WO2019001153A1 - Multi-viewer television program recommendation method and system - Google Patents

Multi-viewer television program recommendation method and system Download PDF

Info

Publication number
WO2019001153A1
WO2019001153A1 PCT/CN2018/086718 CN2018086718W WO2019001153A1 WO 2019001153 A1 WO2019001153 A1 WO 2019001153A1 CN 2018086718 W CN2018086718 W CN 2018086718W WO 2019001153 A1 WO2019001153 A1 WO 2019001153A1
Authority
WO
WIPO (PCT)
Prior art keywords
viewer
program
television program
television
same
Prior art date
Application number
PCT/CN2018/086718
Other languages
French (fr)
Chinese (zh)
Inventor
朱晓君
Original Assignee
深圳市九洲电器有限公司
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 深圳市九洲电器有限公司 filed Critical 深圳市九洲电器有限公司
Publication of WO2019001153A1 publication Critical patent/WO2019001153A1/en

Links

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
    • H04N21/258—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
    • H04N21/251—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
    • H04N21/25866—Management of end-user data
    • H04N21/25875—Management of end-user data involving end-user authentication
    • 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
    • H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
    • H04N21/26258—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists for generating a list of items to be played back in a given order, e.g. playlist, or scheduling item distribution according to such list
    • 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
    • H04N21/441—Acquiring end-user identification, e.g. using personal code sent by the remote control or by inserting a card
    • 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
    • H04N21/4508—Management of client data or end-user data
    • H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, 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]
    • H04N21/40—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
    • H04N21/458—Scheduling content for creating a personalised stream, e.g. by combining a locally stored advertisement with an incoming stream; Updating operations, e.g. for OS modules ; time-related management operations
    • 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 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

