Intelligent AI holographic projection method and system based on artificial intelligence

Abstract

The invention provides an intelligent AI holographic projection method and system based on artificial intelligence, and the method comprises the steps: recognizing a user in a projection region, extracting features of the two-dimensional image and three-dimensional space information of the user, and integrating the features into a user feature vector; performing accurate hierarchical classification on the users according to the user feature vectors in combination with two-dimensional image features, distance features of the users in a three-dimensional space and sight directions of the users; personalized content is generated and distributed for the user according to the user demand matrix, and the specific demand of the user in the holographic projection environment is met; and designing a visual angle adaptive projection matrix and a content synchronization mechanism to carry out personalized holographic real-time projection on the personalized content. The invention provides a new holographic projection system scheme, personalized display and self-adaptive projection effects can be provided according to individual demands of users in a multi-user scene, high flexibility and adaptability are achieved, and it is ensured that each user can obtain a good visual effect and personalized experience at any position.

Description

Technical Field

[0001] The present invention belongs to the field of artificial intelligence, and in particular relates to an intelligent AI holographic projection method and system based on artificial intelligence. Background Art

[0002] In modern exhibitions, education and training, medical imaging and other fields, holographic projection technology is widely used because it can create three-dimensional and visual spatial images. This technology presents three-dimensional content to users with a visual stereoscopic effect through layered processing and projection of images, creating a highly immersive experience. However, with the diversification of user needs, especially in multi-user interactive scenarios in public places, traditional holographic projection technology is facing severe challenges. Existing holographic projection systems mainly perform well in single-user or small-scale user experience, and can provide good visual effects under single content or single viewing angle. However, in multi-user scenarios (such as museums, exhibitions, etc.), the limitations of traditional holographic projection systems become more and more obvious.

[0003] First, existing holographic projection systems generally lack the ability to identify and respond to multiple users in a personalized manner, which makes it difficult to provide personalized interactive experiences for multiple users in the same scene. When multiple users are in the same projection area, the system can only display the same content, which makes it difficult to meet the needs of different users. For example, some users may want to see more detailed content, while others just want to quickly get an overview.

[0004] Since the display content of holographic projection cannot change dynamically according to different user needs, it is easy to cause content conflicts and information interference between users, affecting the experience effect in multi-user scenarios. Secondly, in terms of viewing angle adaptation, traditional holographic systems lack the ability to adapt to multiple perspectives. Different users standing in different positions in the projection area may have completely different viewing effects. Some users may see clear holographic images, while others can only see blurred edges or distorted images due to angle limitations. This single-perspective projection method is limited in a multi-user environment, and it is difficult to ensure that each user has the best visual experience.

[0005] Finally, existing holographic systems are mostly single-level interactions in terms of user interaction, which makes it difficult to dynamically adjust the projected content according to the behaviors and interests of different users, resulting in a single and rigid experience. For example, although some systems can recognize user gestures or positions, they lack hierarchical management in multi-user scenarios and cannot effectively distinguish the needs and interaction levels of different users, resulting in content display that is difficult to meet the requirements of multi-user interaction. Summary of the invention

[0006] The purpose of the present invention is to propose an intelligent AI holographic projection method and system based on artificial intelligence, which realizes providing personalized immersive experience for multiple users in the same projection area through technical innovations such as multi-user recognition, personalized content generation and adaptive adjustment of viewing angle.

[0007] In order to achieve the above object, a first aspect of the present invention provides an intelligent AI holographic projection method based on artificial intelligence, the method comprising:

[0008] S1. Identify the user in the projection area, extract features from the user's two-dimensional image and three-dimensional space information, and integrate them into a user feature vector; the user feature vector includes two-dimensional image features, distance features of the user in three-dimensional space, and the user's line of sight direction;

[0009] S2. Based on the user feature vector combined with the two-dimensional image features, the user's distance features in three-dimensional space, and the user's line of sight direction, the user is accurately classified into different levels, including:

[0010] First, perform preliminary stratification:

[0011] Set the interaction distance threshold D th , if the distance feature is greater than the interaction distance threshold D th If the distance feature is less than the interaction distance threshold D th Then user i is classified as the close interaction layer;

[0012] The interest score of each user is calculated based on the two-dimensional image features, the distance features of the user in the three-dimensional space, and the user's line of sight direction, and the interest score threshold I is designed. th , if the interest score is greater than the interest score threshold I th The user is marked as a high-interest interaction layer, and detailed content is assigned to the user. If the interest score is less than the interest score threshold I th The user is marked as a low-interest interaction layer, and the content display is mainly overview;

[0013] Integrate the results of preliminary stratification and interest score classification to construct a multi-level user demand matrix M to support hierarchical management of personalized content display;

[0014] S3. Generate and distribute personalized content for users according to the user demand matrix M to meet the specific needs of users in the holographic projection environment, including:

[0015] Generate corresponding content matrix C for different user layers according to user demand matrix M;

[0016] Design the distribution frequency matrix L to control the content update frequency of the content matrix C corresponding to the same user layer;

[0017] S4. Design a perspective adaptive projection matrix and content synchronization mechanism to perform personalized holographic real-time projection of personalized content.

