Search

Conversational recommendation systems (CRS) aim to elicit user preferences and provide satisfying recommendations through natural language interactions. Existing CRS methods often assume that users have clear and consistent preferences, which may not reflect the reality of user decision-making processes. In this paper, we introduce a novel scenario called Vague Preference Multi-round Conversational Recommendation (VPMCR), which considers users' vague and dynamic preferences in CRS. In the VPMCR setting, we propose a solution called Adaptive Vague Preference Policy Learning (AVPPL), which consists of two components: Ambiguity-aware Soft Estimation (ASE) and Dynamism-aware Policy Learning (DPL). ASE estimates the vagueness of user feedback and captures their dynamic preferences using a choice-based preference extraction module and a time-aware decaying strategy. DPL leverages the preference distribution estimated by ASE to guide the conversation and adapt to changes in user preferences using a graph-based conversation modeling module and a vague preference policy learning module. We conduct extensive experiments on four real-world datasets and demonstrate the effectiveness of our method in the VPMCR scenario, setting a new benchmark for future research in CRS.

Ultra-broadband near-infrared (NIR) luminescent materials are the most important component of NIR light-emitting devices (LED) and are crucial for their performance in sensing applications. A major challenge is to design novel NIR luminescent materials to replace the traditional Cr3+-doped systems. We report an all-inorganic bismuth halide perovskite Cs2AgBiCl6 single crystal that achieves efficient broadband NIR emission by introducing Na ions. Experiments and density functional theory (DFT) calculations show that the NIR emission originates from self-trapped excitons (STE) emission, which can be enhanced by weakening the strong coupling between electrons and phonons. The high photoluminescence quantum efficiency (PLQY) of 51 %, the extensive full width at half maximum (FWHM) of 270 nm and the stability provide advantages as a NIR luminescent material. The single-crystal-based NIR LED demonstrated its potential applications in NIR spectral detection as well as night vision.

All-inorganic perovskite quantum dots (PQDs), which possess outstanding photophysical properties, are regarded as promising materials for optoelectronic applications. However, the poor light conversion efficiency and severe stability problem hinder their widespread applications. In this work, a novel encapsulation strategy is developed through the in situ growth of CsPbX3 PQDs in presynthesized mesoporous cerium-based metal organic frameworks (Ce-MOFs) and further silane hydrolysis–encapsulation, generating stable CsPbX3@Ce-MOF@SiO2 composites with greatly enhanced light conversion efficiency. Moreover, the simulation results suggest that the pore boundary of Ce-MOFs has a strong waveguide effect on the incident PQD light, constraining PQD light inside the bodies of Ce-MOFs and suppressing reabsorption losses, thus increasing the overall light conversion efficiency of PQDs. Meanwhile, the Ce-MOF@SiO2 protective shell effectively improves the stability by blocking internally embedded PQDs from the harmful external environment. Further, the obtained white-light-emitting diode shows an ultrahigh luminous efficiency of 87.8 lm/W, which demonstrates their great potential in optoelectronic applications.

Traditional recommendation systems estimate user preference on items from past interaction history, thus suffering from the limitations of obtaining fine-grained and dynamic user preference. Conversational recommendation system (CRS) brings revolutions to those limitations by enabling the system to directly ask users about their preferred attributes on items. However, existing CRS methods do not make full use of such advantage -- they only use the attribute feedback in rather implicit ways such as updating the latent user representation. In this paper, we propose Conversational Path Reasoning (CPR), a generic framework that models conversational recommendation as an interactive path reasoning problem on a graph. It walks through the attribute vertices by following user feedback, utilizing the user preferred attributes in an explicit way. By leveraging on the graph structure, CPR is able to prune off many irrelevant candidate attributes, leading to better chance of hitting user preferred attributes. To demonstrate how CPR works, we propose a simple yet effective instantiation named SCPR (Simple CPR). We perform empirical studies on the multi-round conversational recommendation scenario, the most realistic CRS setting so far that considers multiple rounds of asking attributes and recommending items. Through extensive experiments on two datasets Yelp and LastFM, we validate the effectiveness of our SCPR, which significantly outperforms the state-of-the-art CRS methods EAR (arXiv:2002.09102) and CRM (arXiv:1806.03277). In particular, we find that the more attributes there are, the more advantages our method can achieve., Comment: KDD 2020, 11 pages, 6 figures