WO2017113741A1 - 一种基于人脸识别的广告推荐方法和装置 - Google Patents

一种基于人脸识别的广告推荐方法和装置 Download PDF

Info

Publication number
WO2017113741A1
WO2017113741A1 PCT/CN2016/089581 CN2016089581W WO2017113741A1 WO 2017113741 A1 WO2017113741 A1 WO 2017113741A1 CN 2016089581 W CN2016089581 W CN 2016089581W WO 2017113741 A1 WO2017113741 A1 WO 2017113741A1
Authority
WO
WIPO (PCT)
Prior art keywords
advertisement
length
user
file
face
Prior art date
Application number
PCT/CN2016/089581
Other languages
English (en)
French (fr)
Inventor
潘峰
Original Assignee
乐视控股（北京）有限公司
乐视致新电子科技（天津）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 乐视控股（北京）有限公司, 乐视致新电子科技（天津）有限公司 filed Critical 乐视控股（北京）有限公司
Priority to US15/240,273 priority Critical patent/US20170186043A1/en
Publication of WO2017113741A1 publication Critical patent/WO2017113741A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0255—Targeted advertisements based on user history
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0277—Online advertisement
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships

Definitions

  • the invention relates to the field of media communication technology, in particular to an advertisement recommendation method and device based on face recognition.
  • smart TV is an intelligent multimedia terminal that conforms to the trend of “high definition”, “networking” and “intelligence” of TV sets. It has the content of programs obtained from various channels such as the Internet, video equipment and computers.
  • the easy-to-use, integrated operator interface delivers the features that consumers want most clearly on a large screen.
  • the purpose of some embodiments of the present invention is to provide an advertisement recommendation method and apparatus based on face recognition, which solves the problem that accurate advertisement placement cannot be performed for each user.
  • the advertisement file is marked as a valid viewing record, otherwise it is not executed.
  • the length of time for monitoring the play meets a preset condition, where the preset condition is:
  • the advertisement file is marked as a valid viewing record.
  • the method before the initiating the face detection process, the method further includes: obtaining an instruction that the user logs in to the smart TV account, or receiving a trigger instruction that the user clicks on the video file after logging in to the smart TV account.
  • some embodiments of the present invention further provide an advertisement recommendation device based on face recognition, including:
  • a face data acquiring unit configured to start a face detection process and acquire face data
  • An identity information obtaining unit configured to acquire identity information of the user in a preset face user table according to the face data; wherein, the face data of each user is stored in the face user table Correspondence with identity information;
  • a video file recommendation unit configured to upload the acquired identity information to the server, and from the service
  • the server receives the advertisement file recommended according to the user's viewing record; when there is no viewing record, determines whether the played video file is an advertisement video file during the process of playing the video file; when the judgment result is an advertisement video file, Monitoring the length of time the advertisement file is played; if the length of the broadcast is monitored to meet the preset condition, the advertisement file is marked as a valid viewing record; and the acquired identity information and the valid viewing record are uploaded according to the identity information of the user. To the server.
  • the video file recommending unit is further configured to: monitor whether there is a viewer in front of the screen while monitoring the length of time the advertisement file is played;
  • the advertisement file is marked as a valid viewing record, otherwise it is not executed.
  • the video file recommending unit is further configured to: when there is no continuous monitoring of the presence of the viewer in front of the screen during the length of the playing, determining whether the length of time before the screen does not exist exceeds a preset departure time. The time threshold, if not exceeded, marks the advertisement file as a valid viewing record, otherwise it is not executed.
  • the video file recommendation unit monitors that the length of time for playing meets a preset condition, where the preset condition is:
  • the advertisement file is marked as a valid viewing record.
  • the face data obtaining unit is further configured to: obtain an instruction for the user to log in to the smart TV account, or receive a trigger instruction for the user to click on the video file after logging in to the smart TV account before starting the face detection process.
  • the method and device for recommending advertisement based on face recognition initiates a face detection process, acquires and acquires the user in a preset face user table according to the face data.
  • Identity information The acquired identity information is uploaded to the server, and an advertisement file recommended according to the user's viewing history is received from the server.
  • the played video file is an advertisement video file during the process of playing the video file.
  • the judgment result is an advertisement video file, monitoring the length of time the advertisement file is played. If the length of the playback time is monitored to meet the preset condition, the advertisement file is marked as a valid viewing record, and according to the identity information of the user, the advertisement file is obtained.
  • the identity information and the valid viewing history are uploaded to the server.
  • FIG. 1 is a schematic flow chart of an advertisement recommendation method based on face recognition according to an embodiment of the present invention
  • FIG. 2 is a schematic flowchart of a method for recommending advertisement based on face recognition according to an embodiment of the present invention
  • FIG. 3 is a schematic structural diagram of an advertisement recommendation device based on face recognition according to some embodiments of the present invention.
  • the advertisement is only based on experience to determine our delivery goals, and it is impossible to deliver advertisements for each user's real interest.
  • some embodiments of the present invention from the perspective of the user, realize that the user wishes to be able to recommend an advertisement file that is only of interest to him. Therefore, the idea of some embodiments of the present invention is to establish interconnection between face recognition, advertisement files, and personalized recommendations on a smart TV.
  • FIG. 1 is a schematic flowchart of a method for recommending an advertisement based on face recognition according to some embodiments of the present invention
