Partition behavior of penicillins G and V was studied in a novel three-liquid-phase extraction system,which is composed of butyl acetate (BA),polyethylene glycol (PEG),ammonia sulfate (NH4)2SO4 and water (H2O). The ma...Partition behavior of penicillins G and V was studied in a novel three-liquid-phase extraction system,which is composed of butyl acetate (BA),polyethylene glycol (PEG),ammonia sulfate (NH4)2SO4 and water (H2O). The main components in the top,middle and bottom phases are butyl acetate,polyethylene glycol aqueous solution and ammonia sulfate aqueous solution,respectively. Some parameters such as partition coefficients Di/j and mass fractions Ei of penicillins G and V were determined at the room temperature,respectively. Experimental efforts have been made to investigate the partition behavior of penicillin in the three-liquid-phase extraction system,including initial concentrations of phase-forming components PEG and (NH4)2SO4,PEG molecular weight,pH,initial concentration of penicillin. The results indicated that penicillins G and V have the similar partition behavior. They preferentially distribute into the middle phase with the increase of initial concentration of phase-forming components and into the top phase with the decrease of pH,while partition coefficient Dm/b is hardly affected by pH value. The variation of PEG molecular weight has little effect on mass fractions of penicillin. The increase of initial concentration of penicillins G and V could lead to the increase of Dt/b,Dm/b and the decrease of Dt/m,while their mass fractions in all phases were almost independent on their initial concentrations.展开更多
Gas-assisted three-liquid-phase extraction(GATE), which has the advantages of both three-liquid-phase extraction and solvent sublation, is a novel separation technique for separation and concentration of two organic c...Gas-assisted three-liquid-phase extraction(GATE), which has the advantages of both three-liquid-phase extraction and solvent sublation, is a novel separation technique for separation and concentration of two organic compounds into different phases in one step. This highly effective and economically applicable method has been developed for separating emodin and rhein from herbal extract. In a GATE system composed of butyl acetate/PEG4000/ammonium sulfate aqueous solution, influence of various parameters including gas flow rate, flotation time, salt concentration, initial volume of PEG and butyl acetate was investigated. Within 50 min of 30 ml·min-1nitrogen flow, removal ratio of emodin and rhein from aqueous phase could be over 99% and 97%, respectively.Mass fraction of emodin in the BA phase and rhein in the PEG phase could reach 97% and 95%, respectively. It is demonstrated that gas bubbling is effective for partitioning of emodin and rhein into butyl acetate and PEG phase respectively, and dispersed PEG and butyl acetate could be captured from the aqueous solution. Experimental results show that GATE could be an effective and economical technology for concentration and separation of co-existed products in medicinal plants.展开更多
Several three-liquid-phase extraction systems comprised of organic extractant,polymer and salt aqueous solution were applied to isolate and purify simulated herbal extract containing emodin and rhein.Some influential ...Several three-liquid-phase extraction systems comprised of organic extractant,polymer and salt aqueous solution were applied to isolate and purify simulated herbal extract containing emodin and rhein.Some influential factors on the partitioning behaviors were studied.The results revealed that extractant type and solution pH value were crucial factors for improving the separation performance.The optimal separation results were obtained at pH 8.00 with methyl isobutyl ketone as the extractant,10%(ω) polyethylene glycol with the molecular weight 4000 Da,and 10%(ω) ammonium sulphate.Under the optimized conditions,95%emodin and 97%rhein were simultaneously extracted into the organic phase and polymer-rich phase from simulated herbal solution with the initial concentration of 100×l0^(-6)(ω),respectively,and their separation factor of over 10000 was achieved.By adjusting pH value,back extraction rate of both emodin and rhein could be up to about 99%.With the assistance of molecular simulation program XLOGP3 and molecular orbital package,the possible mechanism of extraction was analyzed,and hydrophobic interaction and hydrogen-bonding interaction might be the major driving forces affecting the partitioning behaviors of emodin and rhein.展开更多
A novel three-liquid-phase extraction system （TES） composed of butyl acetate, block copolymer polyethylene oxide-polypropylene oxide-polyethylene oxide and ammonium sulphate aqueous solution [（NH4）2SO4] as top, mi...A novel three-liquid-phase extraction system （TES） composed of butyl acetate, block copolymer polyethylene oxide-polypropylene oxide-polyethylene oxide and ammonium sulphate aqueous solution [（NH4）2SO4] as top, middle, and bottom phase, respectively, has been developed. The copolymer recycling and partitioning behavior of penicillin V has been studied in this system. Results show that the copolymer could be purified and recycled and penicillin V of the filtrated ferment broth could be partitioned unevenly among the phases and purified in the top phase of this TES. About 90 wt.% of penicillin V could be distributed into the top phase around pH 2.5 and only less than 0.1 wt.% left in the bottom phase.展开更多
Standard bacterial suspensions play a crucial role in microbiological diagnosis.Traditional prepar-ation methods,which rely heavily on manual operations,face challenges such as poor reproducibility,low ef-ficiency,and...Standard bacterial suspensions play a crucial role in microbiological diagnosis.Traditional prepar-ation methods,which rely heavily on manual operations,face challenges such as poor reproducibility,low ef-ficiency,and biosafety concerns.In this study,we propose a high-precision automated colony extraction and separation system that combines large-field imaging and artificial intelligence(AI)to facilitate intelligent screening and localization of colonies.Firstly,a large-field imaging system was developed to capture high-resolution images of 90 mm Petri dishes,achieving a physical resolution of 13.2μm and an imaging speed of 13 frames per second.Subsequently,AI technology was employed for the automatic recognition and localiza-tion of colonies,enabling the selection of target colonies with diameters ranging from 1.9 to 2.3 mm.Next,a three-axis motion control platform was designed,accompanied by a path planning algorithm for the efficient extraction of colonies.An electronic pipette was employed for accurate colony collection.Additionally,a bacterial suspension concentration measurement module was developed,incorporating a 650 nm laser diode as the light source,achieving a measurement accuracy of 0.01 McFarland concentration(MCF).Finally,the system’s performance was validated through the preparation of an Esckerichia coli(E.coli)suspension.After 17 hours of cultivation,E.coli was extracted four times,achieving the target concentration set by the system.This work is expected to enable rapid and accurate microbial sample preparation,significantly reducing de-tection cycles and alleviating the workload of healthcare personnel.展开更多
The recycling of neptunium(Np)from nuclear wastes is crucial for the sustainable development of nuclear energy,yet it is still a challenging task owing to the complexity of Np chemistry.Precise control of oxidation st...The recycling of neptunium(Np)from nuclear wastes is crucial for the sustainable development of nuclear energy,yet it is still a challenging task owing to the complexity of Np chemistry.Precise control of oxidation state is highly desirable for the effective recovery of Np.In this study,we report an innovative strategy for Np recovery through in-situ coordination and reduction of Np(Ⅴ)in a biphasic extraction system.By leveraging the synergistic effects of coordination by a P=O donating ligand(trialkyl phosphine oxide,TRPO)and reduction by hydroquinone(HQ)in the organic phase,efficient Np(Ⅴ)-to-Np(Ⅳ)conversion and high distribution ratio(D)of Np were achieved in a single extraction contact.The reduction mechanism of Np was elucidated through spectroscopic and theoretical analyses.This work enriches the redox chemistry of Np and provides a novel pathway for Np recovery in advanced nuclear fuel cycles.展开更多