Definitions

  • the present invention relates to the field of digital television, and in particular, to a multi-viewer television program recommendation method and system.
  • the viewer's TV program preferences are usually obtained according to the viewer's historical viewing history, and the TV program is recommended for the viewer according to the TV program preferences, so that the viewer's selection time can be saved according to the viewer's interest preferences.
  • the invention provides a multi-viewer television program recommendation method, comprising the following steps:
  • S30 Perform statistics on the TV programs in the current favorite program list, and count the number of times the same TV program and the same TV program;
  • S40 Reorder the same television programs from high to low according to the number of times of the same television program, and recommend the television program to the current audience according to the order.
  • step S10 is specifically: capturing the front area by the camera of the digital television device and performing face recognition, and identifying the audience in the front area by the face recognition technology, thereby acquiring the audience identity information.
  • step S10 further includes: after the face is recognized by the face, the recognized audience is displayed in a list for the viewer to confirm and change; if the identified number of viewers is different from the actual number of viewers, the viewer is notified Make changes; for unrecognizable faces, display the unrecognizable face screenshots, prompting the viewer to confirm the face identity information.
  • the step S40 further includes: for the TV program with the same number of times, acquiring the type of the TV program with the same number of times, and comparing with the program type of the top TV program, and ranking the TV programs with the same program type as the front.
  • step S40 further includes: if the number of times is the same and the program type is the same, comparing the playing time of the television program, and ranking the television programs with the playing time close to the front.
  • the invention provides a multi-viewer television program recommendation system, comprising:
  • An identity information obtaining unit which acquires audience identity information of a viewer currently watching a television program
  • a favorite program list obtaining unit which acquires a favorite program list of each viewer according to the viewer identity information
  • the television program statistics unit counts the television programs in the current viewer favorite program list, and counts the number of times of the same television program and the same television program;
  • the ranking recommendation unit reorders the same television programs from high to low according to the number of times of the same television program, and recommends the television programs to the current audience according to the order.
  • the identity information acquiring unit captures the front area through the camera of the digital television device and performs face recognition, and recognizes the audience in the front area through the face recognition technology, thereby acquiring the audience identity information.
  • the identity information acquiring unit displays the identified viewers for the viewer to confirm and change; if the identified number of viewers is different from the actual number of viewers, the viewer is notified Change; for unrecognizable faces, a screenshot of the face that cannot be recognized is displayed, prompting the viewer to confirm the face identity information.
  • the ranking recommendation unit acquires the types of television programs of the same number of times, and compares them with the program types of the television programs that are ranked first, and ranks the television programs with the same program type in the front.
  • the sorting recommendation unit compares the playing time of the television program, and ranks the television programs with the playing time close to the front.
  • the multi-viewer television program recommendation method and system of the present invention acquires the identity information of a plurality of viewers and the corresponding favorite program list when a plurality of viewers currently watch the television program at the same time, and counts the number of times of the same television program and the same television program. Sorting according to the number of times, recommending the TV program to the current plurality of viewers according to the order, so that the common favorite programs of the plurality of viewers are combined to recommend the TV program, thereby satisfying the needs of the plurality of viewers, and bringing great interest to the viewers. Convenience and a good viewing experience.
  • FIG. 1 is a flow chart of a multi-viewer television program recommendation method in an embodiment
  • FIG. 2 is a structural diagram of a multi-viewer television program recommendation system in one embodiment.
  • FIG. 1 is a flow chart of a multi-viewer television program recommendation method in an embodiment. As shown in FIG. 1, the method includes the following steps:
  • Step S10 Acquire viewer identity information of the viewer currently watching the television program.
  • the step is specifically: shooting the front area through the camera of the digital television device and performing Face recognition, through the face recognition technology to identify the audience in the front area, and then obtain the audience identity information.
  • the identified viewers are also displayed in a list for the viewer to confirm and change. If the number of identified viewers differs from the actual number of viewers, the viewer is notified to make changes. For faces that cannot be recognized, a screenshot of the face that cannot be recognized is displayed, prompting the viewer to confirm the face identity information.
  • Step S20 Acquire a favorite program list of each viewer according to the viewer identity information.
  • each viewer identity information ie, each viewer's ID
  • each viewer's identity information may be used to obtain a corresponding favorite program list to understand each viewer's Love the show.
  • Step S30 Perform statistics on the TV programs in the current favorite program list, and count the number of times the same TV program and the same TV program.
  • the step counts the current TV program in the favorite program list, counts the number of the same TV program and the same TV program, and knows the common preferences of the current plurality of viewers.
  • a plurality of favorite program lists if there is a certain television program, such as a variety show or a hit TV show, it means that a plurality of viewers like the TV program.
  • the more favorite programs appearing in the television program that is, the more the number of times, the more viewers are favorite.
  • Step S40 Reorder the same television programs from high to low according to the number of times of the same television program, and recommend the television program to the current audience according to the order.
  • the TV program After counting the number of times the TV program is in the favorite program list, it sorts according to the number of times from high to low, so that the more the TV programs that the viewers like together are ranked higher, and then the TV programs are recommended to the current plurality of viewers according to the order. Thereby, it is possible to better satisfy a plurality of viewers at the current moment.
  • the types of TV programs with the same number of times are acquired, and compared with the program types of the top TV programs, the TV programs with the same program type are sorted. before. If the number of times is the same and the program type is the same, the playing time of the television program is compared, and the television programs with the short playing time are ranked first.
  • the multi-viewer television program recommendation method acquires the identity information of the plurality of viewers and the corresponding favorite program list when a plurality of viewers currently watch the television program at the same time, and counts the number of times of the same television program and the same television program, according to the number of times Sorting, recommending TV programs to a plurality of current viewers according to sorting, so that a plurality of viewers' favorite programs are integrated to recommend TV programs, thereby satisfying the needs of a plurality of viewers, and bringing great convenience and good viewing to the viewers. Viewing experience.
  • the present invention also provides a multi-viewer television program recommendation system, as shown in FIG. 2, the system includes:
  • the identity information obtaining unit 100 acquires audience identity information of the viewer currently watching the television program.
  • the identity information acquiring unit 100 photographs and performs the front area through the camera of the digital television device. Face recognition, through the face recognition technology to identify the audience in the front area, and then obtain the audience identity information.
  • the identity information acquiring unit 100 since the face recognition has certain inaccuracy, after the face recognizes the viewer, the identity information acquiring unit 100 also displays the identified viewers for the viewer to confirm and change. If the number of recognized viewers differs from the actual number of viewers, the identity information acquisition unit 100 notifies the viewer to make the change. For the unrecognizable face, the identity information acquiring unit 100 displays the unrecognizable face screenshot, and prompts the viewer to confirm the face identity information.
  • the favorite program list obtaining unit 200 acquires a favorite program list of each viewer based on the viewer identity information.
  • each viewer identity information ie, each viewer's ID
  • each viewer's identity information may be used to obtain a corresponding favorite program list to understand each viewer's Love the show.
  • the television program statistics unit 300 collects statistics on the television programs in the current viewer favorite program list, and counts the number of times the same television program and the same television program.
  • the television program statistics unit 300 counts the television programs in the current viewer favorite program list, counts the number of the same television program and the same television program, and knows the common preferences of the current plurality of viewers.
  • a plurality of favorite program lists if there is a certain television program, such as a variety show or a hit TV show, it means that a plurality of viewers like the TV program.
  • the more favorite programs appearing in the television program that is, the more the number of times, the more viewers are favorite.
  • the ranking recommendation unit 400 reorders the same television programs from high to low according to the number of times of the same television program, and recommends the television programs to the current audience in order.
  • the ranking recommendation unit 400 sorts according to the number of times from high to low, so that the more the TV programs that the viewers like together are ranked higher, and then the recommended television programs are given to the current order. Multiple viewers, thus being able to better meet multiple viewers at the current moment.
  • the sorting recommending unit 400 acquires the types of television programs of the same number of times, and compares them with the program types of the ranked top TV programs, and the program types are consistent. TV shows are ranked first. If the number of times is the same and the program type is the same, the sort recommendation unit 400 compares the play time of the television program, and ranks the television programs with the near play time in the front.
  • the multi-viewer television program recommendation system acquires the identity information of the plurality of viewers and the corresponding favorite program list when a plurality of viewers currently watch the television program at the same time, and counts the number of times of the same television program and the same television program, according to the number of times. Sorting, recommending TV programs to a plurality of current viewers according to sorting, so that a plurality of viewers' favorite programs are integrated to recommend TV programs, thereby satisfying the needs of a plurality of viewers, and bringing great convenience and good viewing to the viewers. Viewing experience.

Abstract

The present solution relates to a multi-viewer television program recommendation method and system. The method comprises: if there are multiple viewers currently watching a television program at the same time, acquiring identity information and corresponding favorite program lists of the multiple viewers, performing computation to obtain identical television programs and counts of the identical television programs, sorting the same according to the counts, and providing, according to the sorting, a television program recommendation to the multiple current viewers. In this way, the present invention combines identical favorite programs of multiple viewers to recommend a television program, thus meeting the demand of the multiple viewers, and providing great convenience and superior viewer experience to the viewers.

