34 results about "Social information" patented technology

Disclosed in the present application are a social information pushing method, a related apparatus, a device and a storage medium. The method of the present application comprises: in response to a payment transaction request, acquiring a consumption feature vector corresponding to a target user account, the payment transaction request carrying the target user account and device location information; on the basis of the device location information and the consumption feature vector corresponding to the target user account, determining M user accounts; on the basis of the device location information, determining N pieces of recommended location information; and pushing social information to at least two terminals, the at least two terminals comprising a target terminal and at least one terminal, the target terminal having logged into the target user account, each of the at least one terminal having logged into one of the M user accounts, and the social information comprising the N pieces of recommended location information. The present application reduces the social cost of users and can also improve the accuracy of social matching.

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.

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 invention relates to the field of artificial intelligence technology and discloses a multi-agent social network simulation method and system based on a cognitive reasoning chain. The method includes: initializing a multi-agent system comprising a social environment engine, a user profile engine, and a cognitive reasoning engine; executing a multi-agent social network simulation loop with a preset number of iterations; in each iteration, the social environment engine pushes social information to the agents as external stimuli and activates the agents to make independent decisions; updating the cognitive states of each dimension in the cognitive reasoning chain and generating corresponding social behaviors through reasoning using a large-scale language model; recording the social behaviors and their corresponding cognitive state trajectories; periodically analyzing historical records to optimize the influence coefficients between the cognitive dimensions of the cognitive reasoning chain; and adjusting the reasoning strategy of the preset large-scale language model. This makes the simulation of the agent's cognitive process a transparent and traceable evolutionary process, achieving a complete and understandable simulation of the "observation-cognition-behavior" cycle.

The invention belongs to the technical field of recommendation systems, and particularly relates to a recommendation method based on two-channel fusion of graph convolution and hypergraph convolution. According to the method, a two-channel architecture of graph convolution and hypergraph convolution is constructed and is respectively used for capturing explicit interaction information between users and merchants and high-order social information between the users, so that noise interference caused by hyperedge redundancy is effectively relieved; a gating attention fusion mechanism is designed, dynamic aggregation of double-channel embedding is achieved by means of a learnable weight distribution strategy, and recommendation accuracy and personalized expression ability are improved; merchant static features are introduced, category labels, geographical location information and the like are used as semantic vectors to improve recommendation performance, hyperedge noise propagation can be inhibited by means of an information bottleneck principle, and recommendation accuracy is improved.

Embodiments of the present application disclose a motion trajectory generation method and device, electronic equipment and storage medium. Applied to the field of automated testing. Including: obtaining historical motion trajectory data of at least one reference vehicle and a target vehicle. Using a trajectory generation model to determine a social information vector corresponding to the target vehicle according to the historical motion trajectory data of all reference vehicles. Using the trajectory generation model to determine a first historical trajectory feature vector corresponding to the target vehicle according to the historical motion trajectory data of the target vehicle. Using the trajectory generation model to generate a motion planning trajectory of the target vehicle according to the social information vector corresponding to the target vehicle and the trajectory feature vector corresponding to the target vehicle. Embodiments of the present application can quickly generate motion trajectories of multiple traffic participants using a trajectory generation model. In this way, multiple traffic participants can be added to the test scene to increase the complexity of the test scene.

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 invention discloses an Internet of Vehicles trust management method and system based on block chain and social information driving. According to the method, node credibility data are stored in a decentralized mode through a block chain, an intelligent contract is deployed to automatically execute trust evaluation, and network loads are reduced through edge nodes; quantifying social relations such as node ownership and friendship to generate a reference list, dynamically updating a direct trust value, calculating an inter-cluster relative trust value, weighting and calculating an indirect trust value in combination with the reference list, and fusing the three types of trust values to identify malicious nodes; the system comprises a block chain storage module, a smart contract module, an edge node module and the like, and stores data through an MPT structure; the implementation verification shows that the malicious node detection success rate is greatly improved, singing attenuation and DDoS attacks can be resisted, the storage and calculation overhead is reduced, and the security and robustness of Internet of Vehicles trust management are improved.