[0018] Furthermore, the extracting features from the two-dimensional image and three-dimensional spatial information of the user specifically includes:

[0019] Arrange cameras and distance sensors in the projection area to collect the two-dimensional image and three-dimensional spatial information of each user, as shown below:

[0020] U i = {P i ,D i ,V i}

[0021] Among them, U i represents the detection feature vector of each user, P i Represents the two-dimensional image features of the user, which are acquired in real time by the image detection model; D i Represents the distance characteristics of the user in three-dimensional space, that is, the relative position to the projection system, measured by the distance sensor; V i Indicates the direction of the user's gaze, which is determined by the camera detecting the angle and orientation of the face.

[0022] Furthermore, the image detection model is a convolutional neural network, and the two-dimensional image feature processing user's two-dimensional image feature P i Identify the user's facial features in the projection area and calculate the user's line of sight direction V i , analyze the image’s posture information θ through a multi-layer neural network i , which is expressed as follows:

[0023] V i = sin(θ i )+cos(θ i )

[0024] Among them, θ i Represents the user's facial orientation angle, obtained using the 3D point-to-point pose estimation method, and the line of sight direction V is calculated by combining sine and cosine i , ensuring the calculation accuracy at different angles and distances;

[0025] After detecting the user's facial information and line of sight, the distance feature D of the user in three-dimensional space is calculated in real time based on the distance sensor data. i , that is, the distance from the user to the projection device, is expressed as follows:

[0026]

[0027] Among them, (xi ,y i , z i ) represents the user's spatial coordinates, (x c ,y c , z c ) represents the spatial coordinates of the projection center.

[0028] Furthermore, the interest score is calculated by combining the user's gaze time, facial orientation angle, and distance features in three-dimensional space, and is expressed as follows:

[0029] I i =w T T i +w θ |θ i |+λ·f(D i )

[0030] Among them, I i Represents the user's interest score, which is used to determine the user's personalized content needs; T i The time the user looks at the content, reflecting the user's attention to the content; θ i D is the user's facial orientation angle; i is the distance feature in three-dimensional space, through the distance feature D in three-dimensional space i The decay function Introduce distance regularization control, α is the distance attenuation coefficient; w T 、w θ and λ are weight coefficients used to adjust T i ,θ i and D i The impact on the final interestingness score,values ​​are verified through experiments;

[0031] The user demand matrix M is expressed as follows:

[0032]

[0033] Among them, U 近，高 is a set of user characteristics with close proximity and high interest; U 近，低 is a set of user characteristics that are close but of low interest; U 远，高 is a set of user characteristics that are far away but highly interested; U 远，低 A set of user characteristics that are far away and of low interest

[0034] Furthermore, most of the attenuation functions The interest of distant users decreases as the distance increases, thereby reasonably controlling resource allocation in multi-user scenarios.

[0035] Furthermore, generating corresponding content matrices C for different user layers according to the user demand matrix M specifically includes:

[0036] For each user layer U ij , the element C of the content generation matrix ij Calculated by the content generation function φ:

[0037] C ij =φ(M ij )

[0038] Among them, C ij Represents the corresponding layer U ij Personalized content display; φ is the content generation function, input demand matrix M ij , returns customized content;

[0039] The designed distribution frequency matrix L controls the content update frequency of the content matrix C corresponding to the same user layer, which is expressed as follows:

[0040] L ij =δ·(1+η·I ij )

[0041] Among them, L ij Presentation Layer ij The content update frequency; δ is the basic distribution frequency, which is set as the global frame update standard; η is the interest gain coefficient, which controls the influence of interest on the content update frequency.

[0042] Furthermore, the interest adjustment term regularization term is designed in the content matrix C to adapt to the content details, which is expressed as follows:

[0043] C ij =(R·exp(-β·D ij ))·(1+γ·I ij )

[0044] Among them, R is the basic resolution of the content, which determines the clarity of the content; D ij For user set U ij The average distance of is used as a regular term to control the attenuation of content details; β is the distance weight coefficient, which controls the impact of distance on content display effect; I ij is the average interest of users in this layer, which is used to increase the details of users with high interest; γ is the amplification factor of interest.

