CN111432289B

Movatterモバイル変換

Info

Publication number: CN111432289B
Application number: CN202010277294.8A
Authority: CN
Inventors: 宋学龙
Original assignee: Shenzhen Sports Plus Technology Co ltd
Current assignee: Shenzhen Sports Plus Technology Co ltd
Priority date: 2020-04-10
Filing date: 2020-04-10
Publication date: 2022-05-13
Anticipated expiration: 2040-04-10
Also published as: CN111432289A

Abstract

The invention provides a video generation method based on video adjustment, which generates a video generation interface according to a starting instruction, receives a video setting instruction of a user in the video generation interface, generates a position template according to a starting label and the video setting instruction, randomly selects internal content corresponding to a blank section from a preset system database according to the starting label and the position template and fills the internal content to the position template, acquires an editing section on the position template based on the editing instruction of the user, adjusts the content of the editing section, changes the internal content or changes the external content, quickly and accurately fills the content of each block to the corresponding blank section by generating the position template, and then simply adjusts the position template according to the requirement, so that the video which can efficiently generate and accurately meet the requirement of the user, reduces the adjustment operation and has good synthesis effect.

Description

Video generation method based on video adjustment

Technical Field

The invention relates to the technical field of video processing, in particular to a video generation method based on video adjustment.

Background

Video generally refers to various techniques for capturing, recording, processing, storing, transmitting, and reproducing a series of still images as electrical signals. Wherein, with the progress of science and technology, the continuous promotion of cell-phone performance, video later stage editing products appear like spring bamboo shoots after rain, and various video applications in the society are also more and more fierce. However, the existing technology can not synthesize and edit the audio and video well, and can not meet the requirements of consumers.

Therefore, it is desirable to provide a video generation method based on video adjustment to solve the above technical problems.

Disclosure of Invention

The invention provides a video generation method based on video adjustment, which aims to solve the problems that the existing technology can not synthesize and edit audio and video well and can not meet the requirements of consumers.

In order to solve the technical problems, the technical scheme of the invention is as follows: a video generation method based on video adaptation, comprising the steps of:

generating a video generation interface according to the starting instruction so as to obtain a starting label input by a user and provide video setting options;

receiving a video setting instruction of a user in the video generation interface, and generating a position template according to the starting label and the video setting instruction, wherein the position template provides a plurality of blank sections;

randomly selecting internal contents corresponding to the blank sections from a preset system database according to the starting label and the position template and filling the internal contents into the position template;

acquiring an editing section on the position template based on an editing instruction of a user, and adjusting and replacing the content of the editing section with other internal content or external content;

the position template comprises a material blank section, an intermediate content blank section, a leader blank section, a flower blank section and a tail blank section, wherein the material blank section is used for filling material video content related to the industry, the intermediate content blank section is used for filling detailed content of a video, the leader blank section is used for filling brief content of the video, the flower blank section is used for filling abstract content of the video, and the tail blank section is used for filling ending words and video information content of the video.

In the invention, the system database is classified and recorded with material content corresponding to the material blank section, intermediate content corresponding to the intermediate content blank section, leader content corresponding to the leader blank section, trailer content corresponding to the trailer blank section, and trailer content corresponding to the trailer blank section;

the starting label comprises a duration label with video total duration information, the step of receiving a video setting instruction of a user in the video generation interface and generating a position template according to the starting label and the video setting instruction comprises the following steps:

automatically generating the position template consistent with the duration of the duration label according to an automatic setting instruction and the duration label;

or generating a basic position template with the duration less than the duration label and an increase and decrease operation interface for a user to increase and decrease the blank sections according to the autonomous adjustment instruction, increasing and decreasing the corresponding blank sections on the basic position template according to the increase and decrease instruction of the user, and adjusting the relative positions of the plurality of blank sections according to the drag instruction of the user to the blank sections, thereby generating the position template.

In the invention, the internal content comprises an internal video, the external content comprises an external video, and each blank section is provided with a corresponding duration mark;

when replacing a previously filled internal video on the position template with an external video, comprising the steps of:

acquiring an editing section on the position template based on an editing instruction of a user, and covering the internal video by using an external video;

when the time length priority of the external video is higher than the time length corresponding to the editing section, directly covering the internal video with the external video;

when the time length priority of the external video is lower than the time length corresponding to the editing section, the time length of the external video is adjusted according to the time length corresponding to the editing section, and the adjusted external video covers the internal video.

