Digital data conversion method and system based on artificial intelligence

Abstract

The invention belongs to the technical field of digital data conversion, and discloses a digital data conversion method and system based on artificial intelligence. The method comprises the following steps: building a digital data display platform, deploying a block chain network, using an artificial intelligence algorithm, building a digital data conversion engine, and connecting the digital data conversion engine to the digital data display platform; on the basis of the digital data display platform, collecting real-time multi-modal data, and performing feature fusion extraction on the real-time multi-modal data by using a digital data conversion engine to obtain real-time multi-modal fusion features; and according to the real-time multi-modal fusion features, performing digital data conversion by using a digital data conversion engine to obtain real-time digital data, and visualizing the real-time digital data by using a digital data display platform. According to the method, the problems of single data source, low data processing efficiency, insufficient data security and poor visualization effect in the prior art are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of digital data conversion, and particularly relates to a digital data conversion method and system based on artificial intelligence. Background Art

[0002] Digital data refers to various types of data generated, collected, and stored during the process of achieving digital immortality. Digital data can detailedly record an individual's thoughts, experiences, emotions, and memories, thereby preserving the individual's unique identity in the digital world. For an individual, these data are the core of achieving digital immortality and are crucial for their existence and continuation in the digital world. Digital data has great economic value and can drive the development of related industries, such as digital storage, cloud computing, virtual reality, etc. These data may also give rise to new business models and services, such as digital heritage management, virtual companionship, etc. In short, digital data is not only of great significance at the individual level but also has a profound impact on multiple levels such as technology, society, culture, economy, law, and science. However, with the accumulation and application of digital data, a series of challenges and controversies have also arisen.

[0003] The existing digital data conversion technologies have the following defects: 1) Single data source: Existing technologies often focus on feature extraction of single-modal data, such as only paying attention to images or audio, while ignoring the complementarity and correlation between multi-modal data. For complex multi-modal data, existing feature extraction methods may not be able to fully capture deep and subtle features, resulting in information loss and being unable to comprehensively reproduce an individual's digital identity; 2) Low data processing efficiency: When existing technologies process large-scale multi-modal data, they often consume a large amount of time and computing resources, resulting in low data processing efficiency and being difficult to meet real-time requirements; 3) Insufficient data security: Since digital data involves a large amount of privacy information, existing technologies lack effective security mechanisms in the storage and management of digital data and are vulnerable to security threats such as data tampering and leakage; 4) Poor visualization effect: Existing technologies often lack intuitiveness and interactivity in digital data visualization, unable to clearly display digital data, which affects the user experience. Summary of the Invention

[0004] In order to solve the problems of single data source, low data processing efficiency, insufficient data security, and poor visualization effect existing in the prior art, the purpose of the present invention is to provide a digital data conversion method and system based on artificial intelligence.

[0005] The technical solution adopted by the present invention is as follows: A digital data conversion method based on artificial intelligence, comprising the following steps: Build a digital data display platform, deploy a blockchain network, use artificial intelligence algorithms, construct a digital data conversion engine, and connect the digital data conversion engine to the digital data display platform; Based on the digital data display platform, collect real-time multimodal data, and use the digital data conversion engine to perform feature fusion extraction on the real-time multimodal data to obtain real-time multimodal fusion features; According to the real-time multimodal fusion features, use the digital data conversion engine to perform digital data conversion to obtain real-time digital data, and use the digital data display platform to visualize the real-time digital data.

[0006] Furthermore, the digital data display platform is provided with a multimodal data upload module, a conversion requirement collection module, and a digital data visualization module; The digital data conversion engine is provided with a feature fusion extraction model, a digital portrait generation model, a conversion strategy generation model, and a digital data conversion model.

[0007] Furthermore, building a digital data display platform, deploying a blockchain network, using artificial intelligence algorithms, constructing a digital data conversion engine, and connecting the digital data conversion engine to the digital data display platform includes the following steps: On the software program platform, build a digital data display architecture, and build a multimodal data upload module, a conversion requirement collection module, and a digital data visualization module to obtain a digital data display platform; Distributively connect several data servers as data nodes, set up an IPFS system and smart contracts to obtain a blockchain network, and connect the blockchain network to the digital data display platform; Based on the multimodal data upload module of the digital data display platform, collect several historical multimodal data, and preprocess the several historical multimodal data to obtain several preprocessed historical multimodal data; According to the several preprocessed historical multimodal data, use multimodal feature fusion and deep learning algorithms to construct a feature fusion extraction model, and generate several historical multimodal fusion features; According to the several historical multimodal fusion features, use key feature screening and deep learning algorithms to construct a digital portrait generation model, and generate several historical key multimodal features and corresponding historical digital portraits; According to the several historical digital portraits and several preset conversion requirement information, use enhanced reinforcement learning algorithms to construct a conversion strategy generation model, and generate several historical conversion strategies and corresponding historical conversion strategy generation experiences; According to the several historical key multimodal features, corresponding historical digital portraits, and historical conversion strategies, use generative artificial intelligence algorithms to construct a digital data conversion model; Integrate the feature fusion extraction model, digital portrait generation model, conversion strategy generation model, and digital data conversion model to obtain a digital data conversion engine, and connect it to the digital data display platform.

