CN103763480A - Method and equipment for obtaining video dubbing - Google Patents

Abstract

Provided are a method and equipment for obtaining video dubbing. The method comprises the steps that characteristic information of a video to be dubbed is obtained; the obtained characteristic information is sent to a cloud server; dubbing of the video obtained on the basis of the characteristic information is received from the cloud server. According to the method and the equipment, dubbing except for the dubbing carried with a video file can be obtained to be selected by a user, and requirements of the user are met.

Description

Translated fromChinese

获取视频配音的方法及设备Method and device for obtaining video dubbing

技术领域technical field

本发明涉及多媒体技术领域，更具体地讲，涉及一种获取视频配音的方法及设备、在云服务器推送视频配音的方法及设备。The present invention relates to the field of multimedia technology, and more specifically, to a method and device for acquiring video dubbing, and a method and device for pushing video dubbing on a cloud server.

背景技术Background technique

随着电子技术的不断发展，用户通过电子终端（例如，电视、电脑、智能手机等）观看视频（例如，影视剧、综艺节目等）时，对视频的配音的要求也在不断提高，不愿被动接收视频文件所提供的配音，而是希望可以获取视频文件本身所携带的配音之外的配音。With the continuous development of electronic technology, when users watch videos (such as film and television dramas, variety shows, etc.) Passively receive the dubbing provided by the video file, but hope to obtain dubbing other than the dubbing carried by the video file itself.

因此，需要一种获取视频配音的方法及设备，其能够获取视频文件本身所携带的配音之外的配音供用户选择，满足用户需求。Therefore, there is a need for a method and device for obtaining video dubbing, which can obtain dubbing other than the dubbing carried in the video file itself for users to choose, so as to meet user needs.

发明内容Contents of the invention

本发明的目的在于提供一种获取视频配音的方法及设备，可以获取视频文件本身所携带的配音之外的配音供用户选择，满足用户需求。The purpose of the present invention is to provide a method and device for obtaining video dubbing, which can obtain dubbing other than the dubbing carried by the video file itself for users to choose, so as to meet user needs.

本发明的一方面提供一种获取视频配音的方法，包括：a）获取待配音的视频的特征信息；b）将获取的特征信息发送到云服务器；c）从云服务器接收基于所述特征信息获取的所述视频的配音。One aspect of the present invention provides a method for acquiring video dubbing, including: a) acquiring feature information of the video to be dubbed; b) sending the acquired feature information to a cloud server; c) receiving from the cloud server based on the feature information Acquires the audio dubbing of said video.

可选地，从云服务器接收基于所述特征信息获取的所述视频的配音的步骤包括：从云服务器接收基于所述特征信息搜索到的所述视频的配音的索引；将用户根据所述索引从搜索到的所述视频的配音之中选择的配音的获取请求发送到云服务器；从云服务器接收用户请求的配音。Optionally, the step of receiving from the cloud server the dubbing of the video obtained based on the feature information includes: receiving from the cloud server an index of the dubbing of the video searched based on the feature information; An acquisition request for dubbing selected from the dubbing of the video found is sent to the cloud server; and the dubbing requested by the user is received from the cloud server.

可选地，所述待配音的视频的特征信息包括待配音的视频的画面信息和/或待配音的视频的关联信息。Optionally, the feature information of the video to be dubbed includes picture information of the video to be dubbed and/or associated information of the video to be dubbed.

可选地，待配音的视频的画面信息包括待配音的视频的画面和/或待配音的视频的画面的特征值。Optionally, the picture information of the video to be dubbed includes a picture of the video to be dubbed and/or feature values of the picture of the video to be dubbed.

可选地，所述方法还包括：在步骤b）之后，检测在第一预定时间内是否从云服务器接收到用于提示已识别待配音的视频的消息，其中，当在第一预定时间内未从云服务器接收到用于提示已识别待配音的视频的消息时，返回执行步骤a），当在第一预定时间内从云服务器接收到用于提示已识别待配音的视频的消息时，执行步骤c）。Optionally, the method further includes: after step b), detecting whether a message prompting that a video to be dubbed has been identified is received from the cloud server within the first predetermined time, wherein, within the first predetermined time When the message for prompting that the video to be dubbed has been identified is not received from the cloud server, return to step a), and when the message for prompting that the video to be dubbed has been identified is received from the cloud server within the first predetermined time, Execute step c).

可选地，当待配音的视频正在播放时，步骤a）包括：抓取待配音的视频正在播放的画面。Optionally, when the video to be dubbed is playing, step a) includes: grabbing the playing screen of the video to be dubbed.

可选地，步骤a）包括：从待配音的视频所在的文件中获取待配音的视频的特征信息，其中，在与前一抓取时的视频时间点相隔第二预定时间的视频时间点抓取待配音的视频的画面。Optionally, step a) includes: acquiring the feature information of the video to be dubbed from the file where the video to be dubbed is located, wherein, capturing the Capture the footage of the video to be dubbed.

可选地，所述待配音的视频的关联信息从信号源和/或待配音的视频所在的文件获取。Optionally, the associated information of the video to be dubbed is obtained from a signal source and/or a file where the video to be dubbed is located.

可选地，所述待配音的视频的关联信息包括待配音的视频的名称、待配音的视频的发行号、待配音的视频的关键词中的至少一个。Optionally, the associated information of the video to be dubbed includes at least one of the name of the video to be dubbed, the release number of the video to be dubbed, and the keyword of the video to be dubbed.

本发明的另一方面提供一种获取视频配音的设备，包括：特征信息获取单元，获取待配音的视频的特征信息；发送单元，将获取的特征信息发送到云服务器；接收单元，从云服务器接收基于所述特征信息获取的所述视频的配音。Another aspect of the present invention provides a device for acquiring video dubbing, including: a feature information acquisition unit, which acquires feature information of the video to be dubbed; a sending unit, which sends the acquired feature information to a cloud server; a receiving unit, which receives the feature information from the cloud server receiving the dubbing of the video acquired based on the characteristic information.

可选地，接收单元包括：索引接收单元，从云服务器接收基于所述特征信息搜索到的所述视频的配音的索引；获取请求发送单元，将用户根据所述索引从搜索到的所述视频的配音之中选择的配音的获取请求发送到云服务器；配音接收单元，从云服务器接收用户请求的配音。Optionally, the receiving unit includes: an index receiving unit, which receives from the cloud server an index of dubbing of the video searched based on the characteristic information; The dubbing acquisition request selected among the dubbings is sent to the cloud server; the dubbing receiving unit receives the dubbing requested by the user from the cloud server.

可选地，所述待配音的视频的特征信息包括待配音的视频的画面信息和/或待配音的视频的关联信息。Optionally, the feature information of the video to be dubbed includes picture information of the video to be dubbed and/or associated information of the video to be dubbed.

可选地，待配音的视频的画面信息包括待配音的视频的画面和/或待配音的视频的画面的特征值。Optionally, the picture information of the video to be dubbed includes a picture of the video to be dubbed and/or feature values of the picture of the video to be dubbed.

可选地，所述设备还包括：检测单元，在发送单元将获取的特征信息发送到云服务器之后，检测在第一预定时间内是否从云服务器接收到用于提示已识别待配音的视频的消息，其中，当在第一预定时间内未从云服务器接收到用于提示已识别待配音的视频的消息时，返回特征信息获取单元获取待配音的视频的特征信息，当在第一预定时间内从云服务器接收到用于提示已识别待配音的视频的消息时，接收单元从云服务器接收基于所述特征信息获取的所述视频的配音。Optionally, the device further includes: a detecting unit, after the sending unit sends the acquired feature information to the cloud server, detects whether a message for prompting that a video to be dubbed has been identified is received from the cloud server within a first predetermined time; message, wherein, when the message for prompting that the video to be dubbed has been identified is not received from the cloud server within the first predetermined time, the feature information acquisition unit is returned to obtain the feature information of the video to be dubbed, when within the first predetermined time When receiving a message from the cloud server for prompting that a video to be dubbed has been identified, the receiving unit receives from the cloud server the dubbing of the video obtained based on the feature information.

可选地，当待配音的视频正在播放时，特征信息获取单元抓取待配音的视频正在播放的画面。Optionally, when the video to be dubbed is playing, the characteristic information acquisition unit captures the playing screen of the video to be dubbed.

可选地，特征信息获取单元从待配音的视频所在的文件中获取待配音的视频的特征信息，其中，在与前一抓取时的视频时间点相隔第二预定时间的视频时间点抓取待配音的视频的画面。Optionally, the characteristic information obtaining unit obtains the characteristic information of the video to be dubbed from the file where the video to be dubbed is located, wherein the video time point is captured at a video time point that is separated from the video time point of the previous capture by a second predetermined time The frame of the video to be dubbed.

可选地，所述待配音的视频的关联信息从信号源和/或待配音的视频所在的文件获取。Optionally, the associated information of the video to be dubbed is obtained from a signal source and/or a file where the video to be dubbed is located.