[0045] Furthermore, the view-adaptive projection matrix is ​​expressed as follows:

[0046]

[0047] Among them, T ijRepresented as user layer U ij The generated projection matrix controls the brightness, contrast, and transparency of the content; θ ij is the angle at which user i’s perspective deviates from the center; α ij and β ij To adjust the brightness and contrast parameters, the display effect is adjusted based on the user's distance and line of sight; D ij is the user distance, λ is the distance regularization coefficient, Used to ensure balanced brightness and contrast for users at different distances;

[0048] The content synchronization mechanism is expressed as follows:

[0049] S ij =C ij ·T ij ·(1+η·I ij )

[0050] Among them, S ij Represented as user layer U ij Provides a synchronization content signal; C ij To personalize content, the basic display of content is defined; ij is the view-adaptive projection matrix, which is used to adjust the brightness and contrast of the content; ij is the user's interest score, which reflects the user's demand for the current content; η is the interest enhancement coefficient, which is used to increase the content display density of users with high interest.

[0051] Furthermore, in S4, an error correction mechanism is introduced to detect T in real time. ij The deviation from the ideal projection parameters triggers the automatic correction, which is expressed as follows:

[0052]

[0053] Among them, E ij Represents the current projection matrix With ideal projection parameters The perspective error between is the projection parameter of the current frame; is the ideal projection value, calculated from the user's real-time viewing angle data;

[0054] When the error E ij When the threshold ∈ is exceeded, an update will be automatically triggered to recalculate the projection matrix T ij , and synchronize to S ij , ensuring consistency of content from the user’s perspective.

[0055] In a second aspect of the present invention, an intelligent AI holographic projection system based on artificial intelligence is provided, the system comprising:

[0056] A user projection data acquisition module is used to identify users in the projection area, extract features from the user's two-dimensional image and three-dimensional space information, and integrate them into a user feature vector; the user feature vector includes two-dimensional image features, distance features of the user in three-dimensional space, and the user's line of sight direction;

[0057] The user classification module is used to accurately classify users based on the user feature vector combined with the two-dimensional image features, the distance features of the user in the three-dimensional space, and the user's line of sight direction. Specifically, it includes:

[0058] First, perform preliminary stratification:

[0059] Set the interaction distance threshold D th , if the distance feature is greater than the interaction distance threshold D th If the distance feature is less than the interaction distance threshold D th Then user i is classified as the close interaction layer;

[0060] The interest score of each user is calculated based on the two-dimensional image features, the distance features of the user in the three-dimensional space, and the user's line of sight direction, and the interest score threshold I is designed. th , if the interest score is greater than the interest score threshold I th The user is marked as a high-interest interaction layer, and detailed content is assigned to the user. If the interest score is less than the interest score threshold I th The user is marked as a low-interest interaction layer, and the content display is mainly overview;

[0061] Integrate the results of preliminary stratification and interest score classification to construct a multi-level user demand matrix M to support hierarchical management of personalized content display;

[0062] The user demand generation module is used to generate and distribute personalized content for users according to the user demand matrix M to meet the specific needs of users in the holographic projection environment, including:

[0063] Generate corresponding content matrix C for different user layers according to user demand matrix M;

[0064] Design the distribution frequency matrix L to control the content update frequency of the content matrix C corresponding to the same user layer;

[0065] The holographic projection synchronization module is used to design the perspective adaptive projection matrix and content synchronization mechanism to perform personalized holographic real-time projection of personalized content.

[0066] The beneficial technical effects of the present invention are at least as follows:

[0067] The invention adopts a multi-layer AI architecture, which uses cameras and sensors to monitor and identify the location, behavior and sight direction of each user in real time. Based on the AI ​​analysis results, the system assigns users to different interaction layers (such as close interaction layer and long-distance viewing layer), thereby achieving precise hierarchical management of multiple users. This hierarchical mechanism not only meets the personalized needs of each user, but also effectively avoids content conflicts and visual interference between users.

[0068] The AI ​​content generation module of the present invention generates personalized holographic content in real time based on the user's behavior, interests, and interaction level. For example, for users at close range, the system can provide detailed content display, such as enlarged views or layered anatomical information, while users at long distances receive simplified overview content. This innovation not only improves the diversity of user experience, but also effectively avoids the problem of multi-user content in traditional holographic projection that cannot be personalized, ensuring that each user receives targeted content display.

