Video generation method and video generation system

Abstract

The invention discloses a video generation method and a video generation system, and relates to the technical field of video generation, and the method comprises the steps: collecting video information, generating component element information, collecting the feedback of a user to a video through an obtaining unit, and intercepting a time period of the generated element information in the description of the video information; the method comprises the following steps: firstly, generating element information, marking the element information at the rear side of the corresponding generation element information, establishing a jump chain at the starting point and the ending point of a time period, and calculating a matching index for describing video information and a video of a finished product, and the method has the advantages that a part needing to be modified or perfected can be quickly found through an editing unit; according to the method, the user can conveniently and quickly position and check the position of the specific element in the video, the working efficiency is greatly improved, great creation freedom is given to the user, the generated video better meets the requirements of the user, meanwhile, the method is favorable for knowing the editing habits and preferences of the user, the judgment and recording of the personalized trend of the user are realized, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of video generation, and in particular to a video generation method and a video generation system. Background Art

[0002] Video refers to various technologies that capture, record, process, store, transmit and reproduce a series of static images in the form of electrical signals. Video technology was first developed for television systems, but has now developed into various formats to facilitate consumers to record videos. The development of network technology has also enabled video documentary clips to exist on the Internet in the form of streaming media and can be received and played by computers. Video and film are different technologies. The latter uses photography to capture dynamic images as a series of static photos. Common video generation methods and video generation systems cannot accurately locate the frame level or the subtle attribute level of specific elements when in use, making it inconvenient to adjust them. Moreover, when obtaining the required generation element information in other videos, it is inconvenient to apply it to the video you need, causing the generated video to easily deviate from your own expectations. For this reason, we propose a video generation method and a video generation system. Summary of the invention

[0003] The object of the present invention is to provide a video generation method and a video generation system.

[0004] In order to solve the problems raised in the above background technology, the present invention provides the following technical solutions: a video generation method, comprising the following steps: S100, collecting video information, obtaining original video information, splitting the original video information, converting the video information into action surface layer element information and scene element information, and further analyzing the appearance characteristics of the action surface layer element information and the scene element information to generate component element information; S200, establishing an acquisition unit, using the acquisition unit to collect user feedback on the video, and then generating description video information according to component video information and feedback information; S300, splitting the description video information according to the splitting method of the original video information, obtaining the generated element information and the original element video information, establishing an editing unit under the description video information, displaying the generated element information in the editing unit, and intercepting the time period of the generated element information in the description video information; S400, marking the intercepted time period inside the corresponding generated element information, and adding jump links at the start and end of the time period, and when the user clicks the jump link, the description video information will directly jump to the corresponding time point; S500, establishing a custom unit for different generated element information, the user independently edits the custom unit, and then uses the custom unit to improve the generated element information, generates and improves the original element video information, and uses the improved generated element information and the improved original element video information to generate a finished video; S600, recording the generated element information improved by using the custom unit, analyzing all the generated element information in the description video information, and calculating the matching index between the description video information and the finished video; S700: Establish a user habit unit, and at the same time establish a branch folder in the user habit unit, and analyze the common points according to the customized unit improvement information.

[0005] As a further solution of the present invention: in S200, after collecting the user's feedback on the video, the characteristics in the feedback information are analyzed to obtain the retrieval characteristic information, and then the corresponding component element information is retrieved using the retrieval characteristic.

[0006] As a further solution of the present invention: in S500, when the user edits the custom unit, the user independently retrieves the video information that meets his or her needs, obtains the material video information, and enters it into the custom unit. The custom unit then analyzes the detail characteristic information of the material video information and sorts the detail characteristic information in sequence. At this time, the user selects the required detail characteristic information and generates replacement information. The custom unit then replaces the replacement information with the appearance characteristics in the description video information to generate complete detail characteristic information, and establishes a replacement degree analysis function to determine the method of improving the description video information using the replacement degree analysis function.

