[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

WO2021147949A1 - 视频推荐方法及装置 - Google Patents

视频推荐方法及装置 Download PDF

Info

Publication number
WO2021147949A1
WO2021147949A1 PCT/CN2021/073044 CN2021073044W WO2021147949A1 WO 2021147949 A1 WO2021147949 A1 WO 2021147949A1 CN 2021073044 W CN2021073044 W CN 2021073044W WO 2021147949 A1 WO2021147949 A1 WO 2021147949A1
Authority
WO
WIPO (PCT)
Prior art keywords
video
cover
feature
user group
target
Prior art date
Application number
PCT/CN2021/073044
Other languages
English (en)
French (fr)
Inventor
赵志璞
Original Assignee
北京达佳互联信息技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京达佳互联信息技术有限公司 filed Critical 北京达佳互联信息技术有限公司
Publication of WO2021147949A1 publication Critical patent/WO2021147949A1/zh
Priority to US17/842,270 priority Critical patent/US11546663B2/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/73—Querying
    • G06F16/735—Filtering based on additional data, e.g. user or group profiles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/78—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]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/252—Processing of multiple end-users' preferences to derive collaborative data
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
    • H04N21/25866—Management of end-user data
    • H04N21/25891—Management of end-user data being end-user preferences
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/266—Channel or content management, e.g. generation and management of keys and entitlement messages in a conditional access system, merging a VOD unicast channel into a multicast channel
    • H04N21/2668—Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/482—End-user interface for program selection
    • H04N21/4826—End-user interface for program selection using recommendation lists, e.g. of programs or channels sorted out according to their score
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/81—Monomedia components thereof
    • H04N21/8146—Monomedia components thereof involving graphical data, e.g. 3D object, 2D graphics
    • H04N21/8153—Monomedia components thereof involving graphical data, e.g. 3D object, 2D graphics comprising still images, e.g. texture, background image