[0069] Based on the user's position and line of sight, the present invention automatically optimizes the angle, brightness and contrast of the projected content through an AI-driven projection adjustment mechanism, so that each user can enjoy a clear, distortion-free visual experience no matter which direction they watch from. This viewing angle optimization mechanism overcomes the visual limitations brought about by the single viewing angle display in traditional systems, and is particularly suitable for application in complex multi-user scenarios, ensuring that each user's viewing experience is optimal. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0071] Figure 1 This is a flow chart of an intelligent AI holographic projection method based on artificial intelligence of the present invention.

[0072] Figure 2 This is a framework diagram of an intelligent AI holographic projection system based on artificial intelligence in the present invention. DETAILED DESCRIPTION

[0073] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0074] like Figure 1As shown, an embodiment of the present invention provides an intelligent AI holographic projection method based on artificial intelligence, and the method includes:

[0075] S1. Identify the user in the projection area, extract features from the user's two-dimensional image and three-dimensional space information, and integrate them into a user feature vector; the user feature vector includes two-dimensional image features, distance features of the user in three-dimensional space, and the user's line of sight direction;

[0076] S2. Based on the user feature vector combined with the two-dimensional image features, the user's distance features in three-dimensional space, and the user's line of sight direction, the user is accurately classified into different levels, including:

[0077] First, perform preliminary stratification:

[0078] Set the interaction distance threshold D th , if the distance feature is greater than the interaction distance threshold D th If the distance feature is less than the interaction distance threshold D th Then user i is classified as the close interaction layer; that is, if D i ≤D th , then user i is classified as the close interaction layer; if D i >D th , user i is classified as a long-distance viewing layer. The logic of this distance classification is to ensure that users who are closer to the projection area can obtain more refined content display while reducing visual interference for users at a distance. After the classification is completed, a preliminary user set U 近 = {U i |D i ≤D th} and U 远 = {U i |D i >D th};

[0079] The interest score of each user is calculated based on the two-dimensional image features, the distance features of the user in the three-dimensional space, and the user's line of sight direction, and the interest score threshold I is designed. th , if the interest score is greater than the interest score threshold I th The user is marked as a high-interest interaction layer, and detailed content is assigned to the user. If the interest score is less than the interest score threshold I th The user is marked as a low-interest interaction layer, and the content display is mainly overview;

[0080] Integrate the results of preliminary stratification and interest score classification to construct a multi-level user demand matrix M to support hierarchical management of personalized content display;

[0081] S3. Generate and distribute personalized content for users according to the user demand matrix M to meet the specific needs of users in the holographic projection environment, including:

[0082] Generate corresponding content matrix C for different user layers according to user demand matrix M;

[0083] Design the distribution frequency matrix L to control the content update frequency of the content matrix C corresponding to the same user layer;

[0084] S4. Design a perspective adaptive projection matrix and content synchronization mechanism to perform personalized holographic real-time projection of personalized content.

[0085] Furthermore, the extracting features from the two-dimensional image and three-dimensional spatial information of the user specifically includes:

[0086] Arrange cameras and distance sensors in the projection area to collect the two-dimensional image and three-dimensional spatial information of each user, as shown below:

[0087] U i = {P i ,D i ,V i}

[0088] Among them, U i represents the detection feature vector of each user, P i The two-dimensional image features (such as face and gestures) representing the user are acquired in real time by the image detection model; D i Represents the distance characteristics of the user in three-dimensional space, that is, the relative position to the projection system, measured by the distance sensor; V i Indicates the direction of the user's gaze, which is determined by the camera detecting the angle and orientation of the face.

[0089] Furthermore, the image detection model is a convolutional neural network, and the two-dimensional image feature processing user's two-dimensional image feature P i Identify the user's facial features in the projection area and calculate the user's line of sight direction V j , analyze the image’s posture information θ through a multi-layer neural network i , which is expressed as follows:

[0090] V i = sin(θ i )+cos(θ i )

[0091] Among them, θ i Represents the user's facial orientation angle, obtained using the 3D point-to-point pose estimation method, and the line of sight direction V is calculated by combining sine and cosine i , ensuring the calculation accuracy at different angles and distances;

[0092] After detecting the user's facial information and line of sight, the distance feature D of the user in three-dimensional space is calculated in real time based on the distance sensor data. i , that is, the distance from the user to the projection device, is expressed as follows:

[0093]

[0094] Among them, (x i ,y i , z i ) represents the user's spatial coordinates, (x c ,y c , z c ) represents the spatial coordinates of the projection center.

[0095] Furthermore, the above features are integrated to generate the user feature vector U i = {P i , D i , V i}, where each feature has been calibrated according to the three-dimensional spatial information. This feature vector represents the real-time spatial position, posture and sight direction of each user, and through the weighted average method, it ensures that the feature output of each user is clear and non-overlapping in the multi-user scenario to avoid confusion between multiple users. Finally, all U i The vector is the final output of this step and provides basic data for subsequent layering and content generation.

