A geographical teaching device and interaction system based on holographic projection

Abstract

This application provides a holographic projection-based geography teaching device and interactive system. The holographic projection-based geography teaching device includes: a data acquisition module for acquiring interactive data, timestamping the interactive data, and performing sensor data fusion processing to generate a multidimensional behavioral dataset containing timestamps; a behavior analysis module for extracting perspective preference features and analyzing operational habits from the multidimensional behavioral dataset to generate student learning deviation; a dynamic adjustment module for adjusting parameters of the holographic projection system's teaching content mapping relationship based on the student learning deviation to generate a scene change instruction set; and a feedback optimization module for performing trend analysis on student response data after executing the scene change instruction set to generate an optimized interactive experience parameter set. This device can improve geography teaching and educational experience.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent teaching equipment, and in particular relates to a geography teaching device and an interactive system based on holographic projection. Background Art

[0002] As a cutting-edge direction in the field of educational technology, interactive holographic projection geography teaching combines virtual reality and spatial interaction technologies, and is of key significance for improving the learning experience and knowledge transfer efficiency of geography. Its importance lies in breaking the limitations of traditional two-dimensional teaching through intuitive three-dimensional presentation and dynamic interaction, allowing students to deeply participate in the exploration of geographical phenomena in an immersive environment. However, current solutions mostly remain at the level of technical demonstration, and there is a common problem of insufficient data utilization. Traditional teaching systems often only record students' explicit behaviors, such as answers to multiple-choice questions or class attendance, but ignore the implicit data of students during the interaction process, such as perspective preferences and operating habits. This results in extensive teaching feedback and difficulty in accurately adapting to teaching needs.

[0003] Although holographic projection technology has made breakthroughs in visual presentation, the development of its interactive data system still faces significant challenges. The core issues focus on how to effectively collect and analyze the interaction data between students and holographic content, and how to convert this data into actionable basis for teaching adjustments. Specifically, the comprehensiveness of data, the real-time analysis, and the personalization of application are the three major technical bottlenecks. The comprehensiveness of data is limited by the system's ability to capture students' multi-dimensional behaviors. For example, perspective selection and the frequency of questioning are often overlooked; the real-time analysis is difficult to meet the dynamic needs of the classroom due to the lag in big data processing technology; and the personalization of application is even more limited due to the lack of pattern recognition for individual learning characteristics. These unresolved technical factors have resulted in the holographic interactive system being unable to fully realize its teaching potential and it is difficult to achieve a seamless match between content presentation and student needs.

[0004] Traditional holographic geography teaching systems are unable to capture multi-dimensional interactive data in real time and lack the ability to dynamically adjust teaching content, resulting in unsatisfactory teaching results. Summary of the Invention

[0005] Based on this, it is necessary to provide a geography teaching device and interactive system based on holographic projection to address the above technical problems, which can collect and analyze the interaction data between students and holographic geography content in real time, generate an interactive experience parameter set to adjust the holographic projection content, and improve the level of geography teaching and educational experience.

[0006] In a first aspect, the present application provides a geography teaching device based on holographic projection, comprising a data acquisition module, a behavior analysis module, a dynamic adjustment module, and a feedback optimization module:

[0007] The data acquisition module is used to obtain interaction data, perform timestamp tagging and sensor data fusion processing on the interaction data, and generate a multi-dimensional behavior data set containing timestamps; the interaction data is used to characterize the interaction behavior between students and holographic projection geography content;

[0008] The behavior analysis module is used to extract perspective preference features and analyze operation habits of multi-dimensional behavior data sets to generate student learning deviation;

[0009] The dynamic adjustment module is used to adjust the parameters of the teaching content mapping relationship of the holographic projection system according to the student's learning deviation and generate a scene transformation instruction set;

[0010] The feedback optimization module is used to perform trend analysis on the student response data after the scene change instruction set is executed, and generate an optimized interactive experience parameter set. The interactive experience parameter set is used to instruct the holographic projection device to generate a holographic image.

[0011] In a possible embodiment, the data acquisition module includes:

[0012] A multi-source data acquisition unit is used to obtain the student's perspective movement trajectory and quantify the touch operation force based on the pressure sensor to generate the original behavior data stream;

[0013] A data preprocessing unit is used to perform sensor noise compensation processing on the original behavior data stream to generate a denoised original data set;

[0014] The timestamp generation unit is used to perform time synchronization processing on the original data set, align the time axis of the original data set based on the time axis alignment algorithm, and generate a multi-dimensional behavior data set marked with a timestamp.

[0015] In a possible embodiment, the behavior analysis module includes:

[0016] The data cleaning unit is used to filter outliers in the multidimensional behavior data set and eliminate noise data through a sliding window algorithm to generate a standardized behavior data set;

[0017] A viewing preference analysis unit is used to extract a gaze point coordinate sequence from a standardized behavioral dataset, perform spatial aggregation processing on the gaze point coordinate sequence based on a density clustering algorithm, and generate a viewing preference pattern;

[0018] The operation habit analysis unit is used to perform frequent pattern mining on the operation instruction sequences in the standardized behavior data set, match them with the preset behavior templates through the dynamic time warping algorithm, and generate the operation habit feature vector;

[0019] The deviation calculation unit is used to map the perspective preference pattern and operation habit feature vectors to the node space of the pre-trained geographic knowledge graph to obtain the student learning vector, calculate the semantic distance between the student learning vector and the teaching target vector based on the graph neural network, and generate the student learning deviation based on the semantic distance.

[0020] In a possible embodiment, the deviation calculation unit includes:

[0021] The difference comparison subunit is used to map the perspective preference pattern to the node space of the geographic knowledge graph, calculate the matching degree with the target knowledge node based on cosine similarity, and generate a first deviation coefficient;

[0022] The regression analysis subunit is used to perform multivariate linear regression processing on the operation habit feature vector and generate a second deviation coefficient based on the proportional relationship between the regression residual and a preset threshold;

[0023] The weight fusion subunit is used to dynamically assign weights to the first deviation coefficient and the second deviation coefficient through the entropy weight method to generate the student learning deviation.

