WO2021088468A1

WO2021088468A1 - Information pushing method and apparatus

Info

Publication number: WO2021088468A1
Application number: PCT/CN2020/110408
Authority: WO
Inventors: 侯会满
Original assignee: 北京京东尚科信息技术有限公司; 北京京东世纪贸易有限公司
Priority date: 2019-11-07
Filing date: 2020-08-21
Publication date: 2021-05-14
Also published as: CN112784103A

Abstract

An information pushing method and apparatus. The method comprises: determining search information on the basis of operating behavior information of a user (201); pushing a target long video to the user (202), wherein the target long video is a long video with tag information matching the search information in a long video set, the tag information is used for recording a feature category of the long video, and each long video in the long video set comprises at least one short video, and the short video is correspondingly provided with article ID information; and in response to a selection operation of the user for the short video comprised in the target long video, pushing the article information to the user on the basis of the article ID information corresponding to the selected short video (203). This method enables a user to acquire corresponding article information by means of selecting a short video from a long video, thereby realizing targeted information pushing.

Description

信息推送方法和装置Information pushing method and device

本专利申请要求于2019年11月07日提交的、申请号为201911081445.6、发明名称为“信息推送方法和装置”的中国专利申请的优先权，该申请的全文以引用的方式并入本申请中。This patent application claims the priority of the Chinese patent application filed on November 07, 2019 with the application number 201911081445.6 and the invention title "information push method and device". The full text of this application is incorporated into this application by reference. .

技术领域Technical field

本公开的实施例涉及计算机技术领域，具体涉及信息推送方法和装置。The embodiments of the present disclosure relate to the field of computer technology, in particular to an information push method and device.

背景技术Background technique

与文字相比，视频可以在较短的时间内把核心内容直观有效地展现给用户。因此，越来越多的人们开始通过观看视频来了解不同方面的信息。例如，用户发布在电商平台中的用于评价所购买物品的视频，其他用户通过此种评价视频可以快速地获取自己关心的信息，从而做出是否购买的决定。Compared with text, video can visually and effectively show the core content to users in a shorter period of time. Therefore, more and more people are starting to learn about different aspects of information by watching videos. For example, a user publishes a video on an e-commerce platform for evaluating purchased items, and other users can quickly obtain information that they care about through such evaluation videos, so as to make a decision whether or not to purchase.

相关技术中，视频存储位置比较分散，不利于用户观看，因此用户无法从大量视频中准确地获取关心的信息，信息推送的针对性较差。例如，用户在电商平台上查看晒单视频，只能在物品详情页下方的评价区域找到，且对应的晒单视频只是该物品相关的视频，用户无法获取与该物品类似或相关的物品的信息。In related technologies, video storage locations are relatively scattered, which is not conducive for users to watch. Therefore, users cannot accurately obtain information of interest from a large number of videos, and the pertinence of information push is poor. For example, when a user views an ordering video on an e-commerce platform, it can only be found in the evaluation area at the bottom of the item detail page, and the corresponding ordering video is only a video related to the item, and the user cannot obtain information about items similar or related to the item. information.

发明内容Summary of the invention

本公开的实施例提出了信息推送方法和装置。The embodiments of the present disclosure propose information pushing methods and devices.

第一方面，本公开的实施例提供了一种信息推送方法，该方法包括：基于用户的操作行为信息，确定搜索信息；向用户推送目标长视频，其中，目标长视频为长视频集合中、标签信息与搜索信息匹配的长视频，标签信息用于记录长视频的特征类别，长视频集合中的各长视频包括至少一个短视频，短视频对应设有物品ID信息；响应于用户对目标长视频所包括的短视频的选择操作，基于与所选择的短视频对应的物品ID信息，向用户推送物品信息。In the first aspect, the embodiments of the present disclosure provide an information pushing method, the method includes: determining search information based on the user's operation behavior information; pushing a target long video to the user, where the target long video is a set of long videos, The long video whose tag information matches the search information. The tag information is used to record the feature category of the long video. Each long video in the long video set includes at least one short video. The short video corresponds to the item ID information; The selection operation of the short video included in the video pushes the item information to the user based on the item ID information corresponding to the selected short video.

在一些实施例中，长视频通过如下步骤得到：从短视频样本集合中获取满足预设条件的短视频，为所获取的短视频设置标签，其中，标签包括短视频的特征信息；将短视频按照所设置的标签进行分类，并基于同类别的短视频生成长视频，其中，长视频的时长在预设时间范围内；针对长视频，基于该长视频所包括的短视频的标签，确定该长视频的标签信息；为长视频中的各短视频设置对应的物品ID信息。In some embodiments, the long video is obtained by the following steps: obtaining short videos that meet preset conditions from the short video sample set, and setting tags for the obtained short videos, where the tags include feature information of the short videos; Classify according to the set tags, and generate long videos based on short videos of the same category, where the duration of the long video is within the preset time range; for long videos, determine the long video based on the tags of the short videos included in the long video Tag information of the long video; set corresponding item ID information for each short video in the long video.

在一些实施例中，预设条件包括：短视频中包含目标物品图像的图像帧的数量与短视频的图像帧总数的比值大于预设阈值。In some embodiments, the preset condition includes: the ratio of the number of image frames containing the target item image in the short video to the total number of image frames of the short video is greater than a preset threshold.

在一些实施例中，预设条件包括：短视频的视频质量评分大于预设评分，其中，视频质量评分通过短视频的分辨率、清晰度和抖动程度确定。In some embodiments, the preset condition includes: the video quality score of the short video is greater than the preset score, where the video quality score is determined by the resolution, clarity, and degree of jitter of the short video.

在一些实施例中，预设条件包括：短视频中包含人脸图像。In some embodiments, the preset condition includes: the short video contains a face image.

在一些实施例中，方法还包括：将长视频的标签信息存储到第一数据库，在第一数据库中建立长视频与对应的标签信息的索引关系；将长视频中的短视频对应的物品ID信息存储到第二数据库，在第二数据库中建立短视频与对应的物品ID信息的索引关系。In some embodiments, the method further includes: storing the tag information of the long video in a first database, and establishing an index relationship between the long video and the corresponding tag information in the first database; and assigning the item ID corresponding to the short video in the long video The information is stored in the second database, and the index relationship between the short video and the corresponding item ID information is established in the second database.

在一些实施例中，接收用户发送的目标长视频的播放指令，播放目标长视频；响应于接收到目标长视频的暂停指令，确定目标长视频暂停时显示的图像所属的短视频为用户选择的短视频。In some embodiments, the playback instruction of the target long video sent by the user is received, and the target long video is played; in response to receiving the pause instruction of the target long video, it is determined that the short video to which the image displayed when the target long video is paused belongs to is selected by the user Short video.

第二方面，本公开的实施例提供了一种信息推送装置，装置包括：搜索信息确定单元，被配置成基于用户的操作行为信息，确定搜索信息；第一推送单元，被配置成向用户推送目标长视频，其中，目标长视频为长视频集合中、标签信息与搜索信息匹配的长视频，标签信息用于记录长视频的特征类别，长视频集合中的各长视频包括至少一个短视频，短视频对应设有物品ID信息；第二推送单元，被配置成响应于用户对目标长视频所包括的短视频的选择操作，基于与所选择的短视频对应的物品ID信息，向用户推送物品信息。In a second aspect, an embodiment of the present disclosure provides an information pushing device, the device includes: a search information determining unit configured to determine search information based on user operation behavior information; and a first pushing unit configured to push to the user The target long video, where the target long video is a long video in the long video set whose tag information matches the search information, the tag information is used to record the feature category of the long video, and each long video in the long video set includes at least one short video, The short video is correspondingly provided with item ID information; the second pushing unit is configured to respond to the user's selection operation of the short video included in the target long video, and push the item to the user based on the item ID information corresponding to the selected short video information.

