AIGC-based interactive intelligent content generation method and system

Abstract

The invention relates to the technical field of artificial intelligence, and particularly discloses an interactive intelligent content generation method and system based on AIGC. The method comprises the steps that a user editing instruction is collected and analyzed to obtain a first semantic body, and meanwhile a target change vector is extracted; performing connectivity analysis on the high-response pixel points to determine a candidate linkage area; obtaining a candidate linkage area, judging whether a physical shielding or self-shielding effect exists or not, and screening an effective response area; performing attenuation correction on the target change vector, and deriving a collaborative mapping parameter; and constructing a light and shadow guide matrix based on the collaborative mapping parameters, and performing directional guide processing on the effective response area. The system comprises an intention analysis module, a communication analysis module, a region screening module, an attenuation correction module and a synchronous rendering module. According to the invention, synchronous rendering of semantic subject change and ambient light and shadow effects can be realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to an interactive intelligent content generation method and system based on AIGC. BACKGROUND

[0002] With the rapid development of artificial intelligence generated content (AIGC) technology, existing image editing tools usually allow users to replace colors, migrate styles or redraw parts of specific targets in images through natural language instructions, reducing the threshold of professional image processing and enabling non-professional users to quickly produce high-quality visual content.

[0003] However, the existing AIGC generation algorithm has the technical defect of disconnection between semantic changes and physical environment. Most mainstream models are based on statistical prediction of two-dimensional pixel features, lacking explicit perception of three-dimensional spatial structure and physical optical propagation laws. For example, when a user modifies a certain subject in an image to a highlight or a specific color of a light-emitting material through an instruction, traditional algorithms often only change the pixel value of the object itself, ignoring the diffuse reflection, mirror mapping and light attenuation effects that the light-emitting body should have on the surrounding environment, often incorrectly generating unreasonable light influence effects in the occluded area.

[0004] The lack of physical logic often results in generated images that have a clear map or collage feel, with the light and shadow relationship between the subject and the environment being fragmented, which destroys the overall realism and immersion of the image and cannot meet the design requirements of film or professional level; in addition, in order to correct these undesirable light and shadow errors, designers often need to use traditional graphics software for tedious post-processing manual repair, which weakens the automation and efficiency advantages that AIGC technology should have.

[0005] Therefore, the present application provides an interactive intelligent content generation method and system based on AIGC. SUMMARY

[0006] The present application aims to provide an interactive intelligent content generation method and system based on AIGC to solve the above background problems.

[0007] The purpose of the present application can be achieved by the following technical solutions: An interactive intelligent content generation method based on AIGC, comprising the following steps: Obtain the first semantic subject as an index and establish an attention weight matrix of the whole image; filter high-response pixel points based on the attention weight matrix, and perform connectivity analysis on the high-response pixel points to determine a candidate linkage area; Obtain spatial structure information of the candidate linkage region, construct light path geometry checking logic based on the spatial structure information, and determine whether there is physical occlusion or self-occlusion effect between the first semantic subject and the candidate linkage region, and if so, filter the effective response region; Extract image statistical features of the first semantic subject and perform color semantic change processing to obtain a target change vector; Perform spatial distance attenuation analysis on the target change vector based on the spatial position distribution of the effective response region to obtain a basic attenuation coefficient; obtain the material scattering correction of the basic attenuation coefficient based on the image statistical features, and deduce the collaborative mapping parameters of the effective response region; Construct a light and shadow guide matrix based on the collaborative mapping parameters, and perform directional guide processing on the effective response region based on the light and shadow guide matrix to realize synchronous rendering of the first semantic subject and the effective response region.

[0008] Further, the first semantic subject is obtained in the following manner: Collect user editing instructions for the target image and perform intent analysis to obtain the first semantic subject in the target image.

[0009] Further, the intent analysis is performed in the following manner: Extract keywords from the user editing instructions through a multi-modal semantic understanding unit preset in an AIGC large model to identify the action subject in the instructions; Establish a text embedding vector of the user editing instructions based on the action subject; Simultaneously call a visual segmentation large model to perform panoramic segmentation on the target image to obtain the mask region of all independent objects in the image; Establish an image embedding vector based on the mask region of the independent objects; Match the text embedding vector of the action subject with the image embedding vectors of all independent objects for cosine similarity, select the mask region with the highest similarity score, and define it as the first semantic subject.

[0010] Further, the connectivity analysis is performed in the following manner: Establish a heat map of full-image attention for weight zeroing screening, and establish a discrete high-response point set based on the screening result; Perform spatial clustering on the discrete high-response point set using a density clustering algorithm, and establish a candidate linkage region based on the spatial clustering result.

