| 387 | 5 | 382 |
| 下载次数 | 被引频次 | 阅读次数 |
数据驱动的主动服务推荐已成为实现智能服务、提升用户体验的重要技术，如何精确预测用户的服务需求成为当前重要问题之一。针对这个问题，提出了一种基于软注意力与多模态机器学习(SAMML)的服务需求预测方法。该方法首先从文本数据和图像数据提取特征向量并实现多模态数据特征融合；然后应用软注意力机制处理融合后的特征数据，并将结果输入门控制循环单元(GRU)网络，从而更好地学习用户的服务兴趣；最后，基于用户特征与服务数据训练SAMML模型，并实现用户的服务需求精确预测。基于天池大数据众智平台提供的数据集进行了验证实验，SAMML模型的评估指标MAE、MSE、R2分别比对比模型提高了0.021 8、0.026 3、0.031 0。
Abstract：Data-driven active service recommendation has become an important technology for realizing intelligent services and improving user experience. How to accurately predict the service needs of users has become an important problem. To solve this problem, a service demand prediction method based on soft attention and multimodal machine learning(SAMML) was proposed. The method firstly extracted feature vectors from text and image data and realized feature fusion of multimodal data. Then, soft attention machine was applied to process the fused feature data, and the results were input into the gated recurrent unit network, so as to learn the user′s service interest better. Finally, the SAMML model was trained, based on user characteristics and service data, and the user′s service demand was accurately predicted. A large number of verification experiments were carried out based on the data set provided by Tianchi big data intelligence platform, and the SAMML model was 0.021 8, 0.026 3 and 0.031 0 higher than the comparison model on MAE, MSE and R2, respectively.
[1] PHANKOKKRUAD M,WACHARAWICHANANT S.A comparison of extreme gradient boosting and convolutional neural network-long short-term memory for service demand forecasting[C]//The International Conference on Natural Computation,Fuzzy Systems and Knowledge Discovery.Berlin:Springer Press,2019:547-556.
[2] 郝旭政，柴争义.一种改进的深度残差网络行人检测方法[J].计算机应用研究，2019,36(5):1569-1572,1584.HAO X Z,CHAI Z Y.Improved pedestrian detection method based on depth residual network[J].Application research of computers,2019,36(5):1569-1572,1584.
[3] 张冬雯，赵琪，许云峰，等.基于长短期记忆神经网络模型的空气质量预测[J].河北科技大学学报，2020,41(1):67-75.ZHANG D W,ZHAO Q,XU Y F,et al.Air quality prediction based on neural network model of long short-term memory[J].Journal of Hebei university of science and technology,2020,41(1):67-75.
[4] SU X Y,KHOSHGOFTAAR T M.A survey of collaborative filtering techniques[J].Advances in artificial intelligence,2009,2009:421425.
[5] KUANG L,YAN X J,TAN X H,et al.Predicting taxi demand based on 3D convolutional neural network and multi-task learning[J].Remote sensing,2019,11(11):1265.
[6] HU J,LAI Y L,PENG A,et al.Proactive content delivery with service-tier awareness and user demand prediction[J].Electronics,2019,8(1):50.
[7] 张星，刘帅.感知用户的Item-based协同过滤算法[J].信阳师范学院学报(自然科学版),2017,30(1):125-128.ZHANG X,LIU S.User-aware item-based collaborative filtering algorithm[J].Journal of Xinyang normal university (natural sicence edition),2017,30(1):125-128.
[8] XUE P N,JIANG Y,ZHOU Z G,et al.Multi-step ahead forecasting of heat load in district heating systems using machine learning algorithms[J].Energy,2019,188:116085.
[9] LI Z H,FAN Y Y,JIANG B,et al.A survey on sentiment analysis and opinion mining for social multimedia[J].Multimedia tools and applications,2019,78(6):6939-6967.
[10] LI Y C,ISHI C T,WARD N,et al.Emotion recognition by combining prosody and sentiment analysis for expressing reactive emotion by humanoid robot[C]//Asia-Pacific Signal and Information Processing Association Annual Summit and Conference.Piscataway:IEEE Press,2017:1356-1359.
[11] SEMWAL N,KUMAR A,NARAYANAN S.Automatic speech emotion detection system using multi-domain acoustic feature selection and classification models[C]//IEEE International Conference on Identity,Security and Behavior Analysis.Piscataway:IEEE Press,2017:1-6.
[12] WANG Y Z,ZHANG N Q,CHEN X.A short-term residential load forecasting model based on LSTM recurrent neural network considering weather features[J].Energies,2021,14(10):2737.
[13] MOU L C,BRUZZONE L,ZHU X X.Learning spectral-spatial-temporal features via a recurrent convolutional neural network for change detection in multispectral imagery[J].IEEE transactions on geoscience and remote sensing,2019,57(2):924-935.
[14] PAN Y,ZHENG R C,ZHANG J X,et al.Predicting bike sharing demand using recurrent neural networks[J].Procedia computer science,2019,147:562-566.
[15] FANG C H,LU Q Y.Personalized recommendation model of high-quality education resources for college students based on datamining[J].Complexity,2021,2021:9935973.
[16] LAU J H,BALDWIN T.An empirical evaluation of doc2vec with practical insights into document embedding generation[C]//Proceedings of the 1st Workshop on Representation Learning for NLP.Stroudsburg:Association for Computational Linguistics,2016:78-86.
