatile disk such as a "floppy disk”
- a removable non-volatile disk for example, a compact disk read-only memory (Compact)
- each drive can be coupled to bus 18 via one or more data medium interfaces.
- Memory 28 can include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the various embodiments of the present application.
- a program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including but not limited to an operating system, one or more applications, other program modules, and program data. An implementation of the network environment may be included in each or some of these examples.
- Program module 42 typically performs the functions and/or methods of the embodiments described herein.
- Computer device 12 may also be in communication with one or more external devices 14 (eg, a keyboard, pointing device, display 24, etc.), and may also be in communication with one or more devices that enable a user to interact with the computer device 12, and/or Any device (eg, a network card, modem, etc.) that enables the computer device 12 to communicate with one or more other computing devices. This communication can take place via an input/output (I/O) interface 22.
- the computer device 12 can also pass through the network adapter 20 and one or more networks (for example, a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet. ) Communication. As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18.
- network adapter 20 communicates with other modules of computer device 12 via bus 18.
- the processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, for example, implementing the methods mentioned in the foregoing embodiments.
- first and second are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated.
- features defining “first” or “second” may include at least one of the features, either explicitly or implicitly.
- the meaning of "a plurality” is at least two, such as two, three, etc., unless specifically defined otherwise.
- a "computer-readable medium” can be any apparatus that can contain, store, communicate, propagate, or transport a program for use in an instruction execution system, apparatus, or device, or in conjunction with the instruction execution system, apparatus, or device.
- computer readable media include the following: electrical connections (electronic devices) having one or more wires, portable computer disk cartridges (magnetic devices), random access memory (RAM), Read only memory (ROM), erasable editable read only memory (EPROM or flash memory), fiber optic devices, and portable compact disk read only memory (CDROM).
- the computer readable medium may even be a paper or other suitable medium on which the program can be printed, as it may be optically scanned, for example by paper or other medium, followed by editing, interpretation or, if appropriate, other suitable The method is processed to obtain the program electronically and then stored in computer memory.
- portions of the application can be implemented in hardware, software, firmware, or a combination thereof.
- multiple steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system.
- a suitable instruction execution system For example, if implemented in hardware and in another embodiment, it can be implemented by any one or combination of the following techniques well known in the art: discrete with logic gates for implementing logic functions on data signals Logic circuits, application specific integrated circuits with suitable combinational logic gates, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.
- each functional unit in each embodiment of the present application may be integrated into one processing module, or each unit may exist physically separately, or two or more units may be integrated into one module.
- the above integrated modules can be implemented in the form of hardware or in the form of software functional modules.
