Pub Date : 2010-11-29DOI: 10.1109/ICMWI.2010.5648141
Farek Lazhar, T. Yamina
Identification of opinions is a set of techniques which is a part of the natural language processing, especially in the information research area. This consists in developing systems able to extract and explore the opinions existing in corpuses. The presence of important textual mass of Arabic newspapers in an electronic format requires a particular exploration technique. We intend to present in this paper a system of opinions identification, based on the model of Aila Rosà [1], representing the opinion as an object composed of four elements : predicate, source, topic and content. Two properties: polarity and intensity which are inspired from the work of Plantié Mathieu [2] and are added to this model to establish relationships between the different opinions present in the text according to their different degrees of intensity and polarity. In presenting its general architecture, our system uses several techniques such as: XML representation of opinions, semantic expansion of opinions as explained by Nicolas B [3] and finally a statistical representation of the opinions in occurrences matrix format to facilitate the calculation of the similarity between the opinions in the classification phase.
{"title":"Identification of opinions in Arabic newspapers","authors":"Farek Lazhar, T. Yamina","doi":"10.1109/ICMWI.2010.5648141","DOIUrl":"https://doi.org/10.1109/ICMWI.2010.5648141","url":null,"abstract":"Identification of opinions is a set of techniques which is a part of the natural language processing, especially in the information research area. This consists in developing systems able to extract and explore the opinions existing in corpuses. The presence of important textual mass of Arabic newspapers in an electronic format requires a particular exploration technique. We intend to present in this paper a system of opinions identification, based on the model of Aila Rosà [1], representing the opinion as an object composed of four elements : predicate, source, topic and content. Two properties: polarity and intensity which are inspired from the work of Plantié Mathieu [2] and are added to this model to establish relationships between the different opinions present in the text according to their different degrees of intensity and polarity. In presenting its general architecture, our system uses several techniques such as: XML representation of opinions, semantic expansion of opinions as explained by Nicolas B [3] and finally a statistical representation of the opinions in occurrences matrix format to facilitate the calculation of the similarity between the opinions in the classification phase.","PeriodicalId":404577,"journal":{"name":"2010 International Conference on Machine and Web Intelligence","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127501480","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-11-29DOI: 10.1109/ICMWI.2010.5648079
M. T. Khadir, Sihem Klai
This paper describes the design of a fault diagnostic maintenance system for steam turbines based on a domain ontology and coupled to an expert system. The main data and information constituting the system come from disparate data bases with different usage. In this case a database for equipment characteristics and another containing maintenance acts defining symptoms, defects and remedies for maintenance cases. An Expert System (ES) integrated with the domain ontology of the steam turbine is used as a reasoner in order to generate new knowledge. The second aspect of the paper focuses on the possible enhancement and evolution of the developed ontology in order to take into account new maintenance cases. Examples of ontology evolution are given at an instance and class levels.
{"title":"A steam turbine diagnostic maintenance system based on an evolutive domain ontology","authors":"M. T. Khadir, Sihem Klai","doi":"10.1109/ICMWI.2010.5648079","DOIUrl":"https://doi.org/10.1109/ICMWI.2010.5648079","url":null,"abstract":"This paper describes the design of a fault diagnostic maintenance system for steam turbines based on a domain ontology and coupled to an expert system. The main data and information constituting the system come from disparate data bases with different usage. In this case a database for equipment characteristics and another containing maintenance acts defining symptoms, defects and remedies for maintenance cases. An Expert System (ES) integrated with the domain ontology of the steam turbine is used as a reasoner in order to generate new knowledge. The second aspect of the paper focuses on the possible enhancement and evolution of the developed ontology in order to take into account new maintenance cases. Examples of ontology evolution are given at an instance and class levels.","PeriodicalId":404577,"journal":{"name":"2010 International Conference on Machine and Web Intelligence","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121077438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-11-29DOI: 10.1109/ICMWI.2010.5648038
S. Zaidi, M. Laskri, Ahmed Abdelali
Information extraction (IE) from corpora is texts analysis in order to extract structured information such as Named Entities (NE) which may be names of person, organization, address, date, location etc. … GATE is a software toolkit written in Java from 1995 and widely used worldwide by many communities (scientists, companies, teachers, students) for natural language processing. We have experimented Gate for extracting terms by writing new Jape rules (Java Annotation Pattern Engine) and used them on a tagged corpus developed at Leeds University. These terms will be used in the texts-based ontologies building. In our case this ontology will be incorporated into a search engine to expand queries on the Web, in the specified domain.