[0008] Furthermore, the feature fusion extraction model is constructed based on the FPN-DBN-LSTM-Attention algorithm, and the feature fusion extraction model includes an image feature extraction module constructed based on the FPN algorithm, an audio feature extraction module constructed based on the DBN algorithm, a text feature extraction module constructed based on the LSTM algorithm, and a feature fusion module constructed based on the Attention mechanism. The feature fusion module is respectively connected to the image feature extraction module, the audio feature extraction module, and the text feature extraction module.

[0009] Furthermore, the digital portrait generation model is constructed based on the RF-Elman algorithm, and the digital portrait generation model includes a key feature screening module constructed based on the RF algorithm and a digital portrait generation module constructed based on the Elman algorithm connected in sequence.

[0010] Furthermore, the conversion strategy generation model is constructed based on the MPO-MOGRPO algorithm, and the conversion strategy generation model includes a meta-strategy optimization module constructed based on the MPO algorithm and a conversion strategy generation module constructed based on the MOGRPO algorithm. The conversion strategy generation module includes a set of objective functions, a policy network, an experience replay pool, and an agent. The agent is respectively connected to the set of objective functions and the policy network, and the meta-strategy optimization module is connected to the policy network.

[0011] Furthermore, the digital data conversion model is constructed based on the MLP-AIGC algorithm, and the digital data conversion model includes a feature processing module constructed based on the MLP algorithm and a digital data conversion module group constructed based on the AIGC algorithm connected in sequence. The digital data conversion module group includes a text generation module constructed based on the Transformer algorithm, an image generation module constructed based on the GAN, an audio generation module constructed based on the WaveNet algorithm, and a video generation module constructed based on the VGAN. The feature processing module is respectively connected to the text generation module, the image generation module, the audio generation module, and the video generation module.

[0012] Furthermore, based on the digital data display platform, collect real-time multimodal data, and use the digital data conversion engine to perform feature fusion extraction on the real-time multimodal data to obtain real-time multimodal fusion features, including the following steps: Based on the digital data display platform, collect real-time multimodal data and real-time conversion requirement information, and preprocess the real-time multimodal data to obtain preprocessed real-time multimodal data; A feature fusion extraction model using a digital data conversion engine extracts real-time multimodal features from preprocessed real-time multimodal data; Perform feature fusion on the real-time multimodal features to obtain real-time multimodal fusion features of the preprocessed real-time multimodal data.

[0013] Furthermore, according to the real-time multimodal fusion features, use the digital data conversion engine to perform digital data conversion to obtain real-time digital data, and use the digital data display platform to visualize the real-time digital data, including the following steps: Use the digital portrait generation model of the digital data conversion engine to generate a digital portrait according to the real-time multimodal fusion features to obtain real-time key multimodal features and corresponding real-time digital portraits; According to the real-time digital portrait and real-time conversion requirement information, use the conversion strategy generation model of the digital data conversion engine to generate a conversion strategy to obtain a real-time conversion strategy; According to the real-time key multimodal features, real-time digital portrait, and real-time conversion strategy, use the digital data conversion model of the digital data conversion engine to perform digital data conversion to obtain real-time digital data; Use the blockchain network to perform distributed storage of the real-time digital data, and use the digital data display platform to visualize the real-time digital data.

[0014] A digital data conversion system based on artificial intelligence is used to implement the digital data conversion method. The system includes a system initialization unit, a feature fusion extraction unit, and a digital data conversion unit connected in sequence.

