Space situation response type generation method and system based on artificial intelligence

Abstract

The invention relates to the technical field of space situation response type generation, in particular to a space situation response type generation method and system based on artificial intelligence, and the system is realized by adopting a distributed architecture based on edge computing nodes and a cloud intelligent center. The system further comprises a data perception preprocessing module, a dynamic modeling module, a response strategy generation module, an immersive experience module, an emotion recognition module, an anomaly detection module, a cross-modal interaction module and an optimization module. Compared with a traditional scheme, the space situation response type generation method and system based on artificial intelligence show remarkable advantages in the aspects of flexibility, generalization ability, comprehensive perception, real-time response, personalized experience, emotion interaction, abnormal response, continuous optimization and the like, and more intelligent, efficient and immersive space experience is provided for users.

Description

Technical Field

[0001] The present invention relates to the technical field of spatial context responsive generation, and specifically to a spatial context responsive generation method and system based on artificial intelligence. Background Art

[0002] Spatial context response refers to the system's ability to intelligently generate and execute corresponding response strategies based on the current spatial environment, user behavior, and data from multiple modalities to optimize user experience and meet user needs.

[0003] Existing spatial situational perception and response systems are mostly rule-driven and lack flexibility and generalization capabilities. When faced with dynamic and complex spatial environments, traditional systems usually require a large number of manually designed rules, have slow response speeds, and poor adaptability. In addition, they are unable to achieve comprehensive perception and real-time response to the environment, user behavior, and multimodal data, resulting in a poor user experience.

[0004] Based on this, the present invention provides an artificial intelligence-based spatial context responsive generation method and system to solve the technical problems raised above. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for responsively generating spatial contexts based on artificial intelligence to solve the problems raised by the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The first aspect of the present invention:

[0008] Provided is an artificial intelligence-based spatial context responsive generation system, the system adopts a distributed architecture based on edge computing nodes and a cloud-based intelligent center, the edge nodes are used for real-time perception and preliminary processing, the cloud-based center is used for model training and complex context reasoning, the edge computing nodes and the cloud-based intelligent center perform edge-cloud collaborative computing through an AP network, and also includes a data perception preprocessing module, a dynamic modeling module, a response strategy generation module, an immersive experience module, an emotion recognition module, an anomaly detection module, a cross-modal interaction module, and an optimization module;

[0009] The data perception preprocessing module is used for multimodal data collection, data fusion and feature extraction;

[0010] The dynamic modeling module is used for knowledge graph construction, dynamic situation capture and prediction;

[0011] The response strategy generation module is used for reinforcement learning response strategy optimization and response content intelligent generation;

[0012] The immersive experience module is used for digital light and shadow optimization and personalized experience customization;

[0013] The emotion recognition module is used for emotion recognition and generating emotion response strategies;

[0014] The anomaly detection module is used for abnormal behavior detection, early warning and emergency response;

[0015] The cross-modal interaction module is used for cross-modal information conversion and generation of cross-modal interaction strategies;

[0016] The optimization module is used for situational learning and generating situational optimization strategies.

[0017] Preferably, the data perception preprocessing module further includes a multimodal data acquisition unit and a data fusion unit;

[0018] The multimodal data acquisition unit collects visual, audio, and temperature multimodal data in the space through a camera, a microphone, and a temperature sensor;

[0019] The data acquisition unit uses IoT technology to collect real-time data and performs preliminary preprocessing through edge computing nodes;

[0020] The data fusion unit fuses the collected multimodal data and extracts spatial features and semantic information using a deep learning algorithm;

[0021] The data fusion unit processes data through a convolutional neural network or a long short-term memory network feature extraction model based on deep learning to extract key spatial feature information.

[0022] Preferably, the dynamic modeling module further includes a knowledge graph construction unit and a dynamic context capture unit;

[0023] The knowledge graph construction unit constructs a spatial context model based on the knowledge graph to represent the relationship between elements in the space;

[0024] The knowledge graph construction unit uses natural language processing technology and Neo4j graph database to extract and model spatial contextual relationships;

[0025] The dynamic situation capture unit captures the dynamic changes of the spatial situation in real time and predicts possible situation changes in the future;

[0026] The dynamic situation capture unit analyzes and predicts situation changes by integrating random forest and time series analysis prediction models.

