改进深度交叉网络的遥感信息即时智能推荐方法

doi:10.11947/j.AGCS.2024.20230065

测绘学报 ›› 2024, Vol. 53 ›› Issue (3): 537-547.doi: 10.11947/j.AGCS.2024.20230065

改进深度交叉网络的遥感信息即时智能推荐方法

彭染姝^1,2, 陈实¹, 陈宇¹

1. 中国科学院国家空间科学中心, 北京 100190;
2. 中国科学院大学, 北京 100049

收稿日期:2023-03-08 修回日期:2023-08-02 发布日期:2024-04-08
通讯作者: 陈实 E-mail:chenshi@nssc.ac.cn
作者简介:彭染姝(1998—),女,博士生,研究方向为空间智能数据与信息处理技术。E-mail:15501076799@163.com
基金资助:
中国科学院国家空间科学中心“攀登计划”(E1PD30031S)

Improved real-time intelligent recommendation method of remote sensing information in deep cross network

PENG Ranshu^1,2, CHEN Shi¹, CHEN Yu¹

1. National Space Science Center, Chinese Academy of Sciences, Beijing 100190, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China

Received:2023-03-08 Revised:2023-08-02 Published:2024-04-08
Supported by:
Pandeng Program of National Space Science Center, Chinese Academy of Sciences (No. E1PD30031S)

摘要/Abstract

摘要： 随着遥感大数据时代的到来,海量遥感数据的主动、即时推送问题成为限制遥感信息智能服务领域发展的瓶颈。针对现有遥感信息推荐模型空间特征表达能力不足、交叉特征表达能力欠缺和无差别对待交叉特征等问题,本文提出一种融合注意力机制的深度交叉空间变换网络(attention deep & cross spatial-transformation network,ADCSTN)。首先,模型使用深度交叉网络提取遥感信息不同关联的交叉特征;然后,基于栅格划分,利用空间变换层将一维空间属性数据转换为二维空间矩阵,充分捕捉遥感信息空间结构特征;最后,通过注意力层对得到的不同关联的交叉特征设置不同权重,增强模型性能,实现遥感信息的主动、即时、智能推送。本文利用STK仿真1584颗智能遥感卫星组成的遥感卫星星座为20°N—40°N、120°E—140°E区域内的舰船提供实时遥感数据,并设置用户兴趣,得到试验数据集。试验结果表明,本文模型的推荐效果较好,相比于传统的四元组模型,F₁ score提高了37%~54.7%。

Abstract: With the advent of the era of remote sensing big data, the problem of active and real-time push of massive remote sensing data has become a bottleneck limiting the development of remote sensing information intelligent services. Aiming at the problems of insufficient spatial feature expression ability, insufficient cross feature expression ability and non-discriminatory treatment of cross features in existing remote sensing information recommendation models, this paper proposes an attention deep cross spatial transformation network (ADCSTN) integrating attention mechanism. Firstly, the model uses deep cross network to extract the cross features of different associations of remote sensing information. Then, based on grid division, the model uses the spatial transformation layer to convert the one-dimensional spatial attribute data into two-dimensional spatial matrix, fully capturing the spatial structure characteristics of remote sensing information. Finally, the attention layer sets different weights for the different associated cross features to enhance the performance of the model and realize the active, real-time and intelligent push of remote sensing information. In this paper, the remote sensing satellite constellation composed of 1584 intelligent remote sensing satellites is simulated by STK to provide real-time remote sensing data for ships in the area of 20°N—40°N, 120°E—140°E, and set user interests to obtain the experimental data set. The experimental results show that the recommendation effect of the model in this paper is better. Compared with the traditional quad model, the F₁ score is increased by about 50%.

Key words: remote sensing information, recommendation system, deep crossing network, instant push, intelligent remote sensing satellite

中图分类号:

P237

彭染姝, 陈实, 陈宇. 改进深度交叉网络的遥感信息即时智能推荐方法[J]. 测绘学报, 2024, 53(3): 537-547.

PENG Ranshu, CHEN Shi, CHEN Yu. Improved real-time intelligent recommendation method of remote sensing information in deep cross network[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(3): 537-547.

