Holographic projection image intelligent generation method and system applied to stage virtual interaction

Abstract

The application provides a holographic projection image intelligent generation method and system applied to stage virtual interaction, first, stage scene interaction demand information containing a stage performance theme, a performance link time node and a virtual interaction trigger condition is acquired; a target mapping rule is constructed based on the stage scene interaction demand information, and an initial holographic projection image element set is generated by using a generative artificial intelligence model; stages are divided according to the performance link time node, and the image element set is dynamically arranged in stages in combination with the interaction trigger condition, so that a dynamic holographic projection image sequence is obtained; stage real-time interaction data is collected, associated logic of the stage real-time interaction data and image sequence adjustment is established, and parameters are adjusted, so that an optimized sequence is obtained; an output parameter system is constructed based on the optimized sequence, and an instruction drives a holographic projection equipment to output an image, so that the visual effect of stage performance and audience immersion are improved.

Description

Technical Field

[0001] This invention relates to the field of generative artificial intelligence technology, and more specifically, to a method and system for intelligent generation of holographic projection images applied to virtual stage interaction. Background Technology

[0002] In the field of stage performance arts, with the continuous development of technology, holographic projection technology has gradually become an important means to enhance stage visual effects and increase audience immersion. However, existing stage holographic projection applications have many limitations.

[0003] On the one hand, traditional methods often lack in-depth consideration of the interactive needs of stage scenes when generating holographic projection images. Stage performances have rich themes and diverse performance segments, and different segments have specific requirements for the content, timing, and interaction methods of holographic projections. However, existing technologies usually simply preset some fixed projection images and cannot flexibly adjust them according to key information such as the theme of the stage performance, the time nodes of the performance segments, and the triggering conditions of virtual interactions. This results in a low degree of integration between holographic projection and stage performance, making it difficult to create a realistic and creative stage atmosphere.

[0004] On the other hand, existing technologies also have significant shortcomings in the dynamic arrangement and real-time optimization of holographic projection images. During stage performances, real-time interactive data such as actors' movements and audience feedback have a significant impact on the effect of holographic projection. However, traditional methods cannot collect this real-time interactive data in a timely manner and establish an effective correlation logic between it and the adjustment of holographic projection images. This prevents holographic projection images from being dynamically optimized according to the actual stage conditions, and thus fails to meet the real-time and interactive requirements of stage performances. Summary of the Invention

[0005] In view of the aforementioned problems, and in conjunction with the first aspect of the present invention, embodiments of the present invention provide a method for intelligent generation of holographic projection images applied to virtual stage interaction, the method comprising:

[0006] Obtain stage scene interaction requirement information, which includes stage performance theme information, performance segment time node information, and virtual interaction triggering condition information;

[0007] Based on the stage scene interaction requirements information, a target mapping rule is constructed, and a generative artificial intelligence model is called to generate image elements according to the target mapping rule to obtain an initial holographic projection image element set. The initial holographic projection image element set includes static image elements and dynamic image elements that match the stage performance theme information.

[0008] The performance stages are divided according to the time node information of the performance segments. The initial holographic projection image element set is dynamically arranged in stages and combined with the virtual interaction triggering condition information to obtain a dynamic holographic projection image sequence.

[0009] Collect real-time interactive data from the stage, establish a correlation logic between the real-time interactive data and image sequence adjustment, and perform parameter adjustment processing on the dynamic holographic projection image sequence according to the correlation logic to obtain an optimized dynamic holographic projection image sequence.

[0010] Based on the optimized dynamic holographic projection image sequence, a holographic projection output parameter system is constructed, a holographic projection image generation instruction containing the output parameter system is generated, and the holographic projection image generation instruction is sent to the holographic projection device to drive the holographic projection device to output a holographic projection image.

[0011] In another aspect, embodiments of the present invention also provide a holographic projection image intelligent generation system for stage virtual interaction, including a processor and a machine-readable storage medium connected to the processor. The machine-readable storage medium is used to store programs, instructions or code, and the processor is used to execute the programs, instructions or code in the machine-readable storage medium to implement the above-described method.

[0012] Based on the above, this embodiment of the invention acquires stage scene interaction requirement information, covering key elements such as the stage performance theme, performance time nodes, and virtual interaction triggering conditions. Based on this information, a target mapping rule is constructed, and a generative artificial intelligence model is invoked to generate an initial set of holographic projection image elements. This ensures that the generated static and dynamic image elements are highly matched with the stage performance theme. Performance stages are divided according to the performance time nodes, and the initial image element set is dynamically arranged in stages based on the virtual interaction triggering conditions. This allows the holographic projection images to be presented in an orderly manner according to the rhythm and needs of the stage performance, enhancing the coherence and logic of the performance. By collecting real-time stage interaction data and establishing its correlation logic with image sequence adjustments, real-time parameter adjustments to the dynamic holographic projection image sequence can be made according to the actual stage conditions, achieving dynamic optimization of the holographic projection images and improving the real-time performance and interactivity of the stage performance. Finally, based on the optimized image sequence, a holographic projection output parameter system is constructed, and instructions are generated to drive the device output images, ensuring high-quality presentation of the holographic projection images and comprehensively enhancing the visual effects of the stage performance and the audience's immersion. Attached Figure Description

[0013] Figure 1 This is a schematic diagram of the execution flow of the intelligent generation method for holographic projection images applied to virtual stage interaction provided in an embodiment of the present invention.

[0014] Figure 2 This is a schematic diagram of exemplary hardware and software components of the intelligent generation system for holographic projection images applied to virtual stage interaction provided in an embodiment of the present invention. Detailed Implementation

[0015] The present invention will now be described in detail with reference to the accompanying drawings. Figure 1 This is a flowchart illustrating a method for intelligently generating holographic projection images for virtual stage interaction, provided by an embodiment of the present invention. The following is a detailed description of this method for intelligently generating holographic projection images for virtual stage interaction.

[0016] Step S110: Obtain stage scene interaction requirement information, which includes stage performance theme information, performance segment time node information, and virtual interaction trigger condition information.

[0017] This embodiment uses a modern technology-themed concert as the unified application scenario. This scenario integrates modern stage elements such as light shows, virtual singer interaction, and immersive audience participation, and requires the presentation of dynamic, technologically advanced images through holographic projection. Three types of core information are obtained through the requirements input module of the stage planning and management system.

[0018] The stage performance theme is clearly defined as "Future Technology Roaming", which includes a description of the theme style (cyberpunk visual style, holographic light and shadow fusion, dynamic particle effects), core performance elements (virtual singer image, digital neon scene, particle-made musical instruments, dynamic data stream) and the theme's emotional tone (futuristic, immersive, and interactive).

[0019] The performance time information is divided according to the concert flow, including the opening (duration), song performance (including 5 songs, each with an independent duration and interlude duration), interactive segment (duration), intermission (duration), and closing segment (duration). Each segment is marked with precise start and end times, and the key rhythmic nodes within each segment are clearly defined (such as the intro, verse, chorus, and interlude times of the songs).

[0020] The virtual interaction triggering conditions information covers three types of triggering events: audience interaction triggering (such as the distribution of audience members raising glow sticks reaching a set range, or the on-site decibel value exceeding a set threshold), stage equipment triggering (such as the lighting switching to a specific mode, or the stage lift reaching a preset height), and performer triggering (such as the singer making a specific gesture, or the dance movement reaching a preset posture). Each triggering event is marked with the expected holographic image response requirements after triggering (such as scene switching, enhanced particle effects, or virtual singer movement synchronization).

[0021] For audience interaction data (such as glow stick positions and decibel values) involved in the collection process, anonymization is adopted to prevent association with audience personal identity information; data transmission is achieved through encryption protocols, and access permissions are set at different levels during storage, so that only the stage technical team can operate the interactive data to prevent information leakage or tampering.

[0022] Step S120: Based on the stage scene interaction requirement information, construct a target mapping rule, call the generative artificial intelligence model to perform image element generation processing according to the target mapping rule, and obtain an initial holographic projection image element set. The initial holographic projection image element set includes static image elements and dynamic image elements that match the stage performance theme information.

[0023] Based on the theme of "Future Technology Roaming", a set of holographic image elements that fit the scene is obtained by combining rule construction and AI generation. The specific process is as follows.

[0024] Step S121: Analyze the stage performance theme information in the stage scene interaction requirement information, and extract the core visual style keywords and core element type descriptions from the stage performance theme information. The core visual style keywords include color tendency descriptions and style descriptions, and the core element type descriptions include scene element categories and character element categories.

[0025] Analyze the theme information and extract the core visual style keywords: the color tendency is described as "high-saturation neon colors (mainly blue-purple, pink-purple, and cyan), dark background contrast, and strong light and shadow contrast"; the style is described as "cyberpunk, digital art, and dynamic particle effects".

[0026] Extracting core element type descriptions: Scene element categories include "digital city skyline, neon streets, virtual stage background, data stream tunnel"; character element categories include "virtual singer (3D digital image, with a technological and anthropomorphic style), particle-based backup dancers, and dynamic symbolic characters (such as digital musical notes and geometric combination characters)".

[0027] The extracted keywords and element types are organized according to the "style-element" correspondence to form a structured extraction list, ensuring that the core visual and element requirements of the theme are covered.

[0028] Step S122: Construct target mapping rules based on the core visual style keywords and core element type descriptions. The target mapping rules include the correspondence between visual style keywords and image color parameters, and the correspondence between element type descriptions and image morphological features.

[0029] Two core mapping relationships are constructed: visual style-color parameter mapping and element type-morphological feature mapping.

[0030] Visual style - color parameter mapping rules: "Blue-purple neon color" corresponds to color space parameters (hue range, saturation range, brightness range), "dark background" corresponds to the brightness parameter range of the background color, and "strong light and shadow contrast" corresponds to light and shadow parameters (contrast range, highlight intensity range, shadow density range); at the same time, color matching rules are defined, such as "the ratio of the main color blue-purple to the auxiliary color pink-purple, and the matching relationship between the neon color luminous intensity parameter and the background brightness".

[0031] Element type - morphological feature mapping rules: "Digital city skyline" corresponds to morphological parameters (geometric constraints of building outline, building density distribution, height hierarchy relationship), "virtual singer" corresponds to morphological parameters (human body proportion constraints, technological texture features of clothing, digital processing standards of facial features), and "particle musical instrument" corresponds to morphological parameters (particle number range, instrument outline accuracy after particle aggregation, physical constraint parameters of particle movement).

[0032] The mapping rules are encoded into a structured rule file that can be recognized by generative AI, which includes four fields: rule identifier, input keywords, output parameter range, and constraints.

[0033] Step S123: Input the target mapping rule into the generative artificial intelligence model, triggering the generative artificial intelligence model to configure the basic parameters for image generation according to the target mapping rule. The basic parameters for image generation include color configuration parameters, shape configuration parameters, and texture configuration parameters.

[0034] The generative artificial intelligence model based on the diffusion model architecture (trained with millions of stage holographic image data and adapted to the generation of dynamic and static elements) is invoked, and the mapping rule file is input into the rule parsing module of the model.

