An intelligent video image synthesis method based on artificial intelligence

Abstract

The present invention relates to the field of video image synthesis, and specifically discloses an intelligent video image synthesis method based on artificial intelligence. The present invention collects video image data to be synthesized and performs preprocessing; according to the data volume and diversification degree of the video image data to be synthesized, the goals and requirements of the video image synthesis task, and the attributes of each artificial intelligence model for video image synthesis, it screens an adapted artificial intelligence model for video image synthesis to improve the synthesis effect of video images; further sets the basic parameters for video image synthesis, detects indexes such as peak signal-to-noise ratio, structural similarity index, feature similarity index, and information entropy of video image synthesis, evaluates the synthesis effect of video images, judges whether the video image synthesis needs to be optimized, and performs corresponding processing, thereby realizing the intelligent synthesis of video images, improving the efficiency of video image synthesis, and ensuring the quality of video image synthesis.

Description

Technical Field

[0001] The present invention relates to the field of video image synthesis, and relates to an intelligent video image synthesis method based on artificial intelligence. Background Art

[0002] With the progress of artificial intelligence technology, the maturity of computer vision technology, and the improvement of hardware performance, powerful technical support is provided for intelligent video image synthesis. The intelligent video image synthesis technology has developed rapidly and has been widely applied in the film and television entertainment industry, advertising and marketing industry, social media, education and training industry, etc. It not only greatly improves the creation efficiency and quality but also reduces the production cost, which is conducive to promoting the development of related industries.

[0003] However, the existing intelligent video image synthesis technology still has some limitations and deficiencies in practical applications.

[0004] For example, the Chinese patent with the publication number CN114071155A discloses an artificial intelligence processing method and system, including a video upload module, a video decoding module, an image extraction module, a character image extraction module, a clarity enhancement module, an image beautification module, an image synthesis module, a background material selection module, and a video generation module. The video upload module is connected to the video decoding module, the video decoding module is connected to the image extraction module, the image extraction module is connected to the character image extraction module, the character image extraction module is connected to the clarity enhancement module, the clarity enhancement module is connected to the image beautification module, the image beautification module is connected to the image synthesis module, and the image synthesis module is respectively connected to the background material selection module and the video generation module. This invention can facilitate the processing of character images and backgrounds, and can adjust and beautify the clarity of images. Compared with manual image processing, it saves time and effort.

[0005] However, the above patent has the following problems: 1. Different types of artificial intelligence models have different advantages and limitations in synthesizing video images. Selecting a suitable artificial intelligence model is crucial for the synthesis effect of video images. When synthesizing video images through artificial intelligence in the above patent, the artificial intelligence model for video image synthesis is not screened, which may lead to low adaptability of the artificial intelligence model for video image synthesis, thus affecting the synthesis effect of video images.

[0006] 2. After the video image synthesis in the above patent, the synthesis effect of the video image is not detected and evaluated, and an optimization scheme for video image synthesis is not further obtained, so the quality of video image synthesis cannot be better guaranteed. Summary of the Invention

[0007] In view of the above problems, the present invention proposes an intelligent video image synthesis method based on artificial intelligence, and the specific technical solution is as follows: An intelligent video image synthesis method based on artificial intelligence, comprising the following steps: Step 1, video image data acquisition and preprocessing: Collect the video image data to be synthesized and perform preprocessing.

[0008] Step 2, selection of artificial intelligence models for video image synthesis: Obtain the data volume and diversification degree of the video image data to be synthesized, as well as the target and requirement information of the video image synthesis task, where the target and requirement information includes video style, content type, synthesis complexity, and synthesis accuracy, and obtain the attribute information of each artificial intelligence model for video image synthesis, where the attribute information includes the level of computing resource requirements and inference speed, analyze the matching index of each artificial intelligence model for video image synthesis, and screen the suitable artificial intelligence model for video image synthesis.

[0009] Step 3, analysis and setting of video image synthesis parameters: According to the target and requirement information of the video image synthesis task and the suitable artificial intelligence model for video image synthesis, analyze the appropriate basic parameters for video image synthesis, where the basic parameters include resolution, frame rate, color space, contrast, brightness, saturation, transparency, and further set the basic parameters for video image synthesis.

[0010] Step 4, detection and evaluation of video image synthesis effect: Detect the effect indicators of video image synthesis, where the effect indicators include peak signal-to-noise ratio, structural similarity index, feature similarity index, and information entropy, and analyze the effect evaluation index of video image synthesis.