[0011] Further, the determination of whether there is physical occlusion or self-occlusion effect is performed in the following manner: Each pixel point in the candidate linkage region is taken as a target check point; Obtain a three-dimensional surface normal map and a light propagation vector; Extracting the corresponding unit normal vector of the target checkpoint in the three-dimensional surface normal map, performing a normal angle-based reflection consistency check on the target checkpoint, and removing the target checkpoint with self-occlusion effect; Performing re-projection processing on the light propagation vector to obtain path sampling points and performing depth difference ratio check to check whether the path sampling points block the light propagation path; and performing removal processing on the target checkpoint based on the check result.

[0012] Further, the process of obtaining the light propagation vector is: Performing feature extraction on the target image to generate a depth-of-field gradient map representing the relative distance of pixels; Meanwhile, a three-dimensional surface normal map is established, and based on the principle of geometric inverse projection, the two-dimensional coordinates of the image plane and the depth values in the depth-of-field gradient map are combined to establish a pseudo-three-dimensional point cloud space; Calculating the geometric center of the mask region corresponding to the first semantic subject in the pseudo-three-dimensional point cloud space as a virtual radiation source point; and establishing a straight line vector from the virtual radiation source point to the target checkpoint in the pseudo-three-dimensional point cloud space as the light propagation vector.

[0013] Further, the depth difference ratio check is performed in the following manner: Reading the pixel value of the position corresponding to the path sampling point from the depth-of-field gradient map as the actual depth; Based on the depth values of the virtual radiation source point and the target checkpoint, calculating the theoretical projection depth of the path sampling point on the light line; If the actual depth is lower than the theoretical projection depth at any path sampling point, it is determined that the position corresponding to the path sampling point is physically blocked by the light propagation path; If there is a physical entity blocking the light propagation path, it is determined that there is physical occlusion between the first semantic subject and the target checkpoint, and the target checkpoint is removed from the candidate linkage region.

[0014] Further, the material scattering correction is performed in the following manner: Extracting the high-frequency texture feature value in the image statistical feature as a detail adjustment factor; Based on the detail adjustment factor, constructing a damping correction logic to perform weighted down-regulation processing on the basic attenuation coefficient to obtain a comprehensive transmission coefficient; Performing product operation on the detail adjustment factor and the scattering sensitivity regulation constant, and performing summation processing on the result of the product operation and the preset reference value to obtain a scattering damping denominator; Calculating the ratio of the basic attenuation coefficient and the scattering damping denominator, and defining the obtained ratio result as a comprehensive transmission coefficient; The vector direction of the target change vector is kept unchanged, the vector module length of the target change vector is scaled and modulated by using the comprehensive conduction coefficient, and a target module length is obtained; The vector is reconstructed based on the vector direction and the target module length, and the reconstructed vector result is defined as a cooperative mapping parameter.

[0015] Further, the manner for obtaining the basic attenuation coefficient is: The spatial Euclidean distance of each pixel point is squared; The result of the squaring operation is dimensionless, and the dimensionless spatial Euclidean distance is summed with a preset light intensity maintenance constant to obtain a distance attenuation denominator; The ratio of the light intensity maintenance constant to the distance attenuation denominator is calculated, and the ratio is defined as the basic attenuation coefficient.

[0016] An interactive intelligent content generation system based on AIGC, comprising the following modules: An intention analysis module: used for collecting editing instructions of a user on a target image and performing intention analysis to obtain a first semantic subject in the target image; image statistical features of the first semantic subject are extracted and color semantic change processing is performed to obtain a target change vector; A connectivity analysis module: used for establishing an attention weight matrix of the whole image with the first semantic subject as an index; high-response pixel points are screened based on the attention weight matrix, and connectivity analysis is performed on the high-response pixel points to determine a candidate linkage region; A region screening module: used for obtaining spatial structure information of the candidate linkage region, constructing a light path geometry checking logic based on the spatial structure information, and determining whether there is a physical occlusion or self-occlusion effect between the first semantic subject and the candidate linkage region, if there is, an effective response region is screened; An attenuation correction module: based on the spatial position distribution of the effective response region, spatial distance attenuation analysis is performed on the target change vector to obtain a basic attenuation coefficient; based on the image statistical features of the first semantic subject, material scattering correction is performed on the basic attenuation coefficient to derive a cooperative mapping parameter of the effective response region; A synchronous rendering module: based on the cooperative mapping parameter, a light and shadow guide matrix is constructed, and directional guide processing is performed on the effective response region based on the light and shadow guide matrix to realize synchronous rendering of the first semantic subject and the effective response region.