[0027] Preferably, the response strategy generation module further includes a strategy optimization unit and a response content generation unit;

[0028] The strategy optimization unit generates an optimal response strategy using a reinforcement learning algorithm to adapt to different spatial situations;

[0029] The reinforcement learning unit optimizes and generates strategies through Q-learning or Deep Q-Network algorithms to ensure real-time and efficient responses;

[0030] The response content generation unit intelligently generates corresponding spatial situation content and visual and sound data according to the generated response strategy;

[0031] The response content generation unit uses a generative adversarial network or a variational autoencoder method to intelligently generate and fill in content.

[0032] Preferably, the immersive experience module further includes a digital light and shadow optimization unit and a personalized experience customization unit;

[0033] The digital light and shadow optimization unit optimizes the space scenario and improves the user experience by using digital light and shadow technology;

[0034] The digital light and shadow optimization unit simulates and optimizes light and shadow effects through ray tracing algorithms and real-time rendering technology, including Unity or Unreal Engine;

[0035] The personalized experience customization unit customizes an exclusive space experience according to the personalized needs of the user;

[0036] The personalized customization unit uses collaborative filtering algorithms or content-based recommendation algorithms to generate and recommend personalized experiences.

[0037] Preferably, the emotion recognition module further includes an emotion recognition unit and an emotion response unit;

[0038] The emotion recognition unit performs emotion recognition through facial expressions and voice emotion data;

[0039] The emotion recognition unit uses convolutional neural networks to extract and recognize emotions;

[0040] The emotion response unit generates a corresponding response strategy according to the identified emotion;

[0041] The emotional response strategy unit generates and adjusts the emotional response strategy through the emotional dictionary and rule matching algorithm.

[0042] Preferably, the anomaly detection module further includes an abnormal behavior detection unit and an emergency response unit;

[0043] The abnormal behavior detection unit detects abnormal behaviors of destruction and intrusion in the space in real time;

[0044] The abnormal behavior detection unit uses the behavior classification network to detect and analyze abnormal behaviors;

[0045] The emergency response unit performs early warning and emergency response when abnormal behavior is detected;

[0046] The early warning and emergency response unit executes early warning and response measures through predefined emergency response rules and emergency response plans.

[0047] Preferably, the cross-modal interaction module further includes a cross-modal conversion unit and a cross-modal interaction unit;

[0048] The cross-modal conversion unit converts and fuses information of different modalities to achieve cross-modal interaction;

[0049] The cross-modal information conversion unit uses modal mapping to convert and fuse information;

[0050] The cross-modal interaction unit generates a corresponding interaction strategy according to the cross-modal interaction requirements of the user;

[0051] The cross-modal interaction strategy generation unit generates and adjusts the interaction strategy through multimodal fusion algorithms and interaction rules.

[0052] Preferably, the optimization module further includes a situation learning unit and a situation optimization unit;

[0053] The context learning unit continuously optimizes the spatial context model by learning the user's interaction data and feedback;

[0054] The contextual learning unit uses the linear gradient descent method to update and optimize the model in real time;

[0055] The situation optimization unit generates an optimized space situation strategy according to the learning result;

[0056] The situational optimization strategy generation unit optimizes and adjusts the strategy through the policy gradient algorithm to achieve a better user experience.

[0057] On the other hand, based on the above system, the present invention also proposes a spatial context responsive generation method based on artificial intelligence, comprising the following steps:

[0058] S1. The edge computing node uses cameras, microphones, and temperature sensors to collect multimodal data in the space in real time, and performs preliminary processing at the edge node, including fusion and key feature extraction, and uses deep learning algorithms to quickly identify spatial elements and states, providing a basis for subsequent situation modeling;

[0059] S2. Based on the initially processed data, the cloud-based intelligent center builds and dynamically updates the spatial context model based on the knowledge graph and captures context changes in real time, and analyzes future context evolution through the prediction model;

[0060] S3. Use the reinforcement learning algorithm to generate the optimal response strategy and send it to the edge computing node. The edge node intelligently generates spatial context content and visual and sound data based on the strategy.