- the integrated modules, if implemented in the form of software functional modules and sold or used as stand-alone products, may also be stored in a computer readable storage medium.
- the above mentioned storage medium may be a read only memory, a magnetic disk or an optical disk or the like. While the embodiments of the present application have been shown and described above, it is understood that the above-described embodiments are illustrative and are not to be construed as limiting the scope of the present application. The embodiments are subject to variations, modifications, substitutions and variations.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
本申请属于视频处理技术领域,提出一种视频推荐方法、装置、计算机设备和存储介质,通过获取用户观看的目标短视频之后,根据目标短视频的视频指纹特征与候选长视频的视频指纹特征,从候选长视频中,识别出目标短视频所截取自的目标长视频,进而向用户推荐目标长视频。由于采用了根据视频指纹特征,从候选长视频中,识别出目标短视频所截取自的目标长视频的方式,即使在目标短视频的标题未携带任何长视频相关信息的情况下,仍可以识别出所截取自的目标长视频,同时,由于向用户主动推荐目标长视频,避免了用户手动查询的过程,解决现有技术中识别短视频所截取自的长视频操作不够便捷的技术问题。
Description
相关申请的交叉引用
本申请要求北京百度网讯科技有限公司于2017年12月7日提交的、发明名称为“视频推荐方法、装置、计算机设备和存储介质”的、中国专利申请号“201711287361.9”的优先权。
本申请涉及视频处理技术领域,尤其涉及一种视频推荐方法、装置、计算机设备和存储介质。
相对播放时长较长的电影、电视剧、综艺等等长视频来说,短视频由于具有短小精炼的特点,便于用户随时观看。因此,在这种用户需求下,短视频技术得到了较快的发展。
在一些应用场景下,短视频是基于长视频剪辑得到的,用户在观看短视频之后,希望能够获知短视频所截取自的长视频。但在现有技术中,用户只能够通过短视频的标题手动查询相关的长视频,若短视频的标题没有任何长视频相关信息时,用户则无法找到相关的长视频。
发明内容
本申请旨在至少在一定程度上解决相关技术中的技术问题之一。
为此,本申请的第一个目的在于提出一种视频推荐方法,以向用户推荐短视频所截取自的目标长视频,避免了用户手动查找的过程。
本申请的第二个目的在于提出一种视频推荐装置。
本申请的第三个目的在于提出一种计算机设备。
本申请的第四个目的在于提出一种非临时性计算机可读存储介质。
本申请的第五个目的在于提出一种计算机程序产品。
为达上述目的,本申请第一方面实施例提出了一种视频推荐方法,包括:
获取用户观看的目标短视频;
根据所述目标短视频的视频指纹特征与候选长视频的视频指纹特征,从所述候选长视频中,识别出所述短视频所截取自的目标长视频;
向用户推荐所述目标长视频。
本申请实施例的视频推荐方法,通过获取用户观看的目标短视频之后,根据目标短视频 的视频指纹特征与候选长视频的视频指纹特征,从候选长视频中,识别出目标短视频所截取自的目标长视频,进而向用户推荐目标长视频。由于采用了根据视频指纹特征,从候选长视频中,识别出目标短视频所截取自的目标长视频的方式,即使在目标短视频的标题未携带任何长视频相关信息的情况下,仍可以识别出所截取自的目标长视频,同时,由于向用户主动推荐目标长视频,避免了用户手动查询的过程,解决现有技术中识别短视频所截取自的长视频操作不够便捷的技术问题。
为达上述目的,本申请第二方面实施例提出了一种视频推荐装置,包括:
获取模块,用于获取用户观看的目标短视频;
识别模块,用于根据所述目标短视频的视频指纹特征与候选长视频的视频指纹特征,从所述候选长视频中,识别出所述短视频所截取自的目标长视频;
推荐模块,用于向用户推荐所述目标长视频。
本申请实施例的视频推荐装置,通过获取用户观看的目标短视频之后,根据目标短视频的视频指纹特征与候选长视频的视频指纹特征,从候选长视频中,识别出目标短视频所截取自的目标长视频,进而向用户推荐目标长视频。由于采用了根据视频指纹特征,从候选长视频中,识别出目标短视频所截取自的目标长视频的方式,即使在目标短视频的标题未携带任何长视频相关信息的情况下,仍可以识别出所截取自的目标长视频,同时,由于向用户主动推荐目标长视频,避免了用户手动查询的过程,解决现有技术中识别短视频所截取自的长视频操作不够便捷的技术问题。
为达上述目的,本申请第三方面实施例提出了一种计算机设备,包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序,所述处理器执行所述程序时,实现如第一方面所述的视频推荐方法。
为了实现上述目的,本申请第四方面实施例提出了一种非临时性计算机可读存储介质,其上存储有计算机程序,该程序被处理器执行时实现如第一方面所述的视频推荐方法。
为了实现上述目的,本申请第五方面实施例提出了一种计算机程序产品,当所述计算机程序产品中的指令处理器执行时,执行第一方面所述的视频推荐方法。
本申请附加的方面和优点将在下面的描述中部分给出,部分将从下面的描述中变得明显,或通过本申请的实践了解到。
本申请上述的和/或附加的方面和优点从下面结合附图对实施例的描述中将变得明显和容易理解,其中:
图1为本申请实施例所提供的一种视频推荐方法的流程示意图;
图2A为视频播放相关页面示意图之一;
图2B为视频播放相关页面示意图之二;
图2C为视频播放相关页面示意图之三;
图2D为视频播放相关页面示意图之四;
图3为本申请实施例提供的另一种视频推荐方法的流程示意图;
图4为第一关键帧划分为多个局部区域的示意图;
图5为坐标系XY的示意图;
图6为本申请实施例提供的一种视频推荐装置的结构示意图;
图7为本申请实施例提供的另一种视频推荐装置的结构示意图;以及
图8示出了适于用来实现本申请实施方式的示例性计算机设备的框图。
下面详细描述本申请的实施例,所述实施例的示例在附图中示出,其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的,旨在用于解释本申请,而不能理解为对本申请的限制。
下面参考附图描述本申请实施例的视频推荐方法、装置、计算机设备和存储介质。
图1为本申请实施例所提供的一种视频推荐方法的流程示意图。
通过长视频截取出的短视频片段是一种非常有效的传播方式,能够使得影视剧等长视频以短视频形式进行传播。在传播过程中,有部分用户需要进一步了解观看的短视频来源于哪部长视频。
针对这一问题,本申请实施例提供了视频推荐方法,以别出用户观看的目标短视频所截取自的目标长视频,进而向用户推荐该目标长视频。
如图1所示,该视频推荐方法包括以下步骤:
步骤101,获取用户观看的目标短视频。
具体地,当探测到用户使用的浏览器或视频播放应用程序请求短视频资源时,获取用户观看的目标短视频的内容,这里的内容包括目标短视频的标识、图像和音频。
步骤102,根据目标短视频的视频指纹特征与候选长视频的视频指纹特征,从候选长视频中,识别出目标短视频所截取自的目标长视频。
具体地,执行本实施例方法的服务器已经预先获取到了多个候选长视频的视频指纹特征,从而可以根据目标短视频的视频指纹特征,查询视频指纹特征相互匹配的候选长视频,作为目标长视频。由于视频指纹特征用于描述视频的内容,当目标短视频截取自目标长视频时,两者的内容近似,从而视频指纹特征也应当是相互匹配的。本实施例中,根据视频指纹 特征识别出目标短视频所截取自的目标长视频,具有较高的准确度。
视频指纹特征包括图像特征和音频特征,是对视频提取关键帧之后,进行特征提取得到的,具体获取视频指纹特征的方式,将在后续实施例中进行详细介绍,本实施例中对此不再赘述。
步骤103,向用户推荐目标长视频。
具体地,在用于播放所述目标短视频的播放页面上,显示所述目标长视频的提示信息。
这里的提示信息,可以包括目标长视频的标识、目标长视频的资源链接和目标长视频所属长视频集合的标识中的至少一个。具体来说,目标长视频的标识具体可以为目标长视频的标题。目标长视频可能是电视剧的某一集,从而目标长视频所属长视频集合具体为该电视剧的标题。
例如:目标短视频截取自电视剧的某一集,在识别出目标短视频截取自电视剧A的第n集,提示信息可以显示“节选自《电视剧A》,点击查看完整剧集”,提示信息还可以进一步显示具体的集数,如“节选自《电视剧A》的第n集,点击查看完整剧集”。
