Search

In the era of artificial intelligence, trained neural network models have become new products of the information age. Most of machine learning strategies currently used to train neural networks are supervised learning, and thus, training data with labels become new intellectual capital (IC). Due to commercial confidentiality, data cannot be shared directly among information companies, which in turn prevents them from integrating resources to train better models. We need a framework that encrypts neural network models trained on the data and provides certain model exchange rewards that can be used to incentivize data sharing and to protect intellectual property (IP) and privacy of intellectual capital. Currently, federated learning provides a framework to train neural networks without compromising privacy, while block chain–based trading systems can attract other participants through a reward mechanism set by smart contracts. In this paper, we propose a block chain–based federated learning algorithm that enables reliable data sharing while protecting data from leakage, and design smart contracts based on the incentive mechanism of Shapley Values to reward data providers. We design a platform for managing IC by combining federated learning and block chain called Federated Learning Intellectual Capital Platform (FedLICP). [ABSTRACT FROM AUTHOR]

Currently, power generators are facing an imperfectly competitive power market with relatively limited information, and they can increase their own economic returns by raising their quotations through game theory, which leads to an inflated price in the wholesale power market. In this paper, we propose a bidding application for the wholesale power market called Federated Learning Power Quotation System (FedLPQS), which combines federated learning and blockchain to consider the characteristics of the future power trading market of "Liberalizing both ends". FedLPQS using federated learning aggregates cost data of each power plant to achieve a certain degree of transparency and records the data in a blockchain platform based on the consortium chain to reduce the price of power traded in the wholesale power market. [ABSTRACT FROM AUTHOR]

With the rapid development of the Internet, online music has become a new trend. The low cost of access and fast spread speed greatly enriches people's spiritual life, but it also poses great challenges to the protection of intellectual property rights. Nowadays, although the intellectual property rights of music works have been better valued and protected, there are still some problems that limit the development of the music industry and affect the users' experience. For example, the copyrights of different music works may be exclusively represented by different companies, resulting in limited choices for users and vicious competition among music operating companies, which affects the users' experience and is not conducive to the long-term development of the music industry. In order to solve the above problems, we present a decentralized music copyright operation management system based on Blockchain technology. By using the Blockchain's shared ledger mechanism and smart contracts as the basic framework of the Ethereum platform, we realize decentralized music copyright management. The system not only protects copyright better, but also coordinates the interests of creators, copyright owners, operators and users, which is beneficial to the further development of the music industry, and creates more value and better experience for users. [ABSTRACT FROM AUTHOR]