Social robot group detection method based on high-density subgraph detection

• Main Authors: QIN JIAWEN, DENG TING, SUN QINGYUN, JI CHENG, ZHAO TAO, LI JIANXIN, HUANG PENGFENG
• Format: Patent
• Language: Chinese; English
• Published: 08.12.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention realizes the social robot group detection method based on high-density subgraph detection. The method comprises the steps of firstly inputting social network graph content into a tensor construction module, converting a social relation network into a relation tensor, extracting text content features to calculate a repetition rate and similarity, then calculating a suspicious degree score, and finally calculating high-density sub-graph information. Obtaining a relation tensor constructed according to the social network, and inputting the relation tensor into a high-density subgraph mining module; and the high-density sub-graph mining module inputs a relation tensor, obtains a source user group from the high-density sub-graph, and finally detects a social robot group with high density in the social network. Through the above means, the method can detect social robot groups having abnormal cooperation behaviors in a short period in a social network, and observe abnormal cooperation behaviors among