[0017] The beneficial effects of the present application are as follows: 1. By adopting the subject positioning strategy combining AIGC semantic understanding and visual segmentation technology, it is beneficial to separate the physical anchor point corresponding to the user's intention from the image background, and when obtaining the target change vector by combining the conversion of the HSV color space and statistical analysis, the brightness distribution variance and high-frequency texture features of the first semantic subject can be retained, so that the original material reflectivity and surface roughness details of the object can be maintained in the subsequent color semantic change process, and the retention degree of the object's intrinsic physical properties in the content generation process is improved.

[0018] 2. The self-attention mechanism of the generative model decoder is used to construct a weight matrix, which can mine the areas in the image that have potential visual association with the first semantic subject, and the DBSCAN density clustering algorithm is used to constrain the discrete high-response point set in space; it is beneficial to filter out the discrete isolated noise points generated in the attention calculation process of the generative model, limit the linkage area within the sheet-shaped range with density connectivity, and thus screen out the potential reflection or lighting affected areas with logical association in the complex background, thereby reducing the false modification rate of non-related background areas in the image generation process.

[0019] 3. By calculating the basic attenuation coefficient and the comprehensive conduction coefficient to modulate the target change vector, the response intensity of the linkage area decreases linearly with the increase of the distance, and decreases with the increase of the material roughness, so that the physical lighting attenuation effect is reproduced in the image generation, and the problem of uniform distribution of light and shadow effect and lack of level in the traditional generation method is improved.

[0020] 4. The light and shadow guide matrix is constructed and used as a bias term to inject into the iterative denoising process, and combined with the structure locking strategy of high-frequency information, it can adjust the color and lighting atmosphere of the effective response area while suppressing the changes of image edge lines and texture particles; by using the directional guide processing method, the first semantic subject and its environmental light and shadow effect are rendered synchronously, which not only realizes the expected visual change, but also maintains the original structure integrity and texture details of the image, solves the structure collapse or texture blur phenomenon that easily occurs in the image redrawing process, and improves the image fusion degree and visual coordination of the finally generated image. BRIEF DESCRIPTION OF DRAWINGS

[0021] The application will be further described below with reference to the accompanying drawings.

[0022] Figure 1 is a flowchart of an interactive intelligent content generation method based on AIGC of the application; Figure 2 is a flowchart for determining the existence of self-occlusion effect; Figure 3 is a functional module diagram of an interactive intelligent content generation system based on AIGC in the application. DETAILED DESCRIPTION

[0023] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below in conjunction with specific embodiments.

[0024] Example 1 like Figure 1 As shown, an interactive intelligent content generation method based on AIGC includes the following steps: S10. Collect user editing instructions for the target image and perform intent parsing to obtain the first semantic subject in the target image; extract the image statistical features of the first semantic subject and perform color semantic change processing to obtain the target change vector; The method for obtaining the first semantic subject in the target image by collecting the user's editing instructions on the target image and parsing the intent is as follows: In some preferred embodiments, the multimodal semantic understanding unit pre-built in the AIGC large model extracts keywords from user editing instructions and identifies the action subject in the instructions; Text embedding vectors for user editing commands are built based on action subjects; Simultaneously, the visual segmentation model is invoked to perform panoramic segmentation on the target image, obtaining the mask regions of all independent objects in the image; Image embedding vectors are established based on the mask regions of independent objects; Those skilled in the art will understand that the text embedding vector is processed by segmenting and serializing the identified action subject, inputting it into the AIGC pre-trained text encoder to extract deep semantic features, and then mapping it to a joint feature space of a preset dimension through a linear projection layer before performing L2 normalization. The image embedding vector is cropped from the target image based on the boundary coordinates of the mask region. After size normalization preprocessing, it is input into the AIGC visual encoder to extract global visual features. Similarly, it is mapped to the joint feature space through linear projection and L2 normalization. That is, the text and image vectors are mathematically comparable in the same feature space. The text embedding vector of the action subject is matched with the image embedding vectors of all independent objects using cosine similarity. The mask region with the highest similarity score is selected and defined as the first semantic subject. It should be noted that the first semantic subject is the only physical anchor point for subsequent image redrawing operations, the mask area is used to determine the spatial boundary of pixel modification, and the algorithm only applies to the user-specified target and will not accidentally damage other objects of similar color in the image background. The method for extracting the image statistical features of the first semantic subject and performing color semantic change processing to obtain the target change vector is as follows: Preferably, the pixel area corresponding to the first semantic subject is converted from the RGB color space to the HSV (hue, saturation, brightness) color space; Statistical analysis was performed on the pixel regions of the converted color space to calculate the mean hue, variance of brightness distribution, and high-frequency texture feature values ​​within the regions. The hue mean, luminance distribution variance, and high-frequency texture feature values ​​are encapsulated into a feature tensor as image statistical features; It should be noted that image statistical features represent the initial physical state of an object before it is modified. The variance of the brightness distribution of image statistical features characterizes the intensity of reflection on the object's surface (i.e., the smoothness of the material), and the high-frequency texture feature value characterizes the roughness of the object's surface. Preferably, adjective descriptive words (such as "blue" or "glowing") are extracted from user editing instructions, and a color-semantic mapping table pre-stored in the model is read. It should be noted that the color-semantic mapping table is established during the model training phase by analyzing a large number of text-image pairs (i.e., the binding combination established between adjective descriptive words and images) to create a lookup table that corresponds color descriptive words in natural language to numerical ranges in the HSV space. Substitute the adjective descriptive words into the color-semantic mapping table for indexing to obtain the target HSV value expected by the user. The target HSV value is calculated by subtracting the mean hue and mean brightness values ​​in the image statistical features. The resulting combination of differences is the target change vector. It is understandable that the target HSV value contains hue and brightness values, and the target change vector is mathematically represented as a vector with direction and magnitude.