Definitions

  • the present disclosure relates to the field of Internet technology, and in particular to a video recommendation method, device, storage medium, terminal, and server.
  • the video cover as a sign of displaying video content, allows users to have a general understanding of the video content, and its importance is self-evident.
  • the present disclosure provides a video recommendation method, device, storage medium, terminal and server.
  • the technical solutions of the present disclosure are as follows:
  • a video recommendation method is provided, the method is used in a terminal, and the method includes:
  • search for a video cover associated with the related video where the video cover is determined according to the behavior information of the user performing an operation on the related video, and the video cover is added to the video A cover set, where the video cover set includes multiple video covers;
  • the target video and the video cover set are sent to a server, where the server adds different video covers to the target video based on the video cover set and different user groups.
  • the method further includes:
  • the separately determining the popularity of each video cover corresponding to the related video based on the behavior information includes:
  • the popularity of the video cover is determined according to the behavior information of the user performing an operation on the related video to which the video cover is added.
  • a video recommendation method is provided, the method is used in a server, and the method includes:
  • any video cover in the video cover set obtain the video feature of the target video and the cover feature of the video cover; wherein the video feature includes the type of the video, and the cover feature includes the cover style;
  • the determining the user group corresponding to the video cover based on the video feature and the cover feature includes:
  • the user group corresponding to the identifier is determined as the user group corresponding to the video cover.
  • the determining the user group corresponding to the video cover based on the video feature and the cover feature includes:
  • the user group group including at least two user groups
  • the cover feature determine the user group corresponding to the video cover from the user group group.
  • the method in response to receiving the target video and the video cover set sent by the terminal, the method further includes:
  • the video feature of the target video and the cover feature of the video cover are acquired.
  • a video recommendation device is provided, the device is used in a terminal, and the device includes:
  • the related video acquisition module is configured to acquire at least two related videos of the target video
  • the video cover set generating module is configured to, for each of the related videos, search for a video cover associated with the related video, wherein the video cover is determined according to the behavior information of the user performing an operation on the related video, And adding the video cover to a video cover set, where the video cover set includes multiple video covers;
  • the sending module is configured to send the target video and the video cover set to a server, wherein the server adds different video covers to the target video based on the video cover set and different user groups.
  • the device further includes:
  • the behavior information acquisition module is configured to acquire behavior information of the user performing operations on the related video
  • the popularity determination module is configured to determine the popularity of each video cover corresponding to the related video based on the behavior information
  • the associating module is configured to determine the most popular video cover from all the video covers corresponding to the related video, and associate the related video with the most popular video cover.
  • the popularity determination module is configured to:
  • the popularity of the video cover is determined according to the behavior information of the user performing an operation on the related video to which the video cover is added.
  • a video recommendation device is provided, the device is used in a server, and the device includes:
  • a receiving module configured to receive a target video and a video cover set sent by the client, the video cover set including a plurality of video covers;
  • the feature obtaining module is configured to obtain the video feature of the target video and the cover feature of the video cover for any video cover in the video cover set; wherein, the video feature includes the type of the video, and the cover Features include cover style;
  • a user group determining module configured to determine a user group corresponding to the video cover based on the video feature and the cover feature
  • the processing module is configured to add the video cover to the target video, and recommend the target video to which the video cover is added to the user group.
  • the user group determination module is configured to:
  • the user group corresponding to the identifier is determined as the user group corresponding to the video cover.
  • the user group determination module is configured to:
  • the user group group including at least two user groups
  • the cover feature determine the user group corresponding to the video cover from the user group group.
  • the device further includes:
  • a verification module configured to verify the target video and the video cover in the video cover set
  • the feature acquisition module is configured to:
  • the video feature of the target video and the cover feature of the video cover are acquired.
  • a storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the video recommendation method in any possible implementation of the present disclosure are implemented.
  • a terminal including a memory, a processor, and a computer program stored on the memory and capable of running on the processor.
  • the processor implements Steps of the video recommendation method in the first aspect or any possible implementation of the first aspect.
  • a server including a memory, a processor, and a computer program stored on the memory and capable of running on the processor.
  • the processor implements The steps of the video recommendation method in the second aspect or any possible implementation of the second aspect.
  • a computer program product including a computer program, which, when executed by a processor, implements the steps of the video recommendation method in any possible implementation manner of the present disclosure.
  • the embodiment of the present disclosure obtains at least two related videos of a target video, and then for each related video, searches for a video cover associated with the related video, adds the video cover to the video cover set, and then adds
  • the target video and the video cover set are sent to a server, where the server adds different video covers to the target video based on the video cover set and different user groups, so that under different users, You can add different video covers to the video to solve the problem of single video cover.
  • Figure 1 is a schematic diagram of video recommendation in related technologies
  • Fig. 2 is a network architecture diagram of a video recommendation system according to some embodiments.
  • FIG. 3 is a schematic flowchart of a video recommendation method on the client side according to some embodiments.
  • FIG. 4 is a schematic flowchart of a video recommendation method on the server side according to some embodiments.
  • Fig. 5 is a schematic diagram showing video recommendation according to some embodiments.
  • Fig. 6 is a schematic diagram showing a first structure of a video recommendation apparatus on the client side according to some embodiments
  • Fig. 7 is a schematic diagram showing a second structure of a video recommendation device on the client side according to some embodiments.
  • FIG. 8 is a first schematic structural diagram of a video recommendation device on the server side according to some embodiments.
  • FIG. 9 is a schematic diagram showing a second structure of a video recommendation device on the server side according to some embodiments.
  • Fig. 10 is a schematic structural diagram of a terminal according to some embodiments.
  • Fig. 11 is a schematic diagram showing a structure of a server according to some embodiments.
  • the videos recommended to users have only a single cover, and the cover is the same for all users.
  • the video 10 has a single cover 20, and the video 10 with the cover 20 added is recommended to user group A, user group B, and user group C.
  • the cover of Video 10 is the same.
  • different users have obvious differences. Not all users are interested in the video cover. If the user is not interested in the video cover, the user may not click to watch the video, which will result in a lower click-through rate of the video. Therefore, it is necessary to provide a personalized video cover based on different groups of users, so as to increase the click rate of the video.
  • FIG. 2 is a network architecture diagram of a video recommendation system according to some embodiments. As shown in FIG. 2, the network architecture includes multiple terminals 10 and servers 20.
  • the terminal 10 may be a smart phone, a tablet computer, etc., and the terminal 10 is an electronic device running at least one video application (APP) client.
  • APP video application
  • the server 20 is a background server of the video APP, and is used for receiving data sent by the terminal 10 or for sending data to the terminal 10.
  • FIG. 3 is a flowchart of a video recommendation method according to some embodiments. As shown in FIG. 3, the video recommendation method is used in a terminal, and the video recommendation method includes the following steps:
  • the target video may be a video just shot by the user, or an existing video with an undetermined cover.
  • the related video of the target video may be, for example, a similar video similar to the video content of the target video, or may be a video that is the same as the target video in at least one of the following: video author, video publishing location, or Video theme.
  • Related videos can be obtained from the video library through a video similarity matching algorithm, for example, a content-based recommendation algorithm (Content-Based Recommendation), a collaborative filtering recommendation algorithm (Collaborative Filtering Recommendation), and a combined recommendation (Hybrid Recommendation).
  • the content-based recommendation algorithm is based on the content that the user likes in the past, and recommends content that is similar to the content he likes in the past. It uses the content attributes of the items to calculate the similarity between the items, and determines the relevance of the target video based on the similarity of the items. video.
  • Collaborative filtering can be divided into user-based collaborative filtering, item-based collaborative filtering (ItemCF for short), and model-based collaborative filtering (such as matrix decomposition, etc.).
  • ItemCF item-based collaborative filtering
  • model-based collaborative filtering such as matrix decomposition, etc.
  • the ItemCF algorithm mainly calculates the similarity between items by analyzing user behavior data (such as the number of user clicks, watching, reposting, and comments on the video), and determines related videos of the target video according to the similarity of the items.
  • Combined recommendation is to combine multiple recommendation algorithms to determine the relevant videos of the target video.
  • the video cover associated with the related video may be the video cover with the highest popularity, and the popularity of the video cover may be determined according to the behavior information of the user performing an operation on the related video to which the video cover is added.
  • S103 Send the target video and the video cover set to a server, so that the server adds different video covers to the target video based on the video cover set and recommends them to different user groups, the user groups including At least one user.
  • the method before searching for the video cover associated with the related video, the method further includes:
  • the foregoing separately determining the popularity of each video cover corresponding to the related video based on the behavior information includes:
  • the popularity of the video cover is determined according to the behavior information of the user performing an operation on the related video to which the video cover is added.
  • the popularity of the video cover can be determined according to behavioral information such as whether the user clicks or likes the related video with the video cover added, and whether the author of the related video with the video cover added is concerned. .
  • Fig. 4 is a flowchart of a video recommendation method according to other embodiments. As shown in Fig. 4, the video recommendation method is used in a server, and the method includes the following steps.
  • S201 Receive a target video and a video cover set sent by a terminal, where the video cover set includes at least two video covers;
  • the video feature includes the type of the video, for example, food, sports, game, etc.
  • the cover feature includes the cover style.
  • S203 Determine a user group corresponding to the video cover according to the video feature and the cover feature, where the user group includes at least one user;
  • determining the user group corresponding to the video cover based on the video feature and the cover feature in step S203 includes:
  • the user group corresponding to the identifier is determined as the user group corresponding to the video cover.
  • each user group is provided with an identifier, for example, user group A corresponds to the identifier 0x1, user group B corresponds to the identifier 0x2, and user group C corresponds to the identifier 0x3.
  • the video recommendation model is pre-trained, and the video recommendation model may be trained on an electronic device, a server, or a terminal.
  • the training method of the video recommendation model includes:
  • each training sample in the training sample set includes: the video feature of the video, the cover feature of the video cover, and the identification of the user group;
  • the training sample set can be obtained in the following way:
  • the video recommendation history information includes a large amount of video recommendation data, and each piece of video recommendation data records that a user recommends a certain video with a certain video cover to a certain user group;
  • For each piece of video recommendation data according to the video recommendation data, obtain the video feature of the video, the cover feature of the video cover, and determine the identification of the user group recommended by the video with the video cover, and then a training sample can be obtained .