可选地，所述待配音的视频的关联信息包括待配音的视频的名称、待配音的视频的发行号、待配音的视频的关键词中的至少一个。Optionally, the associated information of the video to be dubbed includes at least one of the name of the video to be dubbed, the release number of the video to be dubbed, and the keyword of the video to be dubbed.

本发明的另一方面提供一种在云服务器推送视频配音的方法，包括：a）从电子终端接收待配音的视频的特征信息；b）根据待配音的视频的特征信息获取所述视频的标识信息；c）将根据所述视频的标识信息获取的配音发送到电子终端。Another aspect of the present invention provides a method for pushing video dubbing on a cloud server, including: a) receiving feature information of the video to be dubbed from an electronic terminal; b) acquiring the video identifier according to the feature information of the video to be dubbed information; c) sending the dubbing obtained according to the identification information of the video to the electronic terminal.

可选地，步骤b）包括：获取具有与待配音的视频的特征信息匹配的特征信息的视频的标识信息。Optionally, step b) includes: acquiring identification information of a video having feature information matching feature information of the video to be dubbed.

可选地，步骤c）包括：根据所述视频的标识信息搜索所述视频的配音并生成搜索到的配音的索引；将所述索引发送到电子终端；从电子终端接收用户基于所述索引从搜索到的配音之中选择的配音的获取请求；响应于所述请求将请求的配音发送到电子终端。Optionally, step c) includes: searching for the dubbing of the video according to the identification information of the video and generating an index of the searched dubbing; sending the index to the electronic terminal; receiving from the electronic terminal the an acquisition request for a selected dubbing among the searched dubbings; and sending the requested dubbing to the electronic terminal in response to the request.

可选地，所述待配音的视频的特征信息包括待配音的视频的画面信息，获取具有与待配音的视频的特征信息匹配的特征信息的视频的标识信息的步骤包括：在画面数据库中搜索与所述特征信息中的画面信息匹配的画面信息，其中，所述画面数据库存储有多个视频的画面信息；获取匹配的画面信息所属的视频的标识信息。Optionally, the feature information of the video to be dubbed includes picture information of the video to be dubbed, and the step of obtaining the identification information of the video having feature information matching the feature information of the video to be dubbed includes: searching for The picture information matching the picture information in the feature information, wherein the picture database stores picture information of a plurality of videos; and acquiring the identification information of the video to which the matched picture information belongs.

可选地，所述方法还包括：确定获取的标识信息的数量，其中，当确定获取的标识信息的数量大于1或者等于0时，返回执行步骤a），当确定获取的标识信息的数量等于1时，执行步骤c）。Optionally, the method further includes: determining the quantity of the acquired identification information, wherein, when it is determined that the quantity of the acquired identification information is greater than 1 or equal to 0, returning to step a), and when it is determined that the quantity of the acquired identification information is equal to 1, execute step c).

可选地，确定获取的标识信息的数量的步骤包括：当确定获取的标识信息的数量大于1时，返回执行步骤a），其中，在执行在画面数据库中搜索与所述特征信息中的画面信息匹配的画面信息的步骤时，将搜索范围设置为画面数据库中的匹配的画面信息所属的视频的画面信息。Optionally, the step of determining the quantity of the acquired identification information includes: when it is determined that the quantity of the acquired identification information is greater than 1, returning to step a), wherein, when performing the search in the picture database for the picture in the characteristic information In the step of information matching picture information, the search range is set to the picture information of the video to which the matching picture information in the picture database belongs.

可选地，所述方法还包括：当确定获取的标识信息的数量等于1时，生成用于提示已识别待配音的视频的消息；将所述用于提示已识别待配音的视频的消息发送到电子终端。Optionally, the method further includes: when it is determined that the number of acquired identification information is equal to 1, generating a message for prompting that the video to be dubbed has been identified; sending the message for prompting that the video to be dubbed has been identified to the electronic terminal.

可选地，所述待配音的视频的特征信息包括待配音的视频的画面信息和/或待配音的视频的关联信息。Optionally, the feature information of the video to be dubbed includes picture information of the video to be dubbed and/or associated information of the video to be dubbed.

可选地，待配音的视频的画面信息包括待配音的视频的画面和/或待配音的视频的画面的特征值。Optionally, the picture information of the video to be dubbed includes a picture of the video to be dubbed and/or feature values of the picture of the video to be dubbed.

可选地，所述待配音的视频的关联信息包括待配音的视频的名称、待配音的视频的发行号、待配音的视频的关键词中的至少一个。Optionally, the associated information of the video to be dubbed includes at least one of the name of the video to be dubbed, the release number of the video to be dubbed, and the keyword of the video to be dubbed.

本发明的另一方面提供一种在云服务器推送视频配音的设备，包括：接收单元，从电子终端接收待配音的视频的特征信息；标识信息获取单元，根据待配音的视频的特征信息获取所述视频的标识信息；发送单元，将根据所述视频的标识信息获取的配音发送到电子终端。Another aspect of the present invention provides a device for pushing video dubbing on a cloud server, including: a receiving unit, which receives feature information of a video to be dubbed from an electronic terminal; The identification information of the video; the sending unit is configured to send the dubbing obtained according to the identification information of the video to the electronic terminal.

可选地，标识信息获取单元获取具有与待配音的视频的特征信息匹配的特征信息的视频的标识信息。Optionally, the identification information acquiring unit acquires identification information of a video having feature information matching feature information of the video to be dubbed.

可选地，发送单元包括：索引生成单元，根据所述视频的标识信息搜索所述视频的配音并生成搜索到的配音的索引；索引发送单元，将所述索引发送到电子终端；获取请求接收单元，从电子终端接收用户基于所述索引从搜索到的配音之中选择的配音的获取请求；配音发送单元，响应于所述请求将请求的配音发送到电子终端。Optionally, the sending unit includes: an index generating unit, which searches for the dubbing of the video according to the identification information of the video and generates an index of the searched dubbing; an index sending unit, which sends the index to the electronic terminal; A unit for receiving from the electronic terminal an acquisition request for a dubbing selected by the user from the searched dubbing based on the index; a dubbing sending unit for sending the requested dubbing to the electronic terminal in response to the request.

可选地，所述待配音的视频的特征信息包括待配音的视频的画面信息，标识信息获取单元包括：画面信息匹配单元，在画面数据库中搜索与所述特征信息中的画面信息匹配的画面信息，其中，所述画面数据库存储有多个视频的画面信息；获取单元，获取匹配的画面信息所属的视频的标识信息。Optionally, the feature information of the video to be dubbed includes picture information of the video to be dubbed, and the identification information acquisition unit includes: a picture information matching unit that searches a picture database for a picture that matches the picture information in the feature information information, wherein the picture database stores picture information of a plurality of videos; the acquiring unit acquires identification information of the video to which the matched picture information belongs.

可选地，所述设备还包括：确定单元，确定获取的标识信息的数量，其中，当确定获取的标识信息的数量大于1或者等于0时，返回接收单元从电子终端接收待配音的视频的特征信息，当确定获取的标识信息的数量等于1时，发送单元将根据所述视频的标识信息获取的配音发送到电子终端。Optionally, the device further includes: a determining unit for determining the number of acquired identification information, wherein, when it is determined that the acquired number of identification information is greater than 1 or equal to 0, the return receiving unit receives the video to be dubbed from the electronic terminal. For feature information, when it is determined that the number of acquired identification information is equal to 1, the sending unit sends the dubbing acquired according to the identification information of the video to the electronic terminal.

可选地，当确定单元确定获取的标识信息的数量大于1时，返回接收单元从电子终端接收待配音的视频的特征信息，其中，在画面信息匹配单元在画面数据库中搜索与所述特征信息中的画面信息匹配的画面信息时，将搜索范围设置为画面数据库中的匹配的画面信息所属的视频的画面信息。Optionally, when the determination unit determines that the number of acquired identification information is greater than 1, the return receiving unit receives the feature information of the video to be dubbed from the electronic terminal, wherein the picture information matching unit searches for the feature information in the picture database When the picture information in the picture information matches the picture information, set the search range to the picture information of the video to which the matching picture information in the picture database belongs.

可选地，所述设备还包括：消息生成单元，当确定单元确定获取的标识信息的数量等于1时，生成用于提示已识别待配音的视频的消息；消息发送单元，将所述用于提示已识别待配音的视频的消息发送到电子终端。Optionally, the device further includes: a message generating unit, when the determining unit determines that the number of acquired identification information is equal to 1, generating a message for prompting that the video to be dubbed has been identified; a message sending unit, using the A message is sent to the electronic terminal indicating that a video to be dubbed has been identified.

可选地，所述待配音的视频的特征信息包括待配音的视频的画面信息和/或待配音的视频的关联信息。Optionally, the feature information of the video to be dubbed includes picture information of the video to be dubbed and/or associated information of the video to be dubbed.

可选地，待配音的视频的画面信息包括待配音的视频的画面和/或待配音的视频的画面的特征值。Optionally, the picture information of the video to be dubbed includes a picture of the video to be dubbed and/or feature values of the picture of the video to be dubbed.

