CN109068081A

CN109068081A - Video generation method, device, electronic equipment and storage medium

Info

Publication number: CN109068081A
Application number: CN201810911033.XA
Authority: CN
Inventors: 韩旭
Original assignee: Beijing Microlive Vision Technology Co Ltd
Current assignee: Beijing Microlive Vision Technology Co Ltd
Priority date: 2018-08-10
Filing date: 2018-08-10
Publication date: 2018-12-21
Also published as: WO2020029523A1

Abstract

Present disclose provides a kind of video generation method, device, electronic equipment and storage mediums.This method comprises: obtaining video record resource, video record resource includes music and humanoid standard operation picture corresponding with each broadcast nodes of music when receiving the video record trigger action of user；Music is played, and acquires user video in playing process, in broadcasting to each broadcast nodes, shows corresponding humanoid standard operation picture；According to the matching degree of the standard operation in the user action and corresponding humanoid standard operation picture in the corresponding video frame images of broadcast nodes each in user video, the action evaluation information of each user action is determined；According to the action evaluation information of video record resource, user video and each user action, target video is generated.The scheme of the disclosure provides the selection of more video record modes for user, improves sense of participation of the user in video record, effectively improve the experience of user.

Description

Video generation method, device, electronic equipment and storage medium

Technical field

This disclosure relates to field of terminal technology, and in particular to a kind of video generation method, device, electronic equipment and storage are situated between Matter.

Background technique

With the fast development and the improvement of people's living standards of science and technology, terminal device (such as smart phone, tablet computer Deng) having become indispensable a part in people's life, user can installing terminal application program on the terminal device (APP, Application) enriches respective terminal usage experience.

With the rapidly increase of the type and quantity of APP, requirement of the user to APP is also more and more.In order to preferably full The demand of sufficient user, existing APP also start the interactive experience for increasingly focusing on user, and many social application platforms are also met the tendency of And it gives birth to.By these platforms, user oneself recorded video and can be uploaded, and can watch various types of videos, but existing Some video record modes are relatively simple, and it is impossible to meet the entertainment requirements of user, and the sense of participation of user is relatively low.

Summary of the invention

The purpose of the disclosure is intended at least solve above-mentioned one of technological deficiency.Technical side used by the disclosure Case is as follows:

In a first aspect, present disclose provides a kind of video generation methods, this method comprises:

When receiving the video record trigger action of user, video record resource is obtained, video record resource includes sound Humanoid standard operation picture happy and corresponding with each broadcast nodes of music；

Music is played, and acquires user video in playing process, in broadcasting to each broadcast nodes, is shown corresponding Humanoid standard operation picture；

According to the user action and corresponding humanoid mark in the corresponding video frame images of broadcast nodes each in user video The matching degree of standard operation in quasi- movement picture, determines the action evaluation information of each user action；

According to the action evaluation information of video record resource, user video and each user action, target video is generated.

In a kind of optional embodiment, the corresponding standard operation picture of displaying is the people that transparency is the first transparency Shape standard operation picture；

According to the action evaluation information of video record resource, user video and each user action, target video packet is generated It includes:

According to music, corresponding and transparency is the humanoid standard operation figure of the second transparency with each broadcast nodes of music The action evaluation information of piece, user video and each user action generates target video, wherein the second transparency is greater than first Transparency.

In a kind of optional embodiment, commented according to the movement of video record resource, user video and each user action Valence information, generating target video includes:

Humanoid standard operation picture in video record resource is added in the correspondence video frame images in user video；

It is raw according to the action evaluation information of user video and user action after music, the humanoid standard operation picture of addition At target video.

The action evaluation information of each user action is added in the correspondence video frame images in user video；

According to the user video after video record resource and addition action evaluation information, target video is generated.

In a kind of optional embodiment, after the action evaluation information for determining each user action, further includes:

According to the action evaluation information of each user action, the overall merit information of user video is determined；

According to the user video after video record resource and addition action evaluation information, target video is generated, comprising:

According to the user video and overall merit information after video record resource, addition action evaluation information, mesh is generated Mark video.

In a kind of optional embodiment, this method further include:

After music completion, overall merit information is shown.

In a kind of optional embodiment, video record resource further includes special-effect information corresponding with action evaluation information, Special-effect information includes animation effect and/or audio special efficacy；

After the action evaluation information for determining each user action, further includes:

By the action evaluation information of each user action, and/or, corresponding to the action evaluation information of each user action Special-effect information is shown to the displaying interface of corresponding humanoid standard operation picture.

In a kind of optional embodiment, the action evaluation information of each user action is added to pair in user video It answers in video frame images, comprising:

By the action evaluation information of each user action and spy corresponding with the action evaluation information of each user action Information is imitated, is added in the correspondence video frame images in user video；

According to the user video after video record resource and addition action evaluation information and special-effect information, target is generated Video.

In a kind of optional embodiment, before broadcasting music, further includes:

Determine user within the scope of video capture.

In a kind of optional embodiment, after generation target video, further includes:

The target video for receiving user issues operation；

It is operated according to publication, target video is distributed to video distribution platform；Alternatively,

When receiving when retaking trigger action of user, it is based on video record resource, regenerates target video.

In a kind of optional embodiment, when receiving the video record trigger action of user, video record money is obtained Source, comprising:

When receiving the video record trigger action of user, control display Music selection interface；

By Music selection interface, the selection of music operation of user is obtained；

It is operated according to the selection of music, obtains video record resource.

When receiving the video record trigger action of user by video playing interface, it is current to obtain video playing interface Video record resource corresponding to the video of broadcasting.

Second aspect, present disclose provides a kind of video-generating device, which includes:

Source obtaining module is recorded, in the video record trigger action for receiving user, obtaining video record money Source, video record resource include music and humanoid standard operation picture corresponding with each broadcast nodes of music；

Video acquisition module for playing music, and acquires user video in playing process, is playing to each broadcasting When node, corresponding humanoid standard operation picture is shown；

Evaluation information determining module, for according to the use in the corresponding video frame images of broadcast nodes each in user video The matching degree of family movement and the standard operation in corresponding humanoid standard operation picture, determines that the movement of each user action is commented Valence information；

Target video generation module, for being commented according to the movement of video record resource, user video and each user action Valence information generates target video.