[0035] The model configures basic parameters according to rules: color configuration parameters include the specific color space values ​​of the primary color, secondary color, and background color, color transition modes (such as gradient, abrupt change, and alternating flashing), and brightness attenuation parameters of luminous elements; shape configuration parameters include the geometric contour parameters of various elements (such as the height ratio of the virtual singer and the thickness of the outline lines of buildings), the scaling factor of elements (relative to the stage projection area), and spatial position constraints between elements (such as the distance range between the virtual singer and the backup dancers); texture configuration parameters include the texture type of the element surface (such as the metallic texture of the virtual singer's clothing and the neon tube texture of the building surface), texture resolution parameters, and dynamic change triggering conditions of textures (such as the texture brightness change parameters affected by lighting).

[0036] After the parameters are configured, a parameter list is generated. A low-resolution preview of the parameter effect is then generated through the model's preview module to ensure that it meets the mapping rule requirements.

[0037] Step S124: Determine the image color matching scheme according to the color configuration parameters. The image color matching scheme includes the main color parameter, the auxiliary color parameter, and the color transition rules based on the color model.

[0038] Detailed color schemes are generated based on color configuration parameters: the primary color parameter is defined as the specific color space range of blue-purple, the secondary color parameter is the color space range of pink-purple and cyan, and the usage ratio of primary and secondary colors is defined (such as the proportion of primary color, the proportion of secondary color, and the proportion of accent color).

[0039] Establish tone transition rules based on the HSV (Hue, Saturation, Value) color model: tone transitions within the same element adopt a gradual approach, with the hue change range, saturation change rate, and value change gradient of the transition interval clearly defined; tone transitions between different elements adopt a contrasting and complementary approach to ensure that the tone differences between adjacent elements meet the requirements of visual impact; the tone transitions of dynamic elements are matched with the performance rhythm, such as the tone transition rate accelerating in the chorus and slowing down in the interlude.

[0040] The matching scheme also includes color adaptation rules, such as automatically adjusting the brightness parameters of the hue according to the intensity of the stage ambient light to avoid conflicts between the holographic image and the ambient light.

[0041] Step S125: Determine the morphological feature parameters and texture detail parameters of the image element according to the morphological configuration parameters and texture configuration parameters. The morphological feature parameters include contour structure parameters based on geometric constraints and proportional size parameters relative to the stage projection area. The texture detail parameters include texture density parameters based on pixel distribution and texture quality parameters based on material simulation.

[0042] For each element type, the parameters are refined: taking the "virtual singer" element as an example, the outline structure parameter in the morphological feature parameter defines the geometric outline constraints of the head, torso, and limbs (e.g., the head is an elliptical outline, and the limbs are cylindrical outlines), and the angle constraints of the joints (e.g., the range of elbow joint movement angles); the scale parameter defines the height ratio of the virtual singer relative to the stage projection area (e.g., the proportion of the projection area height), and the proportional relationship with other elements (e.g., the size ratio of the virtual singer to the particle instrument).

[0043] The texture density parameter in the texture detail parameters defines the pixel distribution density of the clothing texture (such as the number of texture pixels per unit area), and the texture quality parameter defines the material simulation parameters (such as the reflectivity of metallic texture and the wrinkle simulation parameters of fabric texture). At the same time, the texture hierarchy is set, such as the resolution of the virtual singer's facial texture being higher than that of the clothing texture, to ensure that the details of key parts are clear.

[0044] Step S126: Call the generative artificial intelligence model to generate static image elements according to the image color matching scheme, morphological feature parameters and texture detail parameters, and obtain static image elements that match the core element type description.

[0045] Input the color scheme, shape and texture parameters into the static element generation module of the generative AI. The module generates static elements in sequence according to element category: scene static elements (such as the static outline of a digital city skyline and the static background of a neon street), character static elements (such as the static standing image of a virtual singer and the static form of a symbolic character), and prop static elements (such as the static outline of a particle musical instrument and the static frame of a virtual stage).

[0046] During the generation process, the model uses a geometric constraint module to ensure that the element shapes meet the parameter requirements, a color rendering module to achieve color matching and transition effects, and a texture mapping module to overlay texture details. After generation, high-resolution static image elements are output (in a lossless format adapted for holographic projection), with each element labeled with its corresponding element category, parameter source, and theme matching score.

[0047] Step S127: Based on the dynamic attribute requirements in the core element type description, configure dynamic change rule parameters, which include the time dimension change frequency and the spatial dimension change trajectory.

[0048] Analysis of the dynamic attribute requirements in the core element type description: such as "virtual singers must perform dance moves in rhythm with the song", "particle instruments must generate particle diffusion and aggregation in sync with the melody", and "data stream tunnels must present a forward-moving effect".

[0049] Configure rule parameters for each dynamic element: the time dimension change frequency parameter defines the time interval of element state changes (e.g., the particle diffusion frequency of a particle instrument is synchronized with the song beat), and the duration of state changes (e.g., the completion time of a dance move by a virtual singer); the spatial dimension change trajectory parameter defines the element's movement path (e.g., the movement path of a virtual singer within the stage projection area, represented by a sequence of coordinate points in the stage coordinate system), the spatial constraints of the movement (e.g., it must not exceed the coordinate range of the projection area boundary), and the posture change parameters during the movement (e.g., the change of limb angles when a virtual singer moves).

[0050] The parameter configuration must match the rhythm nodes in the time node information of the performance segment to ensure that the dynamic changes are synchronized with the performance rhythm.

[0051] Step S128: Call the generative artificial intelligence model to generate dynamic image elements according to the dynamic change rule parameters, and obtain dynamic image elements containing the time dimension change rules.

[0052] Dynamic elements are generated through the following sub-steps:

[0053] Step S1281: Analyze the dynamic attribute requirements in the core element type description to determine the change dimensions of the dynamic image elements. The change dimensions include position change dimension, shape change dimension, and color change dimension.

[0054] Analyze the dynamic attribute requirements and determine the change dimensions of each dynamic element: the virtual singer element includes position change (movement within the stage), shape change (body movements, posture adjustments), and color change (brightness of clothing texture changes with lighting); the particle instrument element includes position change (movement with the virtual singer), shape change (particle aggregation and diffusion), and color change (particle color changes with the mood of the song); the data stream tunnel element includes position change (movement forward), shape change (change in tunnel cross-sectional size), and color change (alternating hues in the data stream).

[0055] The change dimensions of each element are assigned a priority, such as the virtual singer's shape change dimension having a higher priority than the position change dimension.

[0056] Step S1282: For the position change dimension, configure position change rule parameters according to the motion trajectory description in the dynamic attribute requirements. The position change rule parameters include the spatial path node coordinates based on the stage coordinate system and the motion rate between nodes based on the time unit.

[0057] Establish a stage coordinate system (with the bottom left corner of the stage as the origin, the X-axis as the width of the stage, the Y-axis as the height, and the Z-axis as the depth). Configure path node coordinates according to the motion trajectory description of the elements: for example, the movement path of a virtual singer includes the starting point coordinates, multiple intermediate node coordinates, and the ending point coordinates. Each node corresponds to a specific time point in the performance segment.

[0058] Configure the motion rate parameters between nodes: such as the motion rate from the starting point to the first intermediate node, and the rate from the first intermediate node to the second intermediate node. The rate value is set according to the performance rhythm (such as the rate speeding up in the chorus), and define smooth transition parameters for rate changes to avoid motion stuttering.

[0059] Step S1283: For the morphological change dimension, configure morphological change rule parameters according to the morphological evolution description in the dynamic attribute requirements. The morphological change rule parameters include morphological transition node parameters and morphological change amplitude based on percentage change between nodes.

[0060] Based on the morphological evolution description (such as the "raise hand - wave hand - put down" action of a virtual singer), configure the parameters of the morphological transition nodes: each node corresponds to a specific morphology (such as the raising hand node being the specific angle between the arm and the torso, the waving hand node being the angle of the arm swinging, and the putting down node being the angle of the arm hanging down naturally).

[0061] Configure the magnitude of shape changes between nodes: express the change in shape parameters as a percentage (such as the percentage change in angle from raising the hand to waving the hand, or the percentage change in angle from waving the hand to lowering the hand). The magnitude of change is matched with the time interval to ensure that the shape changes are natural and smooth.

[0062] Step S1284: For the color change dimension, configure the color change rule parameters according to the color gradient description in the dynamic attribute requirements. The color change rule parameters include color transition node parameters and color change gradient between nodes based on color space.

[0063] Based on the color gradient description (e.g., the particle instrument transitions from blue-purple to cyan), configure the color transition node parameters: each node corresponds to a specific color space value (e.g., the starting node is the HSV value of blue-purple, the middle node is the HSV value of a blue-cyan mixture, and the ending node is the HSV value of cyan).

[0064] Configure color gradient between nodes: Define gradient values ​​for hue, saturation, and brightness (such as the amount of change in hue per unit time and the rate of change in saturation) to ensure that the gradient process meets visual requirements and is synchronized with the performance's emotions.

[0065] Step S1285: Integrate the position change rule parameters, shape change rule parameters, and color change rule parameters to form a dynamic change rule parameter set.

[0066] The parameters of the three dimensions are integrated by element category to form a parameter set: the parameter set of each element includes parameter identifier, change dimension type, specific parameter value, associated performance time node, and the collaborative relationship between parameters (such as the synchronous triggering condition of position change and form change).

[0067] The parameter set is stored in XML format, which facilitates the parsing and invocation of generative AI.

[0068] Step S1286: Input the set of dynamic change rule parameters into the generative artificial intelligence model to trigger the generative artificial intelligence model to construct a time change model of dynamic image elements. The time change model includes position parameters, shape parameters and color parameters corresponding to different time points.

[0069] The parameter set is input into the dynamic modeling module of the generative AI. The module builds a time-varying model based on the parameters: with the time axis as the reference, the corresponding position parameters (coordinate values), shape parameters (outline and posture parameters), and color parameters (HSV values) are assigned to each time point (the interval is consistent with the performance rhythm node).

[0070] The model fills in the parameter gaps between adjacent time points through a parameter interpolation algorithm to ensure continuous parameter changes; at the same time, it ensures the synchronization of parameters in different dimensions through a collaborative control module (such as triggering corresponding shape and color changes synchronously when the virtual singer moves to a specific position).

[0071] Step S1287: Based on the time change model, generate state data of dynamic image elements at different time points, wherein the state data includes timestamps, location coordinates, morphological parameter values, and color parameter values.

[0072] Based on the time change model, state data is generated in chronological order: each time point corresponds to one state data point, which includes a timestamp accurate to milliseconds, position coordinates on the X / Y / Z axes, morphological parameters (such as limb angles and particle counts), and color parameters (HSV values ​​of primary and secondary hues).

[0073] Status data is stored in sequence, with each data entry associated with a corresponding element identifier, ensuring traceability to a specific dynamic element.

[0074] Step S1288: Generate a frame sequence of dynamic image elements based on the state data. Each frame corresponds to the state of a dynamic image element at a given time point. The time interval of the frame sequence is consistent with the minimum time unit in the time node information of the performance segment.

[0075] The state data is converted into a frame sequence: the state data at each time point generates a frame image, the resolution of the frame matches the output resolution of the holographic projection device, and the frame format is a holographic projection-specific format (such as a format that supports depth information).