参考文献

[1] 王密, 杨芳. 智能遥感卫星与遥感影像实时服务[J]. 测绘学报, 2019, 48(12):1586-1594.DOI:10.11947/j.AGCS.2019.20190454. WANG Mi, YANG Fang. Intelligent remote sensing satellite and remote sensing image real-time service[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(12):1586-1594.DOI:10.11947/j.AGCS.2019.20190454.
[2] 李德仁, 丁霖, 邵振峰. 面向实时应用的遥感服务技术[J]. 遥感学报, 2021, 25(1):15-24. LI Deren, DING Lin, SHAO Zhenfeng. Application-oriented real-time remote sensing service technology[J]. National Remote Sensing Bulletin, 2021, 25(1):15-24.
[3] 程滔. 大数据时代遥感数据管理与服务模式探索[J]. 国土资源遥感, 2016, 28(4):202-206. CHENG Tao. Exploring management and service mode for remote sensing data in big data era[J]. Remote Sensing for Natural Resources, 2016, 28(4):202-206.
[4] 李德仁, 沈欣, 李迪龙, 等. 论军民融合的卫星通信、遥感、导航一体天基信息实时服务系统[J]. 武汉大学学报(信息科学版), 2017, 42(11):1501-1505. LI Deren, SHEN Xin, LI Dilong, et al. On civil-military integrated space-based real-time information service system[J]. Geomatics and Information Science of Wuhan University, 2017, 42(11):1501-1505.
[5] 李德仁, 沈欣. 我国天基信息实时智能服务系统发展战略研究[J]. 中国工程科学, 2020, 22(2):138-143. LI Deren, SHEN Xin. Research on the development strategy of real time and intelligent space-based information service system in China[J]. Strategic Study of CAE, 2020, 22(2):138-143.
[6] ZHU Jiefan, YOU Xiong, XIA Qing, et al. Object-oriented battlefieldenvironment simulation process object model based on task-driven[J].Journal of Geodesy and Geoinformation Science,2019,2(3):31-43.
[7] 柳林, 李德仁, 李万武, 等. 从地球空间信息学的角度对智慧地球的若干思考[J]. 武汉大学学报(信息科学版), 2012, 37(10):1248-1251. LIU Lin, LI Deren, LI Wanwu, et al. Thoughts on smarter planet from the view of geomatics[J]. Geomatics and Information Science of Wuhan University, 2012, 37(10):1248-1251.
[8] 吴巍. 我军新一代通信网络发展设想[J]. 中国电子科学研究院学报, 2007, 2(5):445-449, 463. WU Wei. Development assumption on Chinese army's new generation communication network[J]. Journal of China Academy of Electronics and Information Technology, 2007, 2(5):445-449, 463.
[9] DOUGLASS R J, MORK J, SURESH R. Battlefield awareness and data dissemination (badd) for the warfighter[C]//Proceedings of 1997 Digitization of the Battlefield II. Orlando:SPIE, 1997, 3080:18-24.
[10] STEPHENSON T P, DECLEENE B T, SPECKERT G, et al.BADD phase II:DDS information management architecture[C]//Proceedings of 1997 Digitization of the Battlefield II.Orlando:SPIE, 1997, 3080:49-58.
[11] YU X. Towards intelligent spatial information dissemination based on user profile model[J]. Journal of Tongji University, 2008, 13(6):401-410.
[12] 夏宇, 朱欣焰. 利用区间分析的空间信息智能分发决策[J]. 武汉大学学报(信息科学版), 2013, 38(9):1103-1107. XIA Yu, ZHU Xinyan. Intelligent spatial information delivery decision-making by using interval analysis[J]. Geomatics and Information Science of Wuhan University, 2013, 38(9):1103-1107.
[13] 李新广, 范明虎, 杜武. 面向空间信息智能分发的动态化用户偏好模型研究[J]. 测绘学报, 2011, 40(5):646-654. LI Xinguang, FAN Minghu, DU Wu. Research on dynamic user profile model for intelligent distribution of spatial information[J]. Acta Geodaetica et Cartographica Sinica, 2011, 40(5):646-654.