[0024] In a possible embodiment, the dynamic adjustment module includes:

[0025] An adjustment coefficient generation unit is used to optimize the teaching content mapping function based on the student learning deviation through a gradient descent algorithm to generate an initial adjustment coefficient of the scene transformation parameter;

[0026] The incremental learning unit is used to input the initial adjustment coefficient into the incremental learning model, fuse the historical interaction data based on the random weight averaging algorithm, and generate a dynamically updated personalized model;

[0027] The instruction generation unit is used to convert the adjustment coefficient into a scene rendering instruction set according to the spatial interaction interface protocol of the personalized mode matching holographic projection system, and the scene rendering instruction set is used to instruct the holographic projection device to control the laser parameters and / or light field angle.

[0028] In a possible embodiment, the incremental learning unit includes:

[0029] The history retention evaluation subunit is used to evaluate the historical knowledge retention rate after the model is updated through sliding window cross-validation and generate stability verification results;

[0030] The weight adjustment subunit is used to dynamically adjust the model weight distribution according to the stability verification results and generate coverage threshold parameters. The coverage threshold parameters are used to limit the coverage of new knowledge on historical data.

[0031] The threshold constraint subunit is used to truncate the parameter update gradient of the incremental learning model based on the coverage threshold parameter, generate a personalized model after catastrophic forgetting is suppressed, and the personalized model is used to update the teaching content mapping relationship of the holographic projection system.

[0032] In a possible embodiment, the feedback optimization module includes:

[0033] The response evaluation unit is used to extract the interaction frequency and operation accuracy from the student response data after the scene rendering instruction set is executed, model the response change trend based on the hidden Markov model, and generate a response evaluation value;

[0034] The instruction optimization unit is used to divide the feature space by the C4.5 decision tree algorithm when the response evaluation value is lower than the preset threshold, and generate an improved parameter set driven by the classification rule;

[0035] The real-time update unit is used to input the improved parameter set into the streaming data processing engine, dynamically load the geographic scene resources based on the time-sensitive hash index, and generate an optimized interactive experience parameter set.

[0036] In a second aspect, the present application also provides a geography teaching interactive method based on holographic projection, comprising:

[0037] Acquire interaction data, perform timestamp tagging and sensor data fusion processing on the interaction data, and generate a multi-dimensional behavior dataset containing timestamps; the interaction data is used to characterize the interaction behavior between students and holographic projection geography content;

[0038] Extract perspective preference features and analyze operating habits from multidimensional behavioral data sets to generate student learning deviations;

[0039] According to the students' learning deviation, the parameters of the teaching content mapping relationship of the holographic projection system are adjusted to generate a scene transformation instruction set;

[0040] The student response data after the scene change instruction set is executed is subjected to trend analysis and processing to generate an optimized interactive experience parameter set, which is used to instruct the holographic projection device to generate a holographic image.

[0041] In a third aspect, the present application also provides a geography teaching interactive system based on holographic projection, comprising:

[0042] A holographic projection device, a motion capture sensor array, and a terminal processor, wherein the terminal processor is configured to implement the holographic projection-based geography teaching interaction as in the previous embodiment;

[0043] The terminal processor is communicatively connected with the holographic projection device and the motion capture sensor array respectively.

[0044] In a fourth aspect, the present application also provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the geography teaching method based on holographic projection as described above are implemented.

[0045] The holographic projection-based geography teaching device and interactive system generates a multidimensional behavioral dataset containing spatiotemporal correlation information by timestamping and fusing the interaction data between students and holographic projection geographic content, overcoming the limitations of traditional systems in capturing implicit interactive behaviors. Based on the multidimensional behavioral dataset, perspective preference features are extracted and operational habits are analyzed to generate student learning deviation, quantifying the dynamic difference between students' current cognitive state and teaching objectives. A dynamic adjustment module parameterizes the mapping relationship between the holographic projection system and teaching content based on the student learning deviation, generating a scene transformation instruction set to achieve real-time adaptation of teaching content to individual learning needs. A feedback optimization module analyzes student response data after executing the scene transformation instruction set to generate an optimized interactive experience parameter set, which drives the holographic projection device to dynamically update the geographic scene. This method can improve the utilization of interactive data in the holographic geography teaching system and enhance teaching effectiveness through real-time analysis of multidimensional behavioral data and dynamic iteration of teaching parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1 A schematic structural diagram of a geography teaching device based on holographic projection provided by an embodiment of the present invention;

[0048] Figure 2 A schematic diagram of a flow chart of a geography teaching interactive method based on holographic projection provided by an embodiment of the present invention;

[0049] Figure 3 A schematic structural diagram of a geography teaching interactive system based on holographic projection provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0051] First, a brief introduction is given to the terms involved in the embodiments of this application.

[0052] Holographic projection is a technology that uses the principles of light interference and diffraction to record and reproduce the three-dimensional image of an object. Using specialized optical equipment and materials, it captures the object's light wave information, including amplitude and phase, and stores it in a holographic medium. When illuminated by a specific light source, the holographic medium reconstructs a three-dimensional image of the object, allowing people to observe it from different angles with a near-real-life visual effect. Holographic projection technology is widely used in display, education, entertainment, and other fields, providing an immersive visual experience.

[0053] The Geographic Knowledge Graph is a semantic network that represents geographic knowledge in a graph-like format. By structurally modeling and storing geographic entities (such as cities, mountains, and rivers), geographic concepts (such as terrain types and climate zones), and the complex relationships between them (such as geographic location associations and administrative affiliations), it enables efficient organization and semantic association of geographic information. It provides powerful support for querying, analyzing, reasoning, and visualizing geographic information, and is widely used in fields such as geographic education, intelligent navigation, environmental monitoring, and urban planning, helping users gain a deeper understanding and utilization of geographic knowledge.

