[go: up one dir, main page]

CN107229737A - Video searching method and electronic equipment - Google Patents

Video searching method and electronic equipment Download PDF

Info

Publication number
CN107229737A
CN107229737A CN201710449090.6A CN201710449090A CN107229737A CN 107229737 A CN107229737 A CN 107229737A CN 201710449090 A CN201710449090 A CN 201710449090A CN 107229737 A CN107229737 A CN 107229737A
Authority
CN
China
Prior art keywords
video
key frame
search
candidate
target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201710449090.6A
Other languages
Chinese (zh)
Inventor
曹建中
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Genius Technology Co Ltd
Original Assignee
Guangdong Genius Technology Co Ltd
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 Guangdong Genius Technology Co Ltd filed Critical Guangdong Genius Technology Co Ltd
Priority to CN201710449090.6A priority Critical patent/CN107229737A/en
Publication of CN107229737A publication Critical patent/CN107229737A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/73Querying
    • G06F16/735Filtering based on additional data, e.g. user or group profiles
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/78Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/783Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/7837Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Library & Information Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses a video searching method and electronic equipment, wherein the method comprises the following steps: receiving a video search request, wherein the video search request comprises search terms and a search range; determining candidate videos according to the search range of the video search request, wherein the candidate videos comprise at least one video, and each video is provided with a plurality of video key frames; matching the image content of the video key frame of each video of the candidate videos with the search terms in the video search request, and determining a target video from the candidate videos; and displaying the target video. The embodiment of the invention can improve the accuracy of the search result.

Description

一种视频搜索的方法及电子设备Method and electronic device for video search

技术领域technical field

本发明涉及互联网技术领域,具体涉及一种视频搜索的方法及电子设备。The invention relates to the technical field of the Internet, in particular to a video search method and electronic equipment.

背景技术Background technique

随着互联网技术的快速发展,互联网上可供用户搜索的视频资源也越来越多,在众多的视频资源中,准确搜索出用户需要的视频资源也显得尤为重要。目前,主要采用人工运营的方式,将视频进行拆分,并为拆分出的每个视频片段添加关键字作为标题。用户通过统一的搜索框,输入搜索词进行全网搜索,若搜索词与添加的关键字完全匹配,则展示搜索结果。由于现有技术从视频的拆分到标题的添加,都需要人工运行,其工作量大。其次不同人的描述方式区别也可能很大,这可能导致同一视频片段,用户输入的搜索词与该视频片段添加的关键字完全不匹配,使得搜索结果准确率较低。With the rapid development of Internet technology, there are more and more video resources available for users to search on the Internet. Among the numerous video resources, it is particularly important to accurately search for the video resources required by users. At present, the manual operation method is mainly used to split the video, and add keywords as titles to each split video segment. Users enter search terms through the unified search box to search the entire network. If the search terms exactly match the added keywords, the search results will be displayed. Since the prior art requires manual operations from video splitting to title addition, the workload is heavy. Secondly, the description methods of different people may also be very different, which may lead to the same video clip, the search term entered by the user does not match the keyword added to the video clip, making the accuracy of the search result lower.

发明内容Contents of the invention

本发明实施例公开了一种视频搜索的方法及电子设备,能够提高搜索结果的准确率。The embodiment of the invention discloses a video search method and electronic equipment, which can improve the accuracy of search results.

本发明实施例第一方面公开了一种视频搜索的方法,所述方法包括:The first aspect of the embodiment of the present invention discloses a video search method, the method comprising:

接收视频搜索请求,所述视频搜索请求包括搜索词以及搜索范围;Receive a video search request, the video search request includes a search term and a search scope;

根据所述视频搜索请求的搜索范围确定候选视频,所述候选视频包括至少一个视频,每个所述视频设有多个视频关键帧;Determine candidate videos according to the search range of the video search request, where the candidate videos include at least one video, each of which has multiple video key frames;

将所述候选视频的各个视频的视频关键帧的图像内容与所述视频搜索请求中的搜索词进行匹配,从所述候选视频中确定出目标视频;Matching the image content of the video key frame of each video of the candidate video with the search term in the video search request, and determining the target video from the candidate video;

对所述目标视频进行展示。The target video is displayed.

作为一种可选的实施方式,在本发明实施例第一方面中,所述将所述候选视频的各个视频的视频关键帧的图像内容与所述视频搜索请求中的搜索词进行匹配,从所述候选视频中确定出目标视频,包括:As an optional implementation manner, in the first aspect of the embodiment of the present invention, the matching the image content of the video key frame of each video of the candidate video with the search word in the video search request, from The target video is determined in the candidate video, including:

获取候选视频中的视频的两个视频关键帧,所述两个视频关键帧为第一视频关键帧和第二视频关键帧,所述第一视频关键帧和所述第二视频关键帧为所述视频的多个视频关键帧中时间相邻的视频关键帧;Obtain two video key frames of the video in the candidate video, the two video key frames are a first video key frame and a second video key frame, and the first video key frame and the second video key frame are all Time adjacent video key frames among the plurality of video key frames of the video;

判断所述两个视频关键帧的相似度是否小于或等于预设阈值,若是,则提取所述第一视频关键帧的图像内容;Judging whether the similarity of the two video key frames is less than or equal to a preset threshold, if so, extracting the image content of the first video key frame;

判断提取到的所述图像内容与所述搜索词是否匹配,若是,则将所述视频分类为所述目标视频。Judging whether the extracted image content matches the search word, and if so, classifying the video as the target video.

作为一种可选的实施方式,在本发明实施例第一方面中,所述方法还包括:若提取到的所述图像内容与所述搜索词不匹配,或者,若所述两个视频关键帧的相似度大于所述预设阈值,返回执行所述获取候选视频中的视频的两个视频关键帧的步骤,其中,在该步骤中获取到的所述两个视频关键帧为第三视频关键帧和所述第二视频关键帧。As an optional implementation, in the first aspect of the embodiment of the present invention, the method further includes: if the extracted image content does not match the search word, or if the two video keywords The similarity of the frame is greater than the preset threshold, return to the step of obtaining two video key frames of the video in the candidate video, wherein the two video key frames obtained in this step are the third video keyframe and the second video keyframe.

作为一种可选的实施方式,在本发明实施例第一方面中,当所述候选视频为一个正在播放的视频时,所述接收视频搜索请求包括:As an optional implementation manner, in the first aspect of the embodiment of the present invention, when the candidate video is a currently playing video, the receiving the video search request includes:

在正在播放的所述视频对应的搜索框中,接收视频搜索请求;In the search box corresponding to the video being played, receive a video search request;

所述对所述目标视频进行展示包括:The displaying of the target video includes:

在正在播放的所述视频的播放进度条中,确定出所述目标视频的播放位置,并从所述播放位置开始播放所述目标视频。In the playing progress bar of the video being played, determine the playing position of the target video, and start playing the target video from the playing position.

作为一种可选的实施方式,在本发明实施例第一方面中,当所述候选视频为全网视频集合时,所述接收视频搜索请求包括:As an optional implementation manner, in the first aspect of the embodiment of the present invention, when the candidate video is a network-wide video collection, the receiving the video search request includes:

在全网搜索框中,接收视频搜索请求;In the whole network search box, receive a video search request;

所述对所述目标视频进行展示包括:The displaying of the target video includes:

将所述目标视频以及目标视频的属性信息以列表形式进行展示。The target video and the attribute information of the target video are displayed in a list form.

