79 results about "Social robot" patented technology

Aiming at the problems of insufficient language understanding depth, weak personalized dialogue generation ability, lack of continuous learning and long-term user state modeling and the like in the current emotion recognition and psychological intervention technology, the invention provides a user emotion recognition and psychological intervention method combined with a large language model (LLM). According to the method, the potential emotional state is identified by analyzing free text information input by a user by utilizing the powerful capabilities of a large language model in the aspects of natural language understanding, emotional modeling and text generation; constructing a multi-round dialogue context, and reasoning a psychological change trend of the user; in combination with a psychological knowledge base, personalized and mild psychological intervention dialogue content with a dredging effect is generated. The system supports recognition and classification of various emotional states such as depression, anxiety and alonity, is suitable for various interaction scenes (such as APPs, webpages and social robots), and can greatly improve the precision of emotion recognition and the timeliness and effectiveness of psychological intervention. The emotion recognition and psychological intervention method based on the large language model provides solid technical support for constructing an intelligent, continuous and personalized psychological health management system, and has wide application prospects and profound social significance.

The invention belongs to the technical field of virtual social robot detection, and particularly provides a social robot detection method based on BERT and bidirectional dynamic feature fusion, electronic equipment and a storage medium. Obtaining text modal data, behavior time sequence modal data and social relation modal data of users in the to-be-detected social data set; obtaining enhanced text features and enhanced behavior time sequence features based on the text modal data and the behavior time sequence modal data; generating social structure features based on the social relation modal data; generating a final cross-modal initial association feature based on the enhanced text feature and the enhanced behavior time sequence feature; based on the enhanced behavior time sequence feature, the social structure feature and the final cross-modal initial association feature, obtaining a text semantic anomaly degree and a behavior comprehensive anomaly degree; based on the text semantic anomaly and the behavior comprehensive anomaly, obtaining a social robot detection result; and the detection accuracy and robustness of the social robot are improved.

The invention discloses a social robot identification method and system based on deep learning, and relates to the technical field of robots, and the method comprises the steps: carrying out the smooth processing of a tweet through a large language model, and generating a tweet fused with expression semantics in combination with a natural language processing model; capturing an emotion expression difference between a robot account and a real user; generating a comprehensive feature vector of global context sensing; outputting fusion features; the output fusion features are mapped to a high-dimensional space through a linear layer, and the detection probability of a robot account is output through an activation function; and based on adaptive moment estimation, gradient back propagation is carried out by using a cross entropy loss function, and parameters of the graph convolutional network model are optimized to obtain a final classification result. According to the method, the problems of sparse text expression and emotion information loss are effectively relieved, and the separability of the social robot and the real user in emotion behavior modes is enhanced.

The invention provides a social robot intention recognition system and method based on heterogeneous graph analysis, and the method comprises the steps: carrying out the unified modeling of multi-type nodes and multiple relation edges based on a heterogeneous graph structure, and systematically capturing the complex multi-dimensional behavior association in a social platform; according to the method, technologies such as a large language model and a knowledge graph are fused, fine recognition and classification of multiple types of behavior modes are supported, and meanwhile, hierarchical evaluation for different organized risks is realized by combining account behavior aggregation and emotional polarity analysis, so that a decision basis is provided for supervision and governance; according to the method, automatic collection and preprocessing of multi-source heterogeneous data and heterogeneous graph construction processes are integrated, manual intervention and repeated work are reduced to the maximum extent, the overall data processing efficiency and response speed are improved, and the real-time analysis requirement in a complex dynamic social environment is met; transparent analysis of robot control sites and behavior strategies is supported, and the interpretability of the system, the user credibility and the executive force of policy supervision are greatly improved.

The invention provides a social robot detection method and system, computer equipment and a storage medium, and belongs to the technical field of social robot detection.The method comprises the steps that user multi-source data on a social platform and the social relation between users are collected; a hybrid encoder is adopted to capture local dependence and global time sequence dynamic states of behaviors, and user behavior characteristics are generated; aggregating structure attention features between the initial node features of the target account and the initial node features of the social relation account to obtain multi-modal relation aggregated structure features; introducing a multi-modal adversarial training strategy, adaptively adjusting the disturbance intensity of each modal based on gradient sensitivity, and aligning the characterization of the clean sample and the adversarial sample in combination with a content discriminator and a behavior discriminator; and outputting a target user classification result through the multi-task target function optimization model. According to the method, the problems of insufficient modal fusion and insufficient adversarial robustness of an existing method can be effectively solved, and the accuracy and stability of social robot detection in a complex and adversarial scene are improved.