[0096] Furthermore, the interest score is calculated by combining the user's gaze time, facial orientation angle, and distance features in three-dimensional space, and is expressed as follows:

[0097] I i =w T T i +w θ |θ i |+λ·f(D i )

[0098] Among them, I i Represents the user's interest score, which is used to further determine the user's personalized content needs; T i The time that the user looks at the content (unit: seconds), reflecting the user's attention to the content; θ i is the rotation angle of the user's head (unit: degree), obtained through the gesture recognition module, and measures the user's content viewing angle; D i is the distance feature of the user, through D i The decay function Introduce distance regularization control, α is the distance attenuation coefficient; w T 、w θand λ are weight coefficients used to adjust T i ,θ i and D i The impact on the final interest score is verified by experiments and is set to w T =0.6, w e =0.3, λ=0.1.

[0099] Where f(D i ) innovatively introduces user distance as a regular term, so that the interest of distant users gradually decreases with increasing distance, thereby reasonably controlling resource allocation in a multi-user scenario. i After calculation, I i With the threshold value I th For comparison:

[0100] If I i ≥I th , the user is marked as a high-interest interaction layer, and the system will assign more detailed content to him.

[0101] If I i <I th , it is marked as a low-interest interaction layer, and the content display is mainly overview to reduce system resource usage.

[0102] The results of the above two classification steps are integrated to construct a multi-level user demand matrix M, which is used to support hierarchical management of personalized content display. The user demand matrix M is expressed as follows:

[0103]

[0104] Among them, U 近，高 is a set of user characteristics with close proximity and high interest; U 近，低 is a set of user characteristics that are close but of low interest; U 远，高 is a set of user characteristics that are far away but highly interested; U 远，低 It is a set of user characteristics with long distance and low interest;

[0105] The output multi-level matrix M contains complete user stratification information, which is used as the basic input for the next step of personalized content generation. Matrix M provides support for the system to perform detailed content allocation in multi-user scenarios, ensuring that the content generation in the subsequent steps can accurately match the personalized needs of users at each level.

[0106] Furthermore, most of the attenuation functions The interest of distant users decreases as the distance increases, thereby reasonably controlling resource allocation in multi-user scenarios.

[0107] Furthermore, generating corresponding content matrices C for different user layers according to the user demand matrix M specifically includes:

[0108] For each user layer U ij , the element C of the content generation matrix ij Calculated by the content generation function φ:

[0109] C ij =φ(M ij )

[0110] Among them, C ij Represents the corresponding layer U ij Personalized content display; φ is the content generation function, input demand matrix M ij , returns customized content;

[0111] The content generation function φ adopts a parameterized template generation strategy to adjust the content details, resolution, and display brightness according to the different needs of the user layer. 近，高 At the level, content generation tends to be more inclined to high resolution, high brightness and high detail display to meet the needs of close-up and high-interest users; while U 远，低 The second layer generates low-brightness, low-resolution content to ensure the rational use of system resources.

[0112] After generating the content matrix C, in order to ensure the smoothness and real-time performance of content display in multi-user scenarios, the system designs a distribution frequency matrix L. Matrix L controls the content update frequency of users at different levels to ensure that high-interest users receive more frequent updates, while low-interest users reduce the content refresh frequency, thereby optimizing resource utilization.

[0113] Furthermore, the designed distribution frequency matrix L controls the content update frequency of the content matrix C corresponding to the same user layer, which is expressed as follows:

[0114] L ij =δ·(1+η·I ij )

[0115] Among them, L ij Presentation Layer ij The content update frequency (unit: frames per second); δ is the basic distribution frequency, set as the global frame update standard; η is the interest gain coefficient, which controls the impact of interest on the content update frequency.

[0116] Among them, according to the above formula, L ij with I ijThe content of high-interest users is updated more frequently, ensuring the real-time nature of personalized content. At the same time, the content of low-interest users is updated less frequently, reducing the system load. This design ensures efficient distribution and synchronization of content in the holographic projection scene.

[0117] Furthermore, the interest adjustment term regularization term is designed in the content matrix C to adapt to the content details, which is expressed as follows:

[0118] C ij =(R·exp(-β·D ij ))·(1+γ·I ij )

[0119] Among them, R is the basic resolution of the content, which determines the clarity of the content; D ij For user set U ij The average distance of is used as a regular term to control the attenuation of content details; β is the distance weight coefficient, which controls the impact of distance on content display effect; I ij is the average interest of users in this layer, which is used to increase the details of users with high interest; γ is the amplification factor of interest.