可选地，所述待配音的视频的关联信息包括待配音的视频的名称、待配音的视频的发行号、待配音的视频的关键词中的至少一个。Optionally, the associated information of the video to be dubbed includes at least one of the name of the video to be dubbed, the release number of the video to be dubbed, and the keyword of the video to be dubbed.

根据本发明的获取视频配音的方法及设备，可以获取视频文件本身所携带的配音之外的配音，提供多种配音供用户选择，满足用户需求，不受视频文件本身所携带的配音的限制。According to the method and device for obtaining video dubbing of the present invention, dubbing other than the dubbing carried in the video file itself can be obtained, and a variety of dubbing can be provided for users to choose, satisfying user needs, and not limited by the dubbing carried in the video file itself.

将在接下来的描述中部分阐述本发明总体构思另外的方面和/或优点，还有一部分通过描述将是清楚的，或者可以经过本发明总体构思的实施而得知。Additional aspects and/or advantages of the present general inventive concept will be partially set forth in the following description, and some will be clear from the description, or can be learned through practice of the present general inventive concept.

附图说明Description of drawings

通过下面结合附图对实施例进行的描述，本发明的这些和/或其他方面和优点将会变得清楚和更易于理解，其中：These and/or other aspects and advantages of the present invention will become clearer and easier to understand through the following description of embodiments in conjunction with the accompanying drawings, wherein:

图1示出根据本发明的实施例的在电子终端获取视频配音的方法的流程图。Fig. 1 shows a flowchart of a method for acquiring video dubbing on an electronic terminal according to an embodiment of the present invention.

图2示出根据本发明的实施例的从云服务器接收基于所述特征信息获取的所述视频的配音的方法的流程图。Fig. 2 shows a flowchart of a method for receiving from a cloud server the dubbing of the video obtained based on the feature information according to an embodiment of the present invention.

图3示出根据本发明的实施例的在电子终端获取视频配音的设备的框图。Fig. 3 shows a block diagram of a device for acquiring video dubbing at an electronic terminal according to an embodiment of the present invention.

图4示出根据本发明的实施例的接收单元的框图。Fig. 4 shows a block diagram of a receiving unit according to an embodiment of the present invention.

图5示出根据本发明的实施例的在云服务器推送视频配音的方法的流程图。Fig. 5 shows a flowchart of a method for pushing video dubbing on a cloud server according to an embodiment of the present invention.

图6示出根据本发明的实施例的将根据所述视频的标识信息获取的配音发送到电子终端的方法的流程图。Fig. 6 shows a flowchart of a method for sending dubbing acquired according to the identification information of the video to an electronic terminal according to an embodiment of the present invention.

图7示出根据本发明的实施例的在云服务器推送视频配音的设备的框图。Fig. 7 shows a block diagram of a device for pushing video dubbing on a cloud server according to an embodiment of the present invention.

图8示出根据本发明的实施例的发送单元的框图。Fig. 8 shows a block diagram of a sending unit according to an embodiment of the present invention.

具体实施方式Detailed ways

现在对本发明实施例进行详细的描述，其示例表示在附图中，其中，相同的标号始终表示相同部件。下面通过参照附图对实施例进行描述以解释本发明。Embodiments of the invention will now be described in detail, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to like parts throughout. The embodiments are described below in order to explain the present invention by referring to the figures.

图1示出根据本发明的实施例的在电子终端获取视频配音的方法的流程图。Fig. 1 shows a flowchart of a method for acquiring video dubbing on an electronic terminal according to an embodiment of the present invention.

在步骤101，获取待配音的视频的特征信息。特征信息是可以表示待配音的视频的特征的信息，根据特征信息能够识别出待配音的视频，因此，特征信息可以是各种用于识别出待配音的视频的信息。Instep 101, feature information of a video to be dubbed is acquired. The feature information is information that can represent the features of the video to be dubbed. According to the feature information, the video to be dubbed can be identified. Therefore, the feature information can be various information used to identify the video to be dubbed.

优选地，待配音的视频的特征信息可以包括待配音的视频的画面信息和/或待配音的视频的关联信息。待配音的视频的画面信息是可以表示待配音的视频的画面的信息，例如，可以包括待配音的视频的画面和/或待配音的视频的画面的特征值。待配音的视频的关联信息是与待配音的视频相关联的并且可以表示待配音的视频的特征的信息，例如，可以是待配音的视频的名称、待配音的视频的发行号、待配音的视频的关键词等。Preferably, the feature information of the video to be dubbed may include picture information of the video to be dubbed and/or associated information of the video to be dubbed. The picture information of the video to be dubbed is information that can represent the picture of the video to be dubbed, for example, may include the picture of the video to be dubbed and/or the feature value of the picture of the video to be dubbed. The associated information of the video to be dubbed is information that is associated with the video to be dubbed and can represent the characteristics of the video to be dubbed, for example, it can be the name of the video to be dubbed, the issue number of the video to be dubbed, the video to be dubbed Video keywords, etc.

可以通过现有的各种方式来获取待配音的视频的特征信息。The feature information of the video to be dubbed can be acquired through various existing methods.

在一个实施例中，当待配音的视频正在播放时，抓取待配音的视频正在播放的画面。可以利用各种图像抓取算法来抓取待配音的视频正在播放的画面，以获取待配音的视频的特征信息。此外，也可以利用各种画面特征值计算算法（例如，SURF算法）计算抓取的画面的特征值，作为待配音的视频的特征信息。In one embodiment, when the video to be dubbed is playing, a picture of the video to be dubbed is being played is captured. Various image capture algorithms may be used to capture the playing screen of the video to be dubbed, so as to obtain feature information of the video to be dubbed. In addition, various picture feature value calculation algorithms (for example, SURF algorithm) can also be used to calculate the feature value of the captured picture as feature information of the video to be dubbed.

在一个实施例中，从待配音的视频所在的文件中获取待配音的视频的特征信息，其中，在与前一抓取时的视频时间点相隔第二预定时间的视频时间点抓取待配音的视频的画面。换言之，根据待配音的视频所在的文件的时间轴，每隔时间轴上的特定时间段抓取待配音的视频的画面，以获取待配音的视频的特征信息。此外，也可以利用各种画面特征值计算算法（例如，SURF算法）计算抓取的画面的特征值，作为待配音的视频的特征信息。应该理解，待配音的视频未播放或正在播放时，都可以从待配音的视频所在的文件中获取待配音的视频的特征信息。In one embodiment, the feature information of the video to be dubbed is obtained from the file where the video to be dubbed is located, wherein the time point of the video to be dubbed is captured at a time point of the video that is separated from the time point of the previous capture by a second predetermined time screen of the video. In other words, according to the time axis of the file in which the video to be dubbed is located, the picture of the video to be dubbed is captured every specific time period on the time axis, so as to obtain the characteristic information of the video to be dubbed. In addition, various picture feature value calculation algorithms (for example, SURF algorithm) can also be used to calculate the feature value of the captured picture as feature information of the video to be dubbed. It should be understood that when the video to be dubbed is not being played or is being played, the feature information of the video to be dubbed can be obtained from the file where the video to be dubbed is located.

在一个实施例中，从信号源和/或待配音的视频所在的文件获取待配音的视频的特征信息。可以从信号源（例如，数字信号源等）获取待配音的视频的名称、待配音的视频的发行号、待配音的视频的关键词等特征信息。也可以从待配音的视频所在的文件获取待配音的视频的特征信息，例如，从待配音的视频所在的文件的文件属性信息获取待配音的视频的名称等特征信息。In one embodiment, the feature information of the video to be dubbed is obtained from the signal source and/or the file where the video to be dubbed is located. Characteristic information such as the name of the video to be dubbed, the release number of the video to be dubbed, keywords of the video to be dubbed, etc. may be acquired from a signal source (for example, a digital signal source, etc.). The feature information of the video to be dubbed can also be obtained from the file where the video to be dubbed is located, for example, the feature information such as the name of the video to be dubbed is obtained from the file attribute information of the file where the video to be dubbed is located.

在步骤102，将获取的特征信息发送到云服务器。可通过有线或者无线的方式将获取的特征信息发送到云服务器。Instep 102, the acquired feature information is sent to the cloud server. The acquired feature information can be sent to the cloud server in a wired or wireless manner.

在步骤103，从云服务器接收基于所述特征信息获取的所述视频的配音。可通过有线或者无线的方式从云服务器接收基于所述特征信息获取的所述视频的配音。Instep 103, the dubbing of the video obtained based on the feature information is received from a cloud server. The dubbing of the video obtained based on the feature information may be received from a cloud server in a wired or wireless manner.

