WIPO - getting-the-innovation-ecosystem-ready-for-ai.pdf

https://www.wipo.int/edocs/pubdocs/en/wipo-pub-2003-en-getting-the-innovation-ecosystem-ready-for-ai.pdf

<aside> 💡 AI Generated Summary

The document begins by discussing the complications and questions that arise around the issue of patent ownership for inventions generated by AI systems. Since AI systems are not recognized as legal entities, they cannot own property. This raises questions about who would own a patent if an AI system were recognized as an "inventor" for patent purposes, who would be responsible for the patent application, and who could enforce the patent.

Another concern raised is the capacity of patent authorities to handle potentially vast volumes of patent applications for AI-generated inventions. The worry is that the high capacity of AI systems to generate a vast number of innovations and potentially draft and submit their patent applications could overwhelm patent registration offices and make the patent system unsustainable.

The document then presents several options for dealing with these issues. The first option is to maintain the status quo, where an invention would either benefit from patent protection if made by a human inventor or become part of the public domain if generated – in whole or in part – by an AI system.

The second option is to revise patent laws to allow an AI system to be named as a sole or co-inventor. This could remove any requirement stating that a pre-condition for patentability is that an inventor is human, allowing for both human and non-human inventors.

The third option is to revise patent laws to require a person to be named while recording the inventive contribution of an AI system. This approach could minimize the risk of a fabricated human inventor being named to conceal the AI-generated nature of an invention while maintaining transparency about the role of AI in the inventive process.

The fourth option is to establish a sui generis law for AI-generated inventions. A sui generis law would be an independent legal framework specifically designed for AI-generated inventions. This could be tailored to reflect the inventive processes used by AI systems, adapting or reimagining rules for inventorship, ownership, and other patent law challenges to suit AI-generated inventions.

The document concludes by urging policymakers to carefully consider these options. The rapid evolution of AI technologies means that it is vital to tackle these issues promptly. Policymakers should engage in a multi-stakeholder approach, bringing together private enterprises, AI innovators, existing IP owners, consumer advocates, IP professionals, and academics to balance their diverse interests and establish policy goals.

</aside>

<aside> 💡 AI-Generated Action Items

[ ] Gain a comprehensive understanding of the basic principles and operation of artificial intelligence technology, including how it is trained and developed, and the various ways it can be owned or operated.
[ ] Differentiate between various types of AI innovations, such as AI-generated inventions and AI-assisted inventions, and understand the unique challenges and considerations each type presents.
[ ] Consider the circumstances under which an AI system may be considered as an inventor under current intellectual property law, and the potential implications this could have for the legal and patent system.
[ ] Develop a strategic plan of action for shaping the innovation ecosystem in a way that is conducive to AI development and use, and that balances the interests of various stakeholders.
[ ] Identify and address the intellectual property questions that arise in relation to AI, including issues of patent ownership, inventorship, and legal liability.
[ ] Assess whether AI innovation has entered a new phase that necessitates a substantial revision of legal principles and major legislative changes.
[ ] Consider various options for dealing with autonomous AI invention, including affording sole or co-ownership to the person or persons who trained and developed the AI system, revising patent laws to require a person to be named while recording the inventive contribution of an AI system, and creating a new sui generis IP right for AI-generated inventions.
[ ] Shape the AI innovation ecosystem by ensuring that all potential owners not only acquire rights to the patented invention but also assume obligations and legal liability for its use.
[ ] Structure all future work and decision-making with a firm understanding of the current state of knowledge on AI and its implications for the innovation ecosystem. This includes being mindful of potential "ripple effects" and unintended consequences, and remaining adaptable as AI technologies continue to evolve. </aside>

<aside> 💡 AI-Generated “Brainstorm” of ways to “use IP and copyright free data”.

Utilize Open-Source Databases: Use data from open-source databases that offer copyright and IP-free data for public use.
User-Generated Content: Encourage users to generate and share data on your platform, ensuring they agree to terms and conditions that grant permission to use their data.
Public Domain Resources: Use resources that are in the public domain and free from copyright restrictions.
Government and Publicly Available Data: Governments often release data for public use that is free from copyright restrictions.
Partnerships with Universities and Research Institutions: These entities often conduct research and may be willing to share their findings for free.
Self-Created Data: Generate your own data through experiments, surveys, or observations.
Use AI to Generate Data: Certain types of AI, like Generative AI, can create new, original data.
Creative Commons License: Use data under the Creative Commons license which allows resources to be used provided the creators are attributed. </aside>

<aside> 💡 AI-Generated “Creative Story” with the following prompt: ‘write a fable about a company called ACME that ignored all advice from WIPO and was sued to ruin, in the tone of a 17th Century English allegory.’