[0054] Graph Neural Networks (GNNs) are a class of deep learning models for processing graph-structured data. They aim to capture the graph's topological structure and node features by learning representations of nodes, edges, and their relationships. They aggregate information from neighboring nodes to update the feature representation of the current node, thereby enabling feature extraction and modeling of graph-structured data. GNNs have demonstrated outstanding performance in a variety of fields, including social network analysis, molecular structure prediction, recommendation systems, and knowledge graphs. They can effectively solve tasks such as node classification, graph classification, and link prediction, providing a powerful tool for processing complex graph-structured data.

[0055] Based on the above explanation of terms, the implementation environment of the holographic projection-based geography teaching device 10 provided in the embodiment of the present application is described. Schematically, the implementation environment includes: a holographic projection device, a motion capture sensor array, and a terminal processor. The terminal processor is connected to the motion capture sensor and the holographic projection device via a network device; the holographic projection device can be a holographic projector, a holographic projection screen, or a holographic projection system; the motion capture sensor array includes but is not limited to an infrared camera array, a depth camera array, an inertial measurement unit sensor, an optical motion capture system, and a gesture recognition sensor; and the terminal processor can be a graphics processor, a multi-core central processing unit, an embedded system processor, or an intelligent terminal processor, etc., without limitation herein.

[0056] In combination with the above-mentioned explanations of terms and implementation environments, the application scenarios of the embodiments of the present application are described. The geography teaching device 10 based on holographic projection provided in the embodiments of the present application can be applied to, but not limited to, the following scenarios:

[0057] In geography classes, teachers use holographic projection equipment to display three-dimensional earth models, topography, climate distribution, and other geographical content. Students can observe the geographical features of different regions through gestures (such as rotating and scaling the earth model). The data acquisition module captures students' interactive behaviors in real time, the behavior analysis module analyzes students' operating habits and viewing preferences, and the dynamic adjustment module automatically adjusts the holographic projection display content based on students' learning deviations, for example, highlighting areas that students pay less attention to and providing more detailed explanations. The feedback optimization module further optimizes the interactive experience based on students' subsequent responses, ensuring that students can better understand and participate in learning. By using this device, students can learn geographical knowledge in a more intuitive and proactive way, and teachers can adjust teaching strategies based on real-time feedback to improve teaching effectiveness.

[0058] In the virtual geographical adventure scene, students can "enter" a virtual geographical environment, such as exploring the Amazon rainforest or climbing Mount Everest. By using this device, the holographic projection equipment generates a realistic three-dimensional geographical scene, and the motion capture sensor array captures the students' movements in real time, enabling students to interact with the virtual environment through natural body language, such as touching virtual plants with their hands, climbing virtual mountains, etc. The behavior analysis module analyzes the students' operating habits and learning deviations. The dynamic adjustment module adjusts the scene difficulty or provides prompt information based on the analysis results. The feedback optimization module further optimizes the interactive experience based on the students' responses, ensuring that students always maintain a high level of participation and learning interest during the adventure, making students feel as if they are in a real geographical environment, enhancing the immersion and fun of learning, and dynamically adjusting the content according to the students' learning status to ensure learning effectiveness.

[0059] Illustratively, the geography teaching device 10 based on holographic projection provided in the embodiment of the present application can also be applied to other application scenarios. It is only used as an example here and is not limited to the specific application scenario.

[0060] In an exemplary embodiment, Figure 1 As shown, a geography teaching device 10 based on holographic projection is provided. This embodiment uses the device as an example to illustrate the terminal processor in the aforementioned implementation environment. The geography teaching device 10 based on holographic projection provided in this embodiment includes a data acquisition module 11, a behavior analysis module 12, a dynamic adjustment module 13, and a feedback optimization module 14:

[0061] The data acquisition module 11 is used to obtain interaction data, perform timestamp marking and sensor data fusion processing on the interaction data, and generate a multidimensional behavior data set containing timestamps; the interaction data is used to characterize the interaction behavior between students and holographic projection geography content.

[0062] For example, multiple motion capture sensors arranged around the holographic projection equipment can be used to obtain real-time interaction data between students and holographic projection geographical content, and the interaction data can be timestamped. Through multi-sensor fusion and timestamp synchronization technology, the limitations of traditional single behavior records can be broken through, and the accurate capture of multi-dimensional implicit data such as viewing trajectory and operation force can be achieved, thereby improving the comprehensiveness of behavior analysis.

[0063] The behavior analysis module 12 is used to extract perspective preference features and analyze operation habits of the multi-dimensional behavior data set to generate student learning deviation.

[0064] Specifically, by extracting perspective preference features from the data, analyzing the duration and frequency of students' gazes, and analyzing their operational habits, such as gestures, touch frequency, and interaction paths, this method generates a learning deviation metric, which is used to assess the degree to which students' learning status deviates from the pre-set standard learning model. By combining density clustering with knowledge graph reasoning, discrete interactive behaviors are mapped into a quantifiable learning deviation metric, addressing the crudeness of traditional assessment methods that rely on explicit answer data and enabling accurate diagnosis of students' cognitive status.

[0065] The dynamic adjustment module 13 is used to perform parameter adjustment processing on the teaching content mapping relationship of the holographic projection system according to the student's learning deviation, and generate a scene change instruction set.

[0066] Specifically, the parameters of the teaching content mapping relationship of the holographic projection system can be adjusted according to the student's learning deviation. For example, if the student's learning deviation is high, the device can adjust the display parameters of the holographic projection equipment, such as increasing the highlighting of key areas, adjusting the viewing angle, or adding auxiliary instructions, etc., and generate a scene change instruction set to guide the holographic projection equipment to update the display method of the teaching content, so as to respond to the students' learning needs in real time, dynamically adjust the presentation method of the teaching content, ensure that the teaching process always fits the students' learning progress and understanding level, and improve the teaching effect and students' learning enthusiasm.

[0067] The feedback optimization module 14 is used to perform trend analysis on the student response data after the scene change instruction set is executed, and generate an optimized interactive experience parameter set, which is used to instruct the holographic projection device to generate a holographic image.