In a kind of optional embodiment, video acquisition module is specifically used for when showing corresponding standard operation picture: Show that transparency is the humanoid standard operation picture of the first transparency；

Target video generation module is specifically used for:

In a kind of optional embodiment, target video generation module is specifically used for:

In a kind of optional embodiment, evaluation information determining module is also used to:

After the action evaluation information for determining each user action, according to the action evaluation information of each user action, really Determine the overall merit information of user video；

Target video generation module is generated according to the user video after video record resource and addition action evaluation information It is specifically used for when target video:

In a kind of optional embodiment, the device further include:

First display module, for completing it after determining the overall merit information of user video, and in music Afterwards, overall merit information is shown.

In a kind of optional embodiment, video record resource further includes special-effect information corresponding with action evaluation information, Special-effect information includes animation effect and/or audio special efficacy；The device further include:

Second display module, for after determining the action evaluation information of each user action, by each user action Action evaluation information, and/or, special-effect information corresponding to the action evaluation information of each user action is shown to corresponding humanoid The displaying interface of standard operation picture.

In a kind of optional embodiment, target video generation module adds by the action evaluation information of each user action It is specifically used for when in the correspondence video frame images being added in user video:

In a kind of optional embodiment, video acquisition module is also used to:

Before playing music, determine user within the scope of video capture.

In a kind of optional embodiment, the device further include:

Target video release module, for after generating target video, receiving the target video publication operation of user, root It is operated according to publication, target video is distributed to video distribution platform.

In a kind of optional embodiment, the device further include:

Module is retaken, for when retaking trigger action of user being received, being recorded based on video after generating target video Resource processed, regenerates target video.

In a kind of optional embodiment, records source obtaining module and is specifically used for:

The third aspect, present disclose provides a kind of electronic equipment, including memory and processor；

Computer program instructions are stored in memory；

Processor can to execute disclosure first aspect or any of first aspect for reading computer program instructions Select video generation method shown in embodiment.

Fourth aspect is stored with computer in the storage medium present disclose provides a kind of computer readable storage medium Program instruction, when computer program instructions are executed by processor, processor realizes that disclosure first aspect or first aspect are appointed Video generation method shown in one optional embodiment.

Technical solution provided by the present disclosure has the benefit that video generation method, the device, electricity that the disclosure provides Sub- equipment and storage medium, by during playing music, acquiring user video, and in broadcasting to broadcast nodes, to User shows humanoid standard operation picture, allows the user to make corresponding movement according to picture, by comparing user action With standard operation, the action evaluation information of user is obtained, further according to video record resource, user video and action evaluation information, Generate target video.The program, during video record, user can make according to the standard operation in the picture of displaying Movement completes the recording of the video with dance movement, can effectively promote the sense of participation and usage experience of user, mention for user The selection for having supplied video record mode more abundant, has better met the needs of user.

Detailed description of the invention

It, below will be to institute in embodiment of the present disclosure description in order to illustrate more clearly of the technical solution in the embodiment of the present disclosure Attached drawing to be used is needed to be briefly described.

Fig. 1 is a kind of flow diagram of the video generation method provided in the embodiment of the present disclosure；

Fig. 2 a is in one example of the disclosure for receiving the interface schematic diagram of video record trigger action；

Fig. 2 b is in another example of the disclosure for receiving the interface schematic diagram of video record trigger action；

Fig. 3 a is the exhibition method schematic diagram of humanoid standard operation picture in one example of the disclosure；

Fig. 3 b is the exhibition method schematic diagram of humanoid standard operation picture in another example of the disclosure；

Fig. 4 is the schematic diagram of Music selection interface in one example of the disclosure；

Fig. 5 is the displaying schematic diagram of video frame images in target video in one example of the disclosure；

Fig. 6 is a kind of flow diagram of video generation method in one example of the disclosure；

Fig. 7 is a kind of structural schematic diagram of the video-generating device provided in the embodiment of the present disclosure；

Fig. 8 is a kind of structural schematic diagram of the terminal device provided in the embodiment of the present disclosure.

Specific embodiment

Embodiment of the disclosure is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached The embodiment of figure description is exemplary, and is only used for explaining the disclosure, and is not construed as limiting the claims.

Those skilled in the art of the present technique are appreciated that unless expressly stated, singular " one " used herein, " one It is a ", " described " and "the" may also comprise plural form.It is to be further understood that being arranged used in the specification of the disclosure Diction " comprising " refer to that there are the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition Other one or more features, integer, step, operation, element, component and/or their group.It should be understood that when we claim member Part is " connected " or when " coupled " to another element, it can be directly connected or coupled to other elements, or there may also be Intermediary element.In addition, " connection " used herein or " coupling " may include being wirelessly connected or wirelessly coupling.It is used herein to arrange Diction "and/or" includes one or more associated wholes for listing item or any cell and all combinations.

How the technical solution of the disclosure and the technical solution of the disclosure are solved with specific embodiment below above-mentioned Technical problem is described in detail.These specific embodiments can be combined with each other below, for the same or similar concept Or process may repeat no more in certain embodiments.Below in conjunction with attached drawing, embodiment of the disclosure is described.

Fig. 1 shows a kind of flow diagram of the video generation method provided in one embodiment of the disclosure, such as Fig. 1 institute Show, this method can specifically be executed by terminal device, and this method mainly may include:

Step S110: when receiving the video record trigger action of user, video record resource, video record money are obtained Source includes music and humanoid standard operation picture corresponding with each broadcast nodes of music；

It should be noted that the concrete form of the video record trigger action of user is unrestricted, can according to need It is configured in corresponding application program, can specifically include but be not limited to the triggering of the designated position in the user interface of application program Movement, video record phonetic order of user etc..

For example, in one possible implementation, can be arranged in the user interface of application program in terminal device Video record key, such as it is shown in entitled " dancing video capture " or " personalized video shooting " void answered in user interface Quasi- key, in example as shown in Figure 2 a, when user is triggered to " dancing video capture " corresponding key area, then terminal Equipment has received the video record trigger action of user.