[0025] S20. Establish an attention weight matrix for the entire image using the first semantic subject as the index; filter high-response pixels based on the attention weight matrix, and perform connectivity analysis on the high-response pixels to determine candidate linkage regions; The attention weight matrix for the entire image is established using the first semantic subject as an index; the method for selecting high-response pixels based on the attention weight matrix is ​​as follows: Preferably, feature layers with a preset resolution (such as 32×32 or 64×64) are extracted from the AIGC image generation model decoder; The original mask of the first semantic subject is downsampled to the same resolution as the feature layer to obtain the index mask at the feature layer scale; It should be noted that the reason for downsampling is that the original mask is usually based on the original image resolution (such as 1024×1024), while the self-attention calculation of the AIGC model is performed in the compressed feature space, and spatial dimension alignment is necessary for accurate correspondence. The self-attention tensor of the feature layer is truncated by the forward hook mechanism. The attention weight values ​​of the first semantic subject to other pixels of the whole image are extracted from the self-attention tensor by the index mask and combined to form a heatmap of the whole image attention. The method for determining candidate linkage regions by performing connectivity analysis on high-response pixels is as follows: Gaussian smoothing and noise reduction are applied to the heatmap of attention across the entire image, while a preset linkage response threshold is read. Preferably, the linkage response threshold is 80% of the quantile of the full-image attention heatmap; Reset the attention weight of pixels in the heatmap whose values ​​are lower than or equal to the linkage response threshold to zero; Filter pixels with attention weights higher than a threshold for linkage response to establish a discrete set of high-response points; The density clustering algorithm of DBSCAN is used to perform spatial clustering on discrete high-response point sets, and candidate linkage regions are established based on the spatial clustering results. Those skilled in the art will understand that the method for spatial clustering is as follows: by setting a minimum number of cluster points and a search radius, isolated noise clusters are eliminated, connected pixel regions that meet the density requirements are merged, and the original image resolution is restored by upsampling to obtain candidate linked regions; The physical significance of density clustering analysis is that real light and shadow reflections (such as reflections) are usually continuous sheet-like regions in space, while the errors generated by the AIGC model calculation are usually scattered isolated noise points. Density and connectivity constraints can effectively filter out misjudged regions. The process of defining candidate linkage regions is similar to throwing a stone into a calm water surface (the first semantic subject). The affected area is determined by capturing the range of ripples generated on the water surface. Only areas that are on the ripple transmission path and have continuous ripples are determined to be linkage regions that need to follow the changes of the subject.

[0026] Example 2 Please see Figure 1 As shown, an interactive intelligent content generation method based on AIGC includes the following steps: S30. Obtain the spatial structure information of the candidate linkage region, construct the optical path geometry verification logic based on the spatial structure information, and determine whether there is physical occlusion or self-occlusion effect between the first semantic subject and the candidate linkage region. If so, filter the effective response region. The method for obtaining spatial structure information of candidate linkage regions and constructing optical path geometry verification logic based on spatial structure information is as follows: Preferably, a monocular depth estimation algorithm is used to extract features from the target image to generate a panoramic depth gradient map representing the relative distance between pixels; Simultaneously, the spatial orientation of each pixel in the target image is calculated using a surface normal extraction algorithm to generate a three-dimensional surface normal map. The three-dimensional surface normal map and the panoramic depth gradient map are used as spatial structural information of the candidate linkage region. It should be noted that the pixel grayscale values ​​in the panoramic depth gradient map have a monotonic mapping relationship with the distance from the object to the viewpoint, and the RGB channel values ​​in the 3D surface normal map correspond to the X, Y, and Z axis components of the normal vector in the spatial coordinate system, respectively. Based on the principle of geometric inverse projection, a pseudo-3D point cloud space is established by combining the two-dimensional coordinates of the image plane with the depth value in the panoramic depth gradient map. In some embodiments, when the user editing instructions contain a semantic description characterizing light emission, enhanced brightness, or significant changes in illumination, the first semantic subject is considered to possess characteristics of light effect propagation; The geometric center of the first semantic subject in the pseudo-3D point cloud space is defined as the virtual radiation source point, which is used to construct the spatial influence propagation path. When the user's editing instructions do not contain semantic features, the virtual radiation source point is only used as a reference anchor point for the propagation of intensity, and does not represent a real physical light source.