在一些实施例中，长视频的步骤进一步包括：将长视频的标签信息存储到第一数据库，在第一数据库中建立长视频与对应的标签信息的索引关系；将长视频中的短视频对应的物品ID信息存储到第二数据库，在第二数据库中建立短视频与对应的物品ID信息的索引关系。In some embodiments, the step of the long video further includes: storing the tag information of the long video in a first database, and establishing an index relationship between the long video and the corresponding tag information in the first database; corresponding short videos in the long video The item ID information of is stored in the second database, and the index relationship between the short video and the corresponding item ID information is established in the second database.

在一些实施例中，装置包括：接收单元，被配置成接收用户发送的目标长视频的播放指令，播放目标长视频；短视频确定单元，被配置成响应于接收到目标长视频的暂停指令，确定目标长视频暂停时显示的图像所属的短视频为用户选择的短视频。In some embodiments, the device includes: a receiving unit configured to receive a playback instruction of the target long video sent by a user, and to play the target long video; and a short video determining unit configured to respond to receiving a pause instruction of the target long video, It is determined that the short video to which the image displayed when the target long video is paused belongs to is the short video selected by the user.

本公开的实施例提供的信息推送方法和装置，通过用户的操作行为信息确定搜索信息，之后向用户推送目标长视频，而后响应于用户对目标长视频所包括的短视频的选择操作，基于与所选择的短视频对应的物品ID信息向该用户推送物品信息，从而使得用户可以实现通过从长视频中选择短视频来获取对应的物品信息，提高了信息推送的针对性。The information pushing method and device provided by the embodiments of the present disclosure determine the search information based on the user's operation behavior information, and then push the target long video to the user, and then respond to the user's selection operation of the short video included in the target long video, based on and The item ID information corresponding to the selected short video pushes the item information to the user, so that the user can obtain the corresponding item information by selecting the short video from the long video, which improves the pertinence of the information push.

附图说明Description of the drawings

通过阅读参照以下附图所作的对非限制性实施例所作的详细描述，本公开的其它特征、目的和优点将会变得更明显：By reading the detailed description of the non-limiting embodiments with reference to the following drawings, other features, purposes and advantages of the present disclosure will become more apparent:

图1是本公开的一些实施例可以应用于其中的示例性***架构图；FIG. 1 is an exemplary system architecture diagram in which some embodiments of the present disclosure can be applied;

图2是根据本公开的信息推送方法的一个实施例的流程图；Fig. 2 is a flowchart of an embodiment of an information pushing method according to the present disclosure;

图3是根据本公开的实施例的信息推送方法的一个应用场景的示意图；Fig. 3 is a schematic diagram of an application scenario of an information pushing method according to an embodiment of the present disclosure;

图4是根据本实施例的信息推送方法中的长视频生成方法的流程图；Fig. 4 is a flowchart of a method for generating a long video in an information pushing method according to this embodiment;

图5是根据本公开的信息推送方法的又一个实施例的流程图；FIG. 5 is a flowchart of another embodiment of the information pushing method according to the present disclosure;

图6是根据本公开的信息推送装置的一个实施例的结构示意图；Fig. 6 is a schematic structural diagram of an embodiment of an information pushing device according to the present disclosure;

图7是适于用来实现本公开的实施例的电子设备的结构示意图。FIG. 7 is a schematic structural diagram of an electronic device suitable for implementing the embodiments of the present disclosure.

具体实施方式Detailed ways

下面结合附图和实施例对本公开作进一步的详细说明。可以理解的是，此处所描述的具体实施例仅仅用于解释相关发明，而非对该发明的限定。另外还需要说明的是，为了便于描述，附图中仅示出了与有关发明相关的部分。The present disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described here are only used to explain the related invention, but not to limit the invention. In addition, it should be noted that, for ease of description, only the parts related to the relevant invention are shown in the drawings.

需要说明的是，在不冲突的情况下，本公开中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本公开。It should be noted that the embodiments in the present disclosure and the features in the embodiments can be combined with each other if there is no conflict. Hereinafter, the present disclosure will be described in detail with reference to the drawings and in conjunction with the embodiments.

图1示出了可以应用本公开的实施例的信息推送方法或信息推送装置的示例性***架构100。FIG. 1 shows an exemplary system architecture 100 of an information pushing method or an information pushing device to which embodiments of the present disclosure can be applied.

如图1所示，***架构100可以包括终端设备101、102、103，网络104和服务器105。网络104用以在终端设备101、102、103和服务器105之间提供通信链路的介质。网络104可以包括各种连接类型，例如有线、无线通信链路或者光纤电缆等等。As shown in FIG. 1, the system architecture 100 may include

terminal devices

101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the

terminal devices

101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, and so on.

用户可以使用终端设备101、102、103通过网络104与服务器105交互，以接收或发送消息等。终端设备101、102、103上可以安装有各种通讯客户端应用，例如视频类应用、购物类应用、网页浏览器应用、搜索类应用、即时通信工具、邮箱客户端、社交平台软件等。The user can use the

terminal devices

101, 102, and 103 to interact with the server 105 through the network 104 to receive or send messages and so on. Various communication client applications, such as video applications, shopping applications, web browser applications, search applications, instant messaging tools, email clients, and social platform software, may be installed on the

terminal devices

101, 102, and 103.

终端设备101、102、103可以是硬件，也可以是软件。当终端设备101、102、103为硬件时，可以是具有显示屏并且支持视频播放的各种电子设备，包括但不限于智能手机、平板电脑、电子书阅读器、膝上型便携计算机和台式计算机等等。当终端设备101、102、103为软件时，可以安装在上述所列举的电子设备中。其可以实现成例如用来提供分布式服务的多个软件或软件模块，也可以实现成单个软件或软件模块。在此不做具体限定。The

terminal devices

101, 102, 103 may be hardware or software. When the

terminal devices

101, 102, 103 are hardware, they can be various electronic devices that have a display screen and support video playback, including but not limited to smart phones, tablet computers, e-book readers, laptop portable computers, and desktop computers and many more. When the

terminal devices

101, 102, and 103 are software, they can be installed in the electronic devices listed above. It can be implemented, for example, as multiple software or software modules for providing distributed services, or as a single software or software module. There is no specific limitation here.

服务器105可以是提供各种服务的服务器，例如对终端设备101、102、103上播放的视频提供支持的后台服务器。后台服务器可以对用户的操作行为信息和所选择的短视频等数据进行分析等处理，并将处理结果(例如物品信息)反馈给终端设备。The server 105 may be a server that provides various services, for example, a back-end server that provides support for videos played on the

terminal devices

101, 102, and 103. The back-end server can analyze and process the user's operation behavior information and selected short video and other data, and feed back the processing result (for example, item information) to the terminal device.

需要说明的是，本公开的实施例所提供的用于推送信息的方法可以由终端设备101、102、103执行，也可以由服务器105执行。相应地，用于推送信息的装置可以设置于终端设备101、102、103中，也可以设置于服务器105中。在此不做具体限定。It should be noted that the method for pushing information provided by the embodiments of the present disclosure may be executed by the

terminal devices

101, 102, 103, or may be executed by the server 105. Correspondingly, the device for pushing information may be set in the

terminal devices

101, 102, 103, or may be set in the server 105. There is no specific limitation here.

需要说明的是，服务器可以是硬件，也可以是软件。当服务器为硬件时，可以实现成多个服务器组成的分布式服务器集群，也可以实现成单个服务器。当服务器为软件时，可以实现成例如用来提供分布式服务的多个软件或软件模块，也可以实现成单个软件或软件模块。在此不做具体限定。It should be noted that the server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or as a single server. When the server is software, it can be implemented as multiple software or software modules for providing distributed services, or as a single software or software module. There is no specific limitation here.

应该理解，图1中的终端设备、网络和服务器的数目仅仅是示意性的。根据实现需要，可以具有任意数目的终端设备、网络和服务器。It should be understood that the numbers of terminal devices, networks, and servers in FIG. 1 are merely illustrative. According to implementation needs, there can be any number of terminal devices, networks, and servers.

