Distracted driving action is the main cause of car accidents. In recent years, CNN-based driving action recognition methods have become mainstream. However, these methods train CNN model using a centralized manner, not only need to collect a large amount of data in advance, which may leak user privacy, but also make it difficult for model upgrades. In this paper, we use federated learning for model training, which protects user privacy while achieving online model upgrades. The experiments based on the State Farm dataset show that whether it is under iid or non-iid settings, the accuracy achieved by the model trained using federated learning is competitive with that of the model obtained by centralized training.
{"title":"Driver Action Recognition Using Federated Learning","authors":"Bin Zhang, Jingyang Wang, Junyi Fu, Jinxiang Xia","doi":"10.1145/3507971.3507985","DOIUrl":"https://doi.org/10.1145/3507971.3507985","url":null,"abstract":"Distracted driving action is the main cause of car accidents. In recent years, CNN-based driving action recognition methods have become mainstream. However, these methods train CNN model using a centralized manner, not only need to collect a large amount of data in advance, which may leak user privacy, but also make it difficult for model upgrades. In this paper, we use federated learning for model training, which protects user privacy while achieving online model upgrades. The experiments based on the State Farm dataset show that whether it is under iid or non-iid settings, the accuracy achieved by the model trained using federated learning is competitive with that of the model obtained by centralized training.","PeriodicalId":439757,"journal":{"name":"Proceedings of the 7th International Conference on Communication and Information Processing","volume":"792 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117055168","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}
C. Yang, Jian Xu, Yao Xie, Jingsheng Jiang, Yiwei Zhu
Application of BIM technology is getting deeper and deeper in the field of base station (BS) in smart grid system engineering, and the problem of the lack of BIM standards is becoming more and more prominent. Based on the characteristics of BS engineering, starting from the international LOD classification, combined with mature experience in construction engineering, manufacturing industry engineering, and other fields, we propose an BIM model classification principle suitable for smart grid system and the corresponding relationship between the engineering stages.
{"title":"Research on Fineness of BIM Model of Communication Base Station in Smart Power Grid System","authors":"C. Yang, Jian Xu, Yao Xie, Jingsheng Jiang, Yiwei Zhu","doi":"10.1145/3507971.3508011","DOIUrl":"https://doi.org/10.1145/3507971.3508011","url":null,"abstract":"Application of BIM technology is getting deeper and deeper in the field of base station (BS) in smart grid system engineering, and the problem of the lack of BIM standards is becoming more and more prominent. Based on the characteristics of BS engineering, starting from the international LOD classification, combined with mature experience in construction engineering, manufacturing industry engineering, and other fields, we propose an BIM model classification principle suitable for smart grid system and the corresponding relationship between the engineering stages.","PeriodicalId":439757,"journal":{"name":"Proceedings of the 7th International Conference on Communication and Information Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129819560","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}
Matrix Factorization is a widely adopted technique in the field of recommender system. Matrix Factorization techniques range from SVD, LDA, pLSA, SVD++, MatRec, Zipf Matrix Factorization and Item2Vec. In recent years, distributed word embeddings have inspired innovation in the area of recommender systems. Word2vec and GloVe have been especially emphasized in many industrial application scenario such as Xiaomi's recommender system. In this paper, we propose a new matrix factorization inspired by the theory of power law and GloVe. Instead of the exponential nature of GloVe model, we take advantage of Pareto Distribution to model our loss function. Our method is explainable in theory and easy-to-implement in practice. In the experiment section, we prove our approach is superior to vanilla matrix factorization technique and comparable with GloVe-based model in both accuracy and fairness metrics.