在一个优选的实施例中，在步骤102之后，检测在第一预定时间内是否从云服务器接收到用于提示已识别待配音的视频的消息，其中，当在第一预定时间内未从云服务器接收到用于提示已识别待配音的视频的消息时，返回执行步骤101，当在第一预定时间内从云服务器接收到用于提示已识别待配音的视频的消息时，执行步骤103。具体地说，当在第一预定时间内未从云服务器接收到用于提示已识别待配音的视频的消息时，即云服务器还未识别出待配音的视频，仍需为云服务器提供待配音的视频的特征信息，因此，返回执行步骤101。当在第一预定时间内从云服务器接收到用于提示已识别待配音的视频的消息时，即云服务器已经根据待配音的视频的特征信息识别出待配音的视频，不需再为云服务器提供待配音的视频的特征信息，可执行步骤103。In a preferred embodiment, afterstep 102, it is detected whether a message for prompting that a video to be dubbed has been identified is received from the cloud server within the first predetermined time, wherein, when there is no message from the cloud server within the first predetermined time When the server receives the message for prompting that the video to be dubbed has been identified, return to step 101, and when the server receives the message for prompting that the video to be dubbed has been identified from the cloud server within the first predetermined time, performstep 103. Specifically, when the message for prompting that the video to be dubbed has been identified is not received from the cloud server within the first predetermined time, that is, the cloud server has not identified the video to be dubbed, it is still necessary to provide the cloud server with a video to be dubbed. The feature information of the video, therefore, return to step 101. When receiving a message for prompting that the video to be dubbed has been identified from the cloud server within the first predetermined time, that is, the cloud server has identified the video to be dubbed according to the feature information of the video to be dubbed, and there is no need for the cloud server to The feature information of the video to be dubbed is provided, and step 103 can be executed.

图2示出根据本发明的实施例的从云服务器接收基于所述特征信息获取的所述视频的配音的方法的流程图。可在执行步骤103时执行图2所示的方法。Fig. 2 shows a flowchart of a method for receiving from a cloud server the dubbing of the video obtained based on the feature information according to an embodiment of the present invention. The method shown in FIG. 2 may be executed whenstep 103 is executed.

在步骤201，从云服务器接收基于所述特征信息搜索到的所述视频的配音的索引。视频的配音的索引包括服务器搜索到的所述视频的全部配音的标识信息，标识信息是用于指示配音的信息，例如，可以是配音所使用的语言等。Instep 201, an index of dubbing of the video searched based on the feature information is received from a cloud server. The dubbing index of the video includes identification information of all dubbings of the video searched by the server, and the identification information is information for indicating the dubbing, for example, the language used for the dubbing.

在步骤202，将用户根据所述索引从搜索到的所述视频的配音之中选择的配音的获取请求发送到云服务器。具体地说，用户可以根据所述索引，从搜索到的所述视频的全部配音之中选择喜欢的配音。然后，将用户选择的配音的获取请求发送到云服务器。Instep 202, a request for acquiring the dubbing of the video selected by the user from the dubbing of the video searched according to the index is sent to the cloud server. Specifically, the user may select a favorite dubbing from among all dubbings of the video searched according to the index. Then, a request for acquiring the dubbing selected by the user is sent to the cloud server.

在步骤203，从云服务器接收用户请求的配音。Instep 203, the dubbing requested by the user is received from the cloud server.

图3示出根据本发明的实施例的在电子终端获取视频配音的设备的框图。Fig. 3 shows a block diagram of a device for acquiring video dubbing at an electronic terminal according to an embodiment of the present invention.

如图3所示，根据本发明的在电子终端获取视频配音的设备300包括：特征信息获取单元310、发送单元320、接收单元330。As shown in FIG. 3 , thedevice 300 for acquiring video dubbing at an electronic terminal according to the present invention includes: a characteristic information acquiring unit 310 , a sendingunit 320 , and a receivingunit 330 .

特征信息获取单元310获取待配音的视频的特征信息。特征信息是可以表示待配音的视频的特征的信息，根据特征信息能够识别出待配音的视频，因此，特征信息可以是各种用于识别出待配音的视频的信息。关于待配音的视频的特征信息前面已经详述，对此将不再详述。The characteristic information obtaining unit 310 obtains characteristic information of the video to be dubbed. The feature information is information that can represent the features of the video to be dubbed. According to the feature information, the video to be dubbed can be identified. Therefore, the feature information can be various information used to identify the video to be dubbed. The feature information about the video to be dubbed has been described in detail above, and will not be described in detail here.

特征信息获取单元310可以通过现有的各种方式来获取待配音的视频的特征信息。The characteristic information obtaining unit 310 may obtain characteristic information of the video to be dubbed in various existing ways.

在一个实施例中，当待配音的视频正在播放时，特征信息获取单元310抓取待配音的视频正在播放的画面。特征信息获取单元310可以利用各种图像抓取算法来抓取待配音的视频正在播放的画面，以获取待配音的视频的特征信息。此外，特征信息获取单元310也可以利用各种画面特征值计算算法（例如，SURF算法）计算抓取的画面的特征值，作为待配音的视频的特征信息。In one embodiment, when the video to be dubbed is playing, the characteristic information acquiring unit 310 captures the playing screen of the video to be dubbed. The characteristic information obtaining unit 310 may use various image capture algorithms to capture the playing screen of the video to be dubbed, so as to obtain the characteristic information of the video to be dubbed. In addition, the feature information acquiring unit 310 may also use various picture feature value calculation algorithms (for example, SURF algorithm) to calculate the feature value of the captured picture as feature information of the video to be dubbed.

在一个实施例中，特征信息获取单元310从待配音的视频所在的文件中获取待配音的视频的特征信息，其中，在与前一抓取时的视频时间点相隔第二预定时间的视频时间点抓取待配音的视频的画面。换言之，特征信息获取单元310根据待配音的视频所在的文件的时间轴，每隔时间轴上的特定时间段抓取待配音的视频的画面，以获取待配音的视频的特征信息。此外，特征信息获取单元310也可以利用各种画面特征值计算算法（例如，SURF算法）计算抓取的画面的特征值，作为待配音的视频的特征信息。应该理解，待配音的视频未播放或正在播放时，都可以从待配音的视频所在的文件中获取待配音的视频的特征信息。In one embodiment, the characteristic information obtaining unit 310 obtains the characteristic information of the video to be dubbed from the file where the video to be dubbed is located, wherein, at the video time point separated from the video time point of the previous capture by the second predetermined time Click to capture the screen of the video to be dubbed. In other words, according to the time axis of the file where the video to be dubbed is located, the characteristic information acquisition unit 310 captures the picture of the video to be dubbed at a specific time period on the time axis to obtain the feature information of the video to be dubbed. In addition, the feature information acquiring unit 310 may also use various picture feature value calculation algorithms (for example, SURF algorithm) to calculate the feature value of the captured picture as feature information of the video to be dubbed. It should be understood that when the video to be dubbed is not being played or is being played, the feature information of the video to be dubbed can be obtained from the file where the video to be dubbed is located.

在一个实施例中，特征信息获取单元310从信号源和/或待配音的视频所在的文件获取待配音的视频的特征信息。特征信息获取单元310可以从信号源（例如，数字信号源等）获取待配音的视频的名称、待配音的视频的发行号、待配音的视频的关键词等特征信息。特征信息获取单元310也可以从待配音的视频所在的文件获取待配音的视频的特征信息，例如，特征信息获取单元310从待配音的视频所在的文件的文件属性信息获取待配音的视频的名称等特征信息。In one embodiment, the characteristic information obtaining unit 310 obtains the characteristic information of the video to be dubbed from the signal source and/or the file where the video to be dubbed is located. The characteristic information obtaining unit 310 may obtain characteristic information such as the name of the video to be dubbed, the release number of the video to be dubbed, keywords of the video to be dubbed from a signal source (for example, a digital signal source, etc.). The feature information obtaining unit 310 may also obtain the feature information of the video to be dubbed from the file where the video to be dubbed is located, for example, the feature information obtaining unit 310 obtains the name of the video to be dubbed from the file attribute information of the file where the video to be dubbed is located and other feature information.

发送单元320将获取的特征信息发送到云服务器。发送单元320可通过有线或者无线的方式将获取的特征信息发送到云服务器。The sendingunit 320 sends the acquired feature information to the cloud server. The sendingunit 320 may send the acquired feature information to the cloud server in a wired or wireless manner.

接收单元330从云服务器接收基于所述特征信息获取的所述视频的配音。接收单元330可通过有线或者无线的方式从云服务器接收基于所述特征信息获取的所述视频的配音。The receivingunit 330 receives the dubbing of the video obtained based on the characteristic information from the cloud server. The receivingunit 330 may receive the dubbing of the video obtained based on the characteristic information from the cloud server in a wired or wireless manner.

在一个优选的实施例中，在电子终端获取视频配音的设备300还包括：检测单元（未示出）。In a preferred embodiment, thedevice 300 for acquiring video dubbing by an electronic terminal further includes: a detection unit (not shown).

