Shadi Shahoud, Hatem Khalloof, Moritz Winter, Clemens Düpmeier, V. Hagenmeyer
For a given specific machine learning task, very often several machine learning algorithms and their right configurations are tested in a trial-and-error approach, until an adequate solution is found. This wastes human resources for constructing multiple models, requires a data analytics expert and is time-consuming, since a variety of learning algorithms are proposed in literature and the non-expert users do not know which one to use in order to obtain good performance results. Meta learning addresses these problems and supports non-expert users by recommending a promising learning algorithm based on meta features computed from a given dataset. In the present paper, a new generic microservice-based framework for realizing the concept of meta learning in Big Data environments is introduced. This framework makes use of a powerful Big Data software stack, container visualization, modern web technologies and a microservice architecture for a fully manageable and highly scalable solution. In this demonstration and for evaluation purpose, time series model selection is taken into account. The performance and usability of the new framework is evaluated on state-of-the-art machine learning algorithms for time series forecasting: it is shown that the proposed microservice-based meta learning framework introduces an excellent performance in assigning the adequate forecasting model for the chosen time series datasets. Moreover, the recommendation of the most appropriate forecasting model results in a well acceptable low overhead demonstrating that the framework can provide an efficient approach to solve the problem of model selection in context of Big Data.
{"title":"A Meta Learning Approach for Automating Model Selection in Big Data Environments using Microservice and Container Virtualization Technologies","authors":"Shadi Shahoud, Hatem Khalloof, Moritz Winter, Clemens Düpmeier, V. Hagenmeyer","doi":"10.1145/3415958.3433072","DOIUrl":"https://doi.org/10.1145/3415958.3433072","url":null,"abstract":"For a given specific machine learning task, very often several machine learning algorithms and their right configurations are tested in a trial-and-error approach, until an adequate solution is found. This wastes human resources for constructing multiple models, requires a data analytics expert and is time-consuming, since a variety of learning algorithms are proposed in literature and the non-expert users do not know which one to use in order to obtain good performance results. Meta learning addresses these problems and supports non-expert users by recommending a promising learning algorithm based on meta features computed from a given dataset. In the present paper, a new generic microservice-based framework for realizing the concept of meta learning in Big Data environments is introduced. This framework makes use of a powerful Big Data software stack, container visualization, modern web technologies and a microservice architecture for a fully manageable and highly scalable solution. In this demonstration and for evaluation purpose, time series model selection is taken into account. The performance and usability of the new framework is evaluated on state-of-the-art machine learning algorithms for time series forecasting: it is shown that the proposed microservice-based meta learning framework introduces an excellent performance in assigning the adequate forecasting model for the chosen time series datasets. Moreover, the recommendation of the most appropriate forecasting model results in a well acceptable low overhead demonstrating that the framework can provide an efficient approach to solve the problem of model selection in context of Big Data.","PeriodicalId":198419,"journal":{"name":"Proceedings of the 12th International Conference on Management of Digital EcoSystems","volume":"184 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124914520","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}
New technologies and approaches lead to the Internet of Things (IoT) paradigm. Such a paradigm enables the engineering of more autonomous and smarter software systems solutions. Due to its multidisciplinary nature, it involves several knowledge areas such as software and connectivity that should be combined coherently and uniformly. It should comprise different voices and expertise to deal with IoT in a multi-faceted way. In this context, what to consider while specifying, designing, and implementing IoT software systems? This work raises this discussion by defining a roadmap about what should be considered for engineering IoT software respecting all their facets. Such a roadmap is defined based on evidence acquired at the technical literature combined with a qualitative study.
