Computers & Industrial Engineering最新文献_第2页

Optimization of three-dimensional urban underground logistics system alignment: a deep reinforcement learning approach 三维城市地下物流系统布局优化：一种深度强化学习方法

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-05-07 DOI: 10.1016/j.cie.2025.111185

Longlong Hou , Yuanxian Xu , Rui Ren , Jianping Yang , Lijie Su

{"title":"Optimization of three-dimensional urban underground logistics system alignment: a deep reinforcement learning approach","authors":"Longlong Hou , Yuanxian Xu , Rui Ren , Jianping Yang , Lijie Su","doi":"10.1016/j.cie.2025.111185","DOIUrl":"10.1016/j.cie.2025.111185","url":null,"abstract":"<div><div>The three-dimensional (3D) alignment design of the underground logistics system (ULS) is a key factor in determining the rationality of its underground infrastructure layout. However, existing research mostly focuses on the two-dimensional horizontal alignment optimization, while neglecting the alignment design of vertical space scales, which makes it difficult for research results to effectively support projects implementation. Furthermore, traditional operations research methods struggle to handle the massive underground space data processing tasks required for detailed design of ULS alignment. Therefore, this study aims to consider the dual attributes of underground infrastructure and logistics infrastructure of ULS, proposing innovative deep reinforcement learning (DRL) method to achieve 3D alignment planning. Firstly, a DRL model was developed considering the key design factors of underground infrastructure alignment such as construction, cost, space suitability, and underground space resources. Secondly, given the large and complex optimization search space of the problem, a curriculum learning-based proximal policy optimization (CL-PPO) algorithm was proposed to efficiently solve the model. Finally, based on the Suzhou ULS case, simulations of alignment optimization results under different planning orientations were conducted to demonstrate the effectiveness of the model and algorithm. Results show that CL-PPO has significant advantages over PPO in terms of computational efficiency and global optimization capabilities. Additionally, planning orientations have a significant impact on the ULS alignment layout and project construction cost. The innovative optimization method not only enriches the infrastructure planning theory of ULS, but also provides space layout guidance for the utilization of urban underground space.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"205 ","pages":"Article 111185"},"PeriodicalIF":6.7,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143936435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Phase I change-point detection for ordinal profiles with arbitrary design: A nonparametric method and its application to warranty claims analysis 任意设计有序轮廓的第一阶段变化点检测：一种非参数方法及其在质保索赔分析中的应用

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-05-06 DOI: 10.1016/j.cie.2025.111156

Zhiqiong Wang , Lu Zhang , Ying Wang , Lisha Song , Yangyang Zang , Young-Mok Bae

{"title":"Phase I change-point detection for ordinal profiles with arbitrary design: A nonparametric method and its application to warranty claims analysis","authors":"Zhiqiong Wang , Lu Zhang , Ying Wang , Lisha Song , Yangyang Zang , Young-Mok Bae","doi":"10.1016/j.cie.2025.111156","DOIUrl":"10.1016/j.cie.2025.111156","url":null,"abstract":"<div><div>The functional relationship, commonly referred to as a profile, typically describes the quality characteristics of products or processes. Specifically, the ordinal profile characterizes the functional relationship between a categorical response, which consists of no less than three attributes arranged in a specific order, and certain explanatory variables. Statistical process control for ordinal profiles is attracting increasing interest because it is essential to guarantee product and service quality. However, existing studies have some limitations in modeling and retrospectively analyzing ordinal profiles. Besides, the design points within a profile may not be deterministic in practice. In some cases, they can be random, and different profiles may have different design points. Therefore, we propose a monitoring scheme in Phase I to detect a potential change point in the dataset of ordinal profiles with arbitrary design. The proposed method integrates a change-point model with a two-sample generalized likelihood ratio test on the basis of nonparametric regression. The detection effectiveness and diagnostic accuracy of the method are verified by numerical simulation. In addition, a case study on warranty claims data analysis is presented to further demonstrate the implementation of the proposed method.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"206 ","pages":"Article 111156"},"PeriodicalIF":6.7,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143936126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

High-efficiency stochastic optimization for Unit Commitment with personalized demand response and wind power uncertainty 具有个性化需求响应和风电不确定性的机组承诺高效随机优化

