CN110121116A

CN110121116A - Video generation method and device

Info

Publication number: CN110121116A
Application number: CN201810119436.0A
Authority: CN
Inventors: 李东
Original assignee: Shanghai Quan Toodou Cultural Communication Co Ltd
Current assignee: Alibaba China Co Ltd
Priority date: 2018-02-06
Filing date: 2018-02-06
Publication date: 2019-08-13

Abstract

This disclosure relates to a kind of video generation method and device.This method comprises: the request of the generation video sent in response to terminal device, determines the corresponding keyword of semantic content that request includes；Obtain the video clip to match with keyword；According to video clip, target video is generated；Controlling terminal equipment shows target video.According to the embodiment of the present disclosure, it is able to respond the request of the generation video sent in terminal device, determine the corresponding keyword of semantic content that request includes, to analyze the content that user wishes the video generated, by obtaining the video clip to match with keyword, according to video clip, generate target video, and controlling terminal equipment shows the target video, so that convenient user is quickly generated the video for meeting wish, reduces the cost of video creation.

Description

Video generation method and device

Technical field

This disclosure relates to field of computer technology more particularly to a kind of video generation method and device.

Background technique

Nowadays, whole people's video epoch are come into, video is seen everywhere in daily life, people not only can at any time with Ground shoots video by various equipment (for example, mobile phone, camera etc.), can also according to oneself all kinds of videos of creative making, depending on Frequency has become a kind of social tool that people link up, entertain gradually.

Summary of the invention

In view of this, can facilitate user the present disclosure proposes a kind of video generation method and device and be quickly generated symbol The video of desirable hope reduces the cost of video creation.

According to the one side of the disclosure, a kind of video generation method is provided, which comprises

In response to the request for the generation video that terminal device is sent, the corresponding pass of semantic content for requesting to include is determined Keyword；

Obtain the video clip to match with the keyword；

According to the video clip, target video is generated；

Controlling terminal equipment shows the target video.

In one possible implementation, the request includes in text request, voice request and picture request At least one,

Wherein, the request of the generation video sent in response to terminal device, determines the semantic content pair for requesting to include The keyword answered, comprising:

In response to the request for the generation video that terminal device is sent, the corresponding text information of the request is determined；

According to the semantic content that the text information includes, the keyword is determined.

In one possible implementation, the text information includes multiple semantic contents,

Wherein, the semantic content for including according to the text information determines the keyword, comprising:

Determine the corresponding keyword of each semantic content；

Wherein, the video clip to match with the keyword is obtained, comprising:

Obtain the video clip that keyword corresponding with semantic content each in multiple semantic contents matches.

In one possible implementation, according to the video clip, target video is generated, comprising:

According to the semantic content for requesting to include, video clip is ranked up, and according to the video clip after sequence Generate the target video.

For any semantic content for requesting to include, the view to be matched according to keyword corresponding with the semantic content Frequency segment generates the corresponding target video of the semantic content.

In one possible implementation, the video clip to match with the keyword is obtained, comprising:

In the case where the content of video clip is consistent with the semanteme of keyword, the video clip and the key are determined Word matches.

In one possible implementation, the method also includes:

Obtain the audio content to match with the keyword；

Wherein, according to the video clip, target video is generated, comprising:

According to the video clip and the audio content, the target video is generated.

In one possible implementation, the method also includes:

It is determining to be regarded with described first in response to terminal device to the replacement request of the first video clip of the target video The corresponding candidate video segment of the keyword that frequency segment matches；

Controlling terminal equipment shows the candidate video segment；

The candidate video segment chosen according to terminal device, regenerates target video.

In one possible implementation, the method also includes:

The editing of the target video is requested in response to terminal device, determines clip information；

According to the clip information, target video is regenerated.

According to another aspect of the present disclosure, a kind of video-generating device is provided, described device includes:

Keyword determining module, the request of the generation video for sending in response to terminal device, determines the request packet The corresponding keyword of the semantic content contained；

Video clip obtains module, for obtaining the video clip to match with the keyword；

First video generation module, for generating target video according to the video clip；

First control module shows the target video for controlling terminal equipment.

Wherein, the keyword determining module includes:

Text information determines submodule, the request of the generation video for sending in response to terminal device, asks described in determination Seek corresponding text information；

First keyword determines submodule, and the semantic content for including according to the text information determines the key Word.

Wherein, first keyword determines that submodule includes:

Second keyword determines submodule, for determining the corresponding keyword of each semantic content；

Wherein, the video clip acquisition module includes:

Video clip acquisition submodule, for obtaining keyword phase corresponding with semantic content each in multiple semantic contents The video clip matched.

In one possible implementation, the first video generation module includes:

First video generates submodule, for being ranked up to video clip according to the semantic content for requesting to include, And the target video is generated according to the video clip after sequence.

In one possible implementation, the first video generation module includes:

Second video generate submodule, for for it is described request include any semantic content, according to in the semanteme Hold the video clip that corresponding keyword matches, generates the corresponding target video of the semantic content.

In one possible implementation, the video clip acquisition module includes:

Submodule is determined, for determining the view in the case where the content of video clip is consistent with the semanteme of keyword Frequency segment matches with the keyword.

In one possible implementation, described device further include:

Audio content obtains module, for obtaining the audio content to match with the keyword；

Wherein, the first video generation module includes:

Third video generates submodule, for generating the target according to the video clip and the audio content Video.

In one possible implementation, described device further include:

Candidate video segment determining module, in response to terminal device to the first video clip of the target video Replacement request determines candidate video segment corresponding with the keyword that first video clip matches；

Second control module shows the candidate video segment for controlling terminal equipment；

Second video generation module, the candidate video segment for being chosen according to terminal device, regenerates target video.

In one possible implementation, described device further include:

Clip information determining module determines editing for requesting in response to terminal device the editing of the target video Information；

Third video generation module, for regenerating target video according to the clip information.

According to another aspect of the present disclosure, a kind of video-generating device is provided, comprising: processor；It is handled for storage The memory of device executable instruction；Wherein, the processor is configured to executing the above method.

According to another aspect of the present disclosure, a kind of non-volatile computer readable storage medium storing program for executing is provided, is stored thereon with Computer program instructions, wherein the computer program instructions realize above-mentioned video generation method when being executed by processor.

According to the embodiment of the present disclosure, it is able to respond the request of the generation video sent in terminal device, determines that request includes The corresponding keyword of semantic content matched by obtaining with keyword with analyzing the content that user wishes the video generated Video clip target video is generated, and controlling terminal equipment shows the target video, to just utilize according to video clip Family is quickly generated the video for meeting wish, reduces the cost of video creation.

According to below with reference to the accompanying drawings to detailed description of illustrative embodiments, the other feature and aspect of the disclosure will become It is clear.

Detailed description of the invention

Comprising in the description and constituting the attached drawing of part of specification and specification together illustrates the disclosure Exemplary embodiment, feature and aspect, and for explaining the principles of this disclosure.

Fig. 1 is a kind of flow chart of video generation method shown according to an exemplary embodiment.

Fig. 2 is a kind of flow chart of video generation method shown according to an exemplary embodiment.

Fig. 3 is a kind of flow chart of video generation method shown according to an exemplary embodiment.

Fig. 4 is a kind of flow chart of video generation method shown according to an exemplary embodiment.