[0061] S4. Guide edge nodes to adjust lighting effects to improve user experience. At the same time, analyze user historical data and personalized needs in the cloud, customize space experience strategies, and push personalized content through edge nodes.

[0062] S5. Capture user emotion data through edge computing nodes, upload to the cloud for emotion recognition, generate emotion response strategies in the cloud, and interact with users in the form of vision and sound through edge nodes;

[0063] S6. Use edge computing nodes to detect abnormal behaviors in the space in real time, trigger the early warning mechanism, and quickly respond and support according to the emergency response rules defined in the cloud;

[0064] S7. Capture user cross-modal interaction needs through edge nodes and upload them to the cloud, generate cross-modal interaction strategies in the cloud, realize natural interaction experience through edge nodes, and achieve seamless conversion and integration of different modal information;

[0065] S8. Establish a cloud-based intelligent center to continuously learn user interaction data and feedback mechanisms and optimize spatial context models. Feedback the learning results to edge computing nodes through the edge-cloud collaborative mechanism to guide the generation of spatial context strategies that better meet user needs, and continuously improve user experience and intelligence levels.

[0066] Compared with the prior art, the present invention has the following beneficial effects:

[0067] By adopting artificial intelligence technologies such as deep learning and reinforcement learning, the present invention enables the system to automatically learn and adapt to different spatial situations, quickly generate effective response strategies, collect and fuse multimodal data in real time, and achieve comprehensive perception of the environment, user behavior and multimodal data. By utilizing user interaction data and feedback, it can learn user preferences and needs and generate personalized spatial situation strategies. It also has emotion recognition capabilities and can generate corresponding emotional response strategies based on user facial expressions and voice emotion data. Through the situational learning and optimization module, the system can continuously collect user interaction data and feedback, and update and optimize the spatial situation model in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1The spatial context responsive generation system topology diagram based on artificial intelligence of the present invention;

[0069] Figure 2 This is a flow chart of the spatial context responsive generation method based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0070] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0071] Example 1

[0072] See also Figure 1 , the present invention proposes a spatial context responsive generation system based on artificial intelligence. The system adopts a distributed architecture based on edge computing nodes and a cloud intelligent center. The edge nodes are used for real-time perception and preliminary processing, and the cloud center is used for model training and complex context reasoning. The edge computing nodes and the cloud intelligent center perform edge-cloud collaborative computing through an AP network;

[0073] It should be noted that the system also includes a data perception preprocessing module, a dynamic modeling module, a response strategy generation module, an immersive experience module, an emotion recognition module, an anomaly detection module, a cross-modal interaction module, and an optimization module;

[0074] Among them, it is also necessary to explain that the data perception preprocessing module of this system is used for multimodal data collection, data fusion and feature extraction, the dynamic modeling module of this system is used for knowledge graph construction, dynamic situation capture and prediction, the response strategy generation module of this system is used for reinforcement learning response strategy optimization and intelligent generation of response content, the immersive experience module of this system is used for digital light and shadow optimization and personalized experience customization, the emotion recognition module of this system is used for emotion recognition and generation of emotion response strategy, the anomaly detection module of this system is used for abnormal behavior detection, early warning and emergency response, the cross-modal interaction module of this system is used for cross-modal information conversion and generation of cross-modal interaction strategy, and the optimization module of this system is used for situational learning and generation of situational optimization strategy.

[0075] In this embodiment, it should also be noted that the data perception preprocessing module also includes a multimodal data acquisition unit and a data fusion unit;

[0076] Among them, the multimodal data acquisition unit collects visual, audio, and temperature multimodal data in the space through a camera, a microphone, and a temperature sensor;

[0077] Furthermore, the data acquisition unit uses IoT technology to collect data in real time and performs preliminary preprocessing through edge computing nodes;

[0078] Among them, the data fusion unit fuses the collected multimodal data and uses deep learning algorithms to extract spatial features and semantic information;

[0079] Furthermore, the data fusion unit processes data through a convolutional neural network or a long short-term memory network feature extraction model based on deep learning to extract key spatial feature information.