The lack of macro-continuity and mechanical strength of covalent organic frameworks(COFs)has significantly limited their practical applications.Here,we propose an“alcohol-triggered defect cleavage”strategy to precis...The lack of macro-continuity and mechanical strength of covalent organic frameworks(COFs)has significantly limited their practical applications.Here,we propose an“alcohol-triggered defect cleavage”strategy to precisely regulate the growth and stacking of COF grains through a moderate reversed Schiff base reaction,realizing the direct synthesis of COF nanofibers(CNFs)with high aspect ratio(L/D=103.05)and long length(>20μm).An individual CNF exhibits a biomimetic scale-like architecture,achieving superior flexibility and fatigue resistance under dynamic bending via a multiscale stress dissipation mechanism.Taking advantages of these structural features,we engineer CNF aerogels(CNF-As)with programmable porous structures(e.g.,honeycomb,lamellar,isotropic)via directional ice-template methodology.CNF-As demonstrate 100%COF content,high specific surface area(396.15 m^(2)g^(-1))and superelasticity(~0%elastic deformation after 500 compression cycles at 50%strain),outperforming most COF-based counterparts.Compared with the conventional COF aerogels,the unique structural features of CNF-A enable it to perform outstandingly in uranium extraction,with an 11.72-fold increment in adsorption capacity(920.12 mg g^(-1))and adsorption rate(89.9%),and a 2.48-fold improvement in selectivity(U/V=2.31).This study provides a direct strategy for the development of next-generation COF materials with outstanding functionality and structural robustness.展开更多
As an important class of phenanthroline derivatives containing soft N and hard O donor atoms,the laborious syntheses of unsymmetrical 1,10-phenanthroline-derived diamide ligands(DAPhen) have hindered its extensive stu...As an important class of phenanthroline derivatives containing soft N and hard O donor atoms,the laborious syntheses of unsymmetrical 1,10-phenanthroline-derived diamide ligands(DAPhen) have hindered its extensive study.In this work,we first report a convenient synthetic method for the construction of DAPhen using Friedländer reaction by two facile steps(vs.previous 12 steps).A variety of DAPhen ligands are readily available,especially unsymmetrical ones,which give us a platform to systematically study the substituent effect on f-block elements extraction performance.The performance of unsymmetrical extractants is experimentally confirmed to falls between that of their corresponding symmetrical extractants by extracting UO_(2)^(2+) as the representative f-block element.This work provides a direct and versatile method to synthesize symmetrical and unsymmetrical DAPhen,which paves way for the investigations on their coordination properties with metal ions and other applications.展开更多
The extraction of uranium from seawater via membrane adsorption is a promising strategy for ensuring a long-term supply of uranium and the sustainability of nuclear energy.However,this approach has been hindered by th...The extraction of uranium from seawater via membrane adsorption is a promising strategy for ensuring a long-term supply of uranium and the sustainability of nuclear energy.However,this approach has been hindered by the longstanding challenge of identifying sustainable membrane materials.In response,we propose a prototypal hybridization strategy to design a novel series of aminated conjugated microporous polymer(CMPN)@collagen fiber membrane(COLM).These sustainable and low-cost membrane materials allow a rapid and high-affinity kinetic to capture 90%of the uranium in just 30 min from 50 ppm with a high selectivity of Kd>105 mL·g^(−1).They also afford a robustly reusable adsorption capacity as high as 345 mg·g^(−1)that could harvest 1.61 mg·g^(−1)of uranium in a short 7-day real marine engineering in Fujian Province,even though suffered from very low uranium concentration of 3.29μg·L^(−1)and tough influence of salts such as 10.77 g·L^(−1)of Na^(+),1.75μg·L^(−1)of VO_(3)^(−)etc.in the rough seas.The structural evidence from both experimental and theoretical studies confirmed the formation of favorable chelating motifs from the amino group on CMPN-COLM,and the intensification by the synergistic effect from the size-sieving action of CMPN and the capillary inflow effect of COLM.展开更多
Deep learning has made significant progress in the field of oriented object detection for remote sensing images.However,existing methods still face challenges when dealing with difficult tasks such as multi-scale targ...Deep learning has made significant progress in the field of oriented object detection for remote sensing images.However,existing methods still face challenges when dealing with difficult tasks such as multi-scale targets,complex backgrounds,and small objects in remote sensing.Maintaining model lightweight to address resource constraints in remote sensing scenarios while improving task completion for remote sensing tasks remains a research hotspot.Therefore,we propose an enhanced multi-scale feature extraction lightweight network EM-YOLO based on the YOLOv8s architecture,specifically optimized for the characteristics of large target scale variations,diverse orientations,and numerous small objects in remote sensing images.Our innovations lie in two main aspects:First,a dynamic snake convolution(DSC)is introduced into the backbone network to enhance the model’s feature extraction capability for oriented targets.Second,an innovative focusing-diffusion module is designed in the feature fusion neck to effectively integrate multi-scale feature information.Finally,we introduce Layer-Adaptive Sparsity for magnitude-based Pruning(LASP)method to perform lightweight network pruning to better complete tasks in resource-constrained scenarios.Experimental results on the lightweight platform Orin demonstrate that the proposed method significantly outperforms the original YOLOv8s model in oriented remote sensing object detection tasks,and achieves comparable or superior performance to state-of-the-art methods on three authoritative remote sensing datasets(DOTA v1.0,DOTA v1.5,and HRSC2016).展开更多
Since Google introduced the concept of Knowledge Graphs(KGs)in 2012,their construction technologies have evolved into a comprehensive methodological framework encompassing knowledge acquisition,extraction,representati...Since Google introduced the concept of Knowledge Graphs(KGs)in 2012,their construction technologies have evolved into a comprehensive methodological framework encompassing knowledge acquisition,extraction,representation,modeling,fusion,computation,and storage.Within this framework,knowledge extraction,as the core component,directly determines KG quality.In military domains,traditional manual curation models face efficiency constraints due to data fragmentation,complex knowledge architectures,and confidentiality protocols.Meanwhile,crowdsourced ontology construction approaches from general domains prove non-transferable,while human-crafted ontologies struggle with generalization deficiencies.To address these challenges,this study proposes an OntologyAware LLM Methodology for Military Domain Knowledge Extraction(LLM-KE).This approach leverages the deep semantic comprehension capabilities of Large Language Models(LLMs)to simulate human experts’cognitive processes in crowdsourced ontology construction,enabling automated extraction of military textual knowledge.It concurrently enhances knowledge processing efficiency and improves KG completeness.Empirical analysis demonstrates that this method effectively resolves scalability and dynamic adaptation challenges in military KG construction,establishing a novel technological pathway for advancing military intelligence development.展开更多