需要指出的是，终端设备101、102、103中也可以预先存储有长视频集合，终端设备101、102、103可以向用户推送与搜索信息相匹配的目标长视频，并可以基于与用户选择的短视频对应的ID信息推送物品信息，此时，信息推送方法也可以由终端设备101、102、103执行，相应地，信息推送装置也可以设置于终端设备101、102、103中。此时，示例性***架构100可以不存在服务器105和网络104。It should be pointed out that the

terminal devices

101, 102, 103 can also pre-store long video sets. The

terminal devices

101, 102, 103 can push the target long video that matches the search information to the user, and can be based on the user’s selection. The ID information corresponding to the short video pushes the item information. At this time, the information pushing method can also be executed by the

terminal devices

101, 102, 103, and accordingly, the information pushing device can also be provided in the

terminal devices

101, 102, 103. At this time, the server 105 and the network 104 may not exist in the exemplary system architecture 100.

继续参考图2，示出了根据本公开的信息推送方法的一个实施例的流程200。该信息推送方法，包括以下步骤：Continuing to refer to FIG. 2, a process 200 of an embodiment of the information pushing method according to the present disclosure is shown. The information push method includes the following steps:

步骤201，基于用户的操作行为信息，确定搜索信息。Step 201: Determine search information based on the user's operation behavior information.

在本实施例中，对于用户的操作行为信息，信息推送方法的执行主体(例如图1所示的服务器)可以采用信息提取等方式处理该用户的操作行为信息，从而确定出搜索信息。可以理解的是，上述操作行为信息可以为点击行为信息、浏览行为信息或文字输入行为信息等，这里没有唯一的限定。上述执行主体可以根据用户的点击、浏览或文字输入等操作得到用户的操作行为信息。In this embodiment, for the user's operation behavior information, the execution body of the information push method (for example, the server shown in FIG. 1) can process the user's operation behavior information by means of information extraction, etc., so as to determine the search information. It is understandable that the aforementioned operation behavior information may be click behavior information, browsing behavior information, or text input behavior information, etc., and there is no unique limitation here. The above-mentioned execution subject may obtain the user's operation behavior information according to the user's click, browse, or text input operation.

作为示例，用户可以在终端设备上输入用于搜索的文字，用户的操作行为信息可以包括输入的文字信息，并将所输入的文字信息确定为用于搜索视频的搜索信息。或者，用户在终端上进行视频浏览或网页浏览，上述执行主体可以得到用户的视频浏览信息或网页浏览信息，并对用户的视频浏览信息或网页浏览信息进行归纳提取，得到用户所关心的信息，将所得到的信息确定为搜索信息。As an example, the user may input text for searching on the terminal device, the user's operation behavior information may include the input text information, and the input text information is determined as the search information for searching the video. Or, the user performs video browsing or web browsing on the terminal, the above-mentioned execution subject can obtain the user's video browsing information or web browsing information, and summarize and extract the user's video browsing information or web browsing information to obtain the information that the user cares about. Determine the obtained information as search information.

步骤202，向用户推送目标长视频。Step 202: Push the target long video to the user.

在本实施例中，基于步骤201确定的搜索信息，上述执行主体(例如图1所示的服务器)可以向用户推送与搜索信息对应的目标长视频。其中，目标长视频可以为长视频集合中、标签信息与搜索信息相匹配的长视频。因此，上述执行主体可以预先建立包含至少一个长视频的长视频集合，并且该长视频集合中的个长视频设有标签信息。这里，长视频的标签信息可以用于记录该长视频的特征类别，例如，标签信息可以为古代女装、男士皮鞋等。长视频集合中的各长视频可以包括至少两个短视频，并且长视频中的各短视频可以对应设有物品的ID信息。In this embodiment, based on the search information determined in step 201, the execution subject (for example, the server shown in FIG. 1) may push the target long video corresponding to the search information to the user. Among them, the target long video may be a long video whose tag information matches the search information in the long video set. Therefore, the above-mentioned execution subject may pre-establish a long video set containing at least one long video, and each long video in the long video set is provided with tag information. Here, the tag information of the long video can be used to record the feature category of the long video. For example, the tag information can be ancient women's clothing, men's leather shoes, and so on. Each long video in the long video set may include at least two short videos, and each short video in the long video may be correspondingly provided with ID information of the item.

在确定出搜索信息后，上述执行主体可以将所确定的搜索信息与预设的长视频集合中各长视频的标签信息进行匹配，从而可以从长视频集合中确定出标签信息与搜索信息相配的长视频，并将所确定的长视频确定为目标长视频。可以理解的是，上述执行主体可以确定出一个或多个目标长视频，并将所确定的长视频推送给用户。After the search information is determined, the above-mentioned executive body can match the determined search information with the tag information of each long video in the preset long video set, so that the tag information matching the search information can be determined from the long video set. Long video, and determine the determined long video as the target long video. It is understandable that the above-mentioned executive body may determine one or more target long videos, and push the determined long videos to the user.

通常，用户利用终端上安装的视频类应用来播放视频，这时，用户可以利用终端上安装的视频类应用播放所得到的目标长视频。在本实施例中，上述视频可以包括MPEG格式、AVI格式、nAVI格式、 ASF格式、MOV格式、WMV格式、3GP格式、RMVB格式的视频或者其它未来将开发的格式的视频(只要这种格式的视频可以用视频类应用打开并播放器所包含的图像帧内容)。Generally, the user uses the video application installed on the terminal to play the video. At this time, the user can use the video application installed on the terminal to play the obtained target long video. In this embodiment, the above-mentioned video may include MPEG format, AVI format, nAVI format, ASF format, MOV format, WMV format, 3GP format, RMVB format video or other formats that will be developed in the future (as long as this format is The video can be opened with a video application and the content of the image frame contained in the player).

步骤203，响应于用户对目标长视频所包括的短视频的选择操作，基于与所选择的短视频对应的物品ID信息，向用户推送物品信息。Step 203: In response to the user's selection operation of the short video included in the target long video, push item information to the user based on the item ID information corresponding to the selected short video.

在本实施例中，基于步骤202推送的目标长视频，上述执行主体可以确定用户对目标长视频中所包括的短视频的选择操作，从而可以确定出用户所选择的短视频。上述执行主体可以确定与所选择的短视频对应的物品ID信息，并采用各种方式处理与所选择的短视频对应的物品ID信息，从而确定并向用户推送物品信息。作为示例，上述物品ID信息可以包括物品的名称、描述信息和价格信息等，上述执行主体可以将物品ID信息所包含的物品的名称、描述信息和价格信息推送给用户，以使用户可以得到物品信息。In this embodiment, based on the target long video pushed in step 202, the above-mentioned execution subject can determine the user's selection operation of the short video included in the target long video, so that the short video selected by the user can be determined. The above-mentioned execution subject may determine the item ID information corresponding to the selected short video, and use various methods to process the item ID information corresponding to the selected short video, thereby determining and pushing the item information to the user. As an example, the above item ID information may include the name, description information, and price information of the item, and the above executive body may push the name, description information, and price information of the item contained in the item ID information to the user, so that the user can obtain the item. information.

可以理解的是，用户可以通过各种方式从目标长视频中选择短视频，例如，用户可以将鼠标图标放到目标长视频的进度条，鼠标所在位置对应的短视频即为用户所选择的短视频。It is understandable that the user can select a short video from the target long video in various ways. For example, the user can place the mouse icon on the progress bar of the target long video, and the short video corresponding to the position of the mouse is the short video selected by the user. video.