[0080] In this embodiment, it should also be noted that the dynamic modeling module also includes a knowledge graph construction unit and a dynamic context capture unit;

[0081] Among them, the knowledge graph construction unit constructs a spatial context model based on the knowledge graph to represent the relationship between the elements in the space;

[0082] Furthermore, the knowledge graph construction unit uses natural language processing technology and Neo4j graph database to extract and model spatial contextual relationships;

[0083] Among them, the dynamic situation capture unit captures the dynamic changes of the spatial situation in real time and predicts possible situation changes in the future;

[0084] Furthermore, the dynamic situation capture unit analyzes and predicts situation changes by integrating random forest and time series analysis prediction models.

[0085] In this embodiment, it should also be noted that the response strategy generation module also includes a strategy optimization unit and a response content generation unit;

[0086] Among them, the strategy optimization unit uses reinforcement learning algorithms to generate optimal response strategies to adapt to different spatial situations;

[0087] Furthermore, the reinforcement learning unit optimizes and generates strategies through Q-learning or Deep Q-Network algorithms to ensure real-time and efficient responses;

[0088] Among them, the response content generation unit intelligently generates corresponding spatial situation content and visual and sound data according to the generated response strategy;

[0089] Furthermore, the response content generation unit utilizes a generative adversarial network or a variational autoencoder method to intelligently generate and fill in content.

[0090] In this embodiment, it should also be noted that the immersive experience module also includes a digital light and shadow optimization unit and a personalized experience customization unit;

[0091] Among them, the digital light and shadow optimization unit uses digital light and shadow technology to optimize the space situation and enhance the user experience;

[0092] Furthermore, the digital light and shadow optimization unit simulates and optimizes light and shadow effects through ray tracing algorithms and real-time rendering technology, including Unity or Unreal Engine;

[0093] Among them, the personalized experience customization unit customizes exclusive space experience according to the user's personalized needs;

[0094] Furthermore, the personalized customization unit utilizes a collaborative filtering algorithm or a content-based recommendation algorithm to generate and recommend personalized experiences.

[0095] In this embodiment, it should also be noted that the emotion recognition module also includes an emotion recognition unit and an emotion response unit;

[0096] Among them, the emotion recognition unit performs emotion recognition through facial expressions and voice emotion data;

[0097] Furthermore, the emotion recognition unit uses convolutional neural networks to extract and recognize emotions;

[0098] Among them, the emotion response unit generates a corresponding response strategy according to the identified emotion;

[0099] Furthermore, the emotional response strategy unit generates and adjusts the emotional response strategy through the emotional dictionary and rule matching algorithm.

[0100] In this embodiment, it should also be noted that the anomaly detection module also includes an abnormal behavior detection unit and an emergency response unit;

[0101] Among them, the abnormal behavior detection unit detects abnormal behaviors of destruction and intrusion in the space in real time;

[0102] Furthermore, the abnormal behavior detection unit uses the behavior classification network to detect and analyze abnormal behaviors;

[0103] Among them, the emergency response unit issues early warning and emergency response when abnormal behavior is detected;

[0104] Furthermore, the early warning and emergency response unit executes early warning and response measures through predefined emergency response rules and emergency response plans.

[0105] In this embodiment, it should also be noted that the cross-modal interaction module also includes a cross-modal conversion unit and a cross-modal interaction unit;

[0106] Among them, the cross-modal conversion unit converts and fuses information of different modalities to achieve cross-modal interaction;

[0107] Furthermore, the cross-modal information conversion unit uses modality mapping to convert and fuse information;

[0108] Among them, the cross-modal interaction unit generates corresponding interaction strategies according to the user's cross-modal interaction needs;

[0109] Furthermore, the cross-modal interaction strategy generation unit generates and adjusts the interaction strategy through a multimodal fusion algorithm and interaction rules.

[0110] In this embodiment, it should also be noted that the optimization module also includes a context learning unit and a context optimization unit;

[0111] Among them, the situational learning unit continuously optimizes the spatial situational model by learning the user's interaction data and feedback;

[0112] Furthermore, the contextual learning unit uses the linear gradient descent method to update and optimize the model in real time;

[0113] Among them, the situation optimization unit generates optimized spatial situation strategies based on the learning results;

[0114] Furthermore, the context optimization strategy generation unit optimizes and adjusts the strategy through a policy gradient algorithm to achieve a better user experience.

