Information pushing method based on AIGC

Abstract

The invention belongs to the technical field of information pushing, and discloses an information pushing method based on AIGC. The method comprises the following steps: constructing a knowledge graph generation model, a user portrait generation model, an information push content generation model and an information push strategy generation model; generating a knowledge graph by using a knowledge graph generation model according to the plurality of pieces of real-time knowledge data; according to the real-time user behavior data, user portrait generation and knowledge mapping are carried out by using a user portrait generation model; generating an information push strategy by using an information push strategy generation model according to the real-time user portrait after knowledge mapping; and according to the real-time information push strategy and the real-time user portrait after knowledge mapping, using an information push content generation model to generate information push content. According to the method and the device, the problems of insufficient individuation degree, single content generation, low pushing timeliness and poor user experience in the prior art are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of information push, and in particular relates to an information push method based on AIGC. Background Art

[0002] With the development of Internet technology, information push technology has ushered in an era of rapid development. The so-called information push technology is that information providers push information, data or content according to needs, according to certain rules and strategies, and send them to users on public platforms so that users can understand and access information. Especially in the protection and inheritance of intangible cultural heritage, it is necessary to actively push information and content related to intangible cultural heritage to users, realize the dissemination of intangible cultural heritage, and attract more users to pay attention to and protect intangible cultural heritage.

[0003] The existing information push technology has the following defects: (1) Insufficient personalization: Existing information push technologies often adopt fixed push strategies. This method cannot fully capture users’ dynamic interests and real-time behavior changes, resulting in a deviation between the pushed content and users’ actual needs. (2) Single content generation: The content generation in existing technologies mostly relies on templates or predefined rules. The generated information lacks diversity and innovation, and it is difficult to meet users' demand for high-quality, personalized content. (3) Push notifications are not timely: Existing push notifications rely on manual intervention, which is costly and lacks the ability to quickly adapt to environmental changes, resulting in low push notification timeliness. (4) Poor user experience: Since the push content does not match user needs, users often receive irrelevant or repetitive information, which affects the user experience and may lead to user dissatisfaction with the push service or even abandonment of its use. Summary of the invention

[0004] In order to solve the problems of insufficient personalization, single content generation, weak push timeliness and poor user experience in the prior art, the present invention aims to provide an information push method based on AIGC.

[0005] The technical solution adopted by the present invention is: An information push method based on AIGC includes the following steps: Use natural language processing algorithms to build a knowledge graph generation model, use AIGC algorithms to build user portrait generation models and information push content generation models, and use reinforcement learning algorithms to build information push strategy generation models; Collect some real-time knowledge data in the target field, and use the knowledge graph generation model to generate a knowledge graph based on the real-time knowledge data to obtain a real-time knowledge graph in the target field; Collect the real-time user behavior data of users on the public platform, use the user portrait generation model to generate user portraits based on the real-time user behavior data, obtain real-time user portraits, and use the real-time knowledge graph to perform knowledge mapping on the real-time user portraits of users to obtain real-time user portraits after knowledge mapping; According to the real-time user portrait after knowledge mapping, the information push strategy generation model is used to generate the information push strategy and obtain the real-time information push strategy; According to the real-time information push strategy and the real-time user portrait after knowledge mapping, the information push content generation model is used to generate information push content, obtain real-time information push content, and push the real-time information push content to the corresponding users on the public platform.

[0006] Furthermore, the user portrait generation model is constructed based on the RF-Attention-DBN algorithm, and the user portrait generation model includes a key feature extraction module constructed based on the RF algorithm, an attention weight module constructed based on the Attention mechanism, and a user portrait generation module constructed based on the DBN algorithm, which are connected in sequence.

[0007] Furthermore, the information push content generation model is constructed based on the MLP-AIGC algorithm, and the information push content generation model includes a feature processing module constructed based on the MLP algorithm and an information push content generation module group constructed based on the AIGC algorithm, which are connected in sequence.

[0008] Furthermore, the information push content generation module group includes a text generation module constructed based on the Transformer algorithm, an image generation module constructed based on GAN, an audio generation module constructed based on the WaveNet algorithm, and a video generation module constructed based on VGAN, and 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.

[0009] Furthermore, the information push strategy generation model is constructed based on the MPO-PPO algorithm, and the information push strategy generation model includes a meta-strategy optimization module constructed based on the MPO algorithm and a reinforcement learning module constructed based on the PPO algorithm. The reinforcement learning module is provided with an intelligent agent, a policy network and an experience replay pool. The intelligent agent is respectively connected to the policy network, the experience replay pool and the meta-strategy optimization module, and the meta-strategy optimization module is connected to the experience replay pool.

[0010] Furthermore, the knowledge graph generation model is constructed based on the BERT-Double CRF algorithm, and the knowledge graph generation model includes a text feature extraction module constructed based on the BERT algorithm, a named entity extraction module constructed based on the CRF algorithm, and an entity relationship extraction module constructed based on the CRF algorithm. The text feature extraction module is respectively connected to the named entity extraction module and the entity relationship extraction module.

[0011] Furthermore, a natural language processing algorithm is used to construct a knowledge graph generation model, an AIGC algorithm is used to construct a user portrait generation model and an information push content generation model, and a reinforcement learning algorithm is used to construct an information push strategy generation model, including the following steps: Collecting a number of historical knowledge data in a preset field, a number of multimodal content data sets, and a number of historical user behavior data of users, and preprocessing them to obtain a number of preprocessed historical knowledge data, a number of preprocessed multimodal content data sets, and a number of preprocessed historical user behavior data; Based on some pre-processed historical knowledge data, a natural language processing algorithm is used to build a knowledge graph generation model and generate historical knowledge graphs in several preset fields; Based on some pre-processed historical user behavior data, use the AIGC algorithm to build a user portrait generation model and generate some historical user portraits; According to several historical knowledge graphs, knowledge mapping is performed on several historical user portraits to obtain several historical user portraits after knowledge mapping; Based on the historical user portraits after knowledge mapping, a reinforcement learning algorithm is used to build an information push strategy generation model and generate several historical information push strategies; Based on several historical information push strategies, several multimodal content data sets, and several historical user portraits after knowledge mapping, the AIGC algorithm is used to build an information push content generation model.

[0012] Furthermore, according to the historical user portraits after several knowledge mappings, a reinforcement learning algorithm is used to build an information push strategy generation model, and generate several historical information push strategies, including the following steps: Analyze the historical user portraits after knowledge mapping to obtain several historical user portrait states, define the state space of the intelligent agent based on the several historical user portrait states, set several preset information push actions, and define the action space of the intelligent agent based on the several preset information push actions; According to the impact of the preset information push action on the historical user portrait status, the reward function is defined. Based on the state space, action space and reward function, the intelligent agent and policy network of the reinforcement learning module are constructed, and the experience replay mechanism is used to initialize the experience replay pool. The information push strategy generation problem is used as a simulation environment, and the PPO algorithm is used to build a policy network. The policy network, experience replay pool, and agent are combined to obtain the initial reinforcement learning module. The information push strategy generation tasks in several preset fields are set as several sub-scenarios of meta-strategy optimization, and the MPO algorithm is used to build the initial meta-strategy optimization module; According to the historical user portraits after several knowledge mappings, the initial reinforcement learning module is trained and optimized, and the historical policy network parameters of the policy network of the reinforcement learning module in the training optimization are extracted to obtain the final reinforcement learning module, and several historical information push strategies and corresponding historical reinforcement learning experiences are generated; Based on several sub-scenarios and several historical policy network parameters, the initial meta-policy optimization module is trained and optimized to obtain the final meta-policy optimization module, and several historical meta-policy optimization experiences are generated; Several historical meta-strategy optimization experiences and several historical reinforcement learning experiences are stored in the experience replay pool of the final reinforcement learning module, and the final meta-strategy optimization module and the final reinforcement learning module are integrated to obtain an information push strategy generation model.

[0013] Furthermore, according to several historical information push strategies, several multimodal content data sets and several historical user portraits after knowledge mapping, the AIGC algorithm is used to construct an information push content generation model, including the following steps: Using the AIGC algorithm, an initial information push content generation model is constructed; the initial information push content generation model includes an initial feature processing module, an initial text generation module, an initial image generation module, an initial audio generation module, and an initial video generation module; Performing data analysis on a plurality of multimodal content data sets in different preset fields to obtain a plurality of text content data, a plurality of image content data, a plurality of audio content data, and a plurality of video content data in different preset fields; According to a plurality of text content data, a plurality of image content data, a plurality of audio content data and a plurality of video content data, an initial text generation module, an initial image generation module, an initial audio generation module and an initial video generation module are optimized and trained to obtain an optimized text generation module, an optimized image generation module, an optimized audio generation module and an optimized video generation module; Extract the historical information push strategy features of the historical information push strategy and the knowledge-mapped historical user portrait features of the historical user portrait after knowledge mapping, optimize and train the initial feature processing module based on the historical information push strategy features and the knowledge-mapped historical user portrait features, obtain the final feature processing module, and generate a number of historical processed features; According to several historical processed features, the optimized text generation module, the optimized image generation module, the optimized audio generation module, and the optimized video generation module are debugged to obtain a final text generation module, a final image generation module, a final audio generation module, and a final video generation module; The final feature processing module, the final text generation module, the final image generation module, the final audio generation module and the final video generation module are integrated to obtain the final information push content generation model.

[0014] An information push system based on AIGC is used to implement an information push method. The system includes an AIGC model building unit, a knowledge graph generating unit, a user portrait generating unit, an information push strategy generating unit and an information push content generating unit which are connected in sequence.

[0015] The beneficial effects of the present invention are: The present invention provides an AIGC-based information push method, which constructs a dynamic user portrait and analyzes user behavior in real time through a user portrait generation model, can more accurately capture user interests and needs, realize highly personalized information push, and improve user satisfaction; the information push content generation model is used to automatically and intelligently generate information push content, and can generate rich, diverse and innovative push content, including multiple modalities such as text, image, audio and video, to meet user needs for high-quality content; the knowledge graph generation model is used to build a more complete knowledge graph, which can identify complex domain relationships and deep semantics, thereby improving the relevance and accuracy of the pushed content; the information push strategy generation model is used to generate information push strategies according to user habits, thereby avoiding manual intervention, reducing cost investment, and being able to quickly adapt to environmental changes to ensure the best match between push content and user needs; through precise content push, the push of irrelevant and repeated information is reduced, the user experience is significantly improved, and the user's trust and dependence on the push service is enhanced.

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

[0017] Figure 1 It is a flowchart of the information push method based on AIGC in the present invention.

[0018] Figure 2 It is a structural block diagram of the information push system based on AIGC in the present invention. DETAILED DESCRIPTION

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

[0020] Embodiment 1: like Figure 1 As shown, this embodiment provides an information push method based on AIGC, including the following steps: S1: Use the natural language processing algorithm to build a knowledge graph generation model, use the artificial intelligence generated content (AIGC) algorithm to build a user portrait generation model and an information push content generation model, and use the reinforcement learning algorithm to build an information push strategy generation model, including the following steps: S1-1: Collect some historical knowledge data in a preset field, some multimodal content data sets and some historical user behavior data of users, and perform preprocessing to obtain some preprocessed historical knowledge data, some preprocessed multimodal content data sets and some preprocessed historical user behavior data; This embodiment takes the protection and inheritance of intangible cultural heritage as the application scenario, uses the media, film and television, and new media public platforms as data sources, pushes information in different intangible cultural heritage fields, and pushes the generated intangible cultural heritage content to the user's social media, news client, video program and other public platform programs; social media platform: according to the user's interest preferences, push relevant intangible cultural heritage content generated using the AIGC model, such as intangible cultural heritage project introductions, inheritor stories, intangible cultural heritage activity information, etc.; news client: according to the user's reading habits, push relevant intangible cultural heritage news and information generated using the AIGC model; video program: according to the user's viewing preferences, push relevant intangible cultural heritage videos generated using the AIGC model, such as intangible cultural heritage skill demonstrations, intangible cultural heritage cultural documentaries, etc.; S1-2: Based on some pre-processed historical knowledge data, use natural language processing algorithm to build a knowledge graph generation model and generate historical knowledge graphs of several preset fields; The knowledge graph generation model is built based on the Bidirectional Encoder Representations from Transformers (BERT)-Double Conditional Random Fields (CRF) algorithm, and the knowledge graph generation model includes a text feature extraction module built based on the BERT algorithm, a named entity extraction module built based on the CRF algorithm, and an entity relationship extraction module built based on the CRF algorithm. The text feature extraction module is connected to the named entity extraction module and the entity relationship extraction module respectively; The BERT module can capture deep semantic information in knowledge data, which is very useful for identifying different types of entities and extracting relationships between entities. The CRF module can consider the dependencies between adjacent labels, which can help the model learn the sequence dependencies of entity labels, thereby improving the accuracy of named entity labeling. In the entity relationship labeling task, the CRF module handles the relationship classification between entity pairs, especially when dealing with multiple entities and relationships, to achieve entity relationship labeling. S1-3: Based on some pre-processed historical user behavior data, use the AIGC algorithm to build a user portrait generation model and generate some historical user portraits; The user portrait generation model is built based on the Random Forest (RF)-Attention-Deep Belief Network (DBN) algorithm, and the user portrait generation model includes a key feature extraction module built based on the RF algorithm, an attention weight module built based on the Attention mechanism, and a user portrait generation module built based on the DBN algorithm, which are connected in sequence; The key feature extraction module uses the internal Classification And Regression Tree (CART) to screen the key features of the input user behavior data and extract several key features related to the user portrait label, including platform type, access frequency, access time, attention terms, comment method, etc. The attention weight module uses the preset attention weights to achieve weighted fusion of several key features, enhance the influence of attention features on label prediction, and improve the accuracy of label prediction. The user portrait generation module generates labels based on the fused features, pre-trains the network in an unsupervised way, and then performs supervised fine-tuning, which helps to improve the accuracy of label prediction. S1-4: Based on several historical knowledge graphs, knowledge mapping is performed on several historical user portraits to obtain several historical user portraits after knowledge mapping; S1-5: Based on the historical user portraits after knowledge mapping, use the reinforcement learning algorithm to build an information push strategy generation model and generate several historical information push strategies; The information push strategy generation model is constructed based on the Meta-Policy Optimization (MPO)-Proximal Policy Optimization (PPO) algorithm, and the information push strategy generation model includes a meta-policy optimization module constructed based on the MPO algorithm and a reinforcement learning module constructed based on the PPO algorithm. The reinforcement learning module is provided with an intelligent agent, a policy network, and an experience replay pool. The intelligent agent is connected to the policy network, the experience replay pool, and the meta-policy optimization module respectively, and the meta-policy optimization module is connected to the experience replay pool. The meta-strategy optimization module can quickly adapt to the ever-changing information push environment, initialize the policy network based on historical experience, and use the knowledge learned from other tasks when dealing with new or unseen tasks to improve the generalization ability of the reinforcement learning module, reducing the need to start training from scratch on new tasks, saving computing resources and time; the PPO algorithm of the reinforcement learning module improves the stability of learning and reduces the risk of policy collapse by limiting the policy update range. By using the experience replay pool, data samples can be reused to improve sample utilization and learning efficiency. Through continuous iterative updates, the policy network can learn better information push strategies. The experience replay pool is used to store meta-strategy optimization experience and reinforcement learning experience. Reinforcement learning experience includes state, action, reward and next state. Meta-strategy optimization experience includes network parameters of the policy network in the reinforcement learning module and the corresponding policy adjustment category. Based on the historical user portraits after several knowledge mappings, a reinforcement learning algorithm is used to build an information push strategy generation model and generate several historical information push strategies, including the following steps: S1-5-1: Analyze the historical user portrait after knowledge mapping to obtain several historical user portrait states, define the state space of the intelligent agent according to the several historical user portrait states, set several preset information push actions, and define the action space of the intelligent agent according to the several preset information push actions; S1-5-2: Based on the impact of the preset information push action on the historical user portrait status, define the reward function, build the agent and policy network of the reinforcement learning module based on the state space, action space and reward function, and use the experience replay mechanism to initialize the experience replay pool; the reward function is a key component in reinforcement learning, which guides the agent to learn how to select actions from the state space to obtain the maximum long-term reward, thereby optimizing the push strategy; S1-5-3: Using the information push strategy generation problem as a simulation environment, the PPO algorithm is used to construct a policy network, and the initial reinforcement learning module is obtained by combining the policy network, the experience replay pool, and the agent; S1-5-4: Set the information push strategy generation tasks in several preset fields as several sub-scenarios of meta-strategy optimization, and use the MPO algorithm to build the initial meta-strategy optimization module; S1-5-5: Based on the historical user portraits after several knowledge mappings, the initial reinforcement learning module is trained and optimized, and the historical policy network parameters of the policy network of the reinforcement learning module in the training optimization are extracted to obtain the final reinforcement learning module, and several historical information push strategies and corresponding historical reinforcement learning experiences are generated; through training, the policy network can learn a better information push strategy, thereby improving the relevance and effect of the push; S1-5-6: Based on several sub-scenarios and several historical policy network parameters, the initial meta-policy optimization module is trained and optimized to obtain the final meta-policy optimization module, and several historical meta-policy optimization experiences are generated; S1-5-7: Store several historical meta-strategy optimization experiences and several historical reinforcement learning experiences in the experience replay pool of the final reinforcement learning module, and integrate the final meta-strategy optimization module and the final reinforcement learning module to obtain the information push strategy generation model; storing experience allows the model to continue to benefit from past learning, and the integration of modules ensures the consistency and collaboration of the entire system, thereby generating a more effective push strategy; S1-6: Based on several historical information push strategies, several multimodal content data sets, and several historical user portraits after knowledge mapping, use the AIGC algorithm to build an information push content generation model; The information push content generation model is constructed based on a multi-layer perceptron (MLP)-AIGC algorithm, and the information push content generation model includes a feature processing module constructed based on the MLP algorithm and an information push content generation module group constructed based on the AIGC algorithm; The information push content generation module group includes a text generation module based on the Transformer algorithm, an image generation module based on the Generative Adversarial Networks (GAN), an audio generation module based on the WaveNet algorithm, and a video generation module based on the Video Generative Adversarial Networks (VGAN). The feature processing module is connected to the text generation module, the image generation module, the audio generation module, and the video generation module respectively. 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 and other technologies, which are used to create text, images, audio, video and other forms of data or media content; the feature processing module processes the information push strategy features and the user portrait features after knowledge mapping to obtain processed features, which include the push time selection action features, content customization action features, content type selection action features, etc. of the information push strategy. The user portrait features include user features, such as interest tag features, behavior pattern features, knowledge preference features, etc., and are feature vectors of fixed length to ensure that the feature vectors can be used by subsequent content generation modules; Based on several historical information push strategies, several multimodal content data sets, and several historical user portraits after knowledge mapping, the AIGC algorithm is used to build an information push content generation model, including the following steps: S1-6-1: Use the AIGC algorithm to build an initial information push content generation model; the initial information push content generation model includes an initial feature processing module, an initial text generation module, an initial image generation module, an initial audio generation module, and an initial video generation module; use the AIGC algorithm to build an initial model that includes a feature processing module and multiple content generation modules (text, image, audio, video), and this model will be used to generate multimodal content; S1-6-2: Data analysis is performed on a number of multimodal content data sets in different preset fields to obtain a number of text content data, a number of image content data, a number of audio content data, and a number of video content data in different preset fields; data analysis ensures that the model can receive high-quality, structured input data, which is crucial for training an efficient content generation model; S1-6-3: According to a number of text content data, a number of image content data, a number of audio content data and a number of video content data, the corresponding initial text generation module, the initial image generation module, the initial audio generation module and the initial video generation module are optimized and trained to obtain an optimized text generation module, an optimized image generation module, an optimized audio generation module and an optimized video generation module; the optimization training improves the accuracy and diversity of each module when generating corresponding content, so that the generated content is more in line with the characteristics of the intangible cultural heritage field and user preferences; S1-6-4: extract the historical information push strategy features of the historical information push strategy and the knowledge-mapped historical user portrait features of the historical user portrait, optimize and train the initial feature processing module based on several historical information push strategy features and several knowledge-mapped historical user portrait features, obtain the final feature processing module, and generate several historical processed features; optimizing the feature processing module helps to better convert the user portrait and push strategy into a form that can be understood by the content generation module, thereby improving the relevance and personalization of content generation; S1-6-5: Debugging the optimized text generation module, the optimized image generation module, the optimized audio generation module, and the optimized video generation module according to several historical processed features to obtain the final text generation module, the final image generation module, the final audio generation module, and the final video generation module; the debugging ensures that the content generation module can generate high-quality content according to the optimized features, thereby improving the attractiveness of the pushed content and user satisfaction; S1-6-6: Integrate the final feature processing module, the final text generation module, the final image generation module, the final audio generation module, and the final video generation module to obtain the final information push content generation model; the integrated model can work together to generate multi-modal content according to user portraits and push strategies, thereby improving the efficiency and effectiveness of the entire push system; S2: Collect some real-time knowledge data in the target field, and use the knowledge graph generation model to generate a knowledge graph based on the real-time knowledge data to obtain a real-time knowledge graph in the target field, including the following steps: S2-1: Collect some real-time knowledge data in the target field and perform preprocessing to obtain some preprocessed real-time knowledge data; collect the latest knowledge data from the target field, such as news, research reports, social media posts, etc., and then perform preprocessing operations such as data cleaning, deduplication, and formatting to ensure the quality and consistency of the data. The preprocessed data is more suitable for subsequent knowledge graph generation, reducing the impact of noise and erroneous data, and improving the accuracy and reliability of the knowledge graph; S2-2: Use the knowledge graph generation model to extract named entities and entity relationships from some pre-processed real-time knowledge data to obtain some knowledge named entities and some knowledge entity relationships. Extracting named entities and entity relationships is a key step in building a knowledge graph, which provides a structured data foundation for the knowledge graph, so that the knowledge graph can accurately reflect the relationship between entities. S2-3: Based on several knowledge named entities and several knowledge entity relationships, a knowledge graph is constructed to obtain a real-time knowledge graph of the target domain; the knowledge graph represents knowledge in a graphical way, which is easy to understand and analyze, and integrates scattered knowledge points into an organic whole to provide support for subsequent knowledge mapping; S3: Collect the real-time user behavior data of users on the public platform, use the user portrait generation model to generate user portraits based on the real-time user behavior data, obtain real-time user portraits, and use the real-time knowledge graph to perform knowledge mapping on the real-time user portraits of users to obtain real-time user portraits after knowledge mapping, including the following steps: S3-1: Collect real-time user behavior data on public platforms and perform preprocessing to obtain preprocessed real-time user behavior data; collect real-time user behavior data from public platforms (such as social media, news websites, forums, etc.), and then perform preprocessing operations such as data cleaning, denoising, and normalization; S3-2: Use the user portrait generation model to extract several real-time key features of the pre-processed real-time user behavior data, perform feature fusion on several real-time key features according to the preset attention weight value, obtain real-time fusion features, and generate user portraits based on the real-time fusion features to obtain real-time user portraits; by focusing on key features, the model can more accurately capture the user's personalized information, and the real-time user portrait can reflect the user's latest behavior and interest changes, thereby improving the accuracy and timeliness of information push; S3-3: Obtain several real-time user portrait tags of the real-time user portrait, and obtain the similarity between each real-time user portrait tag and several knowledge named entities in the real-time knowledge graph; extract tags from the real-time user portrait, and calculate the similarity between these tags and the knowledge named entities in the real-time knowledge graph to find the association between the user's interests and the knowledge entities. Similarity matching helps to connect the user's interests with the professional knowledge in the field of intangible cultural heritage, and provide more relevant content for the user; S3-4: Map the knowledge named entities of the real-time knowledge graph to the real-time user portrait tags with the highest similarity, and associate the corresponding knowledge entity relationships to the real-time user portrait tags with the highest similarity, to obtain the real-time user portrait after knowledge mapping; through knowledge mapping, the user portrait contains richer knowledge information, which helps to understand user needs more deeply. The mapped user portrait can better guide the information push strategy, ensure that the push content is highly relevant to the user's interests and knowledge background, provide a more accurate basis for personalized information push, and improve the accuracy of push and user satisfaction; S4: Based on the real-time user portrait after knowledge mapping, the information push strategy generation model is used to generate the information push strategy to obtain the real-time information push strategy, including the following steps: S4-1: According to the target domain, the corresponding target historical meta-strategy optimization experience is extracted from several historical meta-strategy optimization experiences of different sub-scenarios in the experience playback pool of the information push strategy generation model, and the real-time policy network parameters of the policy network of the reinforcement learning module are initialized using the meta-strategy optimization module according to the target historical meta-strategy optimization experience to obtain an updated policy network; by reusing historical experience, the training process of the policy network can be accelerated, and the historical experience for a specific domain can improve the domain adaptability of the policy network; S4-2: Randomly extract a number of historical reinforcement learning experiences from the experience replay pool, and push actions according to the preset information of the historical reinforcement learning experiences to update the action space of the agent and obtain an updated action space; through the diversity of historical experiences, the action space is richer and can cover more possible push strategies. The update of the action space enables the agent to better adapt to different user needs and scenarios; S4-3: Analyze the real-time user portrait after knowledge mapping to obtain several real-time user portrait states, and update the state space of the agent according to the several real-time user portrait states to obtain an updated state space; the update of the state space enables the agent to formulate a push strategy according to the personalized characteristics of the user, and a more accurate state representation helps to generate a more effective push strategy; S4-4: Connect the updated state space to the input end of the updated policy network, connect the updated action space to the output end of the updated policy network, use the agent to control the updated policy network, and generate a probability distribution of all possible information push actions in the updated action space corresponding to each real-time user profile state in the updated state space; S4-5: taking the possible information push action with the highest probability distribution in the updated action space as the execution information push action of the real-time user portrait state, traversing all the real-time user portrait states in the updated state space, obtaining a number of execution information push actions, and obtaining a real-time information push strategy based on the number of execution information push actions; Information push strategies include: Content selection action: select a specific type of content related to the user's interests or historical behavior (such as specific content in the field of intangible cultural heritage, etc.); Content customization actions: Customize content style, language or format according to user preferences; personalize the difficulty or depth of content; Push timing action: determine the best time to push, such as when the user is active or when a specific event occurs; adjust the push frequency based on the user's lifestyle habits; Push channel action: push content on different platforms based on user habits; S5: Based on the real-time information push strategy and the real-time user portrait after knowledge mapping, use the information push content generation model to generate information push content, obtain real-time information push content, and push the real-time information push content to the corresponding user on the public platform, including the following steps: S5-1: Extract the real-time information push strategy features of the real-time information push strategy and the real-time user portrait features after knowledge mapping of the real-time user portrait; extract key features from the real-time information push strategy, such as push time selection action features, content customization action features, content type selection action features, etc., and extract user features from the real-time user portrait after knowledge mapping, such as interest tag features, behavior pattern features, knowledge preference features, etc.; S5-2: Use the information push content generation model to process the real-time information push strategy features and the real-time user portrait features after knowledge mapping to obtain real-time processed features; feature processing improves the generalization ability of the model, enabling it to better adapt to different push scenarios and provide more precise guidance for content generation; S5-3: Generate information push content based on the real-time processed features to obtain real-time information push content, such as text, images, videos, etc., and push the real-time information push content to corresponding users on the public platform according to the real-time information push strategy.

[0021] Embodiment 2: like Figure 2 As shown, this embodiment provides an information push system based on AIGC, which is used to implement an information push method. The system includes an AIGC model building unit, a knowledge graph generating unit, a user portrait generating unit, an information push strategy generating unit, and an information push content generating unit connected in sequence; The AIGC model building unit is used to build a knowledge graph generation model using a natural language processing algorithm, to build a user portrait generation model and an information push content generation model using an AIGC algorithm, and to build an information push strategy generation model using a reinforcement learning algorithm; A knowledge graph generation unit is used to collect a number of real-time knowledge data in a target field, and generate a knowledge graph using a knowledge graph generation model based on the real-time knowledge data to obtain a real-time knowledge graph in the target field; A user portrait generation unit is used to collect real-time user behavior data of users on the public platform, generate user portraits based on the real-time user behavior data using a user portrait generation model to obtain a real-time user portrait, and use a real-time knowledge graph to perform knowledge mapping on the real-time user portrait of the user to obtain a real-time user portrait after knowledge mapping; An information push strategy generation unit is used to generate an information push strategy based on the real-time user portrait after knowledge mapping and use the information push strategy generation model to obtain a real-time information push strategy; The information push content generation unit is used to generate information push content according to the real-time information push strategy and the real-time user portrait after knowledge mapping, use the information push content generation model, obtain the real-time information push content, and push the real-time information push content to the corresponding users on the public platform.

[0022] The present invention provides an AIGC-based information push method, which constructs a dynamic user portrait and analyzes user behavior in real time through a user portrait generation model, can more accurately capture user interests and needs, realize highly personalized information push, and improve user satisfaction; the information push content generation model is used to automatically and intelligently generate information push content, and can generate rich, diverse and innovative push content, including multiple modalities such as text, image, audio and video, to meet user needs for high-quality content; the knowledge graph generation model is used to build a more complete knowledge graph, which can identify complex domain relationships and deep semantics, thereby improving the relevance and accuracy of the pushed content; the information push strategy generation model is used to generate information push strategies according to user habits, thereby avoiding manual intervention, reducing cost investment, and being able to quickly adapt to environmental changes to ensure the best match between push content and user needs; through precise content push, the push of irrelevant and repeated information is reduced, the user experience is significantly improved, and the user's trust and dependence on the push service is enhanced.

[0023] The present invention is not limited to the above optional implementations, and anyone can derive other various forms of products under the enlightenment of the present invention. The above specific implementations should not be understood as limiting the scope of protection of the present invention. The scope of protection of the present invention should be based on the definition in the claims, and the description can be used to interpret the claims.

Claims

1. An information push method based on AIGC, characterized in that: The steps include: Use natural language processing algorithms to build a knowledge graph generation model, use AIGC algorithms to build user portrait generation models and information push content generation models, and use reinforcement learning algorithms to build information push strategy generation models; Collect some real-time knowledge data in the target field, and use the knowledge graph generation model to generate a knowledge graph based on the real-time knowledge data to obtain a real-time knowledge graph in the target field; Collect the real-time user behavior data of users on the public platform, use the user portrait generation model to generate user portraits based on the real-time user behavior data, obtain real-time user portraits, and use the real-time knowledge graph to perform knowledge mapping on the real-time user portraits of users to obtain real-time user portraits after knowledge mapping; According to the real-time user portrait after knowledge mapping, the information push strategy generation model is used to generate the information push strategy and obtain the real-time information push strategy; According to the real-time information push strategy and the real-time user portrait after knowledge mapping, the information push content generation model is used to generate information push content, obtain real-time information push content, and push the real-time information push content to the corresponding users on the public platform.

2. The information push method based on AIGC according to claim 1, characterized in that: The user portrait generation model is constructed based on the RF-Attention-DBN algorithm, and the user portrait generation model includes a key feature extraction module constructed based on the RF algorithm, an attention weight module constructed based on the Attention mechanism, and a user portrait generation module constructed based on the DBN algorithm, which are connected in sequence.

3. The information push method based on AIGC according to claim 2, characterized in that: The information push content generation model is constructed based on the MLP-AIGC algorithm, and the information push content generation model includes a feature processing module constructed based on the MLP algorithm and an information push content generation module group constructed based on the AIGC algorithm, which are connected in sequence.

4. The information push method based on AIGC according to claim 3, characterized in that: The information push content generation 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.

5. The information push method based on AIGC according to claim 4, characterized in that: The information push strategy generation model is constructed based on the MPO-PPO algorithm, and the information push strategy generation model includes a meta-strategy optimization module constructed based on the MPO algorithm and a reinforcement learning module constructed based on the PPO algorithm. The reinforcement learning module is provided with an intelligent agent, a policy network and an experience replay pool. The intelligent agent is respectively connected to the policy network, the experience replay pool and the meta-strategy optimization module, and the meta-strategy optimization module is connected to the experience replay pool.

6. The information push method based on AIGC according to claim 5, characterized in that: The knowledge graph generation model is constructed based on the BERT-Double CRF algorithm, and the knowledge graph generation model includes a text feature extraction module constructed based on the BERT algorithm, a named entity extraction module constructed based on the CRF algorithm, and an entity relationship extraction module constructed based on the CRF algorithm. The text feature extraction module is respectively connected to the named entity extraction module and the entity relationship extraction module.

7. The information push method based on AIGC according to claim 6, characterized in that: Use the natural language processing algorithm to build a knowledge graph generation model, use the AIGC algorithm to build a user portrait generation model and an information push content generation model, and use the reinforcement learning algorithm to build an information push strategy generation model, including the following steps: Collecting a number of historical knowledge data in a preset field, a number of multimodal content data sets, and a number of historical user behavior data of users, and preprocessing them to obtain a number of preprocessed historical knowledge data, a number of preprocessed multimodal content data sets, and a number of preprocessed historical user behavior data; Based on some pre-processed historical knowledge data, a natural language processing algorithm is used to build a knowledge graph generation model and generate historical knowledge graphs in several preset fields; Based on some pre-processed historical user behavior data, use the AIGC algorithm to build a user portrait generation model and generate some historical user portraits; According to several historical knowledge graphs, knowledge mapping is performed on several historical user portraits to obtain several historical user portraits after knowledge mapping; Based on the historical user portraits after knowledge mapping, a reinforcement learning algorithm is used to build an information push strategy generation model and generate several historical information push strategies; Based on several historical information push strategies, several multimodal content data sets, and several historical user portraits after knowledge mapping, the AIGC algorithm is used to build an information push content generation model.

8. The information push method based on AIGC according to claim 7, characterized in that: Based on the historical user portraits after several knowledge mappings, a reinforcement learning algorithm is used to build an information push strategy generation model and generate several historical information push strategies, including the following steps: Analyze the historical user portraits after knowledge mapping to obtain several historical user portrait states, define the state space of the intelligent agent based on the several historical user portrait states, set several preset information push actions, and define the action space of the intelligent agent based on the several preset information push actions; According to the impact of the preset information push action on the historical user portrait status, the reward function is defined. Based on the state space, action space and reward function, the intelligent agent and policy network of the reinforcement learning module are constructed, and the experience replay mechanism is used to initialize the experience replay pool. The information push strategy generation problem is used as a simulation environment, and the PPO algorithm is used to build a policy network. The policy network, experience replay pool, and agent are combined to obtain the initial reinforcement learning module. The information push strategy generation tasks in several preset fields are set as several sub-scenarios of meta-strategy optimization, and the MPO algorithm is used to build the initial meta-strategy optimization module; According to the historical user portraits after several knowledge mappings, the initial reinforcement learning module is trained and optimized, and the historical policy network parameters of the policy network of the reinforcement learning module in the training optimization are extracted to obtain the final reinforcement learning module, and several historical information push strategies and corresponding historical reinforcement learning experiences are generated; Based on several sub-scenarios and several historical policy network parameters, the initial meta-policy optimization module is trained and optimized to obtain the final meta-policy optimization module, and several historical meta-policy optimization experiences are generated; Several historical meta-strategy optimization experiences and several historical reinforcement learning experiences are stored in the experience replay pool of the final reinforcement learning module, and the final meta-strategy optimization module and the final reinforcement learning module are integrated to obtain an information push strategy generation model.

9. The information push method based on AIGC according to claim 8, characterized in that: Based on several historical information push strategies, several multimodal content data sets, and several historical user portraits after knowledge mapping, the AIGC algorithm is used to build an information push content generation model, including the following steps: Using the AIGC algorithm, construct an initial information push content generation model; the initial information push content generation model includes an initial feature processing module, an initial text generation module, an initial image generation module, an initial audio generation module and an initial video generation module; Performing data analysis on a plurality of multimodal content data sets in different preset fields to obtain a plurality of text content data, a plurality of image content data, a plurality of audio content data, and a plurality of video content data in different preset fields; According to a plurality of text content data, a plurality of image content data, a plurality of audio content data and a plurality of video content data, an initial text generation module, an initial image generation module, an initial audio generation module and an initial video generation module are optimized and trained to obtain an optimized text generation module, an optimized image generation module, an optimized audio generation module and an optimized video generation module; Extract the historical information push strategy features of the historical information push strategy and the knowledge-mapped historical user portrait features of the historical user portrait after knowledge mapping, optimize and train the initial feature processing module based on the historical information push strategy features and the knowledge-mapped historical user portrait features, obtain the final feature processing module, and generate a number of historical processed features; According to several historical processed features, the optimized text generation module, the optimized image generation module, the optimized audio generation module, and the optimized video generation module are debugged to obtain a final text generation module, a final image generation module, a final audio generation module, and a final video generation module; The final feature processing module, the final text generation module, the final image generation module, the final audio generation module and the final video generation module are integrated to obtain the final information push content generation model.

Images