[14] 龙恩, 吕守业, 岑鹏瑞, 等. 顾及用户画像的多源遥感信息智能推荐方法[J]. 测绘学报, 2023, 52(2):297-306.DOI:10.11947/j.AGCS.2023.20210335. LONG En, LÜ Shouye, CEN Pengrui, et al. An intelligent recommendation method of multi-source remote sensing information consi-dering user portrait[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(2):297-306.DOI:10.11947/j.AGCS.2023.20210335.
[15] 张秀红. 基于知识图谱的遥感影像应用领域知识服务研究[D]. 武汉:武汉大学, 2020. ZHANG Xiuhong. Remote sensing image application domain knowledge service research based on knowledge graph[D]. Wuhan:Wuhan University, 2020.
[16] 黄立威, 江碧涛, 吕守业, 等. 基于深度学习的推荐系统研究综述[J]. 计算机学报, 2018, 41(7):1619-1647. HUANG Liwei, JIANG Bitao, LÜ Shouye, et al. Survey on deep learning based recommender systems[J]. Chinese Journal of Compu-ters, 2018, 41(7):1619-1647.
[17] WANG Jizhe, HUANG Pipei, ZHAO Huan, et al. Billion-scale commodity embedding forE-commerce recommendation in alibaba[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.London:ACM Press, 2018:839-848.
[18] COVINGTON P, ADAMS J, SARGIN E. Deep neural networks for YouTube recommendations[C]//Proceedings of the 10th ACM Conference on Recommender Systems.Boston:ACM Press, 2016:191-198.
[19] ELKAHKY A M, SONG Yang, HE Xiaodong. A multi-view deep learning approach for cross domain user modeling in recommendation systems[C]//Proceedings of the 24th International Conference on World Wide Web. New York:ACM Press, 2015:278-288.
[20] GRBOVIC M, RADOSAVLJEVIC V, DJURIC N, et al. E-commerce in your inbox:product recommendations at scale[C]//Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.Sydney:ACM Press, 2015:1809-1818.
[21] 张兵. 智能遥感卫星系统[J]. 遥感学报, 2011, 15(3):415-431. ZHANG Bing. Intelligent remote sensing satellite system[J]. Journal of Remote Sensing, 2011, 15(3):415-431.
[22] WANG Ruoxi, FU Bin, FU Gang, et al. Deep & cross network for ad click predictions[C]//Proceedings of the ADKDD'17.Halifax:ACM Press, 2017:1-7.
[23] MIKOLOV T, CHEN Kai, CORRADO G, et al. Efficient estimation of word representations in vector space[EB/OL].[2023-05-10].http://www.arxiv.org/pdf/1301.3781.pdf.
[24] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780.
[25] BAHDANAU D, CHO K, BENGIO Y. Neural machine translation by jointly learning to align and translate[EB/OL].[2023-05-10].https://arXivpreprint/arXiv:1409.0473.
[26] CHENG H T, KOC L, HARMSEN J, et al. Wide & deep learning for recommender systems[C]//Proceedings of the 1st Workshop on Deep Learning for Recommender Systems.Boston:ACM Press, 2016:7-10.

改进深度交叉网络的遥感信息即时智能推荐方法

Improved real-time intelligent recommendation method of remote sensing information in deep cross network

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	李德仁, 王密, 杨芳. 新一代智能测绘遥感科学试验卫星珞珈三号01星[J]. 测绘学报, 2022, 51(6): 789-796.
[2]	纪松, 张永生, 董杨, 范大昭. 星载轻量化影像控制点数据制作方法[J]. 测绘学报, 2022, 51(3): 413-425.
[3]	王密, 杨芳. 智能遥感卫星与遥感影像实时服务[J]. 测绘学报, 2019, 48(12): 1586-1594.
[4]	杨晓霞, 徐婷, 李少达, 杨容浩, 丁雨淋, 曹振宇. 用户模型驱动的遥感信息智能服务方法[J]. 测绘学报, 2015, 44(11): 1285-1294.
[5]	曹天扬, 申莉. 应用光照模型的交通车辆识别定位的高分辨率遥感方法[J]. 测绘学报, 2015, 44(1): 39-45.