59 results about "Social robot" patented technology

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 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 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 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 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 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.

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.

The invention relates to the technical field of man-machine emotion interaction, and discloses a social robot multi-mode emotion analysis intelligent accompanying system, which comprises a data acquisition module used for acquiring voice, image and text input data of a user; the multi-modal emotion recognition module is used for extracting emotion features of the collected voice, image and text data and generating corresponding voice emotion vectors, and the system has five core advantages that three-modal deep fusion is combined with conflict detection and composite emotion analysis, so that the emotion recognition accuracy and anti-interference performance are greatly improved; the multi-Agent collaborative reasoning is matched with a strategy knowledge base, and the co-situation quality of the complex scene is optimized; long-term memory and short-term memory are coordinated, and continuity and individuation of long-term accompanying are The side cloud collaborative architecture reduces the computing power consumption and improves the end side adaptability; the whole process privacy compliance design ensures data security, and lays a foundation for large-scale commercial use.

The invention relates to a public opinion reversal early warning and traceability system based on social robot behavior detection. The system comprises a multi-source social data acquisition module, a social robot recognition module, a dynamic public opinion propagation network construction module, a public opinion evolution monitoring module, a robot propagation sub-graph extraction module, a propagation sub-graph stability quantification module and a public opinion inversion trigger judgment module. By adopting the system, a robot manipulation sign can be found in advance and a driving source can be positioned before public opinion inversion is not dominant.

The application provides a social robot detection system based on microblog platform text features, which comprises: an explicit text feature extraction module for extracting explicit text features corresponding to account meta information text of a microblog platform account and original comment forwarding text; an implicit text feature extraction module for extracting implicit text features corresponding to the account meta information text of the microblog platform account and the original comment forwarding text; a deep text semantic feature extraction module for performing sentiment detection, stance detection, junk content detection, nickname detection and text generation detection on the account meta information text of the microblog platform account and the original comment forwarding text to obtain corresponding deep text semantic features; and a social robot judgment module for splicing the explicit text features, the implicit text features and the deep text semantic features to obtain fusion features, and judging whether the microblog platform account is a social robot according to the fusion features.

The present application belongs to the technical field of data analysis, and specifically relates to a method for detecting an adversarial social robot based on a graph and structure perception. The method comprises the following steps: constructing a user relationship network by taking social platform users as nodes and the forwarding relationship between the users as edges; performing representation learning on different structures in the network by using a structure feature extractor; performing structure similarity calculation between nodes by using a structure self-attention mechanism; training user representation vectors by using a graph Transformer algorithm; and inputting the user representation vectors into a category generative adversarial network for training to obtain a discrimination result of whether the user is a social robot. The method has strong generalization and high robustness by using adversarial thinking and unsupervised training, and can be used for detecting social robots in a large social network platform, thereby providing commercial value for user management, advertisement placement, public opinion safety control and the like of the social platform.

The invention discloses a social robot continuous learning method and system based on emotion distribution embedding, and belongs to the technical field of artificial intelligence and robots. The method comprises the steps of obtaining environment features through a scene perception module; generating a task code through a task coding module; emotion distribution is output through an emotion prediction module; emotion distribution and task features are fused through an emotion fusion module; and long-term learning and behavior optimization are realized through the continuous learning module. The system comprises corresponding modules. According to the method, through an emotion distribution embedding and continuous learning mechanism, the problems of static state, cross-task forgetting, insufficient robustness and the like of an emotion model are solved, and the emotional interaction naturalness and environmental adaptability of the robot in a multi-task scene are improved.

The application relates to a multi-modal fusion emotion recognition method and system for a social robot, and the method comprises the following steps: obtaining real-time sensing information of target personnel, wherein the real-time sensing information comprises image information, tactile information and sound information; pre-processing the real-time sensing information to obtain pre-processed sensing information; and obtaining an emotion recognition result according to the pre-processed sensing information. Compared with the prior art, the application fuses visual, voice and tactile sensing data for emotion recognition, uses a microphone and an electromyography sensor to acquire voice sensing data, and uses multiple key points to capture human parameters for visual sensing data, so that the recognition accuracy is improved and the method is suitable for more environments.

The invention provides a social robot detection method based on uncertainty driving and agent dynamic arrangement, electronic equipment and a storage medium. The method comprises the following steps: obtaining a standardized data packet to be detected; calculating behavior entropy and detection uncertainty based on the to-be-detected data packet, and generating an agent activation signal; initializing a detection agent; outputting an accumulated evidence set based on the detection agent; converting the evidence set into a weighted undirected graph in a graph structure form; outputting a binary detection conclusion based on the weighted undirected graph; calculating a key evidence set; and obtaining a social robot detection conclusion based on the binary detection conclusion, the final abnormal risk score and the key evidence set. According to the method, behavior entropy and detection uncertainty are introduced as triggers, samples with low uncertainty are quickly intercepted or released only by using an extremely low-cost statistical rule, and intelligent agents are activated only for ambiguous samples with high uncertainty for deep detection, so that self-adaptive cost reduction and benefit increase of good steel applied to the cutting edge are realized.

The application discloses an emotion recognition method based on fusion field analysis and mind theory, and the core process comprises four steps: multi-modal frequency domain enhanced feature extraction, reliable low-rank multi-modal fusion, LIMP multi-agent cognitive reasoning and integrated evaluation and verification. The three-level architecture of "frequency domain transformation, pre-training enhancement and attention de-redundancy" is used to purify features, the T-LMF network is constructed based on low-rank decomposition and MoNIG algorithm to solve the dimension disaster and uncertainty problem of modal fusion, the cognitive leap from emotion recognition to intention understanding is realized by means of the LIMP model, and finally the effect is verified by a standardized evaluation system. Under the premise that the parameter quantity is reduced by more than 90%, the emotion classification accuracy is improved by 2.8% to 4.2% compared with the existing model, the F1 value of social target reasoning reaches 89.7%, the robustness and generalization ability are significantly enhanced, and the application can be widely applied to the fields of human-computer interaction, social robots, intelligent assistants and the like, and provides technical support for multi-modal emotion cognition in complex scenes.