{"title":"Arabic collocations extraction using Gate","authors":"S. Zaidi, M. Laskri, Ahmed Abdelali","doi":"10.1109/ICMWI.2010.5648038","DOIUrl":"https://doi.org/10.1109/ICMWI.2010.5648038","url":null,"abstract":"Information extraction (IE) from corpora is texts analysis in order to extract structured information such as Named Entities (NE) which may be names of person, organization, address, date, location etc. … GATE is a software toolkit written in Java from 1995 and widely used worldwide by many communities (scientists, companies, teachers, students) for natural language processing. We have experimented Gate for extracting terms by writing new Jape rules (Java Annotation Pattern Engine) and used them on a tagged corpus developed at Leeds University. These terms will be used in the texts-based ontologies building. In our case this ontology will be incorporated into a search engine to expand queries on the Web, in the specified domain.","PeriodicalId":404577,"journal":{"name":"2010 International Conference on Machine and Web Intelligence","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126205861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-11-29DOI: 10.1109/ICMWI.2010.5648194
B. Benhamou, T. Nabhani, P. Siegel
Symmetry had been well studied in classical logics and constraint programming since a decade. Early, Krishna-murthy showed that some tricky formulas admit short proofs when augmenting the propositional logic resolution proof system by the symmetry rule. However, in Artificial Intelligence, we usually manipulate incomplete information and need to include uncertainty to reason on knowledge with exceptions and non-monotonicity. Several non classic logics are introduced for that purpose, but as far as we know, symmetry for these frameworks had not been studied yet. Here, we are interested to extend the notion of symmetry to that non classical logics such as preferential logics, X-logics and default logics, then give a new symmetry inference rule for the X-logics and the default logics. Finally, we show how symmetry reasoning is profitable for these logics and how they handle some symmetries that do not exist in classical logics.
{"title":"Reasoning by symmetry in non-monotonic inference","authors":"B. Benhamou, T. Nabhani, P. Siegel","doi":"10.1109/ICMWI.2010.5648194","DOIUrl":"https://doi.org/10.1109/ICMWI.2010.5648194","url":null,"abstract":"Symmetry had been well studied in classical logics and constraint programming since a decade. Early, Krishna-murthy showed that some tricky formulas admit short proofs when augmenting the propositional logic resolution proof system by the symmetry rule. However, in Artificial Intelligence, we usually manipulate incomplete information and need to include uncertainty to reason on knowledge with exceptions and non-monotonicity. Several non classic logics are introduced for that purpose, but as far as we know, symmetry for these frameworks had not been studied yet. Here, we are interested to extend the notion of symmetry to that non classical logics such as preferential logics, X-logics and default logics, then give a new symmetry inference rule for the X-logics and the default logics. Finally, we show how symmetry reasoning is profitable for these logics and how they handle some symmetries that do not exist in classical logics.","PeriodicalId":404577,"journal":{"name":"2010 International Conference on Machine and Web Intelligence","volume":"361 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115919288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-11-29DOI: 10.1109/ICMWI.2010.5648199
Chaoui Mohammed, L. M. Tayeb
The field of education has always been closely connected with information and communication technologies (ICT). Currently, we perceive that digital and network technologies increase in their importance where the Web plays a central role. In an application of online learning, Web is used as representative supports for producing, managing and distributing contents. This space is evolving rapidly and is governed by factors regarding its function and modes of signification, so it poses difficulties for teachers, especially for extracting the relevant informations. It is in this context that our research work is situated. Our goal was to offer a Web-based architecture for an e-learning domain. First time using the Web as a medium documentary based on a search engine 'Google', going beyond to the proposal of a model for creating a field for e-Learning. Then, we studied the evolutionary lines of the semantic web and more specifically anthologies, creating and integrating ontology in the same model. We finished by applying a filtering method to extract the relevant parts to build the field of online education.
{"title":"Automatic construction of an on-line learning domain","authors":"Chaoui Mohammed, L. M. Tayeb","doi":"10.1109/ICMWI.2010.5648199","DOIUrl":"https://doi.org/10.1109/ICMWI.2010.5648199","url":null,"abstract":"The field of education has always been closely connected with information and communication technologies (ICT). Currently, we perceive that digital and network technologies increase in their importance where the Web plays a central role. In an application of online learning, Web is used as representative supports for producing, managing and distributing contents. This space is evolving rapidly and is governed by factors regarding its function and modes of signification, so it poses difficulties for teachers, especially for extracting the relevant informations. It is in this context that our research work is situated. Our goal was to offer a Web-based architecture for an e-learning domain. First time using the Web as a medium documentary based on a search engine 'Google', going beyond to the proposal of a model for creating a field for e-Learning. Then, we studied the evolutionary lines of the semantic web and more specifically anthologies, creating and integrating ontology in the same model. We finished by applying a filtering method to extract the relevant parts to build the field of online education.","PeriodicalId":404577,"journal":{"name":"2010 International Conference on Machine and Web Intelligence","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115928440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-11-29DOI: 10.1109/ICMWI.2010.5648130
Djeddi Chawki, Souici-Meslati Labiba
In this paper, we present a novel approach for Arabic Text-Independent Writer Identification and Verification. Given that the handwriting of different people is often visually distinctive, we propose a global approach based on texture analysis, where each writer's handwriting is regarded as a different texture. This allows us to apply a texture classification method mainly based on a set of new proposed features extracted from Grey Level Run Length (GLRL) Matrices. The efficiency of the proposed approach is demonstrated experimentally by the classification of 650 handwriting documents collected from 130 different Arabic writers. Comparisons with Grey Level Co-occurrence Matrices (GLCM) technique demonstrate that the GLRL matrices contain more discriminatory information and that a good method of extracting such information is of great importance for successful classification.