[0076] The time intervals of the frame sequence are strictly matched with the minimum time unit of the performance segment (such as the beat interval of the song) to ensure that the movement rhythm of dynamic elements is synchronized with the performance; at the same time, timestamps are added to the frame sequence to facilitate time alignment during subsequent choreography.

[0077] Step S1289: Perform inter-frame transition processing on the frame sequence, adjust the change amplitude of state parameters between adjacent frames, integrate the processed frame sequence, and form dynamic image elements containing the time dimension change law. The time length of the dynamic image elements matches the time length of the corresponding performance segment in the stage performance theme information.

[0078] The dynamic effects are optimized through inter-frame transition processing. The specific process is as follows:

[0079] Step S1289-1: Extract the dynamic image element state parameters of two adjacent frames in the frame sequence. The dynamic image element state parameters include the position coordinates, shape parameters, and color parameters of the adjacent previous frame, as well as the position coordinates, shape parameters, and color parameters of the adjacent subsequent frame.

[0080] Extract the state parameters of two adjacent frames (such as frame A and frame B): the position coordinates, the virtual singer's body angle parameters, and the main color HSV value of frame A; the position coordinates, body angle parameters, and the main color HSV value of frame B.

[0081] The parameters are categorized and organized by dimension to form a parameter comparison table between frame A and frame B.

[0082] Step S1289-2: Calculate the Euclidean distance difference between the position coordinates of the adjacent previous frame and the adjacent next frame to obtain the position difference; calculate the scalar difference of the morphological parameters between the adjacent previous frame and the adjacent next frame to obtain the morphological difference; calculate the color difference of the color parameters between the adjacent previous frame and the adjacent next frame to obtain the color difference.

[0083] Calculate positional difference: Calculate the spatial distance between the position coordinates of frame A and frame B using the Euclidean distance formula; Calculate morphological difference: Convert morphological parameters such as limb angles into scalar values ​​and then calculate the difference; Calculate color difference: Calculate the color difference of the main color tone of the two frames based on the HSV color space (combining differences in hue, saturation, and brightness).

[0084] Step S1289-3: Determine the transition smoothness requirement between adjacent frames based on the combined magnitude of the position difference, shape difference, and color difference. The larger the combined difference, the higher the transition smoothness requirement.

[0085] The three differences are summed according to their weights to obtain a comprehensive difference (such as position difference weight, shape difference weight, and color difference weight). The smoothness level is divided according to the magnitude of the comprehensive difference (such as low, medium, and high). The larger the comprehensive difference, the higher the smoothness level, and more transition frames need to be generated to ensure smoothness.

[0086] Step S1289-4: Based on the transition smoothness requirements, determine the transition processing method between adjacent frames. The transition processing methods include linear transition processing, curve transition processing, and segmented transition processing.

[0087] The processing method is selected based on the smoothness level: low smoothness level corresponds to linear transition processing, medium smoothness level corresponds to curved transition processing, and high smoothness level corresponds to segmented transition processing. For example, a virtual singer with slight changes in body angle (small shape difference) and short position movement distance (small position difference) has a low overall difference level and uses linear transition processing; a virtual singer moving from the left side of the stage to the right side (large position difference) accompanied by large body swaying (large shape difference) has a high overall difference level and uses segmented transition processing.

[0088] Step S1289-5: If linear transition processing is adopted, the difference change is evenly distributed according to the position difference, shape difference and color difference according to the inter-frame time interval to generate the state parameters of the transition frame. The number of transition frames is determined based on the difference size and frame rate requirements.

[0089] When using linear transition processing, first determine the inter-frame time interval (consistent with the performance rhythm nodes), then divide the position difference into N equal parts (N being the number of transition frames) according to the time interval. The position parameter of each transition frame is the position parameter of the previous frame plus the corresponding equal part of position change. Similarly, the shape difference and color difference are evenly distributed according to the time interval to generate the shape and color parameters of each transition frame. The number of transition frames is adjusted according to the size of the difference: the smaller the difference, the fewer the number of transition frames; the larger the difference, the more the number of transition frames. At the same time, it is necessary to meet the frame rate requirements of the holographic projection device to ensure a smooth transition process.

[0090] Step S1289-6: If a curve transition is used, construct a difference change curve function based on the time progress, calculate the difference allocation at different transition times based on the curve function, generate the state parameters of the transition frame, and adjust the curvature of the curve function according to the transition smoothness requirements.

[0091] When using curve transition processing, a difference change curve function (such as a quadratic or cubic curve) is constructed using the time progress (0 to 1, where 0 corresponds to the previous frame and 1 corresponds to the next frame) as the independent variable. For example, when constructing a quadratic curve function, the difference change is small in the early stage, increases in the middle stage, and decreases in the later stage, giving the transition a "slow start-acceleration-slow stop" effect. The curve curvature is adjusted according to the smoothness requirements: medium smoothness corresponds to a gentle curvature, resulting in a uniform transition; near-high smoothness corresponds to a larger curvature, making the transition more in line with the laws of natural motion. Based on the curve function, the position, shape, and color difference distribution at each transition moment are calculated to generate transition frame parameters.

[0092] Step S1289-7: If segmented transition processing is adopted, the difference is divided into multiple segments based on the rate of change, a corresponding transition rate is configured for each segment, and the state parameters of each transition frame are calculated based on the segmented transition rate. The number of segments is positively correlated with the size of the difference.

[0093] When using segmented transition processing, the position difference is divided into multiple segments (such as acceleration, constant speed, and deceleration segments) according to the rate of change. Each segment is configured with a different transition rate: the rate gradually increases in the acceleration segment, the rate remains stable in the constant speed segment, and the rate gradually decreases in the deceleration segment. For example, the position difference of a virtual singer's movement is divided into three segments: the rate in the first segment (acceleration segment) gradually increases from the initial value to the peak value; the rate in the second segment (constant speed segment) remains at the peak value; and the rate in the third segment (deceleration segment) gradually decreases from the peak value to 0. The number of segments increases as the difference increases; when the difference is extremely large, it can be divided into 4-5 segments. Based on the transition rate and time interval of each segment, the parameter values ​​of each transition frame are calculated to ensure that the motion process is natural and smooth.

[0094] Step S1289-8: Insert the generated transition frame between the adjacent previous frame and the adjacent next frame to form a new frame sequence containing the transition frame.

[0095] Transition frames generated by linear, curved, or segmented transition processing are inserted sequentially between the preceding and following frames to form a complete new frame sequence. After insertion, the timestamps of the frame sequence are recalibrated to ensure that the timestamps of each frame are continuous and match the time nodes of the performance segment. Finally, a dynamic image element containing the changing patterns of the time dimension is formed, and the total duration of the dynamic image element is completely consistent with the duration of the corresponding performance segment.

[0096] Step S129: Integrate the static image elements and dynamic image elements, and perform quantity verification on the integrated image elements according to the number of categories in the core element type description to ensure that the number of static image elements and dynamic image elements corresponds to the number of element categories mentioned in the core element type description, thus forming an initial holographic projection image element set.

[0097] The generated static image elements (such as digital city skylines and static images of virtual singers) and dynamic image elements (such as dynamic frame sequences of virtual singers and dynamic effects of particle instruments) are categorized and integrated according to element types (scenes, characters, props). The number of categories is verified against the descriptions in the core element types: for example, if scene element categories are required to include 4 types (digital city skyline, neon streets, virtual stage background, data stream tunnel), it must be confirmed that static and dynamic scene elements cover all 4 types; if character element categories are required to include 3 types (virtual singer, particle dancers, symbolic characters), it must be confirmed that no character elements are missing any categories. If there are missing categories or mismatches in the number of categories, the process returns to the generation module to regenerate or supplement the elements. After successful verification, an initial set of holographic projection image elements is formed, with each element labeled with its category, parameter information, and theme matching degree.

[0098] Step S130: Divide the performance into stages according to the time node information of the performance segment, and perform phased dynamic choreography on the initial holographic projection image element set in combination with the virtual interaction trigger condition information to obtain a dynamic holographic projection image sequence.

[0099] Based on the performance time nodes and interactive trigger conditions, the image elements are arranged in stages, and the specific process is as follows.

[0100] Step S131: Analyze the time node information of the performance segment, divide the performance into multiple consecutive performance stages according to the interval characteristics of the time nodes, mark the stage duration information for each performance stage, and each performance stage corresponds to a performance content theme.

[0101] The performance is divided into stages based on time node information and interval characteristics: the opening stage (from the start of the concert to the intro of the first song), with a duration matching the opening light show; the song 1 stage (including intro, verse 1, chorus 1, interlude, verse 2, chorus 2, and outro), with a duration consistent with the total duration of song 1; the interactive stage (from the end of song 1 to the intro of song 2), with a duration matching the preset interactive duration; and subsequent stages are divided into song 2-5 stages, a mid-show transition stage, and a closing stage. Each stage is marked with clear start and end timestamps and corresponds to a specific performance theme: for example, the opening stage theme is "creating a technological atmosphere," the song 1 stage theme is "virtual singer dancing with particle effects," and the interactive stage theme is "audience-participated light and shadow interaction."

[0102] Step S132: Classify the static and dynamic image elements in the initial holographic projection image element set. The classification labeling results include matching information with the content theme of each performance stage.

[0103] Each image element was categorized: the static element "Digital City Skyline" was labeled "Scene - Atmosphere Creation," the dynamic element "Virtual Singer Dance Frame Sequence" was labeled "Character - Singing and Dancing," and the dynamic element "Audience Glow Stick Interactive Light and Shadow" was labeled "Interactive - Audience Participation." Simultaneously, the matching degree between each element and the theme of each performance stage was calculated through thematic keyword matching: for example, "Digital City Skyline" had a high matching degree with the opening stage's theme of "Technological Atmosphere Creation," but a low matching degree with the interactive stage's theme of "Audience Participation Light and Shadow Interaction"; "Audience Glow Stick Interactive Light and Shadow" had a high matching degree with the interactive stage's theme, but a low matching degree with other stages. The matching degree was divided into three levels: high, medium, and low, determined based on the overlap between the element's core features and the theme requirements.

[0104] Step S133: Assign corresponding static image elements and dynamic image elements to each performance stage according to the matching degree information, so that the assigned image elements are adapted to the content theme of the performance stage, forming the initial image element group for each performance stage.

[0105] Elements are assigned to each stage based on matching priority: elements with high matching scores are prioritized, followed by elements with medium matching scores, and elements with low matching scores are not assigned. The opening stage is assigned "Digital City Skyline" (static), "Dynamic Data Stream Background" (dynamic), and "Neon Particle Diffusion Effect" (dynamic), forming the initial element group for the opening stage, fitting the "Technological Atmosphere Creation" theme. The Song 1 stage is assigned "Virtual Singer Dance Frame Sequence" (dynamic), "Particle Instrument Dynamic Effect" (dynamic), and "Virtual Stage Background" (static), forming the Song 1 element group, fitting the "Virtual Singer Dancing with Particle Effects" theme. The interactive stage is assigned "Audience Glow Stick Interactive Light and Shadow" (dynamic) and "Dynamic Symbolic Character (Digital Note)" (dynamic), forming the interactive stage element group, fitting the "Audience Participation in Light and Shadow Interaction" theme. Each element group is labeled with its element identifier, element type, and fitting description for the stage theme.