[0068] Specifically, after the holographic projection device executes the scene transformation instruction set, it obtains students' response data to the new scene in real time, which may include new interactive behaviors and changes in vision, etc., and performs trend analysis on these response data to evaluate students' acceptance of the adjusted teaching content and learning effects. Based on the analysis results, the module generates an optimized interactive experience parameter set and further adjusts the display parameters of the holographic projection device to optimize students' learning experience.

[0069] The holographic projection-based geography teaching device generates a multidimensional behavioral dataset containing spatiotemporal correlation information by timestamping and fusing multi-sensor data from student interactions with holographic projection geography content, overcoming the limitations of traditional systems in capturing implicit interactive behaviors. Based on the multidimensional behavioral dataset, it extracts perspective preference features and analyzes operational habits to generate student learning deviations, quantifying the dynamic differences between students' current cognitive states and teaching objectives. Based on the student learning deviations, it parameterizes the mapping relationship between the holographic projection system's teaching content and generates a scene transformation instruction set, enabling real-time adaptation of teaching content to individual learning needs. Trend analysis of student response data after executing the scene transformation instruction set generates an optimized interactive experience parameter set, which drives the holographic projection device to dynamically update the geographic scene. This method improves the utilization of interactive data in the holographic geography teaching system and enhances teaching effectiveness through real-time analysis of multidimensional behavioral data and dynamic iteration of teaching parameters.

[0070] In a possible embodiment, the data acquisition module 11 may include:

[0071] The multi-source data acquisition unit 111 is used to acquire the student's perspective movement trajectory, and quantify the touch operation force based on the pressure sensor to generate an original behavior data stream.

[0072] Specifically, cameras and pressure sensors can be used to obtain students' visual movement trajectories and touch operation strength, generating raw behavioral data streams to comprehensively capture students' interactive behaviors, including not only visual interactions but also tactile interactions, ensuring that every detail of the teaching process can be effectively recorded, providing high-information-density raw data for subsequent analysis.

[0073] The data pre-processing unit 112 is configured to perform sensor noise compensation processing on the original behavior data stream to generate a denoised original data set.

[0074] For example, an adaptive filtering algorithm can be used to suppress noise in the original behavioral data stream: first, a sliding average filter is used to eliminate high-frequency jitter noise in the infrared tracking data, retaining the low-frequency effective displacement signal; a wavelet threshold denoising algorithm is used to separate the environmental electromagnetic interference component in the touch pressure signal, and a smooth pressure change curve is reconstructed; the denoised viewing angle trajectory and touch force data are normalized and mapped to a unified dimensional space to generate a denoised standardized original data set, thereby improving the accuracy and reliability of the data and avoiding data distortion caused by sensor errors or external interference.

[0075] The timestamp generating unit 113 is configured to perform time synchronization processing on the original data set, align the time axis of the original data set based on a time axis alignment algorithm, and generate a multi-dimensional behavior data set marked with a timestamp.

[0076] Specifically, a global time base can be constructed based on a precision clock source: the local clocks of each sensor are synchronized via the IEEE 1588 Precision Time Protocol (PTP), and nanosecond-level timestamps are added to each behavioral record in the standardized raw dataset. Furthermore, a dynamic time warping (DTW) algorithm can be used to nonlinearly align the time axes of multi-source data streams, eliminating timing deviations caused by sensor response delays. This generates a multidimensional behavioral dataset with strictly synchronized timestamps and spatial alignment, addressing the temporal drift of multi-sensor data and ensuring the spatiotemporal consistency of behavioral data, providing a reliable foundation for temporal correlation analysis.

[0077] In a possible embodiment, the behavior analysis module 12 may include:

[0078] The data cleaning unit 121 is used to perform outlier filtering processing on the multidimensional behavior data set and eliminate noise data through a sliding window algorithm to generate a standardized behavior data set.

[0079] Specifically, the multidimensional behavioral data set is filtered for outliers to identify and eliminate data points that obviously do not conform to normal interactive behaviors, such as viewing angles or operating forces that exceed a reasonable range. The remaining data is processed through a sliding window algorithm, and the data within the window is smoothed to eliminate noise data. A standardized behavioral data set is generated to provide a clean and accurate data foundation for subsequent analysis.

[0080] The viewing angle preference analysis unit 122 is configured to extract a gaze point coordinate sequence from the standardized behavior data set, perform spatial aggregation processing on the gaze point coordinate sequence based on a density clustering algorithm, and generate a viewing angle preference pattern.

[0081] Specifically, the students' gaze point coordinate sequences are extracted, and these gaze point coordinate sequences are spatially aggregated based on the density clustering algorithm. Through cluster analysis, the discrete gaze point coordinates are divided into multiple high-density clustering areas. By calculating the centroid coordinates and coverage area of each cluster, a perspective preference pattern is generated to characterize the distribution characteristics of the students' focus of attention, including the coordinates of the hot spot area, the proportion of stay time and the morphological parameters of the scanning path, to achieve quantitative characterization of the perspective behavior pattern.

[0082] The operation habit analysis unit 123 is used to perform frequent pattern mining processing on the operation instruction sequence in the standardized behavior data set, match it with the preset behavior template through the dynamic time warping algorithm, and generate an operation habit feature vector.

[0083] Specifically, a prefix projection pattern mining algorithm can be used to mine frequent subsequences of operation instruction sequences to identify recurring behavioral patterns; at the same time, the dynamic time warping (DTW) algorithm is used to calculate the temporal morphological difference between the student's operation sequence and the preset standard template, and generate a multidimensional operation habit feature vector containing operation frequency, timing deviation and path similarity; this feature vector is normalized through Z-score to eliminate dimensional differences and form a quantifiable and comparable behavioral characteristic indicator.

[0084] The deviation calculation unit 124 is used to map the perspective preference pattern and operation habit feature vector to the node space of the pre-trained geographic knowledge graph to obtain the student learning vector, calculate the semantic distance between the student learning vector and the teaching target vector based on the graph neural network, and generate the student learning deviation based on the semantic distance.