本发明实施例第二方面公开了一种电子设备,所述电子设备包括:The second aspect of the embodiment of the present invention discloses an electronic device, and the electronic device includes:

处理器,适于实现各指令;以及a processor adapted to implement the instructions; and

存储设备,适于存储多条指令,所述指令适于由处理器加载并执行:A storage device adapted to store a plurality of instructions adapted to be loaded and executed by a processor:

接收视频搜索请求,所述视频搜索请求包括搜索词以及搜索范围;Receive a video search request, the video search request includes a search term and a search scope;

根据所述视频搜索请求的搜索范围确定候选视频,所述候选视频包括至少一个视频,每个所述视频设有多个视频关键帧;Determine candidate videos according to the search range of the video search request, where the candidate videos include at least one video, each of which has multiple video key frames;

将所述候选视频的各个视频的视频关键帧的图像内容与所述视频搜索请求中的搜索词进行匹配,从所述候选视频中确定出目标视频;Matching the image content of the video key frame of each video of the candidate video with the search term in the video search request, and determining the target video from the candidate video;

对所述目标视频进行展示。The target video is displayed.

作为一种可选的实施方式,在本发明实施例第二方面中,所述处理器执行将所述候选视频的各个视频的视频关键帧的图像内容与所述视频搜索请求中的搜索词进行匹配,从所述候选视频中确定出目标视频的步骤,具体为:As an optional implementation manner, in the second aspect of the embodiment of the present invention, the processor executes the search term in the video search request to perform Matching, the step of determining the target video from the candidate video, specifically:

获取候选视频中的视频的两个视频关键帧,所述两个视频关键帧为第一视频关键帧和第二视频关键帧,所述第一视频关键帧和所述第二视频关键帧为所述视频的多个视频关键帧中时间相邻的视频关键帧;Obtain two video key frames of the video in the candidate video, the two video key frames are a first video key frame and a second video key frame, and the first video key frame and the second video key frame are all Time adjacent video key frames among the plurality of video key frames of the video;

判断所述两个视频关键帧的相似度是否小于或等于预设阈值,若是,则提取所述第一视频关键帧的图像内容;Judging whether the similarity of the two video key frames is less than or equal to a preset threshold, if so, extracting the image content of the first video key frame;

判断提取到的所述图像内容与所述搜索词是否匹配,若是,则将所述视频分类为所述目标视频。Judging whether the extracted image content matches the search word, and if so, classifying the video as the target video.

作为一种可选的实施方式,在本发明实施例第二方面中,所述处理器还执行以下操作:若提取到的所述图像内容与所述搜索词不匹配,或者,若所述两个视频关键帧的相似度大于所述预设阈值,返回执行所述获取候选视频中的视频的两个视频关键帧的步骤,其中,在该步骤中获取到的所述两个视频关键帧为第三视频关键帧和所述第二视频关键帧。As an optional implementation manner, in the second aspect of the embodiments of the present invention, the processor further performs the following operations: if the extracted image content does not match the search term, or if the two The similarity of a video key frame is greater than the preset threshold, and returns to the step of obtaining two video key frames of the video in the candidate video, wherein the two video key frames obtained in this step are: The third video key frame and the second video key frame.

作为一种可选的实施方式,在本发明实施例第二方面中,As an optional implementation manner, in the second aspect of the embodiment of the present invention,

当所述候选视频为一个正在播放的视频时,所述处理器执行接收视频搜索请求的步骤,具体为:在正在播放的所述视频对应的搜索框中,接收视频搜索请求;When the candidate video is a video being played, the processor executes the step of receiving a video search request, specifically: receiving a video search request in a search box corresponding to the video being played;

所述处理器执行对所述目标视频进行展示的步骤,具体为:在正在播放的所述视频的播放进度条中,确定出所述目标视频的播放位置,并从所述播放位置开始播放所述目标视频。The processor executes the step of displaying the target video, specifically: determining the playback position of the target video in the playback progress bar of the video being played, and starting to play the target video from the playback position. Describe the target video.

作为一种可选的实施方式,在本发明实施例第二方面中,As an optional implementation manner, in the second aspect of the embodiment of the present invention,

当所述候选视频为全网视频集合时,所述处理器执行接收视频搜索请求的步骤,具体为:在全网搜索框中,接收视频搜索请求;When the candidate video is a network-wide video collection, the processor executes the step of receiving a video search request, specifically: receiving a video search request in a network-wide search box;

所述处理器执行对所述目标视频进行展示的步骤,具体为:将所述目标视频以及目标视频的属性信息以列表形式进行展示。The processor executes the step of displaying the target video, specifically: displaying the target video and attribute information of the target video in a list form.

本发明实施例第三方面公开一种计算机可读存储介质,其存储计算机程序,其中,所述计算机程序使得计算机执行本发明实施例第一方面公开的所述视频搜索的方法。The third aspect of the embodiments of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute the video search method disclosed in the first aspect of the embodiments of the present invention.

与现有技术相比,本发明实施例具有以下有益效果:Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

本发明实施例中,根据视频搜索请求的搜索范围确定候选视频,该候选视频包括至少一个视频,每个视频设有多个视频关键帧,将该候选视频的各个视频的视频关键帧的图像内容与该视频搜索请求中的搜索词进行匹配,从该候选视频中确定出目标视频,对目标视频进行展示。可见,实施本发明实施例能够直接将搜索词与视频关键帧的图像内容进行比较,从而确定出目标视频,而图像内容能够真实的反映出该视频的内容,这样基于图像内容获得的视频提高了搜索结果的准确性。In the embodiment of the present invention, the candidate video is determined according to the search scope of the video search request, the candidate video includes at least one video, each video is provided with a plurality of video key frames, and the image content of the video key frames of each video of the candidate video is Match the search term in the video search request, determine the target video from the candidate videos, and display the target video. It can be seen that implementing the embodiment of the present invention can directly compare the search term with the image content of the key frame of the video, thereby determining the target video, and the image content can truly reflect the content of the video, so that the video obtained based on the image content is improved. Accuracy of Search Results.

附图说明Description of drawings

为了更清楚地说明本发明实施例中的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings that need to be used in the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For Those of ordinary skill in the art can also obtain other drawings based on these drawings without making creative efforts.

图1是本发明实施例公开的一种视频搜索的方法的流程示意图;FIG. 1 is a schematic flow diagram of a video search method disclosed in an embodiment of the present invention;

图2是本发明实施例公开的另一种视频搜索的方法的流程示意图;Fig. 2 is a schematic flow chart of another video search method disclosed in an embodiment of the present invention;

图3是本发明实施例公开的一种电子设备的结构示意图;Fig. 3 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present invention;

图4是本发明实施例公开的另一种电子设备的结构示意图。Fig. 4 is a schematic structural diagram of another electronic device disclosed in an embodiment of the present invention.

具体实施方式detailed description

下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

需要说明的是,本发明实施例的术语“包括”和“具有”以及他们的任何变形,意图在于覆盖不排他的包含,例如,包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元,而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。It should be noted that the terms "comprising" and "having" and any variations thereof in the embodiments of the present invention are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or process that includes a series of steps or units. The apparatus is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to the process, method, product or apparatus.