由于提示信息携带有目标长视频的资源链接,当探测到用户对目标长视频的提示信息执行目标操作时,显示用于播放目标长视频的播放页面,以对所述目标长视频进行播放。目标操作具体可以为点击等用于触发跳转至目标长视频的播放页面的操作。
作为一种可能的实现方式,在播放页面上,若采用全屏模式对目标短视频进行播放,在所述播放页面上显示悬浮控件。其中,悬浮控件用于显示所述目标长视频的提示信息,并响应用户执行的目标操作。
作为另一种可能的实现方式,若在所述播放页面内采用一部分展示区域对所述目标短视频进行播放,也就是非全屏模式,则在所述播放页面中采用另一部分展示区域显示所述提示信息。
为了清楚说明本实施例的实现过程,下面将结合图2A至图2D的视频播放相关页面示意图,从用户操作的角度对视频推荐方法进行详细说明。
1)用户在如图2A所示的播放列表页面中选中列表中的第二个短视频,作为目标短视频。具体来说,用户可以通过点击第二个短视频缩略图,或者缩略图右侧的标题进行选中,进而从如图2A所示的播放列表页面跳转至如图2B所示的目标短视频的播放页面,对短视频进行播放。
2)如图2B的播放页面内,布局有用于播放目标短视频的展示区域,另外,在该展示区域下方,布局有另一展示区域,可以采用另一展示区域显示提示信息,另一展示区域可以位于用于播放目标短视频的展示区域的下方。另一展示区域内显示的提示信息携带有目标长视频的资源链接,当用户点击提示信息时,跳转至如图2D所示的目标长视频的播放页面,对 目标长视频进行播放。
3)如图2B所示的播放页面采用了非全屏播放的方式对目标短视频进行播放,当用户在如图2B所示的播放页面内通过全屏操作,得到如图2C所示的全屏播放模式下的播放页面时,可以在如图2C所示的页面中,以悬浮控件的方式,显示面板长视频的提示信息,并在用户点击悬浮控件时,跳转至如图2D所示的目标长视频的播放页面,对目标长视频进行播放。
本实施例中,通过获取用户观看的目标短视频之后,根据目标短视频的视频指纹特征与候选长视频的视频指纹特征,从候选长视频中,识别出目标短视频所截取自的目标长视频,进而向用户推荐目标长视频。由于采用了根据视频指纹特征,从候选长视频中,识别出目标短视频所截取自的目标长视频的方式,即使在目标短视频的标题未携带任何长视频相关信息的情况下,仍可以识别出所截取自的目标长视频,同时,由于向用户主动推荐目标长视频,避免了用户手动查询的过程,解决现有技术中识别短视频所截取自的长视频操作不够便捷的技术问题。
上一实施例侧重从前端实现上,说明对用户推荐目标长视频的过程,为了进一步地说明上一实施例,本实施例提供了另一种视频推荐方法,以重点说明如何实现从候选长视频中,识别出目标短视频所截取自的目标长视频的后台处理过程,图3为本申请实施例提供的另一种视频推荐方法的流程示意图。
如图3所示,该视频推荐方法可以包括以下步骤:
步骤201,建立特征索引库。
具体地,针对每一个候选长视频的每一个第一关键帧,根据第一关键帧内多个局部区域分别进行图像特征提取,以得到第一关键帧的图像特征;根据多个候选长视频的每一个第一关键帧的图像特征,建立所述特征索引库。
特征索引库中主要存储有每一个候选长视频中,各第一关键帧的图像特征。在具体实现上,目标短视频可能是从目标长视频中剪辑出完整帧画面,进而对这些完整帧画面进行视频合成得到的,还有可能是在剪辑出完整帧画面之后,取帧画面一部分,例如中央区域,以截掉该完整帧画面中不需要的画面,例如帧画面下方的字幕,帧画面四角位置的标志等等。
因此,在这种情况下,为了提高识别准确度,可以将每一个第一关键帧划分为多个局部区域,这里局部区域的大小可以根据执行本实施例方法的服务器处理能力,处理能力强,则每一第一关键帧划分的局部区域可以较多,包含的像素数可以相应较少。
如图4所示,为第一关键帧划分为多个局部区域的示意图,如图4所示,每一个局部区域之间可以是不具有重合部分的,在另一种可能的实现方式中,相邻局部区域之间可以是具有重合部分的,本实施例中对此不作限定。
将第一关键帧划分的每一个局部区域进行特征提取,将各个局部区域的图像特征,作为 该第一关键帧的图像特征。
特征索引库中不仅存储有第一关键帧的图像特征,还存储有对应的音频特征。作为一种可能的实现方式,针对每一个第一关键帧,提取与该第一关键帧播放时刻近似的一段音频,对提取到的音频进行特征提取,得到第一关键帧的音频特征。
至此,完成特征索引库的建立过程,建立完成的特征索引库中,针对每一个候选长视频,对应存储有各第一关键帧的图像特征和音频特征。
步骤202,获取用户观看的目标短视频,并对目标短视频进行视频指纹特征提取。
根据所述目标短视频的图像内容,提取所述目标短视频的多个第二关键帧针对所述目标短视频的每一个第二关键帧,提取所述第二关键帧的图像特征作为所述目标短视频的视频指纹特征。
作为一种可能的实现方式,还可以在提取到第二关键帧的图像特征之后,针对每一个第二关键帧,提取与该第二关键帧播放时刻近似的一段音频,对提取到的音频进行特征提取,得到第二关键帧的音频特征。从而将各第二关键帧的图像特征和音频特征作为所述目标短视频的视频指纹特征。
步骤203,在特征索引库中,根据目标短视频中多个第二关键帧的图像特征,查询图像特征匹配的第一关键帧,以得到每一个第二关键帧所匹配的目标第一关键帧。
由于在前述步骤中,对第一关键帧的多个局部区域进行图像特征提取,得到第一关键帧的图像特征。因此,在本步骤中,将第二关键帧与第一关键帧匹配时,若第一关键帧的多个局部区域中,图像特征与第二关键帧匹配的局部区域个数达到阈值个数,才确定该第二关键帧与该第一关键帧匹配。采用前述方式,将每一个关键帧与特征索引库中的各第二关键帧比对,从而确定出每一个第二关键帧所匹配的目标第一关键帧。这里的确定出的目标第一关键帧为多个,可能分属于不同的候选长视频中。
步骤204,根据属于同一候选长视频的各目标第一关键帧的播放时刻,以及所述目标短视频中各第二关键帧的播放时刻,从各候选长视频中确定目标长视频。
其中,目标长视频的各目标第一关键帧的播放时刻,与所述目标短视频中各第二关键帧的播放时刻匹配。
作为一种可能的实现方式,目标短视频中包括依据播放时刻顺序排列的多个第二关键帧,候选长视频中包括依据播放时刻顺序排列的多个目标第一关键帧。根据两个第二关键帧的播放时刻,可以计算出两个的播放间隔,若候选长视频为所需的目标长视频,该播放间隔,应当与候选长视频中对应匹配这两个第二关键帧的两目标第一关键帧之间的播放间隔一致。需要说明的而是,这里的一致是指在一定误差范围内的一致。
作为另一种可能的实现方式,针对每一个候选长视频,将目标短视频中多个第二关键帧 的播放时刻作为纵轴Y,该候选长视频中多个目标第一关键帧的播放时刻作为横轴X,建立坐标系XY。将相互匹配的目标第一关键帧的播放时刻作为x值,第二关键帧的播放时刻作为y值,在坐标系XY中绘制(x,y)坐标点。如图5所示,连接各坐标点,根据各坐标点之间的连线是否趋近于斜率等于1的线性关系,确定候选长视频是否为目标长视频。若候选长视频为所需的目标长视频,各坐标点之间的连线应当趋近于线性关系。
步骤206,向用户推荐目标长视频。
具体推荐方式参见前述实施例中的相关描述,本实施例中对此不再赘述。
本实施例中,通过获取用户观看的目标短视频之后,根据目标短视频的视频指纹特征与候选长视频的视频指纹特征,从候选长视频中,识别出目标短视频所截取自的目标长视频,进而向用户推荐目标长视频。由于采用了根据视频指纹特征,从候选长视频中,识别出目标短视频所截取自的目标长视频的方式,即使在目标短视频的标题未携带任何长视频相关信息的情况下,仍可以识别出所截取自的目标长视频,同时,由于向用户主动推荐目标长视频,避免了用户手动查询的过程,解决现有技术中识别短视频所截取自的长视频操作不够便捷的技术问题。同时,由于根据第一关键帧的局部区域进行特征提取,从而可以更准确地识别出所需的目标长视频,避免了由于短视频仅截取一部分帧画面导致的无法识别出目标长视频的情况出现。
为了实现上述实施例,本申请还提出一种视频推荐装置。
图6为本申请实施例提供的一种视频推荐装置的结构示意图。
如图6所示,该视频推荐装置包括:获取模块61、识别模块62和推荐模块63。
获取模块61,用于获取用户观看的目标短视频。
识别模块62,用于根据所述目标短视频的视频指纹特征与候选长视频的视频指纹特征,从所述候选长视频中,识别出所述短视频所截取自的目标长视频。
推荐模块63,用于向用户推荐所述目标长视频。
可选地,推荐模块63具体用于在用于播放所述目标短视频的播放页面上,显示所述目标长视频的提示信息;其中,所述提示信息包括所述目标长视频的标识、所述目标长视频的资源链接和所述目标长视频所属长视频集合的标识中的至少一个。
作为一种可能的实现方式,在所述播放页面上,若采用全屏模式对所述目标短视频进行播放,在所述播放页面上显示悬浮控件;其中,所述悬浮控件用于显示所述目标长视频的提示信息,并响应用户执行的目标操作。
作为另一种可能的实现方式,若在所述播放页面内采用一部分展示区域对所述目标短视频进行播放,在所述播放页面中采用另一部分展示区域显示所述提示信息。
进一步地,在本申请实施例的一种可能的实现方式中,推荐模块63还用于当探测到用 户对所述目标长视频的提示信息执行目标操作时,显示用于播放所述目标长视频的播放页面,以对所述目标长视频进行播放。