[0085] Specifically, the perspective preference pattern and operation habit feature vectors are input into the pre-trained geographic knowledge graph embedding model, and mapped to the node space of the knowledge graph through the graph attention network (GAT) to generate a 128-dimensional student learning vector that integrates spatial behavior and cognitive characteristics; the teaching goal vector constructed based on the graph neural network (pre-generated by curriculum standard knowledge points) is similar to the student learning vector to obtain a semantic matching degree in the range of 0-1; (1-semantic matching degree) is quantified as a student learning deviation index, which is used to characterize the degree of difference between the student's current cognitive state and the teaching goal, providing a quantitative basis for dynamically adjusting the teaching content, ensuring that the teaching process always fits the students' learning progress and understanding, and improving the teaching effect.

[0086] In a possible embodiment, the deviation calculation unit 124 may include:

[0087] The difference comparison subunit 1241 is used to map the perspective preference pattern to the node space of the geographic knowledge graph, calculate the matching degree with the target knowledge node based on cosine similarity, and generate a first deviation coefficient.

[0088] Specifically, the perspective preference pattern is mapped to the node space of the pre-trained geographic knowledge graph, the perspective preference pattern is compared with the target knowledge nodes in the knowledge graph, and the matching degree between the perspective preference pattern and the target knowledge nodes is calculated based on cosine similarity. The first deviation coefficient is generated by quantifying the matching degree, which is used to characterize the degree of difference between students' perspective preference and teaching objectives.

[0089] The regression analysis subunit 1242 is used to perform multivariate linear regression processing on the operating habit feature vector, and generate a second deviation coefficient based on the proportional relationship between the regression residual and a preset threshold.

[0090] Specifically, multivariate linear regression processing is performed on the operating habit feature vector, and the linear relationship between the feature vector and the preset teaching target feature vector is analyzed. Based on the proportional relationship between the regression residual and the preset threshold, a second deviation coefficient is generated to characterize the degree of deviation between students' operating habits and teaching targets.

[0091] The weight fusion subunit 1243 is used to dynamically assign weights to the first deviation coefficient and the second deviation coefficient using an entropy weight method to generate a student learning deviation.

[0092] For example, the entropy weight method can be used to determine the dynamic weights of the first deviation coefficient and the second deviation coefficient: calculate the information entropy value of each coefficient in the historical data set, the lower the information entropy, the higher the weight; assign weight coefficients according to the entropy calculation results (view deviation weight) and (operation deviation weight), satisfying ; Through the weighted summation formula [student learning deviation = × first deviation coefficient + × second deviation coefficient] generates a comprehensive evaluation index, which is output to the dynamic adjustment module 13 after Z-score standardization. The entropy weight method is used to objectively quantify the contribution of different deviation dimensions, avoiding the subjective bias of manually setting weights, ensuring that the calculation of student learning deviation is more scientific and reasonable, providing more accurate quantitative evaluation for the dynamic adjustment of subsequent teaching content, and improving the personalization and adaptability of teaching.

[0093] In a possible embodiment, the dynamic adjustment module 13 includes:

[0094] The adjustment coefficient generating unit 131 is used to optimize the teaching content mapping function based on the student learning deviation through a gradient descent algorithm to generate an initial adjustment coefficient of the scene transformation parameter.

[0095] Specifically, the optimization objective of the teaching content mapping function can be constructed based on the student learning deviation: the deviation value is used as the weight factor of the loss function, and the partial derivative direction of the terrain complexity parameter, dynamic demonstration speed parameter and information density is calculated through the gradient descent algorithm; for example, the parameter value is iteratively updated at a learning rate of 0.01 until the loss function converges, and an initial adjustment coefficient set including the hierarchical scaling coefficient, light intensity gradient and animation frame rate is generated. The numerical range of the coefficient set is mapped to the [0,1] interval after Min-Max normalization, so as to dynamically adjust the presentation of the teaching content according to the student learning deviation.

[0096] The incremental learning unit 132 is used to input the initial adjustment coefficient into the incremental learning model, perform fusion processing on the historical interaction data based on the random weighted average algorithm, and generate a dynamically updated personalized model.

[0097] Specifically, the initial adjustment coefficient can be input into the historical parameter pool of the incremental learning model, and the stochastic weight averaging (SWA) algorithm can be used for model fusion: for example, the latest 100 groups of valid samples are extracted from the historical interaction data to construct a sliding window data set, and the exponential moving average of the weights of each model in the window is calculated; the high-frequency fluctuations in the parameter update process are smoothed by the momentum factor μ=0.9, and a personalized model with dynamic updates that integrates historical experience and real-time feedback is generated.

[0098] The instruction generation unit 133 is used to convert the adjustment coefficient into a scene rendering instruction set according to the personalized mode matching spatial interaction interface protocol of the holographic projection system, and the scene rendering instruction set is used to instruct the holographic projection device to control laser parameters and / or light field angle.

[0099] Specifically, according to the personalized pattern generated by the incremental learning unit 132, the spatial interaction interface protocol of the holographic projection system is matched, and the adjustment coefficient is converted into a scene rendering instruction set, which is used to instruct the holographic projection device to control the laser parameters and / or light field angle. In this way, the holographic projection device can dynamically adjust the display content according to the personalized needs of students and optimize the teaching effect.

[0100] In one possible embodiment, the incremental learning unit 132 includes:

[0101] The history retention evaluation subunit 1321 is used to evaluate the history knowledge retention rate after the model is updated through sliding window cross-validation to generate a stability verification result.

[0102] Specifically, by using sliding window technology to select historical data from different time periods and divide them into multiple validation sets, the performance of the model is verified after each update, and the degree to which the model retains historical knowledge is calculated, thereby generating stability verification results and providing a basis for subsequent weight adjustments.

[0103] The weight adjustment subunit 1322 is used to dynamically adjust the model weight distribution according to the stability verification result and generate a coverage threshold parameter. The coverage threshold parameter is used to limit the coverage of new knowledge on historical data.