  • the method for recommending advertisement based on face recognition includes:
  • Step 101 Start a face detection process to acquire face data.
  • the face detection process can be initiated.
  • the user may click the trigger command of the video file after logging in to the smart TV account, and then start the face detection process.
  • the login smart TV account means that the smart TV sets the account of the family unit.
  • the user can first log in to the account through the verification of the home account, and then identify the different users who log in to the home account by initiating the face detection process. Thereby, it is possible to identify a plurality of users sharing one family account.
  • the face detection process is set to the resident system, and the default is the background process that runs all the time.
  • Step 102 Acquire, according to the face data, identity information of the user in a preset face user table.
  • the face user table stores a correspondence relationship between the face data and the identity information of each user.
  • the identity information may include a user name, a password, a gender, an age, and the like.
  • the identity information of the user is obtained in the preset face user table, whether the identity information of the user exists in the preset face user table may be determined according to the face data. If yes, the identity information is obtained, otherwise the user identity information corresponding to the face data is established in the face user table. For example, the floating layer may be popped up to allow the user to set the identity information, and the set identity information is associated with the face data and stored in the face user table. Preferably, the updated face user table is uploaded to the server.
  • each home account corresponds to a face user table in which the correspondence between the face data and the identity information of each user after logging in through the home account is stored.
  • the corresponding relationship between the face data and the identity information of all users is stored in the face user table, and the correspondence between the face data and the identity information of the user who performs face detection after logging in through the same home account is included.
  • the relationship also includes the correspondence between the face data and the identity information of the user who performs face detection after logging in through different home accounts.
  • the home account identifier may be further stored in the face user table. That is to say, a home account identifier is also set in the correspondence between the face data and the identity information of each user, and the home account identifiers of multiple users who share a single home account are the same.
  • the face user table may be stored locally or not locally. However, whether or not it is stored locally, the face user table described above is stored on the server side. Preferably, if the face user table is not stored locally, the current local MAC address may be used as a parameter, and a request is sent to the server through the network to obtain a face user table currently stored on the server.
  • Step 103 Upload the acquired identity information to a server, and receive an advertisement file recommended according to the user's viewing record from the server.
  • the played video file when there is no viewing record, it is determined whether the played video file is an advertisement video file during the process of playing the video file.
  • the length of time during which the advertisement file is played is monitored. If the length of time for monitoring is monitored to meet the preset condition, the advertisement file is marked as a valid viewing record, and the acquired identity information and the valid viewing record are uploaded to the server according to the identity information of the user.
  • the preset condition may be that the time length of the playing and the total time length of the advertisement file do not reach a preset highest difference threshold.
  • the length of the playing period refers to the total time of the played portion of the video file.
  • the length of the video file does not reach the original length of the video. Because it may be the user changing the station or shutting down, etc.
  • the preset highest difference threshold may be 1 second, that is, the difference between the length of the played time and the total length of the advertisement file does not reach 1 second, and the advertisement file is marked as a valid viewing record.
  • the obtained identity information and the valid viewing record may be uploaded to the server by using the current local MAC address as a parameter.
  • the face recognition-based advertisement recommendation method can not only implement the markup advertisement file, but also can make the marked advertisement file be of interest to the user, and provide the user with the advertisement file. basis.
  • the advertisement file while monitoring the length of time the advertisement file is played, it is also possible to monitor whether there is a viewer in front of the screen. If it is detected that the length of the playing time meets the preset condition, it is necessary to determine whether the viewer is continuously detected before the screen in the length of the playing time, and the advertising file is marked as a valid viewing record, otherwise it is not executed. Therefore, the advertisement file that is played all the time but not viewed can be discharged out of the effective viewing record, so that the marked advertisement file is truly an effective viewing record.
  • the advertisement file is marked. To view the record effectively, it will not be executed. For example, during the playback of the advertisement file, it is detected that the viewer in front of the screen does not exist when present, but the length of time that does not exist is 10 seconds in total, and the preset departure time threshold is 11 seconds, then the screen does not exist before the screen. If the length of time in which the viewer exists does not exceed the preset departure time threshold, the advertisement file is marked as a valid viewing record.
  • this embodiment can cause the viewer to have some unexpected events during the viewing process, resulting in temporary departure, but the viewer is interested in the advertisement file.
  • the feature of the face of the person can be analyzed by the face image to obtain the center position of the face image. Then, the motion displacement of the current center position and the initial center position before the first time interval is compared.
  • the human eye pupil is used as a criterion for determining the center position of the face. Specifically, the interpupillary distance is calculated based on the position of the pupil, and the position of the center point between the pupils is determined as the center position.