In alternatively possible implementation, it can be pressed so that search is arranged in the user interface of application program in terminal device Key or voice key etc., user can carry out interactive voice by searching for or triggering voice key and equipment.As shown in Figure 2 b In example, user can pass through the search in Application Program InterfaceRegion passes through input " dancing video record " or " individual character After the keywords such as video record " (keyword, which can according to need, to be configured), pass through clickButton carries out video record Trigger action processed, can also be by clicking talk buttonVideo record instruction is said, such as " records personalized video " or " record Dancing video processed " etc., at this point, the phonetic order of user is the video record trigger action of user.

After receiving the video record trigger action of user, video record needed for obtaining recorded video provides terminal device Source, each broadcast nodes of music humanoid standard operation picture corresponding with each broadcast nodes can be pre-configuration, each broadcasting Node corresponds to a movement picture.In practical applications, people can be configured according to the musical note of per song or other musical features The corresponding relationship of shape standard operation picture and broadcast nodes.

Wherein, humanoid standard operation picture refer to include virtual portrait form picture, virtual portrait form has pre- The standard operation of configuration, the standard operation are the movement that user needs to complete.

Step S120: playing music, and acquire user video in playing process, in broadcasting to each broadcast nodes, Show corresponding humanoid standard operation picture；

When starting to play music, by starting the camera of terminal device, shooting interface is opened, and start to shoot, adopted Collect user video.Whenever broadcasting a to broadcast nodes, the corresponding humanoid standard operation picture presentation of the broadcast nodes is existed Interface is shot, allows the user to make dance movement according to the standard operation in picture, gets the view with dance movement The image of frequency frame.As shown in fig. 3a, after starting to play music, camera is opened in control, is started to shoot user images, be carried out Humanoid standard operation picture P is shown to shooting interface, user needs in broadcasting to music node by the recording of user video Corresponding dance movement is completed according to the movement in picture.

In practical applications, user can also control the pause of music as needed, and music can configure user when suspending Video record also suspends or continues to record.

Wherein, show that the concrete mode of humanoid standard operation picture can configure according to actual needs.For example, optional It, can be by the fixed position being pre-configured, or control picture of being displayed in the user interface of picture according to default in embodiment Motion track moved in shooting interface, such as control picture P and from the bottom of terminal device be moved to shooting according to desired guiding trajectory It disappears again behind the designated position at interface.

In practical applications, it since user is from humanoid standard operation picture is seen to corresponding movement is made, needs certain Reaction time therefore can be in the actual play time according to broadcast nodes, the time is set in advance, and to play the node corresponding Humanoid standard operation picture.The setting time can configure according to actual needs, for example, can be set to 0.5 second, then each It plays corresponding movement picture within 0.5 second before broadcast nodes, may be set to be human brain average reaction time, alternatively, can be with Picture is being seen to the time made a response, according to the average reaction time of statistics setting etc. by statistics different user.It can be with Understand, the displaying duration of humanoid standard operation picture also can according to need configuration.

In practical applications, according to factors such as the exhibition method of the humanoid standard operation picture configured, displaying times Difference, the humanoid standard operation picture of difference corresponding to different broadcast nodes can may also be shown simultaneously at same interface.Such as figure In example shown in 3b, humanoid normal pictures can be moved at the top of interface from interface bottom along default estimation to disappear again, Before picture above interface does not disappear also, the corresponding humanoid standard operation picture of next broadcast nodes has also been shown, It is provided by this way for user and sufficient does the time acted.

In addition, in practical applications, when configuring humanoid standard operation picture, can also be matched according to the difference of male/female user It sets two sets or more set people goes back to standard operation picture group in user's registration application program account or progress application program setting It can be provided for user by acquisition user gender or other relevant informations and show the picture for being more in line with user demand, or Person provides picture type option in video record, for user.For example, can provide for female user humanoid in picture is skirt The schemes such as the humanoid standard operation pictures of types such as dress.

Step S130: according to the user action and correspondence in the corresponding video frame images of broadcast nodes each in user video Humanoid standard operation picture in standard operation matching degree, determine the action evaluation information of each user action；

Wherein, matching degree can be the similarity of user action and standard operation.The concrete form of action evaluation information It can according to need configuration, for example, it may be movement score is also possible to evaluation knot such as the specific score value in 0-100 points Fruit, as it is poor, it is good, fine, one in very good etc. results.It, can degree of being similarly configured in an optional embodiment When between 95%-100%, action evaluation information is perfect (perfect), and when similarity is between 90%-95%, movement is commented Valence information is fine (very good), and between 80%-90%, preferably (good), similarity is in 70%- for action evaluation information When 80%, action evaluation information be can (OK), similarity be lower than 70% when, action evaluation information be miss (miss).

In practical applications, according to the difference of the retention time of user action, each broadcasting section in the user video of acquisition The figure of the corresponding video frame of point may be a frame image, it is also possible to multiple image.It is right according to its institute for each broadcast nodes The matching degree for the user action and corresponding standard operation in video frame images answered, determines that the movement of user action is commented It when valence information, can be based on the user action in the corresponding any frame image of broadcast nodes, be also possible to based on broadcast nodes Corresponding each frame image obtains each frame figure according to the matching degree of user action and standard operation in each frame image As corresponding action evaluation information, then it is based on the corresponding action evaluation information of each frame image, determines that the broadcast nodes are corresponding User action action evaluation information.It is somebody's turn to do for example, the corresponding user action evaluation information of each frame image can be integrated The action evaluation information of the corresponding user action of broadcast nodes, can also will be corresponding to the corresponding all frame images of the broadcast nodes Action evaluation information in best action evaluation information, the action evaluation as the corresponding user action of the broadcast nodes believes Breath.

Wherein, the identification of user action, and determine the concrete mode of the matching degree of user action and standard operation, Can using the prior art realize, for example, can depth information or human body based on image artis information identify image In user action, can based in user action key point information in standard operation key point information determination match journey Degree obtains the matching degree of user action and standard operation by obtaining neuroid based on training, herein no longer in detail Description.

Step S140: according to the action evaluation information of video record resource, user video and each user action, mesh is generated Mark video.

The video generation method of the embodiment of the present disclosure, acquires user video during playing music, and to user's exhibition Shape of leting others have a look at standard operation picture allows the user to make corresponding movement according to picture, and by comparing user action and mark Quasi- movement, obtains the action evaluation information of user, so as to be believed according to video record resource, user video and action evaluation Breath generates target video.With this solution, the recording for realizing the video with user's dance movement, provides more for user Add the selection of video record mode abundant, can effectively promote the sense of participation and usage experience of user, better meet use The needs at family.In addition, allowing users to recognize based on the evaluation information certainly by the action evaluation information for generating each user Whether oneself movement complies with standard, and further promotes the use perception of user.