The invention relates to the technical field of information processing, and discloses a social robot identification method based on multi-scale entropy features, a terminal and a medium. The method comprises the following steps: acquiring social network behavior data of a to-be-detected user, and respectively constructing an initial binary time sequence for predefined behavior types; setting a plurality of time windows with different granularities, and mapping the initial binary time sequence into a plurality of coarse-grained behavior sequences with different time scales; for the coarse-grained behavior sequence of each time scale, calculating a behavior information entropy corresponding to the coarse-grained behavior sequence to form a behavior entropy set; based on the behavior entropy set, calculating variable coefficients of entropy values among different time scales so as to quantify dynamic fluctuation characteristics of user behaviors; and fusing the behavior entropy set and the variable coefficient to construct a comprehensive feature vector, inputting the comprehensive feature vector into a trained supervised classification model, and outputting a classification result that the user is a real user or a social robot. According to the invention, the recognition capability for the complex camouflage behavior of the social network robot is improved.

The invention discloses a robot detection method and system based on a sample equalization strategy and a heterogeneous graph, belongs to the technical field of robot detection, effectively relieves the problem of unbalanced data distribution in robot detection through the sample equalization strategy, and combines the multi-relation modeling capability of the heterogeneous graph to improve the robot detection efficiency. And attention behaviors and semantic similarity among the users are fully mined, and the recognition precision of the social robot is remarkably improved. And feature information in different relational graphs is layered and aggregated by using a graph neural network, and multi-modal data is dynamically fused through a semantic attention mechanism, so that the analysis capability of the model on a complex social network relationship is enhanced. Meanwhile, noise interference is reduced through cooperative application of oversampling and undersampling, the generalization performance of the system on the camouflage behavior of the novel robot is further improved, and the robustness and reliability of a detection result in different application scenes are ensured.

The invention relates to the technical field of social network security, in particular to a social robot detection method and system based on residual propagation and label smoothing, a directed social graph G = (V, E) is constructed, a node u belongs to V and represents a user, and a directed edge (u, v) belongs to E and represents a social relation between users; training a topology-independent base predictor f based on the attribute feature xu and the label yu of the labeled node, and outputting an initial prediction zu of the labeled node; based on the prediction residual yu-zu of the annotated node, correcting the prediction result of the unannotated node through a directional residual propagation mechanism; and performing label smoothing processing on the corrected predicted value, and outputting a final classification result. According to the method, the detection precision equivalent to that of the most advanced GNN model is realized through a lightweight architecture (parameter quantity is reduced by 1-2 orders of magnitude), and an efficient and extensible solution is provided for large-scale social network deployment.

The invention discloses a semi-supervised social robot detection method based on a pseudo tag and a graph neural network. The method comprises the steps of obtaining a data set, dividing the data set, extracting multi-modal features, enhancing the multi-modal features, constructing a social robot detection network, training the social robot detection network, testing the social robot detection network, and identifying and detecting a social robot. According to the invention, two multi-modal feature enhancement modes are provided, so that the diversity of input data is improved; a pseudo label generation method is provided, the problem that data labels are rare is effectively solved, and the cost of data labeling is reduced; and a semi-supervised social robot detection network based on a graph neural network is constructed, unlabeled data is effectively utilized to participate in training, and the training data of the social robot detection network is amplified at low cost. The method has the advantages of high detection accuracy, low data labeling cost, large training data scale, short network training time and the like, and can be used for identifying and detecting the social robot.

The invention discloses a digital latent social robot generation and specific data acquisition method and device. The invention belongs to the technical field of computers. The method comprises the following steps: generating a social robot: training a multi-modal large model based on general recognition to obtain the social robot with semantic understanding and simulated dialogue reply generation capabilities; understanding and generation of multi-modal information: understanding the multi-modal information, and generating and replying information; emotion analysis and calculation: carrying out emotion state modeling, analyzing the emotion and understanding of the social contact object, and carrying out dynamic reply; specific personality shaping: carrying out personality shaping to maintain personality, maintaining behavior consistency of roles, and carrying out active identity defense and latency; establishing a specific relationship: identifying a specific target and establishing the relationship; and specific data acquisition: acquiring and storing specific social data in private chat and group chat scenes. According to the technical scheme, information can be replied in time, information collection and analysis efficiency is improved, and comprehensive acquisition of communication data is realized.