[0011] Step 5, judgment and processing of video image synthesis optimization requirements: According to the effect evaluation index of video image synthesis, judge whether video image synthesis needs to be optimized and perform corresponding processing.

[0012] Compared with the prior art, the intelligent video image synthesis method based on artificial intelligence of the present invention has the following beneficial effects: 1. By obtaining the data volume and diversification degree of the video image to be synthesized, the target and requirement information of the video image synthesis task, and the attribute information of each artificial intelligence model for video image synthesis, and then screening the suitable artificial intelligence model for video image synthesis, the matching degree of the artificial intelligence model for video image synthesis can be improved, thereby enhancing the synthesis effect of video images.

[0013] 2. By detecting indicators such as peak signal-to-noise ratio, structural similarity index, feature similarity index, and information entropy of video image synthesis, evaluating the effect of video image synthesis, judging whether video image synthesis needs to be optimized, and performing corresponding processing, the quality of video image synthesis can be better guaranteed. Description of the Drawings

[0014] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0015] Figure 1 It is a schematic flowchart of the method of the present invention.

[0016] Figure 2 It is a structural block diagram of the artificial intelligence model for selecting video image synthesis of the present invention.

[0017] Figure 3 It is a structural block diagram of evaluating the video image synthesis effect of the present invention. Specific embodiments

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0019] Please refer to Figure 1 As shown, an artificial intelligence-based video image intelligent synthesis method provided by the present invention includes the following steps: Step 1, video image data collection and preprocessing: Collect the video image data to be synthesized and perform preprocessing.

[0020] In a specific embodiment, the video image data to be synthesized includes images under different scenarios, different themes, and different lighting conditions.

[0021] It should be noted that preprocessing the video image data to be synthesized includes operations such as image cropping, scaling, and normalization to ensure the consistency and usability of the data. At the same time, the video image data to be synthesized can also be denoised, enhanced, etc. to improve the image quality.

[0022] Step 2, selection of the artificial intelligence model for video image synthesis: Obtain the data volume and diversification degree of the video image data to be synthesized, as well as the target and requirement information of the video image synthesis task, where the target and requirement information includes video style, content type, synthesis complexity, and synthesis accuracy, and obtain the attribute information of each artificial intelligence model for video image synthesis, where the attribute information includes the calculation resource requirement level and inference speed, analyze the matching index of each artificial intelligence model for video image synthesis, and screen the suitable artificial intelligence model for video image synthesis.

[0023] As a preferred solution, refer to Figure 2 As shown, the specific analysis process of the second step includes: obtaining the cumulative data volume of the video image data to be synthesized.

[0024] It should be noted that the cumulative data volume of the video image data to be synthesized can be measured by indicators such as bit rate, file size, and number of pixels.

[0025] Obtain the number of scene transformations, the number of changes in lighting conditions, and the number of changes in shooting angles of the video image data to be synthesized, and substitute them into the relationship function between the number of scene transformations, the number of changes in lighting conditions, the number of changes in shooting angles, and the degree of diversity of the video image data to obtain the degree of diversity of the video image data to be synthesized.

[0026] It should be noted that the more the number of scene transformations, the more the number of changes in lighting conditions, and the more the number of changes in shooting angles, the higher the degree of diversity of the video image data.

[0027] Extract the data volume range and the degree of diversity range of the video image data acceptable to each artificial intelligence model for video image synthesis stored in the database.

[0028] It should be noted that the data volume range and the degree of diversity range of the video image data acceptable to each artificial intelligence model for video image synthesis stored in the database are obtained by summarizing and analyzing the information of the historical synthesized video images of each artificial intelligence model for video image synthesis.

[0029] It should be noted that when selecting an artificial intelligence model for video image synthesis, the adaptability of the artificial intelligence model to the diversity of video image data should be considered. Some models with strong generalization ability, such as models based on the Transformer architecture, can better process diverse video image data.

[0030] If the cumulative data volume of the video image data to be synthesized belongs to the data volume range of the video image data acceptable to a certain artificial intelligence model, then the data volume of the video image data acceptable to this artificial intelligence model meets the requirements; otherwise, the data volume of the video image data acceptable to this artificial intelligence model does not meet the requirements. Set the compliance coefficients corresponding to the data volume of the video image data acceptable to the artificial intelligence model meeting the requirements and not meeting the requirements, and screen to obtain the compliance coefficients of the data volume of the video image data acceptable to each artificial intelligence model for video image synthesis, and denote it as δ i , where i represents the number of the i-th artificial intelligence model for video image synthesis, and i = 1, 2,..., n.

