Integrated evaluator extracted from infringement lawsuits using extension neural network accommodated to patent assessment

Abstract

This study aims at the basis of the patent law and proposes an integrated evaluator for patent assessment. The damage award of a patent-infringement lawsuit is deemed to be the legal value of the patent. Sixty five effective samples are extracted from 4289 patent-related lawsuits retrieved from the US district courts of Delaware, California and Texas. Seventeen indicators are summarised to describe quantitatively the dimensions of the patents. Nine extracted factors are generated from the 17 patent indicators by Factor Analysis. Extension neural network is applied to build the patent valuation model, wherein the extracted factors are the input variables and the damage award is the output variable. The patent valuation model is validated to be made feasible by error analysis. The integrated evaluator for patent is then established by transforming the output of the patent valuation model via the Z-score. The proposed integrated evaluator accommodated to the patent assessment to improve any existing financial approaches. It also contributed to the patent transaction, patent licensing, hypothecation of intangible assets, shareholding by patent-based technologies and venture capital, etc.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 12 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.