[0104] Specifically, based on the stability verification results generated by the historical retention evaluation subunit, the weight distribution of the incremental learning model is dynamically adjusted. The subunit adjusts the weights of each parameter in the model based on the stability verification results to optimize the model's ability to retain historical knowledge, and generates coverage threshold parameters. The coverage threshold parameters are used to limit the coverage of new knowledge on historical data, ensuring that the model does not excessively forget historical knowledge when learning new knowledge.

[0105] The threshold constraint subunit 1323 is used to truncate the parameter update gradient of the incremental learning model based on the coverage threshold parameter to generate a personalized model after catastrophic forgetting is suppressed. The personalized model is used to update the teaching content mapping relationship of the holographic projection system.

[0106] Exemplarily, the parameter update gradients of the incremental learning model are truncated based on the coverage threshold parameter generated by the weight adjustment subunit. Specifically, by limiting the gradient amplitude of parameter updates, the model is prevented from catastrophically forgetting historical knowledge when learning new knowledge, thereby generating a personalized model that suppresses catastrophic forgetting. This personalized model is used to update the teaching content mapping relationship of the holographic projection system, ensuring that the dynamic adjustment of teaching content not only adapts to students' new needs but also preserves important historical knowledge.

[0107] In a possible embodiment, the feedback optimization module 14 includes:

[0108] The response evaluation unit 141 is used to extract the interaction frequency and operation accuracy from the student response data after the scene rendering instruction set is executed, model the response change trend based on the hidden Markov model, and generate a response evaluation value.

[0109] Specifically, through embedded log analysis, student response data can be extracted from the interactive interface of the holographic projection device, the touch event log after the execution of the scene rendering instruction set can be parsed, and the frequency of interactive operations per unit time can be counted; the similarity between the student's actual operation path and the preset standard path can be calculated through the operation sequence matching algorithm, and an operation accuracy index in the range of 0-100% can be generated; further, the temporal changes of the above indicators can be modeled based on the hidden Markov model (HMM), the state transition probability matrix can be trained through the Baum-Welch algorithm, the expected response gain in the next three time windows can be calculated, and a 0-1 normalized response evaluation value can be generated, where an evaluation value below 0.6 triggers the optimization mechanism.

[0110] The instruction optimization unit 142 is used to divide the feature space by using the C4.5 decision tree algorithm when the response evaluation value is lower than a preset threshold, and generate an improved parameter set driven by classification rules.

[0111] Specifically, when the response evaluation value falls below a preset threshold, the unit initiates the partitioning of the feature space using the C4.5 decision tree algorithm. Based on the features in the student response data, this unit constructs a decision tree model and generates a set of improved parameters driven by classification rules. This allows for precise segmentation of learning groups based on student characteristics and learning situations, and generates targeted optimization recommendations for each group.

[0112] The real-time updating unit 143 is used to input the improved parameter set into the streaming data processing engine, dynamically load the geographic scene resources based on the time-sensitive hash index, and generate an optimized interactive experience parameter set.

[0113] Specifically, the improved parameter set is fed into the streaming data processing engine, and geo-scene resources are dynamically loaded based on a time-sensitive hash index to generate an optimized interactive experience parameter set. This unit can quickly respond to the requirements of the improved parameter set and dynamically adjust the display content and interactive parameters of the holographic projection device to ensure real-time updating and optimization of teaching content. Through time-sensitive hash indexing, this unit can efficiently load geo-scene resources, improve the system's responsiveness and operational efficiency, and provide students with a smooth and optimized learning experience.

[0114] In summary, the geography teaching device 10 based on holographic projection provided in the embodiment of the present application uses multi-source sensor fusion technology to capture the interactive behavior of students with holographic geography content in real time, including multi-dimensional data such as perspective movement trajectory and touch operation strength, and generates a high-precision multi-dimensional behavior data set through timestamp synchronization and noise suppression processing; based on the density clustering algorithm and the geographic knowledge graph inference engine, it extracts the perspective preference pattern and operation habit feature vector from the behavior data, and combines the graph neural network to calculate the semantic deviation between the student's cognitive state and the teaching goal; based on the deviation index, the incremental learning model is driven to dynamically tune the teaching content mapping function, and generate a scene transformation instruction set that controls the light field parameters and terrain rendering logic; through the hidden Markov model and streaming computing framework, the teaching effect is evaluated in real time and the parameters are iterated to form an adaptive personalized teaching strategy. The above technical solution can enhance the interactive experience of holographic projection teaching, ensure that the teaching process always fits the students' learning needs, and enhance students' learning enthusiasm and teaching effect.

[0115] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0116] Based on the same inventive concept, the present application also provides a holographic projection-based geography teaching method for implementing the aforementioned holographic projection-based geography teaching device 10. The solution provided by this method is similar to the solution described in the aforementioned device. Therefore, the specific limitations of one or more holographic projection-based geography teaching method embodiments provided below can be found in the above-mentioned limitations of the holographic projection-based geography teaching device 10, and will not be repeated here.

[0117] In an exemplary embodiment, Figure 2 As shown, a geography teaching interactive method based on holographic projection is provided, comprising the following steps:

[0118] S101, acquiring interaction data, performing timestamp marking and sensor data fusion processing on the interaction data, and generating a multi-dimensional behavior data set including timestamps; the interaction data is used to characterize the interaction behavior between students and holographic projection geography content.

[0119] S102, extracting perspective preference features and analyzing operation habits of the multi-dimensional behavior data set to generate student learning deviation.

[0120] S103, performing parameter adjustment processing on the teaching content mapping relationship of the holographic projection system according to the student's learning deviation, and generating a scene change instruction set.

[0121] S104, performing trend analysis on the student response data after the scene change instruction set is executed, and generating an optimized interactive experience parameter set, which is used to instruct the holographic projection device to generate a holographic image.

[0122] In a possible embodiment, the interaction data is timestamped and sensor data fused to generate a multi-dimensional behavior dataset containing timestamps, which may include:

[0123] S201, obtaining the student's visual angle movement trajectory, and quantifying the touch operation force based on the pressure sensor to generate an original behavior data stream.

[0124] S202 , performing sensor noise compensation processing on the original behavior data stream to generate a denoised original data set.