[0031] In a specific embodiment, when the amount of video image data acceptable to the artificial intelligence model meets the requirements, the compliance coefficient of the amount of video image data acceptable to the artificial intelligence model is 1, and when the amount of video image data acceptable to the artificial intelligence model does not meet the requirements, the compliance coefficient of the amount of video image data acceptable to the artificial intelligence model is 0.

[0032] If the degree of diversity of the video image data to be synthesized falls within the range of the degree of diversity of the video image data acceptable to a certain artificial intelligence model for video image synthesis, then the degree of diversity of the video image data acceptable to the artificial intelligence model meets the requirements; otherwise, the degree of diversity of the video image data acceptable to the artificial intelligence model does not meet the requirements. Set the compliance coefficients of the degree of diversity of the video image data acceptable to the artificial intelligence model corresponding to meeting and not meeting the requirements, and screen to obtain the compliance coefficients of the degree of diversity of the video image data acceptable to each artificial intelligence model for video image synthesis, and denote it as ε. i 。

[0033] In a specific embodiment, when the degree of diversity of the video image data acceptable to the artificial intelligence model meets the requirements, the compliance coefficient of the degree of diversity of the video image data acceptable to the artificial intelligence model is 1, and when the degree of diversity of the video image data acceptable to the artificial intelligence model does not meet the requirements, the compliance coefficient of the degree of diversity of the video image data acceptable to the artificial intelligence model is 0.

[0034] By analyzing the formula obtain the first matching index of each artificial intelligence model for video image synthesis where γ 1 represents a correction factor for the preset first matching index, and β 1 , β 2 respectively represent the weights of the compliance coefficient of the acceptable video image data amount and the compliance coefficient of the acceptable video image diversity degree, and β 1 +β 2 =1.

[0035] It should be noted that the setting of the weights of the compliance coefficient of the acceptable video image data amount and the compliance coefficient of the acceptable video image diversity degree is based on the importance of the acceptable video image data amount and the acceptable video image diversity degree of the artificial intelligence model when selecting the artificial intelligence model for video image synthesis. In a specific embodiment, the weights of the compliance coefficient of the acceptable video image data amount and the compliance coefficient of the acceptable video image diversity degree are 0.6 and 0.4 respectively.

[0036] As a preferred solution, the specific analysis process of step two further includes: obtaining the video style, content type, synthesis complexity, and synthesis accuracy of the video image synthesis task.

[0037] It should be noted that the video style, content type, synthesis complexity, and synthesis accuracy of the video image synthesis task are obtained through the user's input information.

[0038] In another specific embodiment, the video image to be synthesized is recognized and compared with the feature elements corresponding to each video style and the feature elements corresponding to each content type stored in the database respectively, so as to obtain the video style and content type of the video image synthesis task.

[0039] Extract the matching factors between each artificial intelligence model for video image synthesis stored in the database and various video styles, and the matching factors between each artificial intelligence model and each content type, and screen to obtain the matching factors between each artificial intelligence model for video image synthesis and the video style and content type of the video image synthesis task, and record them respectively as

[0040] In a specific embodiment, if it is necessary to synthesize a video with a specific artistic style, such as oil painting style, watercolor style, or cartoon style, etc., a style transfer model can be considered. For example, a style transfer algorithm based on deep learning can apply one artistic style to the original video image to achieve a unique visual effect.

[0041] In a specific embodiment, if the synthesis task has very high requirements for details and accuracy, such as the synthesis of medical images and the processing of satellite images, etc., an artificial intelligence model with high-resolution processing ability and precise modeling ability can be selected. For example, a deep model based on a convolutional neural network can effectively extract the features of the image and precisely model the details of the image.

[0042] Extract the acceptable complexity threshold and the achievable accuracy threshold of each artificial intelligence model for video image synthesis stored in the database.

[0043] If the synthesis complexity of the video image synthesis task is less than or equal to the acceptable complexity threshold of a certain artificial intelligence model for video image synthesis, then the acceptable complexity of this artificial intelligence model meets the requirements. Otherwise, the acceptable complexity of this artificial intelligence model does not meet the requirements. Set the acceptable complexity compliance coefficients corresponding to the cases where the acceptable complexity of the artificial intelligence model meets and does not meet the requirements, screen to obtain the acceptable complexity compliance coefficients of each artificial intelligence model for video image synthesis, and record them as

[0044] In a specific embodiment, the acceptable complexity compliance coefficients corresponding to the cases where the acceptable complexity of the artificial intelligence model meets and does not meet the requirements are 1 and 0 respectively.

