Recurrent neural network(RNN) has achieved remarkable performances in complex reasoning on knowledge bases, which usually takes as inputs vector embeddings of relations along a path between an entity ...pair. However, it is insufficient to extract local correlations of a path due to RNN is better at capturing global sequential information of a path. In this paper, we take full advantages of convolutional neural network that can effectively extract local features, and propose a convolutional-based RNN architecture denoted as C-RNN to perform reasoning. C-RNN first utilizes CNN to extract local high-level correlation features of a path, and then feeds the correlation features into recurrent neural network to model the path representation. Our C-RNN architecture is adaptable to obtain not only local features but also global sequential features of a path. Based on C-RNN architecture, we devise two models, the unidirectional C-RNN and bidirectional C-RNN. We empirically evaluate them on a large-scale FreeBase+ClueWeb prediction task. Experimental results show that C-RNN models achieve state-of-the-art predictive performance.
Purpose Current open innovation (OI) and external knowledge search (EKS) research primarily shows a positive linear relationship between EKS and innovation at an individual level. However, ...organizational scholarship argues that excessive EKS may harm innovation. This study combines the knowledge-based view (KBV) and attention-based view (ABV) to articulate a nonlinear theory of EKS and innovation at the individual level. Design/methodology/approach The authors constructed a multi-sourced dataset covering 59,798 USA pharmaceutical patents spanning from 1975 to 2014 and employed negative binomial fixed-effect models to examine theoretical hypotheses. Findings We find a significant concave curvilinear relationship between EKS and innovation quantity as well as innovation quality at an individual level. An individual’s knowledge breadth and depth moderate the relationship between EKS and innovation, such that the threshold at which EKS has diminishing returns for individual innovation is higher for inventors with a broad range of knowledge and those with deeper expertise in the domain where they are innovating. Research limitations/implications Managers should guide inventors toward a moderate investment of time and effort in EKS and should caution against over searching. Besides, managers should recognize that an inventor’s capacity for EKS is determined in part by their breadth of knowledge across various domains as well as the depth of knowledge they have in the knowledge domain where they are innovating. Practical implications We provide both parties with a clearer understanding of when EKS can begin to deteriorate an individual’s innovation performance why that deterioration occurs, and we also highlight two individual-level knowledge characteristics to take into consideration when deciding when to cease the EKS process. Social implications This study provides a novel holistic understanding of OI and knowledge management for policymakers and organizations to nourish innovation dynamism and make the best of knowledge stocks in the community, which in turn will create endless power for sustainable social change and inclusive development. Originality/value This study contributes to OI theory by highlighting the non-linear nature of the relationship between EKS and innovation on an individual level. This represents a fundamental shift in theory on EKS and individual innovation by suggesting a major rethinking of how the two concepts relate, revealing the dark side of EKS in knowledge management if inventors engage in excessive EKS. Likewise, our study’s incorporation of the ABV informs KBV scholarship by highlighting the role of the limited attentional capacity of individuals in firm knowledge management.
Embodied AI is one of the most popular studies in artificial intelligence and robotics, which can effectively improve the intelligence of real-world agents (i.e. robots) serving human beings. Scene ...knowledge is important for an agent to understand the surroundings and make correct decisions in the varied open world. Currently, knowledge base for embodied tasks is missing and most existing work use general knowledge base or pre-trained models to enhance the intelligence of an agent. For conventional knowledge base, it is sparse, insufficient in capacity and cost in data collection. For pre-trained models, they face the uncertainty of knowledge and hard maintenance. To overcome the challenges of scene knowledge, we propose a scene-driven multimodal knowledge graph (Scene-MMKG) construction method combining conventional knowledge engineering and large language models. A unified scene knowledge injection framework is introduced for knowledge representation. To evaluate the advantages of our proposed method, we instantiate Scene-MMKG considering typical indoor robotic functionalities ( Manip ulation and Mob ility), named ManipMob-MMKG . Comparisons in characteristics indicate our instantiated ManipMob-MMKG has broad superiority on data-collection efficiency and knowledge quality. Experimental results on typical embodied tasks show that knowledge-enhanced methods using our instantiated ManipMob-MMKG can improve the performance obviously without re-designing model structures complexly.
Temporal Knowledge Graph (TKG) reasoning involves predicting future facts based on historical information by learning correlations between entities and relations. Recently, many models have been ...proposed for the TKG reasoning task. However, most existing models cannot efficiently utilize historical information, which can be summarized in two aspects: 1) Many models only consider the historical information in a fixed time range, resulting in a lack of useful information; 2) some models use all the historical facts, thus some noise or invalid facts are introduced during reasoning. In this regard, we propose a novel TKG reasoning model with dynamic memory enhancement (DyMemR). Inspired by human memory, we introduce memory capacity, memory loss, and repetition stimulation to design a human-like memory pool that could remember potentially useful historical facts. To fully leverage the memory pool, we utilize a two-stage training strategy. The first stage is guided by the memory-based encoding module which learns embeddings from memory-based subgraphs generated through the memory pool. The second stage is the memory-based scoring module that emphasizes the historical facts in the memory pool. Finally, we extensively validate the superiority of DyMemR against various state-of-the-art baselines.