In the alternative embodiment of the disclosure, when receiving the video record trigger action of user, video record money is obtained Source may include:

It in practical applications, can when the user interface in application program receives the video record trigger action of user To provide the selection of music for user by display Music selection interface, user can carry out the selection of music operation by the interface, The operation is used to indicate the music of user's selection, so that application program can operate to obtain corresponding view according to the user's choice Frequency records resource.With this solution, it allows users to select music according to the hobby of oneself, further improving user makes With perception.

Wherein, Music selection interface is the user interface that music is selected for user, and the concrete form at the interface can basis It needs to configure.For example, in alternative embodiments, the title of all optional music can be shown in the form of a list, use Family the selection of music operation is completed come the title of the music in selective listing by click or other means；It can also be in interface It first shows music type, is shown to user after user's one music type of selection, then by the title of all music under the type, It is selected for user.In another optional embodiment, music searching choosing can also be provided for user in Music selection interface , corresponding music searching result is showed by use according to the search instruction (search key or phonetic search instruction etc.) of user Family is selected for user.

In an example as shown in Figure 4, in the video record trigger action for receiving user, it can be arranged by music Musical designation (music 1, music 2 etc. as illustrated in the drawing) is shown to Music selection interface by the form of table, and user can basis Hobby selects music from list, preferably to promote user experience.

In the embodiment of the present disclosure, the content (such as song title list) that is particularly shown in Music selection interface can be end End equipment obtains from server end and has stored in local content, is also possible in the video record triggering for receiving user After operation, the content that is got to server end.It obtains and stores from server-side likewise, video record resource can be In local resource, or after receiving the selection of music operation, to the video record resource of server end acquisition.

In practical applications, it in order to improve the response efficiency to user's operation, record user also can under off-line state Video processed promotes the experience of user, in Music selection interface be particularly shown content and video record resource is chosen as It obtains and is stored to local resource from server end.

In practical applications, if user is playing some video either when entering the broadcast interface of a certain video, Video record trigger action has been carried out, then has shown that user is likely to want to carry out video record with the corresponding music of current video, Therefore, it can be directly based upon the recording that the corresponding video record resource of the current video carries out video, the side of allowing users at this time Face is fast arrived and enters video record.

It is understood that when video record trigger action is the operation received by video playing interface, it can also Video record resource is determined in a manner of using above-mentioned display Music selection interface.

In the alternative embodiment of the disclosure, before playing music, can also include:

Determine user within the scope of video capture.

In order to guarantee the effect of target video, before starting to play music, user can be determined first whether in video In coverage, when determining that user is in coverage, then start to shoot, so that user appears in video frame images.? When user is not in coverage, user can be prompted by way of voice prompting or text prompt, so that user It enters in coverage.

It should be noted that in practical applications, can be after determining video record resource, broadcasting for music is automatically begun to It puts, be also possible to determine video record resource and receiving when starting the trigger action recorded of user, then start music It plays.No matter which kind of mode before really starting broadcasting, can be determined user within the scope of video capture using Judgement, to guarantee the video effect of target video, promotes the satisfaction of user.

In the alternative embodiment of the disclosure, it is the first transparency that the corresponding standard operation picture of displaying, which can be transparency, Humanoid standard operation picture；

According to the action evaluation information of video record resource, user video and each user action, generating target video can To include:

According in video record resource music, with each broadcast nodes of music corresponding and transparency be the second transparency Humanoid standard operation picture, user video and each user action action evaluation information, generate target video.

In practical applications, the first transparency is chosen as zero, i.e., completely opaque, the second transparency is set greater than zero Value such as can be set to 50%.

Humanoid standard operation picture is the picture for instructing user to complete dance movement, and transparency is lower, such as completely not Transparent, user more can clearly see standard operation clearly, to play better directive function.And in the target video generated, such as The transparency of the humanoid standard operation picture of fruit is too low, then is likely to block user, influences the effect of target video, user's Satisfaction can decline, therefore, by by the transparency of standard operation picture humanoid in target video by instruct user complete dancing The first transparency when movement is adjusted to the second transparency, can effectively reduce movement picture to the shadow of user action in target video It rings, improves user satisfaction, better met practical application request.

In an alternative embodiment, the second transparency is optional is set smaller than 100%, to allow users to be regarded according to target Humanoid standard operation picture in frequency and the movement oneself completed, it is thus understood that the movement of oneself whether standard, further promoted and used The usage experience at family.

In an example as shown in Figure 5, the video frame images of the frame in target video are shown in figure, in the image Illustrate user action H, humanoid standard operation picture P and special-effect information (hereinafter specifically describing) etc..Shown in Fig. 5 The humanoid standard operation picture P shown during video record in movement picture P and Fig. 3 a of humanoid standard out is same One picture, the transparency of picture is the first transparency in Fig. 3 a, and the transparency of picture is the second transparency in Fig. 5, by two width figures In as can be seen that the second transparency is lower than the first transparency, the transparency in Fig. 3 a is lower, can be during video record User shows the instruction movement being more clear, and the transparency in Fig. 5 is higher, can effectively avoid humanoid standard operation picture pair User images are blocked.It should be understood that being an example in Fig. 5, effect in practical applications can be more obvious, improves The usage experience of user.

It should be noted that when the humanoid standard operation picture shown during music and generation catalogue video The humanoid standard operation picture being based on, corresponding is all the humanoid standard operation picture in video record resource, different It is, in order to better meet actual needs, to promote user experience when obtaining target video in exhibiting pictures and based on picture, it can It is adjusted with the transparency to picture.

It is understood that in practical applications, if humanoid standard operation picture is saturating in the video record resource of configuration Lightness is the first transparency, then, only need to be when generating target video by view without being adjusted to transparency when showing The transparency that frequency records the humanoid standard operation picture of resource is adjusted；If humanoid mark in the video record resource of configuration The transparency of quasi- movement picture is the second transparency, then after getting resource, needing before showing the picture of acquisition will be humanoid The transparency of standard operation picture is adjusted to the first transparency, and the tune for carrying out transparency is then no longer needed to when generating target video It is whole；If the transparency of humanoid standard operation picture is neither the first transparency, nor the in the video record resource of configuration Two transparencies need before showing the picture of acquisition by the transparency tune of humanoid standard operation picture then after getting resource Whole is the first transparency, is also required to first be adjusted the humanoid standard operation picture in resource when generating target video.