{"title":"Towards a Roadmap for the Internet of Things Software Systems Engineering","authors":"R. Motta, K. Oliveira, G. Travassos","doi":"10.1145/3415958.3433100","DOIUrl":"https://doi.org/10.1145/3415958.3433100","url":null,"abstract":"New technologies and approaches lead to the Internet of Things (IoT) paradigm. Such a paradigm enables the engineering of more autonomous and smarter software systems solutions. Due to its multidisciplinary nature, it involves several knowledge areas such as software and connectivity that should be combined coherently and uniformly. It should comprise different voices and expertise to deal with IoT in a multi-faceted way. In this context, what to consider while specifying, designing, and implementing IoT software systems? This work raises this discussion by defining a roadmap about what should be considered for engineering IoT software respecting all their facets. Such a roadmap is defined based on evidence acquired at the technical literature combined with a qualitative study.","PeriodicalId":198419,"journal":{"name":"Proceedings of the 12th International Conference on Management of Digital EcoSystems","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126375210","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}
The Latent Dirichlet Allocation (LDA) model [18] was originally developed and utilised for document modeling and topic extraction in Information Retrieval. To design high quality domain ontologies, effective and usable methodologies are needed to facilitate their building process. In this paper, we propose a new approach for semi-automatic ontology enriching from textual corpus based on LDA model. In our approach, LDA is adopted to provide efficient dimension reduction, able to capture semantic relationships between word-topic and topic-document in terms of probability distributions with minimum human intervention. We conducted several experiments with different model parameters and the corresponding behavior of the enriching technique was evaluated by domain experts. We also compared the results of our method with two existing learning methods using the same dataset. The study showed that our method outperforms the other methods in terms of recall and precision measures.
{"title":"LEOnto","authors":"Anis Tissaoui, S. Sassi, R. Chbeir","doi":"10.1145/3415958.3433076","DOIUrl":"https://doi.org/10.1145/3415958.3433076","url":null,"abstract":"The Latent Dirichlet Allocation (LDA) model [18] was originally developed and utilised for document modeling and topic extraction in Information Retrieval. To design high quality domain ontologies, effective and usable methodologies are needed to facilitate their building process. In this paper, we propose a new approach for semi-automatic ontology enriching from textual corpus based on LDA model. In our approach, LDA is adopted to provide efficient dimension reduction, able to capture semantic relationships between word-topic and topic-document in terms of probability distributions with minimum human intervention. We conducted several experiments with different model parameters and the corresponding behavior of the enriching technique was evaluated by domain experts. We also compared the results of our method with two existing learning methods using the same dataset. The study showed that our method outperforms the other methods in terms of recall and precision measures.","PeriodicalId":198419,"journal":{"name":"Proceedings of the 12th International Conference on Management of Digital EcoSystems","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115582575","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}
Polychronis Velentzas, M. Vassilakopoulos, A. Corral
The k Nearest-Neighbor (k-NN) query is a common spatial query that appears in several big data applications. Typically, GPU devices have much larger numbers of processing cores than CPUs and faster device memory than main memory accessed by CPUs, thus, providing higher computing power. We propose and implement a new GPU-based partitioning algorithm for the k-NN query, using the CUDA runtime API. Due to partitioning, this algorithm avoids calculating distances for the whole dataset. Using synthetic and real datasets, we present an extensive experimental performance comparison against six existing algorithms. These algorithms are based on calculating distances for the whole in-memory dataset. This comparison shows that the new algorithm excels in all the conducted experiments and outperforms these six algorithms.