[0007] As a further solution of the present invention: in S500, the substitution degree analysis function includes a 10% relationship level, a 20% relationship level, a 40% relationship level, a 60% relationship level, an 80% relationship level and a complete substitution level. Suppose the relationship level selected in the substitution degree analysis function is , let the replacement information be , let the feature information describing the video information be , assuming that the perfect generated element information is ; ; The perfect generation element information is calculated according to the above formula, and new dynamic video information is generated according to the perfect generation element information, and then the perfect detail characteristic information is replaced with the detail characteristic information in the description video information, wherein the complete replacement level refers to directly replacing the replacement information with the detail characteristic information in the description video information.

[0008] As a further solution of the present invention: in S500, when a relationship level other than the complete replacement level is selected, a comparison unit is synchronously established, and then an original dynamic frame and a perfect dynamic frame are established in the comparison unit, and the original element video information and the perfect original element video information are extracted, and the original element video information and the perfect original element video information are entered into the original dynamic frame and the perfect dynamic frame, and the original dynamic frame and the perfect dynamic frame have mobility and transparency adjustment functions.

[0009] As a further solution of the present invention: In S600, the method for calculating the matching index between the description video information and the finished product video is as follows: S610, extracting the generated element information improved by using the custom unit, and analyzing the quantity and time of the generated element information improved by using the custom unit; S620, extracting all the generated element information in the description video information, and analyzing the number of all the generated element information in the description video information and the overall time of the generated element information; S630, the number of generated element information improved by the custom unit is set to , let the time of generating element information using custom unit be , let the number of all generated element information describing the video information be , let the time of generating element information in the video information be , let the matching index be ; ; The matching index is calculated according to the above formula.

[0010] As a further solution of the present invention: in S600, after the matching index is calculated, a habit threshold is established synchronously, and the habit threshold is set as ; when When the user is using the custom information, a branch folder will not be created in the user's custom unit; when When the user clicks on the custom improvement information, a branch folder is created in the user's custom unit for the custom improvement information, and then the custom improvement information is transferred to the branch folder.

[0011] As a further solution of the present invention: in S700, after analyzing the common points, the personalized trend of the customized improvement information will be determined, and then the personalized trend will be recorded in the branch folder. When the user selects the branch folder, the descriptive video information converted in S200 will tend to the content of the branch folder.

[0012] In addition, a video generation system is proposed, which is applicable to the video generation method.

[0013] By adopting the above technical solution, compared with the prior art, the beneficial effects of the present invention are: 1. The present invention can quickly find the parts that need to be modified or improved through the editing unit, which is convenient for users to quickly locate and view the position of specific elements in the video, greatly improving work efficiency, and giving users great creative freedom, so that the generated video is more in line with their own needs. At the same time, it helps to understand the editing habits and preferences of users, realizes the judgment and recording of user personalized tendencies, provides users with more intimate and personalized services, and improves user experience; 2. The present invention collects user feedback on the video and then analyzes its appearance characteristics to obtain retrieval characteristic information, which can more accurately understand user needs, quickly locate video elements that meet user descriptions, and provide users with more means to optimize and innovate video detail characteristics, thereby creating more personalized and unique video effects, and can fine-tune the details of some elements to make them more refined, providing users with intuitive visual comparisons, which helps users better evaluate the effects of detail feature replacement at different relationship levels; 3. The present invention calculates the matching index between the video information and the finished video through a specific formula, understands the influence of one's own editing operations on the overall structure and content of the video, better analyzes the user's editing habits and preferences, realizes the intelligent management of user habit information, screens out editing operations with certain representativeness and personalized characteristics for recording and analysis, effectively utilizes the user's personalized creative tendencies, and provides targeted video generation guidance for the user according to the user's historical editing habits and preferences. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 Schematic diagram of the method steps in an embodiment of the present invention. DETAILED DESCRIPTION