在本实施例的一些可选的实现方式中，上述执行主体在确定出物品ID信息后，可以进一步确定与该物品ID信息对应的物品网页链接。例如，物品网页链接可以为电商平台中物品销售的网页链接。而后，上述执行主体可以向用户推送与所确定的物品ID信息对应的网页链接，或者可以直接向用户推送该网页链接对应网页。因此，采用本实施例所公开的信息推送方法，用户在对目标长视频中的物品感兴趣时，可以随时获取所感兴趣物品的信息，并可以快速进入物品购买网页，进一步带来订单成交。In some optional implementation manners of this embodiment, after determining the item ID information, the above-mentioned execution subject may further determine the item webpage link corresponding to the item ID information. For example, the article webpage link may be a webpage link for article sales in an e-commerce platform. Then, the above-mentioned execution subject may push the webpage link corresponding to the determined item ID information to the user, or may directly push the webpage corresponding to the webpage link to the user. Therefore, by using the information push method disclosed in this embodiment, when a user is interested in an item in a target long video, the user can obtain information about the item of interest at any time, and can quickly enter the item purchase webpage, which further brings about an order transaction.

继续参见图3，图3是根据本实施例的信息推送方法的应用场景的一个示意图。在图3的应用场景中，对于用户浏览的古装电视剧，基于该用户对视频的浏览行为信息可以确定出搜索信息“古代女装”；而后，后台服务器可以从长视频集合中确定标签信息与搜索信息“古代女装”相匹配的目标长视频，并向用户推送目标长视频；最后，响应于目标用户对目标长视频所包括的短视频的选择操作，从而确定出如图3所示的图像所在的短视频，基于与该短视频对应的物品ID信息，可以向用户推送古代女装的信息301，如图3所示。Continue to refer to FIG. 3, which is a schematic diagram of an application scenario of the information pushing method according to this embodiment. In the application scenario of Figure 3, for the ancient costume TV series that the user browses, the search information "ancient women's clothing" can be determined based on the user's browsing behavior information on the video; then, the backend server can determine the tag information and search information from the long video collection The target long video that matches the "ancient women's clothing", and push the target long video to the user; finally, in response to the target user's selection operation of the short video included in the target long video, it is determined where the image shown in Figure 3 is located. The short video, based on the item ID information corresponding to the short video, can push information 301 of ancient women's clothing to the user, as shown in FIG. 3.

在一些可选的实现方式中，如图4所示，其示出了根据本实施例的信息推送方法中长视频的生成方法的的流程400。上述步骤202中的长视频可以采用如下步骤得到：In some optional implementation manners, as shown in FIG. 4, it shows the process 400 of the method for generating a long video in the information pushing method according to this embodiment. The long video in step 202 can be obtained by using the following steps:

步骤401，从短视频样本集合中获取满足预设条件的短视频，为所获取的短视频设置标签。Step 401: Obtain short videos meeting preset conditions from the short video sample set, and set tags for the obtained short videos.

在本实现方式中，可以预先设置用于筛选短视频的预设条件，而后从短视频样本集合中获取满足预设条件的短视频。可以理解的是，上述预设条件可以根据实际的需求进行设置，例如，预设条件可以为短视频的视频长度大于五秒。在获取满足预设条件的短视频后可以为所获取的各短视频设置标签，该标签可以用于表征该短视频的所包含的内容特征。例如，短视频的标签可以包括其所显示的场景、物品、是否包含人脸图像等信息。In this implementation manner, preset conditions for screening short videos can be preset, and then short videos meeting the preset conditions are obtained from the short video sample set. It is understandable that the foregoing preset condition can be set according to actual requirements. For example, the preset condition can be that the video length of the short video is greater than five seconds. After obtaining the short video that meets the preset condition, a tag may be set for each obtained short video, and the tag may be used to characterize the content feature contained in the short video. For example, the tag of a short video may include information such as the scene, the item, and whether it contains a face image.

在一些可选的实现方式中，上述短视频样本集合中的样品可以为从电商品台中获取的用于评价物品的短视频集合。可以理解的是，对于物品评价的短视频往往需要包含物品图像的比重较大，比重较大的短视频的参考价值往往也较大。例如，对于凉鞋商品的晒单短视频，可以判断识别出的物体中是否包含凉鞋，以及识别出含有凉鞋的图像帧占短视频的所有图像帧的比重，从而可以确定短视频中介绍与物品有关的内容占比多少。因此，上述预设条件可以包括短视频中包含物品图像的图像帧的数量与该短视频的图像帧总数的比值大于预设阈值。采用该预设条件可以从短视频样品集合中筛选出参考价值较大的短视频。短视频的标签可以包括从短视频识别出的物品的名称、视频的场景等信息。In some optional implementation manners, the samples in the above-mentioned short video sample set may be a short video set obtained from an electronic merchandise station for evaluating items. It is understandable that short videos for item evaluation often need to contain a larger proportion of the image of the item, and short videos with a larger proportion often have a larger reference value. For example, for a short video of an order for a sandal product, it can be judged whether the identified object contains sandals, and the proportion of image frames that have identified sandals in all image frames of the short video, so as to determine that the introduction in the short video is related to the item What's the proportion of content. Therefore, the foregoing preset condition may include that the ratio of the number of image frames containing the image of the article in the short video to the total number of image frames of the short video is greater than the preset threshold. Using this preset condition, short videos with greater reference value can be selected from the collection of short video samples. The tag of the short video may include information such as the name of the item recognized from the short video, and the scene of the video.

在一些可选的实现方式中，上述预设条件还可以用于从短视频样品集合中筛选出视频质量较好的短视频。因此，上述预设条件还可以包括短视频的视频质量评分大于预设评分。其中，视频质量评分可以通过短视频的分辨率、清晰度和抖动程度确定。通过该预设条件可以从短视频样品集合中剔除分辨率低、清晰度差、图像抖动剧烈的短视频，从而可以提高所获取的短视频的质量。In some optional implementation manners, the foregoing preset conditions may also be used to filter short videos with better video quality from the short video sample set. Therefore, the foregoing preset condition may also include that the video quality score of the short video is greater than the preset score. Among them, the video quality score can be determined by the resolution, clarity, and degree of jitter of the short video. Through this preset condition, short videos with low resolution, poor definition, and severe image jitter can be eliminated from the short video sample set, so that the quality of the short videos obtained can be improved.

在一些可选的实现方式中，包含人脸的视频往往更容易引起用户的兴趣。因此，可以对短视频样品集合中的各短视频进行人脸识别，从而可以获取用户更感兴趣的短视频。因此，上述预设条件还可以包括短视频中包含人脸图像。在对短视频进行人脸识别后可以，可以为该短视频设置识别结果标签，该标签可以包括人脸识别结果、检测出的人体性别、表情等。可以理解的是，现有技术已经公开了人脸识别、人脸表情识别等技术，这里不再赘述。In some alternative implementations, videos containing human faces are often more likely to arouse users' interest. Therefore, face recognition can be performed on each short video in the short video sample set, so that short videos that users are more interested in can be obtained. Therefore, the foregoing preset condition may also include that the short video contains a human face image. After performing face recognition on the short video, a recognition result label may be set for the short video, and the label may include the face recognition result, the detected human gender, expressions, and so on. It is understandable that the prior art has already disclosed technologies such as face recognition and facial expression recognition, which will not be repeated here.

可以理解的是，通过设置的预设条件可以使得所获取的每个短视频都是与物品相关的高质量视频，质量不好、与物品无关以及涉及违规违法内容的短视频都被过滤掉了。提高了生成长视频的质量。It is understandable that by setting the preset conditions, each short video obtained can be a high-quality video related to the item, and short videos that are of poor quality, have nothing to do with the item, and involve illegal content are filtered out. . Improved the quality of generating long videos.

步骤402，将短视频按照所设置的标签进行分类，并基于同类别的短视频生成长视频。Step 402: Classify short videos according to the set tags, and generate long videos based on short videos of the same category.