  • the center position of the face for example, the outer contour of the face is selected as a whole, and the center of the outer contour is determined by calculation.
  • the ratio of the current pupil distance to the initial pupil distance before the second time interval is further included. If the ratio value is greater than a preset interpupillary threshold, it is determined that the viewer is bowing.
  • the ratio value refers to a ratio obtained by taking the current pupil distance as a numerator and using the pupil distance before the second time interval as a denominator.
  • the face recognition-based advertisement recommendation method may specifically adopt the following steps:
  • Step 201 Acquire an instruction for the user to log in to the smart TV account, or receive a trigger instruction of the video file after the user logs in to the smart TV account.
  • Step 202 Start a face detection process to acquire face data.
  • Step 203 Determine, according to the face data, whether identity information corresponding to the face data exists in a preset face user table. If yes, proceed to step 205, otherwise proceed to step 204.
  • Step 204 Establish identity information of the user according to the face data, and then return to step 201.
  • Step 205 Obtain identity information of the user in a preset face user table, and then proceed to step 206.
  • Step 206 Upload the acquired identity information to the server.
  • Step 207 Receive an advertisement file recommended according to the user's viewing record from the server.
  • step 208 it is determined whether the recommended advertisement file is received, and if the process is received, the process is exited, otherwise step 209 is performed.
  • Step 209 During the process of playing the video file, determine whether the played video file is an advertisement video file, and if yes, execute step 210, otherwise exit the process.
  • Step 210 Monitor the length of time the advertisement file is played and whether there is a viewer in front of the screen.
  • Step 211 If it is detected that the length of the playing time meets the preset condition, it is determined whether the viewer is continuously detected before the screen in the length of the playing time. If yes, step 213 is performed, otherwise step 212 is performed.
  • the preset condition may be the length of time of playing and the advertisement file. The total time length difference does not reach the preset maximum difference threshold.
  • Step 212 Determine whether the length of the viewer does not exist before the screen exceeds a preset departure time threshold. If not, execute step 213, otherwise exit the process.
  • step 213 the advertisement file is marked as a valid viewing record.
  • Step 214 Upload the acquired identity information and the valid viewing record to the server according to the identity information of the user.
  • step 209 to step 214 can be triggered not only when the recommended advertisement file is not received, but also after the user inputs the smart TV account and clicks the trigger instruction of the video file.
  • an advertisement recommendation device based on face recognition is further provided.
  • the face recognition-based video recommendation device includes a face data acquisition unit 301 and an identity that are sequentially connected.
  • the face data obtaining unit 301 is configured to start a face detection process and acquire face data.
  • the identity information obtaining unit 302 is configured to acquire identity information of the user in a preset face user table according to the face data.
  • the video file recommending unit 303 is configured to upload the acquired identity information to the server, and receive an advertisement file recommended according to the user's viewing record from the server.
  • the correspondence between the face data and the identity information of each user is stored in the face user table.
  • the face data acquisition unit 301 acquires an instruction for the user to log in to the smart TV account, or receives a trigger instruction of the video file after the user logs in to the smart TV account.
  • the face data obtaining unit 301 sets the face detection process as a resident system, and defaults to a background process that is always running.
  • the video file recommending unit 303 determines whether the played video file is an advertisement video file during the process of playing the video file.
  • the length of time during which the advertisement file is played is monitored. If the length of time for monitoring is monitored to meet the preset condition, the advertisement file is marked as a valid viewing record, and the acquired identity information and the valid viewing record are uploaded to the server according to the identity information of the user.
  • the preset condition may be that the time length of the playing and the total time length of the advertisement file do not reach a preset highest difference threshold.
  • the preset maximum difference threshold may be 1 second, that is, the difference between the length of the played time and the total length of the advertisement file does not reach 1 second, then the advertisement file is Mark as a valid viewing record.
  • the obtained identity information and the valid viewing record may be uploaded to the server by using the current local MAC address as a parameter.
  • the advertisement file while monitoring the length of time the advertisement file is played, it is also possible to monitor whether there is a viewer in front of the screen. If it is detected that the length of the playing time meets the preset condition, it is necessary to determine whether the viewer is continuously detected before the screen in the length of the playing time, and the advertising file is marked as a valid viewing record, otherwise it is not executed. Further, when there is no continuous monitoring of the viewer in front of the screen during the length of the play, it is determined whether the length of time of the viewer does not exist before the screen exceeds a preset departure time threshold, and if not, the advertisement file is marked. To view the record effectively, it will not be executed.
  • the method and device for recommending advertisement based on face recognition provided by some embodiments of the present invention creatively solves the singularity of the recommendation service of the smart TV advertisement, realizes the diversity of the recommendation service, and can be customized according to the user's preference.
  • the advertisement is accurately recommended; finally, the entire face recognition-based advertisement recommendation method and apparatus are compact and easy to implement.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Physics & Mathematics (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Health & Medical Sciences (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Data Mining & Analysis (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