[0106] Step S134: Analyze the virtual interaction triggering condition information, determine the type and triggering time of the virtual interaction triggering event, and mark the triggering priority for each type of virtual interaction triggering event. The types of virtual interaction triggering events include audience interaction virtual interaction triggering events, stage equipment status virtual interaction triggering events, and performance action virtual interaction triggering events.

[0107] Analyze the trigger condition information to identify three types of trigger events: audience interaction trigger events (such as "audience glow sticks covering more than 50% of the front area of ​​the stage" or "the on-site decibel level exceeds a set threshold"), triggered at any time during the interaction phase; stage equipment trigger events (such as "lights switch to blue neon mode" or "the platform rises to a preset height"), triggered synchronously with the start time of the first chorus of song 1; and performance action trigger events (such as "the singer makes a right-hand raised gesture" or "the dance team completes a specific formation change"), triggered synchronously with the start time of the interlude of song 1. Mark each event with a trigger priority: performance action trigger events have the highest priority (directly related to the performance rhythm), stage equipment trigger events have a medium priority (supporting the performance atmosphere), and audience interaction trigger events have a medium or high priority set according to the needs of the interaction phase.

[0108] Step S135: Based on the type and trigger priority of the virtual interaction trigger event, construct a target association rule, which includes the image element switching method and image element switching timing corresponding to different virtual interaction trigger events.

[0109] The rules are constructed using the following sub-steps:

[0110] Step S1351: Perform attribute analysis on the types of virtual interaction trigger events to determine the influence range corresponding to each type of virtual interaction trigger event. The influence range includes the category range of image element switching and the time influence range.

[0111] Analyzing event attributes: The performance action-triggered event "Singer raises right hand" affects both character and prop elements (switching virtual singer actions and particle instrument forms), and its time impact is a short period after the trigger (matching the gesture duration); the stage equipment-triggered event "Lights switch to blue neon mode" affects both scene and character elements (adjusting background color and virtual singer costume colors), and its time impact is the duration of the lighting mode; the audience interaction-triggered event "Glow sticks cover 50% of the front area" affects both interactive and scene elements (activating audience area lighting effects and adjusting background particle density), and its time impact is the remaining duration of the interaction phase.

[0112] Step S1352: Based on the scope of influence of the virtual interactive triggering event and the preset priority determination criteria, assign a trigger priority to each virtual interactive triggering event. The priority determination criteria include the size of the scope of influence and the degree of correlation with the performance content.

[0113] Preset priority criteria: Events closely related to the performance content (such as directly accompanying the singer's movements) and with a clear scope of impact have high priority; events with a wide scope of impact but moderate relevance have medium priority. Priorities are assigned accordingly: performance-triggered events have priority 1 (highest), stage equipment-triggered events have priority 2 (medium), and audience interaction-triggered events have priority 2 during the interaction phase and priority 3 (low) in other phases. The lower the priority value, the higher the trigger response.

[0114] Step S1353: Based on the type, trigger priority, and scope of influence of the virtual interaction trigger event, construct target association rules. The target association rules include: instant switching rules corresponding to virtual interaction trigger events with first priority, delayed switching rules corresponding to virtual interaction trigger events with second priority, and conditional trigger switching rules corresponding to virtual interaction trigger events with third priority.

[0115] Three categories of rules are constructed based on priority: the first priority (priority 1) corresponds to immediate switching rules, the second priority (priority 2) corresponds to delayed switching rules, and the third priority (priority 3) corresponds to condition-triggered switching rules. The first priority is the highest, the second priority is next, and the third priority is the lowest.

[0116] Step S1354: The instant switching rule is defined as immediately initiating the image element switching process when a first-priority virtual interaction trigger event occurs, and the switching response time does not exceed the minimum time interval in the performance segment time node information.

[0117] The instant switching rule is specifically defined as follows: When a performance action triggers an event (such as the singer raising their right hand), the switching process is initiated within the minimum time interval, switching the virtual singer's action from "standing" to "waving", and the particle instrument from "static" to "glowing and spreading", ensuring that the image elements are synchronized with the singer's actions without any obvious delay.

[0118] Step S1355: The delayed switching rule is defined as starting the image element switching process after a preset time delay when a virtual interaction trigger event of the second priority occurs. The preset time is determined according to the interval between adjacent performance stages.

[0119] The specific definition of the delayed switching rule is as follows: When a stage equipment triggers an event (such as the lights switching to blue neon mode), after a preset delay (such as the same as the gradient time of the light switching), the scene element switching is initiated, and the virtual stage background color is switched from "purple" to "blue". The brightness of the virtual singer's clothing texture is increased synchronously, so that the image switching and the light change are coordinated and consistent, avoiding visual conflicts.

[0120] Step S1356: The condition-triggered switching rule is defined as follows: when a virtual interaction trigger event of the third priority occurs, the image element switching process can only be started after the preset additional trigger conditions are met.

[0121] The specific definition of the condition-triggered switching rule is as follows: When an audience interaction trigger event (such as the decibel value exceeding the threshold) occurs, the additional trigger condition of "currently in the interaction stage" must be met simultaneously to initiate the switching of interactive elements, activate the lighting and shadow effects in the audience area, and adjust the movement trajectory of the dynamic symbolic characters to match the element switching with the interaction scene; if it is not in the interaction stage, the switching will not be initiated even if the decibel value meets the threshold.

[0122] Step S136: Based on the duration information of each performance stage and the triggering time of the virtual interactive triggering event, arrange the initial image element groups of each performance stage in timeline order to form an initial timeline image sequence.

[0123] Based on the timeline, arrange the element groups in the order of performance stages: Opening stage element group (corresponding to opening duration) — Song 1 stage element group (corresponding to song 1 duration) — Interaction stage element group (corresponding to interaction duration) — Song 2 stage element group — ... — Closing stage element group. Mark the start and end timestamps of each element group on the timeline to ensure a perfect match with the performance stage duration. For example, the opening stage element group starts at timestamp 0 and ends at timestamp T1 (T1 is the opening duration); the song 1 stage element group starts at T1 and ends at T1+T2 (T2 is the song 1 duration). At the same time, mark the trigger times of virtual interactive events at the corresponding positions on the timeline, such as marking the stage equipment trigger event at timestamp T1+T3 when the first timetamp of the first chorus of song 1 begins, and marking the performance action trigger event at timestamp T1+T4 when the first timetamp of the interlude begins.

[0124] Step S137: According to the target association rule, set an image element switching mark at the time position corresponding to the virtual interaction trigger event in the initial time axis image sequence, and define the image element to be switched and the target switching image element at the image element switching mark.

[0125] Traverse the initial timeline image sequence and set a switching marker at the time position corresponding to the trigger event: At the stage equipment trigger event time (T1+T3) of Song 1's chorus, set the marker "Device-Scene Switch," defining the image element to be switched as "purple virtual stage background" and the target image element to be switched as "blue virtual stage background"; at the performance action trigger event time (T1+T4) of Song 1's interlude, set the marker "Action-Role Switch," defining the image element to be switched as "virtual singer standing frame sequence" and the target image element to be switched as "virtual singer waving frame sequence"; at the audience interaction trigger event time (T1+T2+T5) of the interactive phase, set the marker "Audience-Interaction Switch," defining the image element to be switched as "static digital note" and the target image element to be switched as "dynamic responsive digital note." Each switching marker includes the event type, trigger priority, ID of the element to be switched, ID of the target element, and switching rule type (immediate / delayed / conditional).

[0126] Step S138: Perform visual coherence processing on the timeline image sequence containing the image element switching markers, adjust the transition parameters between the image element to be switched and the target image element to be switched at the switching markers, so that adjacent image elements achieve a visually smooth transition when switching, and then integrate the processed timeline image sequence to form a dynamic holographic projection image sequence.

[0127] For elements at the transition markers, a smooth transition is implemented: For the "device-scene transition" (purple to blue background), the transition parameters are adjusted to "gradual transition," setting the background hue to gradually transition from purple to blue, while maintaining stable saturation and brightness, and the transition duration is consistent with the light transition duration; for the "action-character transition" (standing to waving), an "inter-frame transition" is used, inserting 3-5 transition frames to gradually raise the virtual singer's arm from a drooping position to a waving posture, avoiding any jerky movements; for the "audience-interaction transition" (static to dynamic notes), a "scaling + glowing" transition effect is set, gradually enlarging the digital notes from a static state and increasing their glow intensity, while simultaneously initiating changes in their motion trajectory. After all transition processing is completed, the element groups, transition markers, and transition frames of each stage are integrated into a complete timeline sequence, forming a dynamic holographic projection image sequence. This dynamic holographic projection image sequence contains all image elements and interactive response logic from the beginning to the end, with the timeline accuracy completely synchronized with the performance rhythm.

[0128] Step S140: Collect real-time interactive data from the stage, establish a correlation logic between the real-time interactive data and the image sequence adjustment, and perform parameter adjustment processing on the dynamic holographic projection image sequence according to the correlation logic to obtain an optimized dynamic holographic projection image sequence.

[0129] The image sequence parameters are dynamically adjusted through real-time data acquisition and analysis. The specific process is as follows.

[0130] Step S141: Collect real-time interactive stage data through stage data acquisition equipment. The real-time interactive stage data includes audience interaction data, stage equipment operation data, and performer action data. The audience interaction data includes the frequency of interactive behavior and the distribution of interactive areas. The stage equipment operation data includes the equipment working mode and the equipment output status. The performer action data includes the action frequency and the action amplitude.

[0131] Multiple types of data acquisition devices are deployed to obtain real-time data: Infrared cameras and decibel sensors are deployed in the audience area to collect audience interaction data—interaction frequency (number of times audience members raise glow sticks and wave their hands per unit time) and interaction area distribution (audience interaction density divided by stage area, such as the proportion of interactive people in the front, middle, and back areas); status sensors are deployed on stage equipment to collect operational data—equipment working modes (resolution mode and projection mode of holographic projection equipment; color mode and brightness mode of lighting equipment) and equipment output status (light output intensity and temperature of projection equipment; actual brightness and color deviation of lighting equipment); motion capture cameras and motion sensors are deployed in the performer area to collect motion data—motion frequency (frequency of singer's hand gesture changes and beat matching degree of dance movements) and motion amplitude (spatial movement distance of hand gestures and range of angle changes of limb joints). The collected data is synchronized with millisecond-level timestamps to ensure data time sequence consistency.

[0132] Step S142: Extract features from the audience interaction data to obtain the interaction frequency feature value and the spatial distribution feature of the interaction area per unit time. Determine the direction of the display frequency adjustment of the dynamic image element based on the comparison result of the interaction frequency feature value and the preset threshold. Determine the direction of the display area adjustment of the image element based on the mapping relationship between the spatial distribution feature and the stage area.

[0133] Feature extraction from audience interaction data: The number of times glow sticks are raised and the frequency of waving are counted per unit time, and after normalization, interaction frequency feature values ​​are obtained. These interaction frequency feature values ​​comprehensively reflect the level of audience participation and activity. The data on the distribution of interaction areas is converted into spatial distribution features. By dividing the stage area into grids (dividing the stage and audience area into multiple grid units), the proportion of interactive participants in each grid unit is counted to form a spatial distribution heatmap feature.