Fig. 5 is a kind of flow chart of video generation method shown according to an exemplary embodiment.

Fig. 6 is a kind of schematic diagram of the application scenarios of video generation method shown according to an exemplary embodiment.

Fig. 7 is a kind of schematic diagram of the application scenarios of video generation method shown according to an exemplary embodiment.

Fig. 8 is a kind of block diagram of video-generating device shown according to an exemplary embodiment.

Fig. 9 is a kind of block diagram of video-generating device shown according to an exemplary embodiment.

Figure 10 is a kind of block diagram of video-generating device shown according to an exemplary embodiment.

Specific embodiment

Various exemplary embodiments, feature and the aspect of the disclosure are described in detail below with reference to attached drawing.It is identical in attached drawing Appended drawing reference indicate element functionally identical or similar.Although the various aspects of embodiment are shown in the attached drawings, remove It non-specifically points out, it is not necessary to attached drawing drawn to scale.

Dedicated word " exemplary " means " being used as example, embodiment or illustrative " herein.Here as " exemplary " Illustrated any embodiment should not necessarily be construed as preferred or advantageous over other embodiments.

In addition, giving numerous details in specific embodiment below to better illustrate the disclosure. It will be appreciated by those skilled in the art that without certain details, the disclosure equally be can be implemented.In some instances, for Method, means, element and circuit well known to those skilled in the art are not described in detail, in order to highlight the purport of the disclosure.

Fig. 1 is a kind of flow chart of video generation method shown according to an exemplary embodiment.This method can be applied to In server.As shown in Figure 1, the video generation method according to the embodiment of the present disclosure includes:

In step s101, the request of the generation video sent in response to terminal device, determines the language for requesting to include The corresponding keyword of adopted content；

In step s 102, the video clip to match with the keyword is obtained；

In step s 103, according to the video clip, target video is generated；

In step S104, controlling terminal equipment shows the target video.

The semantic content pair for including according to the embodiment of the present disclosure, the request by the generation video of determining terminal device transmission The keyword answered obtains the video clip to match with keyword, according to video clip, generates target video, and controlling terminal Equipment shows the target video, in this way, server can pass through determination according to the request for the generation video that terminal device is sent Request includes the corresponding keyword of semantic content, to analyze the content that user wishes the video generated, by obtaining and the pass The video clip that keyword matches generates target video, and convenient user is quickly generated the video for meeting wish, reduces video wound The cost of work.

For example, user produces video creation inspiration, and video creation inspiration may be from certain sheet in its reading Novel, some webpage, some video of viewing etc., want to create video according to its video creation inspiration.However, video is created Process is often more complex, needs oneself shooting video material, carries out editing processing etc. to video material, video create cost compared with It is high.At this point, user can send the request for generating video by its terminal device, for example, can be by its mobile phone, computer etc. eventually End equipment sends the request for generating video.Server in response to terminal device send generation video request, determine described in ask Seek the corresponding keyword of the semantic content for including.

In one possible implementation, the request includes in text request, voice request and picture request It is at least one.

For example, the request for generating video can be text request.For example, user initiates to generate video by its computer Request, text information relevant to its video creation inspiration can be inputted.For example, the video creation inspiration of user from Certain section words of its certain this novel read, user can input this section of words, initiate the request for generating video.Generate asking for video Asking can also be voice request.For example, user can be wished video scene, video details for generating etc. by voice mode Relevant information is sent to server by terminal device.For example, user can issue a Duan Yuyin, the voice to its terminal device Its video creation inspiration is described in detail or it wishes content included by the video generated etc..Generate video request can also be Picture request.For example, user can take pictures to fictitious certain section words by its mobile phone, and is sent and generated by its mobile phone The picture of video is requested.The request for generating video can also be a variety of, the example in text request, voice request and picture request Such as, user takes pictures to fictitious certain section words by its mobile phone, and the picture request for generating video is sent by its mobile phone Afterwards, the request for generating video can also be supplemented by modes such as voice request, text requests.

In this way, the form for generating the request of video can be enriched, the use habit of different user is met, it is convenient User sends the request for generating video according to its use habit by terminal device.It will be understood by those skilled in the art that generating view The request of frequency can also include other forms, the disclosure to this with no restriction.

In one possible implementation, request the semantic content for including can be by corresponding to request itself or request Text information carries out semantic analysis to obtain.

For example, server can carry out semantic analysis according to request itself or the corresponding text information of request to obtain The semantic content that request includes.For example, server can obtain request and include by carrying out semantic analysis to request itself Semantic content, for example, server can carry out semantic analysis to the text information to obtain when request itself includes text information The semantic content etc. that request includes.In addition, server can with the corresponding text information of acquisition request, and by the text believe Breath carries out semantic analysis and obtains the semantic content that request includes.In this way, the semanteme that request includes can be obtained in several ways Content, to determine the corresponding keyword of semantic content for requesting to include.It will be understood by those skilled in the art that a variety of sides can be passed through Formula determines the semantic content that request includes, and related art method realization can be used in semantic analysis, for example, deep learning can be based on Technology and various neural networks extract the potential feature of training data, and training obtains the target that can be used for carrying out semantic analysis Model.It can use the semantic content that the object module acquisition request includes.For example, passage information input is to the target mould In type, one or more semantic contents of this section words can be exported, are realized according to request itself or the corresponding text information of request Semantic analysis is carried out, the semantic content that request includes is obtained.As long as can to the corresponding text information of request or request itself into Row semantic analysis obtain request include semantic content, the disclosure to this with no restriction.

Fig. 2 is a kind of flow chart of video generation method shown according to an exemplary embodiment.In a kind of possible reality In existing mode, as shown in Fig. 2, step S101 may include:

In step S1011, in response to the request for the generation video that terminal device is sent, the corresponding text of the request is determined Word information.

For example, server can carry out text to the request in response to the request for the generation video that terminal device is sent Word identification determines the corresponding text information of the request.For example, when the request that server receives is voice request, server It can identify text information corresponding to the voice request.For example, server can pass through automatic speech recognition technology ASR (Automatic Speech Recognition), speech recognition technology based on depth learning technology etc. carry out voice request Speech recognition determines the corresponding text information of the voice request.When the request that server receives is that picture is requested, server can To identify the corresponding text information of picture request.For example, server can carry out text to the image content that picture is requested Identification, for example, server can be by utilizing optical character identification OCR (Optical Character Recognition) skill Art carries out Text region to the image content, for example, passing through the Chinese identification technology of OCR, determines corresponding to picture request Text information.When the request that server receives is text request, server can be directly obtained the corresponding text of text request Word information.

In this way, server can in response to terminal device send generation video request, determine described in ask Corresponding text information is sought, to realize that accurate acquisition generates the semantic content that the request of video includes, and further determines that the language The corresponding keyword of adopted content, to understand the content that user wishes the video generated.It will be understood by those skilled in the art that service Device can determine the corresponding text information of request for generating video in several ways, for various forms of requests, Ke Yitong It crosses corresponding mode and determines the corresponding text information of request, above-mentioned example is not limited to, as long as can send in response to terminal device Generation video request, determine and request corresponding text information, the disclosure to this with no restriction.

In step S1012, according to the semantic content that the text information includes, the keyword is determined.