The application provides a kind of interest social relation recommendation method, device, system and storage medium, belong to social recommendation technical field, method includes: import user ID data, original project interaction data and original social data;User ID data and original project interaction data are vectorized to obtain initial user node vector and original project interaction vector;Original project interaction vector and original social data are cleaned to obtain interest social data;Training model is constructed, and training model is analyzed by initial user node vector, original project interaction vector and original interest social data to obtain social relation recommendation model.The application can dynamically filter and remove meaningless social in interest social space, effectively filter social information that can interfere or mislead user, improve the calculation efficiency of recommendation algorithm, also can improve the accuracy of recommendation, has great practical value in recommendation method, greatly meets the needs of user.

This application discloses a method, system, server, medium, device, and program for generating social information in multiplayer games. The method includes: constructing a user's player profile based on the user's player information; when the spatial distance between a first character and a second character in the game scene is less than or equal to the social detection distance, determining similar characteristics between the first user and the second user based on the first user's player profile and the second user's player profile, wherein the first character is the character controlled by the first user and the second character is the character controlled by the second user; generating first social information based on the first character's character information and similar characteristics, and / or generating second social information based on the second character's character information and similar characteristics, wherein the first social information is suitable for being sent to the second user in response to the first user's social interaction operation, and the second social information is suitable for being sent to the first user in response to the second user's social interaction operation.

The invention discloses a vehicle-mounted equipment control method based on multiple agents, and belongs to the technical field of intelligent control. According to the method, identity information of a target user using a vehicle is obtained, user real-time information of the target user is collected, the user real-time information comprises operation information, physiological information and social contact information, a corresponding user database is determined according to the identity information, and the user database is used for storing the vehicle information. And screening a target data set in the user database according to the social information and the physiological information, determining equipment control data according to the operation information, the target data set and a large language model, and controlling the vehicle-mounted equipment according to the equipment control data, thereby achieving the beneficial effect of improving the intelligent degree of the vehicle-mounted equipment.

The embodiment of the invention provides an animal social analysis method and device, electronic equipment and a medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: extracting a global video frame sequence from a real-time multi-view video of an animal group; performing real-time group behavior recognition, individual behavior recognition and animal posture recognition on the global video frame sequence, and performing social contact pointing analysis on the animal group according to group social contact behavior categories, single animal behavior categories and target animal posture data obtained through real-time recognition to obtain group social contact pointing data; and according to the group social behavior category, the single animal behavior category and the group social pointing data, social information integration is carried out to obtain target animal social data. According to the embodiment of the invention, the social directivity analysis is carried out according to the group social behavior category, the single animal behavior category and the target animal posture data, so that the social directivity of the animal group social behavior can be accurately judged in real time, and the efficiency and precision of animal social analysis are improved.

The invention relates to an interaction method and device based on promotion content, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps that a social information flow interface of a first account is displayed, the social information flow interface comprises social content sent by a second account having a social relationship with the first account and promotion content sent through a target promotion account, and a virtual article in a first state is displayed in a display area of the promotion content; in response to an interaction operation on the virtual item in the first state, displaying a sharing interface about the virtual item, and displaying a virtual item in a second state in the sharing interface; and in response to a sharing operation on the virtual item in the sharing interface, sharing the virtual item. In this way, the interaction experience is improved.

Embodiments of the present application disclose a social information issuing method and device. A specific embodiment of the method comprises: receiving a social information obtaining request sent by a first user, determining a second user to which the social information obtaining request is directed; obtaining social information uploaded by the second user, wherein the social information at least comprises locked social information; in response to the target social information requested in the social information obtaining request being the locked social information, forwarding the social information obtaining request to the second user; and in response to receiving an authorization permission returned by the second user for the social information obtaining request, sending the target social information to the first user. The embodiment can provide the user with social information published and allowed to be viewed by other users based on the request of the user, protect the privacy of the publisher of the social information, avoid providing the user with too much social information with low value, and improve the quality of the obtained social information.