To ease the scarcity of lithium(Li)resource and cut down on environmental pollution,an efficient,selective,inexpensive and sustainable Li recycling process from waste batteries is needed,which is yet to be achieved.He...To ease the scarcity of lithium(Li)resource and cut down on environmental pollution,an efficient,selective,inexpensive and sustainable Li recycling process from waste batteries is needed,which is yet to be achieved.Here,we report a low-potential photoelectrochemical(PEC)system that selectively and efficiently extracts Li metals from multi-cation electrolytes under 1 sun illumination.Based on the difference of redox potential,we can get rid of the disturbance of other cations(i.e.,Fe,Co and Ni ions)by a bias-free PEC device to realize the extraction of high-purity Li metals on a coplanar Si-based photocathode-TiO_(2) photoanode tandem device at 2 V of applied bias(far less than the redox potentials of Li^(+)/Li).In such system,the extraction rate of Li metals(purity>99.5%)exceeds 1.35 g h^(-1)m^(-2)with 90%of Faradaic efficiency.Long-term experiments,different electrode/electrolyte tests,and various price assessments further demonstrate the stability,compatibility and economy of PEC extraction system,enabling a solar-driven pathway for the recycling of critical metal resources.展开更多
As a key low-carbon energy source,nuclear power plays a vital role in the global transition toward sustainable energy.Photocatalytic uranium extraction from seawater(UES)offers a promising solution to ensure long-term...As a key low-carbon energy source,nuclear power plays a vital role in the global transition toward sustainable energy.Photocatalytic uranium extraction from seawater(UES)offers a promising solution to ensure long-term uranium supply but is challenged by ultra-low uranium concentrations and ion interference.To overcome these issues,we design three diketopyrrolopyrrole-based covalent organic frameworks(COFs)via a synergisticπ-extended lock and carboxyl-functionalized anchor molecular engineering strategy.Among them,TPy-DPP-COF features a covalently lockedπ-conjugated structure that enhances planarity,optimizes energy alignment,and minimizes exciton binding energy,thereby promoting charge transfer and suppressing recombination.Concurrently,carboxyl groups enable uranyl-specific coordination and create local electric fields to facilitate charge separation.These features contribute to the outstanding performance of TPy-DPP-COF,which achieves a high uranium adsorption capacity of 16.33 mg g−1 in natural seawater under irradiation,with only 29.3%capacity loss after 10 cycles,surpassing industrial benchmarks.Density functional theory(DFT)calculations and experimental studies reveal a synergistic photocatalysis-adsorption pathway,with DPP units acting as active sites for uranium reduction.This work highlights a molecular design strategy for developing efficient COF-based photocatalysts for practical marine uranium recovery.展开更多
AIM:To investigate the long-term outcomes in acute primary angle closure(APAC)patients treated with lens extraction(LE)surgery and to identify risk factors for glaucomatous optic neuropathy(GON).METHODS:In this longit...AIM:To investigate the long-term outcomes in acute primary angle closure(APAC)patients treated with lens extraction(LE)surgery and to identify risk factors for glaucomatous optic neuropathy(GON).METHODS:In this longitudinal observational study,detailed medical histories of APAC patients and comprehensive ophthalmic examinations at final followup were collected.Logistic regression analysis was performed to identify predictors of blindness.Univariate and multivariate linear regression analyses were conducted to determine risk factors associated with visual outcomes.RESULTS:This study included 39 affected eyes of 31 subjects(26 females)with an average age of 74.1±8.0y.At 6.7±4.2y after APAC attack,2(5.7%)eyes had bestcorrected visual acuity(VA)worse than 3/60.Advanced glaucomatous visual field loss was observed in 15(39.5%)affected eyes and 5(25.0%)fellow eyes.Nine affected eyes(23.7%)had GON,and 11(28.9%)were blind.Six(15.4%)affected eyes and 2(9.1%)fellow eyes had suspicious progression.A significantly higher blindness rate in factory workers compared to office workers.Logistic regression identified that worse VA at attack(OR 10.568,95%CI 1.288-86.695;P=0.028)and worse early postoperative VA(OR 13.214,95%CI 1.157-150.881;P=0.038)were risk factors for blindness.Multivariate regression showed that longer duration of elevated intraocular pressure(P=0.004)and worse early postoperative VA(P=0.009)were associated with worse visual outcomes.CONCLUSION:Despite LE surgery,some APAC patients experience continued visual function deterioration.Lifelong monitoring is necessary.Target pressure and progression rates should be re-evaluated during follow-up.展开更多
A new method by liquid-liquid-liquid three phase system, consisting of acidified primary amine N1923 （abbreviated as A-N1923）, poly（ethylene glycol） （PEG） and （NH4）2S04 aqueous solution, was suggested for the ...A new method by liquid-liquid-liquid three phase system, consisting of acidified primary amine N1923 （abbreviated as A-N1923）, poly（ethylene glycol） （PEG） and （NH4）2S04 aqueous solution, was suggested for the separation and simultaneous extraction of Ⅴ（Ⅴ） and Cr（Ⅵ） from the acidic leach solutions of high- chromium vanadium-titanium magnetite. Experimental results indicated that Ⅴ（Ⅴ） and Cr（Ⅵ） could be selectively enriched into the A-N1923 organic top phase and PEG-rich middle phase, respectively, while AI（Ⅲ） and other co-existing impurity ions, such as Si（Ⅳ）, Fe（Ⅲ）, Ti（Ⅳ）, Mg（Ⅱ） and Ca（Ⅱ） in acidic leach solutions, could be enriched in the （NH4）2SO4 bottom aqueous phase. During the process for extraction and separation of Ⅴ（Ⅴ） and Cr（Ⅵ）, almost all of impurity ions could be removed. The separation factors between Ⅴ （Ⅴ） and Cr（Ⅵ） could reach 630 and 908, respectively in the organic top phase and PEG middle phase, and yields of recovered Ⅴ（Ⅴ） and Cr（Ⅵ） in the top phase and middle phase respectively were all above 90%. Various effects including aqueous pH, A-N1923 concentration, PEG added amount and （NH4）2SO4 concentration on three-phase partitioning of Ⅴ（Ⅴ） and Cr（Ⅵ） were discussed. It was found that the partition of Cr（Ⅵ） into the PEG-rich middle phase was driven by hydrophobic interaction, while extraction of Ⅴ（Ⅴ） by A-N1923 resulted of anion exchange between NO; and H2V10O4-28. Stripping of Ⅴ（Ⅴ） and Cr（Ⅵ） from the top organic phase and the middle PEG-rich phase were achieved by mixing respectively with NANO3 aqueous solutions and NaOH-（NH4）2SO4 solutions. The present work highlights a new approach for the extraction and purification of V and Cr from the complex multi-metal co-existing acidic leach solutions of high-chromium vanadium-titanium magnetite.展开更多
Nuclear energy is critical not only to sustainable economic development but also to achieving peaking carbon dioxide emissions and carbon neutrality[1].China is expected to host the world’s largest number of nuclear ...Nuclear energy is critical not only to sustainable economic development but also to achieving peaking carbon dioxide emissions and carbon neutrality[1].China is expected to host the world’s largest number of nuclear power plants in a few years.Uranium-235 serves as the primary fissile material for the fabrication of nuclear fuel.However,there are only about 6.14 million tons of uranium resources on land,which can sustain~70 years of operation for global nuclear power plants.Thereby,the recovery of uranium from spent fuel,radioactive waste solutions,seawater,and salt lakes is crucial for the healthy development of nuclear power utilization[2-4].展开更多