[0015] The beneficial effects of the present invention are: A digital data conversion method and system based on artificial intelligence provided by the present invention can fully capture deep and subtle features by collecting real-time multimodal data (including images, audio, video, text, etc.) and using a digital data conversion engine for feature fusion extraction, thereby comprehensively and accurately reproducing an individual's digital identity and avoiding the problem of information loss caused by single-modal data. By using artificial intelligence algorithms to build a digital data conversion engine, the efficiency of data processing is significantly improved, and large-scale multimodal data can be processed in a short time to meet real-time requirements, which is applicable to scenarios such as real-time interaction and dynamic display. By deploying a blockchain network, distributed storage of real-time digital data is achieved, enhancing the security of digital data, effectively preventing security threats such as data tampering and leakage, and protecting users' privacy information. Using a digital data display platform to visualize real-time digital data provides an intuitive and highly interactive display method, enabling users to clearly understand and operate digital data, and significantly improving the user experience. According to real-time multimodal fusion features and real-time conversion requirement information, a real-time conversion strategy is dynamically generated, and a digital data conversion model is used for flexible digital data conversion to adapt to diverse application scenarios and requirements. It is not only applicable to scenarios such as virtual image reconstruction and digital memorial construction, but also can be widely applied to various fields such as cultural inheritance, education, and entertainment, meeting various interactive needs through realistic digital reproduction, and promoting the development and application of digital immortality technology.

[0016] Other beneficial effects of the present invention will be further described in the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a flowchart of the digital data conversion method based on artificial intelligence in the present invention.

[0018] Figure 2 is a structural block diagram of the digital data conversion system based on artificial intelligence in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] The present invention will be further explained below with reference to the accompanying drawings and specific embodiments.