Description

多观众电视节目推荐方法及系统Multi-viewer television program recommendation method and system 技术领域Technical field
本发明涉及数字电视领域，尤其涉及一种多观众电视节目推荐方法及系统。The present invention relates to the field of digital television, and in particular, to a multi-viewer television program recommendation method and system.
背景技术Background technique
目前，电视节目众多，观众可选择各种电视节目进行观看。但是众多的电视节目也给观众选择带来了麻烦，观众需要花费较多时间在电视节目的挑选上。At present, there are many TV programs, and viewers can choose various TV programs for viewing. However, many TV programs have also caused trouble for viewers to choose, and viewers need to spend more time on the selection of TV programs.
为节省观众选择电视节目的时间，通常会根据观众的历史观看记录来获得观众的电视节目喜好，根据电视节目喜好来为观众推荐电视节目，这样可以根据观众的兴趣喜好来节省观众的选择时间。In order to save the time for the viewer to select the TV program, the viewer's TV program preferences are usually obtained according to the viewer's historical viewing history, and the TV program is recommended for the viewer according to the TV program preferences, so that the viewer's selection time can be saved according to the viewer's interest preferences.
但是，这种电视节目喜好的获得大都是根据某段时期内某个观众的观看记录来统计的，当有多个观众（比如，家庭中多个成员）同时观看电视节目时，根据某个观众的喜好推荐的电视节目并不能满足多个观众的要求，这就给观众观看带来不便，降低了观众的观看体验。However, the popularity of such TV shows is mostly based on the watch records of a certain audience during a certain period of time. When there are multiple viewers (for example, multiple members in the family) watching TV programs simultaneously, according to a certain audience. The recommended TV program does not meet the requirements of multiple viewers, which brings inconvenience to viewers and reduces the viewer's viewing experience.
技术问题technical problem
有鉴于此，有必要针对上述根据某个观众的喜好推荐电视节目不能满足多个观众要求的问题，提供一种多观众电视节目推荐方法及系统。In view of this, it is necessary to provide a multi-viewer television program recommendation method and system for the above problem of recommending that a television program cannot satisfy a plurality of viewers according to a viewer's preference.
技术解决方案Technical solution
本发明提供的一种多观众电视节目推荐方法，包括如下步骤：The invention provides a multi-viewer television program recommendation method, comprising the following steps:
S10：获取当前观看电视节目观众的观众身份信息；S10: Acquire viewer identity information of a viewer currently watching a television program;
S20：根据观众身份信息获取每个观众的喜爱节目列表；S20: Obtain a favorite program list of each viewer according to the viewer identity information;
S30：对当前观众喜爱节目列表中的电视节目进行统计，统计出相同电视节目及相同电视节目的次数；S30: Perform statistics on the TV programs in the current favorite program list, and count the number of times the same TV program and the same TV program;
S40：根据相同电视节目的次数，由高到低对相同电视节目进行重新排序，并按照排序将电视节目推荐给当前观众。S40: Reorder the same television programs from high to low according to the number of times of the same television program, and recommend the television program to the current audience according to the order.
进一步的，所述步骤S10具体为：通过数字电视设备的摄像头对前方区域进行拍摄并进行人脸识别，通过人脸识别技术识别出前方区域中的观众，进而获取观众身份信息。Further, the step S10 is specifically: capturing the front area by the camera of the digital television device and performing face recognition, and identifying the audience in the front area by the face recognition technology, thereby acquiring the audience identity information.
进一步的，所述步骤S10还包括：在人脸识别出观众之后，还将识别出的观众进行列表展示，供观众进行确认更改；若识别出的观众数目与真实观众数目有差异，则通知观众进行更改；对于不能识别出的人脸，将不能识别的人脸截图进行显示，提示观众对人脸身份信息进行确认。Further, the step S10 further includes: after the face is recognized by the face, the recognized audience is displayed in a list for the viewer to confirm and change; if the identified number of viewers is different from the actual number of viewers, the viewer is notified Make changes; for unrecognizable faces, display the unrecognizable face screenshots, prompting the viewer to confirm the face identity information.
进一步的，所述步骤S40还包括：对于次数相同的电视节目，获取次数相同电视节目的类型，并与排序靠前电视节目的节目类型进行比较，将节目类型一致的电视节目排序靠前。Further, the step S40 further includes: for the TV program with the same number of times, acquiring the type of the TV program with the same number of times, and comparing with the program type of the top TV program, and ranking the TV programs with the same program type as the front.
进一步的，所述步骤S40还包括：若次数相同且节目类型也相同，则比较电视节目的播放时间，将播放时间近的电视节目排序靠前。Further, the step S40 further includes: if the number of times is the same and the program type is the same, comparing the playing time of the television program, and ranking the television programs with the playing time close to the front.
本发明提供的一种多观众电视节目推荐系统，包括：The invention provides a multi-viewer television program recommendation system, comprising:
身份信息获取单元，获取当前观看电视节目观众的观众身份信息；An identity information obtaining unit, which acquires audience identity information of a viewer currently watching a television program;
喜爱节目列表获取单元，根据观众身份信息获取每个观众的喜爱节目列表；a favorite program list obtaining unit, which acquires a favorite program list of each viewer according to the viewer identity information;
电视节目统计单元，对当前观众喜爱节目列表中的电视节目进行统计，统计出相同电视节目及相同电视节目的次数；The television program statistics unit counts the television programs in the current viewer favorite program list, and counts the number of times of the same television program and the same television program;