[0015] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0016] In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0017] Embodiment 1: The present application proposes a video generation method and a video generation system, as shown in the accompanying drawings of the specification. Figure 1 As shown, the following steps are included: S100, collecting video information, obtaining original video information, splitting the original video information, converting the video information into action surface layer element information and scene element information, and further analyzing the appearance characteristics of the action surface layer element information and the scene element information to generate component element information; S200, establishing an acquisition unit, using the acquisition unit to collect user feedback on the video, and then generating description video information according to component video information and feedback information; S300, splitting the description video information according to the splitting method of the original video information, obtaining the generated element information and the original element video information, establishing an editing unit under the description video information, displaying the generated element information in the editing unit, and intercepting the time period of the generated element information in the description video information; S400, marking the intercepted time period inside the corresponding generated element information, and adding jump links at the start and end of the time period, and when the user clicks the jump link, the description video information will directly jump to the corresponding time point; S500, establishing a custom unit for different generated element information, the user independently edits the custom unit, and then uses the custom unit to improve the generated element information, generates and improves the original element video information, and uses the improved generated element information and the improved original element video information to generate a finished video; And establish an automatic capture function. When the user directly clicks on the generated element information in the video, the automatic capture function will analyze and capture the generated element information content clicked, then retrieve the generated element information content and display it; S600, recording the generated element information improved by using the custom unit, analyzing all the generated element information in the description video information, and calculating the matching index between the description video information and the finished video; S700, establishing a user habit unit, and at the same time establishing a branch folder in the user habit unit, and analyzing the common points according to the customized unit improvement information; Specific workflow: collect video information, split the original video information, convert the video information into action surface level element information and scene element information, analyze the appearance characteristics of the action surface level element information and the scene element information, use the acquisition unit to collect user feedback on the video, obtain the description video information, split the description video information, establish an editing unit under the description video information, display the generated element information in the editing unit, and intercept the time period of the generated element information in the description video information, mark the intercepted time period inside the corresponding generated element information, add jump links at the start and end of the time period, use the custom unit to improve the generated element information, generate the finished video, analyze all the generated element information in the description video information, calculate the matching index between the description video information and the finished video, and analyze their common points based on the information improved by the custom unit; Furthermore, the editing unit can greatly improve work efficiency, quickly find the parts that need to be modified or improved, and at the same time facilitate users to quickly locate and view the position of specific elements in the video, greatly improving work efficiency, quickly find the parts that need to be modified or improved, and give users great creative freedom, so that the generated video is more in line with their own needs. At the same time, it helps to understand the user's editing habits and preferences, realizes the judgment and recording of the user's personalized trends, provides users with more intimate and personalized services, and improves user experience.

[0018] Embodiment 2: Based on the first embodiment, as shown in the accompanying drawings of the specification Figure 1 As shown, in S200, after collecting the user's feedback on the video, the characteristics in the feedback information are analyzed to obtain the retrieval characteristic information, and then the corresponding component element information is retrieved using the retrieval characteristic; In S500, when the user edits the custom unit, the user independently searches for video information that meets his or her needs, obtains material video information, and enters it into the custom unit. Then the custom unit analyzes the detail characteristic information of the material video information and sorts the detail characteristic information in sequence. At this time, the user selects the required detail characteristic information and generates replacement information. Then the custom unit replaces the replacement information with the appearance characteristics in the description video information to generate perfect detail characteristic information, and establishes a replacement degree analysis function to determine the method of perfecting the description video information using the replacement degree analysis function. In S500, the replacement degree analysis function includes a 10% relationship level, a 20% relationship level, a 40% relationship level, a 60% relationship level, an 80% relationship level, and a complete replacement level. Suppose the relationship level selected in the replacement degree analysis function is , let the replacement information be , let the feature information describing the video information be , assuming that the perfect generated element information is ; ; Calculate the perfect generated element information according to the above formula, generate new dynamic video information according to the perfect generated element information, and then replace the perfect detail characteristic information with the detail characteristic information in the description video information, wherein the complete replacement level refers to directly replacing the replacement information with the detail characteristic information in the description video information; In S500, when a relationship level other than the complete replacement level is selected, a comparison unit is synchronously established, and then an original dynamic frame and a perfect dynamic frame are established in the comparison unit, and the original element video information and the perfect original element video information are extracted, and the original element video information and the perfect original element video information are entered into the original dynamic frame and the perfect dynamic frame, and the original dynamic frame and the perfect dynamic frame have mobility and transparency adjustment functions; A capture count analysis function is also established. When the user turns on the capture count analysis function, the user's continuous clicks on the generated element information in the video will be recorded by the capture count analysis function. When the capture count analysis function is turned off, the number of clicks on different generated element information will be analyzed, and then the different generated element information will be sorted according to the number of clicks. Specific workflow: analyze the characteristics in the feedback information, retrieve the corresponding component element information, analyze the detail characteristic information of the material video information, and sort the detail characteristic information in sequence. At this time, the user selects the required detail characteristic information, establishes a replacement degree analysis function, uses the replacement degree analysis function to determine the way to improve the description video information, calculates the improved detail characteristic information, and generates new dynamic video information based on the improved generation element information. The improved detail characteristic information is replaced with the detail characteristic information in the description video information, and an original dynamic frame and a improved dynamic frame are established in the comparison unit, and the original element video information and the improved original element video information are extracted, and the original element video information and the improved original element video information are entered into the original dynamic frame and the improved dynamic frame; Furthermore, by collecting user feedback on the video and analyzing its appearance characteristics to obtain retrieval feature information, we can understand user needs more accurately and quickly locate video elements that meet user descriptions. We can give users more means to optimize and innovate video detail characteristics, thereby creating more personalized and unique video effects, and can fine-tune the details of some elements to make them more refined, providing users with intuitive visual comparisons, which help users better evaluate the effects of detail feature replacement at different relationship levels.