The invention discloses a structure entropy model for detecting a social robot in real time, particularly relates to the technical field of big data mining, and is used for solving the problem that an existing social robot detection method is difficult to balance between detection precision and processing efficiency. User data is processed through a feature selection weighting module to screen key features and distribute weights, a feature stability evaluation module analyzes the contribution degree of the key features to a community structure to screen features with the most distinguishing power, and a multi-relation graph construction module constructs a user similarity graph based on the key features and the weights thereof. The coding tree community division module initializes a coding tree on the user similarity graph and generates a hierarchical community division structure through iterative calculation of structure entropy change; and the community level classification module forms a comprehensive score for each community fusion structure entropy and behavior statistical characteristics and judges a social robot community through comparison with an optimization threshold.

The invention belongs to the technical field of network space security and social platform governance, and particularly provides an agent-driven active interactive social robot detection method, electronic equipment and a storage medium, and the method comprises the steps: obtaining original data of a to-be-detected account, and forming a structured data packet; constructing a preliminary screening evaluation model, and outputting a detection task state based on the structured data packet; generating an initial detection state; obtaining an interaction record; carrying out evidence extraction on the interaction record to obtain an evidence vector of the round; and performing sequential updating on the initial risk score and the uncertainty based on the evidence vector, and outputting a detection result when a stop condition is met. According to the method, an active interactive evidence obtaining mechanism of a detection agent is introduced, and on the basis of passive preliminary screening, probe interaction is automatically selected and initiated to obtain incremental evidence, so that the recognition capability of a high-simulation social robot is improved, and an auditing report containing key evidence and an interactive link is output.

The invention provides a malicious social robot detection method based on Token-level multi-modal fusion and sparse MoE, and belongs to the field of artificial intelligence technology and social networks in the field of computers. Efficient detection is achieved through the following steps that firstly, preprocessing and feature coding are conducted on three types of modal features of metadata, texts and graph structures, and cross-modal alignment is completed through comparative learning; then, the three types of modals are mapped into a unified Token sequence by adopting Token-level pre-fusion, and cross-modal semantic interaction is realized through a Transform structure of Qwen3-4B; a DSselect-k sparse selection mechanism is introduced to screen the key Token so as to eliminate noise; dynamically routing to a matched expert sub-network through the hybrid expert network for dividing and conquering; and finally, outputting a malicious robot prediction probability through a classifier, and completing model training based on a binary cross entropy loss function. Through Token-level fusion, large model semantic modeling, sparse selection and expert processing, the detection precision, robustness and calculation efficiency are significantly improved, and the method is suitable for identification of highly disguised malicious social robots.

The invention discloses a social robot false user identification method and system based on a knowledge graph, and the method comprises the steps: obtaining an initial knowledge graph based on user behavior data and interaction records; based on the initial knowledge graph, obtaining a topological feature set of the user nodes; identifying an abnormal node candidate set based on the topological feature set; based on the abnormal node candidate set, analyzing a group cooperation behavior; and completing false user identification based on group cooperation behaviors. According to the method, the hidden false users and group behaviors thereof can be accurately identified by constructing the dynamic knowledge graph, integrating the dynamic characteristics of the user behaviors and the relationship and combining topological structure analysis and semantic reasoning technologies. Compared with the prior art, the method can effectively deal with complex and disguised false users, capture the dynamic evolution and group cooperation behaviors of the relationship between the users, and reveal the hidden mode of the false user group from the global perspective, thereby improving the authenticity and security of the social media platform, and reducing the propagation of false information.