本发明实施例公开了一种视频搜索的方法及电子设备,实施本发明能够直接将搜索词与视频关键帧的图像内容进行比较,从而确定出目标视频,而图像内容能够真实的反映出该视频的内容,这样基于图像内容获得的视频提高了搜索结果的准确性。The embodiment of the present invention discloses a video search method and electronic equipment. The implementation of the present invention can directly compare the search word with the image content of the video key frame, thereby determining the target video, and the image content can truly reflect the video. content, such that videos obtained based on image content improve the accuracy of search results.

实施例一Embodiment one

请参阅图1,图1是本发明实施例公开的一种视频搜索的方法的流程示意图。该视频搜索的方法可以应用于电子设备,如智能手机、学习机、平板电脑、个人电脑等电子设备;该视频搜索的方法还可以应用于网络设备,如服务器或网关等网络设备,本发明实施例不做限定,本发明实施例以应用于电子设备中为例。如图1所示,该视频搜索的方法可以包括以下操作:Please refer to FIG. 1 . FIG. 1 is a schematic flowchart of a video search method disclosed in an embodiment of the present invention. The method for this video search can be applied to electronic equipment, such as smart phones, learning machines, tablet computers, personal computers and other electronic equipment; the method for this video search can also be applied to network equipment, such as network equipment such as servers or gateways, the present invention implements The example is not limited, and the embodiment of the present invention is applied to an electronic device as an example. As shown in Figure 1, the video search method may include the following operations:

101、接收视频搜索请求,该视频搜索请求包括搜索词以及搜索范围。101. Receive a video search request, where the video search request includes a search term and a search range.

在一种可能的实施例中,电子设备可以在正在播放的视频的播放页中设置一个搜索框,当用户在该搜索框中输入搜索词时,电子设备可以接收到视频搜索请求,此时,搜索范围为正在播放的该视频。In a possible embodiment, the electronic device may set a search box on the playing page of the video being played, and when the user enters a search word in the search box, the electronic device may receive a video search request, at this time, The search scope is the video being played.

可选的,当光标移动到该搜索框的范围内时,电子设备可以在当前播放的视频的播放页中显示该搜索框;当光标移出该搜索框的范围时,电子设备则隐藏该搜索框。搜索框在用户需要搜索视频的时候显示,其余时间则隐藏,避免了搜索框遮挡视频画面,提高了用户体验。Optionally, when the cursor moves within the range of the search box, the electronic device may display the search box on the playback page of the currently playing video; when the cursor moves out of the range of the search box, the electronic device hides the search box . The search box is displayed when the user needs to search for videos, and hidden at other times, which prevents the search box from blocking the video screen and improves user experience.

在另一种可能的实施例中,电子设备还可以通过全网搜索框接收视频搜索请求,此时,搜索范围是针对全网络的视频。In another possible embodiment, the electronic device may also receive a video search request through a network-wide search box. In this case, the search scope is for videos on the entire network.

102、根据该视频搜索请求的搜索范围确定候选视频,该候选视频包括至少一个视频,每个所述视频设有多个视频关键帧。102. Determine candidate videos according to the search range of the video search request, where the candidate videos include at least one video, and each video is provided with multiple video key frames.

一个视频一秒高达几十万帧,每一帧都是一个画面。一般在视频编码时,都会设置视频关键帧,如每隔N帧设定一个视频关键帧,N为预先根据经验设定的值;再如在视频序列上进行镜头分割,再在镜头内提取出能够代表镜头内容的帧作为视频关键帧。A video has hundreds of thousands of frames per second, and each frame is a picture. Generally, during video encoding, video key frames are set, such as setting a video key frame every N frames, and N is a value set in advance based on experience; Frames that can represent the content of the shot are used as video keyframes.

如果电子设备通过正在播放的视频的搜索框接收到视频搜索请求,候选视频则为正在播放的该视频;如果电子设备是通过全网搜索框接收到该视频搜索请求,候选视频则为全网络的视频。If the electronic device receives a video search request through the search box of the video being played, the candidate video is the video being played; if the electronic device receives the video search request through the search box of the entire network, the candidate video is the entire network video.

在一种可能的实施例中,电子设备在接收到视频搜索请求后,可以将该视频搜索请求发送给后台服务器,由后台服务器根据该视频搜索请求的搜索范围确定候选视频。In a possible embodiment, after receiving a video search request, the electronic device may send the video search request to a background server, and the background server determines candidate videos according to a search range of the video search request.

103、将该候选视频的各个视频的视频关键帧的图像内容与该视频搜索请求中的搜索词进行匹配,从该候选视频中确定出目标视频。103. Match the image content of the video key frame of each video of the candidate video with the search word in the video search request, and determine the target video from the candidate video.

在一种可能的实施例中,电子设备可以获取候选视频中的视频的两个视频关键帧,这两个视频关键帧为第一视频关键帧和第二视频关键帧,第一视频关键帧和第二视频关键帧为该视频的多个视频关键帧中时间相邻的视频关键帧;判断这两个视频关键帧的相似度是否小于或等于预设阈值,若是,说明第一视频关键帧和第二视频关键帧的图像内容差异较大,则提取第一视频关键帧的图像内容;判断提取到的图像内容与该搜索词是否匹配,若是,说明该视频可能为用户想观看的视频,则将该视频分类为目标视频。In a possible embodiment, the electronic device may acquire two video key frames of the video in the candidate video, the two video key frames are the first video key frame and the second video key frame, and the first video key frame and the The second video key frame is the video key frame adjacent in time among the multiple video key frames of this video; Judge whether the similarity of these two video key frames is less than or equal to preset threshold value, if so, explain the first video key frame and The image content of the second video key frame has a large difference, then extract the image content of the first video key frame; judge whether the image content extracted matches the search term, if so, explain that this video may be the video that the user wants to watch, then Classify the video as the target video.

第一视频关键帧可以是该视频中第一个播放的视频关键帧或者最后一个播放的视频关键帧。如果该候选视频为正在播放的视频,第一视频关键帧还可以是指定时间段内的视频关键帧,如该视频已经播放的视频片段内的视频关键帧或该视频未播放的视频片段的视频关键帧。The first video key frame may be the first played video key frame or the last played video key frame in the video. If the candidate video is a currently playing video, the first video key frame can also be a video key frame in a specified time period, such as a video key frame in a video segment where the video has been played or a video of a video segment where the video is not played Keyframe.

其中,判断提取到的图像内容与该搜索词是否匹配的具体步骤可以为:检测该图像内容中是否包括该搜索词,若是,则判定提取到的图像内容与该搜索词匹配。该图像内容包括该视频关键帧的画面中的文字以及台词文本。Wherein, the specific step of judging whether the extracted image content matches the search word may be: detecting whether the image content includes the search word, and if so, determining that the extracted image content matches the search word. The image content includes text and line text in the frame of the video key frame.