[0027] Each pixel within the candidate linkage area is used as a target verification point; In the pseudo-3D point cloud space, a straight line vector from the virtual radiation source point to the target verification point is established as the light propagation vector. It is understandable that the purpose of constructing a pseudo-3D point cloud space is: Objective 1: To convert the visual relationships of a two-dimensional image plane into geometric relationships in three-dimensional space; Objective 2: A unified inverse projection transformation can improve the accuracy of occlusion and angular relationships in target images; The method for determining whether there is physical occlusion or self-occlusion effect between the first semantic subject and the candidate linkage region based on optical path geometric verification logic is as follows: S301. Extract the unit normal vector corresponding to the target verification point in the three-dimensional surface normal map, perform reflection compatibility verification based on the normal angle on the target verification point, and remove target verification points with self-occlusion effect. The method for performing reflection compatibility verification based on the included normal angle is as follows: Calculate the dot product of the ray propagation vector and the unit normal vector corresponding to the target verification point, and use it as the light reception determination value; Set a light reception threshold; preferably, set it to 0.1. like Figure 2As shown, when the light-receiving judgment value is less than the light-receiving judgment threshold, it indicates that the surface of the target verification point is facing away from the virtual radiation source point. The target verification point is judged to have a self-occlusion effect and is removed from the candidate linkage area. When the light-receiving judgment value is greater than or equal to the threshold, it indicates that the target verification point meets the light-receiving conditions, and the target verification point is retained for subsequent processing. If the light-receiving judgment value is lower than the light-receiving judgment threshold, the light-receiving judgment value is continuously monitored. S302. Reproject the light propagation vector to obtain path sampling points and perform depth difference comparison verification to check whether the path sampling points block the light propagation path; based on the verification results, remove the target verification points. Preferably, the reprojection process is performed by projecting the light propagation vector onto a two-dimensional image plane to obtain a two-dimensional projection path; Discretize the two-dimensional projection path to obtain N path sampling points; The method for performing depth differential comparison and verification is as follows: Read the pixel values ​​at the corresponding locations of the path sampling points from the panoramic depth gradient map as the actual depth; Based on the depth values ​​of the virtual radiation source and the target verification point, a linear interpolation algorithm is used to calculate the theoretical projection depth of the path sampling point on the ray line; If the actual depth is lower than the theoretical projection depth at any path sampling point, it is determined that there is a physical entity obstructing the light propagation path at the location corresponding to the path sampling point; otherwise, no action is taken. If a physical entity obstructs the path of light propagation, it means that there is a physical occlusion between the first semantic subject and the target verification point, and the target verification point will be removed from the candidate linkage area. Obtain the candidate linkage regions that have not undergone the elimination process, and use them as valid response regions.