[0020] Embodiment 1: As Figure 1 shown, this embodiment provides a digital data conversion method based on artificial intelligence, including the following steps: S1: Build a digital data display platform, deploy a blockchain network, use artificial intelligence algorithms to build a digital data conversion engine, and connect the digital data conversion engine to the digital data display platform; The digital data display platform is provided with a multimodal data upload module, a conversion requirement collection module, and a digital data visualization module; The multi-modal data upload module is used to collect the user's real-time multi-modal data after the user terminal connects to the digital data display platform; the real-time multi-modal data includes real-time image data, real-time video data, real-time text data, and real-time audio data; The conversion requirement collection module is used to collect the user's real-time conversion requirement information; the real-time conversion requirement information includes the user's requirements for the scenario, focus, characters, and style of the real-time digital data; The digital data visualization module is used to visualize the real-time digital data, improving the intuitiveness and convenience of the user to view and inspect the real-time digital data; The digital data conversion engine is provided with a feature fusion extraction model, a digital portrait generation model, a conversion strategy generation model, and a digital data conversion model; The feature fusion extraction model is used to extract the real-time multi-modal features of the pre-processed real-time multi-modal data and perform feature fusion on the real-time multi-modal features to obtain the real-time multi-modal fusion features of the pre-processed real-time multi-modal data; The digital portrait generation model is used to generate a digital portrait based on the real-time multi-modal fusion features to obtain the real-time key multi-modal features and the corresponding real-time digital portrait; The conversion strategy generation model is used to generate a conversion strategy according to the real-time digital portrait and the real-time conversion requirement information, using the conversion strategy generation model of the digital data conversion engine to obtain the real-time conversion strategy; The digital data conversion model is used to perform digital data conversion according to the real-time key multi-modal features, the real-time digital portrait, and the real-time conversion strategy, using the digital data conversion model of the digital data conversion engine to obtain the real-time digital data; Build a digital data display platform, deploy a blockchain network, use artificial intelligence algorithms, construct a digital data conversion engine, and connect the digital data conversion engine to the digital data display platform, including the following steps: S1-1: On the software program platform, build a digital data display architecture, and build a multi-modal data upload module, a conversion requirement collection module, and a digital data visualization module to obtain a digital data display platform; S1-2: Distributively connect several data servers as data nodes, set up an InterPlanetary File System (IPFS) system and a smart contract to obtain a blockchain network, and connect the blockchain network to the digital data display platform; The blockchain network is used to distributively store the real-time digital data, improving the reliability and security of the real-time digital data storage; S1-3: The multi-modal data upload module based on the digital data display platform collects a number of historical multi-modal data and preprocesses the number of historical multi-modal data to obtain a number of preprocessed historical multi-modal data; S1-4: According to the number of preprocessed historical multi-modal data, use the multi-modal feature fusion and deep learning algorithm to construct a feature fusion extraction model and generate a number of historical multi-modal fusion features; The feature fusion extraction model is constructed based on the Feature Pyramid Networks (FPN)-Deep Belief Nets (DBN)-Long Short-Term Memory (LSTM)-Attention algorithm, and the feature fusion extraction model includes an image feature extraction module constructed based on the FPN algorithm, an audio feature extraction module constructed based on the DBN algorithm, a text feature extraction module constructed based on the LSTM algorithm, and a feature fusion module constructed based on the Attention mechanism. The feature fusion module is respectively connected to the image feature extraction module, the audio feature extraction module, and the text feature extraction module; The image feature extraction module combines the top-down path and the bottom-up path of the FPN algorithm to achieve image feature extraction at different scales, capturing multi-level and multi-scale information in the image, such as edges, textures, shapes, etc.; The audio feature extraction module uses the DBN algorithm to perform deep feature learning on audio data, extracts implicit features in the audio, such as frequency, rhythm, pitch, timbre, etc., realizes data dimensionality reduction and feature selection, reduces redundant information, and improves the efficiency of subsequent processing; The text feature extraction module can better understand the semantic information of the text through in-depth modeling of the text sequence by LSTM, improving the semantic expression ability of the text features; The feature fusion module uses the Attention mechanism to perform weighted fusion on the features from images, audio, and text, highlighting important information and suppressing irrelevant information; S1-5: According to the number of historical multi-modal fusion features, use the key feature screening and deep learning algorithm to construct a digital portrait generation model and generate a number of historical key multi-modal features and corresponding historical digital portraits; The digital portrait generation model is constructed based on the Random Forest (RF)-Elman algorithm, and the digital portrait generation model includes a key feature screening module constructed based on the RF algorithm and a digital portrait generation module constructed based on the Elman algorithm connected in sequence; The key feature screening module uses the Random Forest (RF) algorithm to evaluate and screen the importance of the fused multi-modal features, and identifies the most critical and representative feature subset for digital portrait generation from a large number of features; the digital portrait generation module uses the Elman algorithm to model and generate digital portraits for the screened key features, captures the temporal dependence relationships between features, generates coherent and consistent digital portraits, and realizes the efficient and accurate conversion from multi-modal data to digital portraits; S1-6: According to a number of historical digital portraits and a number of preset conversion requirement information, use the enhanced reinforcement learning algorithm to construct a conversion strategy generation model, and generate a number of historical conversion strategies and corresponding historical conversion strategy generation experiences; The conversion strategy generation model is constructed based on the Meta-Policy Optimization (MPO)-Multi-Objective Group Relative Policy Optimization (MOGRPO) algorithm, and the conversion strategy generation model includes a meta-policy optimization module constructed based on the MPO algorithm and a conversion strategy generation module constructed based on the MOGRPO algorithm. The conversion strategy generation module includes an objective function set, a policy network, an experience replay pool, and an agent. The agent is respectively connected to the objective function set and the policy network, and the meta-policy optimization module is connected to the policy network; The meta-policy optimization module is used to convert the network parameters of the policy network in the conversion strategy generation module, so that these parameters can quickly adapt to new and unseen digital portraits, improve the generalization ability of the model, and even under unseen digital portraits, the policy network can be updated based on previous learning experiences, improving the adaptability of the conversion strategy generation model; the objective function set of the conversion strategy generation module can handle multiple conflicting optimization goals, such as minimizing the digital data conversion time, minimizing the digital data conversion computation amount, maximizing the digital data conversion efficiency, etc., and generates conversion strategies that balance these goals. The agent learns historical conversion strategies through the experience replay pool, continuously optimizes its own strategy generation ability, and the agent controls the policy network according to the learned experiences to generate more effective conversion strategies. The design of the experience replay pool and the agent enables the model to continuously learn and optimize, improving the quality of strategy generation. Due to the use of the group exploration method, the conversion strategy generation module can avoid falling into local optimal solutions to a certain extent. The policy network outputs the distribution probability of actions in a given state, and the conversion strategy generation module directly updates the policy network through gradients, eliminating the Critic model in traditional reinforcement learning and making the algorithm structure more concise; According to a number of historical digital portraits and a number of preset conversion requirement information, use an enhanced reinforcement learning algorithm to construct a conversion strategy generation model, and generate a number of historical conversion strategies and corresponding historical conversion strategy generation experiences, including the following steps: S1-6-1: Use the MPO-MOGRPO algorithm to construct an initial conversion strategy generation model; the initial conversion strategy generation model includes an initial meta-policy optimization module and an initial conversion strategy generation module; S1-6-2: Take the optimization goal of digital data conversion as the scenario for meta-policy optimization, and train the initial meta-policy optimization module according to the analysis results of a number of historical data to obtain the final meta-policy optimization module; S1-6-3: Use the final meta-policy optimization module to initialize the policy network of the initial conversion strategy generation module in different scenarios to obtain an initialized policy network; S1-6-4: According to different scenarios of the meta-policy optimization module, that is, the optimization goal of digital data conversion, set a set of target functions for the initial conversion strategy generation module with the initialized policy network, set an experience replay pool, and set an action space and a state space for the agent of the initial conversion strategy generation module; S1-6-5: Take the conversion strategy generation problem as a simulation environment, and obtain an optimized conversion strategy generation module according to the initialized policy network and the agent with the action space and the state space set; S1-6-6: Traverse all the target functions in the set of target functions, and optimize and train the optimized conversion strategy generation module according to a number of historical digital portraits and a number of preset conversion requirement information to obtain the final conversion strategy generation module, and generate a number of historical conversion strategy generation experiences; S1-6-7: Integrate the final meta-policy optimization module and the final conversion strategy generation module to obtain the final conversion strategy generation model, and store a number of historical conversion strategy generation experiences in the experience replay pool; S1-7: According to a number of historical key multi-modal features, corresponding historical digital portraits, and historical conversion strategies, use a generative artificial intelligence algorithm