•OHCs enable physicians to share both general and specific health knowledge.•General knowledge-sharing is positively associated with specific knowledge-sharing through online reputation.•Patient ...involvement strengthens the effects of general knowledge-sharing on online reputation and specific knowledge-sharing.•General knowledge-sharing can be an efficient approach for physicians to recruiting patients.
Although the sharing of knowledge in online health communities (OHCs) has been explored in recent years, little research has been done to explore the relationship between general and specific knowledge-sharing. Based on the literature on knowledge-sharing in OHCs, this study developed a research model to explore how physicians’ general knowledge-sharing behaviors influence their specific knowledge-sharing activities via their online reputations and the contingent role of patient involvement in OHCs. The research model was tested using objective data from a leading OHC in China. The results show that general knowledge-sharing is positively associated with specific knowledge-sharing, and this effect is exerted through online reputation. Moreover, patient involvement strengthens the relationship between general and specific knowledge-sharing as well as the relationship between online reputation and specific knowledge-sharing. By uncovering the relationship between general and specific knowledge-sharing, the research findings extend the understanding of knowledge-sharing and patient recruiting in OHCs and provide significant practical implications for practitioners.
E-learners face a large amount of fragmented learning content during e-learning. How to extract and organize this learning content is the key to achieving the established learning target, especially ...for non-experts. Reasonably arranging the order of the learning objects to generate a well-defined learning path can help the e-learner complete the learning target efficiently and systematically. Currently, knowledge-graph-based learning path recommendation algorithms are attracting the attention of researchers in this field. However, these methods only connect learning objects using single relationships, which cannot generate diverse learning paths to satisfy different learning needs in practice. To overcome this challenge, this paper proposes a learning path recommendation model based on a multidimensional knowledge graph framework. The main contributions of this paper are as follows. Firstly, we have designed a multidimensional knowledge graph framework that separately stores learning objects organized in several classes. Then, we have proposed six main semantic relationships between learning objects in the knowledge graph. Secondly, a learning path recommendation model is designed for satisfying different learning needs based on the multidimensional knowledge graph framework, which can generate and recommend customized learning paths according to the e-learner’s target learning object. The experiment results indicate that the proposed model can generate and recommend qualified personalized learning paths to improve the learning experiences of e-learners.
Purpose
This study aims to investigate the key roles of human and relational capital in the export orientation and competitiveness of knowledge-intensive cooperative companies. It is also aimed to ...examine the moderating role of marketing knowledge capabilities.
Design/methodology/approach
Data from 552 managers at 86 companies, selected from knowledge-intensive export cooperatives, were analyzed with structural equation modeling with the partial least squares approach.
Findings
Results indicate that both human and relational capital exert considerable effects on competitiveness. Export orientation was a driving factor for cooperatives’ competitiveness. Human and relational capital fostered the effects of export orientation on competitiveness. Moreover, marketing knowledge capabilities were found to moderate the relationships between human and relational capital and export orientation, as well as between export orientation and competitiveness.
Originality/value
By highlighting the role of human capital and relational capital in export orientation and competitiveness, this study offers an analysis of important managerial processes within cooperative companies, which have not been sufficiently addressed in previous research. This research also demonstrated the moderating role of marketing knowledge capabilities in strengthening relationships between human and relational capital and export orientation, as well as between export orientation and competitiveness, which has been neglected in previous studies. These findings provide academics and practitioners with a new framework for examining the relationships between these constructs, which will enable them to establish strategies for achieving a competitive advantage.
Knowledge Management Models: A Summative Review Sensuse, Dana Indra; Cahyaningsih, Elin
International journal of information systems in the service sector,
01/2018, Letnik:
10, Številka:
1
Journal Article
Recenzirano
Knowledge and knowledge management started to be an option of organizational strategic step for reach organizational objectives and goals. Knowledge management believed to resolve organizational ...problem in managing their organizational and individual knowledge. Implementation of knowledge management (KM) has received increased interests. This paper aims to discuss KM models based on KM related definitions, concepts, functions, activities and approaches. Literatures on knowledge management models were collected from a number of sources. Each document then was analyzed and categorized in a certain group. The study shows that there are four categories of KM models i.e.: process, strategy, knowledge type, and maturity based knowledge management models.
Purpose
Inspired by the theory of planned behavior, the purpose of this paper is to examine the impact of the big five personality (BFP) traits (openness, conscientiousness, extraversion, ...agreeableness, and neuroticism) on four aspects of individuals’ knowledge management (KM) behaviors: knowledge acquisition, knowledge storage, knowledge sharing, and knowledge application.
Design/methodology/approach
A survey-based approach was used to collect data from 221 employees from five knowledge-intensive firms.
Findings
The partial least square analyses confirmed a positive effect of two personality traits, openness and conscientiousness, on knowledge acquisition as well as knowledge application behavior. In addition, the positive effects of extraversion and conscientiousness traits on knowledge storage behavior were confirmed. The findings also revealed that agreeableness and openness traits positively relate to knowledge sharing behavior. Finally, neuroticism had a negative effect on knowledge acquisition and application behavior.
Practical implications
This study suggests that organizations need to incorporate employees’ personality into the design and implementation of their KM systems. The findings provide managers with insight into the course of personnel selection and retention to facilitate KM behaviors in organizations.
Originality/value
Little is known about the relationship between the BFP traits and four aspects of KM behaviors at the individual level. The present study has contributed to the existing body of literature through clarifying how personality traits relate to four dimensions of individuals’ KM behaviors.