In the international shipping industry, digital intelligence transformation has become essential, with both governments and enterprises actively working to integrate diverse datasets. The domain of maritime and shippi...In the international shipping industry, digital intelligence transformation has become essential, with both governments and enterprises actively working to integrate diverse datasets. The domain of maritime and shipping is characterized by a vast array of document types, filled with complex, large-scale, and often chaotic knowledge and relationships. Effectively managing these documents is crucial for developing a Large Language Model (LLM) in the maritime domain, enabling practitioners to access and leverage valuable information. A Knowledge Graph (KG) offers a state-of-the-art solution for enhancing knowledge retrieval, providing more accurate responses and enabling context-aware reasoning. This paper presents a framework for utilizing maritime and shipping documents to construct a knowledge graph using GraphRAG, a hybrid tool combining graph-based retrieval and generation capabilities. The extraction of entities and relationships from these documents and the KG construction process are detailed. Furthermore, the KG is integrated with an LLM to develop a Q&A system, demonstrating that the system significantly improves answer accuracy compared to traditional LLMs. Additionally, the KG construction process is up to 50% faster than conventional LLM-based approaches, underscoring the efficiency of our method. This study provides a promising approach to digital intelligence in shipping, advancing knowledge accessibility and decision-making.展开更多
Solvent extraction is the main method used to separate and purify rare earth elements.In the process of rare earths extraction,emulsification often generated due to the instability of the aqueous and organic phases or...Solvent extraction is the main method used to separate and purify rare earth elements.In the process of rare earths extraction,emulsification often generated due to the instability of the aqueous and organic phases or improper operating conditions.Once emulsification occurs,it would not only lead to low rare earths recovery efficiency,small product quantities,high production costs and the losing of extractant and rare earth resources,but also result in serious environmental pollution.Therefore,it is very important to study the micro-mechanisms of emulsification and establish new methods to prevent emulsification at the source.In this paper,possible factors resulting in emulsification,such as the compositions and properties of the organic and aqueous phases,the operating conditions of the rare earths extraction are reviewed.The micro-mechanisms of emulsification are summarized basing on the microscopic structures in the bulk phase,aggregations of the extractants at the organic-aqueous interface,spectral characterizations and computational simulations.On this basis,new formation mechanisms are proposed for emulsification.Preliminary explorations are employed to verify the correctness of these new viewpoints.Finally,future directions for studies of the emulsification micro-mechanism are proposed.This study provides a theoretical basis for further understanding the micro-mechanisms of interfacial instability resulting in emulsification in the process of rare earths extraction.展开更多
Given the scarcity of Satellite Frequency and Orbit(SFO)resources,it holds paramount importance to establish a comprehensive knowledge graph of SFO field(SFO-KG)and employ knowledge reasoning technology to automatical...Given the scarcity of Satellite Frequency and Orbit(SFO)resources,it holds paramount importance to establish a comprehensive knowledge graph of SFO field(SFO-KG)and employ knowledge reasoning technology to automatically mine available SFO resources.An essential aspect of constructing SFO-KG is the extraction of Chinese entity relations.Unfortunately,there is currently no publicly available Chinese SFO entity Relation Extraction(RE)dataset.Moreover,publicly available SFO text data contain numerous NA(representing for“No Answer”)relation category sentences that resemble other relation sentences and pose challenges in accurate classification,resulting in low recall and precision for the NA relation category in entity RE.Consequently,this issue adversely affects both the accuracy of constructing the knowledge graph and the efficiency of RE processes.To address these challenges,this paper proposes a method for extracting Chinese SFO text entity relations based on dynamic integrated learning.This method includes the construction of a manually annotated Chinese SFO entity RE dataset and a classifier combining features of SFO resource data.The proposed approach combines integrated learning and pre-training models,specifically utilizing Bidirectional Encoder Representation from Transformers(BERT).In addition,it incorporates one-class classification,attention mechanisms,and dynamic feedback mechanisms to improve the performance of the RE model.Experimental results show that the proposed method outperforms the traditional methods in terms of F1 value when extracting entity relations from both balanced and long-tailed datasets.展开更多
The rapid development of electricity retail market has prompted an increasing number of electricity consumers to sign green electricity contracts with retail electricity companies,which poses greater challenges for th...The rapid development of electricity retail market has prompted an increasing number of electricity consumers to sign green electricity contracts with retail electricity companies,which poses greater challenges for the market service for green energy consumers.This study proposed a two-stage feature extraction approach for green energy consumers leveraging clustering and termfrequency-inverse document frequency(TF-IDF)algorithms within a knowledge graph framework to provide an information basis that supports the green development of the retail electricity market.First,the multi-source heterogeneous data of green energy consumers under an actual market environment is systematically introduced and the information is categorized into discrete,interval,and relational features.A clustering algorithm was employed to extract features of the trading behavior of green energy consumers in the first stage using the parameter data of green retail electricity contracts.Then,TF-IDF algorithm was applied in the second stage to extract features for green energy consumers in different clusters.Finally,the effectiveness of the proposed approach was validated based on the actual operational data in a southern province of China.It is shown that the most significant discrepancy between the retail trading behaviors of green energy consumers is the power share of green retail packages,whose averaged values are 25.64%,50%,39.66%,and 24.89%in four different clusters,respectively.Additionally,power supply bureaus and electricity retail companies affects the behavior of the green energy consumers most significantly.展开更多
基金Supported by the National Natural Science Foundation of China (No.20236050 20406021)+1 种基金 The Innovative Research Group Fund (No. 20236050 20406021)
文摘Partition behavior of penicillins G and V was studied in a novel three-liquid-phase extraction system,which is composed of butyl acetate (BA),polyethylene glycol (PEG),ammonia sulfate (NH4)2SO4 and water (H2O). The main components in the top,middle and bottom phases are butyl acetate,polyethylene glycol aqueous solution and ammonia sulfate aqueous solution,respectively. Some parameters such as partition coefficients Di/j and mass fractions Ei of penicillins G and V were determined at the room temperature,respectively. Experimental efforts have been made to investigate the partition behavior of penicillin in the three-liquid-phase extraction system,including initial concentrations of phase-forming components PEG and (NH4)2SO4,PEG molecular weight,pH,initial concentration of penicillin. The results indicated that penicillins G and V have the similar partition behavior. They preferentially distribute into the middle phase with the increase of initial concentration of phase-forming components and into the top phase with the decrease of pH,while partition coefficient Dm/b is hardly affected by pH value. The variation of PEG molecular weight has little effect on mass fractions of penicillin. The increase of initial concentration of penicillins G and V could lead to the increase of Dt/b,Dm/b and the decrease of Dt/m,while their mass fractions in all phases were almost independent on their initial concentrations.