  • determining the user group corresponding to the video cover based on the video feature and the cover feature in step S203 includes:
  • the cover feature determine the user group corresponding to the video cover from the user group group.
  • the video cover set of the video includes video cover a, video cover b, and video cover c.
  • the video features of the video include games. Find the user group corresponding to the game and determine that the video can be recommended to users including The user group groups of group A, user group B, and user group C, and then according to the cover characteristics of each video cover (such as cover style), respectively determine that the video cover a corresponds to user group A, video cover b corresponds to user group B, and video cover c
  • cover characteristics of each video cover such as cover style
  • the method in response to receiving the target video and the video cover set sent by the client, the method further includes:
  • the steps of obtaining the video feature of the target video and obtaining the cover feature of the video cover are performed.
  • the screening strategy may include, for example, filtering video covers with negative tags (such as sensitive content, being reported, etc.), and filtering videos that violate laws and regulations (such as violent videos, pornographic videos).
  • the technical solution provided by the embodiment of the present disclosure first receives the target video and the video cover set sent by the client, and then for any video cover in the video cover set, the video feature of the target video is obtained, and the video cover is obtained According to the video feature and the cover feature, determine the user group corresponding to the video cover, and then add the video cover to the target video, and add the video cover to the
  • the target video is recommended to the user group, so that different video covers can be added to the video under different users, so that the user can be provided with the video cover of interest, so the problem of single video cover can be solved.
  • FIG. 6 is a block diagram of a video recommendation device according to some embodiments. Referring to FIG. 6, the video recommendation device is used in a client, and the video recommendation device includes: a related video acquisition module 11, a video cover collection generating module 12, and a sending module 13.
  • the related video obtaining module 11 is configured to obtain at least two related videos of the target video
  • the video cover set generating module 12 is configured to, for each related video, search for a video cover associated with the related video, wherein the video cover is determined according to the behavior information of the user performing an operation on the related video , And add the found video cover to a video cover set, where the video cover set includes at least two video covers;
  • the sending module 13 is configured to send the target video and the video cover set to the server, so that the server adds different video covers to the target video based on the video cover set and recommends them to different user groups,
  • the user group includes at least one user.
  • the video cover associated with the related video is the most popular video cover
  • the above-mentioned video recommendation device further includes:
  • the behavior information acquiring module 14 is configured to acquire behavior information of the user performing operations on the related video
  • the popularity determination module 15 is configured to separately determine the popularity of each video cover corresponding to the related video based on the behavior information
  • the associating module 16 is configured to search for the most popular video cover from all the video covers corresponding to the related video, and associate the related video with the most popular video cover.
  • the popularity determination module 15 is configured to:
  • the popularity of the video cover is determined according to the behavior information of the user performing an operation on the related video to which the video cover is added.
  • FIG. 8 is a block diagram of a video recommendation device according to some embodiments.
  • the video recommendation device is used in a server, and the video recommendation device includes: a receiving module 21, a feature acquiring module 22, a user group determining module 23 and a processing module 24.
  • the user group determination module 23 is configured to:
  • the user group corresponding to the identifier is determined as the user group corresponding to the video cover.
  • the user group determination module 23 is configured to:
  • the user group group including at least two user groups
  • the cover feature determine the user group corresponding to the video cover from the user group group.
  • the above-mentioned video recommendation apparatus further includes:
  • the verification module 25 is configured to verify the target video and the video cover in the video cover set according to a set screening strategy
  • the feature acquisition module 22 is configured to:
  • the relevant part can refer to the part of the description of the method embodiment.
  • the device embodiments described above are merely illustrative.
  • 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, they may be located in One place, or it can be distributed to multiple network units.
  • Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the present disclosure. Those of ordinary skill in the art can understand and implement without creative work.
  • the embodiments of the present disclosure further provide a storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the video recommendation method in any of the foregoing possible implementations are implemented.
  • the storage medium may be a non-transitory computer-readable storage medium.
  • the non-transitory computer-readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical disk. Data storage devices, etc.
  • the embodiments of the present disclosure also provide a computer program product, including a computer program, which, when executed by a processor, implements the steps of the video recommendation method in any of the foregoing possible implementations.
  • the embodiments of the present disclosure also provide a terminal, including a memory, a processor, and a computer program stored on the memory and running on the processor;
  • the processor is configured to:
  • search for a video cover associated with the related video where the video cover is determined according to the behavior information of the user performing an operation on the related video, and the found video cover Added to a video cover set, where the video cover set includes at least two video covers;
  • the target video and the video cover set are sent to the server, so that the server adds different video covers for the target video based on the video cover set and recommends them to different user groups, and the user groups include at least one user.
  • FIG. 10 is a schematic structural diagram of a terminal 1700 according to some embodiments of the present disclosure.
  • the terminal 1700 may be a mobile phone with a routing function, a computer, a digital broadcasting terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.
  • the terminal 1700 may include one or more of the following components: a processing component 1702, a memory 1704, a power supply component 1706, a multimedia component 1708, an audio component 1710, an input/output (I/O) interface 1712, a sensor component 1714, And the communication component 1716.
  • the processing component 1702 generally controls the overall operations of the terminal 1700, such as operations associated with display, telephone calls, data communication, camera operations, and recording operations.
  • the processing component 1702 may include one or more processors 1720 to execute instructions to complete all or part of the steps of the foregoing method.
  • the processing component 1702 may include one or more modules to facilitate the interaction between the processing component 1702 and other components.
  • the processing component 1702 may include a multimedia module to facilitate the interaction between the multimedia component 1708 and the processing component 1702.
  • the memory 1704 is configured to store various types of data to support operations in the terminal 1700. Examples of these data include instructions for any application or method operated on the terminal 1700, contact data, phone book data, messages, pictures, videos, etc.
  • the memory 1704 can be implemented by any type of volatile or non-volatile storage device or their combination, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable and Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic Disk or Optical Disk.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read-only memory
  • EPROM erasable and Programmable Read Only Memory
  • PROM Programmable Read Only Memory
  • ROM Read Only Memory
  • Magnetic Memory Flash Memory
  • Magnetic Disk Magnetic Disk or Optical Disk.
  • the power supply component 1706 provides power for various components of the terminal 1700.
  • the power supply component 1706 may include a power management system, one or more power supplies, and other components associated with the generation, management, and distribution of power for the terminal 1700.
  • the multimedia component 1708 includes a screen that provides an output interface between the terminal 1700 and the user.
  • the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touch, sliding, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure related to the touch or slide operation.
  • the multimedia component 1708 includes a front camera and/or a rear camera. When the terminal 1700 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.
  • the audio component 1710 is configured to output and/or input audio signals.
  • the audio component 1710 includes a microphone (MIC).
  • the microphone is configured to receive external audio signals.
  • the received audio signal may be further stored in the memory 1704 or transmitted via the communication component 1716.
  • the audio component 1710 further includes a speaker for outputting audio signals.
  • the I/O interface 1712 provides an interface between the processing component 1702 and a peripheral interface module.
  • the peripheral interface module may be a keyboard, a click wheel, a button, and the like. These buttons may include, but are not limited to: home button, volume button, start button, and lock button.
  • the sensor component 1714 includes one or more sensors for providing the terminal 1700 with various aspects of status evaluation.
  • the sensor component 1714 can detect the open/close state of the terminal 1700 and the relative positioning of components.
  • the component is the display and keypad of the terminal 1700.
  • the sensor component 1714 can also detect the position change of the terminal 1700 or a component of the terminal 1700. , The presence or absence of contact between the user and the terminal 1700, the orientation or acceleration/deceleration of the terminal 1700, and the temperature change of the terminal 1700.
  • the sensor assembly 1714 may include a proximity sensor configured to detect the presence of nearby objects when there is no physical contact.
  • the sensor component 1714 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications.
  • the sensor component 1714 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, a microwave sensor, or a temperature sensor.
  • the communication component 1716 is configured to facilitate wired or wireless communication between the terminal 1700 and other devices.
  • the terminal 1700 can access a wireless network based on a communication standard, such as WiFi, 2G, or 3G, or a combination thereof.
  • the communication component 1716 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel.
  • the communication component 1716 further includes a near field communication (NFC) module to facilitate short-range communication.
  • the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • the terminal 1700 may be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable A gate array (FPGA), controller, microcontroller, microprocessor, or other electronic components are implemented to implement the video recommendation method shown in FIG. 3.
  • ASIC application specific integrated circuits
  • DSP digital signal processors
  • DSPD digital signal processing devices
  • PLD programmable logic devices
  • FPGA field programmable A gate array
  • controller microcontroller, microprocessor, or other electronic components are implemented to implement the video recommendation method shown in FIG. 3.
  • non-transitory computer-readable storage medium including instructions, such as a memory 1704 including instructions, which can be executed by the processor 1720 of the terminal 1700 to complete the foregoing method.
  • the non-transitory computer-readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
  • the embodiments of the present disclosure also provide a server, including a memory, a processor, and a computer program stored on the memory and running on the processor;
  • the processor is configured to:
  • For any video cover in the video cover set obtain the video feature of the target video and obtain the cover feature of the video cover; wherein the video feature includes the type of the video, and the cover feature includes the cover style;
  • FIG. 11 is a schematic structural diagram of a server 1800 according to some embodiments.
  • the server 1800 includes a processing component 1802, which further includes one or more processors, and a memory resource represented by a memory 1804, for storing instructions executable by the processing component 1802, such as application programs.
  • the application program stored in the memory 1804 may include one or more modules each corresponding to a set of instructions.
  • the processing component 1802 is configured to execute instructions to execute the video recommendation method as shown in FIG. 4.
  • the server 1800 may also include a power component 1806 configured to perform power management of the server 1800, a wired or wireless network interface 1808 configured to connect the server 1800 to the network, and an input output (I/O) interface 1810.
  • the server 1800 may operate based on an operating system stored in the storage 1804, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM or the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Library & Information Science (AREA)
  • Computing Systems (AREA)
  • Computer Graphics (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Human Computer Interaction (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