[0125] S203 , performing time synchronization processing on the original data set, aligning the time axis of the original data set based on a time axis alignment algorithm, and generating a multi-dimensional behavior data set marked with a timestamp.

[0126] In a possible embodiment, the behavior analysis module includes:

[0127] S301 , performing outlier filtering processing on the multidimensional behavior dataset and eliminating noise data through a sliding window algorithm to generate a standardized behavior dataset.

[0128] S302 , extracting a gaze point coordinate sequence from the standardized behavior dataset, performing spatial aggregation processing on the gaze point coordinate sequence based on a density clustering algorithm, and generating a viewing angle preference pattern.

[0129] S303, performing frequent pattern mining processing on the operation instruction sequence in the standardized behavior data set, matching it with the preset behavior template through a dynamic time warping algorithm, and generating an operation habit feature vector.

[0130] S304, mapping the perspective preference pattern and operation habit feature vectors to the node space of the pre-trained geographic knowledge graph to obtain the student learning vector, calculating the semantic distance between the student learning vector and the teaching target vector based on the graph neural network, and generating the student learning deviation based on the semantic distance.

[0131] In a possible embodiment, the semantic distance between the student learning vector and the teaching target vector is calculated based on a graph neural network, and the student learning deviation is generated according to the semantic distance, including:

[0132] S401, mapping the perspective preference pattern to the node space of the geographic knowledge graph, calculating the matching degree with the target knowledge node based on cosine similarity, and generating a first deviation coefficient.

[0133] S402 , performing multivariate linear regression processing on the operating habit feature vector, and generating a second deviation coefficient based on a proportional relationship between the regression residual and a preset threshold.

[0134] S403, dynamically assigning weights to the first deviation coefficient and the second deviation coefficient using an entropy weight method to generate a student learning deviation.

[0135] In a possible embodiment, parameter adjustment processing is performed on the teaching content mapping relationship of the holographic projection system according to the student's learning deviation to generate a scene transformation instruction set, including:

[0136] S501, based on the student learning deviation, the teaching content mapping function is optimized through the gradient descent algorithm to generate the initial adjustment coefficient of the scene transformation parameter.

[0137] S502: Input the initial adjustment coefficient into the incremental learning model, perform fusion processing on the historical interaction data based on the random weighted averaging algorithm, and generate a dynamically updated personalized model.

[0138] S503, according to the personalized mode matching holographic projection system's spatial interaction interface protocol, converting the adjustment coefficient into a scene rendering instruction set, where the scene rendering instruction set is used to instruct the holographic projection device to control laser parameters and / or light field angle.

[0139] In one possible embodiment, the initial adjustment coefficient is input into the incremental learning model, and the historical interaction data is fused based on a random weighted averaging algorithm to generate a dynamically updated personalized model, including:

[0140] S601, evaluate the historical knowledge retention rate after the model update through sliding window cross-validation to generate a stability verification result.

[0141] S602: Dynamically adjust the model weight distribution according to the stability verification result to generate a coverage threshold parameter. The coverage threshold parameter is used to limit the coverage of new knowledge on historical data.

[0142] S603, truncating the parameter update gradient of the incremental learning model based on the coverage threshold parameter to generate a personalized model after catastrophic forgetting is suppressed. The personalized model is used to update the teaching content mapping relationship of the holographic projection system.

[0143] In a possible embodiment, performing trend analysis on student response data after the scene change instruction set is executed to generate an optimized interactive experience parameter set includes:

[0144] S701, extracting the interaction frequency and operation accuracy from the student response data after the scene rendering instruction set is executed, modeling the response change trend based on the hidden Markov model, and generating a response evaluation value;

[0145] S702, when the response evaluation value is lower than a preset threshold, partitioning the feature space using a C4.5 decision tree algorithm to generate a classification rule-driven improved parameter set;

[0146] S703: Input the improved parameter set into the streaming data processing engine, dynamically load the geographic scene resources based on the time-sensitive hash index, and generate an optimized interactive experience parameter set.

[0147] Based on the same inventive concept, the present application also provides a holographic projection-based geography teaching interactive system for implementing the aforementioned holographic projection-based geography teaching interactive method. The implementation solution provided by this system is similar to the implementation solution described in the aforementioned method. Therefore, the specific limitations of one or more holographic projection-based geography teaching interactive system embodiments provided below can be found in the above-mentioned limitations of the holographic projection-based geography teaching interactive method, and will not be repeated here.

[0148] In an exemplary embodiment, Figure 3 As shown, a geography teaching interactive system based on holographic projection is provided, comprising:

[0149] A holographic projection device, a motion capture sensor array and a terminal processor, wherein the terminal processor is configured to implement the geography teaching interaction method based on holographic projection in any of the embodiments described above.

[0150] The terminal processor is communicatively connected with the holographic projection device and the motion capture sensor array respectively.

[0151] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the geography teaching method based on holographic projection as described above are implemented.

[0152] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial description of the method embodiments. The device embodiments described above are merely illustrative, wherein the components described as separate parts may or may not be physically separated, and the parts displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the disclosed solution. A person of ordinary skill in the art can understand and implement it without expending creative work.

[0153] The above-described embodiments merely represent several implementation methods of the embodiments of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the concept of the embodiments of the present application, and these modifications and improvements fall within the scope of protection of the embodiments of the present application.