一种基于人脸识别的广告推荐方法和装置，启动人脸检测进程，获取人脸数据（101）；根据所述人脸数据，在预先设置的人脸用户表中获取该用户的身份信息（102）；将获取的身份信息上传至服务器，并从所述服务器接收根据该用户的观看记录推荐的广告文件（103）；当没有观看记录时，则在进行视频文件播放的过程中，判断播放的视频文件是否为广告视频文件；当判断结果为广告视频文件时，监测广告文件播放的时间长度；如果监测到播放的时间长度满足预设的条件，则将该广告文件标记为有效观看记录；根据该用户的身份信息，将获取的身份信息和有效观看记录上传至服务器。因此，所述基于人脸识别的广告推荐方法和装置解决了不能对每个用户进行精准的广告投放问题。

Description

一种基于人脸识别的广告推荐方法和装置
本申请要求在2015年12月29日提交中国专利局、申请号为201511028354.8、发明名称为“一种基于人脸识别的广告推荐方法和装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及媒体传播技术领域，特别是指一种基于人脸识别的广告推荐方法和装置。
背景技术
目前，智能电视是顺应电视机“高清化”、“网络化”、“智能化”的趋势而出现的一种智能多媒体终端，具备从因特网、视频设备、计算机等多种渠道获得节目内容，通过简单易用的整合式操作界面将消费者最需要的内容在大屏幕上清晰地展现的功能。
在高度竞争化的现代商业环境下，在很长的一段时间，我们一边在提倡精准投放，一边却在单纯凭借经验确定我们的广告投放目标，使用传统的年龄或者性别等固定指标给他们贴上标签，从而针对他们的收视情况进行广告投放。实际上，我们并不了解这部分群众是否真正想买我们的产品，以及其他时段是否能够更好的覆盖想买我们产品的人群。由此看来，我们的广告时段选择便完全与“精准投放”的目标背道而驰了。
发明内容
有鉴于此，本发明部分实施例的目的在于提出一种基于人脸识别的广告推荐方法和装置，解决了不能对每个用户进行精准的广告投放问题。
基于上述目的本发明部分实施例提供的基于人脸识别的广告推荐方法，包括步骤：
启动人脸检测进程，获取人脸数据；
根据所述人脸数据，在预先设置的人脸用户表中获取该用户的身份信 息；其中，在所述的人脸用户表中存储有每个用户的脸部数据和身份信息的对应关系；
将获取的身份信息上传至服务器，并从所述服务器接收根据该用户的观看记录推荐的广告文件；当没有观看记录时，则在进行视频文件播放的过程中，判断播放的视频文件是否为广告视频文件；当判断结果为广告视频文件时，监测广告文件播放的时间长度；如果监测到播放的时间长度满足预设的条件，则将该广告文件标记为有效观看记录；根据该用户的身份信息，将获取的身份信息和该有效观看记录上传至服务器。
在一个实施例中，所述监测广告文件播放的时间长度的同时，监测屏幕前是否存在观看者；
如果监测到播放的时间长度满足预设的条件时，判断在该播放的时间长度内是否连续监测到屏幕前存在观看者，是则将该广告文件标记为有效观看记录，否则不执行。
在一个实施例中，所述在该播放的时间长度内没有连续监测到屏幕前存在观看者时，判断屏幕前不存在观看者的时间长度是否超过预设的离开时间阈值，若没有超过则将该广告文件标记为有效观看记录，否则不执行。
在一个实施例中，所述监测到播放的时间长度满足预设的条件，其中所述的预设条件为：
该播放的时间长度与所述广告文件的总时间长度相差值未达到预设的最高差值阈值时，则将该广告文件标记为有效观看记录。
在一个实施例中，所述启动人脸检测进程之前进一步包括：获取用户登录智能电视账户的指令，或者收到用户登录智能电视账户后点击视频文件的触发指令。
在另一方面，本发明部分实施例还提供了一种基于人脸识别的广告推荐装置，包括：
人脸数据获取单元，用于启动人脸检测进程，获取人脸数据；
身份信息获取单元，用于根据所述人脸数据，在预先设置的人脸用户表中获取该用户的身份信息；其中，在所述的人脸用户表中存储有每个用户的脸部数据和身份信息的对应关系；
视频文件推荐单元，用于将获取的身份信息上传至服务器，并从所述服 务器接收根据该用户的观看记录推荐的广告文件；当没有观看记录时，则在进行视频文件播放的过程中，判断播放的视频文件是否为广告视频文件；当判断结果为广告视频文件时，监测广告文件播放的时间长度；如果监测到播放的时间长度满足预设的条件，则将该广告文件标记为有效观看记录；根据该用户的身份信息，将获取的身份信息和该有效观看记录上传至服务器。
在一个实施例中，所述视频文件推荐单元还用于：监测广告文件播放的时间长度的同时，监测屏幕前是否存在观看者；
如果监测到播放的时间长度满足预设的条件时，判断在该播放的时间长度内是否连续监测到屏幕前存在观看者，是则将该广告文件标记为有效观看记录，否则不执行。
在一个实施例中，所述视频文件推荐单元还用于：在该播放的时间长度内没有连续监测到屏幕前存在观看者时，判断屏幕前不存在观看者的时间长度是否超过预设的离开时间阈值，若没有超过则将该广告文件标记为有效观看记录，否则不执行。
在一个实施例中，所述视频文件推荐单元监测到播放的时间长度满足预设的条件，其中所述的预设条件为：
该播放的时间长度与所述广告文件的总时间长度相差值未达到预设的最高差值阈值时，则将该广告文件标记为有效观看记录。
在一个实施例中，所述人脸数据获取单元启动人脸检测进程之前还用于：获取用户登录智能电视账户的指令，或者收到用户登录智能电视账户后点击视频文件的触发指令。
从上面所述可以看出，本发明实施例提供的基于人脸识别的广告推荐方法和装置，启动人脸检测进程，获取并根据人脸数据，在预先设置的人脸用户表中获取该用户的身份信息。将获取的身份信息上传至服务器，并从所述服务器接收根据该用户的观看记录推荐的广告文件。当没有观看记录时，则在进行视频文件播放的过程中，判断播放的视频文件是否为广告视频文件。当判断结果为广告视频文件时，监测广告文件播放的时间长度，如果监测到播放的时间长度满足预设的条件，则将该广告文件标记为有效观看记录，根据该用户的身份信息，将获取的身份信息和该有效观看记录上传至服务器。从而实现了对于每个用户个性化、精准化的广告推荐，优化了智能电视广告 服务的质量。