For example, server can be as it was noted above, by carrying out semantic analysis to text information corresponding with request To obtain the semantic content that request includes.Server can determine keyword according to the semantic content.For example, server can be with Word segmentation processing is carried out to text information, extracts the keyword of the text information, and the semantic content for including according to text information, Determine the corresponding keyword of semantic content that request includes.For example, server carries out at participle the corresponding text information of request Reason, extracts multiple keywords of the text information, and server can will meet in the semanteme that request includes in these keywords One or more keywords of appearance are determined as the corresponding keyword of semantic content that request includes.For example, server believes text Breath carries out word segmentation processing, extracts 10 keywords of the text information, server can be determined for compliance with language according to related algorithm Weight is greater than by the keyword of adopted content for example, the semanteme that can calculate this 10 keywords is directed to the weight of the semantic content Or the keyword equal to weight threshold, it is determined as the corresponding keyword of semantic content, for example, there are 5 passes in 10 keywords Keyword for semantic content weight be greater than or or be equal to weight threshold, then this 5 keywords can be determined as asking by server Seek the corresponding keyword of the semantic content for including.Weight can indicate that keyword, can be by relevant to the importance of semantic meaning representation Weight algorithm calculates.

In this way, server can be in the request of generation video for receiving terminal device transmission, more accurately Ground determines the corresponding keyword of semantic content that the request includes, so that obtaining user more accurately wishes the video generated Content.It will be understood by those skilled in the art that the semantic content that can include according to text information in several ways, determines crucial Word is not limited to above-mentioned example, as long as the request of the generation video sent in response to terminal device, determines the corresponding text of the request Word information, and the semantic content for including according to the text information, determine keyword, the disclosure to this with no restriction.

It will be understood by those skilled in the art that the request for the generation video that server is sent in response to terminal device, Ke Yitong It crosses various ways and determines the corresponding keyword of semantic content that request includes, be not limited to above-mentioned example, determining keyword can be with For one or more, as long as can determine the language for requesting to include in response to the request for the generation video that terminal device is sent The corresponding keyword of adopted content, the disclosure to this with no restriction.

In one possible implementation, the text information includes multiple semantic contents.

For example, the request for the generation video that server is sent in response to terminal device, determines that the request is corresponding Text information may include multiple semantic contents.For example, user inputs the word content of the tourney segment in one section of kungfu novel, This section of word content include more words (for example, before this A group disciple how with the disciple's tourney of B group, then B group Disciple how with the disciple's tourney of C group, last B group disciple how with the disciple's tourney of D group), and pass through its mobile phone Send the text request for generating video.Server determines that the text requests corresponding text information, determines in response to the request Text information includes multiple semantic contents, for example, determining that the text information includes 3 semantic contents, respectively 3 groups of tourneys Journey.It will be understood by those skilled in the art that server determines that text information corresponding with request may include a semantic content, May include multiple semantic contents, the disclosure to this with no restriction.

In one possible implementation, the semantic content for including according to the text information determines the keyword (step S1012) may include: the corresponding keyword of determining each semantic content.

For example, the request for the generation video that server is sent in response to terminal device, determines that the request is corresponding When text information includes multiple semantic contents, server can determine the corresponding keyword of each semantic content.For example, user passes through The request for the generation video that its terminal device is sent is picture request, and server passes through the Chinese identification technology of OCR, determines the figure The corresponding text information of piece request is one section of word (e.g., including multiple semantic contents), then server can determine each semanteme The corresponding keyword of content.It will be understood by those skilled in the art that server can lead to when text information includes multiple semantic contents It crosses various ways and determines the corresponding keyword of each semantic content, for example, server can determine that request corresponds to according to text information Multiple keywords, and multiple keywords are divided into the corresponding keyword of each semantic content according to corresponding semantic content, taken Business device can also determine the corresponding keyword of each semantic content respectively, for example, first determine the corresponding keyword of semantic content 1, then The corresponding keyword of semantic content 2 is determined, until determining the corresponding keyword of each semantic content, as long as can determine in each semanteme Hold corresponding keyword, the disclosure to this with no restriction.

In one possible implementation, the video clip (step S102) to match with the keyword is obtained, it can To include: the video clip for obtaining keyword corresponding with semantic content each in multiple semantic contents and matching.

For example, when server determines request comprising multiple semantic contents, server it is available in multiple semantemes The video clip that the corresponding keyword of each semantic content matches in appearance.For example, server, which determines, requests corresponding text information Including 3 semantic contents, it is followed successively by semantic content 1, semantic content 2 and semantic content 3.This available 3 semantemes of server The video clip that the corresponding keyword of each semantic content matches in content.For example, server is available right with semantic content 1 The video clip d1 that the keyword answered matches, obtain the video clip d2 that corresponding with semantic content 2 keyword matches with And obtain the video clip d3 that keyword corresponding with semantic content 3 matches.

It will be understood by those skilled in the art that server can obtain and semanteme each in multiple semantic contents in several ways The video clip that the corresponding keyword of content matches.For example, server can determine that the corresponding text information of request is included Semantic content 1, and determine the corresponding keyword of semantic content 1, obtain the view that corresponding with semantic content 1 keyword matches Frequency segment d1.Later, server goes to determine the semantic content 2 for requesting corresponding text information to be included again, and determines in semanteme Hold 2 corresponding keywords, obtain the video clip d2 that keyword corresponding with semantic content 2 matches, until getting and more The video clip that the corresponding keyword of each semantic content matches in a semantic content.Server can be as it was noted above, first It determines the multiple semantic contents for requesting corresponding text information to include, and obtains what the corresponding keyword of each semantic content matched Video clip, for example, the video clip that the corresponding keyword of each semantic content matches is obtained respectively, alternatively, obtaining simultaneously each The video clip that the corresponding keyword of semantic content matches.As long as each semantic content pair in available and multiple semantic contents The video clip that the keyword answered matches, the disclosure to this with no restriction.

It will be understood by those skilled in the art that when request is comprising a semantic content, server it is available in the semanteme Hold the video clip that corresponding keyword matches, when request is comprising multiple semantic contents, server is available with multiple languages The video clip that the corresponding keyword of each semantic content matches in adopted content.Wherein, server can obtain in several ways The video clip to match with keyword is taken, for example, server can be relevant to keyword in each video platform search label Video clip, and the determining video clip to match with keyword.Wherein, keyword and the label of video clip match, can Label is consistent with keyword to be, for example, tag hit all or part keyword or label are consistent with keywords semantics, The disclosure does not limit matched specific rules.In addition, also may include diversified forms, example with the video clip that keyword matches Such as, the video clip to match with keyword may include one or more video clips, can also include one or more groups of views Frequency segment, as long as obtaining the video clip to match with keyword, the disclosure to this with no restriction.

Now for obtaining the video clip that keyword corresponding with a semantic content matches, exemplary illustration is obtained A kind of method of the video clip to match with keyword.

In one possible implementation, video platform can be set, a large amount of view is stored in the video platform Frequently, server can carry out structuring processing to the video in video platform.

For example, server can carry out structuring processing to the video in video platform, for example, server can be right These videos carry out video lens segmentation, obtain multiple video clips of each video respectively, and determine each video clip pair respectively The label answered.Wherein, the corresponding label of each video clip can be used for indicating the much information that each video clip is included, for example, The classification information of the video clip content, the video clip scene, personage, the event etc. of generation are relevant to video clip content Peripheral informations relevant to video clip such as information, the video clip shooting location, shooting performer etc..