{"title":"RankMat: Matrix Factorization with Calibrated Distributed Embedding and Fairness Enhancement","authors":"Hao Wang","doi":"10.1145/3507971.3507976","DOIUrl":"https://doi.org/10.1145/3507971.3507976","url":null,"abstract":"Matrix Factorization is a widely adopted technique in the field of recommender system. Matrix Factorization techniques range from SVD, LDA, pLSA, SVD++, MatRec, Zipf Matrix Factorization and Item2Vec. In recent years, distributed word embeddings have inspired innovation in the area of recommender systems. Word2vec and GloVe have been especially emphasized in many industrial application scenario such as Xiaomi's recommender system. In this paper, we propose a new matrix factorization inspired by the theory of power law and GloVe. Instead of the exponential nature of GloVe model, we take advantage of Pareto Distribution to model our loss function. Our method is explainable in theory and easy-to-implement in practice. In the experiment section, we prove our approach is superior to vanilla matrix factorization technique and comparable with GloVe-based model in both accuracy and fairness metrics.","PeriodicalId":439757,"journal":{"name":"Proceedings of the 7th International Conference on Communication and Information Processing","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116478552","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}
Jingqi Li, Min Nie, Guang Yang, Kaijie Han, Jin Wang, Ting Gao, Feng Tian
In order to study the communication performance and parameter analysis of the satellite-to-earth link of the quantum satellite under the condition of forming snowfall in the stratosphere, firstly, according to the distribution function and extinction characteristics of the concentric spherical ice water condensation nuclei in the stratosphere and the snowfall, according to the Mie theory, the system environment is obtained. The extinction efficiency factor establishes the relationship between the quantum signal transmission distance and link attenuation under different system environmental levels. Further studies have been done to establish the relationship between channel capacity, survival function, bit error rate, transmission distance, and system environment level under the condition of long-distance transmission of optical quantum signals at a moderate proportion of stratus cloud and snowfall. The simulation shows that as the transmission distance and environmental level increase, the link attenuation gradually increases, the channel capacity and survival function are greatly reduced, and the bit error rate increases. Therefore, when performing satellite-to-earth link communication, the relevant parameters of quantum communication should be adjusted adaptively to reduce the influence of snowfall caused by the formation of stratus clouds and improve the transmission performance of quantum communication.
{"title":"Parameter analysis and performance simulation of satellite-earth quantum link under the condition of stratus form snowfall","authors":"Jingqi Li, Min Nie, Guang Yang, Kaijie Han, Jin Wang, Ting Gao, Feng Tian","doi":"10.1145/3507971.3508007","DOIUrl":"https://doi.org/10.1145/3507971.3508007","url":null,"abstract":"In order to study the communication performance and parameter analysis of the satellite-to-earth link of the quantum satellite under the condition of forming snowfall in the stratosphere, firstly, according to the distribution function and extinction characteristics of the concentric spherical ice water condensation nuclei in the stratosphere and the snowfall, according to the Mie theory, the system environment is obtained. The extinction efficiency factor establishes the relationship between the quantum signal transmission distance and link attenuation under different system environmental levels. Further studies have been done to establish the relationship between channel capacity, survival function, bit error rate, transmission distance, and system environment level under the condition of long-distance transmission of optical quantum signals at a moderate proportion of stratus cloud and snowfall. The simulation shows that as the transmission distance and environmental level increase, the link attenuation gradually increases, the channel capacity and survival function are greatly reduced, and the bit error rate increases. Therefore, when performing satellite-to-earth link communication, the relevant parameters of quantum communication should be adjusted adaptively to reduce the influence of snowfall caused by the formation of stratus clouds and improve the transmission performance of quantum communication.","PeriodicalId":439757,"journal":{"name":"Proceedings of the 7th International Conference on Communication and Information Processing","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121966811","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. Nneji, Jingye Cai, Jianhua Deng, H. Monday, E. James, Bona D. Lemessa, A. Z. Yutra, Y. B. Leta, Saifun Nahar
Chest X-ray has become a useful method in the detection of coronavirus disease-19 (COVID-19). Due to the extreme global COVID-19 crisis, using the computerized diagnosis method for COVID-19 classification upon CXR images could significantly decrease clinician workload. We explicitly addressed the issue of low CXR image resolution by using Super-Resolution Convolutional Neural Network (SRCNN) to effectively reconstruct high-resolution (HR) CXR images from low-resolution (LR) CXR correspondents. Then, the HRCXR images are fed into the modified capsule network to retrieve distinct features for the classification of COVID-19. We demonstrate the proposed model on a public dataset and achieve ACC of 97.3%, SEN of 97.8%, SPE of 96.9%, and AUC of 98.0%. This new conceptual framework is proposed to play a vital task in the issue facing COVID-19 and related ailments.