{"title":"A Partitioning GPU-based Algorithm for Processing the k Nearest-Neighbor Query","authors":"Polychronis Velentzas, M. Vassilakopoulos, A. Corral","doi":"10.1145/3415958.3433071","DOIUrl":"https://doi.org/10.1145/3415958.3433071","url":null,"abstract":"The k Nearest-Neighbor (k-NN) query is a common spatial query that appears in several big data applications. Typically, GPU devices have much larger numbers of processing cores than CPUs and faster device memory than main memory accessed by CPUs, thus, providing higher computing power. We propose and implement a new GPU-based partitioning algorithm for the k-NN query, using the CUDA runtime API. Due to partitioning, this algorithm avoids calculating distances for the whole dataset. Using synthetic and real datasets, we present an extensive experimental performance comparison against six existing algorithms. These algorithms are based on calculating distances for the whole in-memory dataset. This comparison shows that the new algorithm excels in all the conducted experiments and outperforms these six algorithms.","PeriodicalId":198419,"journal":{"name":"Proceedings of the 12th International Conference on Management of Digital EcoSystems","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124804334","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}
This paper proposes a Secure and Privacy-preserving Tracing (SPT) mechanism in the Fog Computing (FC) network. The proposed SPT mechanism employs a Counting Bloom Filter (CBF) method as a tree framework (CBF-tree) to model a secure tracing system in the FC network. With the proposed SPT mechanism, the fog node can trace a particular Internet of Things (IoT) device in a secure manner, which means that the fog node can trace IoT devices in order to provide them with their requested services without revealing their private data such as the device's identities or locations. Analysis shows that the SPT mechanism is both efficient and resilient against tracing attacks. Simulation results are provided to show that the proposed mechanism is beneficial to the FC network.
{"title":"A Secure Tracing Method in Fog Computing Network for the IoT Devices","authors":"A. Alamer, Sultan Basudan, P. Hung","doi":"10.1145/3415958.3433074","DOIUrl":"https://doi.org/10.1145/3415958.3433074","url":null,"abstract":"This paper proposes a Secure and Privacy-preserving Tracing (SPT) mechanism in the Fog Computing (FC) network. The proposed SPT mechanism employs a Counting Bloom Filter (CBF) method as a tree framework (CBF-tree) to model a secure tracing system in the FC network. With the proposed SPT mechanism, the fog node can trace a particular Internet of Things (IoT) device in a secure manner, which means that the fog node can trace IoT devices in order to provide them with their requested services without revealing their private data such as the device's identities or locations. Analysis shows that the SPT mechanism is both efficient and resilient against tracing attacks. Simulation results are provided to show that the proposed mechanism is beneficial to the FC network.","PeriodicalId":198419,"journal":{"name":"Proceedings of the 12th International Conference on Management of Digital EcoSystems","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126513152","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}
Effective retrieval of jurisprudence (case-law) is imperative to achieve consistency and predictability for any legal system. In this work, we propose and proceed to an empirical evaluation of a framework for jurisprudence retrieval of the Brazilian Superior Court of Justice in order to ease the task of retrieval of other decisions with the same legal opinion. The experimental results shown that our approach based on text similarity performs better than the legacy system of the Court based on Boolean queries. The building of complex Boolean queries is very specialized and we aim to offer a tool able to use free text as queries without any operator. With the legacy system as baseline, we compare the TF-IDF traditional retrieval model, the BM25 probabilistic model and the Word2Vec model. Our results indicate that the Word2Vec Skip-Gram model, trained on a specialized legal corpus and BM25 yield similar performance and surpasses the legacy system. Combining BM25 model with embedding models improved the performance up to 19%.
{"title":"A new conceptual framework for enhancing legal information retrieval at the Brazilian Superior Court of Justice","authors":"Thiago Gomes, M. Ladeira","doi":"10.1145/3415958.3433087","DOIUrl":"https://doi.org/10.1145/3415958.3433087","url":null,"abstract":"Effective retrieval of jurisprudence (case-law) is imperative to achieve consistency and predictability for any legal system. In this work, we propose and proceed to an empirical evaluation of a framework for jurisprudence retrieval of the Brazilian Superior Court of Justice in order to ease the task of retrieval of other decisions with the same legal opinion. The experimental results shown that our approach based on text similarity performs better than the legacy system of the Court based on Boolean queries. The building of complex Boolean queries is very specialized and we aim to offer a tool able to use free text as queries without any operator. With the legacy system as baseline, we compare the TF-IDF traditional retrieval model, the BM25 probabilistic model and the Word2Vec model. Our results indicate that the Word2Vec Skip-Gram model, trained on a specialized legal corpus and BM25 yield similar performance and surpasses the legacy system. Combining BM25 model with embedding models improved the performance up to 19%.","PeriodicalId":198419,"journal":{"name":"Proceedings of the 12th International Conference on Management of Digital EcoSystems","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132013966","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}
In this paper, we describe the design and a prototypical implementation of an open system (ASPires) for the early prevention and early detection of forest fires. Forest fires cause huge, constantly increasing material damage and immaterial costs to humans, the environment and property. Among others, the use of new sensor and mobile communication technologies, the use of drones, data storage and analysis in a cloud, and direct connection with authorities reduces reaction time and thereby damage. Also, biodiversity is sustained in remote areas with rare and endemic species of flora and fauna. This has been tested and proven in 3 national parks in South East Europe.