The invention discloses a knowledge graph-based social robot semantic understanding method and system, electronic equipment and a storage medium, and the method comprises the steps: obtaining historical heterogeneous data composed of historical text input, historical voice input and historical image input, and coding the historical heterogeneous data to obtain a unified multi-modal feature vector representation; entities, relations and attributes in the multi-modal feature vector representation are extracted, and an initial knowledge graph is constructed; weighting and updating the initial knowledge graph by using a graph attention network and a graph convolution network to obtain a dynamically updated knowledge graph; dialogue information currently input by a user is acquired, and user intention and semantic association entities are identified by using the dynamically updated knowledge graph; based on the user intention and the semantic association entity, a semantic understanding result is generated in combination with the context of the dialogue information, and response content is generated based on the semantic understanding result. According to the method, the deep understanding capability of the social robot on complex semantics is remarkably improved.

The invention discloses a graph-enhanced social robot detection method and device based on reinforcement learning, and the method comprises the steps: 1, extracting metadata information and text information of a user in a social network through a multi-layer perceptron and a pre-training language model, carrying out the feature fusion of the information through a multi-head self-attention mechanism, and generating user representation; 2, performing oversampling on minority class nodes in a potential feature space by using a linear interpolation method based on neighborhood perception, and constructing a balanced training sample set; 3, dynamically adjusting an edge retention threshold value based on the feature similarity and a reinforcement learning strategy, and executing an edge filtering operation to eliminate unreliable connection and optimize a graph structure; and 4, inputting the enhanced node features and the purified graph structure into a graph neural network classifier to realize accurate identification of the social robot nodes. According to the method, the problem of misjudgment caused by class imbalance can be effectively relieved, and the detection accuracy and stability are remarkably improved.

The invention relates to the technical field of social robot detection, in particular to a social robot detection method and system based on causal intervention and mixed experts, and the method comprises the steps: constructing a CusBot model which comprises a pseudo-environment estimator and a mixed expert mechanism enhanced graph Transform encoder; estimating the distribution of a potential environment to which each node belongs through a pseudo environment estimator, and generating an environment perception weight based on a Gumbel-Softmax relaxation technology; a graph Transform encoder enhanced by a hybrid expert mechanism is utilized to perform multi-level encoding on node features under the regulation and control of an environment perception weight so as to extract cross-environment invariant causal features; and training the CusBot model by adopting a joint optimization objective function, wherein the objective function comprises a supervision loss item and a KL divergence regularization item. According to the method, environment pseudo-correlation factors are effectively decoupled, cross-environment invariant causal features are extracted, and the stability and accuracy of social robot detection in cross-platform, cross-period and other distributed migration scenes are remarkably improved.

The invention belongs to the field of artificial intelligence, and discloses a social robot detection method and system based on multi-type social behavior heterogeneous graph modeling, and the method comprises the steps: inputting social user information, and constructing a metadata feature channel and a text feature channel; the method comprises the following steps: constructing a network topology structure by using social behaviors of social users, and forming a plurality of different types of HINs by adopting a graph neural network; fusing the obtained metadata and text features to form comprehensive user features; performing supervised contrast learning training by using the fused user features to obtain contrast loss; fusing network structure information in a social behavior scene into user features, and performing message aggregation and feature updating; and inputting the user feature vector into the classifier to complete the detection of the social robot account. According to the method, the problem of social robot detection in a multi-social behavior scene can be effectively solved, the detection performance is ensured, the robustness and adaptive capacity of the model are ensured, and subsequent detection tasks are facilitated.

The application relates to the technical field of information processing, and discloses a social robot identification method based on multi-scale entropy features, a terminal and a medium. The method acquires social network behavior data of a user to be detected, constructs initial binary time series for each predefined behavior type, sets a plurality of time windows with different granularities, maps the initial binary time series into coarse-grained behavior sequences with different time scales, calculates the behavior information entropy of each coarse-grained behavior sequence with a time scale to form a behavior entropy set, calculates the variation coefficient of the entropy values between different time scales based on the behavior entropy set to quantize the dynamic fluctuation features of the user behavior, fuses the behavior entropy set and the variation coefficient to construct a comprehensive feature vector, inputs the comprehensive feature vector into a trained supervised classification model, and outputs the classification result of the user as a real user or a social robot. The application improves the identification ability for the complex camouflage behavior of social network robots.