The invention discloses a vehicle social contact assisting method and device, and the method comprises the steps: determining a target vehicle which is in near-field connection with a vehicle in a target range when the vehicle is in a weak network connection state, and receiving the social contact information sent by the target vehicle; obtaining driving information of the vehicle; and according to the driving information, push display processing of the social information by the vehicle is determined. Thus, even if the vehicle is in the weak network connection state, the vehicle can still stably obtain the social information, and service continuity is guaranteed. Through a driving safety strategy, social information display opportunity and an interaction mode are reasonably controlled, distraction of a driver is avoided, and driving safety and social demands are balanced.

The application discloses a social label prediction method and system for heterogeneous social network distribution external generalization. The application comprises the following steps: 1) constructing social network data into a heterogeneous social network graph; 2) performing initial clustering division on the heterogeneous social network graph; 3) inputting the clustered heterogeneous social network graph into an adaptive neighborhood propagation module based on a graph neural network, and performing one round of parameter optimization on the adaptive neighborhood propagation module under the supervision of existing social information labels in the graph; 4) using the adaptive neighborhood propagation module after a new round of parameter optimization to extract graph feature information of the heterogeneous social network graph again, and then performing clustering cluster division again using the updated graph feature information; 5) repeating iteration to complete the training of the adaptive neighborhood propagation module and use the adaptive neighborhood propagation module for prediction. The application has strong robustness and accuracy for the heterogeneous social network data outside the training set distribution, and can accurately predict user labels.

The invention provides a data processing method and device based on an online conference, equipment and a storage medium. The method comprises the following steps: acquiring conference participation data of a target user who enters an online conference, and acquiring social information between the target user and other users; the conference participation data represents multi-modal data displayed by the user on the conference, and other users represent users except the target user in the online conference; determining credibility information between the target user and other users according to the social information between the target user and other users; the credibility information represents the social contact condition between the two users; according to the credibility information between the target user and other users, performing encryption processing on the conference participation data of the target user, and outputting the encrypted conference participation data to a server; and the server side is used for distributing the encrypted participating data to other users. According to the method provided by the invention, the protection of the online conference on the personal information of the target user is improved, and the security is improved.

The invention provides a social information publishing method and device, a social information display method and device, electronic equipment, a storage medium and a computer program product. The method comprises the following steps: displaying multiple pieces of social information published by a target account in history, wherein the social information carries a publishing position; in response to the information fusion instruction, target social information obtained by fusing the multiple pieces of social information is displayed, the target social information comprises an action track of the target account, the action track comprises a release position of each piece of social information, and in response to the information release instruction, the target social information comprising the action track is released. According to the invention, the diversity of the social information published by the user can be improved, and the richness of social interaction can be improved.

The application discloses a social prompt cold start recommendation method based on an SPGCLRec framework, and comprises the following steps: step one, constructing an interaction graph and pre-training a recommendation model; step two, optimizing a social prompt based on a diffusion model; step three, enhancing a cold start user representation; and step four, generating a cold start recommendation and jointly optimizing a model. The learnable social soft prompt designed by the application embeds social information into a representation space of a pre-training model, and can realize efficient parameter adaptation without fine-tuning core weights of the model, thereby making up for the deficiency of the prior art which only relies on a single auxiliary clue and realizing efficient parameter adaptation of the pre-training model. The diffusion model is used to filter noise social relationships in a latent vector space, thereby improving user representation accuracy. By introducing a contrast learning mechanism and introducing Gaussian noise in a latent space, the semantic consistency of the optimized social prompt and the item representation is strengthened, and the robustness of the user representation is improved.