排序推荐单元，根据相同电视节目的次数，由高到低对相同电视节目进行重新排序，并按照排序将电视节目推荐给当前观众。The ranking recommendation unit reorders the same television programs from high to low according to the number of times of the same television program, and recommends the television programs to the current audience according to the order.
进一步的，所述身份信息获取单元通过数字电视设备的摄像头对前方区域进行拍摄并进行人脸识别，通过人脸识别技术识别出前方区域中的观众，进而获取观众身份信息。Further, the identity information acquiring unit captures the front area through the camera of the digital television device and performs face recognition, and recognizes the audience in the front area through the face recognition technology, thereby acquiring the audience identity information.
进一步的，所述身份信息获取单元在人脸识别出观众之后，还将识别出的观众进行列表展示，供观众进行确认更改；若识别出的观众数目与真实观众数目有差异，则通知观众进行更改；对于不能识别出的人脸，将不能识别的人脸截图进行显示，提示观众对人脸身份信息进行确认。Further, after the face recognition of the viewer, the identity information acquiring unit displays the identified viewers for the viewer to confirm and change; if the identified number of viewers is different from the actual number of viewers, the viewer is notified Change; for unrecognizable faces, a screenshot of the face that cannot be recognized is displayed, prompting the viewer to confirm the face identity information.
进一步的，对于次数相同的电视节目，所述排序推荐单元获取次数相同电视节目的类型，并与排序靠前电视节目的节目类型进行比较，将节目类型一致的电视节目排序靠前。Further, for the television programs of the same number of times, the ranking recommendation unit acquires the types of television programs of the same number of times, and compares them with the program types of the television programs that are ranked first, and ranks the television programs with the same program type in the front.
进一步的，若次数相同且节目类型也相同，所述排序推荐单元则比较电视节目的播放时间，将播放时间近的电视节目排序靠前。Further, if the number of times is the same and the program type is the same, the sorting recommendation unit compares the playing time of the television program, and ranks the television programs with the playing time close to the front.
有益效果Beneficial effect
本发明多观众电视节目推荐方法及系统，在当前有多个观众同时观看电视节目时，获取多个观众的身份信息及对应的喜爱节目列表，统计出出相同电视节目及相同电视节目的次数，根据次数进行排序，按照排序来推荐电视节目给当前多个观众，这样综合多个观众的共同喜爱节目来推荐电视节目，从而很好的满足了多个观众的需求，给观众观看带来很大便利和良好的观看体验。The multi-viewer television program recommendation method and system of the present invention acquires the identity information of a plurality of viewers and the corresponding favorite program list when a plurality of viewers currently watch the television program at the same time, and counts the number of times of the same television program and the same television program. Sorting according to the number of times, recommending the TV program to the current plurality of viewers according to the order, so that the common favorite programs of the plurality of viewers are combined to recommend the TV program, thereby satisfying the needs of the plurality of viewers, and bringing great interest to the viewers. Convenience and a good viewing experience.
附图说明DRAWINGS
图1是一个实施例中的多观众电视节目推荐方法的流程图；1 is a flow chart of a multi-viewer television program recommendation method in an embodiment;
图2是一个实施例中的多观众电视节目推荐系统的结构图。2 is a structural diagram of a multi-viewer television program recommendation system in one embodiment.
本发明的实施方式Embodiments of the invention
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本发明，并不用于限定本发明。The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
图1是一个实施例中的多观众电视节目推荐方法的流程图，如图1所示，该方法包括如下步骤：1 is a flow chart of a multi-viewer television program recommendation method in an embodiment. As shown in FIG. 1, the method includes the following steps:
步骤S10：获取当前观看电视节目观众的观众身份信息。Step S10: Acquire viewer identity information of the viewer currently watching the television program.
在多个观众同时观看电视节目时，为能够为多个观众很好的推荐电视节目，需要首先了解当前多个观众的喜爱节目，这就需要确定当前观众的身份信息。由于目前的数字电视设备（例如机顶盒、智能电视等）都具备摄像头和比较器的处理能力，能够对图像进行智能分析，则该步骤具体为：通过数字电视设备的摄像头对前方区域进行拍摄并进行人脸识别，通过人脸识别技术识别出前方区域中的观众，进而获取观众身份信息。When a plurality of viewers watch a TV program at the same time, in order to be able to recommend a TV program well for a plurality of viewers, it is necessary to first understand the favorite programs of the current plurality of viewers, which requires determining the identity information of the current viewer. Since the current digital television devices (such as set-top boxes, smart TVs, etc.) have the processing capabilities of the camera and the comparator, and can intelligently analyze the image, the step is specifically: shooting the front area through the camera of the digital television device and performing Face recognition, through the face recognition technology to identify the audience in the front area, and then obtain the audience identity information.
进一步的，由于人脸识别存在一定的不精确性，故在人脸识别出观众之后，还将识别出的观众进行列表展示，供观众进行确认更改。若识别出的观众数目与真实观众数目有差异，则通知观众进行更改。对于不能识别出的人脸，将不能识别的人脸截图进行显示，提示观众对人脸身份信息进行确认。Further, since the face recognition has certain inaccuracies, after the face is recognized by the face, the identified viewers are also displayed in a list for the viewer to confirm and change. If the number of identified viewers differs from the actual number of viewers, the viewer is notified to make changes. For faces that cannot be recognized, a screenshot of the face that cannot be recognized is displayed, prompting the viewer to confirm the face identity information.