A method and device for evaluating the influence effect of an academic recommendation algorithm based on a social robot, the method comprising: collecting academic papers, citation relationships and author information through a data interface or a web crawler, and screening target personnel data according to a research field; constructing a virtual social robot and establishing a research interest vector of the virtual social robot based on historical literature and research theme information of the target personnel; presetting multiple literature acquisition strategies for the social robot to form differentiated experimental conditions; controlling the social robot to perform operations such as paper retrieval, access and click recommendation on an academic platform, and recording literature access paths, recommendation results and browsing sequence data in real time; calculating the research theme distribution of the social robot according to a literature set contacted in the experiment, and comparing the research theme distribution with the initial research interest, so as to obtain the change degree of the research direction; and comparing the change results of the research direction of the social robot under different strategies, and quantitatively evaluating the influence degree of the recommendation system on the research direction evolution of the scientific researchers.

This invention relates to the field of robot interaction technology, specifically to a method for recognizing the intensity of human-computer interaction intentions in real time. The method includes the following steps: S1, acquiring video of pedestrians through a collection unit mounted on the robot, performing frame extraction on the video, and using a 3D skeleton extraction model to extract the skeleton information of each pedestrian in each frame in chronological order; S2, based on the skeleton information of each pedestrian in each frame, using a preset lightweight motion behavior recognition model to identify the interaction reference information of each pedestrian; S3, analyzing and processing the three types of interaction reference information—straight-line distance, orientation information, and motion behavior—to obtain the real-time interaction intention intensity of the pedestrian relative to the robot. This invention can accurately identify the interaction intentions of pedestrians, thereby improving the initiative and naturalness of social robots when interacting with humans.

The application discloses a social robot detection method and device, medium and product, and relates to the field of network security. The method comprises the following steps: taking all users in a current social network as nodes and taking the interaction between the users as edges to construct a social graph comprising a center node and a peripheral node; adopting a peripheral enhanced graph neural network to perform center node detection according to the social graph to obtain a detection result; determining a first classification loss according to the detection result of the center node and a corresponding label; determining a second classification loss according to the detection result of the peripheral node and a corresponding label; determining a cross-network domain adaptive loss based on an MK-MMD loss by using the features of the center node and the features of the peripheral node; and determining a total loss according to the first classification loss, the second classification loss and the cross-network domain adaptive loss. The application can improve the accuracy and robustness of social robot detection, thereby guaranteeing the security of the social network.

The invention relates to the technical field of network security, and discloses a social robot collaborative group detection method based on a multi-order collaborative knowledge graph. According to the method, user data in a Chinese social platform is collected through a crawler, a multi-order collaborative interaction graph is constructed based on the interaction relation of users of the social platform and then input into a graph encoder module, node feature vectors are obtained and input into a time perception module and a graph perception module respectively, and a time sequence prediction task and a side link prediction task are executed. Meanwhile, the model is constructed based on a time-graph semantic consistency perception module of a self-attention mechanism. And finally, inputting a node feature vector obtained by training under the guidance of double tasks into a group detection module constructed based on a Gaussian mixture model and a K-means clustering method for detection. According to the method, the complex interaction relationship among the users in the social robot group and the abnormal mode in the time sequence activity can be effectively captured, and efficient detection of the social robot collaborative group in the social network platform is realized.

The application discloses a social robot detection method based on directed relation graph contrast learning, comprising the following steps: taking each user as a user node, obtaining personal attribute information and personal text information of each user node, and converting the personal attribute information and the personal text information into a feature vector after splicing; constructing a user directed relation graph, first learning the features of adjacent users under different relations by using a directed relation graph convolutional neural network, and then performing relation feature fusion based on an attention mechanism; constructing contrast views of the directed relation graph from two aspects of attribute features and graph topological structure combined with direction information, and then performing training and prediction. The application improves the accuracy of robot account identification of a social network platform by using a directed relation graph attention mechanism and directed graph contrast learning, and can effectively utilize direction information of relations of the social network platform in real life and importance information of relations between users by using the directed relation graph combined with the attention mechanism.

The application discloses a feedback method of a social robot based on tactile interaction and the social robot, and the feedback method comprises the following steps: a sensing module acquires petting data of a visitor and sends the petting data to a control chip, a tactile feedback module and a motion simulation module; the tactile feedback module provides tactile feedback to the visitor according to the petting data, and the motion simulation module performs initial simulation motion according to the petting data; the control chip classifies the petting data to obtain current petting classification and sends the current petting classification to the tactile feedback module and the motion simulation module; and the motion simulation module adjusts the initial simulation motion according to the current petting classification to provide visual feedback to the visitor. The application does not need to occupy the attention of the visitor and can reduce the consultation pressure of the first-time visitor.