基金Supported by the National Natural Science Foundation of China(21136009,21106162,21106152)Ministry of Human Resources and Social Security of China and State Key Laboratory of Chemical Engineering(SKL-ChE-11A04)
文摘Gas-assisted three-liquid-phase extraction(GATE), which has the advantages of both three-liquid-phase extraction and solvent sublation, is a novel separation technique for separation and concentration of two organic compounds into different phases in one step. This highly effective and economically applicable method has been developed for separating emodin and rhein from herbal extract. In a GATE system composed of butyl acetate/PEG4000/ammonium sulfate aqueous solution, influence of various parameters including gas flow rate, flotation time, salt concentration, initial volume of PEG and butyl acetate was investigated. Within 50 min of 30 ml·min-1nitrogen flow, removal ratio of emodin and rhein from aqueous phase could be over 99% and 97%, respectively.Mass fraction of emodin in the BA phase and rhein in the PEG phase could reach 97% and 95%, respectively. It is demonstrated that gas bubbling is effective for partitioning of emodin and rhein into butyl acetate and PEG phase respectively, and dispersed PEG and butyl acetate could be captured from the aqueous solution. Experimental results show that GATE could be an effective and economical technology for concentration and separation of co-existed products in medicinal plants.
基金Supported by the National Natural Science Foundation of China(No.2113600921106162+2 种基金21106152)Supported by the National Key Laboratory of Chemical Engineering(No.SKL-ChE-11A04)Supported by the Ministry of Human Resources and Social Security of China
文摘Several three-liquid-phase extraction systems comprised of organic extractant,polymer and salt aqueous solution were applied to isolate and purify simulated herbal extract containing emodin and rhein.Some influential factors on the partitioning behaviors were studied.The results revealed that extractant type and solution pH value were crucial factors for improving the separation performance.The optimal separation results were obtained at pH 8.00 with methyl isobutyl ketone as the extractant,10%(ω) polyethylene glycol with the molecular weight 4000 Da,and 10%(ω) ammonium sulphate.Under the optimized conditions,95%emodin and 97%rhein were simultaneously extracted into the organic phase and polymer-rich phase from simulated herbal solution with the initial concentration of 100×l0^(-6)(ω),respectively,and their separation factor of over 10000 was achieved.By adjusting pH value,back extraction rate of both emodin and rhein could be up to about 99%.With the assistance of molecular simulation program XLOGP3 and molecular orbital package,the possible mechanism of extraction was analyzed,and hydrophobic interaction and hydrogen-bonding interaction might be the major driving forces affecting the partitioning behaviors of emodin and rhein.
基金Innovative Research Group Science Fund (No. 0221603), the National Natural Science Foundation (No. 20406021) and he National Natural Science Key Foundation (No. 20236050) of China
文摘A novel three-liquid-phase extraction system （TES） composed of butyl acetate, block copolymer polyethylene oxide-polypropylene oxide-polyethylene oxide and ammonium sulphate aqueous solution [（NH4）2SO4] as top, middle, and bottom phase, respectively, has been developed. The copolymer recycling and partitioning behavior of penicillin V has been studied in this system. Results show that the copolymer could be purified and recycled and penicillin V of the filtrated ferment broth could be partitioned unevenly among the phases and purified in the top phase of this TES. About 90 wt.% of penicillin V could be distributed into the top phase around pH 2.5 and only less than 0.1 wt.% left in the bottom phase.
文摘Standard bacterial suspensions play a crucial role in microbiological diagnosis.Traditional prepar-ation methods,which rely heavily on manual operations,face challenges such as poor reproducibility,low ef-ficiency,and biosafety concerns.In this study,we propose a high-precision automated colony extraction and separation system that combines large-field imaging and artificial intelligence(AI)to facilitate intelligent screening and localization of colonies.Firstly,a large-field imaging system was developed to capture high-resolution images of 90 mm Petri dishes,achieving a physical resolution of 13.2μm and an imaging speed of 13 frames per second.Subsequently,AI technology was employed for the automatic recognition and localiza-tion of colonies,enabling the selection of target colonies with diameters ranging from 1.9 to 2.3 mm.Next,a three-axis motion control platform was designed,accompanied by a path planning algorithm for the efficient extraction of colonies.An electronic pipette was employed for accurate colony collection.Additionally,a bacterial suspension concentration measurement module was developed,incorporating a 650 nm laser diode as the light source,achieving a measurement accuracy of 0.01 McFarland concentration(MCF).Finally,the system’s performance was validated through the preparation of an Esckerichia coli(E.coli)suspension.After 17 hours of cultivation,E.coli was extracted four times,achieving the target concentration set by the system.This work is expected to enable rapid and accurate microbial sample preparation,significantly reducing de-tection cycles and alleviating the workload of healthcare personnel.