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-05-06 DOI: 10.1016/j.cie.2025.111100

B. Deng , Y.X. Lei , M.S. Li , T.Y. Ji , Q.H. Wu

{"title":"High-efficiency stochastic optimization for Unit Commitment with personalized demand response and wind power uncertainty","authors":"B. Deng , Y.X. Lei , M.S. Li , T.Y. Ji , Q.H. Wu","doi":"10.1016/j.cie.2025.111100","DOIUrl":"10.1016/j.cie.2025.111100","url":null,"abstract":"<div><div>Traditional demand response (DR) strategies often overlook flexible user utility, resulting in low engagement and underutilization of DR’s capacity to manage high-penetration wind power effectively. To address these issues, this brief introduces the variable user utility functions formed by two types of individual adjustment factors (IAF) and proposes personalized DR (PDR) strategies that deeply refine user utility, taking into account users’ inherent response preferences and environmental dynamic responses. Furthermore, by introducing an improved multi-visual mechanism (MVM) and parallelization techniques, this paper presents a powerful Parallel Group Search Optimizer (PGSO) algorithm to address the complexities of large-scale power systems. Ultimately, the efficiency of the proposed methods is validated through modeling the IEEE 118 system that includes the uncertainty of wind power, as a unit commitment with PDR (UCPDR) optimization model. The simulation results for four scenarios show that after the development of the PDR strategies, not only has the average utility sacrifice decreased by approximately 9.70% compared to the baseline scenario, but the fuel cost has also been reduced by 0.66%. In addition, compared to traditional stochastic optimizers, including differential evolution (DE), genetic algorithm (GA), particle swarm optimization (PSO), and covariance matrix adaptation evolution strategy (CMAES), the PGSO algorithm performs better in avoiding local optima and improving various system indicators. It is worth noting that, among up to 3.15 × 10<sup>9</sup> evaluations, the PGSO algorithm completed its computation in just 8.01 s, demonstrating computational speed improvements of 98.53%, 98.15%, 99.23%, and 99.98%. In conclusion, the proposed approach offers more flexible and user-centric energy management, effectively addressing real-world challenges.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"205 ","pages":"Article 111100"},"PeriodicalIF":6.7,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143924453","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Logic mining method via hybrid discrete hopfield neural network 基于混合离散hopfield神经网络的逻辑挖掘方法

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-05-06 DOI: 10.1016/j.cie.2025.111200

Yueling Guo , Mohd Shareduwan Mohd Kasihmuddin , Nur Ezlin Zamri , Jia Li , Nurul Atiqah Romli , Mohd. Asyraf Mansor , Wan Nur Aqlili Ruzai

{"title":"Logic mining method via hybrid discrete hopfield neural network","authors":"Yueling Guo , Mohd Shareduwan Mohd Kasihmuddin , Nur Ezlin Zamri , Jia Li , Nurul Atiqah Romli , Mohd. Asyraf Mansor , Wan Nur Aqlili Ruzai","doi":"10.1016/j.cie.2025.111200","DOIUrl":"10.1016/j.cie.2025.111200","url":null,"abstract":"<div><div>The growing interest in logic mining as a knowledge extraction tool in data mining has attracted considerable attention from researchers. Despite the success, the limitations of existing logic mining methods are often overlooked, hindering the search for optimal solutions in binary classification tasks. To address these challenges, this paper introduces a novel logic mining approach using the Y-type Random 2 Satisfiability logical rule, combined with hybrid mechanisms within the Discrete Hopfield Neural Network. The first contribution involves the incorporation of a Hybrid Differential Evolution Algorithm to accelerate the optimization of synaptic weights during the training phase. Additionally, the retrieval phase is enhanced by proposing a swarm mutation operator, which diversifies the final neuron states, thereby broadening the solution space. Furthermore, an improved reverse analysis method is applied to optimize attribute selection and generate the most effective training logic. To demonstrate the efficacy of the proposed logic mining approach, experiments were conducted using both simulated and real-world datasets. The results indicate that the proposed model significantly outperforms baseline models across all performance metrics. The study concludes that the enhanced logic mining technique effectively captures the knowledge of datasets and facilitates transparent decision-making, making it a valuable tool for both researchers and practitioners.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"206 ","pages":"Article 111200"},"PeriodicalIF":6.7,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143936125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards sustainable Home (Health)-Care: Bi-objective formulation for Electric Vehicle Routing 迈向可持续的家庭（健康）护理：电动汽车路线的双目标制定