[0028] S40. Based on the spatial location distribution of the effective response region, perform spatial distance attenuation analysis on the target change vector to obtain the basic attenuation coefficient; based on the image statistical features of the first semantic subject, perform material scattering correction on the basic attenuation coefficient to derive the collaborative mapping parameters of the effective response region. The method for obtaining the basic attenuation coefficient by performing spatial distance attenuation analysis on the target change vector based on the spatial location distribution of the effective response area is as follows: Preferably, based on the constructed pseudo-3D point cloud space, the spatial Euclidean distance of each pixel within the effective response area relative to the virtual radiation source point is calculated; By performing an inverse mapping between spatial Euclidean distance and energy intensity, the basic attenuation coefficient of the pixel is obtained. Preferably, the method for performing inverse mapping is as follows: Set a maintenance constant for the light intensity; It should be noted that the purpose of setting the maintenance constant for light intensity is to prevent numerical singularities from occurring when the distance is zero; The spatial Euclidean distance in the pseudo-3D point cloud space is normalized. The normalization process is calculated based on the maximum spatial scale of the effective response region in the target image (i.e., the square of the maximum spatial Euclidean distance). The dimensionless spatial Euclidean distance is squared and summed with a preset dimensionless illumination intensity constant to obtain the distance attenuation denominator. Preferably, the value range of the light intensity maintenance constant C is [0.01, 1.0], with a preferred value of 0.1, to prevent calculation overflow when the distance is zero; Calculate the ratio of the illumination intensity maintenance constant to the distance attenuation denominator, and define the resulting ratio as the basic attenuation coefficient; Those skilled in the art will understand that as the spatial Euclidean distance increases, the denominator of the distance attenuation will increase quadratically, causing the final calculated basic attenuation coefficient (i.e., ratio) to drop rapidly and approach zero infinitely, thus replicating the natural attenuation effect of light propagation in the real world. The method for deriving the co-mapping parameters of the effective response region by correcting the material scattering of the basic attenuation coefficient based on the image statistical features of the first semantic subject is as follows: Preferably, high-frequency texture feature values ​​are extracted from the statistical features of the image; It should be noted that high-frequency texture feature values ​​are used to characterize the complexity of surface details of the first semantic subject and are defined as detail adjustment factors; The surface detail adjustment factor is used to empirically modulate the propagation intensity of the target change vector during the generation process. Its role is to simulate the effect of the complexity of surface details on the perceived changes in illumination. The surface detail adjustment factor is a generation control parameter and does not directly correspond to the real physical diffuse reflection parameter.

[0029] Damping correction logic is constructed based on detailed adjustment factors, and the basic attenuation coefficient is weighted down to obtain the comprehensive conduction coefficient. The preferred method for weighted down adjustment is as follows: Set a scattering sensitivity tuning constant; It should be noted that the purpose of setting the scattering sensitivity adjustment constant is to: standardize and constrain the numerical magnitude of high-frequency texture feature values, adjust the influence weight of surface roughness on light energy attenuation, and prevent the calculation results from being distorted due to excessive fluctuations in the original feature values. The detail adjustment factor and the scattering sensitivity control constant are multiplied together, and the result of the multiplication is summed with the preset reference value (the preset reference value is 1) to obtain the scattering damping denominator. Calculate the ratio of the basic attenuation coefficient to the denominator of the scattering damping, and define the resulting ratio as the comprehensive conduction coefficient; Keeping the vector direction of the target change vector unchanged, the vector magnitude of the target change vector is scaled and modulated using the comprehensive transmission coefficient to obtain the target magnitude; Preferably, the scaling modulation method is as follows: obtain the original magnitude of the target change vector, calculate the product of the original magnitude and the comprehensive transmission coefficient to obtain the target magnitude; The reconstructed vector is based on the vector direction and the target magnitude, and the reconstructed vector result is defined as the cooperative mapping parameter; As can be understood by those skilled in the art, the co-mapping parameter is essentially a construction instruction with spatial and material constraints. The physical meaning of the co-mapping parameter is: under the premise of keeping the hue direction of color change consistent, the actual brightness or color change that should occur at the point is calculated based on the distance of the point from the light source (reflected by the base attenuation coefficient) and the roughness of the reflective surface (reflected by the scattering damping denominator).

[0030] S50. Construct a light and shadow guidance matrix based on the collaborative mapping parameters, and perform directional guidance processing on the effective response area based on the light and shadow guidance matrix to achieve synchronous rendering of the first semantic subject and the effective response area. The method for constructing the light and shadow guidance matrix based on the cooperative mapping parameters is as follows: Preferably, the collaborative mapping parameters are arranged according to their coordinate positions in the image to construct a light and shadow guidance matrix aligned with the target image resolution, and the iterative denoising process of the AIGC image generation model is initiated. It should be noted that the iterative denoising process is the core mechanism of AIGC image generation, similar to a painter starting from a blank sheet of paper (pure noise) and gradually creating a clear image through dozens of brushstrokes (denoising steps). The method for synchronous rendering of the first semantic subject and the effective response area by using a light and shadow guidance matrix to perform directional guidance processing on the effective response area is as follows: In each intermediate computation step of the iterative denoising process, the light and shadow guidance matrix is ​​input into the pre-trained variational autoencoder for dimensionality reduction encoding to obtain the latent guidance tensor aligned with the dimension of the noise prediction result. After multiplying the tensor by a preset guiding strength coefficient, it is added to the noise prediction residual of the diffusion model by adding them element by element. The preferred method for superposition is as follows: Obtain the original pixel values ​​currently predicted by the model and read the parameter values ​​at the corresponding positions in the light and shadow guidance matrix; The parameter values ​​are applied to the original pixel values ​​in an incremental manner, causing the pixel values ​​to shift towards the target hue and brightness, thereby achieving directional guidance processing; The method for achieving synchronized visual rendering of the first semantic subject and the effective response area while preserving texture details is as follows: While injecting the light and shadow guidance matrix, a structure locking strategy is executed on the effective response area; Preferably, the structure locking strategy is implemented as follows: extract the latent spatial feature map of the previous generation step, separate the high-frequency edge components through a high-pass filter; in the noise prediction stage of the current generation step, inject the high-frequency edge components into the corresponding skip connection layer of the U-Net decoder in the form of residual connections to constrain the smearing range of low-frequency light and shadow.