[0045] If the synthesis accuracy of the video image synthesis task is less than or equal to the accuracy threshold that an artificial intelligence model for video image synthesis can achieve, then the accuracy of the artificial intelligence model meets the requirements; otherwise, the accuracy of the artificial intelligence model does not meet the requirements. Set the accuracy compliance coefficients corresponding to the artificial intelligence model meeting the requirements and not meeting the requirements, screen to obtain the accuracy compliance coefficients of each artificial intelligence model for video image synthesis, and denote them as

[0046] In a specific embodiment, the accuracy compliance coefficients corresponding to the artificial intelligence model meeting the requirements and not meeting the requirements are 1 and 0 respectively.

[0047] By analyzing the formula obtain the second matching index of each artificial intelligence model for video image synthesis where γ 2 represents the correction factor of the preset second matching index, e represents the natural constant, η 1 、η 2 、η 3 、η 4 respectively represent the weights of the preset video style matching factor, content type matching factor, acceptable complexity compliance coefficient, and accuracy compliance coefficient, and η 1 +η 2 +η 3 +η 4 = 1.

[0048] It should be noted that the setting of the weights of the video style matching factor, content type matching factor, acceptable complexity compliance coefficient, and accuracy compliance coefficient is based on the matching degree between the artificial intelligence model and the video style and content type of the video image synthesis task when selecting the artificial intelligence model for video image synthesis, as well as the importance of the acceptable complexity and accuracy of the artificial intelligence model. In a specific embodiment, the weights of the video style matching factor, content type matching factor, acceptable complexity compliance coefficient, and accuracy compliance coefficient are 0.2, 0.2, 0.3, and 0.3 respectively.

[0049] As a preferred solution, the specific analysis process of the second step further includes: extracting the attribute information of each artificial intelligence model for video image synthesis stored in the database to obtain the calculation resource requirement level and inference speed of each artificial intelligence model for video image synthesis.

[0050] Obtain the computing resource level that the video image synthesis device can provide. If the computing resource requirement level of a certain artificial intelligence model for video image synthesis is equal to or lower than the computing resource level that the video image synthesis device can provide, then the computing resource requirement of this artificial intelligence model can be met. Otherwise, the computing resource requirement of this artificial intelligence model cannot be met. Set the computing resource requirement compliance coefficients corresponding to the satisfied and unsatisfied computing resource requirements of the artificial intelligence model, screen to obtain the computing resource requirement compliance coefficients of each artificial intelligence model for video image synthesis, and denote it as κ i 。

[0051] In a specific embodiment, the computing resource requirement compliance coefficients corresponding to the satisfied and unsatisfied computing resource requirements of the artificial intelligence model are 1 and 0 respectively.

[0052] It should be noted that different artificial intelligence models for video image synthesis have different computing resource requirements during training and inference. Some complex artificial intelligence models for video image synthesis, such as deep neural network models, require a large amount of computing power and memory resources.

[0053] Denote the inference speed of each artificial intelligence model for video image synthesis as v i 。

[0054] It should be noted that for some application scenarios that require real-time synthesis, the inference time of the artificial intelligence model for video image synthesis is very important. If the inference speed of the artificial intelligence model for video image synthesis is too slow, it will cause delays in the synthesized video and affect the user experience.

[0055] Through analyzing the formula obtain the third matching index of each artificial intelligence model for video image synthesis where γ 3 represents the correction factor of the preset third matching index, and λ 1 , λ 2 respectively represent the preset weights of the computing resource requirement compliance coefficient and the inference speed, and λ 1 + λ 2 = 1, and n represents the number of artificial intelligence models for video image synthesis.

[0056] It should be noted that the setting of the weights of the computing resource requirement compliance coefficient and the inference speed is based on whether the computing resource requirement of the artificial intelligence model can be met when selecting the artificial intelligence model for video image synthesis and the importance of the inference speed of the artificial intelligence model. In a specific embodiment, the weights of the computing resource requirement compliance coefficient and the inference speed are 0.7 and 0.3 respectively.