In an optional embodiment of the disclosure, according to video record resource, user video and each user action Action evaluation information, generating target video includes:

By this way, the humanoid standard operation picture in video record resource the collected user of institute is added to complete In video frame images when same movement, so that allowing users to can be in same video frame images when playing target video The movement for seeing standard operation and oneself simultaneously understands the performance of oneself movement, promotes user experience.As shown in Figure 5 Example in, after obtaining target video, user can play the target video, in target video broadcast interface, work as music When broadcasting to broadcast nodes, user can see corresponding view in standard operation and user video in standard operation picture P simultaneously The movement H that oneself is completed in frequency frame image.

In the alternative embodiment of the disclosure, commented according to the movement of video record resource, user video and each user action Valence information, generating target video includes:

With this solution, make to carry phase in the corresponding video frame images of each broadcast nodes in the target video generated The action evaluation information answered, so that the effect for recognizing the dance movement of oneself by playing target video is allowed users to, Solve preferable, which movement needs improvement etc. is completed in which movement.

By being described above it is found that the corresponding video frame images of each broadcast nodes may be the image of multiframe, will be each When the action evaluation information of user action is added in corresponding video frame images, evaluation information can be added to corresponding It in one video frame images, can also be added in each frame image, be based on the frame in multiple image in action evaluation information Image obtain when, action evaluation information can also be added in the frame image.

In the alternative embodiment of the disclosure, video record resource can also include special efficacy letter corresponding with action evaluation information Breath, special-effect information includes animation effect and/or audio special efficacy；After the action evaluation information of the above-mentioned each user action of determination, also May include:

It, can be by the action evaluation information of current user action after determining the action evaluation information of each user action It is shown on the displaying interface of corresponding humanoid movement picture, can also be shown according to action evaluation information to user corresponding Special-effect information, so that user can recognize auto- completion effect according to action evaluation information and/or special-effect information, this Outside, by this way, the sense of participation that can effectively increase user's recorded video keeps recording process more interesting, improves user Use perception.

Wherein, the concrete form of special efficacy can according to need configuration, for example, it may be fresh flower special efficacy, animation effect, sound Special efficacy etc., different action evaluation information correspond to different special-effect informations.As shown in fig. 3a, dynamic based on humanoid standard The matching degree for making the user action that standard operation and user in picture P are made according to the picture determines that active user is dynamic After the action evaluation information (such as good) of work, animation effect shown in action evaluation information " good " and Fig. 3 a can be shown To the displaying interface of picture P, user can preferably know the performance of oneself movement by interface, further, it is also possible to together When play sound effect special efficacy " good ".

In the alternative embodiment of the disclosure, the action evaluation information of each user action is added to pair in user video It answers in video frame images, may include:

Correspondingly, target video is generated according to the user video after video record resource and addition action evaluation information, it can To include:

Using the program, family can be used can also be seen that action evaluation information and special efficacy letter in the target video of generation Breath, can effectively promote the satisfaction of user, enrich the content of target video.

In the alternative embodiment of the disclosure, after the action evaluation information for determining each user action, can also include:

According to the action evaluation information of all user actions, the overall merit information of user video is determined；

Correspondingly, after determining the overall merit information of user video, can also be wrapped in the alternative embodiment of the disclosure It includes:

After music completion, overall merit information is shown.

After the completion of music, by showing the overall merit information of user video, allows users to recognize and regarding In frequency recording process, performance of the user to all standard operations.

By the way that overall merit information to be added in target video, allow users to be obtained simultaneously comprising each of which movement The target video of evaluation information and overall merit information, user can could be aware that itself is right by playing the target video The performance of each movement and comprehensive performance.

Wherein, the form of overall merit information also can according to need configuration, can also be with for example, it may be comprehensive score It is comprehensive evaluation result.In an optional embodiment, the action evaluation information of each user action can be to act Point, overall merit information can be the movement score based on each user action, is calculated using average weighted mode.

It in practical applications, equally can be overall merit information configuration special-effect information, different overall merit information pair Different special-effect informations is answered, when determining overall merit information, shows corresponding special-effect information for user.It is understood that It is that the corresponding special-effect information of overall merit information can use the identical configuration side of special-effect information corresponding with each user action Formula can also use different configuration modes.

In the alternative embodiment of the disclosure, after generating target video, can also include:

The target video for receiving user issues operation；

It is operated according to publication, target video is distributed to video distribution platform.

Wherein, video distribution platform can be platform corresponding to application program itself, for example, for trill application journey Sequence, video distribution platform can be trill video distribution platform, be also possible to third party's distribution platform, can also be other application Program, for example, user, which can share target video, is shared with other people by other application program.

It is understood that user can only need to carry out publication touching if it is platform corresponding to application program itself Hair operation, such as click target video and issue key, if it is other distribution platforms or application program, then user is issuing It can be user's display platform option and/or application option after trigger action, user selects to want the specific of publication from option Platform or application program.

In the alternative embodiment of the disclosure, after generation target video, further includes:

After the generation for completing target video, it can be provided in user interface for user and retake option, such as retake key, used Family can be based on same video record resource by retaking option, and video record, regenerates video again.

In an optional embodiment, it can be shown on overall merit information display interface and retake option, make user It can be determined whether to be recorded again according to overall merit information.

It can also be that user provides target video broadcasting choosing simultaneously in user interface in another alternative embodiment mode , user can trigger the option plays target video, determine whether to be recorded again by playing target video, broadcast It discharges into the page and is provided for user and retake option, if necessary to record again, user retakes type selecting in page triggering.

It is understood that above-mentioned two kinds of cited embodiments are intended only as the explanation of example progress, do not constitute Restriction to the mode for retaking trigger action for receiving user.

It should be noted that user interface involved in embodiment of the disclosure, what is referred to is the display in application program Interface can receive the operation of user by user interface.For user interface corresponding to different operations, in practical application In, it can according to need and be configured to identical user interface, also can be configured to different user interfaces.