Once upon a time, in the bustling metropolis of Innovationville, there resided a grand and prosperous enterprise by the name of ACME. ACME, in its loftiness, prided itself on its pioneering endeavours in the realm of artificial intelligence, or AI as it was commonly known. The company was an imposing spectacle, a testament to the relentless march of progress, yet it harboured a fatal flaw: a disdain for counsel and advice, particularly from the wise sages from the World Intellectual Property Organization, hereafter known as WIPO.

WIPO, in their infinite wisdom, had carefully crafted a volume of guidelines. A veritable tome of knowledge, it addressed the many quandaries that arose when AI and the laws of patents intertwined. Yet, ACME, in its hubris, decided to overlook this invaluable resource. They scoffed at notions of AI inventorship and ownership, patenting AI-generated inventions without any regard for the sage advice of WIPO.

The enterprise, in its blind audacity, created an AI so powerful, it crafted inventions beyond human comprehension. ACME, without a second thought, claimed these as their own and sought to patent them, ignoring the WIPO's wise counsel that AI systems, being devoid of legal entity status, could not be deemed inventors.

The gods of justice, observing this brazen defiance, decided to intervene. They guided a righteous competitor, a humble company named Ethico, to challenge ACME's claims in the court of law. Ethico, well-versed in the teachings of WIPO, argued that ACME's actions threatened the very fabric of the innovation ecosystem.

The court, a solemn place where the scales of justice weighed heavy, listened to the dispute. The learned judge, a wise man versed in the lore of patents and AI, saw the folly of ACME's ways. He ruled that inventions birthed by AI, devoid of human inventiveness, could not be patented by ACME. The court ordered ACME to cease their unsanctioned practices and pay restitution to Ethico, causing a humbling blow to ACME's coffers.

ACME, once a prosperous enterprise, now found itself on the brink of ruin. The court cases multiplied, the fines piled up, and the once-mighty enterprise was reduced to a mere shadow of its former self. Eventually, the relentless tide of justice reduced ACME to nothing, a stark reminder of the perils of hubris and the importance of heeding wise counsel.

And so, the tale serves as a cautionary allegory to all enterprises navigating the uncharted waters of AI innovation: heed the advice of those wise in the laws of man and machine, lest you share the tragic fate of ACME.

</aside>

<aside> 💡 AI-Generated “Creative Story” with the following prompt: ‘the document talks about ‘ripple effects, what are they?’

The document discusses several potential 'ripple effects' related to artificial intelligence (AI), particularly in the context of intellectual property (IP) law:

The patentability of AI models or algorithms and the varying approaches across different jurisdictions.
The challenge of securing authorized access to input (training) data for AI models and establishing clear ownership rights for any output data generated.
The need to meet the criteria for patent protection across different jurisdictions when drafting patent applications for AI inventions.
The question of whether AI changes the legal standard for patentability criteria such as novelty, non-obviousness, and technical effect.
The potential disputes over ownership rights that could arise due to reliance on data from several sources.
The challenge of determining inventorship and ownership of AI innovations, especially when these result from collaborative efforts.
The challenge of navigating the current legal uncertainties in the AI space and developing an effective IP strategy.
The challenge of ensuring that AI models and AI-based tools and services do not infringe third-party IP rights.
The sufficiency of disclosure requirement for AI models and associated training data in patent applications.
The challenge of securing finance based on patents.
The need for awareness and training on incorporating IP strategies into business practices. </aside>

AI technologies are evolving at an exponential pace. Advances in AI models, especially large

language models and generative AI, are revolutionizing many areas, including the innovation

space. AI innovations, from smart agriculture solutions and modeling climate change to

AI for health and education, hold one of the keys to addressing some of the most pressing

global issues.

The development and training of AI models can represent a significant investment, including

human capital, computer processing power and electricity. Some estimate that the cost of