[0115] Example 2

[0116] See also Figure 2 In the actual application process, based on the above system, the present invention also proposes a spatial context responsive generation method based on artificial intelligence, which specifically includes the following steps:

[0117] (1) Data collection and preprocessing:

[0118] (1.1) Multimodal data collection: Edge computing nodes deploy sensors such as cameras, microphones, and temperature sensors to capture multimodal data such as vision, audio, and temperature in the space in real time. IoT technology is used to ensure the real-time and accuracy of data collection. Data is transmitted to edge computing nodes wirelessly or wiredly.

[0119] (1.2) Data fusion: On the edge computing node, the collected multimodal data is initially fused to ensure data consistency and integrity. Deep learning algorithms, such as convolutional neural networks (CNN) or long short-term memory networks (LSTM), are applied to extract features from the fused data to identify key spatial features and semantic information.

[0120] (1.3) Feature extraction and transmission: The extracted feature information is further processed to reduce the amount of data and retain key information. The processed feature data is uploaded to the cloud intelligence center through the AP network, providing a basis for subsequent situation modeling;

[0121] (2) Dynamic scenario modeling and prediction:

[0122] (2.1) Knowledge graph construction: The cloud-based intelligent center uses natural language processing technology and the Neo4j graph database to build a knowledge graph of spatial context based on uploaded feature data. The knowledge graph represents the relationship between elements in the space and provides a structured basis for context understanding.

[0123] (2.2) Dynamic context capture: monitor and update the knowledge graph in real time to capture the dynamic changes of spatial contexts, use random forest and time series analysis prediction models to analyze the trend of context changes and predict possible future context evolution;

[0124] (2.3) Context prediction and update: Integrate the prediction results into the spatial context model to dynamically update the model. Send the updated model information to the edge computing node through the AP network to guide the subsequent response strategy generation.

[0125] (3) Response strategy generation and execution:

[0126] (3.1) Strategy optimization: The cloud-based intelligent center uses reinforcement learning algorithms, such as Q-learning or Deep Q-Network, to generate the optimal response strategy. Through simulation and iterative optimization, it ensures the adaptability and efficiency of the strategy in different spatial scenarios.

[0127] (3.2) Strategy delivery: The optimized response strategy is delivered to the edge computing node through the AP network. The edge computing node prepares to generate corresponding spatial context content and visual and sound data according to the strategy guidance.

[0128] (3.3) Content generation and execution: Edge computing nodes use methods such as generative adversarial networks (GANs) or variational autoencoders (VAEs) to intelligently generate responsive content and present the generated content to users in real time through visual display devices, sound systems, etc., to achieve an immersive spatial experience.

[0129] (4) Immersive experience optimization and personalized customization:

[0130] (4.1) Lighting and shadowing optimization: The cloud-based intelligent center guides the edge computing nodes to optimize the lighting and shadowing effects using digital lighting and shadowing technologies (such as Unity or Unreal Engine), and renders and adjusts the lighting and shadowing in real time to enhance the immersion and realism of the user experience.

[0131] (4.2) Personalized demand analysis: The cloud-based intelligent center analyzes the user's historical interaction data and personalized needs, generates personalized experience strategies using collaborative filtering or content-based recommendation algorithms, and sends the personalized strategies to edge computing nodes to customize exclusive space experiences;

[0132] (4.3) Personalized content push: The edge computing node generates and pushes spatial contextual content that meets user preferences based on personalized strategies, and updates and adjusts the content in real time to meet users’ ever-changing personalized needs;

[0133] (5) Emotion recognition and response:

[0134] (5.1) Emotional data collection: Edge computing nodes capture users’ facial expressions, voice and other emotional data in real time, and upload the emotional data to the cloud intelligence center for further processing;

[0135] (5.2) Emotion recognition: The cloud-based intelligent center uses deep learning algorithms such as convolutional neural networks to perform emotion recognition and identify the user's emotional state, such as happiness, sadness, surprise, etc.