The video generation method provided in the embodiment of the present disclosure is carried out furtherly below with reference to a specific example It is bright.By the scheme of the embodiment of the present disclosure it is found that being with user using the scheme target video generated of the embodiment of the present disclosure Target video in this example, for the more vivid description video, is known as dancing video, generates mesh by the video of movement Required video record resource is known as dancing video record resource when marking video.The action evaluation letter of user action in this example Breath is movement score, and movement score range can be 0-100, and the matching degree of user action and standard operation is higher, acts Divide higher.

The flow diagram of the video generation method in this example is shown in Fig. 6, can be mainly divided into dance in the example It steps video record resources making, the resource acquisition of dancing video record and dancing video and generates three major parts.

Dancing video record resources making: the part is the preparation stage that the embodiment of the present disclosure is realized, for producing and generating Video record resource needed for dancing video.As shown in Figure 6, in practical applications, dancing video record resource can basis Practical application request is configured, and dancing video record resource may include that (user can choose background music when recorded video Music), special efficacy music (i.e. music special efficacy), animation effect, resource picture (i.e. humanoid standard operation picture) etc., for every first back Scape music configures corresponding resource picture, and configures the corresponding relationship of good each resource picture and broadcast nodes, i.e., broadcasts in music It is put into and which resource picture when is shown, it is also necessary to configure the corresponding relationship of different special-effect information and movement score, i.e., Movement score is how many or in which range, it should play what special-effect information.Complete the system of dancing video record resource After work, dancing video record resource is uploaded onto the server.

Dancing video record resource acquisition: different users can be by the application journey installed on respective terminal device Sequence, that is, user end to server sends dancing video record resource acquisition request, after server receives request, by dancing video It records resource and is issued to each client.

The generation of dancing video: client is in the dancing video record trigger action for receiving user, as user is answering When clicking " dancing video record " key with the user interface of program, client can be recorded the dancing video downloaded from server Resource processed shows user in the form of song title, that is, musical designation, and user can choose certain song and enter recording mould Formula, i.e. unlatching camera, into the video record page.

Before starting to play the music that user chooses, it can identify whether have subscriber station in camera lens first, that is, judge Whether whether user, specifically can be by constantly shooting image, by having user to determine in identification image in coverage Whether user is in coverage, if it was not then can prompt user mobile to enter coverage, if user is shooting In range, then it can start to play music, start simultaneously at recording user video.

In the playing process of music, in each broadcasting to broadcast nodes, show that the node is corresponding humanoid to user Standard operation picture, and according to the matching degree for acting the movement done with user in corresponding video frame images of displaying, it obtains The movement score of user action.In this example, standard operation picture is shown in such a way that transparency is zero and according to movement score It shows corresponding special-effect information, such as shows score animation, play score audio, when music finishes, terminate user video Recording.Terminate after recording, the i.e. comprehensive letter of total score of user video based on the movement score of each user action, can be obtained Breath, for example, total score can be calculated by the mode of average weighted mode or other pre-configurations.Finally selected according to user Dancing video record resource, the user video of recording, the movement score of each user action, corresponding special-effect information and The dancing video of total score generation user, wherein when generating dancing video, the transparency of humanoid standard operation picture can be adjusted Whole is 50%, and total score can be located in the first frame image of dancing video, can also be located in last frame image, can also be new Increase a frame image, total score is added in the newly-increased image.

After the generation for completing dancing video, user can play the video, due to humanoid mark in the dancing video of generation Quasi- movement picture be it is translucent, therefore the dance movement of user oneself will not be sheltered from, and user can see simultaneously it is corresponding Standard operation, therefore itself movement and standard operation can be compared, and combine movement score and special-effect information, recognize at any time The performance of oneself dance movement.User, which is also based on total score and learns, is performed integrally situation.

In addition, after the generation of dancing video or after finishing playing, user be also based on video relevant information (such as The movement score of each user action, total score etc.) recorded video again is chosen whether, or as needed send out dancing video Cloth is to relevant video distribution platform etc..The dancing video that record has different user to issue in video distribution platform, user Ke Tong The dancing video of video distribution platform viewing different user publication is crossed, can also initiate to challenge to the author of the dancing video, I.e. based on music recorded video used by author, the interaction between different user can further improve, transferred user's participation The enthusiasm of video record.

Based on principle identical with method shown in Fig. 1, a kind of video generation dress is additionally provided in the embodiment of the present disclosure It sets, as shown in fig. 7, the video-generating device 400 may include recording source obtaining module 410, video acquisition module 420, commenting Valence information determination module 430 and target video generation module 440.Wherein:

Source obtaining module 410 is recorded, for obtaining video record in the video record trigger action for receiving user Resource, video record resource include music and humanoid standard operation picture corresponding with each broadcast nodes of music；

Video acquisition module 420 for playing music, and acquires user video in playing process, is playing to each When broadcast nodes, corresponding humanoid standard operation picture is shown；

Evaluation information determining module 430, for according in the corresponding video frame images of broadcast nodes each in user video User action and the standard operation in corresponding humanoid standard operation picture matching degree, determine the dynamic of each user action Judge information；

Target video generation module 440, for the movement according to video record resource, user video and each user action Evaluation information generates target video.

The video-generating device of the embodiment of the present disclosure, acquires user video during playing music, and to user's exhibition Shape of leting others have a look at standard operation picture allows the user to make corresponding movement according to picture, and by comparing user action and mark Quasi- movement, obtains the action evaluation information of user, so as to be believed according to video record resource, user video and action evaluation Breath generates target video.With this solution, the recording for realizing the video with user's dance movement, provides more for user Add the selection of video record mode abundant, can effectively promote the sense of participation and usage experience of user, better meet use The needs at family.In addition, allowing users to recognize based on the evaluation information certainly by the action evaluation information for generating each user Whether oneself movement complies with standard, and further promotes the use perception of user.

It is understood that above-mentioned each module of the video-generating device in the embodiment of the present disclosure, which has, realizes above-mentioned Fig. 1 Shown in video generation method corresponding steps function, which can also be held by hardware realization by hardware The corresponding software realization of row, the hardware or software include one or more modules corresponding with above-mentioned function.Above-mentioned each module It can be implemented separately, it can also be with multiple module integration realizations.Specifically may be used for the function description of each module of video-generating device Referring to hereinbefore to the corresponding description in video generation method shown in FIG. 1, details are not described herein.

