Pub Date : 2022-05-01DOI: 10.1109/ICSS55994.2022.00037
Xinyu Zhao, Chen Liu, Shuo Zhang, Xin You
To address the problems of large volume of science and technology information, low information value density, and matrix sparsity of recommendation algorithms, we propose STIR-KG, a science and technology information recommendation method integrating knowledge graph, and build a science and technology information recommendation service. The main contributions are: (1) Establishing a new material knowledge graph, which has been open-sourced in GitHub (2) Combining collaborative filtering methods with knowledge graphs to solve the cold-start and matrix sparsity problems. (3) Propose the representation learning method TransAR, which enhances the representation capability compared with traditional methods, and uses the Mahalanobis distance metric score function to reduce the influence of irrelevant dimensions on the similarity calculation. (4) Based on the STIR-KG method, we use the streaming computing framework Flink to build a recommendation service for scientific and technical information, which captures user interest migration in real time and makes the recommendation results more time-efficient. And according to the experimental verification, STIR-KG has significantly improved the accuracy and recall rate compared with other algorithms.
{"title":"A Novel Science and Technology Resource Recommendation Service based on Knowledege Graph and Collaborative Filtering","authors":"Xinyu Zhao, Chen Liu, Shuo Zhang, Xin You","doi":"10.1109/ICSS55994.2022.00037","DOIUrl":"https://doi.org/10.1109/ICSS55994.2022.00037","url":null,"abstract":"To address the problems of large volume of science and technology information, low information value density, and matrix sparsity of recommendation algorithms, we propose STIR-KG, a science and technology information recommendation method integrating knowledge graph, and build a science and technology information recommendation service. The main contributions are: (1) Establishing a new material knowledge graph, which has been open-sourced in GitHub (2) Combining collaborative filtering methods with knowledge graphs to solve the cold-start and matrix sparsity problems. (3) Propose the representation learning method TransAR, which enhances the representation capability compared with traditional methods, and uses the Mahalanobis distance metric score function to reduce the influence of irrelevant dimensions on the similarity calculation. (4) Based on the STIR-KG method, we use the streaming computing framework Flink to build a recommendation service for scientific and technical information, which captures user interest migration in real time and makes the recommendation results more time-efficient. And according to the experimental verification, STIR-KG has significantly improved the accuracy and recall rate compared with other algorithms.","PeriodicalId":327964,"journal":{"name":"2022 International Conference on Service Science (ICSS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127808925","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 : 2022-05-01DOI: 10.1109/ICSS55994.2022.00034
Yu-Shi Jiang, Chengkai Li, Ying Li
Microservice architecture promotes the cost reduction, efficiency increase, and quality improvement of software development. However, with the diversification of manufacturers’ technology and the complexity of the services, the existing research on unified access to microservice lacks a specification that can be summarized, and more intrusive transformations of access service are required in the access process. Aiming at the standardization of unified access of microservice, the Service Unified Access Model (SUAM) is proposed. The main purpose of the model is to solve the complexity of multi-language and multi-platform access of the microservice and the standardization of the access process. The model makes a contribution to the service from three aspects: service resources, product resources, and function properties. This model can not only describe the functionality of the service in more detail but also can help reduce the amount of access code by 15% without affecting the business function of the accessed service.
{"title":"SUAM: A Service Unified Access Model for Microservice Management","authors":"Yu-Shi Jiang, Chengkai Li, Ying Li","doi":"10.1109/ICSS55994.2022.00034","DOIUrl":"https://doi.org/10.1109/ICSS55994.2022.00034","url":null,"abstract":"Microservice architecture promotes the cost reduction, efficiency increase, and quality improvement of software development. However, with the diversification of manufacturers’ technology and the complexity of the services, the existing research on unified access to microservice lacks a specification that can be summarized, and more intrusive transformations of access service are required in the access process. Aiming at the standardization of unified access of microservice, the Service Unified Access Model (SUAM) is proposed. The main purpose of the model is to solve the complexity of multi-language and multi-platform access of the microservice and the standardization of the access process. The model makes a contribution to the service from three aspects: service resources, product resources, and function properties. This model can not only describe the functionality of the service in more detail but also can help reduce the amount of access code by 15% without affecting the business function of the accessed service.","PeriodicalId":327964,"journal":{"name":"2022 International Conference on Service Science (ICSS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115419229","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 : 2022-05-01DOI: 10.1109/ICSS55994.2022.00049
K. Xiao, Yuming Fu, Ying Deng, Lingmei Xia
Today, the Internet is flooded with a lot of learning resources, which are provided by different people. Because the relationship between these learning resources is unclear, it is difficult for instructors and students to use these learning resources for curriculum design and learning path planning. The order of learning resources is usually determined by the core knowledge concepts addressed in each resource. Therefore, identifying the prerequisite relations between concepts will be the key to solving the above problems. In this article, we take Wikipedia as an example and propose a new method for identifying concept prerequisite relations. We define five groups of features for concept pairs and predict whether there is a prerequisite relations between two concepts. Experimental results show that the performance of the proposed method exceeds the existing baselines.
