Jia Hao

Knowledge map-based method for domain knowledge browsing

Abstract The exponential growth of available information and the deployment of knowledge management systems delivers excessive information to the end users that they cannot manage at once. This problem has led to an increased emphasis on solutions to information overload. Searching and browsing are two methods to locate information. Many studies have focused on solving the information overload problem in the searching process, but the methods to alleviate information overload in browsing process have not been adequately studied. Hence, a method that addresses information overload in the browsing process is presented in this paper. The aim is to reduce the information overload during browsing domain knowledge for new knowledge users who have little understanding of the information. In this method, a knowledge map and social network analysis are utilized to navigate the knowledge users. Technologies first construct a knowledge map from text mining and the important knowledge that includes more information about the domain is then identified via social network analysis. Based on this process, the knowledge user can browse the domain knowledge starting from the important knowledge and navigate via the knowledge map. We applied the method to assist new knowledge users in browsing the Computer Numerical Control (CNC) domain knowledge base to validate the method. The results indicate that the method can identify the important knowledge at a highly acceptable level, the constructed knowledge map can efficiently navigate the knowledge users, and the information overload can be significantly decreased.

A Probability-Based Hybrid User Model for Recommendation System

With the rapid development of information communication technology, the available information or knowledge is exponentially increased, and this causes the well-known information overload phenomenon. This problem is more serious in product design corporations because over half of the valuable design time is consumed in knowledge acquisition, which highly extends the design cycle and weakens the competitiveness. Therefore, the recommender systems become very important in the domain of product domain. This research presents a probability-based hybrid user model, which is a combination of collaborative filtering and content-based filtering. This hybrid model utilizes user ratings and item topics or classes, which are available in the domain of product design, to predict the knowledge requirement. The comprehensive analysis of the experimental results shows that the proposed method gains better performance in most of the parameter settings. This work contributes a probability-based method to the community for implement recommender system when only user ratings and item topics are available.

A User-Oriented Design Knowledge Reuse Model

To promote the level of reusing the accumulated design knowledge in the company, we intend to develop a knowledge reuse model in this paper. First, the design knowledge is discussed, and a unified design knowledge model is proposed. Following that, we identify three design knowledge reuse patterns which contribute to the understanding of how designers reuse knowledge during the design process. Based on that, we propose a design knowledge reuse model. This model can provide design knowledge according to the design knowledge reuse patterns. The model also provides the ability to update itself according to the captured actions of the knowledge users. At last, the method is validated with a research cooperator on the hydropneumatic spring component.

A function-based computational method for design concept evaluation

Abstract Concept generation is an indispensable step of innovation design. However, the limited knowledge and design thinking fixation of designers often impede the generation of novel design concepts. Computational tools can be a necessary supplement for designers. They can generate a big number of design concepts based on an existing knowledge base. For filtering these design concepts, this work presents a computational measurement of novelty, feasibility and diversity based on 500,000 granted patents. First, about 1700 functional terms (terminologies) are mapped to high dimensional vectors (100 dimensional space) by word embedding technique. The resulted database is knowledge base-I (KB-I). Then, we adopt circular convolution to convert patents into high dimensional vectors. The resulted database is KB-II. Based on the two knowledge bases, the computational definitions of novelty, feasibility and diversity are developed. We conduct six experiments based on KB-II, a random dataset and a real product dataset, and the results show that these metrics can be used to roughly filter a big number of design concepts, and then expert-based method can be further used. This work provides a computational framework for measuring the novelty, feasibility and diversity of design concept.

Study on Ontology-Based Knowledge Integration

This paper firstly discussed the definition of knowledge integration in the field of product development and proposed the multidimensional knowledge integration model which could be the guidance during the implementation of knowledge integration. Subsequently the framework of knowledge integration is presented, three layer (the enterprise distributes resources layer, enterprise managed knowledge layer and product development process layer) in the framework are explanted respectively. The ontology is introduced to provide the semantic fundament for the framework. The structure of integrative ontology is studied and constructed with OWL(Ontology Web Language). The ontology plays an important role in knowledge organization and knowledge service and it’s the core part of the whole framework. At last a prototype system based on the previous techniques is developed and basically fulfills knowledge integration in product development process.