to construct a digital data conversion model; The digital data conversion model is constructed based on the Multi-Layer Perceptron (MLP)-Artificial Intelligence Generated Content (AIGC) algorithm. The digital data conversion model includes a feature processing module constructed based on the MLP algorithm and a group of digital data conversion modules constructed based on the AIGC algorithm, which are connected in sequence. The group of digital data conversion modules includes a text generation module constructed based on the Transformer algorithm, an image generation module constructed based on the Generative Adversarial Networks (GAN), an audio generation module constructed based on the WaveNet algorithm, and a video generation module constructed based on the Vidio Generative Adversarial Networks (VGAN). The feature processing module is respectively connected to the text generation module, the image generation module, the audio generation module, and the video generation module; The AIGC algorithm refers to an algorithm that uses artificial intelligence technology to generate content. Such algorithms usually include natural language processing, deep learning, generative adversarial networks, variational autoencoders, etc., and are used to create text, images, audio, video, and other forms of generative digital data. The feature processing module processes the historical key multi-modal features and the features of the corresponding historical digital portraits to obtain the processed historical key multi-modal features and the processed historical digital portrait features. According to the historical conversion strategy, the corresponding text generation module, image generation module, audio generation module, and / or video generation module in the group of digital data conversion modules are scheduled, and digital data conversion is performed according to the processed historical key multi-modal features and the processed historical digital portrait features to obtain the corresponding historical digital data; S1-8: Integrate the feature fusion extraction model, the digital portrait generation model, the conversion strategy generation model, and the digital data conversion model to obtain a digital data conversion engine and connect it to the digital data display platform; S2: Based on the digital data display platform, collect real-time multi-modal data and use the digital data conversion engine to perform feature fusion extraction on the real-time multi-modal data to obtain real-time multi-modal fusion features, including the following steps: S2-1: Based on the digital data display platform, collect real-time multi-modal data and real-time conversion requirement information, and preprocess the real-time multi-modal data to obtain preprocessed real-time multi-modal data; Perform frame extraction processing on video data to obtain corresponding frame image data, perform denoising and enhancement processing on the frame image data and the original image data to obtain preprocessed real-time image data; perform format conversion and noise reduction processing on audio to obtain preprocessed real-time audio data; perform magnitude normalization and digitization processing on text data to obtain preprocessed real-time text data; improve data quality to provide data support for subsequent multi-modal feature fusion extraction; The preprocessed real-time multi-modal data includes preprocessed real-time image data, preprocessed real-time text data, and preprocessed real-time audio data; S2-2: Use the feature fusion extraction model of the digital data conversion engine to extract real-time multi-modal features of the preprocessed real-time multi-modal data, including the following steps: S2-2-1: Input the preprocessed real-time multi-modal data into the feature fusion extraction model of the digital data conversion engine; S2-2-2: Use the image feature extraction module of the feature fusion extraction model to extract real-time image features of the preprocessed real-time image data in the preprocessed real-time multi-modal data; S2-2-3: Use the audio feature extraction module of the feature fusion extraction model to extract real-time audio features of the preprocessed real-time audio data in the preprocessed real-time multi-modal data; S2-2-3: Use the text feature extraction module of the feature fusion extraction model to extract real-time text features of the preprocessed real-time text data in the preprocessed real-time multi-modal data; S2-2-3: Integrate real-time image features, real-time audio features, and real-time text features to obtain real-time multi-modal features; S2-3: According to the preset attention weight value, use the feature fusion module of the feature fusion extraction model to perform feature fusion on the real-time multi-modal features to obtain real-time multi-modal fusion features of the preprocessed real-time multi-modal data; S3: According to the real-time multi-modal fusion features, use the digital data conversion engine to perform digital data conversion to obtain real-time digital data, and use the digital data display platform to visualize the real-time digital data, including the following steps: S3-1: Use the digital portrait generation model of the digital data conversion engine to generate a digital portrait according to the real-time multi-modal fusion features to obtain real-time key multi-modal features and corresponding real-time digital portraits, including the following steps: S3-1-1: Input the real-time multi-modal fusion features into the digital portrait generation model of the digital data conversion engine; S3-1-2: Use the key feature screening module of the digital portrait generation model to screen the real-time key multi-modal features of the real-time multi-modal fusion features; Real-time key multimodal features include action preference features, behavior features, physical features, appearance features, scene features, etc. in real-time image features, intonation features, language features, speech rate features, timbre features, etc. in real-time audio features, and text habit features, text preference features, etc. in real-time text features; S3-1-3: According to the real-time key multimodal features, use the digital portrait generation module of the digital portrait generation model to generate a digital portrait and obtain a real-time digital portrait; The real-time digital portrait includes action preference labels, behavior labels, physical labels, appearance labels of a person, scene labels of a scene, etc., intonation labels, language labels, speech rate labels, timbre labels of audio, and text habit labels, text preference labels of text; The real-time digital portrait is used to describe and characterize the characteristics of digital data; S3-2: According to the real-time digital portrait and the real-time conversion requirement information, use the conversion strategy generation model of the digital data conversion engine to generate a conversion strategy and obtain a real-time conversion strategy, including the following steps: S3-2-1: According to the real-time digital portrait, use the meta-strategy optimization module of the conversion strategy model to update the policy network of the conversion strategy generation module and obtain an updated policy network; S3-2-2: Randomly extract several historical conversion strategy generation experiences from the experience replay pool. According to the several historical conversion strategy generation experiences, generate several possible conversion actions, and update the action space of the agent of the conversion strategy generation module to obtain an updated action space; S3-2-3: Parse the real-time digital portrait and the real-time conversion requirement information to obtain several real-time states, and according to the real-time states, update the state space of the agent of the conversion strategy generation module to obtain an updated state space; S3-2-4: Select a real-time objective function from the objective function set of the conversion strategy generation module, and based on the real-time objective function, use the agent to control the updated policy network to generate the probability distribution of all possible conversion actions in the updated action space corresponding to each real-time state in the updated state space; The possible conversion action with the highest probability distribution in the updated action space is used as the execution conversion action corresponding to the real-time state; S3-2-6: Integrate the execution conversion actions of all real-time states in the updated state space to obtain a real-time conversion strategy; The real-time conversion strategy includes real-time module call decisions of text generation modules, image generation modules, audio generation modules, and / or video generation modules in the digital data conversion module group, real-time digital data conversion decisions of each module, real-time digital data conversion content decisions, real-time digital data combination decisions, etc.; S3-3: According to the real-time key multi-modal features, real-time digital portraits, and real-time conversion strategies, use the digital data conversion model of the digital data conversion engine to perform digital data conversion to obtain real-time digital data, including the following steps: S3-3-1: Input the real-time key multi-modal features, real-time digital portraits, and real-time conversion strategies into the digital data conversion model of the digital data conversion engine; S3-3-2: According to the real-time module call decision of the real-time conversion strategy, call the text generation module, image generation module, audio generation module, and / or video generation module in the digital data conversion module group; S3-3-3: According to the real-time digital data conversion decision of the real-time conversion strategy, input the real-time key multi-modal features and real-time digital portraits into the text generation module, image generation module, audio generation module, and / or video generation module; S3-3-3: According to the real-time digital data conversion content decision of the real-time conversion strategy, use the text generation module, image generation module, audio generation module, and / or video generation module to generate corresponding several parts of real-time digital data based on the real-time key multi-modal features and real-time digital portraits; The several parts of real-time digital data include real-time generated text data generated by the text generation module, real-time generated image data of the image generation module, real-time generated audio data of the audio generation module, and / or real-time generated video data of the video generation module; S3-3-4: According to the real-time digital data combination decision of the real-time conversion strategy, combine several parts of real-time digital data to obtain real-time digital data; In the virtual avatar reconstruction application, digital data conversion is performed on multi-modal data such as the user's historical photos, audio and video, and text records to obtain the user's virtual avatar; in the digital memorial hall construction application, digital data conversion is performed on multi-modal data such as historical photos, audio and video, and text records of historical figures to construct a digital memorial hall of historical figures; in the cultural inheritance application, digital data conversion is performed on relevant multi-modal data of cultural heritage, such as cultural relic photos, historical audio, and documentary records, to reproduce the original appearance of cultural heritage; S3-4: Use the blockchain network to perform distributed storage of real-time digital data, and use the digital data display platform to visualize the real-time digital data, including the following steps: S3-4-1: Store the real-time digital data in the IPFS system of the blockchain network and return the corresponding real-time digital data hash value; S3-4-2: Call the smart contract of the blockchain network to generate real-time transaction data based on the real-time digital data hash value, timestamp, etc.; S3-4-3: Use several data nodes with distributed connections in the blockchain network to reach a consensus on real-time transaction data.

