论文标题
根据机器学习输出来衡量知识产权资产的独创性
Measuring the originality of intellectual property assets based on machine learning outputs
论文作者
论文摘要
原创性标准经常用于比较资产，尤其是评估知识产权（IP）权利的有效性，例如版权和设计权。在这项工作中，使用最大熵和惊人分析的概念，资产的原始性是根据该资产及其比较之间距离的函数提出的。也就是说，原创函数是根据与给定资产相关的惊喜来定义的。与通过类似静电对的粒子相比，可以合理地进行创意资产。这允许获得一个非常简单，适当的公式，其中资产的原始性将作为参考能量与赋予该资产的相互作用能量的比率。特别是，资产的原始性可以表示为两个平均距离的比率，即，从该资产与其比较的距离的谐波平均值除以唯一比较之间距离的谐波平均值。因此，由于无监督的机器学习技术或其他距离计算算法，可以简单地根据计算的距离来简单地估算诸如IP资产之类的对象的原创性。应用于各种类型的资产，包括表情符号，字体设计，绘画和新颖标题。
Originality criteria are frequently used to compare assets and, in particular, to assess the validity of intellectual property (IP) rights such as copyright and design rights. In this work, the originality of an asset is formulated as a function of the distances between this asset and its comparands, using concepts of maximum entropy and surprisal analysis. Namely, the originality function is defined according to the surprisal associated with a given asset. Creative assets can be justifiably compared to particles that repel each other via an electrostatic-like pair potential. This allows a very simple, suitably bounded formula to be obtained, in which the originality of an asset writes as the ratio of a reference energy to an interaction energy imparted to that asset. In particular, the originality of an asset can be expressed as a ratio of two average distances, i.e., the harmonic mean of the distances from this asset to its comparands divided by the harmonic mean of the distances between the sole comparands. Accordingly, the originality of objects such as IP assets can be simply estimated based on distances computed thanks to unsupervised machine learning techniques or other distance computation algorithms. Application is made to various types of assets, including emojis, typeface designs, paintings, and novel titles.
