Integrating AI in Human-Human Collaborative Ideation (original) (raw)
Related papers
Proceedings of the ACM on Human-Computer Interaction, 2020
Professional designers create mood boards to explore, visualize, and communicate hard-to-express ideas. We present ImageCascade, an intelligent, collaborative ideation tool that combines individual and shared work spaces, as well as collaboration with multiple forms of intelligent agents. In the collection phase, ImageCascade offers fluid transitions between serendipitous discovery of curated images via ImageCascade, combined text- and image-based Semantic search, and intelligent AI suggestions for finding new images. For later composition and reflection, ImageCascade provides semantic labels, generated color palettes, and multiple tag clouds to help communicate the intent of the mood board. A study of nine professional designers revealed nuances in designers' preferences for designer-led, system-led, and mixed-initiative approaches that evolve throughout the design process. We discuss the challenges in creating effective human-computer partnerships for creative activities, and ...
Human-AI Synergy in Creativity and Innovation
Artificial Intelligence - Emerging Trends and Applications, 2018
In order to maximize creative behavior, humans and computers need to collaborate in a manner that will leverage the strengths of both. A 2017 mathematical proof shows two limits to how innovative a computer can be. Humans can help counteract these demonstrated limits. Humans possess many mental blind spots to innovating (e.g., functional fixedness, design fixation, analogy blindness, etc.), and particular algorithms can help counteract these shortcomings. Further, since humans produce the corpora used by AI technology, human blind spots to innovation are implicit within the text processed by AI technology. Known algorithms that query humans in particular ways can effectively counter these text-based blind spots. Working together, a human-computer partnership can achieve higher degrees of innovation than either working alone. To become an effective partnership, however, a special interface is needed that is both human-and computer-friendly. This interface called BrainSwarming possesses a linguistic component, which is a formal grammar that is also natural for humans to use and a visual component that is easily represented by standard data structures. Further, the interface breaks down innovative problem solving into its essential components: a goal, sub-goals, resources, features, interactions, and effects. The resulting human-AI synergy has the potential to achieve innovative breakthroughs that either partner working alone may never achieve.
AI in design idea development: A workshop on creativity and human-AI collaboration
Proceedings of DRS
In a fast-paced society, AI systems can prove to be reliable teammates alongside human agents during the early stages of the design process, capable of helping to manage the increasing complexity of projects. Therefore, the introduction of AI systems into the design process is analysed according to the implications on the designer's creativity and the kind of human-AI collaboration that is established, highlighting trust balance and the new role played by the designer. The main aspects covered by the study were tested in a workshop, in which continuous and discontinuous human-AI collaboration were compared. In the case of continuous collaboration, the results show that AI assumed the role of a bossy groupmate, leading to an AI-driven creative process. In the second case, AI took the role of an expert capable of generating variance outside the team, leading to a human-driven creative process.
Brainstorming Will Never Be the Same Again—A Human Group Supported by Artificial Intelligence
Machine Learning and Knowledge Extraction
A modification of the brainstorming process by the application of artificial intelligence (AI) was proposed. Here, we describe the design of the software system “kresilnik”, which enables hybrid work between a human group and AI. The proposed system integrates the Open AI-GPT-3.5–turbo model with the server side providing the results to clients. The proposed architecture provides the possibility to not only generate ideas but also categorize them and set priorities. With the developed prototype, 760 ideas were generated on the topic of the design of the Gorenjska region’s development plan with eight different temperatures with the OpenAI-GPT-3.5-turbo algorithm. For the set of generated ideas, the entropy was determined, as well as the time needed for their generation. The distributions of the entropy of the ideas generated by the human-generated and the AI-generated sets of ideas of the OpenAI-GPT-3.5–turbo algorithm at different temperatures are provided in the form of histograms....
Facilitating Creativity in Collaborative Work with Computational Intelligence Software
IEEE Computational Intelligence Magazine, 2016
The use of computational intelligence for leveraging social creativity is a relatively new approach that allows organizations to find creative solutions to complex problems in which the interaction between stakeholders is crucial. The creative solutions that come from joint thinking-from the combined knowledge and abilities of people with diverse perspectivescontrast with traditional views of creativity that focus primarily on the individual as the main contributor of creativity. In an effort to support social creativity in organizations, in this paper we present computational intelligence software tools for that aim and an architecture for creating software mashups based on the concept of affinity space. The affinity space defines a digital setting to facilitate specific scenarios in collaborative business environments. The solution presented includes a set of free and open source software tools ranging from newly developed brainstorming applications to an expertise recommender for enhancing social creativity in the enterprise. The current paper addresses software design issues and presents reflections on the research work undertaken in the COLLAGE project between 2012 and 2015.
Supermind Ideator: Exploring generative AI to support creative problem-solving
arXiv (Cornell University), 2023
Previous efforts to support creative problem-solving have included (a) techniques (such as brainstorming and design thinking) to stimulate creative ideas, and (b) software tools to record and share these ideas. Now, generative AI technologies can suggest new ideas that might never have occurred to the users, and users can then select from these ideas or use them to stimulate even more ideas. Here, we describe such a system, Supermind Ideator. The system uses a large language model (GPT 3.5) and adds prompting, fine tuning, and a user interface specifically designed to help people use creative problem-solving techniques. Some of these techniques can be applied to any problem; others are specifically intended to help generate innovative ideas about how to design groups of people and/or computers ("superminds"). We also describe our early experiences with using this system and suggest ways it could be extended to support additional techniques for other specific problem-solving domains.
A Multi Agent System to manage ideas during Collaborative Creativity Workshops
5th International Conference on Future Computer and Communication, Phuket, Thailand , 2013
During creativity workshops, participants and creativity quizmasters work together in a collaborative way to generate new ideas. They will follow the creativity process based on different phases: discover the topic, apply the creativity methods, generate ideas, formalize ideas, share and evaluate their ideas and select innovative ideas. Up to now, the creativity workshops use simple tools like paperboards, post-its or idea sheets to capture their ideas. With such tools they don’t have the possibility to evaluate, compare, share and select their ideas. In this paper we describe the architecture of a multi agent system called CIMAS (Creativity Ideas Managed by Agent Systems) which helps the participants in a creativity workshop to generate, capture, collect and select their ideas.