The invention relates to the technical field of social robots, in particular to a robot interaction method, a social robot, a medium and equipment. The emotion of the talker is recognized based on the face image of the talker, the target behavior state of the robot is determined according to the emotion of the talker, and the robot is controlled based on the target behavior state, so that the robot responds to the emotion change of the talker by presenting the target behavior state. According to the analysis, the emotion change of the talker is fully considered when the robot interacts with the talker, so that the interaction effect of the robot and the talker is enhanced.

The application discloses a data mining method and system for a social robot. The method comprises the following steps: determining an interactive object currently communicating with the social robot and collecting social media data; performing word segmentation and vectorization processing on the text through a natural language processing algorithm, and extracting an emotional tendency value through an emotional analysis model, and dividing the data into multiple emotional grades according to a preset critical value; extracting keywords and topic fields based on word frequency statistics and topic clustering, and deleting the data if the number of keywords is lower than a threshold value; constructing time series data according to social behaviors and time stamps, predicting an active period and a behavior trend by using an LSTM model, and adjusting the model through a sliding window mechanism; and combining multi-dimensional feature vectors, and assigning personalized labels to the interactive object through clustering results. The application realizes accurate analysis of behavior and emotional characteristics of the interactive object, and provides an effective personalized interaction strategy for the social robot.

The application discloses a social robot behavior semantic consistency detection method for time sequence analysis and belongs to the field of social account detection.The core innovation of the method is to construct a "semantic indexed time sequence interaction graph", realize the deep fusion of semantic content and topological structure, introduce an offline reasoning mechanism, utilize a pre-training language model to construct a static semantic index matrix, adopt a double-flow architecture, fuse a multi-head graph attention network and a GRU on the behavior side, inhibit noise neighbor interference through an adaptive weighting mechanism, capture the space-time behavior evolution track of nodes, utilize a Transformer and a self-attention mechanism on the semantic side to extract deep text logic, mine potential robot gangs through the construction of a homogeneity association graph, extract cluster structure features, align "behavior-semantic" feature spaces through a cross-modal interaction module, and realize high-precision and low-cost identification of social network robot accounts in combination with a multi-task joint optimization strategy.

The application relates to a kind of social platform robot detection methods based on multi-agent, comprising: creating social platform API connection instance to collect target user comment history data to obtain original data set;Build the orchestrator-multi-agent collaborative detection model driven by large language model;Data processing agent constructs comment level relationship to input data, and carries out cleaning, standardization and quality detection, forms the structured data set after preprocessing and writes into shared memory;Feature engineering agent reads structured data from shared memory, calculates user-level multi-dimensional behavior feature vector and writes into shared memory;Rule discrimination agent reads feature data, executes rule discrimination, judges whether feature hits piece by piece, thereby outputs rule risk score and writes into shared memory;Modeling agent reads feature data, trains anomaly detection and supervised classification model, executes multi-model fusion to obtain robot risk determination result and writes into shared memory;Explanation generation agent reads model detection result and rule data, and fusion outputs the final interpretable social robot detection result.The application reduces the dependence on single rule or single model by adopting multi-agent cooperation to complete data processing, feature construction, rule discrimination and multi-model fusion detection, greatly improves the accuracy and robustness of social platform robot detection.

The invention discloses a social robot based on pneumatic driving and an interaction system thereof. The social robot comprises a shell, a body software actuator, a head actuator, a hand reinforced fiber actuator, a sensing module and a sound module. According to the social robot, interaction state information between a user and the robot is obtained through the sensing module, the control and drive module can generate rhythm parameters according to the interaction state information, the body software actuator and the head actuator can generate deformation actions synchronous with respiratory rhythm according to the rhythm parameters, and meanwhile, the motion of the user is controlled to be more stable. The sound module can modulate the envelope and intensity of sound output according to the rhythm parameters, so that the tactile feedback and the auditory feedback are consistent in time, the tactile feedback, the sound feedback and the breathing mechanism are combined, in addition, the hand reinforcing fiber actuator can attract a user to interact with the robot, and the user experience is improved. In this way, the user can obtain stable, continuous and perceptible breathing experience without excessive active operation or continuous attention, and pressure can be better relieved for the user.