步骤S20：根据观众身份信息获取每个观众的喜爱节目列表。Step S20: Acquire a favorite program list of each viewer according to the viewer identity information.
在获取观众身份信息后，由于每个观众身份信息（即每个观众的ID）都有各自的喜爱节目列表，则可根据每个观众身份信息获取各自对应的喜爱节目列表，了解每个观众的喜爱节目。After obtaining the audience identity information, since each viewer identity information (ie, each viewer's ID) has its own favorite program list, each viewer's identity information may be used to obtain a corresponding favorite program list to understand each viewer's Love the show.
步骤S30：对当前观众喜爱节目列表中的电视节目进行统计，统计出相同电视节目及相同电视节目的次数。Step S30: Perform statistics on the TV programs in the current favorite program list, and count the number of times the same TV program and the same TV program.
在获取到当前多个观众的喜爱节目列表后，该步骤统计当前观众喜爱节目列表中的电视节目，统计出相同电视节目及相同电视节目的次数，了解当前多个观众的共同喜好。多个喜爱节目列表中，如果都有某个电视节目，例如某综艺节目或者某热播电视剧，则说明多个观众都喜爱该电视节目。且该电视节目出现的喜欢节目列表越多，即次数越多则说明喜爱的观众越多。After obtaining the favorite program list of the current plurality of viewers, the step counts the current TV program in the favorite program list, counts the number of the same TV program and the same TV program, and knows the common preferences of the current plurality of viewers. In a plurality of favorite program lists, if there is a certain television program, such as a variety show or a hit TV show, it means that a plurality of viewers like the TV program. Moreover, the more favorite programs appearing in the television program, that is, the more the number of times, the more viewers are favorite.
步骤S40：根据相同电视节目的次数，由高到低对相同电视节目进行重新排序，并按照排序将电视节目推荐给当前观众。Step S40: Reorder the same television programs from high to low according to the number of times of the same television program, and recommend the television program to the current audience according to the order.
在统计出电视节目在喜爱节目列表中的次数后，根据次数的多少由高到低排序，这样越多观众共同喜欢的电视节目排名越靠前，然后按照排序推荐电视节目给当前多个观众，从而能够更好的满足当前时刻的多个观众。After counting the number of times the TV program is in the favorite program list, it sorts according to the number of times from high to low, so that the more the TV programs that the viewers like together are ranked higher, and then the TV programs are recommended to the current plurality of viewers according to the order. Thereby, it is possible to better satisfy a plurality of viewers at the current moment.
在排序时，会出现电视节目次数相同的情况，对于次数相同的电视节目，获取次数相同电视节目的类型，并与排序靠前电视节目的节目类型进行比较，将节目类型一致的电视节目排序靠前。若次数相同且节目类型也相同，则比较电视节目的播放时间，将播放时间近的电视节目排序靠前。When sorting, there will be the same number of TV programs. For the same number of TV programs, the types of TV programs with the same number of times are acquired, and compared with the program types of the top TV programs, the TV programs with the same program type are sorted. before. If the number of times is the same and the program type is the same, the playing time of the television program is compared, and the television programs with the short playing time are ranked first.
该多观众电视节目推荐方法，在当前有多个观众同时观看电视节目时，获取多个观众的身份信息及对应的喜爱节目列表，统计出出相同电视节目及相同电视节目的次数，根据次数进行排序，按照排序来推荐电视节目给当前多个观众，这样综合多个观众的共同喜爱节目来推荐电视节目，从而很好的满足了多个观众的需求，给观众观看带来很大便利和良好的观看体验。The multi-viewer television program recommendation method acquires the identity information of the plurality of viewers and the corresponding favorite program list when a plurality of viewers currently watch the television program at the same time, and counts the number of times of the same television program and the same television program, according to the number of times Sorting, recommending TV programs to a plurality of current viewers according to sorting, so that a plurality of viewers' favorite programs are integrated to recommend TV programs, thereby satisfying the needs of a plurality of viewers, and bringing great convenience and good viewing to the viewers. Viewing experience.
同时，本发明还提供一种多观众电视节目推荐系统，如图2所示，该系统包括：Meanwhile, the present invention also provides a multi-viewer television program recommendation system, as shown in FIG. 2, the system includes:
身份信息获取单元100，获取当前观看电视节目观众的观众身份信息。The identity information obtaining unit 100 acquires audience identity information of the viewer currently watching the television program.
在多个观众同时观看电视节目时，为能够为多个观众很好的推荐电视节目，需要首先了解当前多个观众的喜爱节目，这就需要确定当前观众的身份信息。由于目前的数字电视设备（例如机顶盒、智能电视等）都具备摄像头和比较器的处理能力，能够对图像进行智能分析，则身份信息获取单元100通过数字电视设备的摄像头对前方区域进行拍摄并进行人脸识别，通过人脸识别技术识别出前方区域中的观众，进而获取观众身份信息。When a plurality of viewers watch a TV program at the same time, in order to be able to recommend a TV program well for a plurality of viewers, it is necessary to first understand the favorite programs of the current plurality of viewers, which requires determining the identity information of the current viewer. Since the current digital television equipment (such as a set-top box, a smart TV, etc.) has the processing capability of the camera and the comparator, and can perform intelligent analysis on the image, the identity information acquiring unit 100 photographs and performs the front area through the camera of the digital television device. Face recognition, through the face recognition technology to identify the audience in the front area, and then obtain the audience identity information.