[0134] The interaction frequency characteristic value is compared with a preset threshold: if the characteristic value is higher than the threshold, it indicates active audience participation, and the display frequency of dynamic image elements (such as particle effects and digital musical notes) is adjusted to increase; if the characteristic value is lower than the threshold, it indicates insufficient audience participation, and the adjustment direction is to decrease. Based on the mapping relationship between spatial distribution characteristics and stage areas (such as the front area of ​​the audience corresponding to the front projection area of ​​the stage, and the middle area corresponding to the middle area of ​​the stage), if the interaction density of a certain area is high, the adjustment direction of the image element display area corresponding to that area is to expand the coverage and enhance visual prominence; if the interaction density of a certain area is low, the adjustment direction is to reduce the coverage or reduce the visual intensity.

[0135] Step S143: Perform feature analysis on the stage equipment operation data, extract the image resolution adaptation parameters corresponding to the equipment working mode and the light output parameters corresponding to the equipment output state, determine the resolution adjustment direction of the image elements according to the resolution adaptation parameters, and determine the brightness adjustment direction of the image elements according to the light output parameters.

[0136] Feature analysis of stage equipment operation data: Extract resolution adaptation parameters (such as pixel density parameters corresponding to the current resolution level of the holographic projection equipment) from the working mode of the holographic projection equipment. If the equipment switches to low resolution mode, the resolution adaptation parameters decrease, and the resolution adjustment direction of the image elements is determined to be decreasing (such as simplifying texture details and reducing the number of pixels) to ensure smooth image output; if the equipment switches to high resolution mode, the resolution adaptation parameters increase, and the adjustment direction is increasing (such as increasing texture details and increasing pixel density).

[0137] Extract light output parameters from the device output status (such as the actual light output intensity of the projection device and the brightness output value of the lighting device): compare the light output parameters with the device's rated output parameters. If the actual light output intensity is lower than the rated value, determine that the brightness adjustment direction of the image elements is to increase (such as increasing the image's brightness parameter) to compensate for insufficient light output; if the actual light output intensity is higher than the rated value, adjust the direction to decrease to avoid overexposure of the image.

[0138] Step S144: Perform feature analysis on the performer's motion data to obtain motion frequency feature parameters and motion amplitude feature parameters based on spatial coordinate changes per unit time. Determine the motion rhythm adjustment direction of the image element based on the deviation between the motion frequency feature parameters and the preset reference frequency. Determine the motion range adjustment direction of the image element based on the deviation between the motion amplitude feature parameters and the preset reference amplitude.

[0139] Feature analysis is performed on the performer's motion data: the number of hand gesture changes by the singer and the number of beat matches of the dance movements are statistically analyzed per unit time. After standardization, motion frequency characteristic parameters are obtained, which reflect the speed of the performer's movements. The spatial coordinate changes of the performer's limb joints are recorded by a motion capture system, and the maximum distance and angle range of the coordinate changes are calculated to obtain motion amplitude characteristic parameters, which reflect the degree of extension of the movements.

[0140] The motion frequency characteristic parameters are compared with a preset reference frequency (a standard motion frequency set based on the song rhythm): if the parameter is higher than the reference frequency, it indicates that the performer's movements are faster, and the direction of adjusting the motion rhythm of image elements (such as virtual singer dancers, dynamic backgrounds) is to speed up; if the parameter is lower than the reference frequency, the adjustment direction is to slow down. The motion amplitude characteristic parameters are compared with a preset reference amplitude: if the parameter is greater than the reference amplitude, it indicates that the movements are more expansive, and the direction of adjusting the motion range of image elements is to expand (such as increasing the diffusion range of particle effects, the movement distance of virtual characters); if the parameter is less than the reference amplitude, the adjustment direction is to shrink.

[0141] Step S145: Combining all the above adjustment directions, construct the association logic between real-time interactive data and image sequence adjustment. The association logic includes the correspondence between interactive data features and image parameter adjustment amounts, the correspondence between device data features and image parameter adjustment amounts, and the correspondence between action data features and image parameter adjustment amounts.

[0142] The association logic is constructed through the following sub-steps:

[0143] Step S1451: Divide the interaction frequency feature value of the audience interaction data into multiple feature intervals based on statistical distribution, and assign a corresponding dynamic image element display frequency adjustment coefficient to each feature interval. The higher the interaction frequency corresponding to the feature interval, the larger the assigned display frequency adjustment coefficient.

[0144] The interaction frequency characteristic value is divided into multiple characteristic intervals from low to high (such as low activity, medium activity, and high activity). Each interval corresponds to a display frequency adjustment coefficient: the low activity interval corresponds to a small coefficient (small adjustment range), and the high activity interval corresponds to a large coefficient (large adjustment range). For example, the adjustment coefficient of the high activity interval can increase the display frequency of dynamic image elements to several times the original frequency, while the low activity interval only needs to be finely adjusted or not adjusted at all.

[0145] Step S1452: Convert the interactive region feature distribution of the audience interaction data into a region weight value based on the region importance, and assign corresponding image element display area adjustment weights to different interactive regions. The higher the weight value of the interactive region, the greater the adjustment of the proportion of image element display in the corresponding interactive region.

[0146] The importance of interactive areas is determined based on their spatial distribution characteristics: areas with high interaction density (such as the center of the front area) have high weight values, while areas with low interaction density (such as the edges of the back area) have low weight values. Each area is assigned a display area adjustment weight; the higher the weight value, the greater the adjustment in the proportion of image elements displayed in that area. For example, the coverage area of ​​image elements in high-weight areas can be increased by a certain percentage, while the coverage area in low-weight areas can be reduced.

[0147] Step S1453: Match the operating mode of the stage equipment with the preset resolution adaptation table to determine the resolution reference value corresponding to each operating mode. Calculate the resolution adjustment coefficient based on the deviation between the equipment output state and the reference output state. The larger the deviation value, the larger the absolute value of the resolution adjustment coefficient.

[0148] A preset resolution adaptation table is used to define the corresponding resolution baseline values ​​(such as pixel density and texture detail level) for different device operating modes (low, medium, and high resolution modes). The deviation between the actual device output state and the baseline output state (such as the difference between the actual resolution and the baseline resolution) is calculated. Based on the deviation value, a resolution adjustment coefficient is calculated: when the deviation value is positive (actual resolution is higher than the baseline), the coefficient is positive (increasing image resolution); when the deviation value is negative, the coefficient is negative (reducing image resolution). Furthermore, the larger the absolute value of the deviation value, the larger the absolute value of the coefficient, and the more significant the adjustment.

[0149] Step S1454: Compare the brightness output value in the device output status of the stage equipment operation data with the preset brightness standard value, calculate the brightness deviation ratio, and determine the brightness adjustment amount based on the brightness deviation ratio. If the deviation ratio is positive, the brightness adjustment amount is reduced; if the deviation ratio is negative, the brightness adjustment amount is increased.

[0150] Calculate the brightness deviation ratio = (actual brightness output value - preset brightness standard value) / preset brightness standard value. If the deviation ratio is positive (actual brightness is too high), determine the brightness adjustment amount to be negative (reduce the image brightness parameter); if the deviation ratio is negative (actual brightness is too low), the adjustment amount to be positive (increase the image brightness parameter). The magnitude of the adjustment amount is proportional to the absolute value of the deviation ratio.

[0151] Step S1455: Compare the motion frequency feature parameters of the performer's motion data with the motion rhythm baseline parameters of the image elements, calculate the rhythm deviation rate, and determine the motion rhythm adjustment amount based on the rhythm deviation rate. If the deviation rate is positive, the motion rhythm adjustment amount is increased; if the deviation rate is negative, the motion rhythm adjustment amount is decreased.

[0152] Set the baseline parameter for the motion rhythm of the image elements (the standard rhythm value synchronized with the song's beat), and calculate the rhythm deviation rate = (motion frequency characteristic parameter - rhythm baseline parameter) / rhythm baseline parameter. If the deviation rate is positive (the performer's movements speed up), the motion rhythm adjustment amount is positive (increase the speed of the image element's movement); if the deviation rate is negative, the adjustment amount is negative (decrease the speed of movement), and the magnitude of the adjustment amount varies with the absolute value of the deviation rate.

[0153] Step S1456: Compare the motion amplitude feature parameters of the performer's motion data with the motion range reference parameters of the image elements, calculate the range deviation rate, and determine the motion range adjustment amount based on the range deviation rate. If the deviation rate is positive, the motion range adjustment amount is increased; if the deviation rate is negative, the motion range adjustment amount is decreased.

[0154] Set the baseline parameters for the motion range of image elements (such as the standard diffusion radius of particle effects or the standard movement range of virtual characters), and calculate the range deviation rate = (motion amplitude characteristic parameter - range baseline parameter) / range baseline parameter. If the deviation rate is positive (the performer's motion amplitude increases), the motion range adjustment is positive (expanding the motion range of image elements); if the deviation rate is negative, the adjustment is negative (reducing the motion range), and the adjustment amount matches the absolute value of the deviation rate.

[0155] Step S1457: Integrate all the above calculation logic of adjustment coefficients, adjustment weights and adjustment amounts to construct the association logic of real-time interactive data and image sequence adjustment. The association logic includes data feature input items, parameter adjustment amount output items and the calculation mapping relationship between the two.

[0156] The data features input items (such as interaction frequency feature value, resolution deviation value, rhythm deviation rate, etc.) of audience interaction, equipment operation, and performer movements are linked with the corresponding image parameter adjustment output items (such as display frequency adjustment amount, resolution adjustment amount, rhythm adjustment amount, etc.) through calculation mapping relationships to form an association logic table. For example, the input item "interaction frequency feature value (high activity) + rhythm deviation rate (positive)" corresponds to the output item "display frequency adjustment amount (+large) + movement rhythm adjustment amount (+medium)", ensuring that multi-dimensional data features work synergistically for image adjustment.

[0157] Step S146: Calculate the parameter adjustment amount of each image element in the dynamic holographic projection image sequence according to the association logic. The parameter adjustment amount includes the display frequency adjustment amount, display area adjustment amount, resolution adjustment amount, brightness adjustment amount, motion rhythm adjustment amount, and motion range adjustment amount.

[0158] For each image element (such as a virtual singer, particle instrument, or dynamic background) in the dynamic holographic projection image sequence, the corresponding input data features are matched from the association logic based on its element type and current state: for particle effect elements, the interaction frequency feature value, motion frequency feature parameter, and device brightness output value are matched; for virtual singer elements, the motion amplitude feature parameter, device resolution mode, and spatial distribution features are matched.

[0159] Based on the matched input features and the computational mapping relationship in the association logic, the adjustment amounts of each parameter of the element are calculated one by one: the display frequency adjustment amount is calculated based on the interaction frequency feature value and the adjustment coefficient; the display area adjustment amount is determined based on the interaction area weight value; the resolution adjustment amount is calculated based on the device resolution deviation value and the adjustment coefficient; the brightness adjustment amount is generated based on the brightness deviation ratio; the motion rhythm adjustment amount is derived from the rhythm deviation rate; and the motion range adjustment amount is calculated based on the range deviation rate. All adjustments are labeled with the adjustment direction (increase / decrease, expand / shrink) and the adjustment magnitude level (small / medium / large).