附图说明
图1为本发明实施例中基于人脸识别的广告推荐方法的流程示意图；
图2为本发明可参考实施例中基于人脸识别的广告推荐方法的流程示意图；
图3为本发明部分实施例基于人脸识别的广告推荐装置的结构示意图。
具体实施方式
为使本发明部分实施例的目的、技术方案和优点更加清楚明白，以下结合具体实施例，并参照附图，对本发明进一步详细说明。
根据智能电视的使用现状，广告的投放只是单纯凭借经验确定我们的投放目标，无法针对每个用户的真正兴趣进行广告的投放。为了解决这一问题，本发明部分实施例从用户角度，体会到用户希望能够被推荐只针对自己感兴趣的广告文件。因此，本发明部分实施例的思路是在智能电视上，建立人脸识别、广告文件以及个性化推荐之间的互联互通。
参阅图1所示，为本发明部分实施例中基于人脸识别的广告推荐方法的流程示意图，所述基于人脸识别的广告推荐方法包括：
步骤101，启动人脸检测进程，获取人脸数据。
当获取用户登录智能电视账户的指令之后，可以启动人脸检测进程。或者，也可以当收到用户登录智能电视账户后点击视频文件的触发指令，再启动人脸检测进程。
其中，登录智能电视账户是指，智能电视设置了家庭为单位的账户。用户首先可以通过家庭账户的验证登录到该账户中，然后再通过启动人脸检测进程，对登录该家庭账户上的不同用户进行识别。从而，可以对共用一个家庭账户的多个用户进行识别。
另外，将人脸检测进程设置为常驻系统，默认为一直运行的后台进程。
步骤102，根据所述人脸数据，在预先设置的人脸用户表中获取该用户的身份信息。
在实施例中，所述的人脸用户表中存储有每个用户的脸部数据和身份信息的对应关系。其中，所述的身份信息可以包括用户名、密码、性别、年龄等等内容。
需要说明的是，在预先设置的人脸用户表中获取该用户的身份信息之前，可以根据所述人脸数据，判断在预先设置的人脸用户表中是否存在该用户的身份信息。如果存在则获取该身份信息，否则在人脸用户表中建立该人脸数据对应的用户身份信息。例如，可以弹出浮层让用户自行设置身份信息，将设置的身份信息与所述的人脸数据进行对应并存储到所述的人脸用户表中。较佳地，将更新后的人脸用户表上传至服务器。
在本实施例中，每个家庭账户对应一个人脸用户表，在该人脸用户表中存储有通过该家庭账户登录后的每个用户的脸部数据和身份信息的对应关系。或者，在所述的人脸用户表中存储有所有用户的脸部数据和身份信息的对应关系，其中包括通过同一个家庭账户登录后进行人脸检测的用户的脸部数据和身份信息的对应关系，也包括通过不同家庭账户登录后进行人脸检测的用户的脸部数据和身份信息的对应关系。
在本实施例中，当所述的人脸用户表中存储有所有用户的脸部数据和身份信息的对应关系时，可以在所述人脸用户表中还存储有家庭账户标识。也就是说，在每个用户的脸部数据和身份信息的对应关系中还设置了一个家庭账户标识，共用一个家庭账户登录的多个用户的家庭账户标识相同。
与此同时，所述的人脸用户表可以在本地进行存储，也可以不在本地存储。但无论是否在本地存储，在服务器端都要存储有所述的人脸用户表。较佳地，如果在本地没有存储所述人脸用户表，则可以以当前本地的MAC地址为参数，通过网络向服务器发送请求，获得当前存储在服务器上的人脸用户表。
步骤103，将获取的身份信息上传至服务器，并从所述服务器接收根据该用户的观看记录推荐的广告文件。
在本发明的部分实施例中，当没有观看记录时，则在进行视频文件播放的过程中，判断播放的视频文件是否为广告视频文件。当判断结果为广告视频文件时，监测广告文件播放的时间长度。如果监测到播放的时间长度满足预设的条件，则将该广告文件标记为有效观看记录，根据该用户的身份信息，将获取的身份信息和该有效观看记录上传至服务器。优选地，所述的预设条件可以是该播放的时间长度与所述广告文件的总时间长度相差值未达到预设的最高差值阈值。其中，所述播放的时间长度是指视频文件已播放部分的总时间。另外，该视频文件的播放时间长度没有达到视频总时间长度的原 因，可能是用户换台或关机等等情况。
例如，预设的最高差值阈值可以是1秒，即播放的时间长度与广告文件总时间长度的差值未达到1秒，则将该广告文件标记为有效观看记录。
在本实施例中，可以以当前本地的MAC地址为参数，将获取的身份信息和该有效观看记录上传至服务器。
从该实施例中可以看出，所述的基于人脸识别的广告推荐方法不仅能够实现标记广告文件，同时可以做到该标记的广告文件是该用户感兴趣的，并为用户推荐广告文件提供基础。
在本实施例中，监测广告文件播放的时间长度的同时，还可以监测屏幕前是否存在观看者。如果监测到播放的时间长度满足预设的条件时，则需要判断在该播放的时间长度内是否连续监测到屏幕前存在观看者，是则将该广告文件标记为有效观看记录，否则不执行。因此，可以将一直播放但不进行观看的广告文件排出在有效观看记录之外，从而真正做到了标记的广告文件为有效观看记录。
更进一步地，在该播放的时间长度内没有连续监测到屏幕前存在观看者时，判断屏幕前不存在观看者的时间长度是否超过预设的离开时间阈值，若没有超过则将该广告文件标记为有效观看记录，否则不执行。例如，在该广告文件播放的过程中，监测到屏幕前的观看者时而存在时而不存在，但是不存在的时间长度总共为10秒，而预设的离开时间阈值为11秒，则屏幕前不存在观看者的时间长度没有超过预设的离开时间阈值，则将该广告文件标记为有效观看记录。其中，屏幕前观看者时而不存在的原因，例如可以是临时拿东西、看手机或与其他人说话等等情况。因此，该实施例可以将观看者在观看过程中，出现一些突发事件而导致临时离开，但该观看者对该广告文件是感兴趣的情况。