{"title":"Identifying Prerequisite Relations Between Concepts In Wikipedia","authors":"K. Xiao, Yuming Fu, Ying Deng, Lingmei Xia","doi":"10.1109/ICSS55994.2022.00049","DOIUrl":"https://doi.org/10.1109/ICSS55994.2022.00049","url":null,"abstract":"Today, the Internet is flooded with a lot of learning resources, which are provided by different people. Because the relationship between these learning resources is unclear, it is difficult for instructors and students to use these learning resources for curriculum design and learning path planning. The order of learning resources is usually determined by the core knowledge concepts addressed in each resource. Therefore, identifying the prerequisite relations between concepts will be the key to solving the above problems. In this article, we take Wikipedia as an example and propose a new method for identifying concept prerequisite relations. We define five groups of features for concept pairs and predict whether there is a prerequisite relations between two concepts. Experimental results show that the performance of the proposed method exceeds the existing baselines.","PeriodicalId":327964,"journal":{"name":"2022 International Conference on Service Science (ICSS)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116678263","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 : 2022-05-01DOI: 10.1109/icss55994.2022.00042
C. Min, Dongcheng Zhao, Huajie Lu
Machine learning methods have many excellent properties, such as the quality and efficiency of algorithmic that increase with the number of training sessions as new data is fed in. In a large network topology, how to balance the traffic in the network and improve the link utilization has always been a concern of network engineers. We take advantage of the Programming Protocol-Independent Packet Processors(P4) language with protocol-independent features, use in-band telemetry to collect port traffic statistics, delays and other information on the link, use routing protocols to collect topology, weight etc and transmit these information to machine learning server through the Google Remote Procedure Calls(gRPC) interface. The machine learning server uses a machine learning algorithm to generate a policy for adjusting the traffic, converts the policy into a forwarding table and sends it to the forwarding plane to balance the link traffic.
{"title":"A Machine Learning Method and Device Based on Programmable Switch","authors":"C. Min, Dongcheng Zhao, Huajie Lu","doi":"10.1109/icss55994.2022.00042","DOIUrl":"https://doi.org/10.1109/icss55994.2022.00042","url":null,"abstract":"Machine learning methods have many excellent properties, such as the quality and efficiency of algorithmic that increase with the number of training sessions as new data is fed in. In a large network topology, how to balance the traffic in the network and improve the link utilization has always been a concern of network engineers. We take advantage of the Programming Protocol-Independent Packet Processors(P4) language with protocol-independent features, use in-band telemetry to collect port traffic statistics, delays and other information on the link, use routing protocols to collect topology, weight etc and transmit these information to machine learning server through the Google Remote Procedure Calls(gRPC) interface. The machine learning server uses a machine learning algorithm to generate a policy for adjusting the traffic, converts the policy into a forwarding table and sends it to the forwarding plane to balance the link traffic.","PeriodicalId":327964,"journal":{"name":"2022 International Conference on Service Science (ICSS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130678857","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 : 2022-05-01DOI: 10.1109/ICSS55994.2022.00019
Yuqi Zhang, Nancy Wang, Jian Yu, Sira Yongchareon, Mo Nguyen
Many real-world networks including the World Wide Web and the Internet of Things are graphs in their abstract forms. Graph neural networks (GNNs) have emerged as the main solution for deep learning on graphs. Recently, tremendous effort has been made to enhance the performance and expressivity of GNNs. In this paper, we review the state-of-the-art graph neural network models and frameworks with a focus on the latest developments in graph representation learning. We propose a new taxonomy which divides general GNNs into recurrent GNNs, spectral GNNs, spatial GNNs and topology-aware GNNs. We will also discuss the inductive biases behind different categories of GNNs.