胸部x线检查已成为检测新型冠状病毒病(COVID-19)的一种有效方法。由于全球COVID-19危机的极端，使用计算机诊断方法根据CXR图像进行COVID-19分类可以显着减少临床医生的工作量。我们通过使用超分辨率卷积神经网络(SRCNN)从低分辨率(LR) CXR对应体中有效地重建高分辨率(HR) CXR图像，明确解决了低CXR图像分辨率的问题。然后，将HRCXR图像输入到改进的胶囊网络中，以检索不同特征，用于COVID-19分类。我们在一个公共数据集上验证了所提出的模型，并实现了ACC 97.3%， SEN 97.8%， SPE 96.9%和AUC 98.0%。提出这一新的概念框架是为了在COVID-19和相关疾病面临的问题上发挥重要作用。
{"title":"COVID-19 Identification Using Deep Capsule Network: A Perspective of Super-Resolution CNN on Low-Quality CXR Images","authors":"G. Nneji, Jingye Cai, Jianhua Deng, H. Monday, E. James, Bona D. Lemessa, A. Z. Yutra, Y. B. Leta, Saifun Nahar","doi":"10.1145/3507971.3507989","DOIUrl":"https://doi.org/10.1145/3507971.3507989","url":null,"abstract":"Chest X-ray has become a useful method in the detection of coronavirus disease-19 (COVID-19). Due to the extreme global COVID-19 crisis, using the computerized diagnosis method for COVID-19 classification upon CXR images could significantly decrease clinician workload. We explicitly addressed the issue of low CXR image resolution by using Super-Resolution Convolutional Neural Network (SRCNN) to effectively reconstruct high-resolution (HR) CXR images from low-resolution (LR) CXR correspondents. Then, the HRCXR images are fed into the modified capsule network to retrieve distinct features for the classification of COVID-19. We demonstrate the proposed model on a public dataset and achieve ACC of 97.3%, SEN of 97.8%, SPE of 96.9%, and AUC of 98.0%. This new conceptual framework is proposed to play a vital task in the issue facing COVID-19 and related ailments.","PeriodicalId":439757,"journal":{"name":"Proceedings of the 7th International Conference on Communication and Information Processing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127920194","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}
Chien-Hua Wang, Wei-Hsuan Lee, C. Yeh, Chin-Tzong Pang
∗With the increasing development of the “Internet Plus” economy and the rapid rise of e-commerce platforms, online shopping has become an indispensable part of daily life. With its original and novel model, the e-commerce platform, PinDuoDuo, and has emerged and become a veritable “EC dark horse”. However, in the EC platform, only merchants with good service quality and satisfaction can survive for a lone time. In this paper, we adopt information entropy to study the service quality and satisfaction of Pinduoduo so as to help the business to raise profits by means of improving the operating environment, the methods, and strategies.