在本实施例中，在监测屏幕前的观看者是否存在时，可以通过人脸图像分析人脸上的特征，得到人脸图像的中心位置。然后，比对当前中心位置与第一时间间隔前的初始中心位置的运动位移。较佳地，采用人眼瞳孔作为判定人脸中心位置的标准。具体来说，根据瞳孔的位置，计算瞳距，确定瞳孔之间中心点的位置作为所述中心位置。采用人双眼的中点作为人脸的中心位置，可以较好地确定人脸的位置，判定观看者的位移，可以更为精准的确定屏幕前观看者是否在观看播放的广告文件。当然，也可以采用其他方式确定 人脸的中心位置，例如，整体选取人脸的外轮廓，并通过计算确定外轮廓的中心等。
在本实施例中，在屏幕前的观看者低头时也可以判断对播放的广告文件不感兴趣。具体来说，根据所述瞳孔的位置，计算瞳距之后还包括：比对当前瞳距与第二时间间隔前的初始瞳距的比例值。若所述比例值大于预设的瞳距阈值，则判断观看者低头。其中，所述的比例值是指将当前瞳距作为分子，将第二时间间隔前的瞳距作为分母得到的比例。
作为一个可参考的实施例，参阅图2所示，所述基于人脸识别的广告推荐方法具体可采用如下步骤：
步骤201，获取用户登录智能电视账户的指令，或者收到用户登录智能电视账户后点击视频文件的触发指令。
步骤202，启动人脸检测进程，获取人脸数据。
步骤203，根据所述人脸数据，判断在预先设置的人脸用户表中是否存在与该人脸数据相对应的身份信息。若存在则进行步骤205，否则进行步骤204。
步骤204，根据该人脸数据，建立该用户的身份信息，然后返回步骤201。
步骤205，在预先设置的人脸用户表中获取该用户的身份信息，然后进行步骤206。
步骤206，将获取的身份信息上传至服务器。
步骤207，从所述服务器接收根据该用户的观看记录推荐的广告文件。
步骤208，判断是否接收到推荐的广告文件，接收到则退出该流程，否则执行步骤209。
步骤209，在进行视频文件播放的过程中，判断播放的视频文件是否为广告视频文件，若是则执行步骤210，否则退出该流程。
步骤210，监测广告文件播放的时间长度以及屏幕前是否存在观看者。
步骤211，如果监测到播放的时间长度满足预设的条件时，判断在该播放的时间长度内是否连续监测到屏幕前存在观看者，是则执行步骤213，否则执行步骤212。
在本实施例中，所述的预设条件可以是播放的时间长度与所述广告文件 的总时间长度相差值未达到预设的最高差值阈值。
步骤212，判断屏幕前不存在观看者的时间长度是否超过预设的离开时间阈值，若没有超过则执行步骤213，否则退出该流程。
步骤213，该广告文件标记为有效观看记录。
步骤214，根据该用户的身份信息，将获取的身份信息和该有效观看记录上传至服务器。
值得说明的是，步骤209至步骤214不仅可以在没有接收到推荐的广告文件时触发，还可以在收到用户登录智能电视账户后点击视频文件的触发指令之后执行。
在本发明的部分实施例还提供了一种基于人脸识别的广告推荐装置，如图3所示，所述的基于人脸识别的视频推荐装置包括依次连接的人脸数据获取单元301、身份信息获取单元302以及视频文件推荐单元303。其中，人脸数据获取单元301用于启动人脸检测进程，获取人脸数据。身份信息获取单元302用于根据所述人脸数据，在预先设置的人脸用户表中获取该用户的身份信息。视频文件推荐单元303用于将获取的身份信息上传至服务器，并从所述服务器接收根据该用户的观看记录推荐的广告文件。
需要说明的是，在所述的人脸用户表中存储有每个用户的脸部数据和身份信息的对应关系。
在本实施例中，人脸数据获取单元301启动人脸检测进程之前，获取用户登录智能电视账户的指令，或者收到用户登录智能电视账户后点击视频文件的触发指令。优选地，人脸数据获取单元301将人脸检测进程设置为常驻系统，默认为一直运行的后台进程。
在本实施例中，视频文件推荐单元303当没有观看记录时，则在进行视频文件播放的过程中，判断播放的视频文件是否为广告视频文件。当判断结果为广告视频文件时，监测广告文件播放的时间长度。如果监测到播放的时间长度满足预设的条件，则将该广告文件标记为有效观看记录，根据该用户的身份信息，将获取的身份信息和该有效观看记录上传至服务器。优选地，所述的预设条件可以是该播放的时间长度与所述广告文件的总时间长度相差值未达到预设的最高差值阈值。例如，预设的最高差值阈值可以是1秒，即播放的时间长度与广告文件总时间长度的差值未达到1秒，则将该广告文件 标记为有效观看记录。另外，可以以当前本地的MAC地址为参数，将获取的身份信息和该有效观看记录上传至服务器。
在本实施例中，监测广告文件播放的时间长度的同时，还可以监测屏幕前是否存在观看者。如果监测到播放的时间长度满足预设的条件时，则需要判断在该播放的时间长度内是否连续监测到屏幕前存在观看者，是则将该广告文件标记为有效观看记录，否则不执行。更进一步地，在该播放的时间长度内没有连续监测到屏幕前存在观看者时，判断屏幕前不存在观看者的时间长度是否超过预设的离开时间阈值，若没有超过则将该广告文件标记为有效观看记录，否则不执行。
需要说明的是，在本发明部分实施例所述的基于人脸识别的广告推荐装置的具体实施内容，在上面所述的基于人脸识别的广告推荐的方法中已经详细说明了，故在此重复内容不再说明。
综上所述，本发明部分实施例提供的基于人脸识别的广告推荐方法、装置，创造性地解决了智能电视广告推荐服务的单一性，实现了推荐服务的多样性；能够根据用户的喜好、精准地推荐广告；最后，整个所述的基于人脸识别的广告推荐方法和装置紧凑，易于实现。
所属领域的普通技术人员应当理解：以上所述仅为本发明的具体实施例而已，并不用于限制本发明，凡在本发明的精神和原则之内，所做的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。