提供一种视频推荐方法及装置。视频推荐方法可以通过获取目标视频的相关视频及与相关视频关联的视频封面，获取视频封面集，并发送给服务器。服务器可以基于视频封面集为目标视频添加不同的视频封面并推荐给不同的用户群体。

Description

视频推荐方法及装置
相关申请的交叉引用
本申请要求于2020年1月21日在中国国家知识产权局提交的中国专利申请202010072107.2的优先权，其内容通过引用的方式全文并入于此。
技术领域
本公开涉及互联网技术领域，尤其涉及一种视频推荐方法、装置、存储介质、终端及服务器。
背景技术
随着互联网技术的高速发展，越来越多的用户开始用视频来记录自己的生活，并把视频分享给其他用户。
视频封面作为展示视频内容的标志，可以让用户对视频内容有一个大概的认知，其重要性不言而喻。
发明内容
本公开提供一种视频推荐方法、装置、存储介质、终端及服务器。本公开的技术方案如下：
根据本公开实施例的第一方面，提供一种视频推荐方法，所述方法用于终端，所述方法包括：
获取目标视频的至少两个相关视频；
对于每一所述相关视频，查找与所述相关视频关联的视频封面，其中，所述视频封面是根据用户对所述相关视频执行操作的行为信息确定的，并将所述视频封面添加到视频封面集，所述视频封面集包括多个视频封面；
将所述目标视频和所述视频封面集发送给服务器，其中，所述服务器基于所述视频封面集和不同的用户群体为所述目标视频添加不同的视频封面。
在一些实施例中，该方法还包括：
获取用户对相关视频执行操作的行为信息；
基于所述行为信息，分别确定所述相关视频对应的各个视频封面的热度；
从所述相关视频对应的所有视频封面中确定热度最高的视频封面，并关联所述相关视频与所述热度最高的视频封面。
在一些实施例中，所述基于所述行为信息，分别确定所述相关视频对应的各个视频封面的热度，包括：
对于所述相关视频对应的每一视频封面，根据用户对添加有所述视频封面的所述相关 视频执行操作的行为信息，确定所述视频封面的热度。
根据本公开实施例的第二方面，提供一种视频推荐方法，所述方法用于服务器，所述方法包括：
接收终端发送的目标视频和视频封面集，所述视频封面集包括多个视频封面；
对于所述视频封面集中的任一视频封面，获取所述目标视频的视频特征和所述视频封面的封面特征；其中，所述视频特征包括视频的类型，所述封面特征包括封面风格；
根据所述视频特征和所述封面特征，确定所述视频封面对应的用户群体；
为所述目标视频添加所述视频封面，并将添加有所述视频封面的所述目标视频推荐给所述用户群体。
在一些实施例中，所述根据所述视频特征和所述封面特征，确定所述视频封面对应的用户群体，包括：
将所述视频特征和所述封面特征输入到预先训练的视频推荐模型，得到所述视频推荐模型输出的对应用户群体的标识；
将所述标识对应的用户群体，确定为所述视频封面对应的用户群体。
在一些实施例中，所述根据所述视频特征和所述封面特征，确定所述视频封面对应的用户群体，包括：
根据所述视频特征，确定所述目标视频对应的用户群体组，所述用户群体组包括至少两个用户群体；
根据所述封面特征，从所述用户群体组中确定所述视频封面对应的用户群体。
在一些实施例中，响应于接收到终端发送的目标视频和视频封面集，该方法还包括：
对所述目标视频和所述视频封面集中的视频封面进行验证；
响应于所述目标视频通过验证，获取所述目标视频的视频特征和所述视频封面的封面特征。
根据本公开实施例的第三方面，提供一种视频推荐装置，所述装置用于终端，所述装置包括：
相关视频获取模块，被配置为获取目标视频的至少两个相关视频；
视频封面集生成模块，被配置为对于每一所述相关视频，查找与所述相关视频关联的视频封面，其中，所述视频封面是根据用户对所述相关视频执行操作的行为信息确定的，并将所述视频封面添加到视频封面集，所述视频封面集包括多个视频封面；
发送模块，被配置为将所述目标视频和所述视频封面集发送给服务器，其中，所述服务器基于所述视频封面集和不同的用户群体为所述目标视频添加不同的视频封面。
在一些实施例中，所述装置还包括：
行为信息获取模块，被配置为获取用户对相关视频执行操作的行为信息；
热度确定模块，被配置为基于所述行为信息，分别确定所述相关视频对应的各个视频 封面的热度；
关联模块，被配置为从所述相关视频对应的所有视频封面中确定热度最高的视频封面，并关联所述相关视频与所述热度最高的视频封面。
在一些实施例中，所述热度确定模块被配置为：
对于所述相关视频对应的每一视频封面，根据用户对添加有所述视频封面的所述相关视频执行操作的行为信息，确定所述视频封面的热度。
根据本公开实施例的第四方面，提供一种视频推荐装置，所述装置用于服务器，所述装置包括：
接收模块，被配置为接收客户端发送的目标视频和视频封面集，所述视频封面集包括多个视频封面；
特征获取模块，被配置为对于所述视频封面集中的任一视频封面，获取所述目标视频的视频特征和所述视频封面的封面特征；其中，所述视频特征包括视频的类型，所述封面特征包括封面风格；
用户群体确定模块，被配置为根据所述视频特征和所述封面特征，确定所述视频封面对应的用户群体；
处理模块，被配置为为所述目标视频添加所述视频封面，并将添加有所述视频封面的所述目标视频推荐给所述用户群体。
在一些实施例中，所述用户群体确定模块被配置为：
将所述视频特征和所述封面特征输入到预先训练的视频推荐模型，得到所述视频推荐模型输出的对应用户群体的标识；
将所述标识对应的用户群体，确定为所述视频封面对应的用户群体。
在一些实施例中，所述用户群体确定模块被配置为：
根据所述视频特征，确定所述目标视频对应的用户群体组，所述用户群体组包括至少两个用户群体；
根据所述封面特征，从所述用户群体组中确定所述视频封面对应的用户群体。
在一些实施例中，所述装置还包括：
校验模块，被配置为对所述目标视频和所述视频封面集中的视频封面进行验证；
所述特征获取模块被配置为：
响应于所述目标视频通过所述校验模块的验证，获取所述目标视频的视频特征和所述视频封面的封面特征。
根据本公开实施例的第五方面，提供一种存储介质，其上存储有计算机程序，所述程序被处理器执行时实现本公开任意可能的实现方式中的视频推荐方法的步骤。
根据本公开实施例的第六方面，提供一种终端，包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述程序时实现第一方面 或第一方面的任意可能的实现方式中的视频推荐方法的步骤。
根据本公开实施例的第七方面，提供一种服务器，包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述程序时实现第二方面或第二方面的任意可能的实现方式中的视频推荐方法的步骤。
根据本公开实施例的第八方面，提供一种计算机程序产品，包括计算机程序，所述程序被处理器执行时实现本公开任意可能的实现方式中的视频推荐方法的步骤。
本公开的实施例获取目标视频的至少两个相关视频，然后对于每一所述相关视频，查找与所述相关视频关联的视频封面，并将所述视频封面添加到视频封面集，之后，将所述目标视频和所述视频封面集发送给服务器，其中，所述服务器基于所述视频封面集和不同的用户群体为所述目标视频添加不同的视频封面，实现了在用户不同的情况下，可以为视频添加不同的视频封面，从而解决视频封面单一的问题。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理，并不构成对本公开的不当限定。
图1是相关技术中视频推荐的原理图；
图2是根据一些实施例示出的一种视频推荐系统的网络架构图；
图3是根据一些实施例示出的客户端侧的视频推荐方法的流程示意图；
图4是根据一些实施例示出的服务器侧的视频推荐方法的流程示意图；
图5是根据一些实施例示出的视频推荐的原理图；
图6是根据一些实施例示出的客户端侧的视频推荐装置的第一种结构示意图；
图7是根据一些实施例示出的客户端侧的视频推荐装置的第二种结构示意图；
图8是根据一些实施例示出的服务器侧的视频推荐装置的第一种结构示意图；
图9是根据一些实施例示出的服务器侧的视频推荐装置的第二种结构示意图；
图10是根据一些实施例示出的一种终端的结构示意图；
图11是根据一些实施例示出的一种服务器的结构示意图。
具体实施方式
为了使本领域普通人员更好地理解本公开的技术方案，下面将结合附图，对本公开实施例中的技术方案进行清楚、完整地描述。
需要说明的是，本公开的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的 数据在适当情况下可以互换，以便这里描述的本公开的实施例能够以除了在这里图示或描述的那些以外的顺序实施。以下示例性实施例中所描述的实施方式并不代表与本公开相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本公开的一些方面相一致的装置和方法的例子。
目前，推荐给用户的视频都只有单个封面，对所有的用户来说封面都是一样的。如图1所示，视频10，设有单个封面20，添加封面20的视频10推荐给用户群体A、用户群体B和用户群体C，对于用户群体A、用户群体B和用户群体C来说，视频10的封面是一样的。然而，不同的用户有其明显的差异性，不是所有用户都对该视频封面感兴趣，如果用户对视频封面不感兴趣，用户很可能不会点击观看视频，这样会导致视频的点击率比较低，因此需要提供一种基于不同群体用户提供个性化的视频封面，从而提高视频的点击率。