需要说明的是,前述对方法实施例的解释说明也适用于该实施例的装置,此处不再赘述。
基于上述实施例,本申请实施例还提供了一种视频推荐装置的可能的实现方式,图7为本申请实施例提供的另一种视频推荐装置的结构示意图,如图7所示,在上一实施例的基础上,视频推荐装置还包括:建立模块71。
建立模块71,用于获取特征索引库之前,根据多个候选长视频的图像内容,提取第一关键帧,以得到每一个候选长视频的多个第一关键帧;针对每一个候选长视频的每一个第一关键帧,根据所述第一关键帧内多个局部区域分别进行图像特征提取,以得到所述第一关键帧的图像特征;根据多个候选长视频的每一个第一关键帧的图像特征,建立所述特征索引库。
识别模块62,包括:获取单元621、提取单元622和搜索单元623。
获取单元621,用于获取特征索引库,所述特征索引库包括多个候选长视频的视频指纹特征;其中,所述视频指纹特征包括图像特征和/或音频特征。
提取单元622,用于对所述目标短视频提取所述目标短视频的视频指纹特征。
具体地,提取单元622具体用于根据所述目标短视频的图像内容,提取所述目标短视频的多个第二关键帧;针对所述目标短视频的每一个第二关键帧,提取所述第二关键帧的图像特征作为所述目标短视频的视频指纹特征。
搜索单元623,用于根据所述特征索引库,搜索视频指纹特征与所述目标短视频匹配的候选长视频,作为所述目标长视频。
具体地,搜索单元623具体用于在所述特征索引库中,根据所述目标短视频中多个第二关键帧的图像特征,查询图像特征匹配的第一关键帧,以得到每一个第二关键帧所匹配的目标第一关键帧;根据属于同一候选长视频的各目标第一关键帧的播放时刻,以及所述目标短视频中各第二关键帧的播放时刻,从各候选长视频中确定目标长视频;所述目标长视频的各目标第一关键帧的播放时刻与所述目标短视频中各第二关键帧的播放时刻匹配。
本申请实施例中,通过获取用户观看的目标短视频之后,根据目标短视频的视频指纹特征与候选长视频的视频指纹特征,从候选长视频中,识别出目标短视频所截取自的目标长视频,进而向用户推荐目标长视频。由于采用了根据视频指纹特征,从候选长视频中,识别出目标短视频所截取自的目标长视频的方式,即使在目标短视频的标题未携带任何长视频相关信息的情况下,仍可以识别出所截取自的目标长视频,同时,由于向用户主动推荐目标长视频,避免了用户手动查询的过程,解决现有技术中识别短视频所截取自的长视频操作不够便捷的技术问题。
为了实现上述实施例,本申请还提出一种计算机设备,包括存储器、处理器及存储在存 储器上并可在处理器上运行的计算机程序,所述处理器执行所述程序时,实现如前所述的视频推荐方法。
为了实现上述实施例,本申请还提出一种非临时性计算机可读存储介质,其上存储有计算机程序,该程序被处理器执行时实现如前所述的视频推荐方法。
为了实现上述实施例,本申请还提出一种计算机程序产品,当所述计算机程序产品中的指令处理器执行时,执行如前所述的视频推荐方法。
图8示出了适于用来实现本申请实施方式的示例性计算机设备的框图。图8显示的计算机设备12仅仅是一个示例,不应对本申请实施例的功能和使用范围带来任何限制。
如图8所示,计算机设备12以通用计算设备的形式表现。计算机设备12的组件可以包括但不限于:一个或者多个处理器或者处理单元16,系统存储器28,连接不同系统组件(包括系统存储器28和处理单元16)的总线18。
总线18表示几类总线结构中的一种或多种,包括存储器总线或者存储器控制器,外围总线,图形加速端口,处理器或者使用多种总线结构中的任意总线结构的局域总线。举例来说,这些体系结构包括但不限于工业标准体系结构(Industry Standard Architecture;以下简称:ISA)总线,微通道体系结构(Micro Channel Architecture;以下简称:MAC)总线,增强型ISA总线、视频电子标准协会(Video Electronics Standards Association;以下简称:VESA)局域总线以及外围组件互连(Peripheral Component Interconnection;以下简称:PCI)总线。
计算机设备12典型地包括多种计算机系统可读介质。这些介质可以是任何能够被计算机设备12访问的可用介质,包括易失性和非易失性介质,可移动的和不可移动的介质。
存储器28可以包括易失性存储器形式的计算机系统可读介质,例如随机存取存储器(Random Access Memory;以下简称:RAM)30和/或高速缓存存储器32。计算机设备12可以进一步包括其它可移动/不可移动的、易失性/非易失性计算机系统存储介质。仅作为举例,存储系统34可以用于读写不可移动的、非易失性磁介质(图8未显示,通常称为“硬盘驱动器”)。尽管图8中未示出,可以提供用于对可移动非易失性磁盘(例如“软盘”)读写的磁盘驱动器,以及对可移动非易失性光盘(例如:光盘只读存储器(Compact Disc Read Only Memory;以下简称:CD-ROM)、数字多功能只读光盘(Digital Video Disc Read Only Memory;以下简称:DVD-ROM)或者其它光介质)读写的光盘驱动器。在这些情况下,每个驱动器可以通过一个或者多个数据介质接口与总线18相连。存储器28可以包括至少一个程序产品,该程序产品具有一组(例如至少一个)程序模块,这些程序模块被配置以执行本申请各实施例的功能。
具有一组(至少一个)程序模块42的程序/实用工具40,可以存储在例如存储器28中, 这样的程序模块42包括但不限于操作系统、一个或者多个应用程序、其它程序模块以及程序数据,这些示例中的每一个或某种组合中可能包括网络环境的实现。程序模块42通常执行本申请所描述的实施例中的功能和/或方法。
计算机设备12也可以与一个或多个外部设备14(例如键盘、指向设备、显示器24等)通信,还可与一个或者多个使得用户能与该计算机设备12交互的设备通信,和/或与使得该计算机设备12能与一个或多个其它计算设备进行通信的任何设备(例如网卡,调制解调器等等)通信。这种通信可以通过输入/输出(I/O)接口22进行。并且,计算机设备12还可以通过网络适配器20与一个或者多个网络(例如局域网(Local Area Network;以下简称:LAN),广域网(Wide Area Network;以下简称:WAN)和/或公共网络,例如因特网)通信。如图所示,网络适配器20通过总线18与计算机设备12的其它模块通信。应当明白,尽管图中未示出,可以结合计算机设备12使用其它硬件和/或软件模块,包括但不限于:微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、RAID系统、磁带驱动器以及数据备份存储系统等。
处理单元16通过运行存储在系统存储器28中的程序,从而执行各种功能应用以及数据处理,例如实现前述实施例中提及的方法。
在本说明书的描述中,参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本申请的至少一个实施例或示例中。在本说明书中,对上述术语的示意性表述不必须针对的是相同的实施例或示例。而且,描述的具体特征、结构、材料或者特点可以在任一个或多个实施例或示例中以合适的方式结合。此外,在不相互矛盾的情况下,本领域的技术人员可以将本说明书中描述的不同实施例或示例以及不同实施例或示例的特征进行结合和组合。
此外,术语“第一”、“第二”仅用于描述目的,而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此,限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。在本申请的描述中,“多个”的含义是至少两个,例如两个,三个等,除非另有明确具体的限定。
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为,表示包括一个或更多个用于实现定制逻辑功能或过程的步骤的可执行指令的代码的模块、片段或部分,并且本申请的优选实施方式的范围包括另外的实现,其中可以不按所示出或讨论的顺序,包括根据所涉及的功能按基本同时的方式或按相反的顺序,来执行功能,这应被本申请的实施例所属技术领域的技术人员所理解。
在流程图中表示或在此以其他方式描述的逻辑和/或步骤,例如,可以被认为是用于实 现逻辑功能的可执行指令的定序列表,可以具体实现在任何计算机可读介质中,以供指令执行系统、装置或设备(如基于计算机的系统、包括处理器的系统或其他可以从指令执行系统、装置或设备取指令并执行指令的系统)使用,或结合这些指令执行系统、装置或设备而使用。就本说明书而言,"计算机可读介质"可以是任何可以包含、存储、通信、传播或传输程序以供指令执行系统、装置或设备或结合这些指令执行系统、装置或设备而使用的装置。计算机可读介质的更具体的示例(非穷尽性列表)包括以下:具有一个或多个布线的电连接部(电子装置),便携式计算机盘盒(磁装置),随机存取存储器(RAM),只读存储器(ROM),可擦除可编辑只读存储器(EPROM或闪速存储器),光纤装置,以及便携式光盘只读存储器(CDROM)。另外,计算机可读介质甚至可以是可在其上打印所述程序的纸或其他合适的介质,因为可以例如通过对纸或其他介质进行光学扫描,接着进行编辑、解译或必要时以其他合适方式进行处理来以电子方式获得所述程序,然后将其存储在计算机存储器中。