[0021] Embodiment 2: As Figure 2 shown, this embodiment provides an artificial intelligence-based digital data conversion system for implementing a digital data conversion method. The system includes a system initialization unit, a feature fusion extraction unit, and a digital data conversion unit that are connected in sequence. The system initialization unit is used to build a digital data display platform, deploy a blockchain network, use an artificial intelligence algorithm to construct a digital data conversion engine, and connect the digital data conversion engine to the digital data display platform. The feature fusion extraction unit is used to collect real-time multimodal data based on the digital data display platform, and use the digital data conversion engine to perform feature fusion extraction on the real-time multimodal data to obtain real-time multimodal fusion features. The digital data conversion unit is used to perform digital data conversion according to the real-time multimodal fusion features, using the digital data conversion engine, to obtain real-time digital data, and use the digital data display platform to visualize the real-time digital data.

[0022] An artificial intelligence-based digital data conversion method and system provided by the present invention can fully capture deep and subtle features by collecting real-time multimodal data (including images, audio, video, text, etc.) and performing feature fusion extraction using a digital data conversion engine, thereby comprehensively and accurately reproducing an individual's digital identity and avoiding the problem of information loss caused by single-modal data. By using an artificial intelligence algorithm to construct a digital data conversion engine, the efficiency of data processing is significantly improved, and large-scale multimodal data can be processed in a short time to meet real-time requirements, which is suitable for scenarios such as real-time interaction and dynamic display. By deploying a blockchain network, distributed storage of real-time digital data is achieved, enhancing the security of digital data, effectively preventing security threats such as data tampering and leakage, and protecting users' privacy information. Using a digital data display platform to visualize real-time digital data provides an intuitive and highly interactive display method, enabling users to clearly understand and operate digital data, and significantly improving the user experience. According to real-time multimodal fusion features and real-time conversion requirement information, a real-time conversion strategy is dynamically generated, and flexible digital data conversion is performed using a digital data conversion model to adapt to diverse application scenarios and requirements. It is not only applicable to scenarios such as virtual image reconstruction and digital memorial construction, but also can be widely applied to various fields such as cultural inheritance, education, and entertainment, meeting various interactive needs through realistic digital reproduction, and promoting the development and application of digital immortality technology.