The application discloses a kind of graph neural network micro map recommendation method considering social information, comprising: first, the social connection between user, the interaction between user and project and the relationship between project are constructed as a collaborative heterogeneous graph containing multiple types of relationships;Then, through memory enhancement and information aggregation module to refine and strengthen these relationship data, so that the characteristics of each user and project are more distinctive and distinguished, and the embedding features are extracted by multi-layer neural network and attention mechanism;Further, using embedding features to decouple specific types of information, and decoupled information propagation;Finally, by activation function, layer normalization, residual connection, connection operation etc., integrate all information, use contrast learning to further optimize and refine these features, to generate personalized micro map recommendation result.

The invention relates to the technical field of artificial intelligence and the field of financial services, in particular to a product recommendation method and device, equipment and a medium. The client basic information of the target client is acquired, the target client is portrayed, the initial client portrait is matched with the preset product library, the matched product is sent to the target client, the target client is portrayed again, and the product in the second matching result is sent to the target user as the recommended product. The method can be applied to an insurance product recommendation service scene, the target customer is determined to obtain the basic information to construct the initial customer portrait, the initial customer portrait is matched with the preset product library to obtain the first matching result, the authorization verification information is sent, the customer obtains the social information after the customer allows authorization, and the basic information is combined to obtain the optimized customer portrait. And recommending the product in the result to the client. Therefore, the customer portrait is comprehensively optimized according to the information of the target customer, and the recommended product is accurately matched.

The application discloses a kind of interactive network generation methods based on user and user behavior, first is with social interaction behavior connection weight e i→j =[l,c,r] as the directed connection edge between users, a social graph FIG=(V,e j→i ) based on social user attributes and interaction behavior is constructed;Then considering the actual problem that it is difficult to obtain the privacy attribute information of each user in user set USER and it is difficult to obtain sufficient data in the early propagation process of hot event, each user is mapped from the interaction space FIG=(V,e j→i ) to latent variable space FIG_BH using graph variational autoencoder, the attribute information of user is enhanced using user behavior information containing likes, comments and forwards, and the smoothness of social information features is improved by the method of enhancing the correlation of multi-source information.

The invention discloses a personalized recommendation method, system and device, a medium and a product, and relates to the technical field of big data processing.The social relation strength between users with social relations is calculated by obtaining behavior data of all the users; extracting interest theme distribution of each user from the behavior data, and calculating interest similarity among the users; according to the interest similarity and the social relation strength, calculating the interest propagation strength between the users; according to the interest propagation intensity and the interest theme distribution, calculating an interest score of each user for a specific theme; and generating a recommendation result of each user according to the interest score. By adopting the embodiment of the invention, the interest of the user can be mined and mapped by fusing the social information and the behavior data of the user, the precision of personalized recommendation is improved, and meanwhile, the cold start speed and precision are reduced.

Procedure (100,500) for detecting an event from a social stream, wherein the procedure (100,500) comprises the steps of one: Receiving a social stream from a social network, where the social stream contains at least one object; and where the object contains a text, sender information of the text and recipient information of the text (101,510); Assigning the object to a cluster based on a similarity value between the object and the cluster (102,520); Monitoring changes in at least one of the clusters (103,540); and Triggering an alarm when changes in at least one of the clusters exceed a first threshold (104,550), where at least one of the steps is performed using a computer unit, wherein the procedure further includes maintaining changes in the clusters as history data of the social stream (530), wherein in the maintenance step a sketch-supported technique is used, and wherein the sketch-supported technique is used to estimate a structural similarity value between the object and the clusters.

The embodiment of the application provides an embedding feature extraction method and device for social information, comprising: obtaining publishing information corresponding to each social information published by a publisher associated with a target user; extracting first embedding features of each publishing information; determining second embedding features of the target user according to historical interaction behaviors of the target user and the first embedding features; obtaining target social information when the target user performs real-time interaction behaviors; and obtaining third embedding features of the target social information according to the target social information, the first embedding features and the second embedding features.