Claims

1. A geography teaching device based on holographic projection, characterized in that: The device includes a data acquisition module, a behavior analysis module, a dynamic adjustment module and a feedback optimization module: The data acquisition module is used to obtain interaction data, perform timestamp marking and sensor data fusion processing on the interaction data, and generate a multi-dimensional behavior data set containing timestamps; the interaction data is used to characterize the interaction behavior of students with the holographic projection geography content; The behavior analysis module is used to extract perspective preference features and analyze operation habits of the multi-dimensional behavior data set to generate student learning deviation; The dynamic adjustment module is used to perform parameter adjustment processing on the teaching content mapping relationship of the holographic projection system according to the student learning deviation, and generate a scene change instruction set; The feedback optimization module is used to perform trend analysis on the student response data after the scene change instruction set is executed, and generate an optimized interactive experience parameter set, which is used to instruct the holographic projection device to generate a holographic image; Wherein, the data acquisition module includes: A multi-source data acquisition unit is used to obtain the student's perspective movement trajectory and quantify the touch operation force based on the pressure sensor to generate the original behavior data stream; a data preprocessing unit, configured to perform sensor noise compensation processing on the original behavior data stream to generate a denoised original data set; A timestamp generating unit, configured to perform time synchronization processing on the original data set, align the time axis of the original data set based on a time axis alignment algorithm, and generate a multi-dimensional behavior data set marked with a timestamp; The behavior analysis module includes: a data cleaning unit, configured to filter outliers on the multidimensional behavior dataset and eliminate noise data using a sliding window algorithm to generate a standardized behavior dataset; a viewing angle preference analysis unit, configured to extract a gaze point coordinate sequence from the standardized behavior dataset, perform spatial aggregation processing on the gaze point coordinate sequence based on a density clustering algorithm, and generate a viewing angle preference pattern; An operation habit parsing unit, configured to perform frequent pattern mining on the operation instruction sequence in the standardized behavior data set, match it with a preset behavior template through a dynamic time warping algorithm, and generate an operation habit feature vector; A deviation calculation unit is used to map the perspective preference pattern and the operation habit feature vector to the node space of the pre-trained geographic knowledge graph to obtain a student learning vector, calculate the semantic distance between the student learning vector and the teaching target vector based on the graph neural network, and generate the student learning deviation according to the semantic distance.

2. The device according to claim 1, characterized in that The dynamic adjustment module includes: An adjustment coefficient generating unit is used to optimize the teaching content mapping function based on the student learning deviation through a gradient descent algorithm to generate an initial adjustment coefficient of the scene transformation parameter; An incremental learning unit, configured to input the initial adjustment coefficient into an incremental learning model, perform fusion processing on historical interaction data based on a random weighted averaging algorithm, and generate a dynamically updated personalized model; An instruction generation unit is used to convert the adjustment coefficient into a scene rendering instruction set according to the spatial interaction interface protocol of the personalized mode matching holographic projection system, and the scene rendering instruction set is used to instruct the holographic projection device to control laser parameters and / or light field angle.

3. The device according to claim 2, characterized in that The incremental learning unit includes: The history retention evaluation subunit is used to evaluate the historical knowledge retention rate after the model is updated through sliding window cross-validation and generate stability verification results; A weight adjustment subunit is used to dynamically adjust the model weight distribution according to the stability verification result and generate a coverage threshold parameter, wherein the coverage threshold parameter is used to limit the coverage of new knowledge on historical data; The threshold constraint subunit is used to truncate the parameter update gradient of the incremental learning model based on the coverage threshold parameter to generate a personalized model after catastrophic forgetting is suppressed, and the personalized model is used to update the teaching content mapping relationship of the holographic projection system.

4. The device according to claim 2, characterized in that The feedback optimization module includes: a response evaluation unit, configured to extract interaction frequency and operation accuracy from student response data after the scene rendering instruction set is executed, model the response change trend based on a hidden Markov model, and generate a response evaluation value; An instruction optimization unit, configured to, when the response evaluation value is lower than a preset threshold, partition the feature space using a C4.5 decision tree algorithm to generate an improved parameter set driven by a classification rule; A real-time update unit is used to input the improved parameter set into a streaming data processing engine, dynamically load the geographic scene resources based on a time-sensitive hash index, and generate an optimized interactive experience parameter set.

5. A geography teaching interactive method based on holographic projection, characterized in that: include: Acquire interaction data, perform timestamp marking and sensor data fusion processing on the interaction data, and generate a multidimensional behavior data set containing timestamps; The interaction data is used to characterize the interaction behavior between students and holographic projection geography content; Extracting perspective preference features and analyzing operating habits on the multidimensional behavior data set to generate student learning deviation; Performing parameter adjustment processing on the teaching content mapping relationship of the holographic projection system according to the student learning deviation, and generating a scene transformation instruction set; Performing trend analysis on student response data after the scene change instruction set is executed to generate an optimized interactive experience parameter set, wherein the interactive experience parameter set is used to instruct a holographic projection device to generate a holographic image; The acquiring of interaction data, performing timestamp marking and sensor data fusion processing on the interaction data to generate a multi-dimensional behavior data set containing timestamps includes: Obtain the student's perspective movement trajectory, and quantify the touch operation force based on the pressure sensor to generate the original behavior data stream; Performing sensor noise compensation processing on the original behavior data stream to generate a denoised original data set; Performing time synchronization processing on the original data set, aligning the time axis of the original data set based on a time axis alignment algorithm, and generating a multidimensional behavior data set marked with a timestamp; The extracting of perspective preference features and analyzing of operation habits of the multi-dimensional behavior dataset to generate student learning deviation includes: Performing outlier filtering on the multidimensional behavioral dataset and eliminating noise data using a sliding window algorithm to generate a standardized behavioral dataset; extracting a gaze point coordinate sequence from the standardized behavior dataset, performing spatial aggregation processing on the gaze point coordinate sequence based on a density clustering algorithm, and generating a viewing angle preference pattern; Performing frequent pattern mining on the operation instruction sequences in the standardized behavior dataset, matching them with the preset behavior templates through a dynamic time warping algorithm, and generating an operation habit feature vector; The perspective preference pattern and the operation habit feature vector are mapped to the node space of the pre-trained geographic knowledge graph to obtain the student learning vector, the semantic distance between the student learning vector and the teaching target vector is calculated based on the graph neural network, and the student learning deviation is generated according to the semantic distance.

6. A geography teaching interactive system based on holographic projection, characterized in that: The system comprises: A holographic projection device, a motion capture sensor array, and a terminal processor, wherein the terminal processor is configured to implement the geography teaching interactive method based on holographic projection according to claim 5; The terminal processor is communicatively connected to the holographic projection device and the motion capture sensor array respectively.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the method according to claim 5 is implemented.

Images