在本实现方式中，基于步骤401设置的标签，可以将所获取的短视频按照所设置的标签进行分类。而后将同类别的短视频合成长视频。可以理解的是，对于某一短视频，该短视频在被分类时可以属于一种类别或多种类别。作为示例，短视频的标签可以包括物品的品类，此时可以将所获取的短视频按照物品品类进行分类，得到男装、女鞋等不同类别的短视频，并将同类别的短视频合并成长视频。其中，长视频的时长可以在预设时间范围内，如1～10分钟，从而避免长视频过长或过短造成的用户体验较差的情况。这里，对于某一类别来说，该类别也可以包括一个或多个短视频。若该类别仅包括一个短视频，可以将对短视频进行处理后生成长视频，或者直接将该短视频确定为长视频。若该类别包括多个短视频，可以将各短视频进行合并，生成长视频。In this implementation manner, based on the tags set in step 401, the obtained short videos can be classified according to the set tags. Then combine short videos of the same category into long videos. It is understandable that for a certain short video, the short video can belong to one category or multiple categories when it is classified. As an example, the tag of a short video may include the category of the item. In this case, the obtained short video can be classified according to the item category, and short videos of different categories such as men's clothing and women's shoes can be obtained, and the short videos of the same category can be merged into a growing video. . Among them, the duration of the long video may be within a preset time range, such as 1 to 10 minutes, so as to avoid the situation that the long video is too long or too short to cause poor user experience. Here, for a certain category, the category may also include one or more short videos. If the category includes only one short video, the short video can be processed to generate a long video, or the short video can be directly determined as a long video. If the category includes multiple short videos, the short videos can be combined to generate a long video.

步骤403，针对长视频，基于该长视频所包括的短视频的标签，确定该长视频的标签信息。Step 403: For the long video, determine the tag information of the long video based on the tags of the short video included in the long video.

在本实现方式中，针对步骤402生成的长视频，可以采用各种方式处理该长视频所包含的短视频的标签，从而可以确定该长视频的标签信息。作为示例，可以对该长视频所包含的短视频的标签取并集，从而可以生成该长视频的标签信息。或者，还可以对该长视频所包含的短视频的标签进行物品品类信息等提取，从而可以生成该长视频的标签信息。这里，可以根据实际的需求确定长视频的标签信息。In this implementation manner, for the long video generated in step 402, various methods can be used to process the tags of the short video contained in the long video, so that the tag information of the long video can be determined. As an example, the tags of the short videos contained in the long video can be unionized, so that tag information of the long video can be generated. Alternatively, the tag information of the short video included in the long video can be extracted, so that the tag information of the long video can be generated. Here, the tag information of the long video can be determined according to actual needs.

步骤404，为长视频中的各短视频设置对应的物品ID信息。Step 404: Set corresponding item ID information for each short video in the long video.

在本实现方式中，对于步骤402生成的长视频，除了记录该长视频的标签信息，还需要记录每个被合并的短视频对应的物品ID信息。可以理解的是，针对该长视频中的任一短视频，可以首先确定这短视频在长视频的分布时段，而后对该时段的视频设置对应物品ID信息，以便用户在观看长视频的时候，可以随时确定当前播放的视频对应的物品ID信息。In this implementation manner, for the long video generated in step 402, in addition to recording the tag information of the long video, it is also necessary to record the item ID information corresponding to each combined short video. It is understandable that for any short video in the long video, you can first determine the distribution period of the short video in the long video, and then set the corresponding item ID information for the video in this period, so that when the user watches the long video, The item ID information corresponding to the currently playing video can be determined at any time.

在一些可选的实现方式中，可以将长视频的标签信息存储到第一数据库，并在第一数据库中建立长视频与对应的标签信息的索引关系；以及将长视频中的短视频对应的物品ID信息存储到第二数据库，并在第二数据库中建立短视频与对应的物品ID信息的索引关系。作为示例，可以采用mySQL、ES等数据库进行标签信息和物品ID信息存储，把与长视频有关的标签信息的物品ID信息记录到相关的字段中，从而可以借助数据库的检索能力进行搜索。可以理解的是，这里也可以自行对长视频的标签信息建立索引，将视长频与对应的标签信息分类建立起索引关系。在此之上，还可以进一步搭建用于长视频搜索和推荐的引擎，该搜索引擎可以把搜索信息对应到长视频的标签信息上，再检索出目标长视频，推送给用户。In some optional implementations, the tag information of the long video can be stored in the first database, and the index relationship between the long video and the corresponding tag information can be established in the first database; and the short video in the long video can be corresponding to The item ID information is stored in the second database, and an index relationship between the short video and the corresponding item ID information is established in the second database. As an example, databases such as mySQL and ES can be used to store tag information and item ID information, and the item ID information of the tag information related to the long video can be recorded in the relevant fields, so that the search can be carried out with the help of the retrieval capabilities of the database. It is understandable that it is also possible to index the label information of the long video by itself, and establish an index relationship between the visual long frequency and the corresponding label information classification. On top of this, an engine for searching and recommending long videos can be further built. The search engine can map the search information to the tag information of the long videos, and then retrieve the target long videos and push them to users.

上述短视频样本集合中的样本可以为从电商平台中获取的用于评价物品的短视频集合。由于用户观看的是其所感兴趣的、来自真实用户购物体验的视频，因此利用这些短视频生成的长视频对用户的购物决策更具有参考价值，方便用户了解物品的优缺点。可选地，上述短视频样本集合中的样本可以是原始视频，也可以是从原始视频中截取的视频，这里没有唯一的限定。可以理解的是，上述短视频样本集合中的样本还可以是从其它渠道获取的短视频，这里没有具体的限定。The samples in the above-mentioned short video sample set may be a short video set obtained from an e-commerce platform for evaluating items. Since users watch the videos they are interested in and come from the real user's shopping experience, the long videos generated by using these short videos have more reference value for the user's shopping decision, and it is convenient for users to understand the advantages and disadvantages of the items. Optionally, the samples in the above-mentioned short video sample set may be the original video or a video intercepted from the original video, and there is no unique limitation here. It is understandable that the samples in the foregoing short video sample set may also be short videos obtained from other channels, and there is no specific limitation here.

可选地，为了保证电商平台可以提供足够多的、用于构成上述短视频样本集合的短视频，这里可以采用不同的方式鼓励用户发布商品评价视频。例如，当用户完成订单时可以向其发送提示用户发布商品评价视频的提示信息，进一步地，在确定用户已成功发布商品评价视频后，可以给予相应地奖励。Optionally, in order to ensure that the e-commerce platform can provide enough short videos to form the above-mentioned short video sample set, different methods can be used here to encourage users to publish product evaluation videos. For example, when the user completes an order, a prompt message may be sent to the user to prompt the user to publish a product evaluation video, and further, after it is determined that the user has successfully published the product evaluation video, a corresponding reward can be given.

本公开的上述实施例提供的信息推送方法，通过用户的操作行为信息确定搜索信息，之后向用户推送目标长视频，而后响应于用户对目标长视频所包括的短视频的选择操作，基于与所选择的短视频对应的物品ID信息向该用户推送物品信息，从而使得用户可以实现通过从长视频中选择短视频来获取对应的物品信息，提高了信息推送的针对性。The information pushing method provided by the above-mentioned embodiments of the present disclosure determines the search information based on the user's operation behavior information, and then pushes the target long video to the user, and then responds to the user's selection operation of the short video included in the target long video, based on The item ID information corresponding to the selected short video pushes the item information to the user, so that the user can obtain the corresponding item information by selecting the short video from the long video, which improves the pertinence of the information push.

进一步参考图5，其示出了信息推送方法的又一个实施例的流程500。该信息推送方法的流程500，包括以下步骤：With further reference to FIG. 5, it shows a process 500 of another embodiment of an information pushing method. The process 500 of the information push method includes the following steps:

步骤501，基于用户的操作行为信息，确定搜索信息。Step 501: Determine search information based on the user's operation behavior information.

步骤502，向用户推送目标长视频。Step 502: Push the target long video to the user.