{"title":"A Short Survey on Inductive Biased Graph Neural Networks","authors":"Yuqi Zhang, Nancy Wang, Jian Yu, Sira Yongchareon, Mo Nguyen","doi":"10.1109/ICSS55994.2022.00019","DOIUrl":"https://doi.org/10.1109/ICSS55994.2022.00019","url":null,"abstract":"Many real-world networks including the World Wide Web and the Internet of Things are graphs in their abstract forms. Graph neural networks (GNNs) have emerged as the main solution for deep learning on graphs. Recently, tremendous effort has been made to enhance the performance and expressivity of GNNs. In this paper, we review the state-of-the-art graph neural network models and frameworks with a focus on the latest developments in graph representation learning. We propose a new taxonomy which divides general GNNs into recurrent GNNs, spectral GNNs, spatial GNNs and topology-aware GNNs. We will also discuss the inductive biases behind different categories of GNNs.","PeriodicalId":327964,"journal":{"name":"2022 International Conference on Service Science (ICSS)","volume":"124 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129590405","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 : 2022-05-01DOI: 10.1109/ICSS55994.2022.00015
Wenxuan Liu, Donghong Zhang, Jindong Zhao
With the rapid development of blockchain applications, the data that need to be stored increases dramatically, and the blockchain is about to face the problem of storage limitations. To deal with this problem, this paper proposes a storage scaling mechanism for Hyperledger Fabric, which relieves the storage pressure by dividing the peer nodes into clusters, and each node only stores partial data instead of the whole ledger. First, all accounting nodes are divided into clusters that include several nodes respectively, and part of the whole block data is stored in a single cluster; then, the block data are stored overlappingly on some nodes in the cluster, and each block is guaranteed to have some copies in a cluster. By arranging the copies on selected nodes according to our proposed mechanism, all the blocks are overlapped in a cluster. Theoretical analysis and simulation show that the storage volume occupied by nodes is decreased significantly in blockchain applications with frequent transactions, and in the case that the number of node failures in a single cluster does not exceed the threshold, the mechanism can still guarantee data integrity. Moreover, for applications with frequent transactions, storage space consumption can be significantly reduced without increasing excessive query time overhead.
{"title":"Ring-Overlap: A Storage Scaling Mechanism For Consortium Blockchain","authors":"Wenxuan Liu, Donghong Zhang, Jindong Zhao","doi":"10.1109/ICSS55994.2022.00015","DOIUrl":"https://doi.org/10.1109/ICSS55994.2022.00015","url":null,"abstract":"With the rapid development of blockchain applications, the data that need to be stored increases dramatically, and the blockchain is about to face the problem of storage limitations. To deal with this problem, this paper proposes a storage scaling mechanism for Hyperledger Fabric, which relieves the storage pressure by dividing the peer nodes into clusters, and each node only stores partial data instead of the whole ledger. First, all accounting nodes are divided into clusters that include several nodes respectively, and part of the whole block data is stored in a single cluster; then, the block data are stored overlappingly on some nodes in the cluster, and each block is guaranteed to have some copies in a cluster. By arranging the copies on selected nodes according to our proposed mechanism, all the blocks are overlapped in a cluster. Theoretical analysis and simulation show that the storage volume occupied by nodes is decreased significantly in blockchain applications with frequent transactions, and in the case that the number of node failures in a single cluster does not exceed the threshold, the mechanism can still guarantee data integrity. Moreover, for applications with frequent transactions, storage space consumption can be significantly reduced without increasing excessive query time overhead.","PeriodicalId":327964,"journal":{"name":"2022 International Conference on Service Science (ICSS)","volume":"258 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122740779","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 : 2022-05-01DOI: 10.1109/icss55994.2022.00026
Ziliang Wang, Tingting Zhang, Y. Li, Sheng Wang, F. Zhou, Lei Feng, Wenjing Li
With the development of mobile communication, network technology, and the continuous emergence of intelligent network applications, users' demand for network computing power has increased explosively, which promoted the formation of a multi-level computing power system composed of the end devices, mobile network edge cloud, and center clouds. The terminal and edge computing power resources are limited. The cloud computing power is rich, but the delay is high, so the computing power at all levels needs effective cooperation to meet the quality of service requirements of various ubiquitous computing services. In this trend, cloud computing and edge computing begin to evolve into networked collaborative computing. In this paper, a task scheduling heuristic algorithm based on task cost minimization is proposed for network computing services with a large amount of communication and computation and high delay cost. This method divides the computing tasks of network applications into multiple granularities and schedules the divided sub-tasks, which can improve the utilization of the distributed computing resources and enhance the collaborative scheduling capability of computing and network resources.