图2是根据一些实施例示出的一种视频推荐系统的网络架构图，如图2所示，该网络架构包括多个终端10和服务器20。
终端10可以是智能手机、平板电脑等，终端10是运行有至少一个视频应用(APP)的客户端的电子设备。
服务器20为视频APP的后台服务器，用于接收终端10发送的数据，或者用于向终端10发送数据。
图3是根据一些实施例示出的一种视频推荐方法的流程图，如图3所示，该视频推荐方法用于终端中，该视频推荐方法包括以下步骤：
S101、获取目标视频的至少两个相关视频；
本申请的实施例中，目标视频可以是用户刚拍摄的视频，也可以是已有的未确定封面的视频。
本申请的实施例中，目标视频的相关视频例如可以是与所述目标视频的视频内容相似的相似视频，也可以是与目标视频在如下至少一项相同的视频：视频作者、视频发布地点或者视频主题。相关视频可以通过视频相似性匹配算法从视频库中得到，例如，基于内容的推荐算法(Content-Based Recommendation)、协同过滤的推荐算法(Collaborative Filtering Recommendation)、组合推荐(Hybrid Recommendation)等。
基于内容的推荐算法是根据用户过去喜欢的内容，为用户推荐和他过去喜欢的内容相似的内容，其利用物品的内容属性计算物品之间的相似度，根据物品的相似度确定目标视频的相关视频。
协同过滤主要可以分为基于用户的协同过滤、基于物品的协同过滤(简称ItemCF)、以及基于模型的协同过滤(如矩阵分解等)。其中，ItemCF算法主要通过分析用户行为数据(例如用户对视频的点击、观看、转发、评论数)计算物品之间的相似度，根据物品的相似度确定目标视频的相关视频。
组合推荐是将多个推荐算法组合起来确定目标视频的相关视频。
S102、对于每一所述相关视频，查找与所述相关视频关联的视频封面，其中，所述视频封面是根据用户对所述相关视频执行操作的行为信息确定的，并将查找到的所述视频封面添加到视频封面集，所述视频封面集包括至少两个视频封面；
本申请的实施例中，与所述相关视频关联的视频封面可以为热度最高的视频封面，视频封面的热度可以根据用户对添加有该视频封面的相关视频执行操作的行为信息来确定。
S103、将所述目标视频和所述视频封面集发送给服务器，以使服务器基于所述视频封面集，为所述目标视频添加不同的视频封面并推荐给不同的用户群体，所述用户群体包括至少一个用户。
在一些实施例中，在查找与所述相关视频关联的视频封面之前，该方法还包括：
获取用户对相关视频执行操作的行为信息；
基于所述行为信息，分别确定所述相关视频对应的各个视频封面的热度；
从所述相关视频对应的所有视频封面中查找热度最高的视频封面，并关联所述相关视频与所述热度最高的视频封面。
在一些实施例中，上述基于所述行为信息，分别确定所述相关视频对应的各个视频封面的热度，包括：
对于所述相关视频对应的每一视频封面，根据用户对添加有所述视频封面的所述相关视频执行操作的行为信息，确定所述视频封面的热度。
本申请的实施例中，例如可以根据用户是否对添加有视频封面的相关视频进行点击、点赞，对添加有该视频封面的相关视频的作者是否进行关注等行为信息来确定该视频封面的热度。
图4是根据另一些实施例示出的一种视频推荐方法的流程图，如图4所示，该视频推荐方法用于服务器中，该方法包括以下步骤。
S201、接收终端发送的目标视频和视频封面集，所述视频封面集包括至少两个视频封面；
S202、对于所述视频封面集中的任一视频封面，获取所述目标视频的视频特征和所述视频封面的封面特征；
本申请的实施例中，视频特征包括视频的类型，比如，美食、体育、游戏等类型，封面特征包括封面风格。
S203、根据所述视频特征和所述封面特征，确定所述视频封面对应的用户群体，所述用户群体包括至少一个用户；
在一些实施例中，步骤S203中根据所述视频特征和所述封面特征，确定所述视频封面对应的用户群体，包括：
将所述视频特征和所述封面特征输入到预先训练的视频推荐模型，得到所述视频推荐模型输出的对应用户群体的标识；
将所述标识对应的用户群体，确定为所述视频封面对应的用户群体。
本申请的实施例中，每一个用户群体都对应设有一个标识，例如，用户群体A对应标识0x1，用户群体B对应标识0x2，用户群体C对应标识0x3。
在一些实施例中，所述视频推荐模型是预先训练的，所述视频推荐模型可以在电子设备、服务器或终端上进行训练。其中所述视频推荐模型的训练方法包括：
(1)获取训练样本集，所述训练样本集中的每一训练样本包括：视频的视频特征、视频封面的封面特征、以及用户群体的标识；
其中，训练样本集可以通过如下方式获得：
获取视频推荐历史记录信息，视频推荐历史记录信息包括大量的视频推荐数据，每一条视频推荐数据记录了用户将添加有某一视频封面的某一视频推荐给某一用户群体；
对于每一条视频推荐数据，根据该视频推荐数据，获取视频的视频特征，视频封面的封面特征，以及确定添加有该视频封面的该视频所推荐给的用户群体的标识，即可以得到一个训练样本。
(2)通过所述训练样本集，对待训练模型进行训练，得到所述视频推荐模型。
在另一些实施例中，步骤S203中根据所述视频特征和所述封面特征，确定所述视频封面对应的用户群体，包括：
根据所述视频特征，确定所述视频对应的用户群体组，所述用户群体组包括至少两个用户群体；
根据所述封面特征，从所述用户群体组中确定所述视频封面对应的用户群体。
例如，某一视频10，确定该视频的视频封面集包括视频封面a、视频封面b和视频封面c，该视频的视频特征包括游戏，查找游戏对应的用户群体，确定该视频可以推荐给包括用户群体A、用户群体B和用户群体C的用户群体组，再根据各个视频封面的封面特征(比如封面风格)，分别确定视频封面a对应用户群体A，视频封面b对应用户群体B，视频封面c对应用户群体C，也就是说，添加有视频封面a的视频10可以推荐给用户群体A，添加有视频封面b视频10可以推荐给用户群体B，添加有视频封面c视频10可以推荐给用户群体C，如图5所示。
S204、为所述目标视频添加所述视频封面，并将添加有所述视频封面的所述目标视频推荐给所述用户群体。
在一些实施例中，响应于接收到客户端发送的目标视频和视频封面集，该方法还包括：
根据设定的筛选策略对所述目标视频和所述视频封面集中的视频封面进行验证；
响应于所述目标视频通过验证，对于所述视频封面集中的任一通过验证的视频封面，执行获取所述目标视频的视频特征，以及获取所述视频封面的封面特征的步骤。
其中，筛选策略例如可以包括过滤具有负向标签(例如内容敏感，被举报等)的视频封面、过滤违反法律法规的视频(例如暴力视频、色情视频)。
本公开实施例提供的技术方案，首先接收客户端发送的目标视频和视频封面集，然后对于所述视频封面集中的任一视频封面，获取所述目标视频的视频特征，以及获取所述视频封面的封面特征，并根据所述视频特征和所述封面特征，确定所述视频封面对应的用户群体，之后，为所述目标视频添加所述视频封面，并将添加有所述视频封面的所述目标视频推荐给所述用户群体，实现了在用户不同的情况下，可以为视频添加不同的视频封面，从而可以为用户提供其感兴趣的视频封面，因此可以解决视频封面单一的问题。
在一些实施例中，本公开实施例还提供了一种视频推荐装置，图6是根据一些实施例示出的一种视频推荐装置的框图。参照图6，该视频推荐装置用于客户端中，该视频推荐装置包括：相关视频获取模块11、视频封面集生成模块12和发送模块13。
相关视频获取模块11，被配置为获取目标视频的至少两个相关视频；
视频封面集生成模块12，被配置为对于每一所述相关视频，查找与所述相关视频关联的视频封面，其中，所述视频封面是根据用户对所述相关视频执行操作的行为信息确定的，并将查找到的所述视频封面添加到视频封面集，所述视频封面集包括至少两个视频封面；
发送模块13，被配置为将所述目标视频和所述视频封面集发送给服务器，以使服务器基于所述视频封面集，为所述目标视频添加不同的视频封面并推荐给不同的用户群体，所述用户群体包括至少一个用户。
在一些实施例中，与所述相关视频关联的视频封面为热度最高的视频封面；
如图7所示，上述视频推荐装置还包括：
行为信息获取模块14，被配置为获取用户对相关视频执行操作的行为信息；
热度确定模块15，被配置为基于所述行为信息，分别确定所述相关视频对应的各个视频封面的热度；
关联模块16，被配置为从所述相关视频对应的所有视频封面中查找热度最高的视频封面，并关联所述相关视频与所述热度最高的视频封面。
在一些实施例中，热度确定模块15被配置为：
对于所述相关视频对应的每一视频封面，根据用户对添加有所述视频封面的所述相关视频执行操作的行为信息，确定所述视频封面的热度。
在一些实施例中，本公开实施例还提供了一种视频推荐装置，图8是根据一些实施例示出的一种视频推荐装置的框图。参照图8，该视频推荐装置用于服务器中，该视频推荐装置包括：接收模块21、特征获取模块22、用户群体确定模块23和处理模块24。
在一些实施例中，用户群体确定模块23被配置为：
将所述视频特征和所述封面特征输入到预先训练的视频推荐模型，得到所述视频推荐模型输出的对应用户群体的标识；