检测单元在发送单元320将获取的特征信息发送到云服务器之后，检测在第一预定时间内是否从云服务器接收到用于提示已识别待配音的视频的消息，其中，当在第一预定时间内未从云服务器接收到用于提示已识别待配音的视频的消息时，返回特征信息获取单元310获取待配音的视频的特征信息，当在第一预定时间内从云服务器接收到用于提示已识别待配音的视频的消息时，接收单元330从云服务器接收基于所述特征信息获取的所述视频的配音。After the sendingunit 320 sends the acquired feature information to the cloud server, the detection unit detects whether a message for prompting that the video to be dubbed has been identified is received from the cloud server within the first predetermined time, wherein, when within the first predetermined time When not receiving the message for prompting that the video to be dubbed has been identified from the cloud server, the feature information acquisition unit 310 is returned to obtain the feature information of the video to be dubbed, and when the message for prompting is received from the cloud server within the first predetermined time When the message of the video to be dubbed has been identified, the receivingunit 330 receives the dubbed video of the video acquired based on the feature information from the cloud server.

具体地说，当在第一预定时间内未从云服务器接收到用于提示已识别待配音的视频的消息时，即云服务器还未识别出待配音的视频，仍需为云服务器提供待配音的视频的特征信息，因此，返回特征信息获取单元310获取待配音的视频的特征信息。当在第一预定时间内从云服务器接收到用于提示已识别待配音的视频的消息时，即云服务器已经根据待配音的视频的特征信息识别出待配音的视频，不需再为云服务器提供待配音的视频的特征信息，接收单元330从云服务器接收基于所述特征信息获取的所述视频的配音。Specifically, when the message for prompting that the video to be dubbed has been identified is not received from the cloud server within the first predetermined time, that is, the cloud server has not identified the video to be dubbed, it is still necessary to provide the cloud server with a video to be dubbed. Therefore, return to the feature information acquisition unit 310 to acquire feature information of the video to be dubbed. When receiving a message for prompting that the video to be dubbed has been identified from the cloud server within the first predetermined time, that is, the cloud server has identified the video to be dubbed according to the feature information of the video to be dubbed, and there is no need for the cloud server to The feature information of the video to be dubbed is provided, and the receivingunit 330 receives the dubbing of the video obtained based on the feature information from the cloud server.

图4示出根据本发明的实施例的接收单元的框图。Fig. 4 shows a block diagram of a receiving unit according to an embodiment of the present invention.

如图4所示，根据本发明的接收单元330包括：索引接收单元410、获取请求发送单元420、配音接收单元430。As shown in FIG. 4 , the receivingunit 330 according to the present invention includes: anindex receiving unit 410 , an acquisition request sending unit 420 , and adubbing receiving unit 430 .

索引接收单元410从云服务器接收基于所述特征信息搜索到的所述视频的配音的索引。视频的配音的索引包括服务器搜索到的所述视频的全部配音的标识信息，标识信息是用于指示配音的信息，例如，可以是配音所使用的语言等。Theindex receiving unit 410 receives the dubbing index of the video searched based on the feature information from the cloud server. The dubbing index of the video includes identification information of all dubbings of the video searched by the server, and the identification information is information for indicating the dubbing, for example, the language used for the dubbing.

获取请求发送单元420将用户根据所述索引从搜索到的所述视频的配音之中选择的配音的获取请求发送到云服务器。具体地说，用户可以根据所述索引，从搜索到的所述视频的全部配音之中选择喜欢的配音。然后，获取请求发送单元420将用户选择的配音的获取请求发送到云服务器。The acquisition request sending unit 420 sends an acquisition request for the dubbing selected by the user from the dubbing of the video searched according to the index to the cloud server. Specifically, the user may select a favorite dubbing from among all dubbings of the video searched according to the index. Then, the acquisition request sending unit 420 sends an acquisition request of the dubbing selected by the user to the cloud server.

配音接收单元430从云服务器接收用户请求的配音。Thedubbing receiving unit 430 receives the dubbing requested by the user from the cloud server.

图5示出根据本发明的实施例的在云服务器推送视频配音的方法的流程图。Fig. 5 shows a flowchart of a method for pushing video dubbing on a cloud server according to an embodiment of the present invention.

在步骤501，从电子终端接收待配音的视频的特征信息。特征信息是可以表示待配音的视频的特征的信息。Instep 501, feature information of a video to be dubbed is received from an electronic terminal. The characteristic information is information that can represent the characteristics of the video to be dubbed.

在步骤502，根据待配音的视频的特征信息获取所述视频的标识信息。标识信息是用于指示待配音的视频的信息（例如，待配音的视频的名称、待配音的视频的编号等）。可利用现有的各种方法来根据待配音的视频的特征信息获取所述视频的标识信息。Instep 502, the identification information of the video to be dubbed is acquired according to the feature information of the video to be dubbed. The identification information is information for indicating the video to be dubbed (for example, the name of the video to be dubbed, the number of the video to be dubbed, etc.). Various existing methods can be used to obtain the identification information of the video to be dubbed according to the feature information of the video to be dubbed.

优选地，获取具有与待配音的视频的特征信息匹配的特征信息的视频的标识信息。Preferably, the identification information of the video having feature information matching the feature information of the video to be dubbed is acquired.

在一个实施例中，所述待配音的视频的特征信息包括待配音的视频的画面信息，首先可在画面数据库中搜索与所述特征信息中的画面信息匹配的画面信息，其中，所述画面数据库存储有多个视频的画面信息。画面信息可以包括画面和/或画面的特征值中的至少一个。画面数据库可存储有大量视频的各帧画面和/或各帧画面的特征值。例如，从电子终端接收的待配音的视频的特征信息包括待配音的视频的画面的特征值，可以在画面数据库中搜索与所述画面的特征值匹配的画面的特征值。从电子终端接收的待配音的视频的特征信息包括待配音的视频的画面，可以利用各种算法在画面数据库中搜索与所述画面匹配的画面。In one embodiment, the feature information of the video to be dubbed includes picture information of the video to be dubbed, and the picture information that matches the picture information in the feature information can be searched first in the picture database, wherein the picture The database stores frame information of a plurality of videos. The picture information may include at least one of pictures and/or feature values of the pictures. The frame database may store a large amount of video frames and/or feature values of each frame. For example, the characteristic information of the video to be dubbed received from the electronic terminal includes the characteristic value of the picture of the video to be dubbed, and the characteristic value of the picture matching the characteristic value of the picture may be searched in the picture database. The feature information of the video to be dubbed received from the electronic terminal includes the picture of the video to be dubbed, and various algorithms may be used to search for a picture matching the picture in the picture database.

应该理解，从电子终端接收的待配音的视频的特征信息包括待配音的视频的画面的特征值时，电子终端所使用的计算画面的特征值的算法和画面数据库中存储的画面的特征值的计算算法是相同的。It should be understood that when the feature information of the video to be dubbed received from the electronic terminal includes the feature value of the picture of the video to be dubbed, the algorithm used by the electronic terminal to calculate the feature value of the picture and the feature value of the picture stored in the picture database The calculation algorithm is the same.

然后，获取匹配的画面信息所属的视频的标识信息。匹配的画面信息所属的视频的标识信息即是待配音的视频的标识信息。Then, the identification information of the video to which the matched picture information belongs is acquired. The identification information of the video to which the matching picture information belongs is the identification information of the video to be dubbed.

在一个优选的实施例中，确定获取的标识信息的数量，其中，当确定获取的标识信息的数量大于1或者等于0时，返回执行步骤501，当确定获取的标识信息的数量等于1时，执行步骤503。In a preferred embodiment, the quantity of the acquired identification information is determined, wherein, when it is determined that the quantity of the acquired identification information is greater than 1 or equal to 0, return to step 501, and when it is determined that the quantity of the acquired identification information is equal to 1, Executestep 503.

具体地说，当确定获取的标识信息的数量大于1时，即具有与待配音的视频的特征信息匹配的特征信息的视频有多个，不能确定待配音的视频的标识信息，因此，返回执行步骤501，继续从电子终端接收待配音的视频的特征信息。当确定获取的标识信息的数量等于0时，即没有搜索到与待配音的视频的特征信息匹配的特征信息，因此，返回执行步骤501，继续从电子终端接收待配音的视频的特征信息。当确定获取的标识信息的数量等于1时，即已确定待配音的视频的标识信息，执行步骤503。Specifically, when it is determined that the number of identification information obtained is greater than 1, that is, there are multiple videos with feature information matching the feature information of the video to be dubbed, the identification information of the video to be dubbed cannot be determined, and therefore, return toexecution Step 501, continue to receive feature information of the video to be dubbed from the electronic terminal. When it is determined that the number of acquired identification information is equal to 0, that is, no feature information matching the feature information of the video to be dubbed is found, therefore, return to step 501 and continue to receive feature information of the video to be dubbed from the electronic terminal. When it is determined that the number of acquired identification information is equal to 1, that is, the identification information of the video to be dubbed has been determined, and step 503 is executed.