Wherein, when the editing section is the intermediate content blank section, the step of adjusting the duration of the external video according to the duration corresponding to the editing section comprises:

and when the duration of the external video is judged to be greater than the duration corresponding to the editing section, performing double-speed quick-playing setting on the video content of the title blank section, the title blank section and/or the title blank section according to a preset proportion so as to increase the duration corresponding to the editing section.

And when the duration of the external video is judged to be less than the duration corresponding to the editing section, performing slow play and repeated play at double speed on the video content of the title blank section, the title blank section and/or the title blank section so as to reduce the duration corresponding to the editing section.

Further, the step of adjusting the duration of the external video according to the duration corresponding to the editing section further includes:

and when the duration of the external video is greater than the duration corresponding to the editing section, determining a still picture video segment with a still picture in the external video, and deleting the video frame of the still picture video segment of the external video.

Furthermore, a set number of sampling points are preset on a video picture, and a still picture video segment in the external video is determined according to color data of the sampling points;

the video image is provided with an annular first sampling area, a second sampling area located on the inner side of the first sampling area and a third sampling area located on the outer side of the first sampling area, the density of sampling points in the first sampling area is greater than that of the second sampling area, and the density of sampling points in the second sampling area is greater than that of the third sampling area.

Optionally, the step of adjusting the duration of the external video according to the duration corresponding to the editing section further includes:

and when the duration of the external video is larger than the duration corresponding to the editing section, performing double-speed quick playing on the whole external video to shorten the duration of the external video.

when the duration of the external video is larger than the duration corresponding to the editing section, determining a characteristic picture video section with a set characteristic picture and deleting the characteristic picture video section;

or deleting a number of video segments in the external video at set intervals.

and when the duration of the external video is judged to be less than the duration corresponding to the editing section, performing double-speed slow playing and repeated playing on the external video so as to increase the duration of the external video.

when the duration of the external video is smaller than the duration corresponding to the editing section, increasing playing pictures to increase the playing time of the external video;

or copying and overlapping a plurality of video segments in the external video at set intervals;

or determining a still picture video segment with a still picture in the external video, and copying, overlapping and playing the video frames of the still picture video segment of the external video.

Compared with the prior art, the invention has the beneficial effects that: the video generation method based on video adjustment generates a video generation interface according to a starting instruction, receives a video setting instruction of a user in the video generation interface, generates a position template according to a starting label and the video setting instruction, randomly selects internal content corresponding to a blank section from a preset system database according to the starting label and the position template, fills the internal content to the position template, acquires an editing section on the position template based on the editing instruction of the user, adjusts the content of the editing section, changes the internal content or changes the external content, quickly and accurately fills the content of each block to the corresponding blank section by generating the position template, and then simply adjusts according to requirements, so that accurate video meeting the requirements of the user can be efficiently generated, the adjustment operation is reduced, and the synthesis effect is good.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required in the embodiments are briefly introduced below, and the drawings in the following description are only corresponding to some embodiments of the present invention.

Fig. 1 is a video generation flow chart of a first embodiment of a video generation method based on video adjustment according to the present invention.

Fig. 2 is a flow chart of an external video replacing a previously filled internal video on a position template.

Fig. 3 is a flowchart illustrating adjusting the duration of the external video according to the duration corresponding to the editing section.

Fig. 4 is a flowchart of shortening the duration of the external video or increasing the duration corresponding to the editing section.

Fig. 5 is a flow chart for increasing the duration of an external video.

FIG. 6 is a schematic diagram of an example structure of a position template.

FIG. 7 is a partial diagram of sample points on a video frame.

Fig. 8 is a video generation flow chart of a video generation method based on video adjustment according to a second embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The terms "first," "second," and the like in the terms of the invention are used for descriptive purposes only and not for purposes of indication or implication relative importance, nor as a limitation on the order of precedence.

The existing technology can not well synthesize and edit videos and can not meet the requirements of consumers.

The following is a first embodiment of a video generation method based on video adjustment provided by the present invention, which can solve the above technical problems.

Referring to fig. 1, fig. 1 is a video generation flow chart of a video generation method based on audio adjustment according to a first embodiment of the present invention.

In the drawings, elements having similar structures are denoted by the same reference numerals.