将所述标识对应的用户群体，确定为所述视频封面对应的用户群体。
在一些实施例中，用户群体确定模块23被配置为：
根据所述视频特征，确定所述目标视频对应的用户群体组，所述用户群体组包括至少两个用户群体；
根据所述封面特征，从所述用户群体组中确定所述视频封面对应的用户群体。
在一些实施例中，如图9所示，上述视频推荐装置还包括：
校验模块25，被配置为根据设定的筛选策略对所述目标视频和所述视频封面集中的视频封面进行验证；
特征获取模块22被配置为：
响应于所述目标视频通过所述校验模块25的验证，对于所述视频封面集中的任一通过所述校验模块25的验证的视频封面，执行获取所述目标视频的视频特征，以及获取所述视频封面的封面特征的步骤。
上述装置中各个单元的功能和作用的实现过程具体详见上述方法中对应步骤的实现过程，在此不再赘述。
对于装置实施例而言，由于其基本对应于方法实施例，所以相关之处参见方法实施例的部分说明即可。以上所描述的装置实施例仅仅是示意性的，其中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模块来实现本公开方案的目的。本领域普通技术人员在不付出创造性劳动的情况下，即可以理解并实施。
在一些实施例中，本公开实施例还提供了一种存储介质，其上存储有计算机程序，该程序被处理器执行时实现上述任意可能的实现方式中的视频推荐方法的步骤。
在一些实施例中，存储介质可以是非临时性计算机可读存储介质，例如，所述非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
在一些实施例中，本公开实施例还提供了一种计算机程序产品，包括计算机程序，所述程序被处理器执行时实现上述任意可能的实现方式中的视频推荐方法的步骤。
在一些实施例中，本公开实施例还提供了一种终端，包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序；
其中，所述处理器被配置为：
获取目标视频的至少两个相关视频；
对于每一所述相关视频，查找与所述相关视频关联的视频封面，其中，所述视频封面是根据用户对所述相关视频执行操作的行为信息确定的，并将查找到的所述视频封面添加到视频封面集，所述视频封面集包括至少两个视频封面；
将所述目标视频和所述视频封面集发送给服务器，以使服务器基于所述视频封面集， 为所述目标视频添加不同的视频封面并推荐给不同的用户群体，所述用户群体包括至少一个用户。
如图10所示，图10是本公开根据一些实施例示出的一种终端1700的一结构示意图。例如，终端1700可以是具有路由功能的移动电话，计算机，数字广播终端，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理等。
参照图10，终端1700可以包括以下一个或多个组件：处理组件1702，存储器1704，电源组件1706，多媒体组件1708，音频组件1710，输入/输出(I/O)的接口1712，传感器组件1714，以及通信组件1716。
处理组件1702通常控制终端1700的整体操作，诸如与显示，电话呼叫，数据通信，相机操作和记录操作相关联的操作。处理组件1702可以包括一个或多个处理器1720来执行指令，以完成上述的方法的全部或部分步骤。此外，处理组件1702可以包括一个或多个模块，便于处理组件1702和其他组件之间的交互。例如，处理组件1702可以包括多媒体模块，以方便多媒体组件1708和处理组件1702之间的交互。
存储器1704被配置为存储各种类型的数据以支持在终端1700的操作。这些数据的示例包括用于在终端1700上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器1704可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
电源组件1706为终端1700的各种组件提供电力。电源组件1706可以包括电源管理系统，一个或多个电源，及其他与为终端1700生成、管理和分配电力相关联的组件。
多媒体组件1708包括在所述终端1700和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件1708包括一个前置摄像头和/或后置摄像头。当终端1700处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件1710被配置为输出和/或输入音频信号。例如，音频组件1710包括一个麦克风(MIC)，当终端1700处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器1704或经由通信组件1716发送。在一些实施例中，音频组件1710还包括一个扬声器，用于输出音频信号。
I/O接口1712为处理组件1702和外围接口模块之间提供接口，上述外围接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件1714包括一个或多个传感器，用于为终端1700提供各个方面的状态评估。例如，传感器组件1714可以检测到终端1700的打开/关闭状态，组件的相对定位，例如所述组件为终端1700的显示器和小键盘，传感器组件1714还可以检测终端1700或终端1700一个组件的位置改变，用户与终端1700接触的存在或不存在，终端1700方位或加速/减速和终端1700的温度变化。传感器组件1714可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件1714还可以包括光传感器，如CMOS或CCD图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件1714还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器，微波传感器或温度传感器。
通信组件1716被配置为便于终端1700和其他设备之间有线或无线方式的通信。终端1700可以接入基于通信标准的无线网络，如WiFi，2G或3G，或它们的组合。在一个示例性实施例中，通信组件1716经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信组件1716还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
在示例性实施例中，终端1700可以被一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行如图3所示的视频推荐方法。
在一些实施例中，还提供了一种包括指令的非临时性计算机可读存储介质，例如包括指令的存储器1704，上述指令可由终端1700的处理器1720执行以完成上述方法。例如，所述非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
在一些实施例中，，本公开实施例还提供了一种服务器，包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序；
其中，所述处理器被配置为：
接收客户端发送的目标视频和视频封面集，所述视频封面集包括至少两个视频封面；
对于所述视频封面集中的任一视频封面，获取所述目标视频的视频特征，以及获取所述视频封面的封面特征；其中，所述视频特征包括视频的类型，所述封面特征包括封面风格；
根据所述视频特征和所述封面特征，确定所述视频封面对应的用户群体，所述用户群 体包括至少一个用户；
为所述目标视频添加所述视频封面，并将添加有所述视频封面的所述目标视频推荐给所述用户群体。
如图11所示，图11是根据一些实施例示出的一种服务器1800的一结构示意图。参照图11，服务器1800包括处理组件1802，其进一步包括一个或多个处理器，以及由存储器1804所代表的存储器资源，用于存储可由处理组件1802的执行的指令，例如应用程序。存储器1804中存储的应用程序可以包括一个或一个以上的每一个对应于一组指令的模块。此外，处理组件1802被配置为执行指令，以执行如图4所示的视频推荐方法。
服务器1800还可以包括一个电源组件1806，被配置为执行服务器1800的电源管理，一个有线或无线网络接口1808，被配置为将服务器1800连接到网络，和一个输入输出(I/O)接口1810。服务器1800可以操作基于存储在存储器1804的操作系统，例如Windows ServerTM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTM或类似。
本公开所有实施例均可以单独被执行，也可以与其他实施例相结合被执行，均视为本公开要求的保护范围。
本领域技术人员在考虑说明书及实践这里公开的发明后，将容易想到本公开的其它实施方案。本公开旨在涵盖本公开的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本公开的真正范围和精神由所附的权利要求指出。
应当理解的是，本公开并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利要求来限制。