基金the financial support from the National Natural Science Foundation of China(22325603)the financial support from the National Natural Science Foundation of China(22376116)+3 种基金the financial support from the National Natural Science Foundation of China(22076130)the Young Elite Scientists Sponsorship Program by China Association for Science and Technology(CAST)(2023QNRC001)the Fundamental Research Funds for the Central Universities(20826041D4117)the Natural Science Foundation of Sichuan(2025ZNSFSC0109)。
文摘The recycling of neptunium(Np)from nuclear wastes is crucial for the sustainable development of nuclear energy,yet it is still a challenging task owing to the complexity of Np chemistry.Precise control of oxidation state is highly desirable for the effective recovery of Np.In this study,we report an innovative strategy for Np recovery through in-situ coordination and reduction of Np(Ⅴ)in a biphasic extraction system.By leveraging the synergistic effects of coordination by a P=O donating ligand(trialkyl phosphine oxide,TRPO)and reduction by hydroquinone(HQ)in the organic phase,efficient Np(Ⅴ)-to-Np(Ⅳ)conversion and high distribution ratio(D)of Np were achieved in a single extraction contact.The reduction mechanism of Np was elucidated through spectroscopic and theoretical analyses.This work enriches the redox chemistry of Np and provides a novel pathway for Np recovery in advanced nuclear fuel cycles.
基金supported by the National Natural Science Foundation of China(No.52403035)the Shanghai Sailing Program(23YF1400300)+1 种基金the Fundamental Research Funds for the Central Universities(2232023D-05)the Weiqiao Teaching and Research Innovation Program.
文摘The lack of macro-continuity and mechanical strength of covalent organic frameworks(COFs)has significantly limited their practical applications.Here,we propose an“alcohol-triggered defect cleavage”strategy to precisely regulate the growth and stacking of COF grains through a moderate reversed Schiff base reaction,realizing the direct synthesis of COF nanofibers(CNFs)with high aspect ratio(L/D=103.05)and long length(>20μm).An individual CNF exhibits a biomimetic scale-like architecture,achieving superior flexibility and fatigue resistance under dynamic bending via a multiscale stress dissipation mechanism.Taking advantages of these structural features,we engineer CNF aerogels(CNF-As)with programmable porous structures(e.g.,honeycomb,lamellar,isotropic)via directional ice-template methodology.CNF-As demonstrate 100%COF content,high specific surface area(396.15 m^(2)g^(-1))and superelasticity(~0%elastic deformation after 500 compression cycles at 50%strain),outperforming most COF-based counterparts.Compared with the conventional COF aerogels,the unique structural features of CNF-A enable it to perform outstandingly in uranium extraction,with an 11.72-fold increment in adsorption capacity(920.12 mg g^(-1))and adsorption rate(89.9%),and a 2.48-fold improvement in selectivity(U/V=2.31).This study provides a direct strategy for the development of next-generation COF materials with outstanding functionality and structural robustness.
基金financial support from the National Natural Science Foundation of China (Nos.22476178,U2067213)Natural Science Foundation of Zhejiang Province (No.LRG25B060002)。
文摘As an important class of phenanthroline derivatives containing soft N and hard O donor atoms,the laborious syntheses of unsymmetrical 1,10-phenanthroline-derived diamide ligands(DAPhen) have hindered its extensive study.In this work,we first report a convenient synthetic method for the construction of DAPhen using Friedländer reaction by two facile steps(vs.previous 12 steps).A variety of DAPhen ligands are readily available,especially unsymmetrical ones,which give us a platform to systematically study the substituent effect on f-block elements extraction performance.The performance of unsymmetrical extractants is experimentally confirmed to falls between that of their corresponding symmetrical extractants by extracting UO_(2)^(2+) as the representative f-block element.This work provides a direct and versatile method to synthesize symmetrical and unsymmetrical DAPhen,which paves way for the investigations on their coordination properties with metal ions and other applications.
基金supported by National Natural Science Foundation of China(Grant No.22378066,22108040)Collaboration&Innovation Platform Project of National Independent Innovation Demonstration Zone(Fuzhou,Xiamen&Quanzhou)(Project No:3502ZCQXT2023004).
文摘The extraction of uranium from seawater via membrane adsorption is a promising strategy for ensuring a long-term supply of uranium and the sustainability of nuclear energy.However,this approach has been hindered by the longstanding challenge of identifying sustainable membrane materials.In response,we propose a prototypal hybridization strategy to design a novel series of aminated conjugated microporous polymer(CMPN)@collagen fiber membrane(COLM).These sustainable and low-cost membrane materials allow a rapid and high-affinity kinetic to capture 90%of the uranium in just 30 min from 50 ppm with a high selectivity of Kd>105 mL·g^(−1).They also afford a robustly reusable adsorption capacity as high as 345 mg·g^(−1)that could harvest 1.61 mg·g^(−1)of uranium in a short 7-day real marine engineering in Fujian Province,even though suffered from very low uranium concentration of 3.29μg·L^(−1)and tough influence of salts such as 10.77 g·L^(−1)of Na^(+),1.75μg·L^(−1)of VO_(3)^(−)etc.in the rough seas.The structural evidence from both experimental and theoretical studies confirmed the formation of favorable chelating motifs from the amino group on CMPN-COLM,and the intensification by the synergistic effect from the size-sieving action of CMPN and the capillary inflow effect of COLM.
基金funded by the Hainan Province Science and Technology Special Fund under Grant ZDYF2024GXJS292.
文摘Deep learning has made significant progress in the field of oriented object detection for remote sensing images.However,existing methods still face challenges when dealing with difficult tasks such as multi-scale targets,complex backgrounds,and small objects in remote sensing.Maintaining model lightweight to address resource constraints in remote sensing scenarios while improving task completion for remote sensing tasks remains a research hotspot.Therefore,we propose an enhanced multi-scale feature extraction lightweight network EM-YOLO based on the YOLOv8s architecture,specifically optimized for the characteristics of large target scale variations,diverse orientations,and numerous small objects in remote sensing images.Our innovations lie in two main aspects:First,a dynamic snake convolution(DSC)is introduced into the backbone network to enhance the model’s feature extraction capability for oriented targets.Second,an innovative focusing-diffusion module is designed in the feature fusion neck to effectively integrate multi-scale feature information.Finally,we introduce Layer-Adaptive Sparsity for magnitude-based Pruning(LASP)method to perform lightweight network pruning to better complete tasks in resource-constrained scenarios.Experimental results on the lightweight platform Orin demonstrate that the proposed method significantly outperforms the original YOLOv8s model in oriented remote sensing object detection tasks,and achieves comparable or superior performance to state-of-the-art methods on three authoritative remote sensing datasets(DOTA v1.0,DOTA v1.5,and HRSC2016).