应当理解,本申请的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中,多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。如,如果用硬件来实现和在另一实施方式中一样,可用本领域公知的下列技术中的任一项或他们的组合来实现:具有用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路,具有合适的组合逻辑门电路的专用集成电路,可编程门阵列(PGA),现场可编程门阵列(FPGA)等。
本技术领域的普通技术人员可以理解实现上述实施例方法携带的全部或部分步骤是可以通过程序来指令相关的硬件完成,所述的程序可以存储于一种计算机可读存储介质中,该程序在执行时,包括方法实施例的步骤之一或其组合。
此外,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模块中,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模块中。上述集成的模块既可以采用硬件的形式实现,也可以采用软件功能模块的形式实现。所述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时,也可以存储在一个计算机可读取存储介质中。
上述提到的存储介质可以是只读存储器,磁盘或光盘等。尽管上面已经示出和描述了本申请的实施例,可以理解的是,上述实施例是示例性的,不能理解为对本申请的限制,本领域的普通技术人员在本申请的范围内可以对上述实施例进行变化、修改、替换和变型。
Claims (19)
- 一种视频推荐方法,其特征在于,包括以下步骤:获取用户观看的目标短视频;根据所述目标短视频的视频指纹特征与候选长视频的视频指纹特征,从所述候选长视频中,识别出所述目标短视频所截取自的目标长视频;向用户推荐所述目标长视频。
- 根据权利要求1所述的视频推荐方法,其特征在于,所述向用户推荐所述目标长视频,包括:在用于播放所述目标短视频的播放页面上,显示所述目标长视频的提示信息;其中,所述提示信息包括所述目标长视频的标识、所述目标长视频的资源链接和所述目标长视频所属长视频集合的标识中的至少一个。
- 根据权利要求2所述的视频推荐方法,其特征在于,所述显示所述目标长视频的提示信息之后,还包括:当探测到用户对所述目标长视频的提示信息执行目标操作时,显示用于播放所述目标长视频的播放页面,以对所述目标长视频进行播放。
- 根据权利要求2或3所述的视频推荐方法,其特征在于,所述在用于播放所述目标短视频的播放页面上,显示所述目标长视频的提示信息,包括:在所述播放页面上,若采用全屏模式对所述目标短视频进行播放,在所述播放页面上显示悬浮控件;其中,所述悬浮控件用于显示所述目标长视频的提示信息,并响应用户执行的目标操作;若在所述播放页面内采用一部分展示区域对所述目标短视频进行播放,在所述播放页面中采用另一部分展示区域显示所述提示信息。
- 根据权利要求1-4任一项所述的视频推荐方法,其特征在于,所述根据所述目标短视频的视频指纹特征与候选长视频的视频指纹特征,从所述候选长视频中,识别出所述短视频所截取自的目标长视频,包括:获取特征索引库,所述特征索引库包括多个候选长视频的视频指纹特征;其中,所述视频指纹特征包括图像特征和/或音频特征;对所述目标短视频提取所述目标短视频的视频指纹特征;根据所述特征索引库,搜索视频指纹特征与所述目标短视频匹配的候选长视频,作为所述目标长视频。
- 根据权利要求5所述的视频推荐方法,其特征在于,所述获取特征索引库之前,还包括:根据多个候选长视频的图像内容,提取第一关键帧,以得到每一个候选长视频的多个第一关键帧;针对每一个候选长视频的每一个第一关键帧,根据所述第一关键帧内多个局部区域分别进行图像特征提取,以得到所述第一关键帧的图像特征;根据多个候选长视频的每一个第一关键帧的图像特征,建立所述特征索引库。
- 根据权利要求6所述的视频推荐方法,其特征在于,所述对目标短视频提取所述目标短视频的视频指纹特征,包括:根据所述目标短视频的图像内容,提取所述目标短视频的多个第二关键帧;针对所述目标短视频的每一个第二关键帧,提取所述第二关键帧的图像特征作为所述目标短视频的视频指纹特征。
- 根据权利要求7所述的视频推荐方法,其特征在于,所述根据所述特征索引库,搜索视频指纹特征与所述目标短视频匹配的候选长视频,作为所述目标长视频,包括:在所述特征索引库中,根据所述目标短视频中多个第二关键帧的图像特征,查询图像特征匹配的第一关键帧,以得到每一个第二关键帧所匹配的目标第一关键帧;根据属于同一候选长视频的各目标第一关键帧的播放时刻,以及所述目标短视频中各第二关键帧的播放时刻,从各候选长视频中确定目标长视频;所述目标长视频的各目标第一关键帧的播放时刻与所述目标短视频中各第二关键帧的播放时刻匹配。
- 一种视频推荐装置,其特征在于,包括:获取模块,用于获取用户观看的目标短视频;识别模块,用于根据所述目标短视频的视频指纹特征与候选长视频的视频指纹特征,从所述候选长视频中,识别出所述短视频所截取自的目标长视频;推荐模块,用于向用户推荐所述目标长视频。
- 根据权利要求9所述的视频推荐装置,其特征在于,所述推荐模块,具体用于:在用于播放所述目标短视频的播放页面上,显示所述目标长视频的提示信息;其中,所述提示信息包括所述目标长视频的标识、所述目标长视频的资源链接和所述目标长视频所属长视频集合的标识中的至少一个。
- 根据权利要求10所述的视频推荐装置,其特征在于,所述推荐模块,还用于:当探测到用户对所述目标长视频的提示信息执行目标操作时,显示用于播放所述目标长视频的播放页面,以对所述目标长视频进行播放。
- 根据权利要求10或11所述的视频推荐装置,其特征在于,所述推荐模块,具体还用于:在所述播放页面上,若采用全屏模式对所述目标短视频进行播放,在所述播放页面上显 示悬浮控件;其中,所述悬浮控件用于显示所述目标长视频的提示信息,并响应用户执行的目标操作;若在所述播放页面内采用一部分展示区域对所述目标短视频进行播放,在所述播放页面中采用另一部分展示区域显示所述提示信息。
- 根据权利要求9-12任一项所述的视频推荐装置,其特征在于,所述识别模块,包括:获取单元,用于获取特征索引库,所述特征索引库包括多个候选长视频的视频指纹特征;其中,所述视频指纹特征包括图像特征和/或音频特征;提取单元,用于对所述目标短视频提取所述目标短视频的视频指纹特征;搜索单元,用于根据所述特征索引库,搜索视频指纹特征与所述目标短视频匹配的候选长视频,作为所述目标长视频。
- 根据权利要求13所述的视频推荐装置,其特征在于,所述装置,还包括建立模块,用于:根据多个候选长视频的图像内容,提取第一关键帧,以得到每一个候选长视频的多个第一关键帧;针对每一个候选长视频的每一个第一关键帧,根据所述第一关键帧内多个局部区域分别进行图像特征提取,以得到所述第一关键帧的图像特征;根据多个候选长视频的每一个第一关键帧的图像特征,建立所述特征索引库。
- 根据权利要求14所述的视频推荐装置,其特征在于,所述提取单元,具体用于:根据所述目标短视频的图像内容,提取所述目标短视频的多个第二关键帧;针对所述目标短视频的每一个第二关键帧,提取所述第二关键帧的图像特征作为所述目标短视频的视频指纹特征。
- 根据权利要求15所述的视频推荐装置,其特征在于,所述搜索单元,具体用于:在所述特征索引库中,根据所述目标短视频中多个第二关键帧的图像特征,查询图像特征匹配的第一关键帧,以得到每一个第二关键帧所匹配的目标第一关键帧;根据属于同一候选长视频的各目标第一关键帧的播放时刻,以及所述目标短视频中各第二关键帧的播放时刻,从各候选长视频中确定目标长视频;所述目标长视频的各目标第一关键帧的播放时刻与所述目标短视频中各第二关键帧的播放时刻匹配。
- 一种计算机设备,其特征在于,包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序,所述处理器执行所述程序时,实现如权利要求1-8中任一所述的视频推荐方法。
- 一种非临时性计算机可读存储介质,其上存储有计算机程序,其特征在于,该程序 被处理器执行时实现如权利要求1-8中任一所述的视频推荐方法。
- 一种计算机程序产品,其特征在于,当所述计算机程序产品中的指令由处理器执行时,执行如权利要求1-8中任一所述的视频推荐方法。
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2020519269A JP2020536455A (ja) | 2017-12-07 | 2018-07-18 | ビデオ推奨方法、ビデオ推奨装置、コンピュータ機器及び記憶媒体 |
| US16/622,876 US20200322684A1 (en) | 2017-12-07 | 2018-07-18 | Video recommendation method and apparatus |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711287361.9 | 2017-12-07 | ||