Claims (22)

  1. 一种视频推荐方法，应用于终端，所述方法包括：
    获取目标视频的至少两个相关视频；
    对于每一所述相关视频，查找与所述相关视频关联的视频封面，其中，所述视频封面是根据用户对所述相关视频执行操作的行为信息确定的；
    将所述视频封面添加到视频封面集，所述视频封面集包括多个视频封面；
    将所述目标视频和所述视频封面集发送给服务器，其中，所述服务器基于所述视频封面集和不同的用户群体为所述目标视频添加不同的视频封面。
  2. 根据权利要求1所述的方法，其中，所述查找与所述相关视频关联的视频封面包括：
    获取用户对相关视频执行操作的行为信息；
    基于所述行为信息，分别确定所述相关视频对应的各个视频封面的热度；
    从所述相关视频对应的所有视频封面中确定热度最高的视频封面，并关联所述相关视频与所述热度最高的视频封面。
  3. 根据权利要求2所述的方法，其中，所述基于所述行为信息，分别确定所述相关视频对应的各个视频封面的热度，包括：
    对于所述相关视频对应的每一视频封面，根据用户对添加有所述视频封面的所述相关视频执行操作的行为信息，确定所述视频封面的热度。
  4. 一种视频推荐方法，应用于服务器，所述方法包括：
    接收终端发送的目标视频和视频封面集，所述视频封面集包括多个视频封面；
    对于所述视频封面集中的任一视频封面，获取所述目标视频的视频特征和所述视频封面的封面特征；其中，所述视频特征包括视频的类型，所述封面特征包括封面风格；
    根据所述视频特征和所述封面特征，确定所述视频封面对应的用户群体；
    为所述目标视频添加所述视频封面，并将添加有所述视频封面的所述目标视频推荐给所述用户群体。
  5. 根据权利要求4所述的方法，其中，所述根据所述视频特征和所述封面特征，确定所述视频封面对应的用户群体，包括：
    将所述视频特征和所述封面特征输入到预先训练的视频推荐模型，得到所述视频推荐模型输出的对应用户群体的标识；
    将所述标识对应的用户群体，确定为所述视频封面对应的用户群体。
  6. 根据权利要求4所述的方法，其中，所述根据所述视频特征和所述封面特征，确定所述视频封面对应的用户群体，包括：
    根据所述视频特征，确定所述目标视频对应的用户群体组，所述用户群体组包 括至少两个用户群体；
    根据所述封面特征，从所述用户群体组中确定所述视频封面对应的用户群体。
  7. 根据权利要求4所述的方法，其中，响应于接收到客户端发送的目标视频和视频封面集，该方法还包括：
    对所述目标视频和所述视频封面集中的视频封面进行验证；
    响应于所述目标视频通过验证，获取所述目标视频的视频特征和所述视频封面的封面特征。
  8. 一种视频推荐装置，应用于终端，所述装置包括：
    相关视频获取模块，被配置为获取目标视频的至少两个相关视频；
    视频封面集生成模块，被配置为对于每一所述相关视频，查找与所述相关视频关联的视频封面，其中，所述视频封面是根据用户对所述相关视频执行操作的行为信息确定的，并将所述视频封面添加到视频封面集，所述视频封面集包括至少两个视频封面；
    发送模块，被配置为将所述目标视频和所述视频封面集发送给服务器，其中，所述服务器基于所述视频封面集和不同的用户群体为所述目标视频添加不同的视频封面。
  9. 根据权利要求8所述的装置，其中，
    所述装置还包括：
    行为信息获取模块，被配置为获取用户对相关视频执行操作的行为信息；
    热度确定模块，被配置为基于所述行为信息，分别确定所述相关视频对应的各个视频封面的热度；
    关联模块，被配置为从所述相关视频对应的所有视频封面中确定热度最高的视频封面，并关联所述相关视频与所述热度最高的视频封面。
  10. 根据权利要求9所述的装置，其中，所述热度确定模块被配置为：
    对于所述相关视频对应的每一视频封面，根据用户对添加有所述视频封面的所述相关视频执行操作的行为信息，确定所述视频封面的热度。
  11. 一种视频推荐装置，应用于服务器，所述装置包括：
    接收模块，被配置为接收终端发送的目标视频和视频封面集，所述视频封面集包括多个视频封面；
    特征获取模块，被配置为对于所述视频封面集中的任一视频封面，获取所述目标视频的视频特征和所述视频封面的封面特征；其中，所述视频特征包括视频的类型，所述封面特征包括封面风格；
    用户群体确定模块，被配置为根据所述视频特征和所述封面特征，确定所述视频封面对应的用户群体；
    处理模块，被配置为为所述目标视频添加所述视频封面，并将添加有所述视频封面的所述目标视频推荐给所述用户群体。
  12. 根据权利要求11所述的装置，其中，所述用户群体确定模块被配置为：
    将所述视频特征和所述封面特征输入到预先训练的视频推荐模型，得到所述视频推荐模型输出的对应用户群体的标识；
    将所述标识对应的用户群体，确定为所述视频封面对应的用户群体。
  13. 根据权利要求11所述的装置，其中，所述用户群体确定模块被配置为：
    根据所述视频特征，确定所述目标视频对应的用户群体组，所述用户群体组包括至少两个用户群体；
    根据所述封面特征，从所述用户群体组中确定所述视频封面对应的用户群体。
  14. 根据权利要求11所述的装置，其中，所述装置还包括：
    校验模块，被配置为对所述目标视频和所述视频封面集中的视频封面进行验证；
    所述特征获取模块被配置为：
    响应于所述目标视频通过所述校验模块的验证，获取所述目标视频的视频特征和所述视频封面的封面特征。
  15. 一种非暂态存储介质，其上存储有计算机程序，所述程序被处理器执行时实现权利要求1-7任一项所述方法的步骤。
  16. 一种终端，包括：
    处理器；以及
    存储器，其上存储有可在所述处理器上运行的计算机程序，其中，所述处理器被配置为执行所述计算机程序以实现如下步骤：
    获取目标视频的至少两个相关视频；
    对于每一所述相关视频，查找与所述相关视频关联的视频封面，其中，所述视频封面是根据用户对所述相关视频执行操作的行为信息确定的，并将所述视频封面添加到视频封面集，所述视频封面集包括多个视频封面；
    将所述目标视频和所述视频封面集发送给服务器，其中，所述服务器基于所述视频封面集和不同的用户群体为所述目标视频添加不同的视频封面。
  17. 根据权利要求16所述的终端，其中，
    所述处理器进一步被配置为:
    获取用户对相关视频执行操作的行为信息；
    基于所述行为信息，分别确定所述相关视频对应的各个视频封面的热度；
    从所述相关视频对应的所有视频封面中确定热度最高的视频封面，并关联所述相关视频与所述热度最高的视频封面。
  18. 根据权利要求17所述的终端，其中，所述处理器进一步被配置为：
    对于所述相关视频对应的每一视频封面，根据用户对添加有所述视频封面的所述相关视频执行操作的行为信息，确定所述视频封面的热度。
  19. 一种服务器，包括：
    处理器；以及
    存储器，其上存储有可在所述处理器上运行的计算机程序，其中，所述处理器被配置为执行所述计算机程序以实现如下步骤：
    接收客户端发送的目标视频和视频封面集，所述视频封面集包括多个视频封面；
    对于所述视频封面集中的任一视频封面，获取所述目标视频的视频特征和所述视频封面的封面特征；其中，所述视频特征包括视频的类型，所述封面特征包括封面风格；
    根据所述视频特征和所述封面特征，确定所述视频封面对应的用户群体；
    为所述目标视频添加所述视频封面，并将添加有所述视频封面的所述目标视频推荐给所述用户群体。
  20. 根据权利要求19所述的服务器，其中，所述处理器被配置为：
    将所述视频特征和所述封面特征输入到预先训练的视频推荐模型，得到所述视频推荐模型输出的对应用户群体的标识；
    将所述标识对应的用户群体，确定为所述视频封面对应的用户群体。
  21. 根据权利要求19所述的服务器，其中，所述处理器被配置为：
    根据所述视频特征，确定所述目标视频对应的用户群体组，所述用户群体组包括至少两个用户群体；
    根据所述封面特征，从所述用户群体组中确定所述视频封面对应的用户群体。
  22. 根据权利要求19所述的服务器，其中，所述处理器进一步被配置为：
    对所述目标视频和所述视频封面集中的视频封面进行验证；以及
    响应于所述目标视频通过所述校验模块的验证，获取所述目标视频的视频特征和所述视频封面的封面特征。
PCT/CN2021/073044 2020-01-21 2021-01-21 视频推荐方法及装置 WO2021147949A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/842,270 US11546663B2 (en) 2020-01-21 2022-06-16 Video recommendation method and apparatus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010072107.2 2020-01-21
CN202010072107.2A CN111246255B (zh) 2020-01-21 2020-01-21 视频推荐方法、装置、存储介质、终端及服务器