进一步的,若提取到的图像内容与该搜索词不匹配,或者,若两个视频关键帧的相似度大于该预设阈值,则重新获取该视频的两个视频关键帧,本步骤中获取到的两个视频关键帧为第三视频关键帧和第二视频关键帧,第二视频关键帧和第三视频关键帧为该视频的多个视频关键帧中时间相邻的视频关键帧。假设,视频1预先设置有A1、A2、A3、A4、A5、A6、A7,7个视频关键帧,如果第一视频关键帧为A1,则第二视频关键帧为A2,第三视频关键帧为A3;如果第一视频关键帧为A7,则第二视频关键帧则A6,第三视频关键帧为A5,以此类推。其中,预设阈值是预先设定的一个经验值,可以根据实际情况调整。Further, if the extracted image content does not match the search term, or if the similarity of the two video key frames is greater than the preset threshold, then re-acquire the two video key frames of the video, obtained in this step The two video key frames are the third video key frame and the second video key frame, and the second video key frame and the third video key frame are temporally adjacent video key frames among the multiple video key frames of the video. Suppose, video 1 is pre-set with A1, A2, A3, A4, A5, A6, A7, 7 video key frames, if the first video key frame is A1, then the second video key frame is A2, and the third video key frame is A3; if the key frame of the first video is A7, then the key frame of the second video is A6, the key frame of the third video is A5, and so on. Wherein, the preset threshold is a preset empirical value, which can be adjusted according to actual conditions.

在一种可能的实施例中,如果是后台服务器确定的候选视频,则可以有后台服务器将该候选视频的各个视频的视频关键帧的图像内容与该视频搜索请求中的搜索词进行匹配,从该候选视频中确定出目标视频。In a possible embodiment, if it is a candidate video determined by the background server, the background server may match the image content of the video key frame of each video of the candidate video with the search term in the video search request, from A target video is determined from the candidate video.

104、对该目标视频进行展示。104. Display the target video.

在一种可能的实施例中,当候选视频为一个正在播放的视频时,电子设备对该目标视频进行展示的具体步骤可以为:在正在播放的该视频的播放进度条中,确定出目标视频的播放位置,并从该播放位置开始播放该目标视频。In a possible embodiment, when the candidate video is a currently playing video, the specific steps for the electronic device to display the target video may be: in the playback progress bar of the currently playing video, determine the target video , and start playing the target video from that playback position.

其中,电子设备可以根据视频关键帧的时间点确定出目标视频的播放位置。该播放位置为电子设备根据视频搜索请求检索到的,而不是该视频当前实际播放的位置。Wherein, the electronic device can determine the playing position of the target video according to the time point of the key frame of the video. The playback location is retrieved by the electronic device according to the video search request, rather than the current actual playback location of the video.

进一步的,电子设备在确定出目标视频的播放位置时,可以基于该播放位置进行标识提示,当接收到用户针对该标识提示输入的确认指令时,电子设备才从该播放位置开始播放该目标视频。假设该标识提示为一突出区域,当光标移动到该突出区域,并在该突出区域停留预设时长,电子设备则接收到确认指令。Further, when the electronic device determines the playback position of the target video, it can give an identification prompt based on the playback position, and when receiving a confirmation instruction entered by the user for the identification prompt, the electronic device starts to play the target video from the playback position . Assuming that the identification prompt is a highlighted area, when the cursor moves to the highlighted area and stays in the highlighted area for a preset period of time, the electronic device receives a confirmation instruction.

在一种可能的实施例中,当候选视频为全网视频集合时,电子设备需要遍历视频集合中的所有视频,对视频集合中的每个视频执行101~104的步骤,以获得目标视频。电子设备对该目标视频进行展示的具体步骤可以为:将目标视频以及目标视频的属性信息以列表形式进行展示。在该实施方式中,电子设备是针对全网的视频进行目标视频搜索,搜索到目标视频后,将目标视频以列表形式进行展示;由于全网搜索得到的搜索结果较多,因此,还会将该目标视频对应的属性信息一并进行展示,其中,属性信息可以包括电视剧名、集数、综艺名、期数、片断时长、出场人物等信息中的一个或多个组合。In a possible embodiment, when the candidate video is a video collection of the entire network, the electronic device needs to traverse all the videos in the video collection, and perform steps 101 to 104 for each video in the video collection to obtain the target video. A specific step for the electronic device to display the target video may be: displaying the target video and attribute information of the target video in a list form. In this embodiment, the electronic device performs a target video search for videos on the entire network, and displays the target video in a list form after searching for the target video; since there are many search results obtained by searching the entire network, the The attribute information corresponding to the target video is displayed together, wherein the attribute information may include one or more combinations of TV series name, episode number, variety show name, period number, segment duration, characters and other information.

在一种可能的实施例中,如果由后台服务器搜索出目标视频,后台服务器则将搜索出的目标视频传输给电子设备,由电子设备的输出装置输出目标视频。In a possible embodiment, if the background server searches out the target video, the background server transmits the searched target video to the electronic device, and the output device of the electronic device outputs the target video.

本发明实施例中,根据视频搜索请求的搜索范围确定候选视频,该候选视频包括至少一个视频,每个视频设有多个视频关键帧,将该候选视频的各个视频的视频关键帧的图像内容与该视频搜索请求中的搜索词进行匹配,从该候选视频中确定出目标视频,对目标视频进行展示。可见,实施本发明实施例能够直接将搜索词与视频关键帧的图像内容进行比较,从而确定出目标视频,而图像内容能够真实的反映出该视频的内容,这样基于图像内容获得的视频提高了搜索结果的准确性。In the embodiment of the present invention, the candidate video is determined according to the search scope of the video search request, the candidate video includes at least one video, each video is provided with a plurality of video key frames, and the image content of the video key frames of each video of the candidate video is Match the search term in the video search request, determine the target video from the candidate videos, and display the target video. It can be seen that implementing the embodiment of the present invention can directly compare the search term with the image content of the key frame of the video, thereby determining the target video, and the image content can truly reflect the content of the video, so that the video obtained based on the image content is improved. Accuracy of Search Results.

实施例二Embodiment two

请参阅图2,图2是本发明实施例公开的另一种视频搜索的方法的流程示意图。该视频搜索的方法可以应用于电子设备,如智能手机、学习机、平板电脑、个人电脑等电子设备;该视频搜索的方法还可以应用于网络设备,如服务器或网关等网络设备,本发明实施例不做限定,本发明实施例以应用于电子设备中为例。如图2所示,该视频搜索的方法可以包括以下操作:Please refer to FIG. 2 . FIG. 2 is a schematic flowchart of another video search method disclosed in an embodiment of the present invention. The method for this video search can be applied to electronic equipment, such as smart phones, learning machines, tablet computers, personal computers and other electronic equipment; the method for this video search can also be applied to network equipment, such as network equipment such as servers or gateways, the present invention implements The example is not limited, and the embodiment of the present invention is applied to an electronic device as an example. As shown in Figure 2, the video search method may include the following operations:

201、在正在播放的视频对应的搜索框中,接收视频搜索请求,该视频搜索请求包括搜索词,该视频设有多个视频关键帧。201. In the search box corresponding to the video being played, receive a video search request, the video search request includes a search term, and the video is provided with multiple video key frames.

在一种可能的实施例中,电子设备可以在正在播放的视频的播放页中设置一个搜索框,当用户在该搜索框中输入搜索词时,电子设备可以接收到视频搜索请求。In a possible embodiment, the electronic device may set a search box on the playing page of the video being played, and when the user inputs a search term in the search box, the electronic device may receive a video search request.