文摘Since Google introduced the concept of Knowledge Graphs(KGs)in 2012,their construction technologies have evolved into a comprehensive methodological framework encompassing knowledge acquisition,extraction,representation,modeling,fusion,computation,and storage.Within this framework,knowledge extraction,as the core component,directly determines KG quality.In military domains,traditional manual curation models face efficiency constraints due to data fragmentation,complex knowledge architectures,and confidentiality protocols.Meanwhile,crowdsourced ontology construction approaches from general domains prove non-transferable,while human-crafted ontologies struggle with generalization deficiencies.To address these challenges,this study proposes an OntologyAware LLM Methodology for Military Domain Knowledge Extraction(LLM-KE).This approach leverages the deep semantic comprehension capabilities of Large Language Models(LLMs)to simulate human experts’cognitive processes in crowdsourced ontology construction,enabling automated extraction of military textual knowledge.It concurrently enhances knowledge processing efficiency and improves KG completeness.Empirical analysis demonstrates that this method effectively resolves scalability and dynamic adaptation challenges in military KG construction,establishing a novel technological pathway for advancing military intelligence development.
基金the National Natural Science Foundation of China(22479047,22409058)the Outstanding Youth Scientist Foundation of Hunan Province(2022JJ10023)the Provincial Natural Science Foundation of Guangdong(2023A1515011745)for financial support of this research。
文摘To ease the scarcity of lithium(Li)resource and cut down on environmental pollution,an efficient,selective,inexpensive and sustainable Li recycling process from waste batteries is needed,which is yet to be achieved.Here,we report a low-potential photoelectrochemical(PEC)system that selectively and efficiently extracts Li metals from multi-cation electrolytes under 1 sun illumination.Based on the difference of redox potential,we can get rid of the disturbance of other cations(i.e.,Fe,Co and Ni ions)by a bias-free PEC device to realize the extraction of high-purity Li metals on a coplanar Si-based photocathode-TiO_(2) photoanode tandem device at 2 V of applied bias(far less than the redox potentials of Li^(+)/Li).In such system,the extraction rate of Li metals(purity>99.5%)exceeds 1.35 g h^(-1)m^(-2)with 90%of Faradaic efficiency.Long-term experiments,different electrode/electrolyte tests,and various price assessments further demonstrate the stability,compatibility and economy of PEC extraction system,enabling a solar-driven pathway for the recycling of critical metal resources.
基金the Young Elite Scientists Sponsorship Program by JXAST(2024QT11)the National Natural Science Foundation of China(22465001,22309003)the Jiangxi Provincial Natural Science Foundation(20232BAB203042,20242BAB22002).
文摘As a key low-carbon energy source,nuclear power plays a vital role in the global transition toward sustainable energy.Photocatalytic uranium extraction from seawater(UES)offers a promising solution to ensure long-term uranium supply but is challenged by ultra-low uranium concentrations and ion interference.To overcome these issues,we design three diketopyrrolopyrrole-based covalent organic frameworks(COFs)via a synergisticπ-extended lock and carboxyl-functionalized anchor molecular engineering strategy.Among them,TPy-DPP-COF features a covalently lockedπ-conjugated structure that enhances planarity,optimizes energy alignment,and minimizes exciton binding energy,thereby promoting charge transfer and suppressing recombination.Concurrently,carboxyl groups enable uranyl-specific coordination and create local electric fields to facilitate charge separation.These features contribute to the outstanding performance of TPy-DPP-COF,which achieves a high uranium adsorption capacity of 16.33 mg g−1 in natural seawater under irradiation,with only 29.3%capacity loss after 10 cycles,surpassing industrial benchmarks.Density functional theory(DFT)calculations and experimental studies reveal a synergistic photocatalysis-adsorption pathway,with DPP units acting as active sites for uranium reduction.This work highlights a molecular design strategy for developing efficient COF-based photocatalysts for practical marine uranium recovery.
文摘AIM:To investigate the long-term outcomes in acute primary angle closure(APAC)patients treated with lens extraction(LE)surgery and to identify risk factors for glaucomatous optic neuropathy(GON).METHODS:In this longitudinal observational study,detailed medical histories of APAC patients and comprehensive ophthalmic examinations at final followup were collected.Logistic regression analysis was performed to identify predictors of blindness.Univariate and multivariate linear regression analyses were conducted to determine risk factors associated with visual outcomes.RESULTS:This study included 39 affected eyes of 31 subjects(26 females)with an average age of 74.1±8.0y.At 6.7±4.2y after APAC attack,2(5.7%)eyes had bestcorrected visual acuity(VA)worse than 3/60.Advanced glaucomatous visual field loss was observed in 15(39.5%)affected eyes and 5(25.0%)fellow eyes.Nine affected eyes(23.7%)had GON,and 11(28.9%)were blind.Six(15.4%)affected eyes and 2(9.1%)fellow eyes had suspicious progression.A significantly higher blindness rate in factory workers compared to office workers.Logistic regression identified that worse VA at attack(OR 10.568,95%CI 1.288-86.695;P=0.028)and worse early postoperative VA(OR 13.214,95%CI 1.157-150.881;P=0.038)were risk factors for blindness.Multivariate regression showed that longer duration of elevated intraocular pressure(P=0.004)and worse early postoperative VA(P=0.009)were associated with worse visual outcomes.CONCLUSION:Despite LE surgery,some APAC patients experience continued visual function deterioration.Lifelong monitoring is necessary.Target pressure and progression rates should be re-evaluated during follow-up.
基金Supported by the National Basic Research and Development Program of China(973ProgramNo.2013CB632602)the National Natural Science Foundation of China(Nos.51574213,51074150)
文摘A new method by liquid-liquid-liquid three phase system, consisting of acidified primary amine N1923 （abbreviated as A-N1923）, poly（ethylene glycol） （PEG） and （NH4）2S04 aqueous solution, was suggested for the separation and simultaneous extraction of Ⅴ（Ⅴ） and Cr（Ⅵ） from the acidic leach solutions of high- chromium vanadium-titanium magnetite. Experimental results indicated that Ⅴ（Ⅴ） and Cr（Ⅵ） could be selectively enriched into the A-N1923 organic top phase and PEG-rich middle phase, respectively, while AI（Ⅲ） and other co-existing impurity ions, such as Si（Ⅳ）, Fe（Ⅲ）, Ti（Ⅳ）, Mg（Ⅱ） and Ca（Ⅱ） in acidic leach solutions, could be enriched in the （NH4）2SO4 bottom aqueous phase. During the process for extraction and separation of Ⅴ（Ⅴ） and Cr（Ⅵ）, almost all of impurity ions could be removed. The separation factors between Ⅴ （Ⅴ） and Cr（Ⅵ） could reach 630 and 908, respectively in the organic top phase and PEG middle phase, and yields of recovered Ⅴ（Ⅴ） and Cr（Ⅵ） in the top phase and middle phase respectively were all above 90%. Various effects including aqueous pH, A-N1923 concentration, PEG added amount and （NH4）2SO4 concentration on three-phase partitioning of Ⅴ（Ⅴ） and Cr（Ⅵ） were discussed. It was found that the partition of Cr（Ⅵ） into the PEG-rich middle phase was driven by hydrophobic interaction, while extraction of Ⅴ（Ⅴ） by A-N1923 resulted of anion exchange between NO; and H2V10O4-28. Stripping of Ⅴ（Ⅴ） and Cr（Ⅵ） from the top organic phase and the middle PEG-rich phase were achieved by mixing respectively with NANO3 aqueous solutions and NaOH-（NH4）2SO4 solutions. The present work highlights a new approach for the extraction and purification of V and Cr from the complex multi-metal co-existing acidic leach solutions of high-chromium vanadium-titanium magnetite.