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/842,270 Continuation US11546663B2 (en) 2020-01-21 2022-06-16 Video recommendation method and apparatus

Publications (1)

Publication Number Publication Date
WO2021147949A1 true WO2021147949A1 (zh) 2021-07-29

Family

ID=70871428

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/073044 WO2021147949A1 (zh) 2020-01-21 2021-01-21 视频推荐方法及装置

Country Status (3)

Country Link
US (1) US11546663B2 (zh)
CN (1) CN111246255B (zh)
WO (1) WO2021147949A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111246255B (zh) * 2020-01-21 2022-05-06 北京达佳互联信息技术有限公司 视频推荐方法、装置、存储介质、终端及服务器
CN112035196A (zh) * 2020-08-04 2020-12-04 北京达佳互联信息技术有限公司 视频封面的处理方法、装置、电子设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105120336A (zh) * 2015-09-23 2015-12-02 联想(北京)有限公司 一种信息处理方法及电子设备
US20170078707A1 (en) * 2015-09-14 2017-03-16 Alan H. Barber System, device, and method for providing audiences for live video streaming
CN106547767A (zh) * 2015-09-18 2017-03-29 北京国双科技有限公司 确定视频封面图片的方法及装置
CN110572711A (zh) * 2019-09-27 2019-12-13 北京达佳互联信息技术有限公司 视频封面生成方法、装置、计算机设备及存储介质
CN111246255A (zh) * 2020-01-21 2020-06-05 北京达佳互联信息技术有限公司 视频推荐方法、装置、存储介质、终端及服务器

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
ITTO20120867A1 (it) * 2012-10-05 2014-04-06 Rai Radiotelevisione Italiana Metodo e sistema per la raccomandazione di contenuti multimediali su una piattaforma multimediale
US9883245B2 (en) * 2015-08-31 2018-01-30 Opentv, Inc. Systems and methods for enabling a user to generate a plan to access content using multiple content services
CN105893423A (zh) * 2015-12-03 2016-08-24 乐视网信息技术（北京）股份有限公司 视频推荐方法、系统、终端以及服务器
CN108804452B (zh) * 2017-04-28 2021-06-04 阿里巴巴（中国）有限公司 多媒体资源封面展示方法及装置
CN109660854B (zh) * 2017-10-10 2021-08-24 腾讯科技（深圳）有限公司 视频推荐方法、装置、设备和存储介质
CN107958030B (zh) * 2017-11-17 2021-08-24 北京奇虎科技有限公司 视频封面推荐模型优化方法及装置
CN108650524B (zh) * 2018-05-23 2022-08-16 腾讯科技（深圳）有限公司 视频封面生成方法、装置、计算机设备及存储介质
CN109996091A (zh) * 2019-03-28 2019-07-09 苏州八叉树智能科技有限公司 生成视频封面的方法、装置、电子设备和计算机可读存储介质
CN110046263B (zh) * 2019-04-23 2023-08-18 腾讯音乐娱乐科技（深圳）有限公司 多媒体推荐方法、装置、服务器及存储介质
CN110602564B (zh) * 2019-10-12 2022-04-15 北京字节跳动网络技术有限公司 视频优化信息提供方法、装置、电子设备及可读介质
CN113132753A (zh) * 2019-12-30 2021-07-16 阿里巴巴集团控股有限公司 数据处理方法及装置、视频封面生成方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170078707A1 (en) * 2015-09-14 2017-03-16 Alan H. Barber System, device, and method for providing audiences for live video streaming
CN106547767A (zh) * 2015-09-18 2017-03-29 北京国双科技有限公司 确定视频封面图片的方法及装置
CN105120336A (zh) * 2015-09-23 2015-12-02 联想(北京)有限公司 一种信息处理方法及电子设备
CN110572711A (zh) * 2019-09-27 2019-12-13 北京达佳互联信息技术有限公司 视频封面生成方法、装置、计算机设备及存储介质
CN111246255A (zh) * 2020-01-21 2020-06-05 北京达佳互联信息技术有限公司 视频推荐方法、装置、存储介质、终端及服务器

Also Published As

Publication number Publication date
US20220312077A1 (en) 2022-09-29
CN111246255A (zh) 2020-06-05
US11546663B2 (en) 2023-01-03
CN111246255B (zh) 2022-05-06

Similar Documents

Publication Publication Date Title
CN105426152B (zh) 弹幕的显示方法和装置
US11520824B2 (en) Method for displaying information, electronic device and system
US20210314639A1 (en) Method and apparatus for recommending live streaming room
CN106874308B (zh) 一种推荐方法和装置、一种用于推荐的装置
CN104166689B (zh) 电子书籍的呈现方法及装置
WO2015196709A1 (zh) 信息获取方法及装置
WO2017157040A1 (zh) 搜索方法、装置以及用于搜索的装置
CN107784045B (zh) 一种快捷回复方法和装置、一种用于快捷回复的装置
CN110688527A (zh) 视频推荐方法、装置、存储介质及电子设备
CN109783656B (zh) 音视频数据的推荐方法、系统及服务器和存储介质
CN109918565B (zh) 一种搜索数据的处理方法、装置及电子设备
CN107315487A (zh) 一种输入处理方法、装置及电子设备
CN107346316A (zh) 一种搜索方法、装置及电子设备
US11546663B2 (en) Video recommendation method and apparatus
CN108460651A (zh) 车辆推荐方法及装置
CN112445970A (zh) 一种信息推荐方法、装置、电子设备及存储介质
CN106777016B (zh) 基于即时通信进行信息推荐的方法及装置
CN105373580A (zh) 主题显示方法及装置
CN106815291B (zh) 搜索结果项展现方法、装置和用于搜索结果项展现的装置
CN113901241B (zh) 页面展示方法、装置、电子设备及存储介质
CN111241844B (zh) 一种信息推荐方法及装置
CN113239183B (zh) 排序模型的训练方法、装置、电子设备和存储介质
CN106960026B (zh) 搜索方法、搜索引擎和电子设备
CN111368161A (zh) 一种搜索意图的识别方法、意图识别模型训练方法和装置
CN110110046B (zh) 同名实体推荐方法及装置

Legal Events

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

Ref document number: 21743629

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: 21743629

Country of ref document: EP

Kind code of ref document: A1