[0057] As a preferred solution, the specific analysis process of the second step further includes: the first matching indices of each artificial intelligence model for video image synthesis Second matching index Third matching index Substitute into the analysis formula Obtain the matching indices of each artificial intelligence model for video image synthesis where μ 1 、μ 2 、μ 3 respectively represent the weights of the preset first matching index, second matching index, and third matching index, and μ 1 +μ 2 +μ 3 = 1.

[0058] In a specific embodiment, the weights of the first matching index, second matching index, and third matching index are 0.3, 0.35, and 0.35 respectively.

[0059] As a preferred solution, the specific analysis process of the second step further includes: comparing the matching indices of each artificial intelligence model for video image synthesis with each other, and taking the artificial intelligence model corresponding to the maximum matching index as the adapted artificial intelligence model for video image synthesis.

[0060] It should be noted that different types of artificial intelligence models have different advantages and limitations in synthesizing video images. For example, generative adversarial networks perform well in generating realistic images but may have problems with unstable training; variational autoencoders are relatively stable, but the synthesized images may not be clear enough. Therefore, selecting a suitable artificial intelligence model for video image synthesis is crucial for the synthesis effect of video images.

[0061] It should be noted that each artificial intelligence model for video image synthesis includes but is not limited to: generative adversarial networks, diffusion models, variational autoencoders, Transformer models, deep learning-based style transfer models, etc.

[0062] In this embodiment, the present invention can improve the matching degree of the artificial intelligence model for video image synthesis and thus enhance the synthesis effect of video images by obtaining the data volume and diversification degree of the video image to be synthesized, the target and requirement information of the video image synthesis task, and the attribute information of each artificial intelligence model for video image synthesis, and then screening the adapted artificial intelligence model for video image synthesis.

[0063] Step 3. Analysis and setting of video image synthesis parameters: Analyze the appropriate basic parameters for video image synthesis according to the goals and requirement information of the video image synthesis task and the adapted artificial intelligence model for video image synthesis. The basic parameters include resolution, frame rate, color space, contrast, brightness, saturation, and transparency, and further set the basic parameters for video image synthesis.

[0064] As a preferred solution, the specific analysis process of Step 3 is as follows: Extract the case information of historical video image synthesis stored in the database, obtain the goals and requirement information, selected artificial intelligence models, and basic parameters of video image synthesis for each historical video image synthesis case. Use machine learning algorithms to train and obtain a basic parameter analysis model for video image synthesis. Substitute the goals and requirement information of the video image synthesis task and the adapted artificial intelligence model for video image synthesis into the basic parameter analysis model for video image synthesis to obtain the appropriate basic parameters for video image synthesis. The basic parameters include resolution, frame rate, color space, contrast, brightness, saturation, and transparency, and further set the basic parameters for video image synthesis.

[0065] Step 4. Detection and evaluation of video image synthesis effects: Detect the effect indicators of video image synthesis. The effect indicators include peak signal-to-noise ratio, structural similarity index, feature similarity index, and information entropy, and analyze the effect evaluation index of video image synthesis.

[0066] As a preferred solution, refer to Figure 3 As shown, the specific analysis process of Step 4 includes: Detect the synthesized video image, obtain the peak signal-to-noise ratio, structural similarity index, feature similarity index, and information entropy of video image synthesis, and denote them as σ P 、σ S 、σ F 、σ I .

[0067] It should be noted that the acquisition methods of the peak signal-to-noise ratio, structural similarity index, feature similarity index, and information entropy are existing and relatively mature technologies, and will not be elaborated here.

[0068] It should be noted that the peak signal-to-noise ratio is an image quality evaluation index based on the error between corresponding pixel points, that is, based on error sensitivity. Generally speaking, the higher the value of the peak signal-to-noise ratio, the smaller the difference between the synthesized image and the original image, and the better the synthesis effect.

[0069] It should be noted that the structural similarity index consists of three parts: luminance contrast, contrast contrast, and structural contrast. By comparing the similarities between the synthesized image and the original image in these three aspects, a value between 0 and 1 is obtained. The closer the value of the structural similarity index is to 1, the higher the structural similarity between the synthesized image and the original image, and the better the synthesis effect.

[0070] It should be noted that the feature similarity index measures the similarity between the synthesized image and the original image based on features such as the phase consistency and gradient magnitude of the image. The higher the value of the feature similarity index, the better the synthesis effect.

[0071] It should be noted that information entropy is used to measure the richness of information in an image. The larger the information entropy, the richer the information contained in the image, and the better the synthesis effect.