{"title":"A Retrospective on ASPires: An Advanced System for the Prevention and Early Detection of Forest Fires","authors":"P. Peinl","doi":"10.1145/3415958.3433039","DOIUrl":"https://doi.org/10.1145/3415958.3433039","url":null,"abstract":"In this paper, we describe the design and a prototypical implementation of an open system (ASPires) for the early prevention and early detection of forest fires. Forest fires cause huge, constantly increasing material damage and immaterial costs to humans, the environment and property. Among others, the use of new sensor and mobile communication technologies, the use of drones, data storage and analysis in a cloud, and direct connection with authorities reduces reaction time and thereby damage. Also, biodiversity is sustained in remote areas with rare and endemic species of flora and fauna. This has been tested and proven in 3 national parks in South East Europe.","PeriodicalId":198419,"journal":{"name":"Proceedings of the 12th International Conference on Management of Digital EcoSystems","volume":"08 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130738407","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}
G. Gianini, C. Mio, F. Viola, Jianyi Lin, Nawaf I. Almoosa
In this work we address the problem of critical source selection in social sensing. We propose an approach to the ranking of information streams, which is aware of the interdependence among streams (redundancy and synergies), of the cost of individual streams, and of the cost related to the integration of multiple streams. The method is based on the use of the Coalitional Game Theory concept of Power Index, and relies on the polynomial-time estimate of the stream sets characteristics. With respect to other works using a power index, the method takes into account that the problem has a non-trivial cost structure.
{"title":"Selection of Information Streams in Social Sensing: an Interdependence- and Cost-aware Ranking Method","authors":"G. Gianini, C. Mio, F. Viola, Jianyi Lin, Nawaf I. Almoosa","doi":"10.1145/3415958.3433099","DOIUrl":"https://doi.org/10.1145/3415958.3433099","url":null,"abstract":"In this work we address the problem of critical source selection in social sensing. We propose an approach to the ranking of information streams, which is aware of the interdependence among streams (redundancy and synergies), of the cost of individual streams, and of the cost related to the integration of multiple streams. The method is based on the use of the Coalitional Game Theory concept of Power Index, and relies on the polynomial-time estimate of the stream sets characteristics. With respect to other works using a power index, the method takes into account that the problem has a non-trivial cost structure.","PeriodicalId":198419,"journal":{"name":"Proceedings of the 12th International Conference on Management of Digital EcoSystems","volume":"46 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115264973","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}
B. Banihashemi, Z. Maamar, Noura Faci, E. Ugljanin
In the Internet of Things (IoT), mutation aims to enhance functionality and survivability of a thing in the context of dynamic environments by allowing the thing to satisfy a need or seize a potential opportunity. In this paper, we propose a framework based on thing mutation as a countermeasure to certain security threats that could impact things' operations (e.g., sensing and communicating). We then provide a case study which focuses on battery draining attack and propose a mutation-based strategy as a countermeasure to this attack.