A Review of Tacit Knowledge: Current Situation and the Direction to Go

Currently, tacit knowledge has attracted increasing research attention. However, the theoretical foundation of tacit knowledge is still not well formulated, because the researches are very disperse. This work provides a review of the current researches. First, the definition of tacit knowledge is discussed by answering several questions. Next, tacit knowledge sharing, tacit knowledge quantization are identified as two research topics in the current research community. Following that, the technical progress of each topic is summarized and analyzed. Finally, we provide a thumbnail of the researches and identify three research consensuses to answer where we are. While, seven research directions are identified to answer where we shall go.

A brief introduction to tacit knowledge and the current research topics

Computational awareness (CA) is proposed to give awareness capability to a machine. For implementing CA, a direct way is to simulate human awareness. Since tacit knowledge is an important component for human awareness, this work tries to give a brief introduction of the current research topics. First, several consensuses that have been achieved are identified. Then we identify three research topics, including tacit knowledge sharing, tacit knowledge quantization and tacit knowledge generation. Finally, in an attempt to provide a mathematical definition, we present an abstract computational model of tacit knowledge. By this work, we hope to contribute to the research community by clarifying the state-of-the-art of tacit knowledge.

Study on cross-domain knowledge inspired innovation design

Nowadays, knowledge based innovation design has been an essential technique to enhance enterprises competitiveness. Nowadays, the main method to realize the innovation design is Structured Innovation (such as TRIZ) and Heuristic Innovation (such as biological inspired design). The former prefer to address specific issues through processes and tools, the latter is used to stimulate peoples creativity, but how to provide the right information to designers? The problem is complex and it has become a research hotspot. Therefore, this paper proposed a methodology which is used to find the useful information from cross domain knowledge and then recommend the information to designers. In detail, we collect and process different domain literatures first, and then represent the data in matrix models. Finally, K-means clustering analysis is used to detect outlier documents, which will be recommended to designers. At last, a JAVA system-product innovation design supporting system was developed to validate the methodology.

The Reuse Method of Design Knowledge Based on Knowledge Component

To speed up the pro duct design efficiency, product designers would like to utilize the previous design knowledge. This requires a systematic and structured way for design knowledge representation and reuse. A new method which is named knowledge component to make design knowledge reused conveniently is presented in this paper. Knowledge component is a virtual reuse model which has specific function. The internal structure and working principle of knowledge component are discussed; meanwhile the involved design knowledge was analyzed in detail. The design process of barrel chamber was taken as an example to illustrate the executing process of knowledge component. Testing result shows that this method is feasible in terms of increasing design efficiency and helps the designers reuse the existing knowledge rapidly.

A B/S-Based Multi-Server Framework for Knowledge Component Implementation

Knowledge reuse is of great significance for enterprises which rely mainly on new product development or design. For reusing knowledge, knowledge component is a feasible and efficient method. However, the implementation of knowledge component is still a new field to be researched. In this paper, a B/S-based multi-server framework to support knowledge component implementation was proposed. In the framework, a B/S-based knowledge component operating structure was introduced to make it easier for the product designers or developers to use the knowledge component. In order to reduce the computing time and alleviate the workload of the server-side, a multi-server mode was designed to separate the knowledge component operating process into three tiers (data tier, logic tier and computing tier). To improve the utilization of the limited computational resource, a real-time scheduling scheme was proposed to allocate the application software service to dynamic requests. Testing results proves that this framework is feasible and can help the designers reuse the existing knowledge rapidly. This framework will be significantly helpful to those enterprises interested in unlocking the potential of design knowledge reuse.