{"title":"A texture based approach for Arabic writer identification and verification","authors":"Djeddi Chawki, Souici-Meslati Labiba","doi":"10.1109/ICMWI.2010.5648130","DOIUrl":"https://doi.org/10.1109/ICMWI.2010.5648130","url":null,"abstract":"In this paper, we present a novel approach for Arabic Text-Independent Writer Identification and Verification. Given that the handwriting of different people is often visually distinctive, we propose a global approach based on texture analysis, where each writer's handwriting is regarded as a different texture. This allows us to apply a texture classification method mainly based on a set of new proposed features extracted from Grey Level Run Length (GLRL) Matrices. The efficiency of the proposed approach is demonstrated experimentally by the classification of 650 handwriting documents collected from 130 different Arabic writers. Comparisons with Grey Level Co-occurrence Matrices (GLCM) technique demonstrate that the GLRL matrices contain more discriminatory information and that a good method of extracting such information is of great importance for successful classification.","PeriodicalId":404577,"journal":{"name":"2010 International Conference on Machine and Web Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115640843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-11-29DOI: 10.1109/ICMWI.2010.5648104
M. Barr, Ladjel Bellatreche
The subject matter falls within the context of optimization of relational data warehouses. It involves using the algorithm based on ant colonies for the selection of horizontal fragmentation which is one of optimization irredundant techniques. The character NP-complete characterizing the selection of this technique justifies the use of approximate methods or "meta heuristic” to solve it in a finite time. Indeed, the collective intelligence of artificial ants in solving combinatorial optimization problems NP-Complete is a very promising activity. This approach inspires its capacity through the transfer of learning within the colony in a manner which uses the stigmergy for communicate the choice of good solutions based on visibility and the deposit of pheromone. In this article we have modeled our problem of selecting a horizontal fragmentation scheme that be supported by the approach based on ant colonies while defining the input variables which are: the unfragmented data warehouse, the query load frequently used and the maximum number of fragments required by the administrator of the data warehouse (ADW). The result output is the horizontal fragmentation pattern that minimizes the overall cost of the load of requests. The success to formalize the problem as a knapsack problem permits us to present a new approach for resolving the horizontal fragmentation problem. Experimenting with our approach using a Benchmark (APB1 in our case) is one important way to verify the effectiveness of the proposed method on the one hand, and the power to relate to other methods that exist in this area, on the other.
{"title":"A new approach based on ants for solving the problem of horizontal fragmentation in relational data warehouses","authors":"M. Barr, Ladjel Bellatreche","doi":"10.1109/ICMWI.2010.5648104","DOIUrl":"https://doi.org/10.1109/ICMWI.2010.5648104","url":null,"abstract":"The subject matter falls within the context of optimization of relational data warehouses. It involves using the algorithm based on ant colonies for the selection of horizontal fragmentation which is one of optimization irredundant techniques. The character NP-complete characterizing the selection of this technique justifies the use of approximate methods or \"meta heuristic” to solve it in a finite time. Indeed, the collective intelligence of artificial ants in solving combinatorial optimization problems NP-Complete is a very promising activity. This approach inspires its capacity through the transfer of learning within the colony in a manner which uses the stigmergy for communicate the choice of good solutions based on visibility and the deposit of pheromone. In this article we have modeled our problem of selecting a horizontal fragmentation scheme that be supported by the approach based on ant colonies while defining the input variables which are: the unfragmented data warehouse, the query load frequently used and the maximum number of fragments required by the administrator of the data warehouse (ADW). The result output is the horizontal fragmentation pattern that minimizes the overall cost of the load of requests. The success to formalize the problem as a knapsack problem permits us to present a new approach for resolving the horizontal fragmentation problem. Experimenting with our approach using a Benchmark (APB1 in our case) is one important way to verify the effectiveness of the proposed method on the one hand, and the power to relate to other methods that exist in this area, on the other.","PeriodicalId":404577,"journal":{"name":"2010 International Conference on Machine and Web Intelligence","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122206098","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-11-29DOI: 10.1109/ICMWI.2010.5647893
Rafika Hakiki, L. Sekhri
This paper presents a mapping algorithm to deal with a new class of hybrid Petri net (HPN) called Discrete Continue elementary HPN. The method enables us to analyze some system's properties using the linear hybrid automaton generated by the mapping process. The method is applied to a three tanks water system and analyzed by a PHAVer software tool. Its effectiveness is illustrated by numerical simulation results.