It should be noted that it is multiple for can be the Video segmentation when server carries out video lens segmentation to video Video clip (for example, being 5 video clips by video-clips, generates or is stored as video clip 1 to video clip 5), can also Video lens segmentation is carried out to video to be start time point by recording each video clip and end time point, is determined Multiple video clips of video.At this point, and non-real cutting video, but by record multiple groups start time point and at the end of Between point, to video carry out video lens segmentation.For example, being directed to video 1, video 1 can be recorded in server database The corresponding multiple groups start time point of multiple video clips and end time point are (for example, first group of start time point and end time Point is respectively that 00:00 and 02:00, second group of start time point and end time point are respectively 02:00 and 03:00 etc.).Server The start time point and end time point that each video clip can will be recorded in database match as acquisition with keyword The basis of video clip.

In this way, server is accurate, comprehensive by carrying out structuring processing to the video in video platform, and determining can be used for Indicate the label for the much information that each video clip is included, it is ensured that accurately obtain the piece of video to match with keyword Section.It will be understood by those skilled in the art that structuring processing, citing can be carried out to the video in video platform in several ways For, server can the picture to these videos detected frame by frame, for example, to image content carry out feature extraction, scene Identification etc. carries out video lens segmentation, obtains multiple video clips of video when image content differs greatly.Server can To determine the corresponding label of each video clip in several ways, for example, carrying out language by the audio-frequency information to each video clip Sound identification carries out the modes such as Text region, image recognition to each video clip key frame images, determines that each video clip is corresponding Label, the disclosure to this with no restriction.

In one possible implementation, server can search for video relevant to keyword in the video platform Segment, and the determining video clip to match with the keyword.

For example, server can search for video clip relevant to keyword in the video platform, for example, service Device searches multiple video clips relevant to these keywords, server can from this multiple video clip, determine with The video clip that the keyword matches.For example, the semantic content corresponds to 5 keywords, server can be by tag hit The most video clip of keyword is determined as the video clip that keyword corresponding with the semantic content matches.For example, service Device searches video clip d1, and the label of video clip d1 hits this 5 keywords (for example, video clip d1 has 10 simultaneously A label, wherein 5 labels are identical as corresponding 5 keywords are requested), then video clip d1 can be determined as and be closed by server The video clip that keyword matches.

In one possible implementation, the video clip to match with the keyword is obtained, it may include: in video In the case that the content of segment is consistent with the semanteme of keyword, determine that the video clip matches with the keyword.

For example, server can with the quantity of tag hit keyword of comprehensive video segment, the content of video clip and The semanteme of keyword, the determining video clip to match with the keyword, so that the content of video clip and keyword Semantic congruence.

For example, semantic content 1 are as follows: held martial arts circles's conference, each road martial arts circles personage attends.Server determines the language The corresponding keyword of adopted content include 5 (for example, martial arts circles personage, attend, meet, certain group and lively).Video clip d1 Label simultaneously hit this 5 keywords, however, server determines although video clip d1 hits this 5 keywords, but simultaneously The semanteme of keyword is not met.For example, the available label all to video clip d1 of server, for example, getting this 20 labels of video clip d1, server can determine the view of video clip d1 according to 20 labels of video clip d1 Frequency content, for example, the video content of video clip d1 is martial arts circles personage, so-and-so gets married, certain scholar that sends someone attends, and scene is lively non- It is all.As it can be seen that although video clip d1 hits 1 corresponding 5 keyword of semantic content, however, 5 passes of video clip d1 hit The semanteme of keyword is that martial arts circles personage gets married, certain scholar that sends someone attends, rather than in semantic content 1 this 5 keywords semanteme (each road Martial arts circles personage attends martial arts circles's conference).At this point, server can redefine the video clip to match with the keyword. For example, can be by the video clip d2 of 4 keywords of tag hit (for example, the video content of video clip d2 is to have held force Woods conference, each road martial arts circles personage attend) determine the video clip to match with the keyword.

In this way, server can accurately obtain the video clip to match with keyword.This field skill Art personnel should be understood that server can determine the video clip to match with the keyword in several ways, for example, service Device can also search for the video clip that label and keyword match in each video platform, be not limited to above-mentioned example.In addition, with institute Stating the video clip that keyword matches also may include diversified forms, match as long as server is available with keyword Video clip, the disclosure to this with no restriction.

In one possible implementation, it according to the video clip, generates target video (step S103), can wrap It includes: according to the semantic content for requesting to include, video clip being ranked up, and institute is generated according to the video clip after sequence State target video.

For example, the semantic content that server can include according to request, is ranked up video clip, and generate mesh Mark video.For example, server determines that request includes a semantic content, the corresponding keyword of the semantic content is determined, and obtain The video clip (for example, one group of video clip, including video clip a5 and video clip a6) to match with keyword.Server The semantic content that can include according to request, is ranked up video clip, for example, determining that the semantic content that request includes is corresponding 5 keywords, wherein video clip a5 is the video clip to match with the 1st to the 4th keyword, video clip a6 be with The video clip that 5th keyword matches, the then semantic content for including according to request sort to this group of video clip, sequence Are as follows: video clip a5 before this, then be video clip a6, server can generate target video according to the video clip after sequence.

In one possible implementation, server determines that request includes multiple semantic contents.Server is available The video clip that keyword corresponding with semantic content each in multiple semantic contents matches.For example, server is got and language The video clip that video clip d1 that the corresponding keyword of adopted content 1 matches, keyword corresponding with semantic content 2 match The video clip d3 that d2 and keyword corresponding with semantic content 3 match.Server can according to it is described request include Semantic content is ranked up video clip.For example, the sequence of the semantic content for the request that user is sent by terminal device Are as follows: semantic content 1, semantic content 2 and semantic content 3, then server can be according to the semantic content of the request, to piece of video Section is ranked up, for example, sequence are as follows: video clip d1, video clip d2 and video clip d3.Server can be according to sequence Multiple video clips afterwards generate target video.For example, according to video clip d1, video clip d2 and video clip d3 Sequentially, target video is generated.

In this way, the content of the video generated can be wished according to user, generate target video.Art technology Personnel, which should be understood that, to be ranked up video clip, and root in several ways according to the semantic content for requesting to include Generate the target video according to the video clip after sequence, the disclosure to this with no restriction.

In one possible implementation, it according to the video clip, generates target video (step S103), can wrap It includes: for any semantic content for requesting to include, the piece of video to be matched according to keyword corresponding with the semantic content Section, generates the corresponding target video of the semantic content.

For example, server can for it is described request include any semantic content, according to the semantic content pair The video clip that the keyword answered matches generates the corresponding target video of the semantic content.For example, request includes a semanteme When content, the video clip that server can match according to keyword corresponding with the semantic content generates the semantic content Corresponding target video.

In one possible implementation, server determines request comprising multiple semantic contents (for example, including 3 languages Adopted content), server obtains the video clip that the corresponding keyword of each semantic content in multiple semantic contents matches, for example, The video clip that the corresponding keyword of semantic content 1 matches may include video clip d1, the corresponding keyword phase of semantic content 2 The video clip matched may include video clip d2 and video clip d3, the piece of video that the corresponding keyword of semantic content 3 matches Section may include video clip d4.Server can for request include any semantic content, according to the semantic content pair The video clip that the keyword answered matches generates the corresponding target video of the semantic content.For example, server can be according to view The corresponding target video of frequency segment d1 generative semantics content 1, server can be generated according to video clip d2 and video clip d3 The corresponding target video of semantic content 2, server can according to the corresponding target video of video clip d4 generative semantics content 3, Ultimately generate this corresponding target video of 3 semantic contents.