基金supported by the National Natural Science Foundation of China(22341602,U24B20195)。
文摘Nuclear energy is critical not only to sustainable economic development but also to achieving peaking carbon dioxide emissions and carbon neutrality[1].China is expected to host the world’s largest number of nuclear power plants in a few years.Uranium-235 serves as the primary fissile material for the fabrication of nuclear fuel.However,there are only about 6.14 million tons of uranium resources on land,which can sustain~70 years of operation for global nuclear power plants.Thereby,the recovery of uranium from spent fuel,radioactive waste solutions,seawater,and salt lakes is crucial for the healthy development of nuclear power utilization[2-4].
文摘In the international shipping industry, digital intelligence transformation has become essential, with both governments and enterprises actively working to integrate diverse datasets. The domain of maritime and shipping is characterized by a vast array of document types, filled with complex, large-scale, and often chaotic knowledge and relationships. Effectively managing these documents is crucial for developing a Large Language Model (LLM) in the maritime domain, enabling practitioners to access and leverage valuable information. A Knowledge Graph (KG) offers a state-of-the-art solution for enhancing knowledge retrieval, providing more accurate responses and enabling context-aware reasoning. This paper presents a framework for utilizing maritime and shipping documents to construct a knowledge graph using GraphRAG, a hybrid tool combining graph-based retrieval and generation capabilities. The extraction of entities and relationships from these documents and the KG construction process are detailed. Furthermore, the KG is integrated with an LLM to develop a Q&A system, demonstrating that the system significantly improves answer accuracy compared to traditional LLMs. Additionally, the KG construction process is up to 50% faster than conventional LLM-based approaches, underscoring the efficiency of our method. This study provides a promising approach to digital intelligence in shipping, advancing knowledge accessibility and decision-making.
基金Project supported by the National Natural Science Foundation of China(52074031)the Key Research and Development Program of Shandong Province(ZR2021MB051,ZR2020ME256)the Open Project of Key Laboratory of Green Chemical Engineering Process of Ministry of Education(GCP202117)。
文摘Solvent extraction is the main method used to separate and purify rare earth elements.In the process of rare earths extraction,emulsification often generated due to the instability of the aqueous and organic phases or improper operating conditions.Once emulsification occurs,it would not only lead to low rare earths recovery efficiency,small product quantities,high production costs and the losing of extractant and rare earth resources,but also result in serious environmental pollution.Therefore,it is very important to study the micro-mechanisms of emulsification and establish new methods to prevent emulsification at the source.In this paper,possible factors resulting in emulsification,such as the compositions and properties of the organic and aqueous phases,the operating conditions of the rare earths extraction are reviewed.The micro-mechanisms of emulsification are summarized basing on the microscopic structures in the bulk phase,aggregations of the extractants at the organic-aqueous interface,spectral characterizations and computational simulations.On this basis,new formation mechanisms are proposed for emulsification.Preliminary explorations are employed to verify the correctness of these new viewpoints.Finally,future directions for studies of the emulsification micro-mechanism are proposed.This study provides a theoretical basis for further understanding the micro-mechanisms of interfacial instability resulting in emulsification in the process of rare earths extraction.
文摘Given the scarcity of Satellite Frequency and Orbit(SFO)resources,it holds paramount importance to establish a comprehensive knowledge graph of SFO field(SFO-KG)and employ knowledge reasoning technology to automatically mine available SFO resources.An essential aspect of constructing SFO-KG is the extraction of Chinese entity relations.Unfortunately,there is currently no publicly available Chinese SFO entity Relation Extraction(RE)dataset.Moreover,publicly available SFO text data contain numerous NA(representing for“No Answer”)relation category sentences that resemble other relation sentences and pose challenges in accurate classification,resulting in low recall and precision for the NA relation category in entity RE.Consequently,this issue adversely affects both the accuracy of constructing the knowledge graph and the efficiency of RE processes.To address these challenges,this paper proposes a method for extracting Chinese SFO text entity relations based on dynamic integrated learning.This method includes the construction of a manually annotated Chinese SFO entity RE dataset and a classifier combining features of SFO resource data.The proposed approach combines integrated learning and pre-training models,specifically utilizing Bidirectional Encoder Representation from Transformers(BERT).In addition,it incorporates one-class classification,attention mechanisms,and dynamic feedback mechanisms to improve the performance of the RE model.Experimental results show that the proposed method outperforms the traditional methods in terms of F1 value when extracting entity relations from both balanced and long-tailed datasets.
基金support by the Science and Technology Project of Guangdong Power Exchange Center Co.,Ltd.(No.GDKJXM20222599)National Natural Science Foundation of China(No.52207104)Natural Science Foundation of Guangdong Province(No.2024A1515010426).
文摘The rapid development of electricity retail market has prompted an increasing number of electricity consumers to sign green electricity contracts with retail electricity companies,which poses greater challenges for the market service for green energy consumers.This study proposed a two-stage feature extraction approach for green energy consumers leveraging clustering and termfrequency-inverse document frequency(TF-IDF)algorithms within a knowledge graph framework to provide an information basis that supports the green development of the retail electricity market.First,the multi-source heterogeneous data of green energy consumers under an actual market environment is systematically introduced and the information is categorized into discrete,interval,and relational features.A clustering algorithm was employed to extract features of the trading behavior of green energy consumers in the first stage using the parameter data of green retail electricity contracts.Then,TF-IDF algorithm was applied in the second stage to extract features for green energy consumers in different clusters.Finally,the effectiveness of the proposed approach was validated based on the actual operational data in a southern province of China.It is shown that the most significant discrepancy between the retail trading behaviors of green energy consumers is the power share of green retail packages,whose averaged values are 25.64%,50%,39.66%,and 24.89%in four different clusters,respectively.Additionally,power supply bureaus and electricity retail companies affects the behavior of the green energy consumers most significantly.