In the alternative embodiment of the disclosure, video acquisition module 420 is specifically used when showing corresponding standard operation picture In:

Show that transparency is the humanoid standard operation picture of the first transparency；

Target video generation module 440 is specifically used for:

In an alternative embodiment of the disclosure, target video generation module 440 can be specifically used for:

In the alternative embodiment of the disclosure, target video generation module 440 is according to video record resource, user video It can be specifically used for when generating target video with the action evaluation information of each user action:

In embodiment of the disclosure, evaluation information determining module 430 be can be also used for:

After determining the action evaluation information of each user action, according to the action evaluation information of each user action, Determine the overall merit information of user video；

Target video generation module 440 according to video record resource and addition action evaluation information after user video, When generating target video, it can be specifically used for:

In embodiment of the disclosure, video-generating device 400 can also include:

First display module, for showing overall merit information after music is completed.

In embodiment of the disclosure, video record resource further includes special-effect information corresponding with action evaluation information, special efficacy Information includes animation effect and/or audio special efficacy；Video-generating device 400 can also include:

Second display module, for after determining the action evaluation information of each user action, by each user action Action evaluation information, and/or, special-effect information corresponding to the action evaluation information of each user action is shown to corresponding people The displaying interface of shape standard operation picture.

It is understood that the first display module and the second display module can be same module, it is also possible to different Module.

In embodiment of the disclosure, target video generation module 440 adds by the action evaluation information of each user action When being added in the correspondence video frame images in user video, it can be specifically used for:

Correspondingly, target video generation module 440 is according to the use after video record resource and addition action evaluation information Family video can be specifically used for when generating target video:

In embodiment of the disclosure, video acquisition module 420 be can be also used for:

Before playing music, determine user within the scope of video capture.

In embodiment of the disclosure, video-generating device 400 can also include:

Module is retaken, for video record resource being based on, being adopted by video when receiving when retaking trigger action of user Collection module 420, evaluation information determining module 430 and target video generation module 440 regenerate target video.

In embodiment of the disclosure, recording source obtaining module 410 can be specifically used for:

It is understood that movement performed by each module in video-generating device in each embodiment of the disclosure be with The step in video generation method in each embodiment of the disclosure is corresponding, for video-generating device each module it is detailed Function description specifically may refer to hereinbefore shown in description in corresponding video generation method, details are not described herein.

Based on principle identical with the video generation method of the embodiment of the present disclosure, one kind is additionally provided in the embodiment of the present disclosure Electronic equipment, the electronic equipment include memory and processor, computer program instructions are stored in memory, processor is used for Computer program instructions are read, to execute video generation method shown in above-mentioned disclosure any embodiment.

Based on principle identical with the video generation method of the embodiment of the present disclosure, one kind is additionally provided in the embodiment of the present disclosure Computer readable storage medium is stored with computer program instructions in the storage medium, when computer program instructions are by processor When execution, processor realizes video generation method shown in disclosure any embodiment.

The embodiment of the present disclosure additionally provides a kind of terminal device, as shown in Figure 8.The terminal device 2000 may include but not Be limited to: processor 2001, memory 2002, the different components for connecting equipment are total with the communication for realizing different inter-component communications Line 2003.Computer program and data are can store in memory 2002, processor 2001 can be by calling memory Computer program in 2002 is acted accordingly and is handled to execute, and realizes the video generation method in the embodiment of the present disclosure.Figure Shown in the structure of terminal device 2000 do not constitute the restriction to the embodiment of the present disclosure.

Terminal device 2000 can also include display 2004.Processor 2001 execution act or handle during, Letter can be interacted by the user interface that needs or can show, prompt information or with terminal user by display 2004 Breath is shown to user.

Processor 2001 can be CPU, general processor, DSP, ASIC, FPGA or other programmable logic device, crystalline substance Body pipe logical device, hardware component or any combination thereof.It, which may be implemented or executes, combines described by disclosure disclosure Various illustrative logic blocks, module and circuit.Processor 2001 is also possible to realize the combination of computing function, such as wraps It is combined containing one or more microprocessors, DSP and the combination of microprocessor etc..

Communication bus 2003 may include an access, and information is transmitted between said modules.Bus 2003 can be pci bus Or eisa bus etc..Bus 2003 can be divided into address bus, data/address bus, control bus etc..For convenient for indicating, in Fig. 8 only It is indicated with a thick line, it is not intended that an only bus or a type of bus.

Memory 2003 can be ROM or can store the other kinds of static storage device of static information and instruction, RAM Or the other kinds of dynamic memory of information and instruction can be stored, it is also possible to EEPROM, CD-ROM or other CDs Storage, optical disc storage (including compression optical disc, laser disc, optical disc, Digital Versatile Disc, Blu-ray Disc etc.), magnetic disk storage medium Or other magnetic storage apparatus or can be used in carry or store have instruction or data structure form desired program generation Code and can by any other medium of computer access, but not limited to this.

Terminal device 2000 can also include input output assembly 2005, realize information by input output assembly 2005 Input/output and user and equipment interaction.

In practical applications, input output assembly 2005 can configure according to actual needs, may include being not limited to key Disk, mouse, touch screen, audio component, video component etc., for example, terminal device can receive the triggering of user by touch screen Instruction, processor can execute corresponding movement or processing based on the triggering command of user.Audio component/video component can be by It is configured for audio signal/vision signal input and/or output of equipment.Audio component can include but is not limited to loudspeaking Device, microphone etc., video component can include but is not limited to camera, video interface (HDMI, VGA and/or DVI interface) etc.

It is understood that above-mentioned each input output assembly 2005 can realize the processing of information, example alone or in combination Such as, when instructing by the music that touch screen receives user, the broadcasting of music is carried out by audio component.

Terminal device 2000 can also include communication component 2006, and communication component 2006 is configurable for realizing that terminal is set Communication interaction between standby 2000 and other equipment (such as terminal device, storage equipment).Wherein, communication component 2006 can wrap Include but be not limited to wire communication component (such as the mobile network communications such as 3G, 4G, 5G unit), wireless communication components (such as bluetooth, WIFI communication unit), usb communication component, audio component, video component etc..