| CN201711287361.9A CN108024145B (zh) | 2017-12-07 | 2017-12-07 | 视频推荐方法、装置、计算机设备和存储介质 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2019109643A1 true WO2019109643A1 (zh) | 2019-06-13 |
Family
ID=62078906
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2018/096177 Ceased WO2019109643A1 (zh) | 2017-12-07 | 2018-07-18 | 视频推荐方法、装置、计算机设备和存储介质 |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20200322684A1 (zh) |
| JP (1) | JP2020536455A (zh) |
| CN (1) | CN108024145B (zh) |
| WO (1) | WO2019109643A1 (zh) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111447239A (zh) * | 2020-04-13 | 2020-07-24 | 北京字节跳动网络技术有限公司 | 视频流播放控制方法、设备及存储介质 |
| CN112182290A (zh) * | 2019-07-05 | 2021-01-05 | 北京字节跳动网络技术有限公司 | 一种信息处理方法、装置和电子设备 |
| CN112565838A (zh) * | 2020-11-12 | 2021-03-26 | 深圳市易平方网络科技有限公司 | 基于电视的开机处理方法、装置、终端及介质 |
| CN113010703A (zh) * | 2021-03-22 | 2021-06-22 | 腾讯科技(深圳)有限公司 | 一种信息推荐方法、装置、电子设备和存储介质 |
| CN113194351A (zh) * | 2021-02-24 | 2021-07-30 | 北京字跳网络技术有限公司 | 一种视频展示方法、装置、电子设备及存储介质 |
| CN114401435A (zh) * | 2021-12-29 | 2022-04-26 | 阿里巴巴(中国)有限公司 | 短视频的生成方法、装置、电子设备及可读存储介质 |
| CN115237314A (zh) * | 2022-04-18 | 2022-10-25 | 网易(杭州)网络有限公司 | 信息推荐方法、装置和电子设备 |
| CN115348460A (zh) * | 2021-05-13 | 2022-11-15 | 北京字节跳动网络技术有限公司 | 视频的预加载方法、装置、设备及存储介质 |
Families Citing this family (53)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108024145B (zh) * | 2017-12-07 | 2020-12-11 | 北京百度网讯科技有限公司 | 视频推荐方法、装置、计算机设备和存储介质 |
| CN108989856B (zh) * | 2018-06-19 | 2021-05-18 | 康佳集团股份有限公司 | 基于短视频获取正片关联数据的处理方法、终端及介质 |
| CN110691281B (zh) | 2018-07-04 | 2022-04-01 | 北京字节跳动网络技术有限公司 | 视频播放处理方法、终端设备、服务器及存储介质 |
| CN110418147A (zh) * | 2018-10-11 | 2019-11-05 | 彩云之端文化传媒(北京)有限公司 | 一种短视频引导长视频的跨屏收视方法 |
| CN109389088B (zh) * | 2018-10-12 | 2022-05-24 | 腾讯科技(深圳)有限公司 | 视频识别方法、装置、机器设备以及计算机可读存储介质 |
| CN111246254A (zh) * | 2018-11-28 | 2020-06-05 | 北京字节跳动网络技术有限公司 | 一种视频推荐方法、装置,服务器、终端设备及存储介质 |
| CN110162664B (zh) * | 2018-12-17 | 2021-05-25 | 腾讯科技(深圳)有限公司 | 视频推荐方法、装置、计算机设备及存储介质 |
| CN109982106B (zh) * | 2019-04-29 | 2021-11-26 | 百度在线网络技术(北京)有限公司 | 一种视频推荐方法、服务器、客户端及电子设备 |
| CN110290419B (zh) * | 2019-06-25 | 2021-11-26 | 北京奇艺世纪科技有限公司 | 视频播放方法、装置及电子设备 |
| CN110278449B (zh) * | 2019-06-26 | 2022-06-10 | 腾讯科技(深圳)有限公司 | 一种视频检测方法、装置、设备及介质 |
| CN110213661A (zh) * | 2019-06-26 | 2019-09-06 | 深圳市酷开网络科技有限公司 | 全视频化的控制方法、智能电视及计算机可读存储介质 |
| CN112911378B (zh) * | 2019-12-03 | 2024-09-24 | 西安光启智能技术有限公司 | 一种视频帧的查询方法 |
| CN110958470A (zh) * | 2019-12-09 | 2020-04-03 | 北京字节跳动网络技术有限公司 | 一种多媒体内容处理方法、装置、介质和电子设备 |
| CN111428087B (zh) * | 2020-03-20 | 2022-10-25 | 腾讯科技(深圳)有限公司 | 视频截取方法、装置、计算机设备和存储介质 |
| CN111767814A (zh) * | 2020-06-19 | 2020-10-13 | 北京奇艺世纪科技有限公司 | 一种视频确定方法及装置 |
| CN111970560B (zh) * | 2020-07-09 | 2022-07-22 | 北京百度网讯科技有限公司 | 视频获取方法、装置、电子设备及存储介质 |
| WO2022015464A1 (en) * | 2020-07-16 | 2022-01-20 | Sony Interactive Entertainment Inc. | Influencer tools for stream curation based on follower information |
| CN111860367B (zh) * | 2020-07-24 | 2024-12-27 | 上海连尚网络科技有限公司 | 视频重复性识别方法、电子设备及计算机可读存储介质 |
| CN111966909B (zh) * | 2020-08-26 | 2023-07-21 | 腾讯科技(深圳)有限公司 | 视频推荐方法、装置、电子设备及计算机可读存储介质 |
| CN114154012B (zh) * | 2020-09-07 | 2025-08-05 | 抖音视界有限公司 | 一种视频推荐方法、装置、电子设备和存储介质 |
| CN112153470B (zh) * | 2020-09-11 | 2022-04-08 | 腾讯科技(深圳)有限公司 | 一种视频播放方法、装置、计算机设备和存储介质 |
| CN113395584B (zh) * | 2020-10-10 | 2024-03-22 | 腾讯科技(深圳)有限公司 | 一种视频数据处理方法、装置、设备以及介质 |
| CN112203108A (zh) * | 2020-10-12 | 2021-01-08 | 广州欢网科技有限责任公司 | 根据短视频流识别切换成直播视频流的方法及设备 |
| CN112235625A (zh) * | 2020-10-14 | 2021-01-15 | 广州欢网科技有限责任公司 | 电视端的短视频正片溯源方法、系统及电视终端 |
| CN112565825B (zh) * | 2020-12-02 | 2022-05-13 | 腾讯科技(深圳)有限公司 | 一种视频数据处理方法、装置、设备以及介质 |
| CN112612918A (zh) * | 2020-12-16 | 2021-04-06 | 北京字节跳动网络技术有限公司 | 一种视频资源的映射方法、装置、设备及介质 |
| CN112612435A (zh) * | 2020-12-16 | 2021-04-06 | 北京字节跳动网络技术有限公司 | 信息处理方法、装置、设备及存储介质 |