可选的,当光标移动到该搜索框的范围内时,电子设备可以在当前播放的视频的播放页中显示该搜索框;当光标移出该搜索框的范围时,电子设备则隐藏该搜索框。搜索框在用户需要搜索视频的时候显示,其余时间则隐藏,避免了搜索框遮挡视频画面,提高了用户体验。Optionally, when the cursor moves within the range of the search box, the electronic device may display the search box on the playback page of the currently playing video; when the cursor moves out of the range of the search box, the electronic device hides the search box . The search box is displayed when the user needs to search for videos, and hidden at other times, which prevents the search box from blocking the video screen and improves user experience.

一个视频一秒高达几十万帧,每一帧都是一个画面。一般在视频编码时,都会设置视频关键帧,如每隔N帧设定一个视频关键帧,N为预先根据经验设定的值;再如在视频序列上进行镜头分割,再在镜头内提取出能够代表镜头内容的帧作为视频关键帧。A video has hundreds of thousands of frames per second, and each frame is a picture. Generally, during video encoding, video key frames are set, such as setting a video key frame every N frames, and N is a value set in advance based on experience; Frames that can represent the content of the shot are used as video keyframes.

202、获取该视频的两个视频关键帧,该两个视频关键帧为第一视频关键帧和第二视频关键帧。202. Acquire two video key frames of the video, where the two video key frames are a first video key frame and a second video key frame.

第一视频关键帧可以是该视频中第一个播放的视频关键帧、最后一个播放的视频关键帧,或者指定时间段内的视频关键帧,如该视频已经播放的视频片段内的视频关键帧或该视频未播放的视频片段的视频关键帧。The first video key frame can be the first played video key frame in this video, the last played video key frame, or a video key frame within a specified time period, such as a video key frame in a video segment that has already been played in this video Or the video keyframes of the video clips that the video is not playing.

第二视频关键帧为该视频的多个视频关键帧中与第一视频关键帧时间相邻的视频关键帧。The second video key frame is a video key frame temporally adjacent to the first video key frame among the multiple video key frames of the video.

203、判断该两个视频关键帧的相似度是否小于或等于预设阈值。203. Determine whether the similarity between the two video key frames is less than or equal to a preset threshold.

如果该两个视频关键帧的相似度小于或等于该预设阈值,则执行步骤204,否则返回执行步骤202,电子设备在返回执行步骤202时,获取到的两个视频关键字为第二视频关键帧和第三视频关键帧。假设,该视频预先设置有A1、A2、A3、A4、A5、A6、A7,7个视频关键帧,如果第一视频关键帧为A1,则第二视频关键帧为A2,第三视频关键帧为A3;如果第一视频关键帧为A7,则第二视频关键帧则A6,第三视频关键帧为A5,以此类推。其中,预设阈值是预先设定的一个经验值,可以根据实际情况调整。If the similarity of the two video key frames is less than or equal to the preset threshold, then execute step 204, otherwise return to execute step 202, and when the electronic device returns to execute step 202, the acquired two video keywords are the second video keyframe and third video keyframe. Suppose, the video is preset with A1, A2, A3, A4, A5, A6, A7, 7 video key frames, if the first video key frame is A1, then the second video key frame is A2, and the third video key frame is A3; if the key frame of the first video is A7, then the key frame of the second video is A6, the key frame of the third video is A5, and so on. Wherein, the preset threshold is a preset empirical value, which can be adjusted according to actual conditions.

204、提取第一视频关键帧的图像内容。204. Extract the image content of the key frame of the first video.

205、判断提取到的图像内容与该搜索词是否匹配。205. Determine whether the extracted image content matches the search term.

如果提取到的图像内容与该搜索词匹配,则执行步骤206,否则返回执行步骤202,电子设备在返回执行步骤202时,获取到的两个视频关键字为第二视频关键帧和第三视频关键帧。If the extracted image content matches the search word, execute step 206, otherwise return to execute step 202, and when the electronic device returns to execute step 202, the two video keywords obtained are the second video key frame and the third video key frame Keyframe.

其中,判断提取到的图像内容与该搜索词是否匹配的具体步骤可以为:检测该图像内容中是否包括该搜索词,若是,则判定提取到的图像内容与该搜索词匹配。该图像内容包括该视频关键帧的画面中的文字以及台词文本。Wherein, the specific step of judging whether the extracted image content matches the search word may be: detecting whether the image content includes the search word, and if so, determining that the extracted image content matches the search word. The image content includes text and line text in the frame of the video key frame.

206、在正在播放的该视频的播放进度条中,确定出播放位置,并从该播放位置开始播放该视频。206. In the playing progress bar of the video being played, determine the playing position, and start playing the video from the playing position.

在一种可能的实施例中,电子设备可以根据视频关键帧的时间点确定出该视频的播放位置。如果电子设备在第一视频关键帧中提取到的图像内容与搜索词匹配,则根据第一视频关键帧的时间点确定出视频的播放位置;如果电子设备在第二视频关键帧中提取到的图像内容与搜索词匹配,则根据第二视频关键帧的时间点确定出视频的播放位置。即该播放位置为电子设备根据视频搜索请求检索到的,而不是该视频当前实际播放的位置。In a possible embodiment, the electronic device may determine the playback position of the video according to the time point of the key frame of the video. If the image content extracted by the electronic device in the first video key frame matches the search word, then determine the playback position of the video according to the time point of the first video key frame; if the electronic device extracts the image content in the second video key frame If the image content matches the search term, the playback position of the video is determined according to the time point of the second video key frame. That is, the playback location is retrieved by the electronic device according to the video search request, rather than the current actual playback location of the video.

在一种可能的实施例中,电子设备在确定出播放位置时,可以基于该播放位置进行标识提示,当接收到用户针对该标识提示输入的确认指令时,电子设备才从该播放位置开始播放该视频。假设该标识提示为一突出区域,当光标移动到该突出区域,并在该突出区域停留预设时长,电子设备则接收到确认指令。In a possible embodiment, when the electronic device determines the playback position, it may provide an identification prompt based on the playback position, and the electronic device will start playing from the playback position only when a confirmation instruction input by the user for the identification prompt is received. the video. Assuming that the identification prompt is a highlighted area, when the cursor moves to the highlighted area and stays in the highlighted area for a preset period of time, the electronic device receives a confirmation instruction.

本发明实施例中,获取正在播放的视频的两个视频关键帧,如果该两个视频关键帧的相似度小于或等于该预设阈值,则提取第一视频关键帧的图像内容,如果提取到的图像内容与搜索词匹配,则根据第一视频关键帧关键帧的时间点确定视频的播放位置,并从该播放位置开始播放该视频。可见,实施本发明实施例能够直接将搜索词与视频关键帧的图像内容进行比较,从而在正在播放的视频中确定出视频播放位置,而图像内容能够真实的反映出该视频的内容,这样基于图像内容获得的视频提高了搜索结果的准确性。并且,电子设备在根据视频关键帧进行检测时,可以忽略相同的视频关键字的检测,提高了检测效率。In the embodiment of the present invention, two video key frames of the video being played are acquired, and if the similarity of the two video key frames is less than or equal to the preset threshold, the image content of the first video key frame is extracted, and if the similarity of the two video key frames is extracted If the image content of the video matches the search term, the playback position of the video is determined according to the time point of the key frame of the first video, and the video is played from the playback position. It can be seen that implementing the embodiment of the present invention can directly compare the search term with the image content of the key frame of the video, so as to determine the video playback position in the video being played, and the image content can truly reflect the content of the video, so based on Image content gained from video increases the accuracy of search results. Moreover, when the electronic device detects according to the video key frame, it can ignore the detection of the same video keyword, which improves the detection efficiency.