优选地，当确定获取的标识信息的数量大于1时，返回执行步骤501，其中，在执行在画面数据库中搜索与所述特征信息中的画面信息匹配的画面信息的步骤时，将搜索范围设置为画面数据库中的匹配的画面信息所属的视频的画面信息。具体地说，当确定获取的标识信息的数量大于1时，即具有与待配音的视频的特征信息匹配的特征信息的视频有多个，不能确定待配音的视频的标识信息，因此，返回执行步骤501，继续从电子终端接收待配音的视频的特征信息，在执行在画面数据库中搜索与所述特征信息中的画面信息匹配的画面信息的步骤时，在画面数据库中的匹配的画面信息所属的视频的画面信息中搜索与接收的待配音的视频的画面信息匹配的画面信息。Preferably, when it is determined that the number of acquired identification information is greater than 1, return to step 501, wherein, when performing the step of searching the picture database for picture information that matches the picture information in the feature information, set the search range to is the screen information of the video to which the matched screen information in the screen database belongs. Specifically, when it is determined that the number of identification information obtained is greater than 1, that is, there are multiple videos with feature information matching the feature information of the video to be dubbed, the identification information of the video to be dubbed cannot be determined, and therefore, return toexecution Step 501, continue to receive the feature information of the video to be dubbed from the electronic terminal, and when performing the step of searching the picture database for picture information that matches the picture information in the feature information, the matching picture information in the picture database belongs to The screen information of the video to be dubbed is searched for the screen information matching the received screen information of the video to be dubbed.

在一个实施例中，当确定获取的标识信息的数量等于1时，生成用于提示已识别待配音的视频的消息。然后，将所述用于提示已识别待配音的视频的消息发送到电子终端。具体地说，当确定获取的标识信息的数量等于1时，即已确定待配音的视频的标识信息，不需要再从电子终端获取待配音的视频的特征信息，因此，生成用于提示已识别待配音的视频的消息发送到电子终端，以提示电子终端停止发送待配音的视频的特征信息。In one embodiment, when it is determined that the number of acquired identification information is equal to 1, a message for prompting that a video to be dubbed has been identified is generated. Then, the message for prompting that the video to be dubbed has been identified is sent to the electronic terminal. Specifically, when it is determined that the number of acquired identification information is equal to 1, that is, the identification information of the video to be dubbed has been determined, and there is no need to obtain the feature information of the video to be dubbed from the electronic terminal. The message of the video to be dubbed is sent to the electronic terminal to prompt the electronic terminal to stop sending the characteristic information of the video to be dubbed.

在步骤503，将根据所述视频的标识信息获取的配音发送到电子终端。Instep 503, the dubbing obtained according to the identification information of the video is sent to the electronic terminal.

图6示出根据本发明的实施例的将根据所述视频的标识信息获取的配音发送到电子终端的方法的流程图。可在执行步骤503时执行图6所示的方法。Fig. 6 shows a flowchart of a method for sending dubbing acquired according to the identification information of the video to an electronic terminal according to an embodiment of the present invention. The method shown in FIG. 6 may be executed whenstep 503 is executed.

在步骤601，根据所述视频的标识信息搜索所述视频的配音并生成搜索到的配音的索引。索引包括搜索到的所述视频的全部配音的标识信息，标识信息是用于指示配音的信息，例如，可以是配音所使用的语言等。Instep 601, search for the dubbing of the video according to the identification information of the video and generate an index of the found dubbing. The index includes identification information of all dubbings of the searched video, where the identification information is information used to indicate dubbing, for example, the language used for dubbing.

在步骤602，将所述索引发送到电子终端。Instep 602, the index is sent to the electronic terminal.

在步骤603，从电子终端接收用户基于所述索引从搜索到的配音之中选择的配音的获取请求。Instep 603, a request for acquiring a dubbing selected by the user from the searched dubbings based on the index is received from the electronic terminal.

在步骤604，响应于所述请求将请求的配音发送到电子终端。换言之，将用户根据所述索引从搜索到的配音之中选择的配音发送到电子终端。Instep 604, the requested dubbing is sent to the electronic terminal in response to the request. In other words, the dubbing selected by the user from among the searched dubbings according to the index is transmitted to the electronic terminal.

图7示出根据本发明的实施例的在云服务器推送视频配音的设备的框图。Fig. 7 shows a block diagram of a device for pushing video dubbing on a cloud server according to an embodiment of the present invention.

如图7所示，根据本发明的在云服务器推送视频配音的设备700包括：接收单元710、标识信息获取单元720、发送单元730。As shown in FIG. 7 , thedevice 700 for pushing video dubbing on a cloud server according to the present invention includes: a receivingunit 710 , an identification information acquiring unit 720 , and a sendingunit 730 .

接收单元710从电子终端接收待配音的视频的特征信息。特征信息是可以表示待配音的视频的特征的信息。The receivingunit 710 receives feature information of the video to be dubbed from the electronic terminal. The characteristic information is information that can represent the characteristics of the video to be dubbed.

标识信息获取单元720根据待配音的视频的特征信息获取所述视频的标识信息。标识信息是用于指示待配音的视频的信息（例如，待配音的视频的名称、待配音的视频的编号等）。标识信息获取单元720可利用现有的各种方法来根据待配音的视频的特征信息获取所述视频的标识信息。The identification information acquiring unit 720 acquires the identification information of the video to be dubbed according to the feature information of the video to be dubbed. The identification information is information for indicating the video to be dubbed (for example, the name of the video to be dubbed, the number of the video to be dubbed, etc.). The identification information obtaining unit 720 may use various existing methods to obtain the identification information of the video to be dubbed according to the feature information of the video to be dubbed.

优选地，标识信息获取单元720获取具有与待配音的视频的特征信息匹配的特征信息的视频的标识信息。Preferably, the identification information acquiring unit 720 acquires the identification information of the video having feature information that matches the feature information of the video to be dubbed.

在一个实施例中，所述待配音的视频的特征信息包括待配音的视频的画面信息，标识信息获取单元720首先可在画面数据库中搜索与所述特征信息中的画面信息匹配的画面信息，其中，所述画面数据库存储有多个视频的画面信息。画面信息可以包括画面和/或画面的特征值中的至少一个。画面数据库可存储有大量视频的各帧画面和/或各帧画面的特征值。例如，接收单元710从电子终端接收的待配音的视频的特征信息包括待配音的视频的画面的特征值，标识信息获取单元720可以在画面数据库中搜索与所述画面的特征值匹配的画面的特征值。接收单元710从电子终端接收的待配音的视频的特征信息包括待配音的视频的画面，标识信息获取单元720可以利用各种算法在画面数据库中搜索与所述画面匹配的画面。In one embodiment, the feature information of the video to be dubbed includes picture information of the video to be dubbed, and the identification information acquiring unit 720 may first search the picture database for picture information that matches the picture information in the feature information, Wherein, the picture database stores picture information of multiple videos. The picture information may include at least one of pictures and/or feature values of the pictures. The frame database may store a large amount of video frames and/or feature values of each frame. For example, the feature information of the video to be dubbed received by the receivingunit 710 from the electronic terminal includes the feature value of the picture of the video to be dubbed, and the identification information acquisition unit 720 may search the picture database for the picture that matches the feature value of the picture. Eigenvalues. The feature information of the video to be dubbed received by the receivingunit 710 from the electronic terminal includes the picture of the video to be dubbed, and the identification information acquiring unit 720 may use various algorithms to search for a picture matching the picture in the picture database.

应该理解，接收单元710从电子终端接收的待配音的视频的特征信息包括待配音的视频的画面的特征值时，电子终端所使用的计算画面的特征值的算法和画面数据库中存储的画面的特征值的计算算法是相同的。It should be understood that when the feature information of the video to be dubbed received by the receivingunit 710 from the electronic terminal includes the feature value of the picture of the video to be dubbed, the algorithm used by the electronic terminal to calculate the feature value of the picture and the picture stored in the picture database The calculation algorithm for the eigenvalues is the same.

然后，标识信息获取单元720获取匹配的画面信息所属的视频的标识信息。匹配的画面信息所属的视频的标识信息即是待配音的视频的标识信息。Then, the identification information acquiring unit 720 acquires the identification information of the video to which the matched picture information belongs. The identification information of the video to which the matching picture information belongs is the identification information of the video to be dubbed.

在一个优选的实施例中，在云服务器推送视频配音的设备700还包括：确定单元（未示出）。In a preferred embodiment, thedevice 700 for pushing video dubbing on the cloud server further includes: a determining unit (not shown).

确定单元确定获取的标识信息的数量，其中，当确定获取的标识信息的数量大于1或者等于0时，返回接收单元710从电子终端接收待配音的视频的特征信息，当确定获取的标识信息的数量等于1时，发送单元730将根据所述视频的标识信息获取的配音发送到电子终端。The determination unit determines the quantity of the acquired identification information, wherein, when it is determined that the acquired identification information is greater than 1 or equal to 0, thereturn receiving unit 710 receives the feature information of the video to be dubbed from the electronic terminal, and when it is determined that the acquired identification information When the number is equal to 1, the sendingunit 730 sends the dubbing obtained according to the identification information of the video to the electronic terminal.

