A Cognitive Assistant for Operators: AI-Powered Knowledge Sharing on Complex Systems

Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems

2023

Self Cite

Many industries are facing the challenge of how to capture workers' knowledge such that it can be shared, in particular tacit knowledge. The operation of complex systems such as a manufacturing line is knowledge-intensive, especially if the operator must frequently reconfgure it for diferent products. Considering the breadth and dynamic nature of this knowledge, existing solutions for sharing knowledge (e.g., word-of-mouth, issue reports, document creation, and decision support systems) are inefcient and/or resource-intensive. Conversational user interfaces are an efcient way to convey information that mimics the way humans share knowledge; however, we know little about how to design them specifcally for this purpose, especially regarding tacit knowledge. In this work, my main goal is to investigate how a cognitive assistant can be designed to facilitate (tacit) knowledge transfer between users of dynamic complex systems. I aim to achieve this by outlining the design requirements, challenges, and opportunities in factories; by collaboratively designing, implementing, and evaluating a cognitive assistant for sharing knowledge; studying the efects of design characteristics on aspects such as user experience; and fnally, creating a set of design guidelines. CCS CONCEPTS• Human-centered computing → Empirical studies in HCI; Interactive systems and tools; Natural language interfaces.

Section: Preliminary Resultsmentioning

confidence: 99%

The Human Factors of AI-Empowered Knowledge Sharing

Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems

2023

Self Cite

“…Cognitive assistants in manufacturing offer significant advantages, including centralized access to heterogeneous information systems, task delegation, and hands-and gaze-free interactions during work [37]. Moreover, cognitive assistants can be employed for on-the-job worker training [18] and for adjusting machine parameters in simulations [22].…”

Section: Literature Review 21 Cognitive Assistants and Their Applicat...mentioning

confidence: 99%

Harnessing Large Language Models for Cognitive Assistants in Factories

Proceedings of the 5th International Conference on Conversational User Interfaces

Foosherian²,

Wang

et al. 2023

Self Cite

As agile manufacturing expands and workforce mobility increases, the importance of efficient knowledge transfer among factory workers grows. Cognitive Assistants (CAs) with Large Language Models (LLMs), like GPT-3.5, can bridge knowledge gaps and improve worker performance in manufacturing settings. This study investigates the opportunities, risks, and user acceptance of LLM-powered CAs in two factory contexts: textile and detergent production. Several opportunities and risks are identified through a literature review, proof-of-concept implementation, and focus group sessions. Factory representatives raise concerns regarding data security, privacy, and the reliability of LLMs in high-stake environments. By following design guidelines regarding persistent memory, realtime data integration, security, privacy, and ethical concerns, LLMpowered CAs can become valuable assets in manufacturing settings and other industries. CCS CONCEPTS• Human-centered computing → Human computer interaction (HCI); Natural language interfaces; • Computing methodologies → Natural language generation; • Information systems → Users and interactive retrieval; • Applied computing → Industry and manufacturing.

“…The development of the IA for systematic refection was carried out in close collaboration with factory partners; It builds on several existing features such as collecting issue descriptions and providing recommendations as described in previous literature [20,21]. The development involved conducting semi-structured interviews, collecting requirements from workers and management, observation, user evaluations, and integrating the IA with the factory's IT systems.…”

Section: Systematic Reflection Supported By An Intelligent Assistant ...mentioning

confidence: 99%

“…Several IAs using a conversational interface have emerged in diferent research communities with other names (e.g., intelligent (personal) assistants, digital assistants, software robots, or chatbots). IAs can have signifcant benefts, such as central access to information systems and ubiquitous decision support [2,21,39]. Intelligent (robot) systems can support decision-making by analyzing shop foor data, identifying production issues, and evaluating operation performance [1,35].…”

Section: Introductionmentioning

confidence: 99%

“…Intelligent assistants (IA), a type of assistance system that implements artifcial intelligence to increase human task performance at work [25], are becoming increasingly popular in the home and at businesses. Whereas the most iconic IAs are consumer-facing (e.g., Alexa, Google Assistant, or customer service chatbots), they are increasingly being used in a professional setting (e.g., medical decision support or cognitive assistance on the shop foor (e.g., [21]). Some of the benefts that (voice-enabled) IAs provide include hand and gaze-free interaction, quickly accessing information, processing a large volume of information from their user (as natural language), and can help to visualize and analyze data in real-time.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Tacit Knowledge Elicitation for Shop-floor Workers with an Intelligent Assistant

Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems

Wang

Ruiz-Arenas

et al. 2023

Self Cite

Many industries face the challenge of capturing workers' knowledge to share it, particularly tacit knowledge. The operation of complex systems such as a manufacturing line is knowledge-intensive. Considering this knowledge's breadth and dynamic nature, existing knowledge-sharing solutions are inefcient and resource intensive. Conversational user interfaces are an efcient way to convey information that mimics how humans share knowledge; however, we know little about how to design them specifcally for knowledge sharing, especially regarding tacit knowledge. In this work, we present an intelligent assistant that we have developed to support the elicitation of tacit knowledge from workers through systematic refection. The system can interact with workers by voice or text and generate visualizations of shop foor data to support refective prompts. CCS CONCEPTS• Human-centered computing → Empirical studies in HCI; Interactive systems and tools; Natural language interfaces.