The invention provides a video generation method based on audio adjustment, which is characterized in that a client inputs a plurality of initial labels, such as a time length label, an industry label, a use label, a style label and the like, so that a system can generate videos meeting the requirements of the client according to the initial labels, and the method comprises the following steps:

step S11: and generating a video generation interface according to the starting instruction so as to obtain a starting label input by the user and provide video setting options, wherein the user equivalently inputs a corresponding video setting instruction to the system after selecting the video setting options.

Step S12: the method comprises the steps of receiving a video setting instruction of a user in a video generation interface, generating a position template A according to a starting label and the video setting instruction, wherein the position template A is used for providing different blank sections to correspondingly fill different contents, each blank section is provided with a corresponding time length mark, and the video, audio and other contents with consistent time length can be matched from a preset system database B at a higher speed through the time length mark, so that the video generation can be realized very quickly under the condition that the user does not upload external contents, and the requirements of the user are met.

Step S13: and randomly selecting internal contents from a preset system database B according to the initial label and the position template A to be filled into the position template A, and numbering and classifying the internal contents in the system database B according to different industries, purposes, styles and the like to be put in storage, so that the system can select the corresponding internal contents to be filled according to the initial label input by a user, and a video meeting the requirements of the user is generated.

Step S14: based on an editing instruction of a user, an editing section is obtained on the position template A, the content of the editing section is adjusted and replaced by other internal content or external content, and the external content can be uploaded through the video generation interface, so that when a user is unsatisfied with the generated video, the user can perform adjustment operations such as deletion, composition and the like on the generated video, or can select other internal content from the system database B for replacement, or upload the external content by himself for replacement.

The time length label in the invention can be used for feeding back the total time length information of the video required by the client to the system.

Referring to fig. 6, in the present embodiment, the position template a may include a head blank section, a tail blank section, a plurality of intermediate content blank sections, a plurality of flower blank sections, a plurality of material blank sections, and the like.

The intermediate content blank section is used to fill in the details of the video.

The material blank section is used to fill some industry-related material video content.

The leader white space is used to fill in the brief content of the video, and is intended to guide the viewer's interest in the subsequent story, by some narration or by cropping highlights to show the general plot of the video.

The trailer blank section is used for filling the summary content of the video, and is inserted between the main content of the video, such as a background video segment, an inserted commentary video segment, and the like.

The end-of-the-slice blank section is used for filling the ending language and the video information content of the video.

The system database B classifies and records material content corresponding to the blank sections of the material, intermediate content corresponding to the blank sections of the intermediate content, leader content corresponding to the blank sections of the leader, trailer content corresponding to the blank sections of the trailer and trailer content corresponding to the blank sections of the trailer.

In the embodiment, the system database B may include internal contents with unfixed duration corresponding to the blank sections that are not particularly important, such as the leader blank section, the trailer blank section, and the corresponding important intermediate content blank section includes internal contents with fixed duration, so that when the duration requirement of the client cannot be met, the duration of the unimportant section can be adjusted, thereby ensuring the duration of the important intermediate content blank section, and further enabling the video content of the important intermediate content blank section to be played with high quality.

The position template a shown in fig. 6 is composed of a leaderblank section 11, a materialblank section 12, a first flowerblank section 13, a first intermediate contentblank section 14, a second flowerblank section 15, a second intermediate contentblank section 16, and a trailerblank section 17, which are connected in sequence.

Wherein step S12 specifically includes:

and automatically generating a position template A consistent with the time length of the time length label according to the automatic setting instruction and the time length label, and automatically giving the position template A and meeting the requirement of the time length label.

Or generating a basic position template with the duration less than the duration label and an increase and decrease operation interface for the user to increase and decrease blank sections according to the autonomous adjustment instruction, where the basic position template is equivalent to only the first intermediate contentblank section 14 shown in fig. 6, increasing and decreasing the corresponding blank sections on the basic position template according to the increase and decrease instruction of the user, and adjusting the relative positions of the plurality of blank sections according to the drag instruction of the user on the blank sections, thereby generating a position template a, satisfying the duration requirement and simultaneously satisfying the typesetting requirement of the user for the video.

It should be noted that the system can calculate the remaining duration according to the duration of the duration label and the basic position template, and provide other blank sections with fixed duration for the user to select according to the remaining duration, so that the blank sections selected by the user can still meet the internal content with fixed duration in the system database B, the durations are consistent, and the filling speed and the playing quality can be ensured.