| CN112632323A (zh) * | 2020-12-16 | 2021-04-09 | 北京字节跳动网络技术有限公司 | 一种视频播放方法、装置、设备及介质 |
| CN112612919A (zh) * | 2020-12-16 | 2021-04-06 | 北京字节跳动网络技术有限公司 | 一种视频资源的关联方法、装置、设备及介质 |
| CN112637668B (zh) * | 2020-12-16 | 2023-02-28 | 北京字节跳动网络技术有限公司 | 一种视频播放方法、装置、设备及介质 |
| CN113065008A (zh) * | 2021-03-23 | 2021-07-02 | 北京达佳互联信息技术有限公司 | 信息推荐方法、装置、电子设备及存储介质 |
| CN115278326B (zh) * | 2021-04-29 | 2025-04-25 | 腾讯科技(深圳)有限公司 | 视频展示方法、装置、计算机可读介质及电子设备 |
| CN113515696A (zh) * | 2021-05-17 | 2021-10-19 | 上海众源网络有限公司 | 推荐方法、装置、电子设备及存储介质 |
| CN113468374A (zh) * | 2021-05-31 | 2021-10-01 | 北京达佳互联信息技术有限公司 | 目标展示方法、装置、电子设备及存储介质 |
| CN113438522A (zh) * | 2021-06-24 | 2021-09-24 | 广州欢网科技有限责任公司 | 一种电视端长视频推荐方法及系统 |
| CN113676764B (zh) * | 2021-08-04 | 2023-12-05 | 深圳康佳电子科技有限公司 | 一种屏幕分屏显示方法、装置及存储介质 |
| CN113608651A (zh) * | 2021-08-11 | 2021-11-05 | 北京字跳网络技术有限公司 | 数据交互方法、装置、设备及存储介质 |
| CN115705705B (zh) * | 2021-08-12 | 2026-01-16 | 腾讯科技(北京)有限公司 | 基于机器学习的视频识别方法、装置、服务器和存储介质 |
| CN113688260B (zh) * | 2021-08-31 | 2025-02-14 | 维沃移动通信有限公司 | 视频推荐方法和装置 |
| CN113825007B (zh) * | 2021-09-27 | 2023-05-09 | 海信视像科技股份有限公司 | 视频播放方法、装置及显示设备 |
| CN113963674B (zh) * | 2021-09-30 | 2025-07-04 | 北京百度网讯科技有限公司 | 作品生成的方法、装置、电子设备及存储介质 |
| CN114286198B (zh) * | 2021-12-30 | 2023-11-10 | 北京爱奇艺科技有限公司 | 一种视频关联方法、装置、电子设备和存储介质 |
| CN114786062A (zh) * | 2022-03-07 | 2022-07-22 | 维沃移动通信有限公司 | 信息推荐方法、装置和电子设备 |
| CN114579801B (zh) * | 2022-04-28 | 2022-08-12 | 深圳市华曦达科技股份有限公司 | 一种基于天鹰优化算法的长视频推荐方法 |
| US12149788B2 (en) * | 2022-05-18 | 2024-11-19 | Lemon Inc. | Automatic identification of video series |
| CN115080792B (zh) * | 2022-05-19 | 2025-02-11 | 北京爱奇艺科技有限公司 | 一种视频关联方法、装置、电子设备及存储介质 |
| CN115052196B (zh) * | 2022-05-23 | 2025-02-11 | 北京达佳互联信息技术有限公司 | 一种视频处理方法及相关设备 |
| CN115086700B (zh) * | 2022-06-15 | 2024-10-11 | 北京有竹居网络技术有限公司 | 推送处理方法、装置、设备及介质 |
| CN114996505A (zh) * | 2022-06-15 | 2022-09-02 | 湖南快乐阳光互动娱乐传媒有限公司 | 一种视频数据处理方法及装置、电子设备、存储介质 |
| CN115811637A (zh) * | 2022-11-29 | 2023-03-17 | 北京字跳网络技术有限公司 | 一种基于视频的交互方法、装置、设备及存储介质 |
| CN116049486B (zh) * | 2023-01-31 | 2026-04-14 | 百度(中国)有限公司 | 视频指纹生成方法、装置、设备及存储介质 |
| CN116958882A (zh) * | 2023-08-28 | 2023-10-27 | 河北广电无线传媒股份有限公司 | 视频匹配方法、装置、电子设备及存储介质 |
| CN118013075A (zh) * | 2024-03-13 | 2024-05-10 | 北京有竹居网络技术有限公司 | 用于跨类型推荐的方法、装置、电子设备和程序产品 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104142984A (zh) * | 2014-07-18 | 2014-11-12 | 电子科技大学 | 一种基于粗细粒度的视频指纹检索方法 |
| CN104159140A (zh) * | 2014-03-03 | 2014-11-19 | 腾讯科技(北京)有限公司 | 一种视频处理的方法、装置和系统 |
| CN104881486A (zh) * | 2015-06-05 | 2015-09-02 | 腾讯科技(北京)有限公司 | 一种信息查询方法、终端设备及系统 |
| CN105653700A (zh) * | 2015-03-13 | 2016-06-08 | Tcl集团股份有限公司 | 视频检索方法及系统 |
| US9558407B1 (en) * | 2013-12-24 | 2017-01-31 | Google Inc. | Methods, systems, and media for detecting and presenting related media content |
| CN108024145A (zh) * | 2017-12-07 | 2018-05-11 | 北京百度网讯科技有限公司 | 视频推荐方法、装置、计算机设备和存储介质 |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010199907A (ja) * | 2009-02-25 | 2010-09-09 | Canon Inc | 記録再生装置 |
| CA2837725C (en) * | 2011-06-10 | 2017-07-11 | Shazam Entertainment Ltd. | Methods and systems for identifying content in a data stream |
| CN104025017A (zh) * | 2011-07-22 | 2014-09-03 | 谷歌公司 | 链接内容文件 |
| CN103984778B (zh) * | 2014-06-06 | 2017-12-01 | 北京猎豹网络科技有限公司 | 一种视频检索方法及系统 |
| CN104618788B (zh) * | 2014-12-29 | 2018-08-07 | 北京奇艺世纪科技有限公司 | 一种显示视频信息的方法及装置 |
| US20170279757A1 (en) * | 2016-03-22 | 2017-09-28 | Facebook, Inc. | Systems and methods for identifying matching content |
-
2017
- 2017-12-07 CN CN201711287361.9A patent/CN108024145B/zh active Active
-
2018
- 2018-07-18 US US16/622,876 patent/US20200322684A1/en not_active Abandoned
- 2018-07-18 JP JP2020519269A patent/JP2020536455A/ja active Pending
- 2018-07-18 WO PCT/CN2018/096177 patent/WO2019109643A1/zh not_active Ceased
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9558407B1 (en) * | 2013-12-24 | 2017-01-31 | Google Inc. | Methods, systems, and media for detecting and presenting related media content |