[0031] Example 3 Please see Figure 3 As shown, an interactive intelligent content generation system based on AIGC includes the following modules: Intent parsing module: used to collect user editing instructions for the target image and perform intent parsing to obtain the first semantic subject in the target image; extract the image statistical features of the first semantic subject and perform color semantic change processing to obtain the target change vector; Connectivity Analysis Module: Used to build an attention weight matrix for the entire graph with the first semantic subject as the index; based on the attention weight matrix, high-response pixels are selected, and connectivity analysis is performed on the high-response pixels to determine candidate linkage regions; Region filtering module: used to obtain the spatial structure information of candidate linkage regions, construct optical path geometry verification logic based on the spatial structure information, and determine whether there is physical occlusion or self-occlusion effect between the first semantic subject and the candidate linkage region. If so, the effective response region is filtered. Attenuation correction module: Based on the spatial location distribution of the effective response region, the target change vector is analyzed for spatial distance attenuation to obtain the basic attenuation coefficient; based on the image statistical features of the first semantic subject, the basic attenuation coefficient is corrected for material scattering, and the cooperative mapping parameters of the effective response region are derived. Synchronous rendering module: Constructs a light and shadow guidance matrix based on collaborative mapping parameters, and performs directional guidance processing on the effective response area based on the light and shadow guidance matrix to achieve synchronous rendering of the first semantic subject and the effective response area.

[0032] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the present invention should still fall within the scope of the present invention.

Claims

1. An interactive intelligent content generation method based on AIGC, characterized in that, Includes the following steps: The first semantic subject is obtained as the index and an attention weight matrix for the entire image is established. High-response pixels are selected based on the attention weight matrix, and connectivity analysis is performed on the high-response pixels to determine candidate linkage regions. Obtain the spatial structure information of the candidate linkage region, construct the optical path geometry verification logic based on the spatial structure information, and determine whether there is physical occlusion or self-occlusion effect between the first semantic subject and the candidate linkage region. If so, filter the effective response region. The image statistical features of the first semantic subject are extracted and color semantic change processing is performed to obtain the target change vector; Based on the spatial location distribution of the effective response area, a spatial distance attenuation analysis is performed on the target change vector to obtain the basic attenuation coefficient; Image statistical features are obtained to correct the material scattering of the basic attenuation coefficient, and the co-mapping parameters of the effective response region are derived. A light and shadow guidance matrix is ​​constructed based on the collaborative mapping parameters. The effective response area is then guided by the light and shadow guidance matrix to achieve synchronous rendering of the first semantic subject and the effective response area.

2. The interactive intelligent content generation method based on AIGC according to claim 1, characterized in that: The first semantic subject is obtained by: collecting the user's editing instructions on the target image and performing intent parsing to obtain the first semantic subject in the target image.

3. The interactive intelligent content generation method based on AIGC according to claim 2, characterized in that: The intent parsing is performed as follows: The AIGC large model uses a pre-built multimodal semantic understanding unit to extract keywords from user editing commands and identify the action subject in the commands. Text embedding vectors for user editing commands are built based on action subjects; Simultaneously, the visual segmentation model is invoked to perform panoramic segmentation on the target image, obtaining the mask regions of all independent objects in the image; Image embedding vectors are established based on the mask regions of independent objects; The text embedding vector of the action subject is matched with the image embedding vectors of all independent objects using cosine similarity. The mask region with the highest similarity score is selected and defined as the first semantic subject.

4. The interactive intelligent content generation method based on AIGC according to claim 1, characterized in that: The connectivity analysis is performed as follows: A heatmap of full-graph attention is constructed and zero-weighted screening is performed. Based on the screening results, a discrete set of high-response points is constructed. Density clustering algorithm is used to spatially cluster discrete high-response point sets, and candidate linkage regions are established based on the spatial clustering results.

5. The interactive intelligent content generation method based on AIGC according to claim 1, characterized in that: The method for determining whether physical occlusion or self-occlusion exists is as follows: Each pixel within the candidate linkage area is used as a target verification point; Obtain the 3D surface normal map and ray propagation vector; Extract the unit normal vector corresponding to the target verification point in the 3D surface normal map, perform reflection compatibility verification based on the normal angle on the target verification point, and remove target verification points with self-occlusion effect; The light propagation vector is reprojected to obtain path sampling points, and depth difference comparison is performed to verify whether the path sampling points block the light propagation path; based on the verification results, the target verification points are eliminated.