Terminal device 2000 can also include power management module 2007, and power management module 2007 can be configured for The power supply of equipment, the transformation of equipment electric energy and management of charging and discharging of power supply etc., which can be configured with charging interface.

It should be noted that the terminal device of the embodiment of the present disclosure can be implemented as including but not limited to intelligent hand Machine, smart television, personal digital assistant (Personal Digital Assistant, PDA), tablet computer, desktop computer, just Take terminal device (such as portable computer), mobile unit etc..

It should be understood that although each step in the flow chart of attached drawing is successively shown according to the instruction of arrow, These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps Execution there is no stringent sequences to limit, can execute in the other order.Moreover, at least one in the flow chart of attached drawing Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps Completion is executed, but can be executed at different times, execution sequence, which is also not necessarily, successively to be carried out, but can be with other At least part of the sub-step or stage of step or other steps executes in turn or alternately.

The above is only some embodiments of the invention, it is noted that for the ordinary skill people of the art For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered It is considered as protection scope of the present invention.

Claims

1. a kind of video generation method characterized by comprising

When receiving the video record trigger action of user, video record resource is obtained, the video record resource includes sound Humanoid standard operation picture happy and corresponding with each broadcast nodes of the music；

The music is played, and acquires user video in playing process, in broadcasting to each broadcast nodes, is shown corresponding Humanoid standard operation picture；

According to the user action and corresponding humanoid mark in the corresponding video frame images of broadcast nodes each in the user video The matching degree of standard operation in quasi- movement picture, determines the action evaluation information of each user action；

According to the video record resource, the action evaluation information of the user video and each user action, mesh is generated Mark video.

2. the method according to claim 1, wherein it is that the corresponding standard operation picture shown, which is transparency, The humanoid standard operation picture of one transparency；

It is described according to the video record resource, the action evaluation information of the user video and each user action, it is raw Include: at target video

According to the music, corresponding and transparency is that the humanoid standard of the second transparency is dynamic with each broadcast nodes of the music The action evaluation information for making picture, the user video and each user action, generates the target video, wherein institute The second transparency is stated greater than first transparency.

3. method according to claim 1 or 2, which is characterized in that described according to the video record resource, the user The action evaluation information of video and each user action, generating target video includes:

The correspondence video frame figure humanoid standard operation picture in the video record resource being added in the user video As in；

According to the action evaluation of the user video and the user action after the music, the humanoid standard operation picture of addition Information generates the target video.

4. method according to claim 1 or 2, which is characterized in that described according to the video record resource, the user The action evaluation information of video and each user action, generating target video includes:

The action evaluation information of each user action is added in the correspondence video frame images in the user video；

According to the user video after the video record resource and addition action evaluation information, the target video is generated.

5. according to the method described in claim 4, it is characterized in that, the action evaluation information of each user action of the determination it Afterwards, further includes:

According to the action evaluation information of each user action, the overall merit information of the user video is determined；

The user video according to after the video record resource and addition action evaluation information, generates target video, Include:

According to the user video and overall merit letter after the video record resource, addition action evaluation information Breath, generates the target video.

6. according to the method described in claim 5, it is characterized by further comprising:

After music completion, the overall merit information is shown.

7. according to the method described in claim 4, it is characterized in that, the video record resource further includes and action evaluation information Corresponding special-effect information, the special-effect information include animation effect and/or audio special efficacy；

After the action evaluation information of each user action of determination, further includes:

By the action evaluation information of each user action, and/or, the action evaluation information institute of each user action is right The special-effect information answered is shown to the displaying interface of corresponding humanoid standard operation picture.

8. the method according to the description of claim 7 is characterized in that the action evaluation information by each user action It is added in the correspondence video frame images in the user video, comprising:

By the action evaluation information of each user action and corresponding with the action evaluation information of each user action Special-effect information, be added in the correspondence video frame images in the user video；

According to the user video after the video record resource and addition action evaluation information and special-effect information, generate The target video.

9. method according to claim 1 or 2, which is characterized in that before the broadcasting music, further includes:

Determine the user within the scope of video capture.

10. method according to claim 1 or 2, which is characterized in that after the generation target video, further includes:

Receive the target video publication operation of the user；

It is operated according to the publication, the target video is distributed to video distribution platform；Alternatively,

When receiving when retaking trigger action of the user, it is based on the video record resource, regenerates the target video.

11. method according to claim 1 or 2, which is characterized in that described as the video record triggering behaviour for receiving user When making, video record resource is obtained, comprising:

When receiving the video record trigger action of the user, control display Music selection interface；

By the Music selection interface, the selection of music operation of the user is obtained；

It is operated according to the selection of music, obtains the video record resource.

12. method according to claim 1 or 2, which is characterized in that described as the video record triggering behaviour for receiving user When making, video record resource is obtained, comprising:

When receiving the video record trigger action of the user by video playing interface, the video playing interface is obtained Video record resource corresponding to currently playing video.

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

Source obtaining module is recorded, for obtaining video record resource, institute in the video record trigger action for receiving user Stating video record resource includes music and humanoid standard operation picture corresponding with each broadcast nodes of the music；

Video acquisition module for playing the music, and acquires user video in playing process, is playing to each broadcasting When node, corresponding humanoid standard operation picture is shown；

Evaluation information determining module, for according to the use in the corresponding video frame images of broadcast nodes each in the user video The matching degree of family movement and the standard operation in corresponding humanoid standard operation picture, determines that the movement of each user action is commented Valence information；

Target video generation module, for according to the video record resource, the user video and each user action Action evaluation information, generate target video.

14. device according to claim 13, which is characterized in that the video acquisition module is showing that corresponding standard is dynamic Make to be specifically used for when picture:

The target video generation module is specifically used for:

According to the music, corresponding and transparency is the humanoid standard operation of the second transparency with each broadcast nodes of the music The action evaluation information of picture, the user video and each user action generates target video, wherein described second Transparency is greater than first transparency.

15. a kind of electronic equipment, which is characterized in that including memory and processor；

Computer program instructions are stored in the memory；

The processor, for reading the computer program instructions, with view described in any one of perform claim requirement 1 to 12 Frequency generation method.

16. a kind of computer readable storage medium, which is characterized in that computer program instructions are stored in the storage medium, When the computer program instructions are executed by processor, the processor realizes the described in any item views of claim 1 to 12 Frequency generation method.