[0160] Step S147: Modify the parameters of each image element in the dynamic holographic projection image sequence according to the parameter adjustment amount to obtain the adjusted image elements. Recombine the adjusted image elements in the original time axis order to form the adjusted dynamic holographic projection image sequence.

[0161] Based on the calculated parameter adjustments, the parameters of each image element are modified accordingly: For particle effect elements, if the display frequency adjustment is set to "Increase - Medium," the number of particles generated per unit time and the flashing frequency are increased; if the display area adjustment is set to "Expand - Front Area," the generation range of the particle effect is expanded to the stage projection area corresponding to the front area of ​​the audience. For virtual singer elements, if the movement rhythm adjustment is set to "Speed ​​Up - Small," the frame interval of their dance movements is shortened; if the movement range adjustment is set to "Expand - Left Area," their movement path in the stage coordinate system is adjusted, increasing the movement distance in the left area. For dynamic background elements, if the resolution adjustment is set to "Decrease - Medium," the detail levels of the background texture are simplified; if the brightness adjustment is set to "Increase - Large," the brightness parameter value of the background image is increased.

[0162] All image elements with modified parameters are rearranged and combined in the original timeline order to ensure that the appearance time of the elements, the switching logic and the time nodes of the performance are consistent with the time nodes of the performance, forming an adjusted dynamic holographic projection image sequence.

[0163] Step S148: Perform an overall visual consistency check on the adjusted dynamic holographic projection image sequence, and fine-tune the image element parameters based on the check results to obtain the optimized dynamic holographic projection image sequence.

[0164] The visual coordination verification module is activated to perform multi-dimensional verification on the adjusted image sequence: verifying the parameter coordination between different elements (such as whether the movement rhythm of the virtual singer is synchronized with the display frequency of particle effects, and whether the brightness of the background and the brightness of the foreground elements are compatible); verifying the coordination between image elements and the stage environment (such as whether the image resolution matches the actual output capability of the projection device, and whether the color style and lighting mode conflict); and verifying the coordination between the image sequence and the performance rhythm (such as whether the timing of element switching matches the intro and chorus of the song).

[0165] If inconsistencies are found during verification (such as particle effects being too fast and out of sync with the virtual singer's movements, or background brightness being too high and obscuring foreground elements), fine-tune the corresponding parameters based on the problem type: reduce the display frequency of particle effects to match the rhythm of the virtual singer's movements; reduce the background brightness adjustment to ensure that foreground elements are clearly visible. After fine-tuning, verify again until the image sequence achieves harmony in visual effects, device compatibility, and rhythm synchronization, ultimately forming an optimized dynamic holographic projection image sequence.

[0166] Step S150: Construct a holographic projection output parameter system based on the optimized dynamic holographic projection image sequence, generate a holographic projection image generation instruction containing the output parameter system, and send the holographic projection image generation instruction to the holographic projection device to drive the holographic projection device to output a holographic projection image.

[0167] The final output of the holographic image is achieved through parameter system construction and instruction generation. The specific process is as follows.

[0168] Step S151: Extract the image data information and timestamp information of each image frame in the optimized dynamic holographic projection image sequence. The image data information includes image pixel data, image size data, and image color depth data.

[0169] The optimized image sequence is traversed, and the core data of each image frame is extracted: image pixel data includes the color value (HSV format) and depth value (reflecting the pixel's position in three-dimensional space) of each pixel within the frame; image size data includes the width and height of the frame in pixels and its corresponding physical dimensions (adapting to the stage projection area size); image color depth data includes the number of bits per pixel (determining color accuracy). Simultaneously, the timestamp information of each image frame (accurate to milliseconds) is extracted to determine the frame's playback time. This information is then organized according to the frame sequence to form an image frame data list.

[0170] Step S152: Construct format adaptation parameters for the holographic projection image based on the image data information. The format adaptation parameters include pixel arrangement, size scaling ratio, and color depth conversion standard. The format adaptation parameters must match the input format supported by the holographic projection device.

[0171] Based on the technical specifications of the holographic projection equipment, determine the supported input format requirements and construct the format adaptation parameters: the pixel arrangement method is set to a device-compatible arrangement order (such as row priority or column priority) to ensure correct mapping of pixel data; the size scaling ratio is calculated based on the projection resolution of the equipment and the actual projection area size of the stage, so that the image frame can completely cover the projection area without distortion after scaling; the color depth conversion standard converts the color depth data of the image frame into the bit depth standard supported by the equipment (such as converting high color depth to a device-compatible bit depth while maintaining color fidelity).

[0172] Perform compatibility testing on the format adaptation parameters. Process the test image frame according to the parameters and input it into the device to verify whether the image can be displayed normally. If there are display abnormalities (such as color deviation or size misalignment), adjust the adaptation parameters until the adaptation is normal.

[0173] Step S153: Construct playback timing parameters for the holographic projection image based on the timestamp information. The playback timing parameters include the playback start time, playback duration, and inter-frame switching interval for each image frame. The playback timing parameters must be synchronized with the time node information of the performance segment.

[0174] Based on the timestamp information of the image frames and combined with the time nodes of the performance segments, playback timing parameters are constructed: the playback start time of each image frame corresponds to its timestamp, ensuring precise synchronization with the performance rhythm (such as song beats and action nodes); the playback duration is determined according to the frame rate of the frame sequence (for example, when the frame rate is a certain value, the duration of a single frame is the reciprocal of the frame rate); the inter-frame switching interval is set to be consistent with the duration to ensure smooth playback without stuttering.

[0175] Compare the playback timing parameters with the performance time node table, and check whether the playback time of key frames (such as the image frame at the beginning of the chorus of a song) matches the node perfectly. If there is a deviation (such as the frame playback time being earlier than the node), fine-tune the timestamp parameters to make the timing parameters completely synchronized with the performance nodes.

[0176] Step S154: Integrate the format adaptation parameters and playback timing parameters to construct a holographic projection output parameter system. The holographic projection output parameter system also includes image output accuracy parameters and projection area positioning parameters. The image output accuracy parameters are related to the image resolution, and the projection area positioning parameters are related to the stage space layout information.

[0177] The format adaptation parameters and playback timing parameters are integrated into the basic parameter layer, and two new core parameters are added to form a complete output parameter system: the image output precision parameter is set based on the image resolution, including sub-parameters such as pixel density and texture detail level. The higher the resolution, the higher the output precision parameter setting is to ensure clear image details; the projection area positioning parameter is set according to the stage space layout information (such as the installation position, angle, and projection distance of the projection equipment), including sub-parameters such as projection offset, rotation angle, and scaling factor, so that the image can be accurately projected onto the preset stage projection area (such as the central area of ​​the stage or the background wall area).

[0178] The parameter system adopts a hierarchical structure for storage: the basic parameter layer contains format and timing parameters, the extended parameter layer contains output precision and positioning parameters, and each layer of parameters is labeled with parameter name, data type, value range and device mapping relationship, which facilitates device parsing.

[0179] Step S155: Add parameter identification information to the holographic projection output parameter system. Each parameter corresponds to a unique identification code, which is used for parameter identification when the holographic projection device is resolving the parameter.

[0180] Assign a unique identifier code (such as a combination of numbers and letters) to each parameter in the parameter system. The encoding rules follow the device's parameter identification protocol. For example, the "pixel arrangement" in the format adaptation parameter corresponds to the code "FMT-PA-001", the "playback start time" in the playback timing parameter corresponds to the code "SEQ-ST-001", the "pixel density" in the image output precision parameter corresponds to the code "PRE-PD-001", and the "projection offset" in the projection area positioning parameter corresponds to the code "LOC-OF-001".

[0181] The correspondence between parameters and identifier codes is formed into a parameter coding table, which is sent to the device along with the parameter system to help the device quickly identify and match parameters.

[0182] Step S156: According to the communication protocol requirements of the holographic projection device, the holographic projection output parameter system containing parameter identification information is encapsulated into an instruction data structure. The instruction data structure includes an instruction header, a parameter area, and a verification area. The instruction header contains an instruction type identifier, the parameter area contains the specific data of the output parameter system, and the verification area contains a data integrity check code.

[0183] According to the communication protocols supported by the device (such as TCP / IP protocol, device-specific communication protocol), the instruction data structure is constructed as follows: The instruction header contains an instruction type identifier (such as a specific identifier code corresponding to "holographic image generation instruction"), instruction length, and sending timestamp, which are used by the device to identify the instruction type and basic information; The parameter area stores the specific data of the output parameter system (such as the combination of parameter identifier code and parameter value) in the order of parameter encoding, and the data format is a device-compatible binary format; The verification area uses the CRC check algorithm to calculate the check code of the parameter area data, which is used by the device to verify whether the data is complete and has not been tampered with after receiving the instruction.

[0184] The format of the encapsulated instruction data structure is validated to ensure that it conforms to the frame structure requirements of the communication protocol and to avoid instruction transmission failure due to format errors.

[0185] Step S157: Generate a holographic projection image generation instruction containing the instruction data structure, perform format conversion on the holographic projection image generation instruction, and establish a communication link with the holographic projection device.

[0186] Using the encapsulated instruction data structure as the core, complete holographic projection image generation instructions are generated. These instructions are then format-converted to a transmission format supported by the holographic projection device (such as binary stream format) to ensure correct parsing. Subsequently, a communication connection request is initiated through the device's communication interface (such as Ethernet or USB), verifying the correctness of the device's IP address and port number. Once the holographic projection device returns a connection confirmation response, a stable bidirectional communication link is established. This bidirectional communication link supports real-time interaction between instruction transmission and device status feedback data.

[0187] Step S158: The holographic projection image generation instruction is sent to the holographic projection device through the established communication link, so that after receiving the holographic projection image generation instruction, the holographic projection device loads the corresponding image data according to the output parameter system and controls the projection component to output the holographic projection image according to the playback timing parameters.

[0188] Through the established communication link, the holographic projection image generation command is sent to the holographic projection device using a data packet fragmentation transmission method. During transmission, the integrity of each data packet is verified in real time; if a data packet is lost or corrupted, a retransmission mechanism is immediately triggered. Upon receiving the command, the holographic projection device activates the command parsing module, parsing the output parameter system according to the parameter identifier encoding: First, it parses the format adaptation parameters, performing format conversion processing on the optimized dynamic holographic projection image sequence image data based on pixel arrangement, size scaling ratio, and color depth conversion standard to ensure the image data matches the device's input requirements; next, it parses the playback timing parameters, calibrating the playback start time, duration, and inter-frame switching interval of each image frame with the device's internal time synchronization module to ensure the playback rhythm is completely consistent with the performance's timing; finally, it parses the image output accuracy parameters and projection area positioning parameters, adjusting the device's projection resolution and light output intensity, and controlling the device's projection angle and focal length according to the projection area positioning parameters to ensure the projection range accurately covers the preset stage projection area.