[0136] (5.3) Emotional response strategy generation: Based on the identified emotional state, the cloud intelligent center generates the corresponding emotional response strategy and sends it to the edge computing node to interact with the user in the form of vision, sound, etc. to enhance emotional resonance;

[0137] (6) Anomaly detection and emergency response:

[0138] (6.1) Abnormal behavior detection: The edge computing node uses the behavior classification network to detect abnormal behaviors in the space in real time, such as sabotage and intrusion. Once abnormal behavior is detected, the early warning mechanism is immediately triggered;

[0139] (6.2) Early warning and emergency response: According to the emergency response rules pre-defined in the cloud, the edge computing nodes quickly respond to abnormal behaviors and upload the abnormal information to the cloud intelligence center for further analysis and processing;

[0140] (6.3) Cloud support and response: The cloud intelligence center provides support and guidance for emergency response, ensures the accuracy and effectiveness of the response, and updates emergency response rules as needed to deal with new abnormal behaviors that may appear in the future;

[0141] (7) Cross-modal interaction processing:

[0142] (7.1) Cross-modal demand capture: Edge computing nodes capture users’ cross-modal interaction needs, such as using vision and voice to interact at the same time, and upload the needs to the cloud intelligence center for further processing;

[0143] (7.2) Cross-modal interaction strategy generation: The cloud intelligence center uses multimodal fusion algorithms and interaction rules to generate cross-modal interaction strategies and sends the strategies to edge computing nodes to achieve a natural cross-modal interaction experience;

[0144] (7.3) Cross-modal interaction implementation: Edge computing nodes implement seamless conversion and fusion of information from different modalities based on cross-modal interaction strategies, providing users with a smooth and natural cross-modal interaction experience;

[0145] (8) Contextual learning and optimization:

[0146] (8.1) User interaction data collection: The cloud intelligence center continuously collects user interaction data and feedback, and stores the data in the cloud database to provide a basis for subsequent learning;

[0147] (8.2) Context model optimization: Use optimization algorithms such as the linear gradient descent method to update and optimize the spatial context model in real time, and continuously adjust model parameters based on user interaction data and feedback to improve the accuracy and adaptability of the model;

[0148] (8.3) Contextual strategy generation and optimization: Based on the learning results, the cloud-based intelligent center generates optimized spatial contextual strategies and feeds back the optimized strategies to the edge computing nodes through the edge-cloud collaborative mechanism to guide the generation of spatial contextual strategies that better meet user needs. The optimization process is continuously iterated to continuously improve the user experience and the intelligence level of the system.

[0149] Through the above steps, the artificial intelligence-based spatial context responsive generation method and system of the present invention show significant advantages over traditional solutions in terms of flexibility, generalization ability, comprehensive perception, real-time response, personalized experience, emotional interaction, abnormal response and continuous optimization, providing users with a more intelligent, efficient and immersive spatial experience.

[0150] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0151] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A spatial context responsive generation system based on artificial intelligence. The system adopts a distributed architecture based on edge computing nodes and a cloud intelligent center. The edge nodes are used for real-time perception and preliminary processing, and the cloud center is used for model training and complex context reasoning. The edge computing nodes and the cloud intelligent center perform edge-cloud collaborative computing through an AP network. The system is characterized by: It also includes data perception preprocessing module, dynamic modeling module, response strategy generation module, immersive experience module, emotion recognition module, anomaly detection module, cross-modal interaction module and optimization module; The data perception preprocessing module is used for multimodal data collection, data fusion and feature extraction; The dynamic modeling module is used for knowledge graph construction, dynamic situation capture and prediction; The response strategy generation module is used for reinforcement learning response strategy optimization and response content intelligent generation; The immersive experience module is used for digital light and shadow optimization and personalized experience customization; The emotion recognition module is used for emotion recognition and generating emotion response strategies; The anomaly detection module is used for abnormal behavior detection, early warning and emergency response; The cross-modal interaction module is used for cross-modal information conversion and generation of cross-modal interaction strategies; The optimization module is used for situational learning and generating situational optimization strategies.

2. The artificial intelligence-based spatial context responsive generation system according to claim 1 is characterized in that: The data perception preprocessing module also includes a multimodal data acquisition unit and a data fusion unit; The multimodal data acquisition unit collects visual, audio, and temperature multimodal data in the space through a camera, a microphone, and a temperature sensor; The data fusion unit fuses the collected multimodal data and uses a deep learning algorithm to extract spatial features and semantic information.