[0120] Among them, through D ij The attenuation term exp(-β·D ij ), the system reduces the detail of the content for distant users; at the same time, the interest adjustment term (1+γ·I ij ) makes the content display for high-interest users more detailed. The generation formula innovatively combines the distance and interest regularization terms to match the content detail level with the user's interaction needs, thereby effectively solving the challenge of unbalanced content display in multi-user scenarios.

[0121] Furthermore, based on the user's feature vector U i = {Pi, D i , V i} position and line of sight information V i , the present invention constructs an innovative perspective adaptive projection matrix T ij . T ij The projection parameters can be automatically adjusted according to the user's viewing angle and distance to ensure the display effect of multiple users at different viewing angles. The viewing angle adaptive projection matrix is ​​expressed as follows:

[0122]

[0123] Among them, T ij Represented as user layer U ij The generated projection matrix controls the brightness, contrast, and transparency of the content; θ ij is the angle at which user i’s perspective deviates from the center; α ij and βij To adjust the brightness and contrast parameters, the display effect is adjusted based on the user's distance and line of sight; D ij is the user distance, λ is the distance regularization coefficient, Used to ensure balanced brightness and contrast for users at different distances;

[0124] The construction of this projection matrix performs a combination of cosine and sine corrections based on the viewing angle deviation of different users, and adds an inverse adjustment term of the distance. Ensures balanced brightness and contrast for users at different distances.

[0125] The content synchronization mechanism is expressed as follows:

[0126] S ij =C ij ·T ij ·(1+η·I ij )

[0127] Among them, S ij Represented as user layer U ij Provides a synchronization content signal; C ij To personalize content, the basic display of content is defined; ij is the view-adaptive projection matrix, which is used to adjust the brightness and contrast of the content; ij is the user's interest score, which reflects the user's demand for the current content; η is the interest enhancement coefficient, which is used to increase the content display density of users with high interest.

[0128] In this formula, the distribution signal S ij By T ij and I ij Dual control not only enables personalized content distribution, but also ensures smooth content updates when users are on the move.

[0129] Furthermore, in S4, an error correction mechanism is introduced to detect T in real time. ij The deviation from the ideal projection parameters triggers the automatic correction, which is expressed as follows:

[0130]

[0131] Among them, E ij Represents the current projection matrix With ideal projection parameters The perspective error between is the projection parameter of the current frame; is the ideal projection value, calculated from the user's real-time viewing angle data;

[0132] When the error E ijWhen the threshold ∈ is exceeded, an update will be automatically triggered to recalculate the projection matrix T ij , and synchronize to S ij , ensuring the consistency of content from the user's perspective. Error correction ensures that multiple users have a consistent experience from a dynamic perspective.

[0133] like Figure 2 As shown, an embodiment of the present invention further provides an intelligent AI holographic projection system based on artificial intelligence, the system comprising:

[0134] The user projection data acquisition module 3011 is used to identify the user in the projection area, extract features from the user's two-dimensional image and three-dimensional space information, and integrate them into a user feature vector; the user feature vector includes two-dimensional image features, distance features of the user in three-dimensional space, and the user's line of sight direction;

[0135] The user classification module 3012 is used to accurately classify users according to the user feature vector combined with the two-dimensional image feature, the distance feature of the user in the three-dimensional space and the user's line of sight direction, including:

[0136] First, perform preliminary stratification:

[0137] Set the interaction distance threshold D th , if the distance feature is greater than the interaction distance threshold D th If the distance feature is less than the interaction distance threshold D th Then user i is classified as the close interaction layer;

[0138] The interest score of each user is calculated based on the two-dimensional image features, the distance features of the user in the three-dimensional space, and the user's line of sight direction, and the interest score threshold I is designed. th , if the interest score is greater than the interest score threshold I th The user is marked as a high-interest interaction layer, and detailed content is assigned to the user. If the interest score is less than the interest score threshold I th The user is marked as a low-interest interaction layer, and the content display is mainly overview;

[0139] Integrate the results of preliminary stratification and interest score classification to construct a multi-level user demand matrix M to support hierarchical management of personalized content display;

[0140] The user demand generation module 3013 is used to generate and distribute personalized content for users according to the user demand matrix M to meet the specific needs of users in the holographic projection environment, specifically including:

[0141] Generate corresponding content matrix C for different user layers according to user demand matrix M;

[0142] Design the distribution frequency matrix L to control the content update frequency of the content matrix C corresponding to the same user layer;

[0143] The holographic projection synchronization module 3014 is used to design a perspective adaptive projection matrix and a content synchronization mechanism to perform personalized holographic real-time projection of personalized content.