进一步的，由于人脸识别存在一定的不精确性，故在人脸识别出观众之后，身份信息获取单元100还将识别出的观众进行列表展示，供观众进行确认更改。若识别出的观众数目与真实观众数目有差异，身份信息获取单元100则通知观众进行更改。对于不能识别出的人脸，身份信息获取单元100将不能识别的人脸截图进行显示，提示观众对人脸身份信息进行确认。Further, since the face recognition has certain inaccuracy, after the face recognizes the viewer, the identity information acquiring unit 100 also displays the identified viewers for the viewer to confirm and change. If the number of recognized viewers differs from the actual number of viewers, the identity information acquisition unit 100 notifies the viewer to make the change. For the unrecognizable face, the identity information acquiring unit 100 displays the unrecognizable face screenshot, and prompts the viewer to confirm the face identity information.
喜爱节目列表获取单元200，根据观众身份信息获取每个观众的喜爱节目列表。The favorite program list obtaining unit 200 acquires a favorite program list of each viewer based on the viewer identity information.
在获取观众身份信息后，由于每个观众身份信息（即每个观众的ID）都有各自的喜爱节目列表，则可根据每个观众身份信息获取各自对应的喜爱节目列表，了解每个观众的喜爱节目。After obtaining the audience identity information, since each viewer identity information (ie, each viewer's ID) has its own favorite program list, each viewer's identity information may be used to obtain a corresponding favorite program list to understand each viewer's Love the show.
电视节目统计单元300，对当前观众喜爱节目列表中的电视节目进行统计，统计出相同电视节目及相同电视节目的次数。The television program statistics unit 300 collects statistics on the television programs in the current viewer favorite program list, and counts the number of times the same television program and the same television program.
在获取到当前多个观众的喜爱节目列表后，电视节目统计单元300统计当前观众喜爱节目列表中的电视节目，统计出相同电视节目及相同电视节目的次数，了解当前多个观众的共同喜好。多个喜爱节目列表中，如果都有某个电视节目，例如某综艺节目或者某热播电视剧，则说明多个观众都喜爱该电视节目。且该电视节目出现的喜欢节目列表越多，即次数越多则说明喜爱的观众越多。After obtaining the favorite program list of the current plurality of viewers, the television program statistics unit 300 counts the television programs in the current viewer favorite program list, counts the number of the same television program and the same television program, and knows the common preferences of the current plurality of viewers. In a plurality of favorite program lists, if there is a certain television program, such as a variety show or a hit TV show, it means that a plurality of viewers like the TV program. Moreover, the more favorite programs appearing in the television program, that is, the more the number of times, the more viewers are favorite.
排序推荐单元400，根据相同电视节目的次数，由高到低对相同电视节目进行重新排序，并按照排序将电视节目推荐给当前观众。The ranking recommendation unit 400 reorders the same television programs from high to low according to the number of times of the same television program, and recommends the television programs to the current audience in order.
在统计出电视节目在喜爱节目列表中的次数后，排序推荐单元400根据次数的多少由高到低排序，这样越多观众共同喜欢的电视节目排名越靠前，然后按照排序推荐电视节目给当前多个观众，从而能够更好的满足当前时刻的多个观众。After counting the number of times the television program is in the favorite program list, the ranking recommendation unit 400 sorts according to the number of times from high to low, so that the more the TV programs that the viewers like together are ranked higher, and then the recommended television programs are given to the current order. Multiple viewers, thus being able to better meet multiple viewers at the current moment.
在排序时，会出现电视节目次数相同的情况，对于次数相同的电视节目，排序推荐单元400获取次数相同电视节目的类型，并与排序靠前电视节目的节目类型进行比较，将节目类型一致的电视节目排序靠前。若次数相同且节目类型也相同，排序推荐单元400则比较电视节目的播放时间，将播放时间近的电视节目排序靠前。In the case of sorting, the same number of TV programs may occur. For the television programs of the same number of times, the sorting recommending unit 400 acquires the types of television programs of the same number of times, and compares them with the program types of the ranked top TV programs, and the program types are consistent. TV shows are ranked first. If the number of times is the same and the program type is the same, the sort recommendation unit 400 compares the play time of the television program, and ranks the television programs with the near play time in the front.
该多观众电视节目推荐系统，在当前有多个观众同时观看电视节目时，获取多个观众的身份信息及对应的喜爱节目列表，统计出出相同电视节目及相同电视节目的次数，根据次数进行排序，按照排序来推荐电视节目给当前多个观众，这样综合多个观众的共同喜爱节目来推荐电视节目，从而很好的满足了多个观众的需求，给观众观看带来很大便利和良好的观看体验。The multi-viewer television program recommendation system acquires the identity information of the plurality of viewers and the corresponding favorite program list when a plurality of viewers currently watch the television program at the same time, and counts the number of times of the same television program and the same television program, according to the number of times. Sorting, recommending TV programs to a plurality of current viewers according to sorting, so that a plurality of viewers' favorite programs are integrated to recommend TV programs, thereby satisfying the needs of a plurality of viewers, and bringing great convenience and good viewing to the viewers. Viewing experience.
以上仅为本发明的较佳实施例而已，并不用以限制本发明，凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等，均应包含在本发明的保护范围之内。The above are only the preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalents, and improvements made within the spirit and scope of the present invention should be included in the scope of the present invention. Inside.