Referring to fig. 2, fig. 3, fig. 4 and fig. 5, fig. 2 is a flowchart illustrating an internal video previously filled on the external video replacement position template a. Fig. 3 is a flowchart illustrating adjusting the duration of the external video according to the duration corresponding to the editing section. Fig. 4 is a flowchart of shortening the duration of the external video or increasing the duration corresponding to the editing section. Fig. 5 is a flow chart for increasing the duration of an external video.

In the invention, the internal content comprises an internal video, and the external content comprises an external video uploaded by a user;

when the previously filled internal video on the position template a is replaced with the external video, the method comprises the following steps:

step S21: based on the user's edit instruction, an edit section is acquired on the position template a, and the internal video is overlaid with the external video.

Step S22: when the time length priority of the external video is higher than the time length corresponding to the editing section, the external video is not limited by the time length corresponding to the editing section, and the internal video is directly covered by the external video, so that the quality of the video is ensured.

When the time length priority of the external video is lower than the time length corresponding to the editing section, the time length of the external video is adjusted according to the time length corresponding to the editing section, and the adjusted external video covers the internal video, so that the requirement of a user on the time length is met.

It should be noted that the intermediate content blank section is the most important core part for the user, so the editing section herein mainly refers to the intermediate content blank section, and the step of adjusting the duration of the external video according to the duration corresponding to the editing section includes:

step S31: and when the duration of the external video is greater than the duration corresponding to the editing section, shortening the duration of the external video or increasing the duration corresponding to the editing section.

Step S31 includes:

step S311: the video content of the leader blank section, the leader blank section and/or the leader blank section is subjected to double-speed quick playback setting according to a preset proportion, so that the duration corresponding to the more important editing section is increased by changing the duration of the unimportant blank section, the replacement content is not changed, and the original quality of the replacement content can be ensured.

Step S312: if the duration of the external video is greater than the duration corresponding to the editing section after the operation of step S311, the still picture video segment with the still picture in the external video is determined, the video frames of the still picture video segment of the external video are deleted, and the still picture video segment is adjusted so as to ensure the quality of the video.

Step S313: if the duration of the external video is greater than the duration corresponding to the editing section after the operation of step S312, the entire external video obtained in step S312 is subjected to double-speed fast playback to shorten the duration of the external video.

It is understood that steps S311, S312 and S313 can be used not only in a progressive combination one layer after another as described above, but each step can also be used individually.

Referring to fig. 7, fig. 7 is a partial schematic diagram of sample points on a video frame.

In the present embodiment, the method of determining a still picture video segment in external video is:

the preset number of sampling points 25 are preset on thevideo picture 21, the still picture video segment in the external video is determined according to the color data of the sampling points 25, if the difference of the color data of a plurality of continuous video pictures 21 is less than the set value, the video segment is determined to be a net value picture video segment.

Preferably, an annularfirst sampling area 22, asecond sampling area 23 located inside thefirst sampling area 22, and athird sampling area 24 located outside thefirst sampling area 22 are provided on thevideo picture 21, the density of sampling points 25 in thefirst sampling area 22 is greater than that of thesecond sampling area 23, the density of sampling points 25 in thesecond sampling area 23 is greater than that of thethird sampling area 24, the center of thefirst sampling area 22 and the center of thevideo picture 21 are set to approximately coincide, so that the annularfirst sampling area 22 in thevideo picture 21 in fig. 7 is mainly subjected to finer sampling, and the sampling efficiency and the accuracy of sampling feedback are improved.

Optionally, when determining that the duration of the external video is greater than the duration corresponding to the editing section, the processing mode for shortening the duration of the external video may further include:

the characteristic picture video segment with the set characteristic picture is determined and deleted to shorten the time length of the external video, for example, when the external video is a video for introducing a product, the picture with a person can be determined as the characteristic picture video segment and deleted, so that the product can be well shown and introduced by the video.

and deleting a plurality of video segments in the external video at set intervals to shorten the time length of the external video, so that the deletion is uniform and the video quality is ensured.

The various ways of shortening the duration of the external video in this embodiment may be used alone or in combination.

Step S32: and when the duration of the external video is less than the duration corresponding to the editing section, increasing the duration of the external video.