[0072] As a preferred solution, the specific analysis process of step four further includes: substituting the peak signal-to-noise ratio σ P , structural similarity index σ S , feature similarity index σ F , and information entropy σ I of the video image synthesis into the analysis formula to obtain the effect evaluation index ξ of the video image synthesis, where ψ 1 , ψ 2 , ψ 3 , ψ 4 respectively represent the preset weights of the peak signal-to-noise ratio, structural similarity index, feature similarity index, and information entropy, and ψ 1 + ψ 2 + ψ 3 + ψ 4 = 1.

[0073] In a specific embodiment, the weights of the peak signal-to-noise ratio, structural similarity index, feature similarity index, and information entropy are 0.25, 0.25, 0.25, and 0.25 respectively.

[0074] Step five: Judgment and processing of the optimization requirements for video image synthesis: According to the effect evaluation index of the video image synthesis, judge whether the video image synthesis needs to be optimized and perform corresponding processing.

[0075] As a preferred solution, the specific analysis process of step five is: comparing the effect evaluation index of the video image synthesis with the preset effect evaluation index threshold. If the effect evaluation index of the video image synthesis is less than the preset effect evaluation index threshold, then the video image synthesis needs to be optimized, obtain the optimization scheme for the video image synthesis, and give feedback.

[0076] It should be noted that an optimized solution for video image synthesis can be obtained by adjusting the parameters of the artificial intelligence model for video image synthesis, improving the synthesis strategy, increasing the data volume, etc.

[0077] In this embodiment, the present invention evaluates the effect of video image synthesis by detecting indicators such as the peak signal-to-noise ratio, structural similarity index, feature similarity index, and information entropy of video image synthesis, determines whether video image synthesis needs to be optimized, and performs corresponding processing, which can better guarantee the quality of video image synthesis.

[0078] The above content is only an example and illustration of the concept of the present invention. Those skilled in the art of the present technology can make various modifications or supplements to the described specific embodiments or use similar methods for substitution, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should fall within the protection scope of the present invention.

Claims

1. A video image intelligent synthesis method based on artificial intelligence, characterized in that: The steps include: Step 1: Video image data acquisition and preprocessing: Acquire the video image data to be synthesized and perform preprocessing; Step 2: Selection of artificial intelligence models for video image synthesis: obtaining the amount and diversity of the video image data to be synthesized, as well as the objectives and requirements of the video image synthesis task, where the objectives and requirements include video style, content type, synthesis complexity, and synthesis accuracy, and obtaining the attribute information of each artificial intelligence model for video image synthesis, where the attribute information includes the computing resource requirement level and inference speed, analyzing the matching index of each artificial intelligence model for video image synthesis, and screening the adapted artificial intelligence model for video image synthesis; The accumulated data volume and diversity of the video image data to be synthesized are obtained, and compared with the data volume range and diversity range of the video image data acceptable to each artificial intelligence model for video image synthesis stored in the database to determine whether the data volume and diversity of the video image data acceptable to each artificial intelligence model meet the requirements. According to the judgment results, the compliance coefficient of the acceptable video image data volume and the compliance coefficient of the acceptable video image diversity degree of each artificial intelligence model for video image synthesis are obtained by screening, and are recorded as , ; pass and Analyze and obtain the first matching index of each artificial intelligence model for video image synthesis , The first The number of the AI ​​model, ; The video style and content type of the video image synthesis task are obtained, and the matching factors of each artificial intelligence model of video image synthesis and various video styles and the matching factors of each content type stored in the database are extracted. The matching factors of each artificial intelligence model of video image synthesis and the video style and content type of the video image synthesis task are screened and recorded as , ; Obtain the synthesis complexity and synthesis accuracy of the video image synthesis task, and extract the acceptable complexity threshold and achievable accuracy threshold of each artificial intelligence model of video image synthesis stored in the database, and judge whether the acceptable complexity and accuracy of each artificial intelligence model meet the requirements. According to the judgment results, screen the acceptable complexity compliance coefficient and accuracy compliance coefficient of each artificial intelligence model of video image synthesis, and record them as , ; pass , , as well as Analyze and obtain the second matching index of each artificial intelligence model for video image synthesis ; Obtain the computing resource requirement level of each artificial intelligence model for video image synthesis, and compare it with the computing resource level that can be provided by the video image synthesis device to determine whether the computing resource requirements of each artificial intelligence model can be met. According to the judgment result, select the computing resource requirement compliance coefficient of each artificial intelligence model for video image synthesis and record it as ; And obtain the inference speed of each artificial intelligence model for video image synthesis, which is recorded as ; pass and Analyze and obtain the third matching index of each artificial intelligence model for video image synthesis ; The first matching index of each artificial intelligence model synthesized from video images , the second matching index , the third matching index Substitute into the analysis formula Get the matching index of each artificial intelligence model for video image synthesis ,in Respectively represent the weights of the preset first matching index, second matching index, and third matching index, ; Step 3: Analyze and set video image synthesis parameters: According to the objectives and requirements of the video image synthesis task and the adapted artificial intelligence model of video image synthesis, analyze the basic parameters suitable for video image synthesis, where the basic parameters include resolution, frame rate, color space, contrast, brightness, saturation, and transparency, and further set the basic parameters of video image synthesis; Step 4: Video image synthesis effect detection and evaluation: Detect the effect index of video image synthesis, where the effect index includes peak signal-to-noise ratio, structural similarity index, feature similarity index, information entropy, and analyze the effect evaluation index of video image synthesis; Step 5: Determine and process the optimization needs of video image synthesis: Determine whether the video image synthesis needs to be optimized based on the effect evaluation index of the video image synthesis, and perform corresponding processing.