[0189] After the device completes the parsing, the converted image data is loaded into the memory buffer. The projection control module is then activated, controlling the laser projection component, spatial light modulator, and other core components to output images frame by frame according to the playback timing parameters. During the output process, the device's status monitoring module collects real-time operating data such as projection brightness, color deviation, and device temperature, and feeds this data back to the stage control terminal via a communication link. If the feedback data shows abnormalities (such as brightness deviation exceeding the allowable range or device temperature being too high), the stage control terminal can generate parameter adjustment instructions based on preset anomaly handling rules and send them to the device via the communication link to adjust the projection parameters in real time. This ensures that the holographic projection image maintains a stable and clear output effect at all times, ultimately achieving a holographic projection presentation that is synchronized with the rhythm of a modern technology-themed concert and has a harmonious visual effect.

[0190] Figure 2 The illustration shows exemplary hardware and software components of a holographic projection image intelligent generation system 100 for virtual stage interaction, which can implement the ideas of this application, according to some embodiments of this application. For example, a processor 120 can be integrated into the holographic projection image intelligent generation system 100 for virtual stage interaction and used to perform the functions in this application.

[0191] The holographic projection image intelligent generation system 100 for stage virtual interaction can be a general-purpose server or a special-purpose server; both can be used to implement the holographic projection image intelligent generation method for stage virtual interaction of this application. Although only one server is shown in this application, for convenience, the functions described in this application can be implemented in a distributed manner on multiple similar platforms to balance the processing load.

[0192] For example, a holographic projection image intelligent generation system 100 for stage virtual interaction may include a network port 110 connected to a network, one or more processors 120 for executing program instructions, a communication bus 130, and various forms of storage media 140, such as a disk, ROM, or RAM, or any combination thereof. Exemplarily, the holographic projection image intelligent generation system 100 for stage virtual interaction may also include program instructions stored in ROM, RAM, or other types of non-transitory storage media, or any combination thereof. The methods of this application can be implemented according to the program instructions. The holographic projection image intelligent generation system 100 for stage virtual interaction also includes an I / O interface 150 between the computer and other input / output devices.

[0193] For ease of explanation, only one processor is described in the holographic projection image intelligent generation system 100 for stage virtual interaction. However, it should be noted that the holographic projection image intelligent generation system 100 for stage virtual interaction in this application may also include multiple processors. Therefore, the steps performed by one processor as described in this application may also be performed jointly or individually by multiple processors. For example, if the processor of the holographic projection image intelligent generation system 100 for stage virtual interaction performs steps A and B, it should be understood that steps A and B may also be performed jointly by two different processors or individually by one processor. For example, the first processor performs step A, the second processor performs step B, or the first processor and the second processor jointly perform steps A and B.

[0194] Furthermore, this embodiment of the invention also provides a readable storage medium, wherein computer-executable instructions are preset in the readable storage medium, and when the processor executes the computer-executable instructions, the above-mentioned intelligent generation method for holographic projection images applied to virtual stage interaction is implemented.

[0195] It should be noted that, in order to simplify the description of the present invention and thus help to understand one or more embodiments of the invention, multiple features may sometimes be grouped into one embodiment, drawing or description thereof in the foregoing description of the embodiments of the present invention.

Claims

1. A method for intelligent generation of holographic projection images applied to virtual stage interaction, characterized in that, The method includes: Obtain stage scene interaction requirement information, which includes stage performance theme information, performance segment time node information, and virtual interaction triggering condition information; Based on the stage scene interaction requirements information, a target mapping rule is constructed, and a generative artificial intelligence model is called to generate image elements according to the target mapping rule to obtain an initial holographic projection image element set. The initial holographic projection image element set includes static image elements and dynamic image elements that match the stage performance theme information. The performance stages are divided according to the time node information of the performance segments, and the initial holographic projection image element set is dynamically arranged in stages in combination with the virtual interaction triggering condition information to obtain a dynamic holographic projection image sequence. Collect real-time interactive data from the stage, establish a correlation logic between the real-time interactive data and image sequence adjustment, and perform parameter adjustment processing on the dynamic holographic projection image sequence according to the correlation logic to obtain an optimized dynamic holographic projection image sequence. Based on the optimized dynamic holographic projection image sequence, a holographic projection output parameter system is constructed, a holographic projection image generation instruction containing the output parameter system is generated, and the holographic projection image generation instruction is sent to the holographic projection device to drive the holographic projection device to output a holographic projection image; The process involves collecting real-time interactive data from the stage, establishing a correlation logic between the real-time interactive data and image sequence adjustment, and performing parameter adjustment processing on the dynamic holographic projection image sequence based on the correlation logic to obtain an optimized dynamic holographic projection image sequence, including: Real-time interactive stage data is collected through stage data acquisition equipment. The real-time interactive stage data includes audience interaction data, stage equipment operation data, and performer movement data. The audience interaction data includes the frequency of interactive behavior and the distribution of interactive areas. The stage equipment operation data includes the equipment working mode and the equipment output status. The performer movement data includes the movement frequency and the movement amplitude. Feature extraction is performed on the audience interaction data to obtain the interaction frequency feature value and the spatial distribution feature of the interaction area per unit time. The display frequency adjustment direction of the dynamic image element is determined based on the comparison result of the interaction frequency feature value and the preset threshold. The display area adjustment direction of the image element is determined based on the mapping relationship between the spatial distribution feature and the stage area. The stage equipment operation data is analyzed for features, and the image resolution adaptation parameters corresponding to the equipment working mode and the light output parameters corresponding to the equipment output state are extracted. The resolution adjustment direction of the image elements is determined according to the resolution adaptation parameters, and the brightness adjustment direction of the image elements is determined according to the light output parameters. The performer's motion data is analyzed to obtain motion frequency feature parameters and motion amplitude feature parameters based on spatial coordinate changes per unit time. The direction of motion rhythm adjustment of image elements is determined based on the deviation of the motion frequency feature parameters from a preset reference frequency, and the direction of motion range adjustment of image elements is determined based on the deviation of the motion amplitude feature parameters from a preset reference amplitude. Combining all the above adjustment directions, a correlation logic is constructed between real-time interactive data and image sequence adjustment. The correlation logic includes the correspondence between interactive data features and image parameter adjustment amounts, the correspondence between device data features and image parameter adjustment amounts, and the correspondence between motion data features and image parameter adjustment amounts. The parameter adjustment amount of each image element in the dynamic holographic projection image sequence is calculated according to the correlation logic. The parameter adjustment amount includes display frequency adjustment amount, display area adjustment amount, resolution adjustment amount, brightness adjustment amount, motion rhythm adjustment amount, and motion range adjustment amount. The parameters of each image element in the dynamic holographic projection image sequence are modified according to the parameter adjustment amount to obtain the adjusted image elements. The adjusted image elements are then recombined in the original time axis order to form the adjusted dynamic holographic projection image sequence. The overall visual consistency of the adjusted dynamic holographic projection image sequence is verified, and the image element parameters are finely adjusted based on the verification results to obtain the optimized dynamic holographic projection image sequence.

2. The intelligent generation method for holographic projection images applied to virtual stage interaction according to claim 1, characterized in that, The step involves constructing target mapping rules based on the stage scene interaction requirements information, and then calling a generative artificial intelligence model to generate image elements according to the target mapping rules, resulting in an initial holographic projection image element set, including: The stage performance theme information in the stage scene interaction requirement information is analyzed, and the core visual style keywords and core element type descriptions in the stage performance theme information are extracted. The core visual style keywords include color tendency description and style school description, and the core element type description includes scene element category and character element category. Based on the core visual style keywords and core element type descriptions, a target mapping rule is constructed. The target mapping rule includes the correspondence between visual style keywords and image color parameters, and the correspondence between element type descriptions and image morphological features. The target mapping rule is input into the generative artificial intelligence model, which triggers the generative artificial intelligence model to configure the basic parameters for image generation according to the target mapping rule. The basic parameters for image generation include color configuration parameters, shape configuration parameters, and texture configuration parameters. The image color matching scheme is determined based on the color configuration parameters. The image color matching scheme includes a primary color parameter, an auxiliary color parameter, and a color transition rule based on a color model. The morphological feature parameters and texture detail parameters of the image elements are determined based on the morphological configuration parameters and texture configuration parameters. The morphological feature parameters include contour structure parameters based on geometric constraints and proportional size parameters relative to the stage projection area. The texture detail parameters include texture density parameters based on pixel distribution and texture quality parameters based on material simulation. The generative artificial intelligence model is invoked to generate static image elements according to the image color matching scheme, morphological feature parameters and texture detail parameters, so as to obtain static image elements that match the core element type description; Based on the dynamic attribute requirements in the core element type description, configure dynamic change rule parameters, which include the time dimension change frequency and the spatial dimension change trajectory. The generative artificial intelligence model is invoked to generate dynamic image elements according to the dynamic change rule parameters, resulting in dynamic image elements containing the change rules of the time dimension; The static and dynamic image elements are integrated, and the number of integrated image elements is verified according to the number of categories in the core element type description to ensure that the number of static and dynamic image elements corresponds to the number of element categories mentioned in the core element type description, thus forming an initial holographic projection image element set.

3. The intelligent generation method for holographic projection images applied to virtual stage interaction according to claim 2, characterized in that, Based on the dynamic attribute requirements in the core element type description, dynamic change rule parameters are configured, and a generative artificial intelligence model is invoked to perform dynamic image element generation processing according to the dynamic change rule parameters, resulting in dynamic image elements containing time-dimension change patterns, including: The dynamic attribute requirements in the core element type description are analyzed to determine the change dimensions of the dynamic image elements, which include position change dimension, shape change dimension and color change dimension; For the dimension of position change, based on the motion trajectory description in the dynamic attribute requirements, position change rule parameters are configured. The position change rule parameters include spatial path node coordinates based on the stage coordinate system and the motion rate between nodes based on time units. For the dimension of morphological change, based on the morphological evolution description in the dynamic attribute requirements, morphological change rule parameters are configured, including morphological transition node parameters and morphological change amplitude between nodes based on percentage changes. For the dimension of color change, based on the color gradient description in the dynamic attribute requirements, color change rule parameters are configured. The color change rule parameters include color transition node parameters and color change gradient between nodes based on color space. The position change rule parameters, shape change rule parameters, and color change rule parameters are integrated to form a dynamic change rule parameter set; The set of dynamic change rule parameters is input into the generative artificial intelligence model, which triggers the generative artificial intelligence model to construct a time change model of dynamic image elements. The time change model includes position parameters, shape parameters and color parameters corresponding to different time points. Based on the time change model, state data of dynamic image elements at different time points are generated, and the state data includes timestamps, location coordinates, shape parameter values, and color parameter values. A frame sequence of dynamic image elements is generated based on the state data. Each frame corresponds to the state of a dynamic image element at a certain time point. The time interval of the frame sequence is consistent with the minimum time unit in the time node information of the performance segment. The frame sequence is subjected to inter-frame transition processing to adjust the change amplitude of state parameters between adjacent frames. The processed frame sequence is then integrated to form dynamic image elements containing time dimension change patterns. The duration of the dynamic image elements matches the duration of the corresponding performance segment in the stage performance theme information.