Step S32 specifically includes:

step S321: the video content of the film head blank section, the film head blank section and/or the film head blank section is slowly played at double speed and repeatedly played, so that the time length corresponding to the editing section is reduced to correspond to the time length of the external video, the time length corresponding to the more important editing section is increased by changing the time length of the unimportant blank section, the replacement content is not changed, and the original quality of the replacement content can be ensured.

Step S322: if the duration of the external video is less than the duration corresponding to the editing section after the operation of step S321 is performed, the external video is slowly played at double speed and repeatedly played to increase the duration of the external video.

It is to be understood that steps S321 and S322 may be used not only in a progressive combination one layer after another as described above, but also each step may be used alone.

Optionally, when the duration of the external video is determined to be less than the duration corresponding to the editing section, the processing mode for increasing the duration of the external video further includes:

and adding a playing picture to increase the playing time of the external video, wherein the picture can be an internal picture of the system database B or an external picture uploaded by a user.

a plurality of video segments in the external video are copied, overlapped and played at set intervals, the video segments are uniformly increased, and the video quality is ensured.

the method comprises the steps of determining a still picture video segment with a still picture in an external video, copying, superposing and playing a video frame of the still picture video segment of the external video, and slightly changing a video picture by prolonging the playing time of an original still picture video segment so as to ensure the video quality.

The various ways of increasing the duration of the external video in this embodiment may be used alone or in combination.

The following is a second embodiment of the video generation method based on audio adjustment provided by the present invention, which can solve the above technical problems.

Referring to fig. 8, fig. 8 is a video generation flow chart of a video generation method based on audio adjustment according to a second embodiment of the present invention.

step S41: and generating a video generation interface according to the starting instruction so as to obtain a starting label input by the user, the uploaded external content and provide video setting options, wherein the user equivalently inputs a corresponding video setting instruction to the system after selecting the video setting options.

Step S42: receiving a video setting instruction of a user in a video generation interface, and generating a position template according to a starting label and the video setting instruction, wherein the position template provides a plurality of blank sections, different blank sections are used for correspondingly filling different contents, and each blank section is provided with a corresponding duration mark.

Step S43: randomly selecting internal contents corresponding to the blank sections from a preset system database according to the initial labels and the position templates and filling the internal contents into the position templates;

step S44: based on an editing instruction of a user, an editing section is obtained on the position template, and the internal audio of the editing section is adjusted, replaced by other internal audio or replaced by external audio.

The position template comprises a material blank section, an intermediate content blank section, a head blank section, a flower blank section and a tail blank section, wherein the material blank section is used for filling material video content related to industry, the intermediate content blank section is used for filling detailed content of a video, the head blank section is used for filling brief content of the video, the flower blank section is used for filling abstract content of the video, and the tail blank section is used for filling closing words and video information content of the video.

The system database records the material content corresponding to the blank section of the material, the intermediate content corresponding to the blank section of the intermediate content, the head content corresponding to the head blank section, the flower content corresponding to the flower blank section and the tail content corresponding to the tail blank section in a classified manner.

In the present invention, step S42 specifically includes:

and automatically generating a position template consistent with the time length of the time length label according to the automatic setting instruction and the time length label, and automatically giving the position template and meeting the requirement of the time length label.

Or generating a basic position template with the time length less than the time length label and an increase and decrease operation interface for a user to increase and decrease blank sections according to the autonomous adjustment instruction, wherein the basic position template is equivalent to only the first intermediate contentblank section 14 shown in fig. 6, increasing and decreasing corresponding blank sections on the basic position template according to the increase and decrease instruction of the user, and adjusting the relative positions of a plurality of blank sections according to the drag instruction of the user to the blank sections, so that a position template is generated, the time length requirement is met, and the typesetting requirement of the user for the video can be met.

In the present embodiment, the internal content includes internal audio, and the external content includes external audio, where the audio may be understood as background music or dubbing, etc.;

the step of replacing the internal audio of the editing section with the external audio includes:

comparing the external audio with the duration of the corresponding editing section;

when the duration of the external audio is longer than that of the editing section, the external audio is subjected to double-speed quick playing;

and when the duration of the external audio is less than that of the editing section, performing double-speed slow playing on the external audio.