[0144] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0145] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a division of logical functions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0146] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0147] Although embodiments of the present invention have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

Claims

1. An intelligent AI holographic projection method based on artificial intelligence, characterized in that: The method comprises: S1. Identify the user in the projection area, extract features from the user's two-dimensional image and three-dimensional space information, and integrate them into a user feature vector; the user feature vector includes two-dimensional image features, distance features of the user in three-dimensional space, and the user's line of sight direction; S2. Based on the user feature vector combined with the two-dimensional image features, the user's distance features in three-dimensional space, and the user's line of sight direction, the user is accurately classified into different levels, including: First, perform preliminary stratification: Set the interaction distance threshold D th , if the distance feature is greater than the interaction distance threshold D th If the distance feature is less than the interaction distance threshold D th Then user i is classified as the close interaction layer; The interest score of each user is calculated based on the two-dimensional image features, the distance features of the user in the three-dimensional space, and the user's line of sight direction, and the interest score threshold I is designed. th , if the interest score is greater than the interest score threshold I th The user is marked as a high-interest interaction layer, and detailed content is assigned to the user. If the interest score is less than the interest score threshold I th The user is marked as a low-interest interaction layer, and the content display is mainly overview; Integrate the results of preliminary stratification and interest score classification to construct a multi-level user demand matrix M to support hierarchical management of personalized content display; S3. Generate and distribute personalized content for users according to the user demand matrix M to meet the specific needs of users in the holographic projection environment, including: Generate corresponding content matrix C for different user layers according to user demand matrix M; Design the distribution frequency matrix L to control the content update frequency of the content matrix C corresponding to the same user layer; S4. Design a perspective adaptive projection matrix and content synchronization mechanism to perform personalized holographic real-time projection of personalized content.

2. The method of intelligent AI holographic projection based on artificial intelligence according to claim 1, characterized in that: The extracting features from the two-dimensional image and three-dimensional spatial information of the user specifically includes: Arrange cameras and distance sensors in the projection area to collect the two-dimensional image and three-dimensional spatial information of each user, as shown below: U i ={P i ,D i ,V i } Among them, U i represents the detection feature vector of each user, P i Represents the two-dimensional image features of the user, which are acquired in real time by the image detection model; D i Represents the distance characteristics of the user in three-dimensional space, that is, the relative position to the projection system, measured by the distance sensor; V i Indicates the direction of the user's gaze, which is determined by the camera detecting the angle and orientation of the face.

3. The method of intelligent AI holographic projection based on artificial intelligence according to claim 2, characterized in that: The image detection model is a convolutional neural network, and the two-dimensional image feature processing user's two-dimensional image feature P i Identify the user's facial features in the projection area and calculate the user's line of sight V i , analyze the image’s posture information θ through a multi-layer neural network i , which is expressed as follows: V i =sin(θ i )+cos(θ i ) Among them, θ i Represents the user's facial orientation angle, obtained using the 3D point-to-point pose estimation method, and the line of sight direction V is calculated by combining sine and cosine i , ensuring the calculation accuracy at different angles and distances; After detecting the user's facial information and line of sight, the distance feature D of the user in three-dimensional space is calculated in real time based on the distance sensor data. i , that is, the distance from the user to the projection device, is expressed as follows: Among them, (x i ,y i ,z i ) represents the user's spatial coordinates, (x c ,y c ,z c ) represents the spatial coordinates of the projection center.

4. The method of intelligent AI holographic projection based on artificial intelligence according to claim 1, characterized in that: The interest score is calculated by combining the user's gaze time, facial orientation angle, and distance features in three-dimensional space, and is expressed as follows: I i =w T T i +w θ |θ i |+λ·f(D i ) Among them, I i Represents the user's interest score, which is used to determine the user's personalized content needs; T i The time the user looks at the content, reflecting the user's attention to the content; θ i D is the user's facial orientation angle; i is the distance feature in three-dimensional space, through the distance feature D in three-dimensional space i The decay function Introduce distance regularization control, α is the distance attenuation coefficient; w T 、w θ and λ are weight coefficients used to adjust T i ,θ i and D i The impact on the final interestingness score,values ​​are verified through experiments; The user demand matrix M is expressed as follows: Among them, U 近,高 is a set of user characteristics with close proximity and high interest; U 近,低 is a set of user characteristics that are close but of low interest; U 远,高 is a set of user characteristics that are far away but highly interested; U 远,低 It is a feature set of users with low interest and long distance.

5. The method of intelligent AI holographic projection based on artificial intelligence according to claim 4, characterized in that: Most of the decay functions The interest of distant users decreases as the distance increases, thereby reasonably controlling resource allocation in multi-user scenarios.