4. The intelligent generation method for holographic projection images applied to virtual stage interaction according to claim 3, characterized in that, The step of performing inter-frame transition processing on the frame sequence and adjusting the change amplitude of state parameters between adjacent frames includes: Extract the dynamic image element state parameters of two adjacent frames in the frame sequence. The dynamic image element state parameters include the position coordinates, shape parameters, and color parameters of the adjacent previous frame, as well as the position coordinates, shape parameters, and color parameters of the adjacent next frame. Calculate the Euclidean distance difference between the position coordinates of the adjacent previous frame and the adjacent next frame to obtain the position difference; calculate the scalar difference of the morphological parameters between the adjacent previous frame and the adjacent next frame to obtain the morphological difference; calculate the color difference of the color parameters between the adjacent previous frame and the adjacent next frame to obtain the color difference. Based on the combined magnitude of the position difference, shape difference, and color difference, the transition smoothness requirement between adjacent frames is determined. The larger the combined difference, the higher the transition smoothness requirement. Based on the requirements for smoothness of transition, the transition processing method between adjacent frames is determined. The transition processing methods include linear transition processing, curved transition processing, and segmented transition processing. If linear transition processing is adopted, the change in difference is evenly distributed according to the position difference, shape difference and color difference, and the state parameters of the transition frame are generated. The number of transition frames is determined based on the difference size and frame rate requirements. If a curve transition is used, a difference change curve function based on the time progress is constructed. The difference distribution at different transition times is calculated based on the curve function, and the state parameters of the transition frame are generated. The curvature of the curve function is adjusted according to the transition smoothness requirements. If segmented transition processing is adopted, the difference is divided into multiple segments based on the rate of change, a corresponding transition rate is configured for each segment, and the state parameters of each transition frame are calculated based on the segmented transition rate. The number of segments is positively correlated with the size of the difference. The generated transition frames are inserted between the adjacent preceding frame and the adjacent following frame to form a new frame sequence containing the transition frames.

5. The intelligent generation method for holographic projection images applied to virtual stage interaction according to claim 1, characterized in that, The process of dividing the performance into stages based on the performance segment time node information and combining the virtual interaction triggering condition information to perform staged dynamic choreography on the initial holographic projection image element set, resulting in a dynamic holographic projection image sequence, includes: The time node information of the performance segment is analyzed, and multiple consecutive performance stages are divided according to the interval characteristics of the time nodes. The duration information of each performance stage is marked, and each performance stage corresponds to a performance content theme. The static and dynamic image elements in the initial holographic projection image element set are categorized and labeled. The categorization and labeling results include matching information with the content theme of each performance stage. Based on the matching information, corresponding static and dynamic image elements are assigned to each performance stage, so that the assigned image elements are adapted to the content theme of the performance stage, forming the initial image element group for each performance stage. The virtual interaction triggering condition information is analyzed to determine the type and triggering time of the virtual interaction triggering event. Each type of virtual interaction triggering event is marked with a triggering priority. The types of virtual interaction triggering events include audience interaction virtual interaction triggering events, stage equipment status virtual interaction triggering events, and performance action virtual interaction triggering events. Based on the type and priority of the virtual interaction triggering events, a target association rule is constructed. The target association rule includes the image element switching method and the image element switching timing corresponding to different virtual interaction triggering events. Based on the duration of each performance stage and the triggering time of virtual interactive events, the initial image element groups of each performance stage are arranged in chronological order to form an initial timeline image sequence. According to the target association rule, an image element switching marker is set at the time position corresponding to the virtual interaction trigger event in the initial time axis image sequence, and the image element to be switched and the target image element to be switched at the image element switching marker are defined. Visual coherence processing is performed on the timeline image sequence containing the image element switching markers. The transition parameters between the image element to be switched and the target image element to be switched at the switching markers are adjusted so that adjacent image elements achieve a visually smooth transition when switching. The processed timeline image sequence is then integrated to form a dynamic holographic projection image sequence.

6. The intelligent generation method for holographic projection images applied to virtual stage interaction according to claim 5, characterized in that, The step of constructing target association rules based on the type and priority of the virtual interaction trigger event, and setting image element switching markers at the time positions corresponding to the virtual interaction trigger events in the initial timeline image sequence according to the target association rules, includes: Attribute analysis is performed on the types of virtual interaction trigger events to determine the scope of influence for each type of virtual interaction trigger event. The scope of influence includes the category range and time range of image element switching. Based on the scope of influence of the virtual interactive triggering events and the preset priority determination criteria, a trigger priority is assigned to each virtual interactive triggering event. The priority determination criteria include the size of the scope of influence and the degree of correlation with the performance content. Based on the type, triggering priority, and scope of influence of virtual interaction trigger events, target association rules are constructed. The target association rules include: instant switching rules corresponding to virtual interaction trigger events with first priority, delayed switching rules corresponding to virtual interaction trigger events with second priority, and conditional trigger switching rules corresponding to virtual interaction trigger events with third priority. The instant switching rule is defined as follows: when a virtual interaction trigger event of the first priority occurs, the image element switching process is immediately initiated, and the switching response time does not exceed the minimum time interval in the performance segment time node information. The delay switching rule is defined as starting the image element switching process after a preset time delay when a virtual interaction trigger event of the second priority occurs. The preset time is determined according to the interval between adjacent performance stages. The condition-triggered switching rule is defined as follows: when a virtual interaction trigger event of the third priority occurs, the image element switching process can only be started after a preset additional trigger condition is met. Traverse the initial timeline image sequence, mark the position of the trigger time of each virtual interaction trigger event on the timeline, and label the type and priority of each virtual interaction trigger event; Based on the target association rule, a corresponding switching rule is matched to the trigger time position of each marker to determine the category of image element to be switched and the target switching image element category specified in the switching rule; An image element switching marker is set at the trigger time location. The image element switching marker includes the type of virtual interaction trigger event, the trigger priority, the identifier of the image element to be switched, the identifier of the target image element to be switched, and the switching rule type. The timeline image sequence containing the image element switching markers is temporarily stored.

7. The intelligent generation method for holographic projection images applied to virtual stage interaction according to claim 1, characterized in that, The above-mentioned adjustment directions are combined to construct a correlation logic between real-time interactive data and image sequence adjustment. Based on this correlation logic, the parameter adjustment amount for each image element in the dynamic holographic projection image sequence is calculated, including: The interaction frequency feature value of the audience interaction data is divided into multiple feature intervals based on statistical distribution. A corresponding dynamic image element display frequency adjustment coefficient is assigned to each feature interval. The higher the interaction frequency corresponding to the feature interval, the larger the assigned display frequency adjustment coefficient. The interactive region feature distribution of audience interaction data is converted into a region weight value based on region importance. Corresponding image element display area adjustment weights are assigned to different interactive regions. The higher the weight value of the interactive region, the greater the adjustment of the proportion of image element display in the corresponding interactive region. The operating mode of the stage equipment is matched with the preset resolution adaptation table to determine the resolution reference value corresponding to each operating mode. The resolution adjustment coefficient is calculated based on the deviation between the equipment output state and the reference output state. The larger the deviation value, the larger the absolute value of the resolution adjustment coefficient. The brightness output value in the equipment output status of the stage equipment operation data is compared with the preset brightness standard value to calculate the brightness deviation ratio. The brightness adjustment amount is determined according to the brightness deviation ratio. If the deviation ratio is positive, the brightness adjustment amount is reduced, and if the deviation ratio is negative, the brightness adjustment amount is increased. The motion frequency feature parameters of the performer's motion data are compared with the motion rhythm baseline parameters of the image elements to calculate the rhythm deviation rate. The motion rhythm adjustment amount is determined based on the rhythm deviation rate. If the deviation rate is positive, the motion rhythm adjustment amount is increased; if the deviation rate is negative, the motion rhythm adjustment amount is decreased. The motion amplitude feature parameters of the performer's motion data are compared with the motion range reference parameters of the image elements to calculate the range deviation rate. The motion range adjustment amount is determined based on the range deviation rate. If the deviation rate is positive, the motion range adjustment amount is increased; if the deviation rate is negative, the motion range adjustment amount is decreased. By integrating the calculation logic of all the above adjustment coefficients, adjustment weights and adjustment amounts, a correlation logic between real-time interactive data and image sequence adjustment is constructed. The correlation logic includes data feature input items, parameter adjustment amount output items and the calculation mapping relationship between the two. Obtain the current parameter value of each image element in the dynamic holographic projection image sequence. The current parameter value includes the current display frequency, the current display area ratio, the current resolution, the current brightness, the current motion rhythm, and the current motion range. The real-time interactive data feature value corresponding to each image element is input into the association logic. Through the calculation mapping relationship in the association logic, the adjustment amount of display frequency, display area, resolution, brightness, motion rhythm, and motion range of each image element are calculated respectively to form a set of parameter adjustment amounts.

8. The intelligent generation method for holographic projection images applied to virtual stage interaction according to claim 1, characterized in that, The process of constructing a holographic projection output parameter system based on the optimized dynamic holographic projection image sequence, generating a holographic projection image generation instruction containing the output parameter system, and sending the holographic projection image generation instruction to the holographic projection device to drive the holographic projection device to output a holographic projection image includes: Extract the image data information and timestamp information of each image frame in the optimized dynamic holographic projection image sequence. The image data information includes image pixel data, image size data, and image color depth data. Based on the image data information, format adaptation parameters for holographic projection images are constructed. The format adaptation parameters include pixel arrangement, size scaling ratio, and color depth conversion standard. The format adaptation parameters must match the input format supported by the holographic projection device. The playback timing parameters of the holographic projection image are constructed based on the timestamp information. The playback timing parameters include the playback start time, playback duration, and inter-frame switching interval for each image frame. The playback timing parameters need to be synchronized with the time node information of the performance segment. By integrating the format adaptation parameters and playback timing parameters, a holographic projection output parameter system is constructed. The holographic projection output parameter system also includes image output accuracy parameters and projection area positioning parameters. The image output accuracy parameters are related to image resolution, and the projection area positioning parameters are related to stage space layout information. Add parameter identification information to the holographic projection output parameter system, with each parameter corresponding to a unique identification code, which is used for parameter identification when the holographic projection device is analyzing the parameters. According to the communication protocol requirements of holographic projection equipment, the holographic projection output parameter system containing parameter identification information is encapsulated into an instruction data structure. The instruction data structure includes an instruction header, a parameter area, and a verification area. The instruction header contains an instruction type identifier, the parameter area contains the specific data of the output parameter system, and the verification area contains a data integrity check code. A holographic projection image generation instruction containing the aforementioned instruction data structure is generated. After format conversion of the holographic projection image generation instruction, a communication link is established with the holographic projection device. The holographic projection image generation instruction is sent to the holographic projection device through the established communication link, so that after receiving the holographic projection image generation instruction, the holographic projection device loads the corresponding image data according to the output parameter system and controls the projection component to output the holographic projection image according to the playback timing parameters.

9. A holographic projection image intelligent generation system for virtual stage interaction, characterized in that, The intelligent generation system for holographic projection images applied to virtual stage interaction includes a processor and a memory. The memory and the processor are connected. The memory is used to store programs, instructions, or code. The processor is used to execute the programs, instructions, or code in the memory to implement the intelligent generation method for holographic projection images applied to virtual stage interaction as described in any one of claims 1-8.

Images