Optionally, when the duration of the external audio is greater than the duration of the editing section, determining homophonic audio segments with continuous same pronunciation in the external audio, and deleting audio frames of the homophonic audio segments, so that the external audio is less affected by changes, and the audio quality is ensured.

Optionally, when the duration of the external audio is greater than the duration of the editing section, deleting a plurality of audio segments in the external audio at set intervals, wherein the audio segments are increased more uniformly, and the audio quality is ensured.

Optionally, when the duration of the external audio is longer than the duration of the editing section, the method further includes deleting an audio segment with a smaller volume in the external audio, so that the external audio is less affected by the change of the external audio, and the audio quality is ensured.

Optionally, when the duration of the external audio is less than the duration of the editing section, the method further includes performing fast-speed playback on the external audio and then repeatedly playing the external audio.

Wherein the same alternatives for the same purpose may be used alone or in combination.

In addition, the internal content in this embodiment includes an internal picture, the external content includes an external picture, and the same filling methods for the internal picture and the external picture include:

the method comprises the steps of determining the insertion position of a picture according to a position instruction input by a user, expanding the insertion position to a playing interval for playing the picture with set duration by quickly playing video contents before and after the insertion position, and filling an internal picture or an external picture into the playing interval for playing.

Preferably, the method for filling the internal picture and the external picture further includes:

the hue, saturation and brightness of the picture are adjusted according to the video images before and after the insertion position, so that the playing of the picture is linked with the playing of the video more naturally.

Alternatively, the picture may be inserted into a set area of the video frame and displayed on the video frame.

The internal content of the invention also comprises internal characters, and the external content also comprises external characters.

The filling method of the internal characters comprises the following steps:

analyzing color data of a plurality of preset detection areas in a plurality of video images at different time points, wherein the plurality of preset detection areas can be four side areas of the video images, and the detection areas with high color uniformity and small color change degree are used as display areas of characters to obtain a clearer font display effect, and are filled with preset fonts, colors and sizes.

Preferably, the playing time of the internal characters is 5-10 seconds shorter than that of the video, and the middle point of the playing time of the internal characters is aligned with the central point of the playing time of the video, so that a viewer has more response time to the characters.

The filling method of the external characters comprises the following steps:

the user selected font, color, size, and display position are used for filling.

Preferably, the playing time of the external characters is 5-10 seconds shorter than the playing time of the video, and the middle point of the playing time of the external characters is aligned with the central point of the playing time of the video, so that a viewer has more response time to the characters.

In addition, as in the first embodiment, the method of replacing the external video with the previously filled internal video on the position template may also be applied to this embodiment in combination, in which the filling of the video is completed first, and then the filling of the audio, the picture and the text is completed in sequence.

When a user needs to generate a video by using the video generation method based on audio adjustment, the user can input a starting instruction to generate a video generation interface, then the user can input a starting label on the video generation interface, and simultaneously can select to input an automatic setting instruction to automatically generate a position template, or select to input an autonomous adjustment instruction to generate a basic position template, and the generation of the basic position template requires the user to input an increase and decrease instruction and/or a drag instruction to generate a position template required by the user, and the position template can refer to fig. 6.

After the position template is generated, the system randomly selects internal contents from the system database according to the starting label and the position template and fills the internal contents into the position template, and the user fills external contents into the position template.

The system database in the invention can be manually edited and combined into a large amount of professional videos, and meanwhile, various labels are marked on the videos in a numbering mode for classification and are recorded into the system database, for example, the system database is marked with an industry label: electronic technology, such as labeling for use: the business propaganda, forming the number 1234, the first two 12 represent electronic technology, and the last two 34 represent business propaganda. So that the subsequent system can call the video content corresponding to the initial label input by the user according to the number.

In addition, the video generation method based on audio adjustment can automatically search and download contents such as pictures, characters, audio and videos through the network according to the labels, and simultaneously classify the contents to be used as fragment materials which are manually edited and combined into professional videos, so that the efficiency is high.

For example, the video generation method of the invention can access the system to generate AI of the video file script by means of a Baidu file SDK interface, namely, the tag input by the user is subjected to algorithm analysis, then the file keyword required by the tag is calculated, then the character fragments of the system database are called according to the keyword to form the video file script, then all other fragments are called according to the script to carry out video splicing, and finally the video creation is completed. On the other hand, the system classifies all fragments in the fragment library, then an editor and a director manually splice and combine massive professional videos according to past experiences, each step of splicing is recorded by the system algorithm deep learning system and automatically tuned and optimized, own deep learning and algorithm basic data are gradually formed, and finally calculation and matching are performed according to user labels.