实施例三Embodiment three

请参阅图3,图3是本发明实施例公开的一种电子设备的结构示意图。如图3所示,该电子设备300可以包括接收单元301、筛选单元302、匹配单元303以及展示单元304,其中:Please refer to FIG. 3 . FIG. 3 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present invention. As shown in FIG. 3, the electronic device 300 may include a receiving unit 301, a screening unit 302, a matching unit 303, and a display unit 304, wherein:

接收单元301用于接收视频搜索请求,该视频搜索请求包括搜索词以及搜索范围。在一种可能的实施例中,电子设备可以在正在播放的视频的播放页中设置一个搜索框,当用户在该搜索框中输入搜索词时,接收单元301可以接收到视频搜索请求,此时,搜索范围为正在播放的该视频。在另一种可能的实施例中,接收单元301还可以通过全网搜索框接收视频搜索请求,此时,搜索范围是针对全网络的视频。The receiving unit 301 is configured to receive a video search request, where the video search request includes a search term and a search range. In a possible embodiment, the electronic device may set a search box on the playing page of the video being played, and when the user inputs a search term in the search box, the receiving unit 301 may receive a video search request, and at this time , the search scope is the video that is playing. In another possible embodiment, the receiving unit 301 may also receive a video search request through a network-wide search box. In this case, the search scope is for videos on the entire network.

筛选单元302用于根据该视频搜索请求的搜索范围确定候选视频,候选视频包括至少一个视频,每个所述视频设有多个视频关键帧。如果接收单元301通过正在播放的视频的搜索框接收到视频搜索请求,筛选单元302确定的候选视频则为正在播放的该视频;如果接收单元301是通过全网搜索框接收到该视频搜索请求,筛选单元302确定的候选视频则为全网络的视频。The screening unit 302 is configured to determine candidate videos according to the search scope of the video search request, the candidate videos include at least one video, and each video is provided with multiple video key frames. If the receiving unit 301 receives the video search request through the search box of the video being played, the candidate video determined by the screening unit 302 is the video being played; if the receiving unit 301 receives the video search request through the whole network search box, The candidate videos determined by the screening unit 302 are videos from the entire network.

匹配单元303用于将筛选单元302筛选出的候选视频的各个视频的视频关键帧的图像内容与所述视频搜索请求中的搜索词进行匹配,从所述候选视频中确定出目标视频。The matching unit 303 is configured to match the image content of video key frames of each video of the candidate videos screened out by the screening unit 302 with the search words in the video search request, and determine the target video from the candidate videos.

展示单元304用于对匹配单元303匹配出的目标视频进行展示。The display unit 304 is configured to display the target video matched by the matching unit 303 .

其中,匹配单元303具体包括:Wherein, the matching unit 303 specifically includes:

获取子单元3031,用于获取候选视频中的视频的两个视频关键帧,两个视频关键帧为第一视频关键帧和第二视频关键帧,所述第一视频关键帧和所述第二视频关键帧为所述视频的多个视频关键帧中时间相邻的视频关键帧。The acquisition subunit 3031 is configured to acquire two video key frames of the video in the candidate video, the two video key frames are a first video key frame and a second video key frame, and the first video key frame and the second video key frame The video key frame is a temporally adjacent video key frame among the multiple video key frames of the video.

第一判断子单元3032,用于判断获取子单元3031获取到的所述两个视频关键帧的相似度是否小于或等于预设阈值。The first judging subunit 3032 is configured to judge whether the similarity of the two video key frames acquired by the acquiring subunit 3031 is less than or equal to a preset threshold.

提取子单元3033,用于若两个视频关键帧的相似度小于或等于该预设阈值,则提取所述第一视频关键帧的图像内容。The extracting subunit 3033 is configured to extract the image content of the first video key frame if the similarity between the two video key frames is less than or equal to the preset threshold.

第二判断子单元3034,用于判断提取子单元3033提取到的所述图像内容与所述搜索词是否匹配。可选的,第二判断子单元3034可以检测该图像内容中是否包括该搜索词,若是,则判定提取子单元3033提取到的图像内容与该搜索词匹配。该图像内容包括该视频关键帧的画面中的文字以及台词文本。The second judging subunit 3034 is configured to judge whether the image content extracted by the extracting subunit 3033 matches the search term. Optionally, the second judging subunit 3034 may detect whether the image content includes the search term, and if so, determine that the image content extracted by the extracting subunit 3033 matches the search term. The image content includes text and line text in the frame of the video key frame.

分类子单元3035,用于若提取子单元3033提取到的所述图像内容与所述搜索词匹配,则将所述视频分类为所述目标视频。The classification subunit 3035 is configured to classify the video as the target video if the image content extracted by the extraction subunit 3033 matches the search term.

进一步的,获取子单元3031还用于:若提取子单元3033提取到的所述图像内容与所述搜索词不匹配,或者,若所述两个视频关键帧的相似度大于所述预设阈值,重新获取候选视频中的视频的两个视频关键帧,其中,获取子单元3031在该步骤中获取到的两个视频关键帧为第三视频关键帧和所述第二视频关键帧。假设,视频1预先设置有A1、A2、A3、A4、A5、A6、A7,7个视频关键帧,如果第一视频关键帧为A1,则第二视频关键帧为A2,第三视频关键帧为A3;如果第一视频关键帧为A7,则第二视频关键帧则A6,第三视频关键帧为A5,以此类推。其中,预设阈值是预先设定的一个经验值,可以根据实际情况调整。Further, the acquisition subunit 3031 is also used for: if the image content extracted by the extraction subunit 3033 does not match the search term, or if the similarity between the two video key frames is greater than the preset threshold , to reacquire two video key frames of the video in the candidate video, wherein the two video key frames obtained by the obtaining subunit 3031 in this step are the third video key frame and the second video key frame. Suppose, video 1 is pre-set with A1, A2, A3, A4, A5, A6, A7, 7 video key frames, if the first video key frame is A1, then the second video key frame is A2, and the third video key frame is A3; if the key frame of the first video is A7, then the key frame of the second video is A6, the key frame of the third video is A5, and so on. Wherein, the preset threshold is a preset empirical value, which can be adjusted according to actual conditions.

在一种可能的实施例中,当候选视频为一个正在播放的视频时,展示单元304对该目标视频进行展示的具体可以为:在正在播放的该视频的播放进度条中,确定出目标视频的播放位置,并从该播放位置开始播放该目标视频。In a possible embodiment, when the candidate video is a currently playing video, the presentation unit 304 may specifically display the target video as follows: in the playback progress bar of the currently playing video, determine the target video , and start playing the target video from that playback position.

其中,展示单元304可以根据视频关键帧的时间点确定出目标视频的播放位置。该播放位置为电子设备根据视频搜索请求检索到的,而不是该视频当前实际播放的位置。Wherein, the presentation unit 304 may determine the playback position of the target video according to the time point of the key frame of the video. The playback location is retrieved by the electronic device according to the video search request, rather than the current actual playback location of the video.