具体地说，当确定单元确定获取的标识信息的数量大于1时，即具有与待配音的视频的特征信息匹配的特征信息的视频有多个，不能确定待配音的视频的标识信息，因此，返回接收单元710从电子终端接收待配音的视频的特征信息。当确定获取的标识信息的数量等于0时，即没有搜索到与待配音的视频的特征信息匹配的特征信息，因此，返回接收单元710从电子终端接收待配音的视频的特征信息。当确定单元确定获取的标识信息的数量等于1时，即已确定待配音的视频的标识信息，发送单元730将根据所述视频的标识信息获取的配音发送到电子终端。Specifically, when the determination unit determines that the number of identification information acquired is greater than 1, that is, there are multiple videos with feature information matching the feature information of the video to be dubbed, the identification information of the video to be dubbed cannot be determined. Therefore, Thereturn receiving unit 710 receives feature information of the video to be dubbed from the electronic terminal. When it is determined that the number of acquired identification information is equal to 0, that is, no feature information matching the feature information of the video to be dubbed is found. Therefore, thereturn receiving unit 710 receives the feature information of the video to be dubbed from the electronic terminal. When the determination unit determines that the number of acquired identification information is equal to 1, that is, the identification information of the video to be dubbed has been determined, and the sendingunit 730 sends the dubbing acquired according to the identification information of the video to the electronic terminal.

在一个实施例中，，当确定单元确定获取的标识信息的数量大于1时，返回接收单元710从电子终端接收待配音的视频的特征信息，其中，标识信息获取单元720在画面数据库中搜索与所述特征信息中的画面信息匹配的画面信息时，将搜索范围设置为画面数据库中的匹配的画面信息所属的视频的画面信息。具体地说，当确定单元确定获取的标识信息的数量大于1时，即具有与待配音的视频的特征信息匹配的特征信息的视频有多个，不能确定待配音的视频的标识信息，因此，返回接收单元710从电子终端接收待配音的视频的特征信息，标识信息获取单元在画面数据库中搜索与所述特征信息中的画面信息匹配的画面信息时，在画面数据库中的匹配的画面信息所属的视频的画面信息中搜索与接收的待配音的视频的画面信息匹配的画面信息。In one embodiment, when the determination unit determines that the number of acquired identification information is greater than 1, thereturn receiving unit 710 receives the feature information of the video to be dubbed from the electronic terminal, wherein the identification information acquisition unit 720 searches the picture database corresponding to When the picture information in the characteristic information matches the picture information, the search range is set to the picture information of the video to which the matched picture information in the picture database belongs. Specifically, when the determination unit determines that the number of identification information acquired is greater than 1, that is, there are multiple videos with feature information matching the feature information of the video to be dubbed, the identification information of the video to be dubbed cannot be determined. Therefore, Thereturn receiving unit 710 receives the feature information of the video to be dubbed from the electronic terminal, and when the identification information acquisition unit searches the picture database for picture information matching the picture information in the feature information, the matching picture information in the picture database belongs to The screen information of the video to be dubbed is searched for the screen information matching the received screen information of the video to be dubbed.

在一个实施例中，在云服务器推送视频配音的设备700还包括：消息生成单元（未示出）和消息发送单元（未示出）。In one embodiment, thedevice 700 for pushing video dubbing on a cloud server further includes: a message generating unit (not shown) and a message sending unit (not shown).

消息生成单元当确定单元确定获取的标识信息的数量等于1时，生成用于提示已识别待配音的视频的消息。消息发送单元将所述用于提示已识别待配音的视频的消息发送到电子终端。具体地说，当确定单元确定获取的标识信息的数量等于1时，即已确定待配音的视频的标识信息，不需要再从电子终端获取待配音的视频的特征信息，因此，消息生成单元生成用于提示已识别待配音的视频的消息经由消息发送单元发送到电子终端，以提示电子终端停止发送待配音的视频的特征信息。The message generating unit generates a message for prompting that the video to be dubbed has been identified when the determining unit determines that the number of acquired identification information is equal to 1. The message sending unit sends the message for prompting that the video to be dubbed has been identified to the electronic terminal. Specifically, when the determination unit determines that the number of acquired identification information is equal to 1, that is, the identification information of the video to be dubbed has been determined, and there is no need to obtain the feature information of the video to be dubbed from the electronic terminal. Therefore, the message generating unit generates The message for prompting that the video to be dubbed has been identified is sent to the electronic terminal via the message sending unit, so as to prompt the electronic terminal to stop sending the characteristic information of the video to be dubbed.

发送单元730将根据所述视频的标识信息获取的配音发送到电子终端。The sendingunit 730 sends the dubbing acquired according to the identification information of the video to the electronic terminal.

图8示出根据本发明的实施例的发送单元的框图。Fig. 8 shows a block diagram of a sending unit according to an embodiment of the present invention.

如图8所示，根据本发明的发送单元730包括：索引生成单元810、索引发送单元820、获取请求接收单元830、配音发送单元840。As shown in FIG. 8 , the sendingunit 730 according to the present invention includes: anindex generating unit 810 , an index sending unit 820 , an acquisition request receiving unit 830 , and adubbing sending unit 840 .

索引生成单元810根据所述视频的标识信息搜索所述视频的配音并生成搜索到的配音的索引。索引包括搜索到的所述视频的全部配音的标识信息，标识信息是用于指示配音的信息，例如，可以是配音所使用的语言等。Theindex generating unit 810 searches for the dubbing of the video according to the identification information of the video and generates an index of the found dubbing. The index includes identification information of all dubbings of the searched video, where the identification information is information used to indicate dubbing, for example, the language used for dubbing.

索引发送单元820将所述索引发送到电子终端。The index sending unit 820 sends the index to the electronic terminal.

获取请求接收单元830从电子终端接收用户基于所述索引从搜索到的配音之中选择的配音的获取请求。The acquisition request receiving unit 830 receives an acquisition request of a dubbing selected by the user from among the searched dubbings based on the index from the electronic terminal.

配音发送单元840响应于所述请求将请求的配音发送到电子终端。换言之，配音发送单元840将用户根据所述索引从搜索到的配音之中选择的配音发送到电子终端。Thedubbing sending unit 840 sends the requested dubbing to the electronic terminal in response to the request. In other words, thedubbing transmitting unit 840 transmits the dubbing selected by the user from among the dubbings searched according to the index to the electronic terminal.

应该理解，上述方法和设备所涉及的云服务器可以是各种部署了存储云和计算云的云计算平台（例如，AWS云计算平台）。It should be understood that the cloud server involved in the above methods and devices may be various cloud computing platforms (for example, AWS cloud computing platform) on which storage clouds and computing clouds are deployed.

此外，根据本发明的示例性实施例的上述方法可以被实现为计算机程序，从而当运行该程序时，实现上述方法。根据本发明的示例性实施例的上述设备中的各个单元可被实现硬件组件。本领域技术人员根据限定的各个单元所执行的处理，可以例如使用现场可编程门阵列（FPGA）或专用集成电路（ASIC）来实现各个单元。Furthermore, the above-described methods according to exemplary embodiments of the present invention can be implemented as a computer program so that when the program is executed, the above-described methods are implemented. Each unit in the above-described apparatus according to an exemplary embodiment of the present invention may be implemented as a hardware component. Those skilled in the art may implement each unit, for example, using a Field Programmable Gate Array (FPGA) or an Application Specific Integrated Circuit (ASIC) according to the defined processing performed by each unit.

根据本发明的获取视频配音的方法及设备，可以获取视频文件本身所携带的配音之外的配音，提供多种配音供用户选择，满足用户需求，不受视频文件本身所携带的配音的限制。According to the method and device for obtaining video dubbing of the present invention, dubbing other than the dubbing carried in the video file itself can be obtained, and a variety of dubbing can be provided for users to choose, satisfying user needs, and not limited by the dubbing carried in the video file itself.

虽然已表示和描述了本发明的一些实施例，但本领域技术人员应该理解，在不脱离由权利要求及其等同物限定其范围的本发明的原理和精神的情况下，可以对这些实施例进行修改。While certain embodiments of the present invention have been shown and described, it should be understood by those skilled in the art that modifications may be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents. to modify.

Claims (38)

1. obtain the method that video is dubbed, comprising:

A) obtain the characteristic information of video to be dubbed;

B) characteristic information obtaining is sent to Cloud Server;

C) dubbing of the described video obtaining based on described characteristic information from Cloud Server reception.

2. the step of dubbing of the described video the method for claim 1, wherein obtaining based on described characteristic information from Cloud Server reception comprises:

From Cloud Server, receive the index of dubbing of the described video searching based on described characteristic information;

User is sent to Cloud Server according to described index from the request of obtaining of dubbing of selecting among the dubbing of the described video that searches;

From Cloud Server, receive dubbing of user's request.

3. method as claimed in claim 1 or 2, wherein, described in the characteristic information of video to be dubbed comprise the image information of video to be dubbed and/or the related information of video to be dubbed.

4. method as claimed in claim 3, wherein, the image information of video to be dubbed comprises the characteristic value of the picture of video to be dubbed and/or the picture of video to be dubbed.