3. The spatial context responsive generation system based on artificial intelligence according to claim 1 is characterized in that: The dynamic modeling module also includes a knowledge graph construction unit and a dynamic context capture unit; The knowledge graph construction unit constructs a spatial context model based on the knowledge graph to represent the relationship between elements in the space; The dynamic situation capture unit captures the dynamic changes of the spatial situation in real time and predicts possible situation changes in the future.

4. The artificial intelligence-based spatial context responsive generation system according to claim 1 is characterized in that: The response strategy generation module also includes a strategy optimization unit and a response content generation unit; The strategy optimization unit generates an optimal response strategy to adapt to different spatial situations using a reinforcement learning algorithm; The response content generation unit generates corresponding spatial context content and visual and sound data according to the generated response strategy.

5. The artificial intelligence-based spatial context responsive generation system according to claim 1 is characterized in that: The immersive experience module also includes a digital light and shadow optimization unit and a personalized experience customization unit; The digital light and shadow optimization unit optimizes the space scenario using digital light and shadow technology; The personalized experience customization unit customizes an exclusive space experience according to the personalized needs of the user.

6. The artificial intelligence-based spatial context responsive generation system according to claim 1 is characterized in that: The emotion recognition module also includes an emotion recognition unit and an emotion response unit; The emotion recognition unit performs emotion recognition through facial expressions and voice emotion data; The emotion response unit generates a corresponding response strategy according to the identified emotion.

7. The artificial intelligence-based spatial context responsive generation system according to claim 1 is characterized in that: The anomaly detection module also includes an abnormal behavior detection unit and an emergency response unit; The abnormal behavior detection unit detects abnormal behaviors of destruction and intrusion in the space in real time; The emergency response unit performs early warning and emergency response when abnormal behavior is detected.

8. The artificial intelligence-based spatial context responsive generation system according to claim 1 is characterized in that: The cross-modal interaction module also includes a cross-modal conversion unit and a cross-modal interaction unit; The cross-modal conversion unit converts and fuses information of different modalities to achieve cross-modal interaction; The cross-modal interaction unit generates a corresponding interaction strategy according to the cross-modal interaction requirements of the user.

9. The artificial intelligence-based spatial context responsive generation system according to claim 1 is characterized in that: The optimization module also includes a situation learning unit and a situation optimization unit; The context learning unit continuously optimizes the spatial context model by learning the user's interaction data and feedback; The situation optimization unit generates an optimized space situation strategy according to the learning result.

10. A method for responsive generation of spatial context based on artificial intelligence, applied to the system for responsive generation of spatial context based on artificial intelligence according to any one of claims 1 to 9, characterized in that: The following steps are involved: S1. The edge computing node uses cameras, microphones, and temperature sensors to collect multimodal data in the space in real time, and performs preliminary processing at the edge node, including fusion and key feature extraction, and uses deep learning algorithms to quickly identify spatial elements and states, providing a basis for subsequent situation modeling; S2. Based on the initially processed data, the cloud-based intelligent center builds and dynamically updates the spatial context model based on the knowledge graph and captures context changes in real time, and analyzes future context evolution through the prediction model; S3. Use the reinforcement learning algorithm to generate the optimal response strategy and send it to the edge computing node. The edge node intelligently generates spatial context content and visual and sound data based on the strategy. S4. Guide edge nodes to adjust lighting effects to improve user experience. At the same time, analyze user historical data and personalized needs in the cloud, customize space experience strategies, and push personalized content through edge nodes. S5. Capture user emotion data through edge computing nodes, upload to the cloud for emotion recognition, generate emotion response strategies in the cloud, and interact with users in the form of vision and sound through edge nodes; S6. Use edge computing nodes to detect abnormal behaviors in the space in real time, trigger the early warning mechanism, and quickly respond and support according to the emergency response rules defined in the cloud; S7. Capture user cross-modal interaction needs through edge nodes and upload them to the cloud, generate cross-modal interaction strategies in the cloud, realize natural interaction experience through edge nodes, and achieve seamless conversion and integration of different modal information; S8. Establish a cloud-based intelligent center to continuously learn user interaction data and feedback mechanisms and optimize spatial context models. Feedback the learning results to edge computing nodes through the edge-cloud collaborative mechanism to guide the generation of spatial context strategies that better meet user needs, and continuously improve user experience and intelligence levels.

Images