进一步的,展示单元304在确定出目标视频的播放位置时,可以基于该播放位置进行标识提示,当接收到用户针对该标识提示输入的确认指令时,展示单元304才从该播放位置开始播放该目标视频。假设该标识提示为一突出区域,当光标移动到该突出区域,并在该突出区域停留预设时长,展示单元304则接收到确认指令。Further, when the display unit 304 determines the playback position of the target video, it may give an identification prompt based on the playback position, and when a confirmation instruction input by the user for the identification prompt is received, the display unit 304 starts to play the video from the playback position. target video. Assuming that the identification prompt is a highlighted area, when the cursor moves to the highlighted area and stays in the highlighted area for a preset time, the display unit 304 receives a confirmation instruction.

在一种可能的实施例中,当候选视频为全网视频集合时,展示单元304对该目标视频进行展示的具体可以为:将目标视频以及目标视频的属性信息以列表形式进行展示。在该实施方式中,匹配单元303是针对全网的视频进行目标视频搜索,搜索到目标视频后,展示单元304将目标视频以列表形式进行展示;由于全网搜索得到的搜索结果较多,因此,展示单元304还可以将该目标视频对应的属性信息一并进行展示,其中,属性信息可以包括电视剧名、集数、综艺名、期数、片断时长、出场人物等信息中的一个或多个组合。In a possible embodiment, when the candidate video is a collection of videos on the entire network, the presentation unit 304 may specifically display the target video by: displaying the target video and the attribute information of the target video in a list form. In this embodiment, the matching unit 303 searches for the target video for videos on the entire network. After the target video is found, the display unit 304 displays the target video in a list form; , the display unit 304 can also display the attribute information corresponding to the target video together, wherein the attribute information can include one or more of the TV series name, episode number, variety show name, period number, segment duration, characters and other information combination.

可见,实施图3所描述的电子设备300能够直接将搜索词与视频关键帧的图像内容进行比较,从而确定出目标视频,而图像内容能够真实的反映出该视频的内容,这样基于图像内容获得的视频提高了搜索结果的准确性。It can be seen that the implementation of the electronic device 300 described in FIG. 3 can directly compare the search term with the image content of the key frame of the video, thereby determining the target video, and the image content can truly reflect the content of the video, so that based on the image content, the obtained of videos improved the accuracy of search results.

实施例四Embodiment four

请参阅图4,图4是本发明实施例公开的另一种电子设备的结构示意图。如图4所示,该电子设备可以包括:Please refer to FIG. 4 . FIG. 4 is a schematic structural diagram of another electronic device disclosed in an embodiment of the present invention. As shown in Figure 4, the electronic equipment may include:

存储有可执行程序代码的存储器401;A memory 401 storing executable program codes;

与存储器401耦合的处理器402;a processor 402 coupled to the memory 401;

其中,处理器402调用存储器401中存储的可执行程序代码,执行图1或图2所描述的方法。Wherein, the processor 402 invokes the executable program code stored in the memory 401 to execute the method described in FIG. 1 or FIG. 2 .

此外,实施图4所描述的电子设备,可以实现将搜索词与视频关键帧的图像内容进行比较,从而提高搜索结果的准确性。In addition, implementing the electronic device described in FIG. 4 can realize the comparison of the search word with the image content of the key frame of the video, thereby improving the accuracy of the search result.

发明实施例公开一种计算机可读存储介质,其存储计算机程序,其中,该计算机程序使得计算机执行图1或图2所描述的方法。The embodiment of the invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes the computer to execute the method described in FIG. 1 or FIG. 2 .

本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成,该程序可以存储于一计算机可读存储介质中,存储介质包括只读存储器(Read-Only Memory,ROM)、随机存储器(Random Access Memory,RAM)、可编程只读存储器(Programmable Read-only Memory,PROM)、可擦除可编程只读存储器(Erasable Programmable Read Only Memory,EPROM)、一次可编程只读存储器(One-time Programmable Read-Only Memory,OTPROM)、电子抹除式可复写只读存储器(Electrically-Erasable Programmable Read-Only Memory,EEPROM)、只读光盘(CompactDisc Read-Only Memory,CD-ROM)或其他光盘存储器、磁盘存储器、磁带存储器、或者能够用于携带或存储数据的计算机可读的任何其他介质。Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above-mentioned embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes read-only Memory (Read-Only Memory, ROM), Random Access Memory (Random Access Memory, RAM), Programmable Read-Only Memory (Programmable Read-only Memory, PROM), Erasable Programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), One-time Programmable Read-Only Memory (OTPROM), Electronically Erasable Programmable Read-Only Memory (EEPROM), Compact Disc Read-Only Memory (CompactDisc Read -Only Memory, CD-ROM) or other optical disk storage, magnetic disk storage, tape storage, or any other computer-readable medium that can be used to carry or store data.

以上对本发明实施例公开的一种视频搜索的方法及电子设备进行了详细介绍,本文中应用了具体个例对本发明的原理及实施方式进行了阐述,以上实施例的说明只是用于帮助理解本发明的方法及其核心思想;同时,对于本领域的一般技术人员,依据本发明的思想,在具体实施方式及应用范围上均会有改变之处,综上所述,本说明书内容不应理解为对本发明的限制。The above is a detailed introduction of a video search method and electronic equipment disclosed in the embodiments of the present invention. In this paper, specific examples are used to illustrate the principle and implementation of the present invention. The description of the above embodiments is only used to help understand the present invention The method of the invention and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation and scope of application. In summary, the content of this specification should not be understood To limit the present invention.

Claims (11)