2. The method for intelligent synthesis of video images based on artificial intelligence according to claim 1, characterized in that: The specific analysis process of step 2 includes: Obtaining the accumulated data volume of the video image data to be synthesized; Obtain the number of scene changes, the number of lighting condition changes, and the number of shooting angle changes of the video image data to be synthesized, and substitute them into a preset relationship function between the number of scene changes, the number of lighting condition changes, the number of shooting angle changes, and the degree of diversity of the video image data to obtain the degree of diversity of the video image data to be synthesized; Extract the data volume range and diversity range of video image data acceptable to each artificial intelligence model for video image synthesis stored in the database; If the cumulative data volume of the video image data to be synthesized falls within the data volume range of video image data acceptable to a certain artificial intelligence model, then the data volume of video image data acceptable to the artificial intelligence model meets the requirements; otherwise, the data volume of video image data acceptable to the artificial intelligence model does not meet the requirements. The compliance coefficients of the video image data volumes acceptable to the artificial intelligence model corresponding to the data volumes of video image data acceptable to the artificial intelligence model that meet the requirements and do not meet the requirements are set, and the compliance coefficients of the video image data volumes acceptable to each artificial intelligence model for video image synthesis are screened and recorded as , The first The number of the AI ​​model, ; If the diversity degree of the video image data to be synthesized falls within the range of the diversity degree of video image data acceptable to a certain artificial intelligence model for video image synthesis, then the diversity degree of video image data acceptable to the artificial intelligence model meets the requirements; otherwise, the diversity degree of video image data acceptable to the artificial intelligence model does not meet the requirements. The compliance coefficients of the diversity degree of video images acceptable to the artificial intelligence model corresponding to the diversity degree of video image data acceptable to the artificial intelligence model that meets the requirements and does not meet the requirements are set, and the compliance coefficients of the diversity degree of video images acceptable to each artificial intelligence model for video image synthesis are screened and recorded as ; By analyzing the formula Get the first matching index of each artificial intelligence model for video image synthesis ,in represents a correction factor of the preset first matching index, They respectively represent the weights of the preset acceptable video image data volume compliance coefficient and the acceptable video image diversity compliance coefficient, .