{"title":"Thing Mutation as a Countermeasure to Safeguard IoT","authors":"B. Banihashemi, Z. Maamar, Noura Faci, E. Ugljanin","doi":"10.1145/3415958.3433033","DOIUrl":"https://doi.org/10.1145/3415958.3433033","url":null,"abstract":"In the Internet of Things (IoT), mutation aims to enhance functionality and survivability of a thing in the context of dynamic environments by allowing the thing to satisfy a need or seize a potential opportunity. In this paper, we propose a framework based on thing mutation as a countermeasure to certain security threats that could impact things' operations (e.g., sensing and communicating). We then provide a case study which focuses on battery draining attack and propose a mutation-based strategy as a countermeasure to this attack.","PeriodicalId":198419,"journal":{"name":"Proceedings of the 12th International Conference on Management of Digital EcoSystems","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128003569","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}
Nitin Sukhija, Elizabeth Bautista, Owen James, Daniel Gens, Siqi Deng, Yu Lam, Tony Quan, Basil Lalli
The challenge of monitoring and event response management of a high performance computing facility grows significantly as the facilities employs and orchestrates more complex and heterogeneous systems and infrastructure. As the computational components encompassing the HPC facility system increases, the computational staff experiences rise in alert fatigue due to the false alarms and noise related to the similar events generated by monitoring tools. The National Energy Research Scientific Computing Center (NERSC) at the Lawrence Berkeley National Laboratory (LBNL) has begun to address the issues of duplication of alerts and alert remediation. However, more automation and integration is needed for collecting, aggregating, correlating, analyzing, managing and visualizing the scale of events that will be generated by the emergent hybrid computing infrastructures. In this paper, we present an event management and monitoring framework that addresses the operational needs of the future pre-exascale systems at the Lawrence Berkeley National Laboratory's National Energy Research Scientific Computing Center (NERSC). The framework integrates the Operations Monitoring and Notification Infrastructure (OMNI) at NERSC with the Prometheus, Grafana and ServiceNow platforms to help identify, diagnose, and resolve incidents in real-time, as well as conduct more thorough post-incident reviews enabled by the intuitive dashboards that provides a single pane of glass console for an efficient operations management and real-time proactive monitoring.
{"title":"Event Management and Monitoring Framework for HPC Environments using ServiceNow and Prometheus","authors":"Nitin Sukhija, Elizabeth Bautista, Owen James, Daniel Gens, Siqi Deng, Yu Lam, Tony Quan, Basil Lalli","doi":"10.1145/3415958.3433046","DOIUrl":"https://doi.org/10.1145/3415958.3433046","url":null,"abstract":"The challenge of monitoring and event response management of a high performance computing facility grows significantly as the facilities employs and orchestrates more complex and heterogeneous systems and infrastructure. As the computational components encompassing the HPC facility system increases, the computational staff experiences rise in alert fatigue due to the false alarms and noise related to the similar events generated by monitoring tools. The National Energy Research Scientific Computing Center (NERSC) at the Lawrence Berkeley National Laboratory (LBNL) has begun to address the issues of duplication of alerts and alert remediation. However, more automation and integration is needed for collecting, aggregating, correlating, analyzing, managing and visualizing the scale of events that will be generated by the emergent hybrid computing infrastructures. In this paper, we present an event management and monitoring framework that addresses the operational needs of the future pre-exascale systems at the Lawrence Berkeley National Laboratory's National Energy Research Scientific Computing Center (NERSC). The framework integrates the Operations Monitoring and Notification Infrastructure (OMNI) at NERSC with the Prometheus, Grafana and ServiceNow platforms to help identify, diagnose, and resolve incidents in real-time, as well as conduct more thorough post-incident reviews enabled by the intuitive dashboards that provides a single pane of glass console for an efficient operations management and real-time proactive monitoring.","PeriodicalId":198419,"journal":{"name":"Proceedings of the 12th International Conference on Management of Digital EcoSystems","volume":"2013 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128868068","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：