1. a kind of method of video search, it is characterised in that methods described includes:
Video search request is received, the video search request includes search term and hunting zone;
The hunting zone asked according to the video search determines candidate video, and the candidate video includes at least one video, Each video is provided with multiple key frame of video;
Search during the picture material of the key frame of video of each video of the candidate video and the video search are asked Word is matched, and target video is determined from the candidate video;
The target video is shown.
2. according to the method described in claim 1, it is characterised in that the video of each video by the candidate video is closed Search term during the picture material of key frame is asked with the video search is matched, and target is determined from the candidate video Video, including:
Obtain candidate video in video two key frame of video, described two key frame of video be the first key frame of video and Second key frame of video, first key frame of video and second key frame of video are multiple Video Keys of the video Temporally adjacent key frame of video in frame;
Judge whether the similarity of described two key frame of video is less than or equal to predetermined threshold value, if so, then extracting described first The picture material of key frame of video;
Judge whether the described image content extracted matches with the search term, if so, being then described by the visual classification Target video.
3. method according to claim 2, it is characterised in that methods described also includes:
If the described image content extracted and the search word mismatch, or, if described two key frame of video is similar Degree is more than the predetermined threshold value, the step of returning to two key frame of video for performing the video in the acquisition candidate video, its In, the described two key frame of video got in this step are the 3rd key frame of video and second key frame of video.
4. the method according to any one of claim 1-3, it is characterised in that
When the candidate video is a video played, the reception video search request includes:
In the corresponding search box of the video played, video search request is received;
It is described the target video is shown including:
In the playing progress bar for the video played, the play position of the target video is determined, and from described Play position commences play out the target video.
5. the method according to any one of claim 1-3, it is characterised in that
When the candidate video is the whole network video collection, the reception video search request includes:
In the whole network search box, video search request is received;
It is described the target video is shown including:
The attribute information of the target video and target video is shown with tabular form.
6. a kind of electronic equipment, it is characterised in that the electronic equipment includes:
Processor, is adapted for carrying out each instruction;And
Storage device, suitable for storing a plurality of instruction, the instruction is suitable to be loaded and performed by processor:
Video search request is received, the video search request includes search term and hunting zone;
The hunting zone asked according to the video search determines candidate video, and the candidate video includes at least one video, Each video is provided with multiple key frame of video;
Search during the picture material of the key frame of video of each video of the candidate video and the video search are asked Word is matched, and target video is determined from the candidate video;
The target video is shown.
7. electronic equipment according to claim 6, it is characterised in that the computing device is each by the candidate video Search term during the picture material of the key frame of video of individual video is asked with the video search is matched, and is regarded from the candidate The step of target video being determined in frequency, be specially:
Obtain candidate video in video two key frame of video, described two key frame of video be the first key frame of video and Second key frame of video, first key frame of video and second key frame of video are multiple Video Keys of the video Temporally adjacent key frame of video in frame;
Judge whether the similarity of described two key frame of video is less than or equal to predetermined threshold value, if so, then extracting described first The picture material of key frame of video;
Judge whether the described image content extracted matches with the search term, if so, being then described by the visual classification Target video.
8. electronic equipment according to claim 7, it is characterised in that
The processor also performs following operation:
If the described image content extracted and the search word mismatch, or, if described two key frame of video is similar Degree is more than the predetermined threshold value, the step of returning to two key frame of video for performing the video in the acquisition candidate video, its In, the described two key frame of video got in this step are the 3rd key frame of video and second key frame of video.
9. the electronic equipment according to any one of claim 6-8, it is characterised in that
When the candidate video is a video played, the computing device receives the step of video search request Suddenly, it is specially:
In the corresponding search box of the video played, video search request is received;
The step of computing device is shown to the target video, be specially:
In the playing progress bar for the video played, the play position of the target video is determined, and from described Play position commences play out the target video.
10. the electronic equipment according to any one of claim 6-8, it is characterised in that
When the candidate video is the whole network video collection, the computing device receives the step of video search is asked, specifically For:
In the whole network search box, video search request is received;
The step of computing device is shown to the target video, be specially:
The attribute information of the target video and target video is shown with tabular form.
11. a kind of computer-readable recording medium, it is characterised in that it stores computer program, wherein, the computer program So that computer perform claim requires the method described in 1~5 any one.
CN201710449090.6A 2017-06-14 2017-06-14 Video searching method and electronic equipment Pending CN107229737A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710449090.6A CN107229737A (en) 2017-06-14 2017-06-14 Video searching method and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710449090.6A CN107229737A (en) 2017-06-14 2017-06-14 Video searching method and electronic equipment

Publications (1)

Publication Number Publication Date
CN107229737A true CN107229737A (en) 2017-10-03

Family

ID=59935987

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710449090.6A Pending CN107229737A (en) 2017-06-14 2017-06-14 Video searching method and electronic equipment

Country Status (1)

Country Link
CN (1) CN107229737A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107862003A (en) * 2017-10-24 2018-03-30 珠海市魅族科技有限公司 Video contents search method, apparatus, terminal and readable storage medium storing program for executing
CN111651635A (en) * 2020-05-28 2020-09-11 拾音智能科技有限公司 Video retrieval method based on natural language description
CN111984823A (en) * 2020-09-01 2020-11-24 咪咕文化科技有限公司 Video searching method, electronic device and storage medium
CN112269899A (en) * 2020-10-20 2021-01-26 西安工程大学 A video retrieval method based on deep learning
CN112749297A (en) * 2020-03-03 2021-05-04 腾讯科技(深圳)有限公司 Video recommendation method and device, computer equipment and computer-readable storage medium
CN113139093A (en) * 2021-05-06 2021-07-20 北京百度网讯科技有限公司 Video search method and apparatus, computer device, and medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104731938A (en) * 2015-03-30 2015-06-24 北京奇艺世纪科技有限公司 Video searching method and device
CN105677735A (en) * 2015-12-30 2016-06-15 腾讯科技(深圳)有限公司 Video search method and apparatus
CN106776890A (en) * 2016-11-29 2017-05-31 北京小米移动软件有限公司 The method of adjustment and device of video playback progress

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104731938A (en) * 2015-03-30 2015-06-24 北京奇艺世纪科技有限公司 Video searching method and device
CN105677735A (en) * 2015-12-30 2016-06-15 腾讯科技(深圳)有限公司 Video search method and apparatus
CN106776890A (en) * 2016-11-29 2017-05-31 北京小米移动软件有限公司 The method of adjustment and device of video playback progress

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107862003A (en) * 2017-10-24 2018-03-30 珠海市魅族科技有限公司 Video contents search method, apparatus, terminal and readable storage medium storing program for executing
CN112749297A (en) * 2020-03-03 2021-05-04 腾讯科技(深圳)有限公司 Video recommendation method and device, computer equipment and computer-readable storage medium
CN111651635A (en) * 2020-05-28 2020-09-11 拾音智能科技有限公司 Video retrieval method based on natural language description
CN111984823A (en) * 2020-09-01 2020-11-24 咪咕文化科技有限公司 Video searching method, electronic device and storage medium
CN112269899A (en) * 2020-10-20 2021-01-26 西安工程大学 A video retrieval method based on deep learning
CN113139093A (en) * 2021-05-06 2021-07-20 北京百度网讯科技有限公司 Video search method and apparatus, computer device, and medium

Similar Documents

Publication Publication Date Title
US10642892B2 (en) Video search method and apparatus
CN107229737A (en) Video searching method and electronic equipment
CN109819284B (en) Short video recommendation method and device, computer equipment and storage medium
CN110430476B (en) Live broadcast room searching method, system, computer equipment and storage medium
JP6015568B2 (en) Method, apparatus, and program for generating content link
WO2019134587A1 (en) Method and device for video data processing, electronic device, and storage medium
CN109558513B (en) Content recommendation method, device, terminal and storage medium
WO2017096877A1 (en) Recommendation method and device
US8090715B2 (en) Method and system for dynamically generating a search result
JP2019507417A (en) User interface for multivariable search
CN108924658B (en) Bullet screen association input method and device and computer readable storage medium
US9652534B1 (en) Video-based search engine
US10311038B2 (en) Methods, computer program, computer program product and indexing systems for indexing or updating index
CN106708905B (en) Video content searching method and device
CN111767814A (en) Video determination method and device
CN106210836A (en) Interactive learning method and device in video playing process and terminal equipment
US10255321B2 (en) Interactive system, server and control method thereof
US20190266406A1 (en) Automatically detecting contents expressing emotions from a video and enriching an image index
CN107330040B (en) Learning question searching method and system
US20170171334A1 (en) Single-account multiple-preference recommendation method for video website and electronic device
CN111294660A (en) Video clip positioning method, server, client and electronic equipment
US20140114656A1 (en) Electronic device capable of generating tag file for media file based on speaker recognition
TW200834355A (en) Information processing apparatus and method, and program
AU2022429021A1 (en) Video generating method and apparatus, electronic device, and readable storage medium
CN106899879B (en) Multimedia data processing method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20171003

RJ01 Rejection of invention patent application after publication