Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

46 results about "Event propagation" patented technology

A social network rumor identification method based on feature aggregation

ActiveCN109685153ASolve the problem that it is difficult to deal with heterogeneous informationSolve problems that are difficult to feed into machine learning modelsData processing applicationsCharacter and pattern recognitionStudy methodsData quality
The invention discloses a social network rumor identification method based on feature aggregation, and the method comprises the steps: designing time sequence propagation mode features acceptable by adeep neural network and time sequence text features, constructing a rumor detection model by using a feature aggregation technology, and carrying out the final detection and early detection of a rumor. The problem that propagation mode characteristics of social network event propagation are difficult to serve as machine learning model input is solved, the propagation mode characteristics do not depend on characteristic engineering and field knowledge, the influence of various factors in the actual propagation process is comprehensively embodied, and the method can be effectively applied to different rumor identification scenes; The defect that the quality of feature data is reduced due to huge difference of the number of messages contained in different samples is avoided, the problem thata single model is difficult to deal with heterogeneous information in a traditional machine learning method is solved, and compared with an existing rumor identification method, the accuracy is obviously improved.
Owner:WUHAN UNIV

Data analysis method and apparatus

The invention provides a data analysis method and apparatus. The data analysis method comprises the steps of collecting multi-channel original public sentiment events; according to a set data cleansing rule, cleansing the multi-channel original public sentiment events to generate to-be-clustered information; performing classification polymerization processing on the to-be-clustered information to generate a public sentiment event analysis result; generating the public sentiment event analysis result into graph data; and showing the graph data according to requirement of a user. By adoption of the data analysis method and apparatus disclosed by the invention, the polymerization efficiency of effective public sentiment events is greatly improved, and the problem of more abundant information and single analysis channel in the conventional public sentiment event analysis method is solved; in addition, the invention also provides a public sentiment event service for realizing all-around showing of the development process and trend of the public sentiment events to form a complete public sentiment event propagation path, so that a more accurate and more all-around public sentiment event analysis result is provided for the user; and therefore, social situation can be mastered in time, hidden dangers can be found, hidden risks can be recognized, and forceful data support is provided.
Owner:INDUSTRIAL AND COMMERCIAL BANK OF CHINA

Key node selection method in network public opinion information propagation

ActiveCN111222029ASmall averageIncreased cost-benefit ratioData processing applicationsWeb data indexingInformation propagationGreedy algorithm
The invention discloses a key node selection method in network public opinion information propagation. The method comprises the following steps: 1) collecting public opinion event propagation flow data under a specific theme from a real social network; 2) modeling the propagation process of the single microblog message by adopting an infectious disease model and accurately estimating the propagation influence of the single microblog message; 3) in order to solve the problem of high algorithm time complexity due to excessive users, reducing the number of seeds by adopting a heuristic method from the perspective of network structure characteristics, introducing the concept of isolation efficiency, and selecting a node with the highest isolation efficiency in each simulation process by adopting a greedy algorithm to add into a key node set; 4) solving the problem of simulation randomness by adopting a depth-first algorithm in directed graph search, and obtaining a group of key node sets in an information propagation process. according to the invention, the structural characteristics of a network and dynamic characteristics of information propagation are comprehensively considered in akey node selection process in network public opinion information propagation, so the method is more suitable for an actual application scene.
Owner:XI AN JIAOTONG UNIV

Method for performing two-dimensional graphic layer drawing and event handling by using Qt

The invention discloses a method for performing two-dimensional graphic layer drawing and event handling by using Qt. The method extracts out different basic graphic drawing conditions and combines with gesture operation, and the drawing process is simplified. State management is conducted on the drawn graphic layer. When multiple graphics having overlapped zones are drawn, coordinate mapping is conducted on selection points firstly, conversion from a global coordinate system to a graphic layer internal coordinate system is achieved, then the selection points are reversely transmitted to graphic layers according to a queue creating sequence, different position relation judging algorithms are automatically called according to the types of the graphic layers, and finally state switching is achieved. In addition, state tracking conducted on produced system events is supported, inter-layer transfer of the produced events is performed, whether the events are needed to be processed or not is judged by the graphic layers till the events are processed or neglected, and state tracking is completed at the moment. The problems of the complicated Qt two-dimensional graphic layer drawing process and non-penetrating event propagation are effectively solved by adopting the method.
Owner:南京仁谷防务科技有限公司

