Abnormal transaction identification method based on multi-dimensional reputation management of multiple transaction objects

Abstract

The invention discloses an abnormal transaction identification method based on multi-transaction object multi-dimensional reputation management. Abnormal behavior characteristics of multiple transaction objects (multiple clients and alliance nodes) in the intelligent contract transaction are extracted respectively; the multi-dimensional reputation value of each transaction object is comprehensively evaluated by quantifying and modeling the behavior characteristics of the multiple transaction objects, so that each abnormal transaction object is effectively monitored, the abnormal contract is further identified according to the abnormal transaction object in the intelligent contract transaction, and the accuracy is relatively high. The method comprises the following steps: firstly, respectively extracting abnormal behavior characteristics of multiple alliance nodes and multiple clients, then quantifying and modeling the multi-behavior characteristics by using a random petri network, andcomprehensively monitoring each abnormal transaction object through multi-dimensional reputation management and fuzzy logic; and finally, effectively identifying whether the transaction is abnormal according to each abnormal transaction object in the transaction process, so that the transaction reliability is improved.

Description

technical field [0001] The invention belongs to the transaction identification technology based on the alliance chain, and in particular relates to an abnormal transaction identification method based on the multi-dimensional reputation management of multiple transaction objects. Background technique [0002] A smart contract is a quantitative transaction agreement that executes electronically on actual contract terms. The overall goal of smart contracts is to satisfy common contractual conditions (such as payment terms, liens, confidentiality, and enforcement) while minimizing reliance on trusted intermediaries. Smart contracts have been applied in many fields such as electronic voting and supply chain management, and have broad prospects. [0003] However, in the smart contract transactions of distributed sub-centers, due to the lack of an effective supervision mechanism, it is easy to breed attackers or illegal transaction objects, posing a threat to system security. Eff...

AI Technical Summary

Problems solved by technology

Deep learning can use empirical data to monitor abnormal behavior, but it requires a large number of training sets, the training cost is large and there are hyperparameters

Images