In this way, server can for request include any semantic content, according to the semantic content pair The video clip that the keyword answered matches generates the corresponding target video of the semantic content, selects for user.Art technology Personnel should be understood that can in several ways can for request include any semantic content, according to the semantic content pair The video clip that the keyword answered matches, generates the corresponding target video of the semantic content, the disclosure to this with no restriction.

It will be understood by those skilled in the art that can be raw in several ways according to the video clip to match with keyword At target video.For example, it may be according to the video clip that the corresponding keyword of multiple semantic contents that request includes matches, Target video is generated, the video clip that can also be matched according to the corresponding keyword of any semantic content that request includes is raw At the corresponding target video of the semantic content, wherein the quantity of the target video of generation can be one or more.For example, language When the video clip that the corresponding keyword of adopted content matches includes multiple or multiple groups video clip, multiple mesh can be generated respectively Video is marked, the splicing of multiple or multiple groups video clip can also be generated into a target video.In addition, server can also obtain language Adopted content corresponds to one or more video clips that keyword matches, and the terminal device for controlling user shows video clip, The video clip that the available user of server chooses, and according to corresponding video segment, generate target video.As long as can basis Server obtain the video clip to match with keyword, generate target video, the disclosure to this with no restriction.

In one possible implementation, as shown in Fig. 2, in step S104, controlling terminal equipment shows the mesh Mark video.

For example, server can control terminal device and show the target video after generating target video.For example, Server can be after generating target video, and the terminal device for controlling user shows the target video.The target is triggered in user When the play control of video, the target video is played.

In this way, the case where user can be facilitated and watch target video, understand the target video that server generates. It will be understood by those skilled in the art that can show that the target regards by well known mode controlling terminal equipment in the related technology Frequently, the disclosure to this with no restriction.

Fig. 3 is a kind of flow chart of video generation method shown according to an exemplary embodiment.In a kind of possible reality In existing mode, as shown in figure 3, the method also includes:

In step s105, the audio content to match with the keyword is obtained.

For example, the available audio content to match with the keyword of server.For example, server determine with The corresponding keyword of the semantic content that request includes, and obtain the audio content to match with keyword.Those skilled in the art It should be understood that the audio content to match with the keyword can be obtained in several ways, for example, request includes multiple semantemes When content, server can determine the corresponding keyword of each semantic content, and obtain keyword phase corresponding with each semantic content Matched audio content etc., as long as the available audio content to match with keyword, the disclosure to this with no restriction.

In one possible implementation, as shown in figure 4, step S103 may include:

In step S1031, according to the video clip and the audio content, the target video is generated.

For example, server can generate the target video according to the video clip and the audio content. For example, it includes: video clip d1, video clip d2 and video clip that server, which obtains the video clip to match with keyword, D3, it includes: audio content 1, audio content 2 and audio content 3, clothes that server, which obtains the audio content to match with keyword, Being engaged in device can be according to the video clip to match with keyword and audio content that it is obtained, generation target video.For example, raw At target video beginning content be video clip d1 content, background music with the content synchronization of video clip d1 It can be audio content 1, the content of target video middle section is the content of video clip d2, same with the content of video clip d2 The background music of step can be audio content 2, and the back-page content of target video is the content of video clip d3, with piece of video The background music of the content synchronization of section d3 can be audio content 3.

In this way, the form that can enrich the target video of generation, improves the entertainment of target video.This field It should be understood to the one skilled in the art that the audio content to match with the keyword can be obtained in several ways, and according to the view Frequency segment and the audio content, generate the target video, the disclosure to this with no restriction.

Fig. 4 is a kind of flow chart of video generation method shown according to an exemplary embodiment.In a kind of possible reality In existing mode, as shown in figure 4, the method also includes:

In step s 106, in response to terminal device to the replacement request of the first video clip of the target video, really Fixed candidate video segment corresponding with the keyword that first video clip matches.

For example, user is after the target video that preview server generates, it may be desirable to the part of the target video Video content is replaced, and is asked at this point, it can be sent by terminal device to the replacement of the first video clip of target video It asks, wherein the first video clip can be used to generate the video clip of target video for server.For example, server is according to video Segment d1, video clip d2 and video clip d3 generate target video.User is after the preview target video, to video clip d1 Corresponding video content is dissatisfied, can initiate the replacement request for video clip d1.

In one possible implementation, server is in response to terminal device to the first piece of video of the target video The replacement request of section, can determine candidate video segment corresponding with the keyword that first video clip matches.

For example, it as it was noted above, server determines the corresponding keyword of semantic content 1, and obtains and semantic content 1 The video clip d1 that matches of keyword.For example, server searches for the corresponding keyword of semantic content 1 in video platform, this When, server may search out multiple video clips (e.g., including video clip d1, video clip d11 and video clip D111), and determine that the video clip d1 in multiple video clips is the video clip to match with the keyword of semantic content 1 (for example, video clip d1 is the video clip that tag hit keyword is most in these video clips).Server can incite somebody to action Video clip d11 and video clip d111 is determined as the keyword pair to match with first video clip (video clip d1) The candidate video segment answered.When user initiates to be directed to the replacement request of video clip d1, server can directly determine video Segment d11 and video clip d111 is candidate video segment.

In this way, candidate video segment can be quickly determined, for selection by the user.Those skilled in the art answer Understand, server can determine candidate video piece corresponding with the keyword that the first video clip matches in several ways Section, for example, the determining keyword to match with the first video clip, and candidate video piece is re-searched for according to determining keyword Section etc., is not limited to above-mentioned example.Wherein, candidate video segment may include one or more, the disclosure to this with no restriction.

In step s 107, controlling terminal equipment shows the candidate video segment.

For example, server can control subscriber terminal equipment and show candidate video after determining candidate video segment Segment.At this point, user can carry out the preview candidate video segment, choose the relevant operations such as candidate video segment.

In this way, convenient user's preview candidate video segment meets the candidate video of its needs for its selection Segment is replaced.It will be understood by those skilled in the art that server can pass through well known mode controlling terminal in the related technology Equipment shows the candidate video segment, the disclosure to this with no restriction.

In step S108, the candidate video segment chosen according to terminal device regenerates target video.

For example, the candidate video segment that the available subscriber terminal equipment of server is chosen, for example, server controls Subscriber terminal equipment illustrates 3 candidate video segments, and user thinks candidate video segment after 3 candidate video segments of preview 1 meets its demand, and candidate video segment 1 can be chosen by its terminal device.What server can be chosen according to terminal device The video clip d1 of the target video generated before the replacement of candidate video segment 1, regenerates target video.

In this way, target video can be generated according to the needs of users.It will be understood by those skilled in the art that can The candidate video segment chosen in such a way that use is well known in the related technology according to terminal device, regenerates target video, this It discloses to this with no restriction.

Fig. 5 is a kind of flow chart of video generation method shown according to an exemplary embodiment.In a kind of possible reality In existing mode, as shown in figure 5, the method also includes:

In step S109, the editing of the target video is requested in response to terminal device, determines clip information；

In step s 110, according to the clip information, target video is regenerated.