[0023] The present invention is not limited to the above optional embodiments, and any person can obtain other various forms of products under the inspiration of the present invention. The above specific embodiments should not be construed as limiting the protection scope of the present invention, and the protection scope of the present invention should be defined by the claims, and the specification can be used to interpret the claims.

Claims

1. A digital data conversion method based on artificial intelligence, characterized in that: The steps include: Build a digital data display platform, deploy a blockchain network, use artificial intelligence algorithms, build a digital data conversion engine, and connect the digital data conversion engine to the digital data display platform; Based on the digital data display platform, real-time multimodal data is collected, and the digital data conversion engine is used to perform feature fusion extraction on the real-time multimodal data to obtain real-time multimodal fusion features; According to the real-time multimodal fusion characteristics, a digital data conversion engine is used to convert digital data to obtain real-time digital data, and a digital data display platform is used to visualize the real-time digital data.

2. The method for digital data conversion based on artificial intelligence according to claim 1, characterized in that: The digital data display platform is provided with a multimodal data uploading module, a conversion requirement collection module and a digital data visualization module; The digital data conversion engine is provided with a feature fusion extraction model, a digital image generation model, a conversion strategy generation model and a digital data conversion model.

3. The method for digital data conversion based on artificial intelligence according to claim 2, characterized in that: Building a digital data display platform, deploying a blockchain network, using artificial intelligence algorithms, building a digital data conversion engine, and connecting the digital data conversion engine to the digital data display platform includes the following steps: On the software program platform, a digital data display architecture is constructed, and a multimodal data upload module, a conversion requirement collection module, and a digital data visualization module are constructed to obtain a digital data display platform; Connect several data servers as data nodes in a distributed manner, set up the IPFS system and smart contracts, obtain a blockchain network, and connect the blockchain network to the digital data display platform; Based on the multimodal data uploading module of the digital data display platform, a number of historical multimodal data are collected, and the number of historical multimodal data are preprocessed to obtain a number of preprocessed historical multimodal data; Based on several pre-processed historical multimodal data, a feature fusion extraction model is constructed using multimodal feature fusion and deep learning algorithms, and several historical multimodal fusion features are generated; Based on several historical multimodal fusion features, a digital portrait generation model is constructed using key feature screening and deep learning algorithms, and several historical key multimodal features and corresponding historical digital portraits are generated; Based on several historical digital portraits and several preset conversion requirement information, an enhanced reinforcement learning algorithm is used to construct a conversion strategy generation model, and several historical conversion strategies and corresponding historical conversion strategy generation experiences are generated; Based on several key historical multimodal features, corresponding historical digital portraits, and historical conversion strategies, a digital data conversion model is constructed using generative artificial intelligence algorithms; The feature fusion extraction model, the digital portrait generation model, the conversion strategy generation model and the digital data conversion model are integrated to obtain a digital data conversion engine, which is then connected to a digital data display platform.