Referring to fig. 6, a technology company that produces earphones needs to generate 160 seconds of business promotion video.

Firstly, a user can input a starting instruction to produce a video generation interface, and then information such as a company name, a company product, a video duration, a video purpose and the like is input into the video generation interface, and the system can convert the information into the following starting labels: industry tags-headphones; application labels-exhibition, propaganda and promotion; duration tag-160 seconds; type-Enterprise propaganda.

The user may then select a video setting option, such as the "auto generation" option, to input an auto setting instruction to the system, which receives the auto setting instruction and automatically generates a location template a in combination with the duration label of 160 seconds, such as the location template a in fig. 6 comprising a 10 second leaderblank section 11, a 30 second materialblank section 12, a 10 second first flowerblank section 13, a 60 second first intermediate contentblank section 14, a 10 second flowerblank section 15, a 30 second intermediate contentblank section 16, and a 10 second tailblank section 17, for which the system will match corresponding duration flags to feed back their durations.

Wherein the system will preferentially set the materialblank sections 12, the first intermediate contentblank sections 14, and the second intermediate contentblank sections 16 to be of a duration consistent with the corresponding internal content durations in the system database B, such as setting the materialblank sections 12 to be of 10 seconds, 15 seconds, or 30 seconds consistent with the material content durations.

Of course, it should be noted that the time length steps of the internal contents in the system database B are not limited to the 10 second, 15 second, 30 second and other steps in the figure, and the number of the internal contents in the system database B is not limited to 100, 200 and other steps in the figure.

Or, the user may select the option of "manual adjustment", so as to input an autonomous adjustment instruction to the system to generate a basic position template with a time length shorter than the time length label and an increase/decrease operation interface for the user to increase/decrease blank sections, where the basic position template corresponds to only the first intermediate contentblank section 14 shown in fig. 6, the user inputs an increase/decrease instruction according to a preference to correspondingly add blank sections such as the leaderblank section 11, the materialblank section 12, the first flowerblank section 13, the second flowerblank section 15, the second intermediate contentblank section 16, and the tailblank section 17, and simultaneously, by inputting a drag instruction, the relative positions of the plurality of blank sections may be adjusted, so as to generate a position template that is the same as or different from the position template a in fig. 6.

If the position template a is generated, the system will randomly select internal contents from the system database B according to the labels of the industry label, the earphone, the application label, the exhibition, the promotion, the duration label, 160 seconds, the type, the enterprise promotion, etc., and fill the internal contents into the position template a, specifically, for example, randomly select one of 200 intermediate contents from 60 seconds, and then fill the selected video into the first intermediate contentblank section 14.

Meanwhile, the blank sections, such as the headblank section 11, the materialblank section 12, the first flowerblank section 13, the second flowerblank section 15, the second intermediate contentblank section 16, and the endblank section 17, are filled with the label-compliant and time-length-uniform internal video in the above manner.

And after the video is filled, randomly selecting internal audio from the system database B to be filled on the position template A.

After the audio is filled, the system determines the insertion position of the picture according to the position instruction input by the user, expands the insertion position into a playing interval with set duration by rapidly playing the video content before and after the insertion position, randomly selects an internal picture from the system database B or receives an external picture, and fills the internal picture or the external picture into the playing interval to play.

After the internal picture is filled, the color data of a plurality of preset detection areas in a plurality of video images at different time points are analyzed, wherein the plurality of preset detection areas can be four side areas of the video images, the detection areas with high color uniformity and small color change degree are used as display areas of characters to obtain a clearer font display effect, and the preset fonts, colors and sizes are used for filling.

The upward arrow in fig. 6 indicates the selection of internal content from within the system database B to populate the location template a.

If the user is not satisfied with the content of a certain section, the user can input an instruction to cause the system to determine that the section is an edited section, and then can perform adjustment operations such as deletion and composition of the content in the edited section, or can replace the content with other internal content or external content.

Wherein, the first embodiment can be referred to by replacing the internal video of a certain section with the external video, the second embodiment can be referred to by replacing the internal audio of a certain section with the external audio, and if the duration of the video and the audio is not matched after the video is replaced, the audio can be correspondingly replaced.