[17] HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE Press,2016:770-778.
[18] GUO G,ZHANG T Q.A residual spatio-temporal architecture for travel demand forecasting[J].Transportation research part C:emerging technologies,2020,115:102639.
[19] LIU Y,LIU Z Y,LYU C,et al.Attention-based deep ensemble net for large-scale online taxi-hailing demand prediction[J].IEEE transactions on intelligent transportation systems,2020,21(11):4798-4807.
[20] ZHENG B,HU Q,MING L,et al.Spatial-temporal demand forecasting and competitive supply via graph convolutional networks[EB/OL].[2021-01-18].https://arxiv.org/abs/2009.12157.
[21] CHU K F,LAM A Y S,LI V O K.Deep multi-scale convolutional LSTM network for travel demand and origin-destination predictions[J].IEEE transactions on intelligent transportation systems,2020,21(8):3219-3232.
[22] ZHANG R Y,LU Q B,GUO F P.User-based collaborative filtering recommendation method combining with privacy concerns intensity in mobile commerce[J].International journal of wireless and mobile computing,2019,17(1):63.
[23] GARDINO G B,MEO R,CRAPAROTTA G.Multi-view latent learning applied to fashion industry[J].Information systems frontiers,2021,23(1):53-69.
[24] LAW R,LI G,FONG D K C,et al.Tourism demand forecasting:a deep learning approach[J].Annals of tourism research,2019,75:410-423.
[25] XU Y B,ZHANG J,LONG Z Q,et al.Hourly urban water demand forecasting using the continuous deep belief echo state network[J].Water,2019,11(2):351.
[26] 丰凯.大数据环境下服务需求动态感知方法研究[D].焦作：河南理工大学，2021.FENG K.Research on dynamic service demand awareness method in big data environment[D].Jiaozuo:Henan Polytechnic University,2021.
[27] SHEN T,ZHOU T Y,LONG G D,et al.Reinforced self-attention network:a hybrid of hard and soft attention for sequence modeling[EB/OL].[2021-11-31].https://arxiv.org/abs/1801.10296.
[28] SON L H,KUMAR A,SANGWAN S R,et al.Sarcasm detection using soft attention-based bidirectional long short-term memory model with convolution network[J].IEEE access,2019,7:23319-23328.
[29] CHO K,VAN MERRIENBOER B,GULCEHRE C,et al.Learning phrase representations using RNN encoder-decoder for statistical machinetranslation[C]//Conference on Empirical Methods in Natural Language Processing.Stroudsburg:Association for Computational Linguistics,2014:1724-1734.
[30] SHIHAB M S H,ADITYA S,SETU J H,et al.A hybrid GRU-CNN feature extraction technique for speaker identification[C]//The 23rd International Conference on Computer and Information Technology.Piscataway,IEEE Press,2020:1-6.
[31] 朱乔木，李弘毅，王子琪，等.基于长短期记忆网络的风电场发电功率超短期预测[J].电网技术，2017,41(12):3797-3802.ZHU Q M,LI H Y,WANG Z Q,et al.Short-term wind power forecasting based on LSTM[J].Power system technology,2017,41(12):3797-3802.
[32] 殷兆凯，廖卫红，王若佳，等.基于长短时记忆神经网络(LSTM)的降雨径流模拟及预报[J].南水北调与水利科技，2019,17(6):1-9,27.YIN Z K,LIAO W H,WANG R J,et al.Rainfall-runoff modelling and forecasting based on long short-term memory(LSTM)[J].South-to-northwater transfers and water science & technology,2019,17(6):1-9,27.
[33] 王增平，赵兵，纪维佳，等.基于GRU-NN模型的短期负荷预测方法[J].电力系统自动化，2019,43(5):53-58.WANG Z P,ZHAO B,JI W J,et al.Short-term load forecasting method based on GRU-NN model[J].Automation of electric power systems,2019,43(5):53-58.
[34] JUNG S,MOON J,PARK S,et al.An attention-based multilayer GRU model for multistep-ahead short-term load forecasting [J].Sensors,2021,21(5):1639.
[35] CAI G Y,CHEN N N.Recommendation based on multimodal information of user-item interactions[C]//The 9th International Conference on Information Science and Technology.Piscataway:IEEE Press,2019:288-293.
[36] LV J M,SONG B,GUO J,et al.Interest-related item similarity model based on multimodal data for top-N recommendation[J].IEEE access,2019,7:12809-12821.
[37] HU P,ZHEN L L,PENG D Z,et al.Scalable deep multimodal learning for cross-modal retrieval[C]//Proceedings of the 42nd International ACM Conference on Research and Development in Information Retrieval.New York:ACM Press,2019:635-644.
基本信息:
DOI：10.13705/j.issn.1671-6841.2021498
中图分类号:TP391.3;TP18
引用信息:
[1]海燕,宋宗珀,刘志中,等.多模态数据驱动的服务需求预测方法研究[J],2023,55(02):70-78.DOI:10.13705/j.issn.1671-6841.2021498.
基金信息:
国家自然科学基金项目(61872126,61772159);; 山东省自然科学基金重点项目(ZR2020KF019);; 河南省教育厅重点研发项目(20A520014)
2021-11-18
2021
2023-03-17
2023
3