For example, user may have editing demand to the partial content of some video clip in target video, for example, with Family only wants to the preceding 10 minutes contents for retaining video clip d1 in target video, and it is desirable that 10 minutes contents are repeated 2 times, At this point, its editing that can be sent by terminal device to target video is requested.

Server can request the editing of the target video in response to terminal device, determine clip information.For example, clothes Business device can determine that user is to the clip information of target video: video clip d1 retains preceding 10 minutes contents, and repeats 2 It is secondary.Server can regenerate target video according to determining clip information.

In this way, user can be facilitated, the target video that server generates is carried out at editing according to its demand Reason generates target video according to the demand of user to realize.It will be understood by those skilled in the art that can ring in several ways The editing of the target video should be requested in terminal device, determine clip information, and according to the clip information, regenerate Target video.Wherein, clip information may include the clip information to some video clip of target video, also may include to mesh The clip information of some audio content of video is marked, the content of clip information can include but is not limited to shearing, repetition, mobile etc. Operation, the disclosure to this with no restriction.

Using example 1

Below in conjunction with " user carry out video creation " property application scenarios as an example, provide according to the embodiment of the present disclosure Application example, in order to understand the process of video generation method.It will be understood by those skilled in the art that below only using example It is to be not construed as the limitation to the embodiment of the present disclosure for the purpose for being easy to understand the embodiment of the present disclosure.

Fig. 6 is a kind of schematic diagram of the application scenarios of video generation method shown according to an exemplary embodiment.Such as Fig. 6 It is shown, it applies in example at this, during user reads a kungfu novel, when reading a tourney segment, generates Video creation inspiration.The user can send the request for generating video by its mobile phone.For example, user is with its mobile phone to swordsman The tourney segment of novel is taken pictures, and the request (for example, picture request) for generating video is sent by its mobile phone.

It is applied in example at this, server is requested in response to the picture for the generation video that user mobile phone is sent, described in determination Picture requests corresponding text information.For example, server can be by carrying out text using picture of the OCR technique to the image content Word identification, the determining text information corresponding with picture request.For example, server determines that picture requests corresponding text information Including the semantic content 1 in multiple semantic contents are as follows: held martial arts circles's conference, each road martial arts circles personage attends.

It is applied in example at this, server determines the corresponding keyword of semantic content 1.For example, server can be to text Information carries out word segmentation processing, extracts the keyword of the text information.For example, extracting 10 keywords, server is according to language Adopted content 1, determines keyword, corresponds to for example, the keyword for meeting semantic content 1 can be determined as semantic content 1 by server Keyword, such as 5 keywords in 10 keywords are the corresponding keyword of semantic content 1.

It is applied in example at this, server can obtain the piece of video to match according to the corresponding keyword of semantic content 1 Section.For example, server can be searched for and semanteme in the issued related swordsman's class film of each video platform, episodes The relevant video clip of the corresponding keyword of content 1, and obtain the video clip to match.For example, server can be by label The video clip d1 for hitting the corresponding keyword of all and semantic content 1 is determined as keyword phase corresponding with semantic content 1 The video clip matched.

It is applied in example at this, server successively determines that picture requests multiple semantic contents that corresponding text information includes In the corresponding keyword of each semantic content, and successively obtain the video clip that keyword corresponding with each semantic content matches, E.g., including video clip d1, video clip d2 and video clip d3.

It is applied in example at this, server can also obtain the audio content to match with keyword.For example, server obtains The keyword corresponding with this 3 semantic contents of audio content 1 is got to match.It is applied in example at this, server can basis Video clip d1, video clip d2, video clip d3 and the sound that the keyword corresponding with each semantic content obtained matches Frequency content 1 generates target video.For example, user send picture request in multiple semantic contents sequence be semantic content 1, Semantic content 2 and semantic content 3 can then be ranked up multiple video clips according to the sequence of multiple semantic contents, suitable Sequence are as follows: video clip d1, video clip d2 and video clip d3 are according to the sequence and audio content 1 of each video clip Background music generates target video.

It is applied in example at this, server controlling terminal equipment shows the target video.At this point, user can pass through its hand Machine preview plays the target video.

It is applied in example at this, user thinks that video clip d1 does not meet its expection, can be sent by mobile phone to mesh The replacement request for marking the first video clip (video clip d1) of video, for example, as shown in fig. 6, user's triggered mark has d1's Control initiates the replacement request for being directed to video clip d1.Server is in response to the replacement request, determination and video clip d1 phase The corresponding candidate video segment of the keyword matched.For example, server is before generating target video, the search of each video platform with The relevant video clip of the corresponding keyword of semantic content 1, for example, getting 4 relevant video clips.Wherein, server The video clip d1 of 5 keywords of tag hit is determined as the video clip that keyword corresponding with semantic content 1 matches, Other 3 video clips can also be determined as candidate video segment by server, and is issued in user by mobile phone and be directed to video When the replacement request of segment d1,3 candidate video segments directly are shown to user.It is applied in example at this, server control is used 3 candidate video segments of cell phone display at family.For example, as shown in fig. 6, show this 3 candidate video segments of r1, r2 and r3, For user's preview, select.

This using in example, after 3 candidate video segments of user's preview, it is believed that r1 meets its expection, then can lead to Crossing its mobile phone chooses r1, the r1 that server can be chosen according to mobile phone to regenerate target video.For example, according to r1, piece of video The sequence of section d2, video clip d3, background music are audio content 1, regenerate target video.

It is applied in example at this, user has editing demand to the target video of generation.For example, user thinks video clip d3 Last 5 minutes content values it is little, the contents of the section can be cut, in addition, user thinks to have among video clip d2 Tourney camera lens is simply marvelous, and user wants this tourney camera lens and is repeated 3 times.At this point, it can initiate to regard target by mobile phone The editing of frequency is requested, and server can respond editing request, and determine clip information.For example, the editing letter that server determines Breath includes: to be repeated 3 times to minute X seconds camera lenses of X for XX seconds X X minutes in 1, d2.2, it cuts within d3 last 5 minutes.Server can To regenerate target video according to the clip information.

It is applied in example at this, user is very satisfied to the target video regenerated, server can be generated Target video is issued in each video platform, the target video of generation can also be sent to its good friend.

Using example 2

Below in conjunction with " user handles text information, generates corresponding video " property application scenarios as an example, root is provided According to the application example of the embodiment of the present disclosure, in order to understand the process of video generation method.It will be understood by those skilled in the art that with It is lower using example merely for the sake of the purpose for being easy to understand the embodiment of the present disclosure, be not construed as the limitation to the embodiment of the present disclosure.

Fig. 7 is a kind of schematic diagram of the application scenarios of video generation method shown according to an exemplary embodiment.Such as Fig. 7 It is shown, it is applied in example at this, user wishes to watch video by its terminal device.For example, so-and-so novel according to the video Film, TV play of shooting etc..It is applied in example at this, the terminal device of user can show the broadcast interface of the video, use It family can be by triggering play control, to play the video.Meanwhile the terminal device of user also shows the corresponding text of the video Word information, wherein text information corresponding to video can be novel content of video capture foundation etc., be also possible to according to view The content of frequency, the corresponding verbal description etc. determined.For example, as shown in fig. 7, the film is shot according to novel Z, the end of user The content of the film and novel Z is shown in end equipment.