6. The method of intelligent AI holographic projection based on artificial intelligence according to claim 1, characterized in that: Generating corresponding content matrices C for different user layers according to the user demand matrix M specifically includes: For each user layer U ij , the element C of the content generation matrix ij Calculated by the content generation function φ: C ij =φ(M ij ) Among them, C ij Represents the corresponding layer U ij Personalized content display; φ is the content generation function, input demand matrix M ij , return customized content; The designed distribution frequency matrix L controls the content update frequency of the content matrix C corresponding to the same user layer, which is expressed as follows: L ij =δ·(1+η·I ij ) Among them, L ij Presentation Layer ij The content update frequency; δ is the basic distribution frequency, which is set as the global frame update standard; η is the interest gain coefficient, which controls the influence of interest on the content update frequency.

7. The method of intelligent AI holographic projection based on artificial intelligence according to claim 6, characterized in that: In the content matrix C, the interest adjustment term and regular term are designed to adapt to the content details, which are expressed as follows: C ij =(R·exp(-β·D ij ))·(1+γ·I ij ) Among them, R is the basic resolution of the content, which determines the clarity of the content; D ij For user set U ij The average distance of is used as a regular term to control the attenuation of content details; β is the distance weight coefficient, which controls the impact of distance on content display effect; I ij is the average interest of users in this layer, which is used to increase the details of users with high interest; γ is the amplification factor of interest.

8. The method of intelligent AI holographic projection based on artificial intelligence according to claim 1, characterized in that: The view-adaptive projection matrix is ​​expressed as follows: Among them, T ij Represented as user layer U ij The generated projection matrix controls the brightness, contrast, and transparency of the content; θ ij is the angle at which user i’s perspective deviates from the center; α ij and β ij To adjust the brightness and contrast parameters, the display effect is adjusted based on the user's distance and line of sight; D ij is the user distance, λ is the distance regularization coefficient, Used to ensure balanced brightness and contrast for users at different distances; The content synchronization mechanism is expressed as follows: S ij =C ij ·T ij ·(1+η·I ij ) Among them, S ij Represented as user layer U ij Provides a synchronization content signal; C ij To personalize content, the basic display of content is defined; ij is the view-adaptive projection matrix, which is used to adjust the brightness and contrast of the content; ij is the user's interest score, which reflects the user's demand for the current content; η is the interest enhancement coefficient, which is used to increase the content display density of users with high interest.

9. The method of intelligent AI holographic projection based on artificial intelligence according to claim 8, characterized in that: In S4, an error correction mechanism is also introduced to detect T in real time. ij The deviation from the ideal projection parameters triggers the automatic correction, which is expressed as follows: Among them, E ij Represents the current projection matrix With ideal projection parameters The perspective error between is the projection parameter of the current frame; is the ideal projection value, calculated from the user's real-time viewing angle data; When the error E ij When the threshold ∈ is exceeded, an update will be automatically triggered to recalculate the projection matrix T ij , and synchronize to S ij , ensuring consistency of content from the user’s perspective.

10. An intelligent AI holographic projection system based on artificial intelligence, characterized in that: The system comprises: A user projection data acquisition module is used to identify users in the projection area, extract features from the user's two-dimensional image and three-dimensional space information, and integrate them into a user feature vector; the user feature vector includes two-dimensional image features, distance features of the user in three-dimensional space, and the user's line of sight direction; The user classification module is used to accurately classify users based on the user feature vector combined with the two-dimensional image features, the distance features of the user in the three-dimensional space, and the user's line of sight direction. Specifically, it includes: First, perform preliminary stratification: Set the interaction distance threshold D th , if the distance feature is greater than the interaction distance threshold D th If the distance feature is less than the interaction distance threshold D th Then user i is classified as the close interaction layer; The interest score of each user is calculated based on the two-dimensional image features, the distance features of the user in the three-dimensional space, and the user's line of sight direction, and the interest score threshold I is designed. th , if the interest score is greater than the interest score threshold I th The user is marked as a high-interest interaction layer, and detailed content is assigned to the user. If the interest score is less than the interest score threshold I th The user is marked as a low-interest interaction layer, and the content display is mainly overview; Integrate the results of preliminary stratification and interest score classification to construct a multi-level user demand matrix M to support hierarchical management of personalized content display; The user demand generation module is used to generate and distribute personalized content for users according to the user demand matrix M to meet the specific needs of users in the holographic projection environment, including: Generate corresponding content matrix C for different user layers according to user demand matrix M; Design the distribution frequency matrix L to control the content update frequency of the content matrix C corresponding to the same user layer; The holographic projection synchronization module is used to design the perspective adaptive projection matrix and content synchronization mechanism to perform personalized holographic real-time projection of personalized content.

Images