Knowledge retrieval

Abstract: In a knowledge-intensive engineering product design process, case retrieval based on partial problem descriptions (PPDs) becomes more important than the general case retrieval in normal conditions for product design and acts as a crucial role in decision-making. Within the consultation mechanism, similarity knowledge can be acquired expediently and effectively in the product case base described with partial and incomplete information and knowledge. At one time, PPDs can interact with domain knowledge in an appropriate manner to serve the acquisition of similarity knowledge based on consultation (SKC) and case retrieval based on PPDs effectively. So, the consultation approach to case knowledge retrieval is provided to support engineering product design in this paper and the consultation hierarchy is analyzed and discussed from the viewpoint of knowledge transfer. The similarity transformation matrix for similarity measures is presented to handle the relationship between the partial unknown features and the related features, and the determination of weights found on the semantic knowledge of the design domain. As the complementarities of the domain knowledge, explanation knowledge is utilized to explain design requirements for case knowledge reuse and to assist the acquisition of similarity knowledge. Finally, the PPD of an oil pump design is employed to demonstrate the above viewpoints.

Abstract: PROBLEM TO BE SOLVED: To provide retrieval environment which is adapted to a user by dynamically updating link information according to the access process of the user. SOLUTION: When one node is selected in a global knowledge base 251 or local knowledge base 252, a retrieval part 24 regards a word specifying this node as a retrieval key and retrieves a node which includes this word as a word specifying itself in the other knowledge network and when the retrieval part 24 retrieves the node including the word as the word specifying itself in the other knowledge network, a knowledge base management part 22 temporarily links the selected nodes with the retrieved node. Consequently, links between nodes can be updated dynamically according to the processes of access to the respective knowledge networks by respective users and knowledge retrieval environment suitable to the users can be provided.

Abstract: Cloud manufacturing is a kind of knowledge intensive manufacturing mode, in which knowledge plays a key role. This paper presents the knowledge in cloud manufacturing from the perspective of knowledge management. The forms, characteristics and functions of knowledge in cloud manufacturing were analysed. The knowledge acquisition and retrieval in cloud manufacturing were studied respectively. The structure of knowledge management system for cloud manufacturing was designed and a prototype was developed. A case study was carried out to verify the proposed methods.

Abstract: We have developed a distributed DSS capable to working in a dynamic way. That is, when a domain of an organization needs a new kind of information, the system looks for this information. This system is based on the usage of mobile agents, which receive the user's queries and visit the appropriate DSS domains to gather the required information. The system itself must analyze where this information can be generated. To make this decision there is an intelligent agent (the Router) with a knowledge base (KB) where the information managed by each domain is represented. In this work, we present a strategy to obtain the initial data to be stored in the KB, a knowledge retrieval mechanism from the KB, and a learning mechanism so that the KB and the DSS operation can be continually improved. The proposed learning process is an interpretative case-based reasoning, which uses a set of rules to analyze the results of the information retrieval process and modifies the content of the router KB. Some examples are presented to illustrate the learning mechanism.