{"title":"Multi-Granularity Decomposition based Task Scheduling for Migration Cost Minimization","authors":"Ziliang Wang, Tingting Zhang, Y. Li, Sheng Wang, F. Zhou, Lei Feng, Wenjing Li","doi":"10.1109/icss55994.2022.00026","DOIUrl":"https://doi.org/10.1109/icss55994.2022.00026","url":null,"abstract":"With the development of mobile communication, network technology, and the continuous emergence of intelligent network applications, users' demand for network computing power has increased explosively, which promoted the formation of a multi-level computing power system composed of the end devices, mobile network edge cloud, and center clouds. The terminal and edge computing power resources are limited. The cloud computing power is rich, but the delay is high, so the computing power at all levels needs effective cooperation to meet the quality of service requirements of various ubiquitous computing services. In this trend, cloud computing and edge computing begin to evolve into networked collaborative computing. In this paper, a task scheduling heuristic algorithm based on task cost minimization is proposed for network computing services with a large amount of communication and computation and high delay cost. This method divides the computing tasks of network applications into multiple granularities and schedules the divided sub-tasks, which can improve the utilization of the distributed computing resources and enhance the collaborative scheduling capability of computing and network resources.","PeriodicalId":327964,"journal":{"name":"2022 International Conference on Service Science (ICSS)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131186512","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 : 2022-05-01DOI: 10.1109/ICSS55994.2022.00021
M. Hesenius, Nils Schwenzfeier, Ole Meyer, V. Gruhn
With the increased availability of solutions using Artificial Intelligence and Machine Learning, more and more business processes are based on technical components delivering probabilistic results. A prominent examples are applications from the Internet of Things that heavily rely on sensor information and data stream processing. Another trend that is gaining more traction is the use of No- and Low-Code-Platforms to create applications. Such approaches focus on defining the business logic via business process modeling and automatically create a corresponding executable application. We argue that using components based on Artificial Intelligence and Machine Learning in such applications requires to handle uncertainty resulting from probabilistic results accordingly. This means to introduce, e.g., fallback mechanisms if results delivered from composing using Artificial Intelligence err into modeled business processes. In this position paper, we discuss scenarios, arising problems, and potential solutions.
{"title":"On the Uncertainty in IoT-enabled Business Processes using Artificial Intelligence Components","authors":"M. Hesenius, Nils Schwenzfeier, Ole Meyer, V. Gruhn","doi":"10.1109/ICSS55994.2022.00021","DOIUrl":"https://doi.org/10.1109/ICSS55994.2022.00021","url":null,"abstract":"With the increased availability of solutions using Artificial Intelligence and Machine Learning, more and more business processes are based on technical components delivering probabilistic results. A prominent examples are applications from the Internet of Things that heavily rely on sensor information and data stream processing. Another trend that is gaining more traction is the use of No- and Low-Code-Platforms to create applications. Such approaches focus on defining the business logic via business process modeling and automatically create a corresponding executable application. We argue that using components based on Artificial Intelligence and Machine Learning in such applications requires to handle uncertainty resulting from probabilistic results accordingly. This means to introduce, e.g., fallback mechanisms if results delivered from composing using Artificial Intelligence err into modeled business processes. In this position paper, we discuss scenarios, arising problems, and potential solutions.","PeriodicalId":327964,"journal":{"name":"2022 International Conference on Service Science (ICSS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121576062","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 : 2022-05-01DOI: 10.1109/ICSS55994.2022.00014
Zhiwei Ma, Chunyang Ye, Hui Zhou
Sentiment analysis plays an indispensable role to help understand people’s opinions automatically based on their reviews. Existing research on sentiment analysis mainly focuses on film reviews, e-commerce reviews and other fields. These work cannot be applied to analyze the sentiment of travel reviews directly because the mainstream commodity review dataset is richer and more regular than that of travel review dataset. More specifically, the special characteristic of travel reviews makes existing solutions fail to achieve satisfactory results. To address this issue, we first construct a travel review data set for sentiment analysis. Then, we conduct a systematic study to investigate and compare the factors that may affect the accuracy of sentiment analysis for travel reviews. Based on the study findings, we design a lightweight Glove-BiLSTM-CNN model and BERT-BiLSTM-CNN to analyze the sentiment for travel reviews. Experimental results show that our proposed models outperform the baseline solutions.