The invention discloses a social information maximization propagation method and system based on information variation, and the method specifically comprises the steps: carrying out the quantification of information variation, constructing an expression from a piece of social content to a multi-dimensional information vector, and enabling each dimension to correspond to a certain specific attribute of information, quantizing variability between different information vectors through a cosine similarity function of any two information vectors; content sentiment calculation is carried out, when it is detected that the similarity of the information is lower than a threshold value, sentiment polarity analysis is carried out on the information through a sentiment classification model, and if the information shows strong forward sentiment, it is considered that the user is effectively influenced; and finally, selecting propagation nodes, and selecting user nodes by adopting a greedy algorithm based on the ERR set so as to maximize the propagation effect of information. According to the method, a feasible optimization strategy is provided for information spreading on an actual social network platform, the spreading effect and coverage range of social information are effectively improved, and the product popularization accuracy and the popularization effect of related products are improved.

The invention provides a community information dissemination system and method based on a random directed hypergraph theory, which introduces community structures and attributes on the basis of a traditional information dissemination model on the basis of the directed hypergraph theory, simulates high-order asymmetric interaction in a real society through a method of randomly adding directed hyperedges, and provides a community information dissemination system and method based on the random directed hypergraph theory. According to the method, roles and susceptibility degrees of different individuals in information propagation are distinguished, and a new social information propagation model and a theoretical calculation method of the influence density of the social information propagation model are constructed. In practical application, community network model parameters are set according to a to-be-analyzed information spreading scene, a random simulation experiment is carried out by using a Monte Carlo algorithm, so that the influence density approaches a theoretical value, and spreading of information, influence or infectious diseases in a complex network in a real society can be better simulated, understood and explained; the critical value of the key control parameter can be quickly found, and the control and management of the information spreading can be further realized.

The invention provides a social interaction pushing method and related equipment thereof. The social interaction pushing method comprises the following steps: acquiring operation data of a target object during interaction at a terminal; performing feature extraction processing on the interaction behavior data and the environment perception data, and determining interaction intention data of the target object and corresponding emotion data; key interaction recognition processing is carried out on the interaction intention data and the corresponding emotion data, and corresponding key interaction metadata is determined; when it is detected that the preset interaction condition is met, push content corresponding to the key interaction metadata is generated and pushed to the terminal. Through multi-modal data fusion and semantic-emotion joint analysis, semantic understanding and emotion association recognition of interaction behaviors of a target object are realized, key interaction events can be judged based on topic association degree and emotion intensity, and timeline type determination pushing is generated after an interaction closed loop is detected. And the pertinence and the intelligent degree of social information pushing are improved.

The invention discloses a social information pushing method, a related device, equipment and a storage medium. The method comprises the steps that in response to a payment transaction request, a consumption feature vector corresponding to a target user account is acquired, and the payment transaction request carries the target user account and equipment position information; determining M user accounts according to the equipment position information and the consumption feature vector corresponding to the target user account; determining N pieces of recommended place information according to the equipment position information; the social information is pushed to at least two terminals, the at least two terminals comprise a target terminal and at least one terminal, the target terminal has logged in the target user account, each terminal in the at least one terminal has logged in one user account in the M user accounts, and the social information comprises N pieces of recommended place information. According to the invention, the social cost of the user is reduced, and the accuracy of social matching can be improved.

The application belongs to the technical field of computer information processing, and provides a target service determination method and device based on a heterogeneous graph neural network and electronic equipment, the method comprising: obtaining social information of a target to be evaluated; constructing a social relationship heterogeneous graph according to the social information, determining an attention weight corresponding to the target to be evaluated; and inputting the attention weight into a preset security evaluation model to calculate a trust degree of the target to be evaluated. According to the social information of the target to be evaluated, the application constructs a social relationship heterogeneous graph with different types of social relationships, calculates an attention weight corresponding to the target to be evaluated, and inputs the attention weight vector into a preset security evaluation model to calculate a trust degree of the target to be evaluated, and determines a service strategy according to the trust degree. In this scheme, the trust degree obtained through the social relationship of the target to be evaluated enables a service provider to make a response strategy in time before providing a service, avoids losses caused by mismatched services, and guarantees the data security of the service.