Abstract Face swiping is the action of registering facial recognition data with a biometric authentication application. Face swiping‐based medical services (FSMSs) is an emerging measurement technology underpinning modern intelligent medical services in China. In view of convenience in the delivery of medical services and the potential to reduce medical costs, FSMSs have become an important part of China's medical reform. However, modelling its eventual uses has not been fully explored in theory and practice, and this is hindering the take up of FSMSs in China. In this paper, we build an evolutionary game model to explore three stakeholders—policy makers, hospitals, and patients—and their dynamic interdependence of their decision‐making when adopting FSMS. Based on our game theoretic analysis, we develop a novel model to track the behaviour of these three stakeholders and analyse the corresponding payoff matrix to establish the replication dynamic equation (RDE) for the game. Further, we then use RDE to calculate the different stability points of players and determine the game's stable strategy. Finally, we validate the proposed model with a detailed simulation. Our observations may benefit not only FSMS participants but also several other forms of medical services and industries.

Abstract In China, Type 2 diabetes mellitus (T2DM) is increasingly affecting people's health. Although many risk factors related to T2DM have been researched, the association between social relationships and risk management of T2DM in China has not been fully researched. Therefore, we obtained 2,969 valid cases from the National Chinese Medicine Clinical Research Base‐Key Disease of Diabetes Mellitus Study to evaluate the role of social relationships in the risk management of T2DM. We first establish an indicators system of social relationship factors and then propose a comprehensive method that integrates subjective (analytical network process) and objective (entropy weight method) evaluations to rank the importance of the 17 social relationship factors that were the most important and commonly used. The results suggest that different social relationship factors have different effects on the risk management of T2DM. Patients and health workers should pay more attention to the high‐benefit factors and thus improve the efficiency of the risk management of T2DM. These findings provided theoretical support for patients and health workers by developing the positive effects of social relationships in improving the risk management of T2DM to the fullest degree.

Automatic optimization of spoken dialog management policies that are robust to environmental noise has long been the goal for both academia and industry. Approaches based on reinforcement learning have been proved to be effective. However, the numerical representation of dialog policy is human-incomprehensible and difficult for dialog system designers to verify or modify, which limits its practical application. In this paper we propose a novel framework for optimizing dialog policies specified in domain language using genetic algorithm. The human-interpretable representation of policy makes the method suitable for practical employment. We present learning algorithms using user simulation and real human-machine dialogs respectively. Empirical experimental results are given to show the effectiveness of the proposed approach.

Discriminative dialog state tracking has become a hot topic in dialog research com-munity recently. Compared to genera-tive approach, it has the advantage of be-ing able to handle arbitrary dependent fea-tures, which is very appealing. In this paper, we present our approach to the DSTC2 challenge. We propose to use dis-criminative Markovian models as a natu-ral enhancement to the stationary discrim-inative models. The Markovian structure allows the incorporation of ‘transitional’ features, which can lead to more effi-ciency and flexibility in tracking user goal changes. Results on the DSTC2 dataset show considerable improvements over the baseline, and the effects of the Markovian dependency is tested empirically. 1

Dialog state tracking (DST), which infers user goals in the presence of noise, is important for spoken dialog systems. Recently it has attracted a lot of attention in the dialog research community. Several new tracking approaches have been proposed, especially in the series of DST Challenges (DSTC). But the problem of cross-domain generalization, i.e., whether trackers designed for one domain will perform similarly well on other domains, is still an open issue. This becomes the focus in DSTC3. To tackle this problem, we adopt domain-independent models and features. We extend our Markovian discriminative model with a joint feature space for effective parameter sharing, so as to accommodate the domain mismatch. In addition, a new two-step training procedure is used to mitigate the `label over-coupling' problem brought by the Markovian structure. When evaluated on the DSTC3 data, our system outperforms all the baselines.

Robustness is one of the most challenging issues for spoken language understanding (SLU). In this paper we studied the semantic understanding of Chinese spoken language for a voice search dialogue system. We first simplified the problem of semantic understanding into a named entity recognition (NER) task, which was further formulated as sequential tagging. We carried out experiments to opt for character over word as the tagging unit. Then two approaches were proposed to exploit prior knowledge - in the form of a domain lexicon - into the character-based tagging framework. One enriched tagger features by incorporating more formal lexical features with a domain lexicon. The other made plain use of domain entities by simply adding them to the training data. Experiment results show that both approaches are effective. The best performance is achieved by combining the above two complimentary approaches. By exploiting prior knowledge we improved the NER performance from 75.27 to 90.24 in F1score on a field test set using speech recognizer output.