{"title":"A Study on Sentiment Analysis for Smart Tourism","authors":"Zhiwei Ma, Chunyang Ye, Hui Zhou","doi":"10.1109/ICSS55994.2022.00014","DOIUrl":"https://doi.org/10.1109/ICSS55994.2022.00014","url":null,"abstract":"Sentiment analysis plays an indispensable role to help understand people’s opinions automatically based on their reviews. Existing research on sentiment analysis mainly focuses on film reviews, e-commerce reviews and other fields. These work cannot be applied to analyze the sentiment of travel reviews directly because the mainstream commodity review dataset is richer and more regular than that of travel review dataset. More specifically, the special characteristic of travel reviews makes existing solutions fail to achieve satisfactory results. To address this issue, we first construct a travel review data set for sentiment analysis. Then, we conduct a systematic study to investigate and compare the factors that may affect the accuracy of sentiment analysis for travel reviews. Based on the study findings, we design a lightweight Glove-BiLSTM-CNN model and BERT-BiLSTM-CNN to analyze the sentiment for travel reviews. Experimental results show that our proposed models outperform the baseline solutions.","PeriodicalId":327964,"journal":{"name":"2022 International Conference on Service Science (ICSS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115597762","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 : 2022-05-01DOI: 10.1109/ICSS55994.2022.00040
Yushuang Fang, Min Yuan, Hangrui Zhang, Ruzhen Wang
With the rapid development of the digital economy and the new generation of information technology, digital services often need to cross the boundaries of different industries, organizations, and regions. Choosing an appropriate recommendation method for crossover service providers has become challenging. Generally, the performance of the recommendation revealed by the evaluation indicators is used to reflect the pros and cons of the recommendation method. Compared with the traditional evaluation based on results, this paper proposes a procedural evaluation model. It comprehensively considers the laws of economic activities. From three different stages of crossover cooperation: input, execution and output, three process evaluation indicators of entropy, cost and profit are proposed respectively, and dynamic analysis of crossover service recommendation is carried out. Take the commonly used collaborative filtering recommendation method as an example; the experimental results show that the process evaluation model proposed in this paper can select the recommendation method. The method conforms to the law of market changes according to the different states of crossover cooperation of service providers.
{"title":"A Process Evaluation Method for Crossover Service Recommendation","authors":"Yushuang Fang, Min Yuan, Hangrui Zhang, Ruzhen Wang","doi":"10.1109/ICSS55994.2022.00040","DOIUrl":"https://doi.org/10.1109/ICSS55994.2022.00040","url":null,"abstract":"With the rapid development of the digital economy and the new generation of information technology, digital services often need to cross the boundaries of different industries, organizations, and regions. Choosing an appropriate recommendation method for crossover service providers has become challenging. Generally, the performance of the recommendation revealed by the evaluation indicators is used to reflect the pros and cons of the recommendation method. Compared with the traditional evaluation based on results, this paper proposes a procedural evaluation model. It comprehensively considers the laws of economic activities. From three different stages of crossover cooperation: input, execution and output, three process evaluation indicators of entropy, cost and profit are proposed respectively, and dynamic analysis of crossover service recommendation is carried out. Take the commonly used collaborative filtering recommendation method as an example; the experimental results show that the process evaluation model proposed in this paper can select the recommendation method. The method conforms to the law of market changes according to the different states of crossover cooperation of service providers.","PeriodicalId":327964,"journal":{"name":"2022 International Conference on Service Science (ICSS)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115209834","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：