5. the method for claim 1, also comprises:

After step b), detect whether from Cloud Server, receive the message of identifying video to be dubbed for pointing out within first scheduled time,

Wherein, when not receiving when pointing out the message of identifying wait the video of dubbing from Cloud Server, return to execution step a) within first scheduled time,

When receiving when pointing out the message of identifying wait the video of dubbing from Cloud Server within first scheduled time, execution step c).

6. the method for claim 1, wherein when the video wait dubbing is being play, step a) comprises:

Capture the in progress picture of video to be dubbed.

7. the method for claim 1, wherein step a) comprises:

From the file at video place to be dubbed, obtain the characteristic information of video to be dubbed,

Wherein, the be separated by video time point of second scheduled time of the video time point when with last capture captures the picture of video to be dubbed.

8. method as claimed in claim 3, wherein, described in the related information of video to be dubbed from the file acquisition at signal source and/or video place to be dubbed.

9. the method as described in claim 3 or 8, wherein, described in the related information of video to be dubbed comprise the title of video to be dubbed, at least one in the keyword of the issue number of video to be dubbed, video to be dubbed.

10. obtain the equipment that video is dubbed, comprising:

Characteristic acquisition unit, obtains the characteristic information of video to be dubbed;

Transmitting element, sends to Cloud Server by the characteristic information obtaining;

Receiving element, receives dubbing of the described video obtain based on described characteristic information from Cloud Server.

11. equipment as claimed in claim 10, wherein, receiving element comprises:

Index receiving element, the index of dubbing of the described video searching based on described characteristic information from Cloud Server reception;

Obtain request transmitting unit, user is sent to Cloud Server according to described index from the request of obtaining of dubbing of selecting among the dubbing of the described video that searches;

Dub receiving element, from Cloud Server, receive dubbing of user's request.

12. equipment as described in claim 10 or 11, wherein, described in the characteristic information of video to be dubbed comprise the image information of video to be dubbed and/or the related information of video to be dubbed.

13. equipment as claimed in claim 12, wherein, the image information of video to be dubbed comprises the characteristic value of the picture of video to be dubbed and/or the picture of video to be dubbed.

14. equipment as claimed in claim 10, also comprise:

Detecting unit, after transmitting element sends to Cloud Server by the characteristic information obtaining, detects whether from Cloud Server, receive the message of identifying video to be dubbed for pointing out within first scheduled time,

Wherein, when not receiving when pointing out the message of identifying wait the video of dubbing from Cloud Server within first scheduled time, backout feature information acquisition unit is obtained the characteristic information of video to be dubbed,

When receiving when pointing out the message of identifying wait the video of dubbing from Cloud Server within first scheduled time, receiving element receives dubbing of the described video that obtains based on described characteristic information from Cloud Server.

15. equipment as claimed in claim 10, wherein, when the video wait dubbing is being play, characteristic acquisition unit captures the in progress picture of video to be dubbed.

16. equipment as claimed in claim 10, wherein, characteristic acquisition unit is obtained the characteristic information of video to be dubbed from the file at video place to be dubbed,

Wherein, the be separated by video time point of second scheduled time of the video time point when with last capture captures the picture of video to be dubbed.

17. equipment as claimed in claim 12, wherein, described in the related information of video to be dubbed from the file acquisition at signal source and/or video place to be dubbed.

18. equipment as described in claim 12 or 17, wherein, described in the related information of video to be dubbed comprise the title of video to be dubbed, at least one in the keyword of the issue number of video to be dubbed, video to be dubbed.

19. 1 kinds of methods of dubbing at Cloud Server pushing video, comprising:

A) from electric terminal, receive the characteristic information of video to be dubbed;

B) according to the characteristic information of video to be dubbed, obtain the identification information of described video;

C) dubbing of obtaining according to the identification information of described video sent to electric terminal.

20. methods as claimed in claim 19, wherein, step b) comprises:

Obtain the identification information of the video with the characteristic information mating with the characteristic information of video to be dubbed.

21. methods as claimed in claim 19, wherein, step c) comprises:

According to the identification information of described video, search for dubbing of described video and generate the index of dubbing searching;

Described index is sent to electric terminal;

From electric terminal receive user based on described index from search dub among the request of obtaining of dubbing selected;

In response to described request, dubbing of request sent to electric terminal.

22. methods as claimed in claim 20, wherein, described in the characteristic information of video to be dubbed comprise the image information of video to be dubbed, the step of obtaining the identification information of the video with the characteristic information mating with the characteristic information of video to be dubbed comprises:

The image information that search is mated with image information in described characteristic information in picture data storehouse, wherein, described picture data stock contains the image information of a plurality of videos;

Obtain the identification information of the video under the image information of coupling.

23. methods as claimed in claim 22, also comprise:

Determine the quantity of the identification information obtaining,

Wherein, when determining that the quantity of the identification information obtain is greater than 1 or while equaling 0, return to execution step a),

When determining that the quantity of the identification information obtaining equals 1, execution step c).

24. methods as claimed in claim 23, wherein, determine that the step of the quantity of the identification information obtaining comprises:

When determining that the quantity of the identification information obtaining is greater than 1, return to execution step a),

Wherein, when carrying out the step of the image information that in picture data storehouse search mates with image information in described characteristic information, hunting zone is set to the image information of the video under the image information of the coupling in picture data storehouse.

25. methods as claimed in claim 23, also comprise:

When determining that the quantity of the identification information obtaining equals 1, generate for pointing out the message of identifying video to be dubbed;

The described message of identifying video to be dubbed for pointing out is sent to electric terminal.

26. methods as described in claim 19 or 20, wherein, described in the characteristic information of video to be dubbed comprise the image information of video to be dubbed and/or the related information of video to be dubbed.

27. methods as claimed in claim 26, wherein, the image information of video to be dubbed comprises the characteristic value of the picture of video to be dubbed and/or the picture of video to be dubbed.

28. methods as claimed in claim 27, wherein, described in the related information of video to be dubbed comprise the title of video to be dubbed, at least one in the keyword of the issue number of video to be dubbed, video to be dubbed.

29. 1 kinds of equipment of dubbing at Cloud Server pushing video, comprising:

Receiving element, receives the characteristic information of video to be dubbed from electric terminal;

Identification information obtaining unit, obtains the identification information of described video according to the characteristic information of video to be dubbed;

Transmitting element, sends to electric terminal by dubbing of obtaining according to the identification information of described video.

30. equipment as claimed in claim 29, wherein, identification information obtaining unit is obtained the identification information of the video with the characteristic information mating with the characteristic information of video to be dubbed.

31. equipment as claimed in claim 29, wherein, transmitting element comprises:

Index generation unit, searches for dubbing of described video and generates the index of dubbing searching according to the identification information of described video;

Index transmitting element, sends to electric terminal by described index;

Obtain request reception unit, from electric terminal receive user based on described index from search dub among the request of obtaining of dubbing selected;

Dub transmitting element, in response to described request, dubbing of request sent to electric terminal.

32. equipment as claimed in claim 30, wherein, described in the characteristic information of video to be dubbed comprise the image information of video to be dubbed, identification information obtaining unit comprises:

Image information matching unit, the image information that search is mated with image information in described characteristic information in picture data storehouse, wherein, described picture data stock contains the image information of a plurality of videos;

Acquiring unit, obtains the identification information of the video under the image information of coupling.

33. equipment as claimed in claim 32, also comprise:

Determining unit, the quantity of definite identification information obtaining,

Wherein, when determining that the quantity of the identification information obtain is greater than 1 or while equaling 0, return to receiving element and from electric terminal, receive the characteristic information of video to be dubbed,

When determining that the quantity of the identification information obtaining equals 1, transmitting element sends to electric terminal by dubbing of obtaining according to the identification information of described video.

34. equipment as claimed in claim 33, wherein, when determining unit determines that the quantity of the identification information obtaining is greater than 1, return to receiving element and from electric terminal, receive the characteristic information of video to be dubbed,

Wherein, while searching for the image information mating with image information in described characteristic information in picture data storehouse at image information matching unit, hunting zone is set to the image information of the video under the image information of the coupling in picture data storehouse.

35. equipment as claimed in claim 33, also comprise:

Message generation unit, when determining unit determines that the quantity of the identification information obtaining equals 1, generates for pointing out the message of identifying video to be dubbed;

Message sending unit, sends to electric terminal by the described message of identifying video to be dubbed for pointing out.

36. equipment as described in claim 29 or 30, wherein, described in the characteristic information of video to be dubbed comprise the image information of video to be dubbed and/or the related information of video to be dubbed.

37. equipment as claimed in claim 36, wherein, the image information of video to be dubbed comprises the characteristic value of the picture of video to be dubbed and/or the picture of video to be dubbed.

38. equipment as claimed in claim 37, wherein, described in the related information of video to be dubbed comprise the title of video to be dubbed, at least one in the keyword of the issue number of video to be dubbed, video to be dubbed.

Images