Meanwhile, it should be noted that, because some users in some sections basically do not upload content to replace the content by themselves or the editing is not good at a high probability, the system may further limit users in some sections from not editing, and only select internal content from the system database B, for example, material content to be filled in blank sections of the material may need corresponding editing and synthesizing operations on multiple industry materials, which is more auxiliary and is not good at a high probability by the user, so that the blank sections of the material may be limited from not editing, and only internal content may be selected from the system database B.

On the other hand, if the system database B does not have the content conforming to the above-mentioned label, the system can also automatically search and download the contents such as pictures, characters, audio and video through the network, automatically edit them to form the corresponding contents, and fill them in the template.

The video generation method based on audio adjustment generates a video generation interface according to a starting instruction, receives a video setting instruction of a user in the video generation interface, generates a position template according to a starting label and the video setting instruction, randomly selects internal content corresponding to a blank section from a preset system database according to the starting label and the position template, fills the internal content to the position template, acquires an editing section on the position template based on the editing instruction of the user, adjusts the content of the editing section, changes the internal content or changes the external content, quickly and accurately fills the content of each block to the corresponding blank section by generating the position template, and then simply adjusts according to requirements, so that accurate video meeting the requirements of the user can be efficiently generated, the adjustment operation is reduced, and the synthesis effect is good.

In summary, although the present invention has been described with reference to the preferred embodiments, the above-described preferred embodiments are not intended to limit the present invention, and those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention, therefore, the scope of the present invention shall be determined by the appended claims.

Claims

1. A video generation method based on video adjustment, comprising the steps of:

the position template comprises a material blank section, an intermediate content blank section, a leader blank section, a flower blank section and a tail blank section, wherein the material blank section is used for filling material video content related to the industry, the intermediate content blank section is used for filling detailed content of a video, the leader blank section is used for filling brief content of the video, the flower blank section is used for filling abstract content of the video, and the tail blank section is used for filling a final phrase and video information content of the video;

the internal content comprises an internal video, the external content comprises an external video, and each blank section is provided with a corresponding duration mark;

when the time length priority of the external video is higher than the time length corresponding to the editing section, directly covering the internal video with the external video, thereby ensuring the quality of the video;

when the time length priority of the external video is lower than the time length corresponding to the editing section, adjusting the time length of the external video according to the time length corresponding to the editing section, and covering the adjusted external video on the internal video, so that the requirement of a user on the time length is ensured;

when the editing section is the intermediate content blank section, the step of adjusting the duration of the external video according to the duration corresponding to the editing section includes:

when the duration of the external video is judged to be greater than the duration corresponding to the editing section, performing double-speed quick-playing setting on the video content of the leader blank section, the leader blank section and/or the leader blank section according to a preset proportion so as to increase the duration corresponding to the editing section, thereby not changing the replacement content and ensuring the original quality of the replacement content;

after the video contents of the slice header blank section, the slice header blank section and/or the slice header blank section are subjected to double-speed quick playing according to a preset proportion, if the time length of the external video is judged to be still greater than the time length corresponding to the editing section, determining a still picture video section with a still picture in the external video, deleting the video frame of the still picture video section of the external video, and adjusting the still picture video section so as to ensure the quality of the video;

2. The video generation method based on video adjustment according to claim 1, wherein the system database is classified and recorded with material content corresponding to the material blank section, intermediate content corresponding to the intermediate content blank section, title content corresponding to the title blank section, and title content corresponding to the title blank section;

3. The video generation method based on video adjustment according to claim 1, wherein a set number of sampling points are preset on a video picture, and a still picture video segment in the external video is determined according to color data of the sampling points;

4. The video generation method based on video adjustment according to claim 1, wherein the step of adjusting the duration of the external video according to the duration corresponding to the editing section further comprises:

5. The video generation method based on video adjustment according to claim 1, wherein the step of adjusting the duration of the external video according to the duration corresponding to the editing section further comprises:

or deleting a number of video segments in the external video at set intervals.

6. The video generation method based on video adjustment according to claim 1, wherein the step of adjusting the duration of the external video according to the duration corresponding to the editing section further comprises:

7. The video generation method based on video adjustment according to claim 1, wherein the step of adjusting the duration of the external video according to the duration corresponding to the editing section further comprises: