107 results about "Social graph" patented technology

The invention relates to the technical field of social network information propagation prediction, in particular to an event propagation prediction method based on group influence. The method comprises the following steps: constructing a social network graph of target event participating users, calculating an activation probability matrix among the users by using historical propagation data, and performing social graph structure enhancement based on a threshold value to obtain a de-noised social graph; applying a graph neural network on the de-noised social graph and introducing information bottleneck constrained self-supervised contrast learning optimization node embedding, and reserving features useful for group division and propagation prediction; dynamically dividing user groups related to propagation according to the similarity and propagation context of de-noising node embedding to form a group-level propagation sequence; based on the group representation, utilizing an attention mechanism and a group relation graph to carry out modeling on propagation influence among the groups to obtain global group representation of the event; global group representation is combined with candidate user embedding, propagation probability distribution is calculated, and future participating users of corresponding events are predicted.

The invention relates to an interaction method and device based on virtual reality, equipment and a medium. According to the method, firstly, state data of a user in a virtual reality environment is collected and preprocessed to generate a standardized data stream, and then the distance, orientation similarity and interaction frequency between the user and a virtual avatar are calculated based on the data so as to construct a situational social graph representing social relation strength. Meanwhile, an attention model representing attention weight is constructed by analyzing a fixation point and a head direction of a virtual avatar of the user, and then information priority is calculated through weighted summation of social relation strength and the attention weight by utilizing a situational social graph and the attention model; according to the method and the device, the priority of the user is obtained, the audio, visual and text information is dynamically filtered or enhanced according to the priority to generate the optimized information flow, and finally the information flow is presented in the virtual reality environment, so that the cognitive load of the user in a dense social scene is effectively reduced, and the social interaction efficiency and immersion are improved.

The invention relates to a node representation learning method fusing diffusion hypergraph modeling and a graph convolutional network, and belongs to the technical field of modeling and prediction of a complex diffusion process. The method comprises the following steps: extracting a static node structure representation of a social graph, and obtaining a social context feature representation of the static node structure representation; constructing a diffusion hypergraph according to the propagation diffusion sequence, and dividing the diffusion hypergraph into a plurality of sub diffusion hypergraphs; performing feature extraction and fusion on each sub-diffusion hypergraph to obtain user information features; obtaining time sequence feature information embedding based on the improved LSTM network and the user information features; and performing cross-dimension splicing on the social context feature representation and the time sequence feature information to obtain a splicing fusion feature, obtaining a propagation probability based on the splicing fusion feature, and completing model performance evaluation based on the propagation probability. The objective of the invention is to solve the technical problems that time sequence information is not deeply learned and global information is not integrated in the prior art.

The application discloses a social network relationship prediction method based on a multi-curvature hyperbolic graph neural network, and belongs to the technical field of social networks, and comprises the following steps: constructing a social network graph; constructing a category prediction network comprising a random deletion layer, a multi-curvature hyperbolic space mapping layer, an improved hyperbolic graph convolutional neural network, a dynamic curvature fusion layer and a classifier; training the category prediction network to obtain a category prediction model; obtaining a social network graph to be identified, and obtaining a corresponding fusion feature matrix Zr through the category prediction model; processing Zr into a binary matrix, and determining an edge relationship according to element values in the binary matrix. The application introduces a multi-curvature learning mechanism, so that the model is more flexible and more accurate in matching the real geometric characteristics of substructures in the social network graph, a scaling aggregation factor is introduced during hyperbolic graph neural network feature extraction to adjust the contribution of neighbors, so as to adjust node features, maintain the hierarchical relationship during multi-layer feature extraction, and finally improve the accuracy of relationship prediction.

This invention discloses a social denoising recommendation method based on edge confidence invariant learning, belonging to the recommender system field within machine learning. The invention constructs an edge confidence estimation mechanism that integrates preference similarity and structural priors, and based on this, performs soft pruning and confidence-weighted propagation on the social graph to suppress noise diffusion from low-quality social edges at the source. Addressing social structural perturbations and noise distribution changes, the invention introduces a multi-environment generation mechanism, constructing multiple differentiated social environments under the guidance of edge confidence priors, and learning stable and effective preference signals through cross-environment invariance constraints, thereby reducing the model's dependence on environment-specific spurious correlations. Simultaneously, the invention designs a cross-domain gating fusion mechanism to selectively forget and enhance social representations, and combines cross-domain alignment constraints to alleviate semantic shifts between the social and recommendation domains, improving the controllability of social information injection.

There is provided a computer implemented method of dynamic generation of audio content of a panel including questions asked by a moderator and responses by responders, comprising: accessing user interest(s) of a target user, accessing a social network graph that includes the target user, selecting questions correlated with the user interest(s) of the target user, selecting responses to questions by responders, wherein the responders are linked to the target user in the social network graph, wherein the responders are associated with user interests correlated with the user interest(s) of the target user, dynamically assembling audio content(s) from voice records and / or from audio recordings generating by converting text to voice, each audio content including a sub-set of the selected questions and a sub-set of the responses, and providing dynamically assembled audio content(s) for selection thereof for playing on a speaker.

The present application provides a method for querying a high-connectivity shortest influence path between users, a device, and a product. The method includes: constructing an indexed linked list data structure based on an obtained social network graph; determining, based on the indexed linked list data structure, a start node, a target node, and a path connectivity in a current iteration, whether there is a shortest influence path satisfying the path connectivity in the current iteration; if yes, updating a minimum path connectivity in a previous iteration and determining the path connectivity in the current iteration based on the minimum path connectivity; or if no, determining the path connectivity in the current iteration as a maximum path connectivity in the previous iteration; and continuing the iteration based on the maximum path connectivity and the minimum path connectivity until a high-connectivity shortest influence path is determined.

The invention discloses a fine-grained privacy information propagation control strategy generation method and device, and belongs to the technical field of privacy control, and the method comprises the steps: obtaining an intimacy heterogeneous graph according to a social graph and a diffusion graph between users; updating the node embedding representation of the user node according to the graph neural network and the intimacy heterogeneous graph to obtain an updated node embedding representation; obtaining an initial user activation probability matrix according to the updated node embedding representation; obtaining a privacy disclosure score and a propagation scale according to the initial user activation probability matrix; constructing an optimization problem according to the privacy disclosure score and the propagation scale; and solving the optimization problem to obtain an optimal solution set, and taking a user in the optimal solution set as a node for next hop forwarding. According to the method, the accuracy of information diffusion prediction is higher and is closer to actual data, the static and rigid problems in the prior art are solved, a privacy control scheme with higher quality and more comprehensive selection is provided for the user, and the real optimal balance of effectiveness is realized.

A video recommendation method fusing social information comprises the steps that firstly, a user-video interaction graph and a social graph are constructed through video media platform data, different combination strategies of a diffusion model and graph convolution operation are applied in a denoising priority path and a structure priority path respectively, and collaborative perception and fusion of user embedding and structure information are achieved; secondly, aligning user embedding output by the double-track denoising path by adopting comparative learning, and enhancing robustness; secondly, performing deep coding on the user-video interaction graph and the social graph by applying a double-graph neural network, comprehensively capturing user preferences and embedding videos; and finally, for noise possibly introduced by multi-module fusion, deep denoising is executed to purify user embedding again. According to the method, guidance of structural information is introduced in the diffusion denoising process, and more robust user embedding is obtained by using a comparative learning strategy, so that a structural perception high-fidelity social denoising task is completed, and personalized video recommendation is realized on a video media platform.

This application relates to the field of relational network analysis in artificial intelligence, specifically to a user differentiation method, apparatus, device, and medium based on content and network features, comprising: acquiring a social network graph; acquiring node features of each node based on the social network graph; inputting the node features into a Markov random field model to obtain a first classification result of the node; extracting content features from the content information; inputting the content features into a trained content classification model to obtain a second classification result of the content features; and determining the user type of the node based on the first classification result and the second classification result. This application combines the different characteristics of content features and network features, utilizing more comprehensive user information to detect whether users on social network platforms are spam accounts, making it less likely for malicious users to bypass the detection.

The invention provides a credit card risk control method, device, medium and system, and the method comprises the steps: constructing and updating a multi-dimensional user portrait, the multi-dimensional user portrait comprises a risk type of a credit card holder determined on the basis of real-time transaction flow data, multi-source credit investigation data, behavior biological characteristic data and social graph data under the condition of user authorization; generating a risk user management list according to the risk type; and under the condition that the repayment event is detected, adjusting the credit line of the card holder of the credit card according to the information in the risk user management list. The problem that risk intervention of the credit card depends on manual judgment in the prior art, so that the risk control effect is difficult to meet the expectation is solved.

This invention discloses a method and apparatus for predicting the popularity of short videos based on learnable graph augmentation, belonging to the field of artificial intelligence technology. The method includes: collecting keyframe sets, text data sets, and behavioral data sets from short videos; constructing a graph edge to obtain a heterogeneous social graph; inputting this graph into a heterogeneous attribute graph neural network; extracting content features from the target video; performing odd-hop propagation and even-hop propagation; employing feature fusion operations and learnable sparse masks; and inputting this into a trained popularity prediction model to obtain the predicted future popularity of the target video. This invention, by integrating learnable graph augmentation and social propagation relationship modeling, can effectively utilize unlabeled data even when labeled samples are insufficient, enhancing the model's robustness and generalization ability, thereby more accurately predicting the popularity of short videos.

The application discloses a red envelope flow control method and system based on a social platform, and relates to the technical field of computers.The application dynamically divides user levels based on a social graph, so that high-value users in a star fan group can obtain priority access rights, the requests of core fans can still be stably reached in a flow peak, and the risk of loss of high-value users is reduced.Rigid concurrent control is converted into dynamic probability decision-making, the passing rate under a node overload scenario is automatically inhibited through a load-sensitive function, and global lock competition caused by atomic operation is avoided.A random decision mechanism disperses request peak pressure, maintains millisecond-level response capability, and guarantees the stability of the system under the condition of instantaneous concurrent access of ten thousand people.Meanwhile, a delay retry channel associated with a social level is enabled for limited requests, buffer opportunities are provided for core propagators, a timeout compensation strategy is combined, negative emotions of users caused by direct rejection are reduced, the integrity of a red envelope fission path is maintained, and positive circulation of social propagation is strengthened.

The application provides a kind of key user identification method and system in social network, it is related to user identification technical field, comprising: according to social network data, construct social network graph model;Through graph theory algorithm, calculate basic centrality index;Social network data is divided into multiple communities, and the local role of user node in multiple communities is identified;Calculate the local centrality index of local role;Global score and local score are generated;Global score and local score are ranked respectively, and key user node is screened out.The application solves the problem of insufficient identification of cross-community bridge nodes and local core users in traditional methods by fusing two-dimensional analysis of global centrality index and local role features, significantly improves the comprehensiveness and accuracy of key user identification;Through the double check of time sequence feature analysis and rule engine verification, the abnormal state of disguised as high-influence user is effectively identified, and the result reliability is significantly improved.

The application discloses a social recommendation method and device based on hyperbolic space contrast learning, and the method comprises the following steps: step S1, mapping the nodes of a user-item interaction graph and a social network graph into a hyperbolic space, and reconstructing the user-item interaction graph to obtain a reconstructed graph; step S2, combining the user-item interaction graph, the social network graph and the reconstructed graph, and performing hyperbolic graph learning by using a graph neural network to obtain preliminary fusion embedding of each node; step S3, based on the preliminary fusion embedding, performing social information conversion fusion for each user to obtain personalized fusion embedding; step S4, taking the hyperbolic distance between the user and the item as a prediction score to construct a hyperbolic space model, setting a contrast learning strategy of positive sample weighting and negative sample screening, and setting a contrast learning loss of social awareness and interaction awareness; and using the hyperbolic space model to score the correlation between the user and the item. The application is significantly improved in recommendation effect.

The application discloses a kind of federal social recommendation method and device based on adaptive diffusion denoising, belong to personalized recommendation technical field in electronic commerce and social platform. For the problem of serious noise interference, server load is too high and slow response in existing social federal recommendation, the application constructs interaction graph and social graph by collecting user interaction and social data, initializes user and project embedding representation, carries out adaptive diffusion denoising process in client local, wherein noise scheduling is dynamically adjusted according to user social structure characteristics, and through federal training framework, client local model updating and server global parameter aggregation are realized, finally, denoised social embedding and user interaction embedding are fused to carry out recommendation score prediction and list generation. The application effectively suppresses social noise interference, improves recommendation accuracy and robustness, reduces server load and communication overhead, and is suitable for personalized recommendation service of electronic commerce and social platform.

This disclosure relates to the field of computer technology and discloses a method, apparatus, computer device, and storage medium for identifying associated communities. The method includes: acquiring each node in a social network and the atomic relationships between them; for any target node among the nodes, determining the graph embedding information corresponding to the target node based on the atomic relationships; constructing a social graph between the target node and all other nodes according to the graph embedding information; and identifying the target associated community from the social graph based on the node relationships in the social graph. By implementing the technical solution of this disclosure, multi-path information between nodes can be considered, facilitating better capture of complex relationships and features between nodes, and fully utilizing the graph data structure information of the social graph to achieve the identification of associated communities.

The invention discloses a differentiated privacy protection method and system based on social propagation force perception, and the method comprises the following steps: S1, constructing a social graph, and carrying out the preprocessing and community division of the graph, and obtaining community tags; s2, calculating the propagation degree, the influence and the propagation weight of the node based on the community label; s3, grouping the nodes according to the comprehensive risk score, and presetting an initial differential privacy parameter for each group; s4, based on a grouping result, adaptively adjusting the noise intensity of each group through a water level type strategy, and carrying out differential training; and S5, after training is completed, constructing a strong black box node member to infer attacks, calculating node-level attack advantages and spreading weighted privacy risks, and evaluating and visualizing a privacy protection effect. Under the same global privacy budget, the effective noise variance needing to be superposed is lower than that of an independent Gaussian noise scheme, so that the model training stability can still be maintained in a strong privacy scene.

The invention discloses a shortest path searching method and a social network relation analysis method, and belongs to the technical field of network information, the social network relation analysis method comprises the steps that a knowledge graph of a social network is constructed, vertexes in the knowledge graph comprise users or entities, and edges in the knowledge graph represent the interaction relation between the vertexes; calculating a shortest path from the source point to the target point based on a shortest path searching method; wherein the source point and the target point belong to a vertex set of the knowledge graph; and obtaining a relation analysis result of the source point and the target point according to the interaction relation on the shortest path from the source point to the target point. According to the method, large-scale social network graph data with a complex structure can be efficiently and stably processed.

The invention provides a malicious user identification method and system giving consideration to privacy protection in a social network, and relates to the technical field of network privacy security, and the method comprises the steps: carrying out the structure perception sub-graph segmentation of a social network graph through an METIS algorithm, dividing an original graph into a plurality of sub-graphs, minimizing the number of edges crossing the sub-graphs, and keeping the scale balance of the sub-graphs; constructing a privacy perception GNN of an integrated gating residual attention module, wherein the privacy perception GNN comprises a privacy perception linear layer and a gating residual mechanism; based on differential privacy stochastic gradient descent framework training, combining an adaptive noise scheduling strategy, dynamically adjusting the noise scale according to privacy consumption deviation, and performing closed-loop control budget to obtain a trained model; and malicious users are identified through the trained model. According to the method, the problem of performance reduction caused by fixed noise injection and noise amplification is solved, and efficient and robust identification of malicious users is realized while differential privacy constraints are met.

Profile Information is aggregated from online websites and services to correlate discovered identities to one another via computational analysis of Intra-Personal Relationships, Inter-Personal Relationships, and Profile Data. The information, relationships and content of identities which have been determined to share Intra-Personal relationships are aggregated into Meta-Profiles; the Meta-Profiles are used in place of component Intra-Related identities to optimize computer functions such as social graph operations, content customization, and audience operations (including: analysis, metrics, profiling and targeting). The system processes identities and relationships belonging to individuals registered with the system and those belonging to unregistered users. The system is provided with data from users, via third-party systems, or through automated discovery. These innovations solve problems of online identity disambiguation specific to internet computing, and improve computer operations by optimizing memory footprint and operation calls to minimize the number of nodes and edges traversed.

The invention discloses a feed delivery line self-adaptive accurate feeding method, and belongs to the technical field of feeding, and the method comprises the steps: collecting chickens and chicken flocks to obtain multi-modal data and chicken behavior data; constructing a social network graph of the chicken flocks according to the chicken behavior data to obtain individual indexes of each chicken, obtaining fusion data based on the multi-modal data, the chicken behavior data and the individual indexes, inputting the fusion data into a multi-modal time sequence prediction model to obtain growth trend prediction data of each chicken, and predicting the growth trend of each chicken according to the growth trend prediction data. A composite feeding strategy is obtained based on the growth trend prediction data and the feed consumption, and the feed conveying line unit is regulated and controlled to conduct feeding according to the composite feeding strategy. According to the method, the dynamic nutritional requirements of chicken flocks in different growth stages, different environment temperatures and different health states can be met, the individual difference between different chickens is met by predicting the growth of each chicken, the laying rate of the chickens is increased, and the feeding amount of feed can be adaptively adjusted according to a composite feeding strategy.

The invention relates to the technical field of network security, in particular to a heterogeneous social graph detection method and system fusing neighborhood perception and adaptive gating, a heterogeneous social graph is constructed, nodes represent users, and edges represent various social relations among the users; coding the node features to generate a low-dimensional dense initial feature vector; the multi-layer neighborhood perception graph neural network NANNN takes R-GCN as a backbone network to carry out node representation learning, explicitly models heterogeneity of different types of social relations, and introduces an adaptive gating module into each layer of the R-GCN; and based on the final node representation, predicting the probability that the node belongs to a robot or a human through a classifier, and optimizing all model parameters through end-to-end training. According to the method, through a triple perception adaptive gating aggregation mechanism, the remarkable effects of higher precision, lower parameter quantity and higher data efficiency are achieved in a social robot detection task.

A system and method for zero-knowledge social graph management with session-revealed identities is disclosed. The system is configured for receiving registration requests comprising user communication addresses. The system is further configured to generate cryptographic hashes of communication addresses without storing plaintext addresses. The system is further configured to generate asymmetric key pairs with private keys stored exclusively on user devices. The system is further configured to generate encrypted identity packets containing personally identifiable information encrypted with recipient public keys and transmit connection requests after verifying target existence through hash comparison. The system is further configured to enable recipient-controlled decryption revealing requester identities only when recipients review requests. The system is further configured to generate real-time social connection hashes from communication address hashes and compare them with stored hashes to verify connections without identity exposure, providing zero-knowledge proof of connection.

This invention relates to a method and apparatus for social network anonymization based on multi-agent reinforcement learning. The method includes: S1: Constructing a reinforcement learning environment and initial state; acquiring the social network graph data to be processed, modeling the anonymization task as a Markov decision process, and establishing the state representation and reward feedback mechanism of the environment; S2: Executing dual-agent collaborative decision-making; constructing a structural perturbation agent and a feature confusion agent, with the structural perturbation agent deciding on edge-connecting actions at nodes, and subsequently, the feature confusion agent deciding on feature modification actions at nodes based on structural perturbation information; S3: Constructing a joint parameter optimization objective based on a proximal policy optimization algorithm; evaluating the value of the global state using a centralized value network, and calculating the advantage function of the dual agents in conjunction with immediate rewards; constructing the policy loss and value loss of the dual agents; S4: Executing an iterative training process to optimize network parameters; collecting the interaction trajectories between the dual agents and the environment, and synchronously updating the parameters of the policy network and value network according to the joint parameter optimization objective; S5: Obtaining the social network anonymization results and evaluating the model utility; using the trained policy network to perform deterministic perturbations on the input test set graph data, outputting the anonymized graph data results, and calculating the anonymization success rate.

The invention provides a socialized recommendation method and system based on an independent cascade model, and relates to the technical field of social networks. The method comprises the following steps: firstly, acquiring a user set and an item set, and constructing a user-item interaction graph and a user-user social graph; performing independent cascade enhancement on the social graph; respectively inputting the enhanced social graph and the interaction graph into two LightGCN networks to obtain social characterization and interaction characterization of the user and interaction characterization of the project, further calculating a prediction score for expressing the degree of interest of the user on the non-interacted project, calculating the loss of the recommendation task, and obtaining the recommendation result of the recommendation task. Calculating the loss of the contrast learning task based on the hierarchical influence and the representation matching, and further calculating the total loss; and finally, by taking the user as a unit, calculating a prediction score of each user for non-interacted items, then sorting according to a descending order of the prediction scores, and selecting the first K items to be recommended to the user. According to the method, more accurate and more personalized recommendation can be provided for the user.

The invention discloses a marketing effect analysis method and system based on deep learning, and relates to the technical field of marketing analysis, and the method comprises the steps: defining time, collecting user sets, collecting comment texts, marketing actions and external environment feature data, generating word vectors based on the comment texts, and carrying out emotion semantic feature extraction by using a CNN-LSTM model; defining an observation vector for the user based on the emotion semantic features, the marketing actions and the external environment features, defining and initializing a potential state, and constructing an increment updating equation based on the observation vector; constructing a social graph according to the relationship between the users, calculating a companion influence vector of each user by using an attention mechanism, and correcting an increment updating equation by using the companion influence vector to obtain a final potential state updating formula so as to update the potential states of the users; and deep description of user behavior dynamics and marketing strategy effects is realized.

The invention belongs to the field of human factor engineering and human-computer interaction, and provides a pilot load modeling method, system and device based on a cognitive network and a medium, and the method comprises the steps: constructing a human-computer interaction sequential network model; calculating and correcting the cognitive demand of each task according to the time overlapping condition; aggregating cognitive demands of tasks with the same operator node, the same system resource node and the same interaction direction in the sequential network model, constructing an incidence matrix, and generating a cognitive social network graph for visualizing operator cognitive workload distribution based on the incidence matrix; the change of the distributed cognitive workload is identified by comparing cognitive social network graphs, and optimization suggestions are proposed according to the result. According to the method, the problem that the distributed cognitive workload cannot be quantized, visualized and compared and analyzed in the prior art can be solved, and scientific and intuitive decision support is provided for optimization design of man-machine function distribution.

The application discloses a kind of fusion social network graph and hypergraph information recommendation system matrix filling method, comprising the following steps: S1, using generative model modeling generation social network graph information and hypergraph information;S2, the generation and input of incomplete recommendation matrix;S3, through three-stage algorithm, using social network hypergraph information and incomplete matrix information are carried out matrix filling, output the recommendation matrix after completion, and then complete recommendation task;S4, collect user feedback information, optimize recommendation algorithm: according to the feedback of user, improve social network information and then optimize recommendation algorithm.Compared with prior art, the present application uses mixed graph and more complex hypergraph for modeling, can better make full use of complex social network data, on this basis, through three-stage algorithm, using social network hypergraph information auxiliary matrix filling, can carry out more accurate matrix reply, and then enable recommendation system to realize more efficient recommendation.

The invention discloses a network water army identification method based on user influence. The method comprises the following steps: step 1, collecting full-dimensional data of social media users; 2, text analysis and directed social graph construction: performing word segmentation and stop word removal on the text content of the full-dimensional data, obtaining sentiment polarity through sentiment analysis, and extracting semantic features; constructing a directed social graph based on the attention relationship between the users; 3, defining a comprehensive influence score of the user, wherein the score is formed by weighting and fusing three sub-dimensions of propagation influence, structure influence and time stability; 4, calculating an influence-activeness ratio and an influence mutation index based on the comprehensive influence score and activeness, and performing water army risk classification on the user in combination with the multi-dimensional feature vector; and step 5, result output and feedback optimization: generating a high-risk water army list, and continuously optimizing a judgment threshold and a feature weight through manual auditing and feeding back a closed loop so as to realize self-adaptive evolution of the recognition capability.