在本实施例中，基于步骤501确定的搜索信息，上述执行主体(例如图1所示的服务器)可以向用户推送与搜索信息对应的目标长视频。其中，目标长视频可以为长视频集合中、标签信息与搜索信息相匹配的长视频。因此，上述执行主体可以预先建立包含至少两个长视频的长视频集合，并且该长视频集合中的个长视频设有标签信息。这里，长视频的标签信息可以用于记录该长视频的特征类别，例如，标签信息可以为古代女装、男士皮鞋等。长视频集合中的各长视频可以包括至少两个短视频，并且长视频中的各短视频可以对应设有物品的ID信息。In this embodiment, based on the search information determined in step 501, the execution subject (for example, the server shown in FIG. 1) may push the target long video corresponding to the search information to the user. Among them, the target long video may be a long video whose tag information matches the search information in the long video set. Therefore, the above-mentioned execution subject may pre-establish a long video set containing at least two long videos, and each long video in the long video set is provided with tag information. Here, the tag information of the long video can be used to record the feature category of the long video. For example, the tag information can be ancient women's clothing, men's leather shoes, and so on. Each long video in the long video set may include at least two short videos, and each short video in the long video may be correspondingly provided with ID information of the item.

步骤503，接收用户发送的目标长视频的播放指令，控制目标长视频播放。Step 503: Receive a playback instruction of the target long video sent by the user, and control the playback of the target long video.

在本实施例中，用户在接收到推送的目标长视频后，可以向上述执行主体发送用于控制目标长视频播放的播放指令。上述执行主体在接收到用户发送的播放指令后，可以控制该目标长视频进行播放。In this embodiment, after receiving the pushed target long video, the user may send a playback instruction for controlling the playback of the target long video to the above-mentioned execution subject. After receiving the playback instruction sent by the user, the above-mentioned execution subject can control the target long video to be played.

步骤504，响应于接收到目标长视频的暂停指令，确定目标长视频暂停时显示的图像所属的短视频为用户选择的短视频。 Step 504, in response to receiving the pause instruction of the target long video, determine that the short video to which the image displayed when the target long video is paused belongs to is the short video selected by the user.

在本实施例中，用户在观看所播放的目标长视频的过程中，可以从目标长视频中确定其所感兴趣的物品。并在确定出其感兴趣的物品时发送视频暂停指令。上述执行主体在接收到目标长视频的暂停指令后，可以确定出目标长视频暂停时显示的图像所属的短视频，并将该短视频确定为用户选择的短视频。In this embodiment, in the process of watching the played target long video, the user can determine the item of interest from the target long video. And send a video pause instruction when the item of interest is determined. After receiving the pause instruction of the target long video, the above-mentioned execution subject may determine the short video to which the image displayed when the target long video is paused belongs, and determine the short video as the short video selected by the user.

步骤505，基于与所选择的短视频对应的物品ID信息，向用户推送物品信息。Step 505: Push the item information to the user based on the item ID information corresponding to the selected short video.

在本实施例中，上述执行主体在确定出与用户所选择的短视频对应的物品ID信息后，可以采用各种方式处理与所选择的短视频对应的物品ID信息，从而确定并向用户推送物品信息。作为示例，上述物品ID信息可以包括物品的名称、描述信息和价格信息等，上述执行主体可以将物品ID信息所包含的物品的名称、描述信息和价格信息推送给用户，以使用户可以得到物品信息。In this embodiment, after the above-mentioned executive body determines the item ID information corresponding to the short video selected by the user, it can use various methods to process the item ID information corresponding to the selected short video, thereby determining and pushing to the user Item information. As an example, the above item ID information may include the name, description information, and price information of the item, and the above executive body may push the name, description information, and price information of the item contained in the item ID information to the user, so that the user can obtain the item. information.

从图5中可以看出，与图2对应的实施例相比，本实施例中的信息推送方法的流程500，用户在观看目标长视频的过程中，可以暂停目标长视频的方式确定所选择短视频，操作简单，从而可以提高了物品信息的推送效率。It can be seen from FIG. 5 that, compared with the embodiment corresponding to FIG. 2, in the process 500 of the information pushing method in this embodiment, the user can pause the target long video to determine the selected long video while watching the target long video. Short video, simple operation, which can improve the efficiency of pushing item information.

进一步参考图6，作为对上述各图所示方法的实现，本公开提供了一种信息推送装置的一个实施例，该装置实施例与图2所示的方法实施例相对应，该装置具体可以应用于各种电子设备中。With further reference to FIG. 6, as an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of an information push device. The device embodiment corresponds to the method embodiment shown in FIG. Used in various electronic devices.

如图6所示，本实施例的信息推送装置600包括：搜索信息确定单元601、第一推送单元602、第二推送单元603。其中，搜索信息确定单元601被配置成基于用户的操作行为信息，确定搜索信息；第一推送单元602被配置成向用户推送目标长视频，其中，目标长视频为长视频集合中、标签信息与搜索信息匹配的长视频，标签信息用于记录长视频的特征类别，长视频集合中的各长视频包括至少一个短视频，短视频对应设有物品ID信息；第二推送单元603被配置成响应于用户对目标长视频所包括的短视频的选择操作，基于与所选择的短视频对应的物品ID信息，向用户推送物品信息。As shown in FIG. 6, the information pushing device 600 of this embodiment includes: a search information determining unit 601, a first pushing unit 602, and a second pushing unit 603. Wherein, the search information determining unit 601 is configured to determine the search information based on the user's operation behavior information; the first pushing unit 602 is configured to push the target long video to the user, where the target long video is the long video set, tag information and Search for long videos that match the information. The tag information is used to record the feature categories of the long videos. Each long video in the long video set includes at least one short video, and the short video is correspondingly provided with item ID information; the second pushing unit 603 is configured to respond For the user's selection operation of the short video included in the target long video, the item information is pushed to the user based on the item ID information corresponding to the selected short video.

在本实施例的一些可选的实现方式中，长视频通过如下步骤得到：从短视频样本集合中获取满足预设条件的短视频，为所获取的短视频设置标签，其中，标签包括短视频的特征信息；将短视频按照所设置的标签进行分类，并基于同类别的短视频生成长视频，其中，长视频的时长在预设时间范围内；针对长视频，基于该长视频所包括的短视频的标签，确定该长视频的标签信息；为长视频中的各短视频设置对应的物品ID信息。In some optional implementations of this embodiment, the long video is obtained by the following steps: obtaining a short video meeting preset conditions from the short video sample set, and setting tags for the obtained short video, where the tags include the short video The feature information of the short video; classify short videos according to the set tags, and generate long videos based on short videos of the same category, where the length of the long video is within the preset time range; for long videos, based on the long video included The tag of the short video determines the tag information of the long video; sets the corresponding item ID information for each short video in the long video.

在本实施例的一些可选的实现方式中，预设条件包括：短视频中包含目标物品图像的图像帧的数量与短视频的图像帧总数的比值大于预设阈值。In some optional implementations of this embodiment, the preset condition includes: the ratio of the number of image frames containing the target item image in the short video to the total number of image frames of the short video is greater than the preset threshold.

在本实施例的一些可选的实现方式中，预设条件包括：短视频的视频质量评分大于预设评分，其中，视频质量评分通过短视频的分辨率、清晰度和抖动程度确定。In some optional implementations of this embodiment, the preset condition includes: the video quality score of the short video is greater than the preset score, where the video quality score is determined by the resolution, clarity, and jitter degree of the short video.

在本实施例的一些可选的实现方式中，预设条件包括：短视频中包含人脸图像。In some optional implementation manners of this embodiment, the preset condition includes: the short video contains a face image.

在本实施例的一些可选的实现方式中，长视频的步骤进一步包括：将长视频的标签信息存储到第一数据库，在第一数据库中建立长视频与对应的标签信息的索引关系；将长视频中的短视频对应的物品ID信息存储到第二数据库，在第二数据库中建立短视频与对应的物品ID信息的索引关系。In some optional implementations of this embodiment, the step of the long video further includes: storing the tag information of the long video in a first database, and establishing an index relationship between the long video and the corresponding tag information in the first database; The item ID information corresponding to the short video in the long video is stored in the second database, and an index relationship between the short video and the corresponding item ID information is established in the second database.