{"title":"Hybrid Petri nets based approach for analyzing complex dynamic systems","authors":"Rafika Hakiki, L. Sekhri","doi":"10.1109/ICMWI.2010.5647893","DOIUrl":"https://doi.org/10.1109/ICMWI.2010.5647893","url":null,"abstract":"This paper presents a mapping algorithm to deal with a new class of hybrid Petri net (HPN) called Discrete Continue elementary HPN. The method enables us to analyze some system's properties using the linear hybrid automaton generated by the mapping process. The method is applied to a three tanks water system and analyzed by a PHAVer software tool. Its effectiveness is illustrated by numerical simulation results.","PeriodicalId":404577,"journal":{"name":"2010 International Conference on Machine and Web Intelligence","volume":"219 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134124857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-11-29DOI: 10.1109/ICMWI.2010.5648110
I. Sayad, J. Martinet, T. Urruty, Samir Amir, C. Djeraba
Having effective methods to access the desired images is essential nowadays with the availability of huge amount of digital images. The proposed approach is based on an analogy between image retrieval containing desired objects (object-based image retrieval) and text retrieval. We propose a higher-level visual representation, for object-based image retrieval beyond visual appearances. The proposed visual representation improves the traditional part-based bag-of-words image representation, in two aspects. First, the approach strengthens the discrimination power of visual words by constructing an mid level descriptor, visual phrase, from frequently co-occurring and non noisy visual word-set in the same local context. Second, to bridge the visual appearance difference or to achieve better intra-class invariance power, the approach clusters visual words and phrases into visual sentence, based on their class probability distribution.
{"title":"Effective object-based image retrieval using higher-level visual representation","authors":"I. Sayad, J. Martinet, T. Urruty, Samir Amir, C. Djeraba","doi":"10.1109/ICMWI.2010.5648110","DOIUrl":"https://doi.org/10.1109/ICMWI.2010.5648110","url":null,"abstract":"Having effective methods to access the desired images is essential nowadays with the availability of huge amount of digital images. The proposed approach is based on an analogy between image retrieval containing desired objects (object-based image retrieval) and text retrieval. We propose a higher-level visual representation, for object-based image retrieval beyond visual appearances. The proposed visual representation improves the traditional part-based bag-of-words image representation, in two aspects. First, the approach strengthens the discrimination power of visual words by constructing an mid level descriptor, visual phrase, from frequently co-occurring and non noisy visual word-set in the same local context. Second, to bridge the visual appearance difference or to achieve better intra-class invariance power, the approach clusters visual words and phrases into visual sentence, based on their class probability distribution.","PeriodicalId":404577,"journal":{"name":"2010 International Conference on Machine and Web Intelligence","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132363805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-11-29DOI: 10.1109/ICMWI.2010.5647881
Hicham Behja, E. Zemmouri, A. Marzak
In this paper, we propose a new approach that makes the viewpoint notion explicit in a multiview Knowledge Discovery in Databases (KDD) process. We define a viewpoint in KDD as an analyst's perception of a KDD process, which refers to his own knowledge. Our purpose is to facilitate both the reusability and adaptability of a KDD process, and to reduce its complexity whilst maintaining the trace of the past analysis in terms of viewpoints. We also propose a viewpoint-based conceptual model for KDD process that integrates both the analyzed and the analyst domain knowledge.
{"title":"Viewpoint-based annotations for Knowledge Discovery in Databases","authors":"Hicham Behja, E. Zemmouri, A. Marzak","doi":"10.1109/ICMWI.2010.5647881","DOIUrl":"https://doi.org/10.1109/ICMWI.2010.5647881","url":null,"abstract":"In this paper, we propose a new approach that makes the viewpoint notion explicit in a multiview Knowledge Discovery in Databases (KDD) process. We define a viewpoint in KDD as an analyst's perception of a KDD process, which refers to his own knowledge. Our purpose is to facilitate both the reusability and adaptability of a KDD process, and to reduce its complexity whilst maintaining the trace of the past analysis in terms of viewpoints. We also propose a viewpoint-based conceptual model for KDD process that integrates both the analyzed and the analyst domain knowledge.","PeriodicalId":404577,"journal":{"name":"2010 International Conference on Machine and Web Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131158921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：