Claims (10)

  1. 一种多观众电视节目推荐方法，其特征在于，包括如下步骤：A multi-viewer television program recommendation method, comprising the steps of:
    S10：获取当前观看电视节目观众的观众身份信息；S10: Acquire viewer identity information of a viewer currently watching a television program;
    S20：根据观众身份信息获取每个观众的喜爱节目列表；S20: Obtain a favorite program list of each viewer according to the viewer identity information;
    S30：对当前观众喜爱节目列表中的电视节目进行统计，统计出相同电视节目及相同电视节目的次数；S30: Perform statistics on the TV programs in the current favorite program list, and count the number of times the same TV program and the same TV program;
    S40：根据相同电视节目的次数，由高到低对相同电视节目进行重新排序，并按照排序将电视节目推荐给当前观众。S40: Reorder the same television programs from high to low according to the number of times of the same television program, and recommend the television program to the current audience according to the order.
  2. 根据权利要求1所述的多观众电视节目推荐方法，其特征在于，所述步骤S10具体为：通过数字电视设备的摄像头对前方区域进行拍摄并进行人脸识别，通过人脸识别技术识别出前方区域中的观众，进而获取观众身份信息。The multi-viewer television program recommendation method according to claim 1, wherein the step S10 is specifically: capturing a front area by a camera of the digital television device and performing face recognition, and recognizing the front by a face recognition technology. The audience in the area, in turn, obtains viewer identity information.
  3. 根据权利要求2所述的多观众电视节目推荐方法，其特征在于，所述步骤S10还包括：在人脸识别出观众之后，还将识别出的观众进行列表展示，供观众进行确认更改；若识别出的观众数目与真实观众数目有差异，则通知观众进行更改；对于不能识别出的人脸，将不能识别的人脸截图进行显示，提示观众对人脸身份信息进行确认。The multi-viewer television program recommendation method according to claim 2, wherein the step S10 further comprises: after the face is recognized by the face, the recognized viewer is also displayed in a list for the viewer to confirm and change; If the number of recognized viewers differs from the actual number of viewers, the viewer is notified to make changes; for the unrecognizable face, a screenshot of the unrecognizable face is displayed, prompting the viewer to confirm the facial identity information.
  4. 根据权利要求2所述的多观众电视节目推荐方法，其特征在于，所述步骤S40还包括：对于次数相同的电视节目，获取次数相同电视节目的类型，并与排序靠前电视节目的节目类型进行比较，将节目类型一致的电视节目排序靠前。The multi-viewer television program recommendation method according to claim 2, wherein the step S40 further comprises: acquiring, for the television program of the same number of times, the type of the television program of the same number of times, and sorting the program type of the television program of the previous TV program. For comparison, the TV programs with the same program type are ranked first.
  5. 根据权利要求4所述的多观众电视节目推荐方法，其特征在于，所述步骤S40还包括：若次数相同且节目类型也相同，则比较电视节目的播放时间，将播放时间近的电视节目排序靠前。The multi-viewer television program recommendation method according to claim 4, wherein the step S40 further comprises: if the number of times is the same and the program type is the same, comparing the playing time of the television program, and sorting the television programs with the short playing time. Back to front.
  6. 一种多观众电视节目推荐系统，其特征在于，包括：A multi-viewer television program recommendation system, comprising:
    身份信息获取单元，获取当前观看电视节目观众的观众身份信息；An identity information obtaining unit, which acquires audience identity information of a viewer currently watching a television program;
    喜爱节目列表获取单元，根据观众身份信息获取每个观众的喜爱节目列表；a favorite program list obtaining unit, which acquires a favorite program list of each viewer according to the viewer identity information;
    电视节目统计单元，对当前观众喜爱节目列表中的电视节目进行统计，统计出相同电视节目及相同电视节目的次数；The television program statistics unit counts the television programs in the current viewer favorite program list, and counts the number of times of the same television program and the same television program;
    排序推荐单元，根据相同电视节目的次数，由高到低对相同电视节目进行重新排序，并按照排序将电视节目推荐给当前观众。The ranking recommendation unit reorders the same television programs from high to low according to the number of times of the same television program, and recommends the television programs to the current audience according to the order.
  7. 根据权利要求6所述的多观众电视节目推荐系统，其特征在于，所述身份信息获取单元通过数字电视设备的摄像头对前方区域进行拍摄并进行人脸识别，通过人脸识别技术识别出前方区域中的观众，进而获取观众身份信息。The multi-viewer television program recommendation system according to claim 6, wherein the identity information acquisition unit captures a front area and performs face recognition through a camera of the digital television device, and recognizes a front area by face recognition technology. The audience in the audience, in turn, obtains viewer identity information.
  8. 根据权利要求7所述的多观众电视节目推荐系统，其特征在于，所述身份信息获取单元在人脸识别出观众之后，还将识别出的观众进行列表展示，供观众进行确认更改；若识别出的观众数目与真实观众数目有差异，则通知观众进行更改；对于不能识别出的人脸，将不能识别的人脸截图进行显示，提示观众对人脸身份信息进行确认。The multi-viewer television program recommendation system according to claim 7, wherein the identity information acquisition unit displays the recognized viewers in a list after the face recognizes the viewer, for the viewer to confirm and change; If there is a difference between the number of viewers and the actual number of viewers, the viewer is notified to make changes; for the unrecognizable face, a screenshot of the face that cannot be recognized is displayed, prompting the viewer to confirm the identity information of the face.
  9. 根据权利要求6所述的多观众电视节目推荐系统，其特征在于，对于次数相同的电视节目，所述排序推荐单元获取次数相同电视节目的类型，并与排序靠前电视节目的节目类型进行比较，将节目类型一致的电视节目排序靠前。The multi-viewer television program recommendation system according to claim 6, wherein, for the television programs of the same number of times, the sorting recommendation unit acquires the type of the television program of the same number of times and compares with the program type of the pre-listed television program. Sort TV programs with the same type of program in the top.
  10. 根据权利要求9所述的多观众电视节目推荐系统，其特征在于，若次数相同且节目类型也相同，所述排序推荐单元则比较电视节目的播放时间，将播放时间近的电视节目排序靠前。The multi-viewer television program recommendation system according to claim 9, wherein if the number of times is the same and the program type is the same, the sorting recommending unit compares the playing time of the television program, and ranks the television programs with the playing time close. .
PCT/CN2018/086718 2017-06-28 2018-05-14 Multi-viewer television program recommendation method and system WO2019001153A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710506417.9 2017-06-28
CN201710506417.9A CN107172453A (en) 2017-06-28 2017-06-28 Many spectators' TV programme suggesting methods and system