[0019] Embodiment three: Based on the second embodiment, as shown in the accompanying drawings of the specification Figure 1 As shown, in S600, the method for calculating the matching index between the description video information and the finished video is as follows: S610, extracting the generated element information improved by using the custom unit, and analyzing the quantity and time of the generated element information improved by using the custom unit; S620, extracting all the generated element information in the description video information, and analyzing the number of all the generated element information in the description video information and the overall time of the generated element information; S630, the number of generated element information improved by the custom unit is set to , let the time of generating element information using custom unit be , let the number of all generated element information describing the video information be , let the time of generating element information in the video information be , let the matching index be ; ; The matching index is calculated according to the above formula; In S600, after the matching index is calculated, a habit threshold is established synchronously. The habit threshold is set as ; when When the user is using the custom information, a branch folder will not be created in the user's custom unit; when When the user clicks the button, a branch folder is created in the user habit unit for the customized improvement information, and then the customized improvement information is transferred to the branch folder; In S700, after analyzing the common points, the personalized trend of the customized improvement information is determined, and then the personalized trend is recorded in the branch folder. When the user selects the branch folder, the descriptive video information converted in S200 will tend to the content of the branch folder; For the information stored in the branch folder, further analyze its differences from other regular video information in terms of content form, emphasis and expression style, so as to determine its personalized tendency. Use text analysis technology to analyze the feedback in the customized information in terms of vocabulary, sentence structure, etc., and compare the text content in the original video information to find out its uniqueness. Specific workflow: extracting the generated element information improved by using the custom unit, analyzing the number and time of the generated element information improved by using the custom unit, extracting all the generated element information in the description video information, analyzing the number of all the generated element information in the description video information and the overall time of the generated element information, calculating the matching index, transmitting the customized improved information to the branch folder, judging the personalized trend of the customized improved information, and then recording the personalized trend in the branch folder. When the user selects the branch folder, the description video information converted in S200 will tend to the content of the branch folder; Furthermore, by calculating the matching index between the information describing the video and the finished video through a specific formula, we can understand the impact of our own editing operations on the overall structure and content of the video, better analyze the user's editing habits and preferences, realize the intelligent management of user habit information, screen out editing operations with certain representative and personalized characteristics for recording and analysis, effectively utilize the user's personalized creative tendencies, and provide targeted video generation guidance for users based on their historical editing habits and preferences.