It is applied in example at this, user may want to regenerate its desired target video according to the video.For example, The user thinks that broadcasting full version film can expend the content of too long time or the novel and excessively draw, corresponding film Partial content can be cut completely.It is applied in example at this, user can delete the corresponding segment word information of video The respective handlings such as remove, adjust, for example, user can leave its interested part in the corresponding text information of video.For example, with Family thinks that the chapter 1 content of novel is excessively boring, and user can directly choose and delete of novel shown by terminal device One chapter.User thinks that the content of novel middle section description is excessively dilatory, repeats, what user can also think it can to delete Content is deleted.User is also possible to be unsatisfied with the sequence of certain two parts content of novel, in this adjustable two parts The sequence of appearance.In short, user the corresponding text information of video can be deleted, be adjusted etc. according to its individual demand it is corresponding Processing.

This using in example, user thinks it treated that novel content is succinct, clear, can pass through terminal device The request for generating video is sent, for example, sending according to its treated novel content, generates the request of corresponding video.It answers at this With in example, the request that server is sent in response to subscriber terminal equipment can determine that the semantic content that request includes is corresponding Keyword.For example, server can determine that user wishes the corresponding text information of video request generated.This apply example In, server can determine keyword, and obtain the view that keyword matches according to the semantic content of its text information determined Frequency segment.For example, server can obtain the video clip that keyword matches from the corresponding video of the novel.For example, electric Shadow is shot according to novel, and film includes multiple video clips, these video clips respectively correspond each text information of novel, Server can determine the piece of video to match according to corresponding text information is requested from multiple video clips of the film Section.

It is applied in example at this, server generates target video according to video clip.For example, novel includes 5 chapters, the 1st chapter Beginning 10 minutes for saving the corresponding film.After user deletes the content of the 1st chapter of novel, the request for generating video, service are sent Device should mutually request, and determine the corresponding keyword of semantic content that request includes, obtain in the film and match with keyword Video clip, and target video is generated according to video clip, for example, the target video generated is to delete former film beginning 10 The target video of minute.

It is applied in example at this, server controlling terminal equipment shows the target video.For example, in the terminal device of user It is upper to show according to the needs of users, the target video of generation.

Fig. 8 is a kind of block diagram of video-generating device shown according to an exemplary embodiment.As shown in figure 8, the view Frequency generating means include:

Keyword determining module 701, the request of the generation video for sending in response to terminal device, determines the request The corresponding keyword of the semantic content for including；

Video clip obtains module 702, for obtaining the video clip to match with the keyword；

First video generation module 703, for generating target video according to the video clip；

First control module 704 shows the target video for controlling terminal equipment.

Fig. 9 is a kind of block diagram of video-generating device shown according to an exemplary embodiment.As shown in figure 9, in one kind In possible implementation, the request includes at least one of text request, voice request and picture request,

Wherein, the keyword determining module 701 includes:

Text information determines submodule 7011, and the request of the generation video for sending in response to terminal device determines institute State the corresponding text information of request；

First keyword determines submodule 7012, the semantic content for including according to the text information, described in determination Keyword.

Wherein, first keyword determines that submodule 7012 includes:

Wherein, the video clip acquisition module 702 includes:

In one possible implementation, the first video generation module 703 includes:

In one possible implementation, the video clip acquisition module 702 includes:

As shown in figure 9, in one possible implementation, described device further include:

Audio content obtains module 705, for obtaining the audio content to match with the keyword；

Wherein, the first video generation module 703 includes:

Third video generates submodule 7031, for according to the video clip and the audio content, described in generation Target video.

Candidate video segment determining module 706, for the first piece of video in response to terminal device to the target video The replacement request of section determines candidate video segment corresponding with the keyword that first video clip matches；

Second control module 707 shows the candidate video segment for controlling terminal equipment；

Second video generation module 708, the candidate video segment for being chosen according to terminal device regenerate target view Frequently.

Clip information determining module 709, for requesting in response to terminal device the editing of the target video, determination is cut Collect information；

Third video generation module 710, for regenerating target video according to the clip information.

Figure 10 is a kind of block diagram of video-generating device shown according to an exemplary embodiment.For example, device 1900 can To be provided as a server.Referring to Fig.1 0, it further comprises one or more places that device 1900, which includes processing component 1922, Manage device and memory resource represented by a memory 1932, for store can by the instruction of the execution of processing component 1922, Such as application program.The application program stored in memory 1932 may include it is one or more each correspond to one The module of group instruction.In addition, processing component 1922 is configured as executing instruction, to execute the above method.

Device 1900 can also include that a power supply module 1926 be configured as the power management of executive device 1900, and one Wired or wireless network interface 1950 is configured as device 1900 being connected to network and input and output (I/O) interface 1958.Device 1900 can be operated based on the operating system for being stored in memory 1932, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM or similar.

In the exemplary embodiment, a kind of non-volatile computer readable storage medium storing program for executing is additionally provided, for example including calculating The memory 1932 of machine program instruction, above-mentioned computer program instructions can be executed by the processing component 1922 of device 1900 to complete The above method.

The disclosure can be system, method and/or computer program product.Computer program product may include computer Readable storage medium storing program for executing, containing for making processor realize the computer-readable program instructions of various aspects of the disclosure.

Computer readable storage medium, which can be, can keep and store the tangible of the instruction used by instruction execution equipment Equipment.Computer readable storage medium for example can be-- but it is not limited to-- storage device electric, magnetic storage apparatus, optical storage Equipment, electric magnetic storage apparatus, semiconductor memory apparatus or above-mentioned any appropriate combination.Computer readable storage medium More specific example (non exhaustive list) includes: portable computer diskette, hard disk, random access memory (RAM), read-only deposits It is reservoir (ROM), erasable programmable read only memory (EPROM or flash memory), static random access memory (SRAM), portable Compact disk read-only memory (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanical coding equipment, for example thereon It is stored with punch card or groove internal projection structure and the above-mentioned any appropriate combination of instruction.Calculating used herein above Machine readable storage medium storing program for executing is not interpreted that instantaneous signal itself, the electromagnetic wave of such as radio wave or other Free propagations lead to It crosses the electromagnetic wave (for example, the light pulse for passing through fiber optic cables) of waveguide or the propagation of other transmission mediums or is transmitted by electric wire Electric signal.

Computer-readable program instructions as described herein can be downloaded to from computer readable storage medium it is each calculate/ Processing equipment, or outer computer or outer is downloaded to by network, such as internet, local area network, wide area network and/or wireless network Portion stores equipment.Network may include copper transmission cable, optical fiber transmission, wireless transmission, router, firewall, interchanger, gateway Computer and/or Edge Server.Adapter or network interface in each calculating/processing equipment are received from network to be counted Calculation machine readable program instructions, and the computer-readable program instructions are forwarded, for the meter being stored in each calculating/processing equipment In calculation machine readable storage medium storing program for executing.

Computer program instructions for executing disclosure operation can be assembly instruction, instruction set architecture (ISA) instructs, Machine instruction, machine-dependent instructions, microcode, firmware instructions, condition setup data or with one or more programming languages The source code or object code that any combination is write, the programming language include the programming language-of object-oriented such as Smalltalk, C++ etc., and conventional procedural programming languages-such as " C " language or similar programming language.Computer Readable program instructions can be executed fully on the user computer, partly execute on the user computer, be only as one Vertical software package executes, part executes on the remote computer or completely in remote computer on the user computer for part Or it is executed on server.In situations involving remote computers, remote computer can pass through network-packet of any kind It includes local area network (LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as benefit It is connected with ISP by internet).In some embodiments, by utilizing computer-readable program instructions Status information carry out personalized customization electronic circuit, such as programmable logic circuit, field programmable gate array (FPGA) or can Programmed logic array (PLA) (PLA), the electronic circuit can execute computer-readable program instructions, to realize each side of the disclosure Face.

Referring herein to according to the flow chart of the method, apparatus (system) of the embodiment of the present disclosure and computer program product and/ Or block diagram describes various aspects of the disclosure.It should be appreciated that flowchart and or block diagram each box and flow chart and/ Or in block diagram each box combination, can be realized by computer-readable program instructions.

These computer-readable program instructions can be supplied to general purpose computer, special purpose computer or other programmable datas The processor of processing unit, so that a kind of machine is produced, so that these instructions are passing through computer or other programmable datas When the processor of processing unit executes, function specified in one or more boxes in implementation flow chart and/or block diagram is produced The device of energy/movement.These computer-readable program instructions can also be stored in a computer-readable storage medium, these refer to It enables so that computer, programmable data processing unit and/or other equipment work in a specific way, thus, it is stored with instruction Computer-readable medium then includes a manufacture comprising in one or more boxes in implementation flow chart and/or block diagram The instruction of the various aspects of defined function action.

Computer-readable program instructions can also be loaded into computer, other programmable data processing units or other In equipment, so that series of operation steps are executed in computer, other programmable data processing units or other equipment, to produce Raw computer implemented process, so that executed in computer, other programmable data processing units or other equipment Instruct function action specified in one or more boxes in implementation flow chart and/or block diagram.

The flow chart and block diagram in the drawings show system, method and the computer journeys according to multiple embodiments of the disclosure The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation One module of table, program segment or a part of instruction, the module, program segment or a part of instruction include one or more use The executable instruction of the logic function as defined in realizing.In some implementations as replacements, function marked in the box It can occur in a different order than that indicated in the drawings.For example, two continuous boxes can actually be held substantially in parallel Row, they can also be executed in the opposite order sometimes, and this depends on the function involved.It is also noted that block diagram and/or The combination of each box in flow chart and the box in block diagram and or flow chart, can the function as defined in executing or dynamic The dedicated hardware based system made is realized, or can be realized using a combination of dedicated hardware and computer instructions.

The presently disclosed embodiments is described above, above description is exemplary, and non-exclusive, and It is not limited to disclosed each embodiment.Without departing from the scope and spirit of illustrated each embodiment, for this skill Many modifications and changes are obvious for the those of ordinary skill in art field.The selection of term used herein, purport In the principle, practical application or technological improvement to the technology in market for best explaining each embodiment, or lead this technology Other those of ordinary skill in domain can understand each embodiment disclosed herein.

Claims

1. a kind of video generation method, which is characterized in that the described method includes:

In response to the request for the generation video that terminal device is sent, the corresponding key of semantic content for requesting to include is determined Word；

Obtain the video clip to match with the keyword；

According to the video clip, target video is generated；

Controlling terminal equipment shows the target video.

2. the method according to claim 1, wherein the request includes text request, voice request and figure At least one of piece request,

Wherein, the request of the generation video sent in response to terminal device determines that the semantic content for requesting to include is corresponding Keyword, comprising:

3. according to the method described in claim 2, it is characterized in that, the text information include multiple semantic contents,

Determine the corresponding keyword of each semantic content；

Wherein, the video clip to match with the keyword is obtained, comprising:

4. the method according to claim 1, which is characterized in that according to the video clip, generate mesh Mark video, comprising:

According to the semantic content for requesting to include, video clip is ranked up, and is generated according to the video clip after sequence The target video.

5. the method according to claim 1, which is characterized in that according to the video clip, generate mesh Mark video, comprising:

For any semantic content for requesting to include, the piece of video to be matched according to keyword corresponding with the semantic content Section, generates the corresponding target video of the semantic content.

6. being wrapped the method according to claim 1, wherein obtaining the video clip to match with the keyword It includes:

In the case where the content of video clip is consistent with the semanteme of keyword, the video clip and the keyword phase are determined Matching.

7. the method according to claim 1, wherein the method also includes:

Obtain the audio content to match with the keyword；

Wherein, according to the video clip, target video is generated, comprising:

8. the method according to claim 1, wherein the method also includes:

In response to terminal device to the replacement request of the first video clip of the target video, determining and first piece of video The corresponding candidate video segment of keyword that section matches；

Controlling terminal equipment shows the candidate video segment；

9. the method according to claim 1, wherein the method also includes:

According to the clip information, target video is regenerated.

10. a kind of video-generating device, which is characterized in that described device includes:

Keyword determining module, the request of the generation video for sending in response to terminal device determine that the request includes The corresponding keyword of semantic content；

First control module shows the target video for controlling terminal equipment.

11. device according to claim 10, which is characterized in that it is described request include text request, voice request and At least one of picture request,

Wherein, the keyword determining module includes:

Text information determines submodule, and the request of the generation video for sending in response to terminal device determines the request pair The text information answered；

First keyword determines submodule, and the semantic content for including according to the text information determines the keyword.

12. device according to claim 11, which is characterized in that the text information includes multiple semantic contents,

Wherein, first keyword determines that submodule includes:

Wherein, the video clip acquisition module includes:

Video clip acquisition submodule matches for obtaining keyword corresponding with semantic content each in multiple semantic contents Video clip.

13. device described in any one of 0 to 12 according to claim 1, which is characterized in that the first video generation module Include:

First video generates submodule, for being ranked up to video clip, and root according to the semantic content for requesting to include The target video is generated according to the video clip after sequence.

14. device described in any one of 0 to 12 according to claim 1, which is characterized in that the first video generation module Include:

Second video generate submodule, for for it is described request include any semantic content, according to the semantic content pair The video clip that the keyword answered matches generates the corresponding target video of the semantic content.

15. device according to claim 10, which is characterized in that the video clip obtains module and includes:

Submodule is determined, for determining the piece of video in the case where the content of video clip is consistent with the semanteme of keyword Section matches with the keyword.

16. device according to claim 10, which is characterized in that described device further include:

Wherein, the first video generation module includes:

Third video generates submodule, for generating the target video according to the video clip and the audio content.

17. device according to claim 10, which is characterized in that described device further include:

Candidate video segment determining module, for the replacement in response to terminal device to the first video clip of the target video Request determines candidate video segment corresponding with the keyword that first video clip matches；

18. device according to claim 10, which is characterized in that described device further include:

Clip information determining module determines clip information for requesting in response to terminal device the editing of the target video；

19. a kind of video-generating device characterized by comprising

Processor；

Memory for storage processor executable instruction；

Wherein, the processor is configured to: perform claim require any one of 1 to 9 described in method.

20. a kind of non-volatile computer readable storage medium storing program for executing, is stored thereon with computer program instructions, which is characterized in that institute It states and realizes method described in any one of claim 1 to 9 when computer program instructions are executed by processor.