Publications (1)

Publication Number Publication Date
WO2019001153A1 true WO2019001153A1 (en) 2019-01-03

Family

ID=59827778

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/086718 WO2019001153A1 (en) 2017-06-28 2018-05-14 Multi-viewer television program recommendation method and system

Country Status (2)

Country Link
CN (1) CN107172453A (en)
WO (1) WO2019001153A1 (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107172453A (en) * 2017-06-28 2017-09-15 深圳市九洲电器有限公司 Many spectators' TV programme suggesting methods and system
CN107948737A (en) * 2017-11-17 2018-04-20 上海与德科技有限公司 The recommendation method and device of TV programme
CN109684509A (en) * 2018-12-27 2019-04-26 贵州省广播电视信息网络股份有限公司 A kind of video recommendation method and system based on more people's scenes
CN112073766B (en) * 2019-06-10 2023-05-30 海信视像科技股份有限公司 Display equipment
CN110519620A (en) * 2019-08-30 2019-11-29 三星电子（中国）研发中心 Recommend the method and television set of TV programme in television set

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011103587A (en) * 2009-11-11 2011-05-26 Canon Inc Program recommendation apparatus and control method thereof
CN102263999A (en) * 2011-08-03 2011-11-30 Tcl集团股份有限公司 Face-recognition-based method and system for automatically classifying television programs
CN103873941A (en) * 2012-12-17 2014-06-18 联想(北京)有限公司 Display method and electronic equipment
CN104053060A (en) * 2013-03-15 2014-09-17 富泰华工业（深圳）有限公司 Intelligent television and television program playing method thereof
CN107172453A (en) * 2017-06-28 2017-09-15 深圳市九洲电器有限公司 Many spectators' TV programme suggesting methods and system

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104599367A (en) * 2014-12-31 2015-05-06 苏州福丰科技有限公司 Multi-user parallel access control recognition method based on three-dimensional face image recognition

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011103587A (en) * 2009-11-11 2011-05-26 Canon Inc Program recommendation apparatus and control method thereof
CN102263999A (en) * 2011-08-03 2011-11-30 Tcl集团股份有限公司 Face-recognition-based method and system for automatically classifying television programs
CN103873941A (en) * 2012-12-17 2014-06-18 联想(北京)有限公司 Display method and electronic equipment
CN104053060A (en) * 2013-03-15 2014-09-17 富泰华工业（深圳）有限公司 Intelligent television and television program playing method thereof
CN107172453A (en) * 2017-06-28 2017-09-15 深圳市九洲电器有限公司 Many spectators' TV programme suggesting methods and system

Also Published As

Publication number Publication date
CN107172453A (en) 2017-09-15

Similar Documents

Publication Publication Date Title
WO2019001153A1 (en) Multi-viewer television program recommendation method and system
US8935727B2 (en) Information processing apparatus, information processing method, and program
US9252897B2 (en) Multi-feed event viewing
US8943537B2 (en) Method and system for presenting personalized television program recommendation to viewers
CN103763585B (en) A kind of user's characteristic information acquisition methods, device and terminal device
US11064233B2 (en) Providing service recommendation information on the basis of a device use history
CN109121007A (en) Movie and television contents recommended method, smart television and system based on plurality of human faces identification
CN101365102B (en) Audience rating statistical method and system based on video content recognition
US10298978B2 (en) Interest prediction
CN103686344A (en) Enhanced video system and method
CN107480265B (en) Data recommendation method, device, equipment and storage medium
CN105681901A (en) Program recommending method and device
US20170195706A1 (en) Method and device for providing a video stream for an object of interest
US8584166B2 (en) Probabilistic-based content recommender
CN107948737A (en) The recommendation method and device of TV programme
US20190124402A1 (en) Information provision device, reception device, information provision system, information provision method and program
KR102611422B1 (en) Display device and method for recommending contents of the display device
TWI540894B (en) Display system and program selection method thereof
KR20160090123A (en) Apparatus and method for providing preferred channel service
WO2016206035A1 (en) Information recommendation method and user terminal
US20180121962A1 (en) Electronic apparatus and controlling method thereof
US20190132645A1 (en) Electronic apparatus and controlling method thereof
WO2016138925A1 (en) Image display device capable of automatically scanning alternative program contents with remote recording function
US20100050200A1 (en) Program information prompting method and apparatus and television set using the same
CN110879944A (en) Anchor recommendation method, storage medium, equipment and system based on face similarity

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: 18824458

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: 18824458

Country of ref document: EP

Kind code of ref document: A1