{"title":"A Study of Service Quality and Satisfaction on PinDuoDuo Platform by Information Entropy","authors":"Chien-Hua Wang, Wei-Hsuan Lee, C. Yeh, Chin-Tzong Pang","doi":"10.1145/3507971.3507993","DOIUrl":"https://doi.org/10.1145/3507971.3507993","url":null,"abstract":"∗With the increasing development of the “Internet Plus” economy and the rapid rise of e-commerce platforms, online shopping has become an indispensable part of daily life. With its original and novel model, the e-commerce platform, PinDuoDuo, and has emerged and become a veritable “EC dark horse”. However, in the EC platform, only merchants with good service quality and satisfaction can survive for a lone time. In this paper, we adopt information entropy to study the service quality and satisfaction of Pinduoduo so as to help the business to raise profits by means of improving the operating environment, the methods, and strategies.","PeriodicalId":439757,"journal":{"name":"Proceedings of the 7th International Conference on Communication and Information Processing","volume":"203 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115496036","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 Wireless Sensor Networks (WSNs), we wish the range both of perception coverage and communication coverage is same. Being the limited energy in micro sensors, we would try to minimize the energy consumption in WSNs to prolong the networks lifetime. In this paper, we analyze most change cases of two parameters in WSNs. These two parameters are the cluster size and the propagation distance of data in the network. These two parameters often need to be considered or used when we design routing strategies. It is valuable to analyze them in theory. In addition, we have done numerical simulation and comparative analysis on two factors affecting cluster size: mixfactor and density based on LEACH. We believe that the density-factor might help to extend the lifetime of the network. The energy consumption in the network would be distributed uniformly.
{"title":"Setting and comparison of several parameters in clustering protocols for Wireless Sensor Networks","authors":"Dongmei Xing","doi":"10.1145/3507971.3508002","DOIUrl":"https://doi.org/10.1145/3507971.3508002","url":null,"abstract":"In Wireless Sensor Networks (WSNs), we wish the range both of perception coverage and communication coverage is same. Being the limited energy in micro sensors, we would try to minimize the energy consumption in WSNs to prolong the networks lifetime. In this paper, we analyze most change cases of two parameters in WSNs. These two parameters are the cluster size and the propagation distance of data in the network. These two parameters often need to be considered or used when we design routing strategies. It is valuable to analyze them in theory. In addition, we have done numerical simulation and comparative analysis on two factors affecting cluster size: mixfactor and density based on LEACH. We believe that the density-factor might help to extend the lifetime of the network. The energy consumption in the network would be distributed uniformly.","PeriodicalId":439757,"journal":{"name":"Proceedings of the 7th International Conference on Communication and Information Processing","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126292020","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 studies the synchronization of sampling frequency for OFDM systems. A method of blind synchronization of OFDM sampling frequency based on correlation peak is proposed. The interpolation algorithm is used to interpolate the sampled signals at different intervals. The peak position of the correlation curve between the interpolated signals and the cyclic prefix of the original signals is used for accurate estimation of effective symbol length, through which the accurate synchronization of sampling frequency offset is possible. The simulation results show that the method is independent of sampling frequency offset, carrier frequency offset and OFDM system baseband modulation method. With the method, a small number of OFDM symbols are needed for high-accuracy estimation of sampling frequency offset.
{"title":"Blind Synchronization Method of OFDM Sampling Frequency Based on Correlation Peak","authors":"Zixin Ye, Xi Tian, Hao Xie, Keju Zhang","doi":"10.1145/3507971.3508012","DOIUrl":"https://doi.org/10.1145/3507971.3508012","url":null,"abstract":"This paper studies the synchronization of sampling frequency for OFDM systems. A method of blind synchronization of OFDM sampling frequency based on correlation peak is proposed. The interpolation algorithm is used to interpolate the sampled signals at different intervals. The peak position of the correlation curve between the interpolated signals and the cyclic prefix of the original signals is used for accurate estimation of effective symbol length, through which the accurate synchronization of sampling frequency offset is possible. The simulation results show that the method is independent of sampling frequency offset, carrier frequency offset and OFDM system baseband modulation method. With the method, a small number of OFDM symbols are needed for high-accuracy estimation of sampling frequency offset.","PeriodicalId":439757,"journal":{"name":"Proceedings of the 7th International Conference on Communication and Information Processing","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129630532","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}
Hough transform has the advantage of incomplete edge recognition. A large number of practices show that: for the actual circular object detection, the detected points are usually concentrated in a relatively continuous arc. If the detected points are scattered in various positions of the circle, it is usually the interference of noise that causes the wrong recognition of the target. On this basis, this paper proposes an algorithm, that is, to calculate the standard deviation of the angle of the detected edge points, and compare the standard deviation value with the detected edge points, so as to judge whether the recognition of the circular object is correct. In this paper, the algorithm is applied to human head recognition and good results are obtained.