在本实施例的一些可选的实现方式中，装置包括：接收单元，被配置成接收用户发送的目标长视频的播放指令，播放目标长视频；短视频确定单元，被配置成响应于接收到目标长视频的暂停指令，确定目标长视频暂停时显示的图像所属的短视频为用户选择的短视频。In some optional implementations of this embodiment, the device includes: a receiving unit configured to receive a playback instruction of the target long video sent by the user, and to play the target long video; and the short video determining unit is configured to respond to receiving The pause instruction of the target long video determines that the short video to which the image displayed when the target long video is paused belongs to is the short video selected by the user.

装置600中记载的诸单元与参考图2描述的方法中的各个步骤相对应。由此，上文针对方法描述的操作和特征同样适用于装置600及其中包含的单元，在此不再赘述。The units recorded in the device 600 correspond to the steps in the method described with reference to FIG. 2. Therefore, the operations and features described above for the method are also applicable to the device 600 and the units included therein, and will not be repeated here.

下面参考图7，其示出了适于用来实现本公开的实施例的电子设备(例如图1中的服务器)700的结构示意图。图7示出的服务器仅仅是一个示例，不应对本公开的实施例的功能和使用范围带来任何限制。Referring now to FIG. 7, it shows a schematic structural diagram of an electronic device (for example, the server in FIG. 1) 700 suitable for implementing the embodiments of the present disclosure. The server shown in FIG. 7 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present disclosure.

如图7所示，电子设备700可以包括处理装置(例如中央处理器、图形处理器等)701，其可以根据存储在只读存储器(ROM)702中的程序或者从存储装置708加载到随机访问存储器(RAM)703中的程序而执行各种适当的动作和处理。在RAM 703中，还存储有电子设备700操作所需的各种程序和数据。处理装置701、ROM 702以及RAM703通过总线704彼此相连。输入/输出(I/O)接口705也连接至总线704。As shown in FIG. 7, the electronic device 700 may include a processing device (such as a central processing unit, a graphics processor, etc.) 701, which may be loaded into a random access device according to a program stored in a read-only memory (ROM) 702 or from a storage device 708. The program in the memory (RAM) 703 executes various appropriate actions and processing. In the RAM 703, various programs and data required for the operation of the electronic device 700 are also stored. The processing device 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to the bus 704.

通常，以下装置可以连接至I/O接口705：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置706；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置707；包括例如磁带、硬盘等的存储装置708；以及通信装置709。通信装置709可以允许电子设备700与其他设备进行无线或有线通信以交换数据。虽然图7示出了具有各种装置的电子设备700，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。图7中示出的每个方框可以代表一个装置，也可以根据需要代表多个装置。Generally, the following devices can be connected to the I/O interface 705: including input devices 706 such as touch screens, touch pads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; including, for example, liquid crystal displays (LCD), speakers, vibrations An output device 707 such as a device; a storage device 708 such as a magnetic tape, a hard disk, etc.; and a communication device 709. The communication device 709 may allow the electronic device 700 to perform wireless or wired communication with other devices to exchange data. Although FIG. 7 shows an electronic device 700 having various devices, it should be understood that it is not required to implement or have all of the illustrated devices. It may alternatively be implemented or provided with more or fewer devices. Each block shown in FIG. 7 may represent one device, or may represent multiple devices as needed.

特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置709从网络上被下载和安装，或者从存储装置708被安装，或者从ROM 702被安装。在该计算机程序被处理装置701执行时，执行本公开的实施例的方法中限定的上述功能。需要说明的是，本公开的实施例的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的***、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开的实施例中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行***、装置或者器件使用或者与其结合使用。而在本公开的实施例中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行***、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network through the communication device 709, or installed from the storage device 708, or installed from the ROM 702. When the computer program is executed by the processing device 701, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed. It should be noted that the computer-readable medium of the embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination of any of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable removable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In the embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device. In the embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as a part of a carrier wave, and a computer-readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium. The computer-readable signal medium may send, propagate or transmit the program for use by or in combination with the instruction execution system, apparatus, or device . The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.

上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：基于用户的操作行为信息，确定搜索信息；向用户推送目标长视频，其中，目标长视频为长视频集合中、标签信息与搜索信息匹配的长视频，标签信息用于记录长视频的特征类别，长视频集合中的各长视频包括至少一个短视频，短视频对应设有物品ID信息；响应于用户对目标长视频所包括的短视频的选择操作，基于与所选择的短视频对应的物品ID信息，向用户推送物品信息。The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist alone without being assembled into the electronic device. The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: determines the search information based on the user's operation behavior information; pushes the target long video to the user, Among them, the target long video is the long video in the long video set whose tag information matches the search information. The tag information is used to record the feature category of the long video. Each long video in the long video set includes at least one short video. There is item ID information; in response to the user's selection operation of the short video included in the target long video, the item information is pushed to the user based on the item ID information corresponding to the selected short video.

可以以一种或多种程序设计语言或其组合来编写用于执行本公开的实施例的操作的计算机程序代码，程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)——连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。The computer program code used to perform the operations of the embodiments of the present disclosure can be written in one or more programming languages or a combination thereof. The programming languages include object-oriented programming languages—such as Java, Smalltalk, C++, and Conventional procedural programming language-such as "C" language or similar programming language. The program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user’s computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to Connect via the Internet).

附图中的流程图和框图，图示了按照本公开各种实施例的***、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的***来实现，或者可以用专用硬件与计算机指令的组合来实现。The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions, and operations of the system, method, and computer program product according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, program segment, or part of code, and the module, program segment, or part of code contains one or more for realizing the specified logical function Executable instructions. It should also be noted that, in some alternative implementations, the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two blocks shown in succession can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations Or it can be realized by a combination of dedicated hardware and computer instructions.

描述于本公开的实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。所描述的单元也可以设置在处理器中，例如，可以描述为：一种处理器包括搜索信息确定单元、第一推送单元、第二推送单元。其中，这些单元的名称在某种情况下并不构成对该单元本身的限定，例如，搜索信息确定单元还可以被描述为“基于用户的操作行为信息，确定搜索信息的单元”。The units involved in the embodiments described in the present disclosure may be implemented in a software manner, and may also be implemented in a hardware manner. The described unit may also be provided in the processor. For example, it may be described as: a processor includes a search information determining unit, a first pushing unit, and a second pushing unit. Wherein, the names of these units do not constitute a limitation on the unit itself under certain circumstances. For example, the search information determination unit can also be described as "a unit that determines search information based on the user's operation behavior information."

以上描述仅为本公开的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开的实施例中所涉及的发明范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述发明构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开的实施例中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。The above description is only a preferred embodiment of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solution formed by the specific combination of the above technical features, and should also cover the above-mentioned inventive concept without departing from the above-mentioned inventive concept. Other technical solutions formed by any combination of technical features or their equivalent features. For example, the above-mentioned features and the technical features disclosed in the embodiments of the present disclosure (but not limited to) having similar functions are replaced with each other to form a technical solution.