| CN104159140A (zh) * | 2014-03-03 | 2014-11-19 | 腾讯科技(北京)有限公司 | 一种视频处理的方法、装置和系统 |
| CN104142984A (zh) * | 2014-07-18 | 2014-11-12 | 电子科技大学 | 一种基于粗细粒度的视频指纹检索方法 |
| CN105653700A (zh) * | 2015-03-13 | 2016-06-08 | Tcl集团股份有限公司 | 视频检索方法及系统 |
| CN104881486A (zh) * | 2015-06-05 | 2015-09-02 | 腾讯科技(北京)有限公司 | 一种信息查询方法、终端设备及系统 |
| CN108024145A (zh) * | 2017-12-07 | 2018-05-11 | 北京百度网讯科技有限公司 | 视频推荐方法、装置、计算机设备和存储介质 |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112182290A (zh) * | 2019-07-05 | 2021-01-05 | 北京字节跳动网络技术有限公司 | 一种信息处理方法、装置和电子设备 |
| CN111447239A (zh) * | 2020-04-13 | 2020-07-24 | 北京字节跳动网络技术有限公司 | 视频流播放控制方法、设备及存储介质 |
| US12413799B2 (en) | 2020-04-13 | 2025-09-09 | Douyin Vision Co., Ltd. | Video stream playing control method and apparatus, and storage medium |
| US11889135B2 (en) | 2020-04-13 | 2024-01-30 | Douyin Vision Co., Ltd. | Video stream playing control method and apparatus, and storage medium |
| CN111447239B (zh) * | 2020-04-13 | 2023-07-04 | 抖音视界有限公司 | 视频流播放控制方法、设备及存储介质 |
| CN112565838A (zh) * | 2020-11-12 | 2021-03-26 | 深圳市易平方网络科技有限公司 | 基于电视的开机处理方法、装置、终端及介质 |
| CN113194351B (zh) * | 2021-02-24 | 2023-06-27 | 北京字跳网络技术有限公司 | 一种视频展示方法、装置、电子设备及存储介质 |
| CN113194351A (zh) * | 2021-02-24 | 2021-07-30 | 北京字跳网络技术有限公司 | 一种视频展示方法、装置、电子设备及存储介质 |
| CN113010703A (zh) * | 2021-03-22 | 2021-06-22 | 腾讯科技(深圳)有限公司 | 一种信息推荐方法、装置、电子设备和存储介质 |
| CN113010703B (zh) * | 2021-03-22 | 2024-04-12 | 深圳市雅阅科技有限公司 | 一种信息推荐方法、装置、电子设备和存储介质 |
| CN115348460A (zh) * | 2021-05-13 | 2022-11-15 | 北京字节跳动网络技术有限公司 | 视频的预加载方法、装置、设备及存储介质 |
| CN115348460B (zh) * | 2021-05-13 | 2024-06-07 | 北京字节跳动网络技术有限公司 | 视频的预加载方法、装置、设备及存储介质 |
| CN114401435A (zh) * | 2021-12-29 | 2022-04-26 | 阿里巴巴(中国)有限公司 | 短视频的生成方法、装置、电子设备及可读存储介质 |
| CN115237314B (zh) * | 2022-04-18 | 2023-09-08 | 网易(杭州)网络有限公司 | 信息推荐方法、装置和电子设备 |
| CN115237314A (zh) * | 2022-04-18 | 2022-10-25 | 网易(杭州)网络有限公司 | 信息推荐方法、装置和电子设备 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108024145B (zh) | 2020-12-11 |
| JP2020536455A (ja) | 2020-12-10 |
| CN108024145A (zh) | 2018-05-11 |
| US20200322684A1 (en) | 2020-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108024145B (zh) | 视频推荐方法、装置、计算机设备和存储介质 | |
| JP5038607B2 (ja) | スマートメディアコンテンツサムネイル抽出のシステムおよび方法 | |
| US20180041796A1 (en) | Method and device for displaying information on video image | |
| US9881215B2 (en) | Apparatus and method for identifying a still image contained in moving image contents | |
| CN111095939B (zh) | 识别媒体项目的先前流传输部分以避免重复重放 | |
| US20120209841A1 (en) | Bookmarking segments of content | |
| US20090190804A1 (en) | Electronic apparatus and image processing method | |
| JP7204786B2 (ja) | 視覚的検索方法、装置、コンピュータ機器及び記憶媒体 | |
| CN101365134B (zh) | 帧指定方法 | |
| WO2009125166A1 (en) | Television receiver and method | |
| CN104618803A (zh) | 信息推送方法、装置、终端及服务器 | |
| CN109729429B (zh) | 视频播放方法、装置、设备和介质 | |
| CN109697245A (zh) | 基于网页视频的语音搜索方法和装置 | |
| BR112020003189B1 (pt) | Método, sistema, e, mídia legível por computador não transitória para focalização de multimídia | |
| WO2017181597A1 (zh) | 视频播放方法及装置 | |
| CN103984778B (zh) | 一种视频检索方法及系统 | |
| CN106851395B (zh) | 视频播放方法和播放器 | |
| US9535991B2 (en) | Video display for displaying a series of representative images for video | |
| KR20090089878A (ko) | 개요 및 리포트를 이미 포함하는 시청각 도큐먼트의 새로운 개요를 생성하기 위한 방법 및 상기 방법을 구현할 수 있는 수신기 | |
| CN115080792A (zh) | 一种视频关联方法、装置、电子设备及存储介质 | |
| CN107948718B (zh) | 一种节目信息的处理方法、装置及系统 | |
| US20170040040A1 (en) | Video information processing system | |
| CN114117120B (zh) | 基于内容分析的视频文件智能索引生成系统及方法 | |
| CN116450859A (zh) | 用于媒体内容推荐的方法、装置、设备和存储介质 | |
| KR20180062005A (ko) | 동영상 발췌 및 관리 시스템 및 방법 |
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: 18886550 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2020519269 Country of ref document: JP Kind code of ref document: A |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 18886550 Country of ref document: EP Kind code of ref document: A1 |