3. The method for intelligent synthesis of video images based on artificial intelligence according to claim 2, characterized in that: The specific analysis process of step 2 also includes: Obtain the video style, content type, synthesis complexity and synthesis accuracy of the video image synthesis task; Extract the matching factors of each artificial intelligence model for video image synthesis and various video styles and the matching factors of each artificial intelligence model and each content type stored in the database, screen and obtain the matching factors of each artificial intelligence model for video image synthesis and the video style and content type of the video image synthesis task, and record them as , ; Extract the acceptable complexity threshold and achievable accuracy threshold of each artificial intelligence model for video image synthesis stored in the database; If the synthesis complexity of the video image synthesis task is less than or equal to the acceptable complexity threshold of a certain artificial intelligence model for video image synthesis, then the acceptable complexity of the artificial intelligence model meets the requirements; otherwise, the acceptable complexity of the artificial intelligence model does not meet the requirements. The acceptable complexity compliance coefficients corresponding to the acceptable complexity of the artificial intelligence model that meets the requirements and does not meet the requirements are set, and the acceptable complexity compliance coefficients of each artificial intelligence model for video image synthesis are screened and recorded as ; If the synthesis accuracy of the video image synthesis task is less than or equal to the accuracy threshold of a certain artificial intelligence model for video image synthesis, then the accuracy of the artificial intelligence model meets the requirements; otherwise, the accuracy of the artificial intelligence model does not meet the requirements. The accuracy compliance coefficients corresponding to the accuracy of the artificial intelligence model that meets the requirements and does not meet the requirements are set, and the accuracy compliance coefficients of each artificial intelligence model for video image synthesis are screened and recorded as ; By analyzing the formula Get the second matching index of each artificial intelligence model for video image synthesis ,in represents a correction factor of the preset second matching index, represents a natural constant, They represent the weights of the preset video style matching factor, content type matching factor, acceptable complexity matching coefficient, and accuracy matching coefficient, respectively. .

4. The method for intelligent synthesis of video images based on artificial intelligence according to claim 3, characterized in that: The specific analysis process of step 2 also includes: Extracting attribute information of each artificial intelligence model for video image synthesis stored in the database, and obtaining the computing resource requirement level and reasoning speed of each artificial intelligence model for video image synthesis; Obtain the computing resource level that the video image synthesis device can provide. If the computing resource requirement level of a certain artificial intelligence model of video image synthesis is equal to or lower than the computing resource level that the video image synthesis device can provide, then the computing resource requirement of the artificial intelligence model can be met. Otherwise, the computing resource requirement of the artificial intelligence model cannot be met. Set the computing resource requirement compliance coefficient of the artificial intelligence model corresponding to the computing resource requirement that can be met and cannot be met. Filter and obtain the computing resource requirement compliance coefficient of each artificial intelligence model of video image synthesis, and record it as ; The inference speed of each artificial intelligence model for video image synthesis is recorded as ; By analyzing the formula Get the third matching index of each artificial intelligence model for video image synthesis ,in represents the correction factor of the preset third matching index, They represent the preset computing resource requirements and the weights of the inference speed, respectively. , Represents the number of AI models for video image synthesis.

5. The method for intelligent synthesis of video images based on artificial intelligence according to claim 1, characterized in that: The specific analysis process of step 2 also includes: The matching indexes of the various artificial intelligence models for video image synthesis are compared with each other, and the artificial intelligence model corresponding to the maximum matching index is used as the adapted artificial intelligence model for video image synthesis.

6. The method for intelligent synthesis of video images based on artificial intelligence according to claim 1, characterized in that: The specific analysis process of step three is as follows: Extract the case information of historical video image synthesis stored in the database, obtain the goals and demand information of each historical video image synthesis case, the selected artificial intelligence model and the basic parameters of video image synthesis, use the machine learning algorithm to train and obtain the basic parameter analysis model of video image synthesis, substitute the goals and demand information of the video image synthesis task and the adapted artificial intelligence model of video image synthesis into the basic parameter analysis model of video image synthesis, and obtain the appropriate basic parameters for video image synthesis, where the basic parameters include resolution, frame rate, color space, contrast, brightness, saturation, and transparency, and further set the basic parameters of video image synthesis.

7. The method for intelligent synthesis of video images based on artificial intelligence according to claim 1, characterized in that: The specific analysis process of step 4 includes: The synthesized video image is detected to obtain the peak signal-to-noise ratio, structural similarity index, feature similarity index, and information entropy of the video image synthesis, which are recorded as .

8. The method for intelligent synthesis of video images based on artificial intelligence according to claim 7, characterized in that: The specific analysis process of step 4 also includes: Peak signal-to-noise ratio of video images , structural similarity index , feature similarity index , Information Entropy Substitute into the analysis formula Get the effect evaluation index of video image synthesis ,in They represent the preset peak signal-to-noise ratio, structural similarity index, feature similarity index, and information entropy weights respectively. .

9. The method for intelligent synthesis of video images based on artificial intelligence according to claim 1, characterized in that: The specific analysis process of step 5 is as follows: The effect evaluation index of the video image synthesis is compared with the preset effect evaluation index threshold. If the effect evaluation index of the video image synthesis is less than the preset effect evaluation index threshold, the video image synthesis needs to be optimized, and the optimization plan of the video image synthesis is obtained and feedback is given.

Images