{"title":"Recognize Human Head Shot Top Down Based on Hough Transform","authors":"Y. He, Yiqun Huang, Zhibiao Li","doi":"10.1145/3507971.3507986","DOIUrl":"https://doi.org/10.1145/3507971.3507986","url":null,"abstract":"Hough transform has the advantage of incomplete edge recognition. A large number of practices show that: for the actual circular object detection, the detected points are usually concentrated in a relatively continuous arc. If the detected points are scattered in various positions of the circle, it is usually the interference of noise that causes the wrong recognition of the target. On this basis, this paper proposes an algorithm, that is, to calculate the standard deviation of the angle of the detected edge points, and compare the standard deviation value with the detected edge points, so as to judge whether the recognition of the circular object is correct. In this paper, the algorithm is applied to human head recognition and good results are obtained.","PeriodicalId":439757,"journal":{"name":"Proceedings of the 7th International Conference on Communication and Information Processing","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128912233","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 presents a hard switching decode and forward multihop hybrid free-space optical and radio frequency (FSO/RF) system. We aim to get better performance by changing modulation. The FSO channel is modeled using Gamma-Gamma distribution under IM/DD with Differential Phase Shift Keying Subcarrier Intensity Modulation (DPSK-SIM) scheme. The RF channel is modeled using Nakagami-m distribution. We derive a closed-form expression for the outage probability of the multi-hop FSO link using DPSK-SIM and consider the system performance under various haze weather conditions, including the impact of the number of hops, pointing error, and link distance. Finally, the performance of the DPSK-SIM is compared with the performance of phase-shift keying (PSK) modulation. The outcomes confirm that the DPSK-SIM scheme improves under different haze weather conditions, pointing error displacement (jitter), and hop to hop link distance. CCS CONCEPTS • Hardware → Integrated circuits; Interconnect; Photonic and optical interconnect.
{"title":"On the Performance Analysis of Multi-Hop Hybrid FSO/RF Systems Using DPSK-SIM Over Gamma-Gamma Turbulence Channel","authors":"Hailay TEKLEHAIMANOT BELAY, Hui Zhao, Andrews ALLOTEI OKINE","doi":"10.1145/3507971.3508014","DOIUrl":"https://doi.org/10.1145/3507971.3508014","url":null,"abstract":"This paper presents a hard switching decode and forward multihop hybrid free-space optical and radio frequency (FSO/RF) system. We aim to get better performance by changing modulation. The FSO channel is modeled using Gamma-Gamma distribution under IM/DD with Differential Phase Shift Keying Subcarrier Intensity Modulation (DPSK-SIM) scheme. The RF channel is modeled using Nakagami-m distribution. We derive a closed-form expression for the outage probability of the multi-hop FSO link using DPSK-SIM and consider the system performance under various haze weather conditions, including the impact of the number of hops, pointing error, and link distance. Finally, the performance of the DPSK-SIM is compared with the performance of phase-shift keying (PSK) modulation. The outcomes confirm that the DPSK-SIM scheme improves under different haze weather conditions, pointing error displacement (jitter), and hop to hop link distance. CCS CONCEPTS • Hardware → Integrated circuits; Interconnect; Photonic and optical interconnect.","PeriodicalId":439757,"journal":{"name":"Proceedings of the 7th International Conference on Communication and Information Processing","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129068130","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：