4. The method for digital data conversion based on artificial intelligence according to claim 3, characterized in that: The feature fusion extraction model is constructed based on the FPN-DBN-LSTM-Attention algorithm, and the feature fusion extraction model includes an image feature extraction module constructed based on the FPN algorithm, an audio feature extraction module constructed based on the DBN algorithm, a text feature extraction module constructed based on the LSTM algorithm, and a feature fusion module constructed based on the Attention mechanism. The feature fusion module is respectively connected to the image feature extraction module, the audio feature extraction module, and the text feature extraction module.

5. The method for digital data conversion based on artificial intelligence according to claim 4, characterized in that: The digital portrait generation model is constructed based on the RF-Elman algorithm, and the digital portrait generation model includes a key feature screening module constructed based on the RF algorithm and a digital portrait generation module constructed based on the Elman algorithm, which are connected in sequence.

6. The method for digital data conversion based on artificial intelligence according to claim 5, characterized in that: The conversion strategy generation model is constructed based on the MPO-MOGRPO algorithm, and the conversion strategy generation model includes a meta-strategy optimization module constructed based on the MPO algorithm and a conversion strategy generation module constructed based on the MOGRPO algorithm. The conversion strategy generation module includes an objective function set, a strategy network, an experience replay pool and an intelligent agent. The intelligent agent is connected to the objective function set and the strategy network respectively, and the meta-strategy optimization module is connected to the strategy network.

7. The method for digital data conversion based on artificial intelligence according to claim 6, characterized in that: The digital data conversion model is constructed based on the MLP-AIGC algorithm, and the digital data conversion model includes a feature processing module constructed based on the MLP algorithm and a digital data conversion module group constructed based on the AIGC algorithm, which are connected in sequence. The digital data conversion module group includes a text generation module constructed based on the Transformer algorithm, an image generation module constructed based on the GAN, an audio generation module constructed based on the WaveNet algorithm, and a video generation module constructed based on the VGAN. The feature processing module is respectively connected to the text generation module, the image generation module, the audio generation module, and the video generation module.

8. The method for digital data conversion based on artificial intelligence according to claim 7, characterized in that: Based on the digital data display platform, real-time multimodal data is collected, and the digital data conversion engine is used to perform feature fusion extraction on the real-time multimodal data to obtain real-time multimodal fusion features, including the following steps: Based on the digital data display platform, real-time multimodal data and real-time conversion requirement information are collected, and the real-time multimodal data is preprocessed to obtain preprocessed real-time multimodal data; Use the feature fusion extraction model of the digital data conversion engine to extract real-time multimodal features from pre-processed real-time multimodal data; The real-time multimodal features are fused to obtain the real-time multimodal fusion features of the preprocessed real-time multimodal data.

9. The method for digital data conversion based on artificial intelligence according to claim 8, characterized in that: According to the real-time multimodal fusion characteristics, a digital data conversion engine is used to convert digital data to obtain real-time digital data, and a digital data display platform is used to visualize the real-time digital data, including the following steps: The digital portrait generation model of the digital data conversion engine is used to generate digital portraits according to the real-time multimodal fusion features, and obtain the real-time key multimodal features and the corresponding real-time digital portraits; According to the real-time digital portrait and the real-time conversion requirement information, a conversion strategy generation model of the digital data conversion engine is used to generate a conversion strategy to obtain a real-time conversion strategy; According to the real-time key multimodal features, real-time digital portraits and real-time conversion strategies, the digital data conversion model of the digital data conversion engine is used to convert digital data to obtain real-time digital data; Use the blockchain network to distribute and store real-time digital data, and use the digital data display platform to visualize real-time digital data.

10. A digital data conversion system based on artificial intelligence, used to implement the digital data conversion method according to any one of claims 1 to 9, characterized in that: The system comprises a system initialization unit, a feature fusion extraction unit and a digital data conversion unit which are connected in sequence.

Images