[0020] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A video generation method, characterized in that: The following steps are involved: S100, collecting video information, obtaining original video information, splitting the original video information, converting the video information into action surface layer element information and scene element information, and further analyzing the appearance characteristics of the action surface layer element information and the scene element information to generate component element information; S200, establishing an acquisition unit, using the acquisition unit to collect user feedback on the video, and then generating description video information according to component video information and feedback information; S300, splitting the description video information according to the splitting method of the original video information, obtaining the generated element information and the original element video information, establishing an editing unit under the description video information, displaying the generated element information in the editing unit, and intercepting the time period of the generated element information in the description video information; S400, marking the intercepted time period inside the corresponding generated element information, and adding jump links at the start and end of the time period, and when the user clicks the jump link, the description video information will directly jump to the corresponding time point; S500, establishing a custom unit for different generated element information, the user independently edits the custom unit, and then uses the custom unit to improve the generated element information, generates and improves the original element video information, and uses the improved generated element information and the improved original element video information to generate a finished video; S600, recording the generated element information improved by using the custom unit, analyzing all the generated element information in the description video information, and calculating the matching index between the description video information and the finished video; S700: Establish a user habit unit, and at the same time establish a branch folder in the user habit unit, and analyze the common points according to the customized unit improvement information.

2. A video generation method according to claim 1, characterized in that: In S200, after collecting the user's feedback on the video, the characteristics in the feedback information are analyzed to obtain the retrieval characteristic information, and then the corresponding component element information is retrieved using the retrieval characteristic.

3. A video generation method according to claim 1, characterized in that: In S500, when the user edits the custom unit, the user independently retrieves the video information that meets his or her needs, obtains the material video information, and enters it into the custom unit. The custom unit then analyzes the detail characteristic information of the material video information and sorts the detail characteristic information in sequence. At this time, the user selects the required detail characteristic information and generates replacement information. The custom unit then replaces the replacement information with the appearance characteristics in the description video information to generate complete detail characteristic information, and establishes a replacement degree analysis function to determine the method of improving the description video information using the replacement degree analysis function.

4. A video generation method according to claim 3, characterized in that: In S500, the substitution degree analysis function includes a 10% relationship level, a 20% relationship level, a 40% relationship level, a 60% relationship level, an 80% relationship level, and a complete substitution level. Suppose the relationship level selected in the substitution degree analysis function is , let the replacement information be , let the feature information describing the video information be , assuming that the perfect generated element information is ; ； The perfect generation element information is calculated according to the above formula, and new dynamic video information is generated according to the perfect generation element information, and then the perfect detail characteristic information is replaced with the detail characteristic information in the description video information, wherein the complete replacement level refers to directly replacing the replacement information with the detail characteristic information in the description video information.

5. A video generation method according to claim 4, characterized in that: In S500, when a relationship level other than the complete replacement level is selected, a comparison unit is synchronously established, and then an original dynamic frame and a perfect dynamic frame are established in the comparison unit, and the original element video information and the perfect original element video information are extracted, and the original element video information and the perfect original element video information are entered into the original dynamic frame and the perfect dynamic frame. The original dynamic frame and the perfect dynamic frame have mobility and transparency adjustment functions.

6. A video generation method according to claim 1, characterized in that: In S600, the method for calculating the matching index between the description video information and the finished video is as follows: S610, extracting the generated element information improved by using the custom unit, and analyzing the quantity and time of the generated element information improved by using the custom unit; S620, extracting all the generated element information in the description video information, and analyzing the number of all the generated element information in the description video information and the overall time of the generated element information; S630, the number of generated element information improved by the custom unit is set to , let the time of generating element information using custom unit be , let the number of all generated element information describing the video information be , let the time of generating element information in the video information be , let the matching index be ; ； The matching index is calculated according to the above formula.

7. A video generation method according to claim 6, characterized in that: In S600, after the matching index is calculated, a habit threshold is established synchronously. The habit threshold is set as ; when When the user is using the custom information, a branch folder will not be created in the user's custom unit; when When the user clicks on the custom improvement information, a branch folder is created in the user's custom unit for the custom improvement information, and then the custom improvement information is transferred to the branch folder.

8. A video generation method according to claim 1, characterized in that: In the above S700, after analyzing the common points, the personalized trend of the customized improvement information is determined, and then the personalized trend is recorded in the branch folder. When the user selects the branch folder, the descriptive video information converted in S200 will tend to the content of the branch folder.

9. A video generation system, characterized in that: The system is applicable to the video generation method according to any one of claims 1 to 8.

Images