Claims

一种信息推送方法，包括：An information push method, including:

基于用户的操作行为信息，确定搜索信息；Determine the search information based on the user's operating behavior information;

向所述用户推送目标长视频，其中，所述目标长视频为长视频集合中、标签信息与所述搜索信息匹配的长视频，标签信息用于记录长视频的特征类别，所述长视频集合中的各长视频包括至少一个短视频，所述短视频对应设有物品ID信息；以及Push a target long video to the user, where the target long video is a long video in a long video set whose tag information matches the search information, and the tag information is used to record the feature category of the long video, and the long video set Each long video in includes at least one short video, and the short video is correspondingly provided with item ID information; and

响应于所述用户对所述目标长视频所包括的短视频的选择操作，基于与所选择的短视频对应的物品ID信息，向所述用户推送物品信息。In response to the user's selection operation of the short video included in the target long video, item information is pushed to the user based on the item ID information corresponding to the selected short video.
根据权利要求1所述的方法，其中，所述长视频通过如下步骤得到：The method according to claim 1, wherein the long video is obtained through the following steps:

从短视频样本集合中获取满足预设条件的短视频，为所获取的短视频设置标签，其中，所述标签包括所述短视频的特征信息；Acquire short videos that meet preset conditions from the short video sample set, and set tags for the obtained short videos, where the tags include feature information of the short videos;

将所述短视频按照所设置的标签进行分类，并基于同类别的短视频生成所述长视频，其中，所述长视频的时长在预设时间范围内；Classify the short videos according to the set tags, and generate the long videos based on short videos of the same category, wherein the duration of the long videos is within a preset time range;

针对所述长视频，基于该长视频所包括的短视频的标签，确定该长视频的标签信息；以及For the long video, determine the tag information of the long video based on the tags of the short video included in the long video; and

为所述长视频中的各短视频设置对应的物品ID信息。Set corresponding item ID information for each short video in the long video.
根据权利要求2所述的方法，其中，所述预设条件包括：The method according to claim 2, wherein the preset condition comprises:

所述短视频中包含目标物品图像的图像帧的数量与所述短视频的图像帧总数的比值大于预设阈值。The ratio of the number of image frames containing the target item image in the short video to the total number of image frames of the short video is greater than a preset threshold.
根据权利要求2所述的方法，其中，所述预设条件包括：The method according to claim 2, wherein the preset condition comprises:

所述短视频的视频质量评分大于预设评分，其中，所述视频质量评分通过所述短视频的分辨率、清晰度和抖动程度确定。The video quality score of the short video is greater than a preset score, wherein the video quality score is determined by the resolution, clarity, and degree of jitter of the short video.
根据权利要求2所述的方法，其中，所述预设条件包括：The method according to claim 2, wherein the preset condition comprises:

所述短视频中包含人脸图像。The short video contains a face image.
根据权利要求2所述的方法，其中，所述方法还包括：The method according to claim 2, wherein the method further comprises:

将所述长视频的标签信息存储到第一数据库，在所述第一数据库中建立所述长视频与对应的标签信息的索引关系；以及Storing the tag information of the long video in a first database, and establishing an index relationship between the long video and the corresponding tag information in the first database; and

将所述长视频中的短视频对应的物品ID信息存储到第二数据库，在所述第二数据库中建立短视频与对应的物品ID信息的索引关系。The item ID information corresponding to the short video in the long video is stored in a second database, and an index relationship between the short video and the corresponding item ID information is established in the second database.
根据权利要求1-6任一项所述的方法，其中，所述方法包括：The method according to any one of claims 1-6, wherein the method comprises:

接收所述用户发送的目标长视频的播放指令，播放所述目标长视频；以及Receiving a playback instruction of the target long video sent by the user, and playing the target long video; and

响应于接收到所述目标长视频的暂停指令，确定所述目标长视频暂停时显示的图像所属的短视频为所述用户选择的短视频。In response to receiving the pause instruction of the target long video, it is determined that the short video to which the image displayed when the target long video is paused belongs to is the short video selected by the user.
一种信息推送装置，包括：An information push device, including:

搜索信息确定单元，被配置成基于用户的操作行为信息，确定搜索信息；The search information determining unit is configured to determine the search information based on the user's operation behavior information;

第一推送单元，被配置成向所述用户推送目标长视频，其中，所述目标长视频为长视频集合中、标签信息与所述搜索信息匹配的长视频，标签信息用于记录长视频的特征类别，所述长视频集合中的各长视频包括至少一个短视频，所述短视频对应设有物品ID信息；以及The first pushing unit is configured to push a target long video to the user, wherein the target long video is a long video in a long video set whose tag information matches the search information, and the tag information is used to record the long video Feature category, each long video in the long video set includes at least one short video, and the short video is correspondingly provided with item ID information; and

第二推送单元，被配置成响应于所述用户对所述目标长视频所包括的短视频的选择操作，基于与所选择的短视频对应的物品ID信息，向所述用户推送物品信息。The second pushing unit is configured to, in response to the user's selection operation of the short video included in the target long video, push item information to the user based on item ID information corresponding to the selected short video.
根据权利要求8所述的装置，其中，所述长视频通过如下步骤得到：The device according to claim 8, wherein the long video is obtained through the following steps:

从短视频样本集合中获取满足预设条件的短视频，为所获取的短视频设置标签，其中，所述标签包括所述短视频的特征信息；Acquire short videos that meet preset conditions from the short video sample set, and set tags for the obtained short videos, where the tags include feature information of the short videos;

将所述短视频按照所设置的标签进行分类，并基于将同类别的短视频生成所述长视频，其中，所述长视频的时长在预设时间范围内；Classifying the short videos according to the set tags, and generating the long videos based on short videos of the same category, wherein the duration of the long videos is within a preset time range;

针对所述长视频，基于该长视频所包括的短视频的标签，确定该长视频的标签信息；以及For the long video, determine the tag information of the long video based on the tags of the short video included in the long video; and

为所述长视频中的各短视频设置对应的物品ID信息。Set corresponding item ID information for each short video in the long video.
根据权利要求9所述的装置，其中，所述预设条件包括：The device according to claim 9, wherein the preset condition comprises:

所述短视频中包含目标物品图像的图像帧的数量与所述短视频的图像帧总数的比值大于预设阈值。The ratio of the number of image frames containing the target item image in the short video to the total number of image frames of the short video is greater than a preset threshold.
根据权利要求9所述的装置，其中，所述预设条件包括：The device according to claim 9, wherein the preset condition comprises:

所述短视频的视频质量评分大于预设评分，其中，所述视频质量评分通过所述短视频的分辨率、清晰度和抖动程度确定。The video quality score of the short video is greater than a preset score, wherein the video quality score is determined by the resolution, clarity, and degree of jitter of the short video.
根据权利要求9所述的装置，其中，所述预设条件包括：The device according to claim 9, wherein the preset condition comprises:

所述短视频中包含人脸图像。The short video contains a face image.
根据权利要求9所述的装置，其中，所述长视频的步骤还包括：The device according to claim 9, wherein the step of the long video further comprises:

将长视频的标签信息存储到第一数据库，在第一数据库中建立长视频与对应的标签信息的索引关系；以及Storing the tag information of the long video in the first database, and establishing an index relationship between the long video and the corresponding tag information in the first database; and

将长视频中的短视频对应的物品ID信息存储到第二数据库，在第二数据库中建立短视频与对应的物品ID信息的索引关系。The item ID information corresponding to the short video in the long video is stored in the second database, and an index relationship between the short video and the corresponding item ID information is established in the second database.
根据权利要求8-13任一项所述的装置，其中，所述装置还包括：The device according to any one of claims 8-13, wherein the device further comprises:

接收单元，被配置成接收用户发送的目标长视频的播放指令，播放目标长视频；以及The receiving unit is configured to receive the playback instruction of the target long video sent by the user, and play the target long video; and

短视频确定单元，被配置成响应于接收到目标长视频的暂停指令，确定目标长视频暂停时显示的图像所属的短视频为用户选择的短视频。The short video determining unit is configured to, in response to receiving a pause instruction of the target long video, determine that the short video to which the image displayed when the target long video is paused belongs to is the short video selected by the user.
一种电子设备，包括：An electronic device including:

一个或多个处理器；One or more processors;

存储装置，其上存储有一个或多个程序，A storage device on which one or more programs are stored,

当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1-7中任一所述的方法。When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1-7.
一种计算机可读介质，其上存储有计算机程序，其中，所述程序被处理器执行时实现如权利要求1-7中任一所述的方法。A computer readable medium having a computer program stored thereon, wherein the program is executed by a processor to implement the method according to any one of claims 1-7.