Claims (10)

  1. 一种基于人脸识别的广告推荐方法，包括步骤：
    启动人脸检测进程，获取人脸数据；
    根据所述人脸数据，在预先设置的人脸用户表中获取该用户的身份信息；其中，在所述的人脸用户表中存储有每个用户的脸部数据和身份信息的对应关系；
    将获取的身份信息上传至服务器，并从所述服务器接收根据该用户的观看记录推荐的广告文件；当没有观看记录时，则在进行视频文件播放的过程中，判断播放的视频文件是否为广告视频文件；当判断结果为广告视频文件时，监测广告文件播放的时间长度；如果监测到播放的时间长度满足预设的条件，则将该广告文件标记为有效观看记录；根据该用户的身份信息，将获取的身份信息和该有效观看记录上传至服务器。
  2. 根据权利要求1所述的方法，其中，所述监测广告文件播放的时间长度的同时，监测屏幕前是否存在观看者；
    如果监测到播放的时间长度满足预设的条件时，判断在该播放的时间长度内是否连续监测到屏幕前存在观看者，是则将该广告文件标记为有效观看记录，否则不执行。
  3. 根据权利要求2所述的方法，其中，所述在该播放的时间长度内没有连续监测到屏幕前存在观看者时，判断屏幕前不存在观看者的时间长度是否超过预设的离开时间阈值，若没有超过则将该广告文件标记为有效观看记录，否则不执行。
  4. 根据权利要求1，2或3所述的方法，其中，所述监测到播放的时间长度满足预设的条件，其中所述的预设条件为：
    该播放的时间长度与所述广告文件的总时间长度相差值未达到预设的最高差值阈值时，则将该广告文件标记为有效观看记录。
  5. 根据权利要求1到4任一项所述的方法，其中，所述启动人脸检测进程之前进一步包括：获取用户登录智能电视账户的指令，或者收到用户登录智能电视账户后点击视频文件的触发指令。
  6. 一种基于人脸识别的广告推荐装置，包括：
    人脸数据获取单元，用于启动人脸检测进程，获取人脸数据；
    身份信息获取单元，用于根据所述人脸数据，在预先设置的人脸用户表中获取该用户的身份信息；其中，在所述的人脸用户表中存储有每个用户的脸部数据和身份信息的对应关系；
    视频文件推荐单元，用于将获取的身份信息上传至服务器，并从所述服务器接收根据该用户的观看记录推荐的广告文件；当没有观看记录时，则在进行视频文件播放的过程中，判断播放的视频文件是否为广告视频文件；当判断结果为广告视频文件时，监测广告文件播放的时间长度；如果监测到播放的时间长度满足预设的条件，则将该广告文件标记为有效观看记录；根据该用户的身份信息，将获取的身份信息和该有效观看记录上传至服务器。
  7. 根据权利要求6所述的装置，其中，所述视频文件推荐单元还用于：监测广告文件播放的时间长度的同时，监测屏幕前是否存在观看者；
    如果监测到播放的时间长度满足预设的条件时，判断在该播放的时间长度内是否连续监测到屏幕前存在观看者，是则将该广告文件标记为有效观看记录，否则不执行。
  8. 根据权利要求7所述的装置，其中，所述视频文件推荐单元还用于：在该播放的时间长度内没有连续监测到屏幕前存在观看者时，判断屏幕前不存在观看者的时间长度是否超过预设的离开时间阈值，若没有超过则将该广告文件标记为有效观看记录，否则不执行。
  9. 根据权利要求6，7或8所述的装置，其中，所述视频文件推荐单元监测到播放的时间长度满足预设的条件，其中所述的预设条件为：
    该播放的时间长度与所述广告文件的总时间长度相差值未达到预设的最高差值阈值时，则将该广告文件标记为有效观看记录。
  10. 根据权利要求6至9任一项所述的装置，其中，所述人脸数据获取单元启动人脸检测进程之前还用于：获取用户登录智能电视账户的指令，或者收到用户登录智能电视账户后点击视频文件的触发指令。
PCT/CN2016/089581 2015-12-29 2016-07-10 一种基于人脸识别的广告推荐方法和装置 WO2017113741A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US15/240,273 US20170186043A1 (en) 2015-12-29 2016-08-18 Advertisement recommendation method and based on face recogntion and recognition and electronic device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201511028354.8A CN105868685A (zh) 2015-12-29 2015-12-29 一种基于人脸识别的广告推荐方法和装置
CN201511028354.8 2015-12-29

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/240,273 Continuation US20170186043A1 (en) 2015-12-29 2016-08-18 Advertisement recommendation method and based on face recogntion and recognition and electronic device

Publications (1)

Publication Number Publication Date
WO2017113741A1 true WO2017113741A1 (zh) 2017-07-06

Family

ID=56624153

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/089581 WO2017113741A1 (zh) 2015-12-29 2016-07-10 一种基于人脸识别的广告推荐方法和装置

Country Status (2)

Country Link
CN (1) CN105868685A (zh)
WO (1) WO2017113741A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112184324A (zh) * 2020-10-13 2021-01-05 广州欢网科技有限责任公司 适用于直播场景的个性化广告投放方法、装置和控制器
CN112233286A (zh) * 2020-10-19 2021-01-15 合肥市嘉辉电子科技有限公司 一种银行用人脸识别人机对话广告机
CN115580754A (zh) * 2022-12-06 2023-01-06 成都智元汇信息技术股份有限公司 一种地铁公共空间内容点播方法及系统
CN117252651A (zh) * 2023-11-17 2023-12-19 深圳市远景达物联网技术有限公司 一种基于数字身份的物联终端广告投放方法、装置及介质