6. The interactive intelligent content generation method based on AIGC according to claim 5, characterized in that: The process of obtaining the light propagation vector is as follows: Feature extraction is performed on the target image to generate a panoramic depth gradient map representing the relative distances between pixels; Simultaneously, a three-dimensional surface normal map is established. Based on the principle of geometric inverse projection, and combining the two-dimensional coordinates of the image plane with the depth values ​​in the panoramic depth gradient map, a pseudo-three-dimensional point cloud space is established. Calculate the geometric center of the mask region corresponding to the first semantic subject in the pseudo-3D point cloud space, and use it as the virtual radiation source point; A virtual radiation source point to the target verification point is established in the pseudo-3D point cloud space as a straight line vector, which serves as the light propagation vector.

7. The interactive intelligent content generation method based on AIGC according to claim 5, characterized in that: The method for performing the depth differential comparison and verification is as follows: The pixel values ​​at the corresponding positions of the path sampling points are read from the panoramic depth gradient map as the actual depth; the theoretical projection depth of the path sampling points on the line of light is calculated based on the depth values ​​of the virtual radiation source point and the target verification point. If at any path sampling point the actual depth is lower than the theoretical projection depth, then it is determined that there is a physical entity at the location corresponding to the path sampling point that is obstructing the path of light propagation. If a physical entity obstructs the path of light propagation, it is determined that there is a physical occlusion between the first semantic subject and the target verification point, and the target verification point is removed from the candidate linkage area.

8. The interactive intelligent content generation method based on AIGC according to claim 1, characterized in that: The method for performing the material scattering correction is as follows: High-frequency texture feature values ​​are extracted from the statistical features of the image and defined as the detail adjustment factor; Damping correction logic is constructed based on detailed adjustment factors, and the basic attenuation coefficient is weighted down to obtain the comprehensive conduction coefficient. The detail adjustment factor and the scattering sensitivity control constant are multiplied together, and the result of the multiplication is summed with the preset benchmark value to obtain the scattering damping denominator. Calculate the ratio of the basic attenuation coefficient to the denominator of the scattering damping, and define the resulting ratio as the comprehensive conduction coefficient; Keeping the vector direction of the target change vector unchanged, the vector magnitude of the target change vector is scaled and modulated using the comprehensive transmission coefficient to obtain the target magnitude; The vector is reconstructed based on the vector direction and the target magnitude, and the reconstructed vector result is defined as the cooperative mapping parameter.

9. The interactive intelligent content generation method based on AIGC according to claim 8, characterized in that: The basic attenuation coefficient is obtained as follows: Squaring the spatial Euclidean distance of each pixel; The result of the squaring operation is made dimensionless, and the dimensionless spatial Euclidean distance is summed with the preset constant illumination intensity to obtain the distance attenuation denominator. Calculate the ratio of the maintenance constant of light intensity to the denominator of the distance attenuation, and define the ratio as the basic attenuation coefficient.

10. An AIGC-based interactive intelligent content generation system, used to implement the AIGC-based interactive intelligent content generation method according to any one of claims 1-9, characterized in that, Includes the following modules: Intent parsing module: used to collect user editing instructions for the target image and perform intent parsing to obtain the first semantic subject in the target image; extract the image statistical features of the first semantic subject and perform color semantic change processing to obtain the target change vector; Connectivity Analysis Module: Used to build the attention weight matrix of the entire graph using the first semantic subject as an index; High-response pixels are selected based on the attention weight matrix, and connectivity analysis is performed on the high-response pixels to determine candidate linkage regions. Region filtering module: used to obtain the spatial structure information of candidate linkage regions, construct optical path geometry verification logic based on the spatial structure information, and determine whether there is physical occlusion or self-occlusion effect between the first semantic subject and the candidate linkage region. If so, the effective response region is filtered. Attenuation correction module: Based on the spatial location distribution of the effective response area, the target change vector is analyzed for spatial distance attenuation to obtain the basic attenuation coefficient; Based on the image statistical features of the first semantic subject, the basic attenuation coefficient is corrected by material scattering, and the cooperative mapping parameters of the effective response region are derived. Synchronous rendering module: Constructs a light and shadow guidance matrix based on collaborative mapping parameters, and performs directional guidance processing on the effective response area based on the light and shadow guidance matrix to achieve synchronous rendering of the first semantic subject and the effective response area.

Images