Propagation influence evaluation method for comprehensively calculating events

The invention discloses a propagation influence evaluation method for comprehensively calculating events, which comprises the following steps of: S1, event data acquisition: firstly, acquiring data related to a specific event in a social media website by using the website of social media and taking a keyword of the specific event as query content, and counting the acquired related data; the invention relates to the technical field of internet propagation. According to the propagation influence evaluation method for the comprehensive calculation event, the user data of which the like number andthe forwarding number exceed the threshold values are independently classified, the event data of which the historical like number and the historical forwarding number are calculated by utilizing theuser data of which the like number and the forwarding number exceed the threshold values, and statistical post-evaluation is carried out in cooperation with the user data; according to the method, malicious assessed user data can be effectively eliminated, the spreading influence of the event can be assessed by comprehensively calculating the event, the basis and reference of hotspot event assessment are provided, and the accuracy of the assessment method for comprehensively calculating the spreading influence of the event is greatly improved.
Owner:北京宏博知微科技有限公司

Cross-platform dissemination trend evaluation and grading method based on specific events

The invention relates to a cross-platform dissemination trend evaluation and grading method based on specific events, and belongs to the field of network information. The cross-platform disseminationtrend evaluation and grading method based on the specific event specifically comprises four functional modules, namely an original network element detection module, a topic propagation calculation module of the specific event, a grade evaluation and threat analysis module of topic dissemination model parameters, and a task scheduling and optimization module. The problem that a dissemination trendevaluation and grading method of events is not considered in the prior art is solved, a quantitative evaluation method for specific event dissemination situations and a grading means with discrimination are provided, an information system framework is established, and cross-platform dissemination trend evaluation and grading of the specific events are realized. The subsequent monitoring work is guided according to the cross-platform dissemination trend evaluation of the specific events, so that the judgment capability on the emergency or influence degree of event dissemination is effectively improved, and the actual work is guided.
Owner:NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT

Social media network event propagation key time prediction method, system, and medium

The invention belongs to the technical field of online information propagation prediction, and discloses a social media network event propagation key time prediction method, a system, and a medium. The method comprises the steps: carrying out the classification according to different time sequence features of social media network event online information; carrying out smoothing processing on the popularity time sequence with too strong volatility by adopting a Hort linear trend method; recognizing a time interval in which a key node propagated by the preprocessed social media network event occurs; carrying out time window division on the preprocessed time series data, and extracting time series, fluctuation and text emotion features based on online information data; constructing a prediction model training sample, and training a prediction model by adopting an XGBoost algorithm according to the training sample and the number of future time windows; and predicting the occurrence time ofthe key nodes in the event propagation process of the social media network by adopting the trained model. The method can effectively predict the occurrence time of the key node in the event propagation process of the social media network.
Owner:XIDIAN UNIV +1

Method, device and equipment for simulating network event propagation

The invention provides a simulation method, device and equipment for network event propagation, and relates to the technical field of computers, and the method comprises the steps: obtaining a networkevent and the attribute of the network event; Wherein the attributes at least comprise one of the following attributes: time, type or theme; Obtaining the node attribute of the current node, and calculating emotion attitude information according to the attribute and the node attribute of the network event and the historical emotion attitude information of the previous node; Determining emotionalbias information of the current node to the network event according to the emotional attitude information; Wherein the emotion deviation information is any one of the following information: support, anti-alignment or neutrality; If the emotion deviation information is supported or inversely aligned, the network event is propagated to an adjacent node; And if the emotion deviation information is neutral, ending the propagation of the network event at the current node. According to the method, the emotional attitude information is calculated, so that the accuracy of information propagation process simulation is improved, and the method is more suitable for practical application.
Owner:PEKING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products