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107451850A (zh) * 2016-11-03 2017-12-08 黑龙江瑞腾传媒有限公司 大数据下基于用户兴趣的广告播放方法
CN106874891A (zh) * 2017-03-16 2017-06-20 湖南众益文化传媒股份有限公司 基于人脸识别的智能媒体广告系统
CN108197995A (zh) * 2018-01-10 2018-06-22 北京掌阔移动传媒科技有限公司 一种基于人脸识别的精准广告投放方法
CN108460622A (zh) * 2018-01-30 2018-08-28 深圳冠思大数据服务有限公司 一种线下互动式广告系统
CN109255652B (zh) * 2018-08-24 2021-09-03 深圳市启鹏天辰科技有限公司 基于人脸的广告播放方法及相关产品
CN112243589A (zh) * 2018-12-20 2021-01-19 海信视像科技股份有限公司 接收装置及接收方法、收发系统及由收发系统执行的方法、录像播放装置及录像播放方法
CN109766558A (zh) * 2018-12-29 2019-05-17 河北三川科技有限公司 一种基于身份信息播放翻译广告字幕的方法
CN111523920B (zh) * 2019-04-04 2024-02-23 维肯智能(深圳)有限公司 一种信息推送方法、装置及终端设备
CN110309710A (zh) * 2019-05-20 2019-10-08 特斯联（北京）科技有限公司 基于人脸识别的内容关注大数据处理方法、装置及系统
CN110753252B (zh) * 2019-09-29 2021-04-13 联想(北京)有限公司 一种控制显示的方法和设备、存储介质
CN113032605B (zh) * 2019-12-25 2023-08-18 中移(成都)信息通信科技有限公司 一种信息展示方法、装置、设备及计算机存储介质
CN111275874B (zh) * 2020-01-16 2022-04-26 广州康行信息技术有限公司 基于人脸检测的资讯显示方法、装置、设备及存储介质
CN111242693B (zh) * 2020-01-16 2023-08-25 秒针信息技术有限公司 设备标识确定方法、装置、电子设备及存储介质
CN111383054A (zh) * 2020-03-10 2020-07-07 中国联合网络通信集团有限公司 广告检验方法和装置
CN113495967A (zh) * 2020-03-20 2021-10-12 华为技术有限公司 一种多媒体数据的推送方法、设备、服务器以及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103514242A (zh) * 2012-12-19 2014-01-15 Tcl集团股份有限公司 一种电子广告牌的智能交互方法及系统
CN103533394A (zh) * 2013-10-08 2014-01-22 十分（北京）信息科技有限公司 信息推送方法、装置和服务器
CN103942705A (zh) * 2014-03-25 2014-07-23 惠州Tcl移动通信有限公司 一种基于人脸识别的广告分类匹配推送方法及系统
CN104363474A (zh) * 2014-11-14 2015-02-18 四川长虹电器股份有限公司 一种基于多用户的智能电视节目推荐系统及方法
CN104573619A (zh) * 2014-07-25 2015-04-29 北京智膜科技有限公司 基于人脸识别的智能广告大数据分析方法及系统

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104836783B (zh) * 2014-06-04 2018-10-30 腾讯科技（北京）有限公司 数据传输的方法、装置及系统
CN105100837A (zh) * 2015-07-23 2015-11-25 常州大学 基于手机的广告投放效果评价方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103514242A (zh) * 2012-12-19 2014-01-15 Tcl集团股份有限公司 一种电子广告牌的智能交互方法及系统
CN103533394A (zh) * 2013-10-08 2014-01-22 十分（北京）信息科技有限公司 信息推送方法、装置和服务器
CN103942705A (zh) * 2014-03-25 2014-07-23 惠州Tcl移动通信有限公司 一种基于人脸识别的广告分类匹配推送方法及系统
CN104573619A (zh) * 2014-07-25 2015-04-29 北京智膜科技有限公司 基于人脸识别的智能广告大数据分析方法及系统
CN104363474A (zh) * 2014-11-14 2015-02-18 四川长虹电器股份有限公司 一种基于多用户的智能电视节目推荐系统及方法

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112184324A (zh) * 2020-10-13 2021-01-05 广州欢网科技有限责任公司 适用于直播场景的个性化广告投放方法、装置和控制器
CN112233286A (zh) * 2020-10-19 2021-01-15 合肥市嘉辉电子科技有限公司 一种银行用人脸识别人机对话广告机
CN115580754A (zh) * 2022-12-06 2023-01-06 成都智元汇信息技术股份有限公司 一种地铁公共空间内容点播方法及系统
CN117252651A (zh) * 2023-11-17 2023-12-19 深圳市远景达物联网技术有限公司 一种基于数字身份的物联终端广告投放方法、装置及介质
CN117252651B (zh) * 2023-11-17 2024-03-19 深圳市远景达物联网技术有限公司 一种基于数字身份的物联终端广告投放方法、装置及介质

Also Published As

Publication number Publication date
CN105868685A (zh) 2016-08-17

Similar Documents

Publication Publication Date Title
WO2017113741A1 (zh) 一种基于人脸识别的广告推荐方法和装置
WO2017113740A1 (zh) 一种基于人脸识别的视频推荐方法和装置
US20170188103A1 (en) Method and device for video recommendation based on face recognition
US11880442B2 (en) Authentication of audio-based input signals
US20170186043A1 (en) Advertisement recommendation method and based on face recogntion and recognition and electronic device
US9706235B2 (en) Time varying evaluation of multimedia content
US20180152736A1 (en) Live video recording, streaming, viewing, and storing mobile application, and systems and methods of use thereof
US20130080260A1 (en) Targeted Digital Media Content
US20190090027A1 (en) Methods, systems, and media for recommending media content based on attribute grouped viewing sessions
US20150319468A1 (en) System, apparatus, and method for recommending tv program based on content
US11449136B2 (en) Methods, and devices for generating a user experience based on the stored user information
CN108781300A (zh) 用于基于网络状况推荐内容的方法、系统以及介质
CN104317804B (zh) 发布投票信息的方法和装置
CN106604078B (zh) 一种网络视频推荐方法及装置
CN105530548A (zh) 智能电视及其节目互动方法、服务器
WO2016000429A1 (zh) 视频会议热点场景的检测方法和装置
WO2017161744A1 (zh) 一种视频推荐方法及装置
WO2017166472A1 (zh) 广告数据匹配方法、装置及系统
US11212579B2 (en) Presence and authentication for media measurement
US20220053218A1 (en) Digital Sporting Event Viewer
US9678960B2 (en) Methods and systems of dynamic content analysis
US9961382B1 (en) Interaction-based identification of items in content
CN108369597A (zh) 用于基于场境来指示视频的观众群的方法、系统和介质
JP6125454B2 (ja) マッチング装置、マッチングシステム及びマッチング方法
CN108093044A (zh) 一种培训课件播放方法和系统

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: 16880539

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: 16880539

Country of ref document: EP

Kind code of ref document: A1