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-05-05 DOI: 10.1016/j.cie.2025.111165

Salma HadjTaieb , Mohamed Cheikh , Yasmina Hani , Abderrahman El Mhamedi , Taicir Moalla Loukil

{"title":"Towards sustainable Home (Health)-Care: Bi-objective formulation for Electric Vehicle Routing","authors":"Salma HadjTaieb , Mohamed Cheikh , Yasmina Hani , Abderrahman El Mhamedi , Taicir Moalla Loukil","doi":"10.1016/j.cie.2025.111165","DOIUrl":"10.1016/j.cie.2025.111165","url":null,"abstract":"<div><div>The growing life expectancy in developed nations has led to an increased demand for Home (Health)-Care services due to the imbalanced growth rate between hospitals, residential care facilities and medical staff. Home (Health)-Care centers face several practical challenges related to the route such as its fees, duration, distance and ecological impact, etc. This drives our efforts to addresses the operational challenges in routing and scheduling problem considering multi-dimensional aspects simultaneously (social, economic and environmental). We propose a bi-objective Green Vehicle Routing Problem with Time Windows, Temporal Dependency, Multiple Structures and Multiple Specialties “Bi-GVRPTW-TD-2MS” model. This model aims to minimize patients’ dissatisfaction degree towards caregivers and reduce the overall travel distances of Electric Vehicles “EVs”. It incorporates the potential for recharging at any of the available charging stations through a suitable recharging strategy. This new variant extends the literature on the “VRPTW-TD-2MS” problem, which is studied as a mono-objective function with only a focus on the economic aspect. We present computational results using the Cplex solver for small-scale instances and introduce the Random General Variable Neighborhood Search “RGVNS” metaheuristic for medium and large-scale instances. The superiority of our approach over the existing methods applied to the VRPTW-TD-2MS model, is demonstrated through a comparative study. The experiments demonstrate the effectiveness and efficiency of the RGVNS method in solving both the Bi-GVRPTW-TD-2MS and VRPTW-TD-2MS problems.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"205 ","pages":"Article 111165"},"PeriodicalIF":6.7,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143929103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A critical review of MIP models for lot-sizing and scheduling in the beverage industry 饮料工业中批量生产和调度的MIP模型的重要回顾

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-05-05 DOI: 10.1016/j.cie.2025.111151

Víctor Mario Noble-Ramos , Deisemara Ferreira , Douglas Alem , Reinaldo Morabito

{"title":"A critical review of MIP models for lot-sizing and scheduling in the beverage industry","authors":"Víctor Mario Noble-Ramos , Deisemara Ferreira , Douglas Alem , Reinaldo Morabito","doi":"10.1016/j.cie.2025.111151","DOIUrl":"10.1016/j.cie.2025.111151","url":null,"abstract":"<div><div>This paper presents a comprehensive literature review of studies that have formulated mixed-integer programming models to address lot-sizing and scheduling problems in the beverage industry. For the first time, we highlight the distinguishing characteristics and challenges of beverage production and scheduling, such as the existence of two production stages, the need for synchronization between stages, and perishability issues associated with the liquids in production tanks—issues that have previously been overlooked by specialized literature. Given the absence of a classification scheme to systematize these characteristics, we introduce a novel and extensive set of classification criteria for lot-sizing and scheduling models tailored to the beverage sector. Our review provides an up-to-date summary of over 50 mixed-integer programming models and their real-world applications in the production of soft drinks, fruit-based beverages, beer, and yogurts. We also identify gaps in the literature and suggest promising directions for future research, underscoring the importance of addressing machine maintenance and data uncertainty, as well as the potential contributions of Machine Learning & Industry 4.0 and 5.0 to enhancing lot-sizing and scheduling within the beverage industry.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"205 ","pages":"Article 111151"},"PeriodicalIF":6.7,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143936432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A social trust network-based classification consensus decision-making method with incomplete information: cross-classification adjustment perspective 基于社会信任网络的不完全信息分类共识决策方法：交叉分类调整视角

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-05-05 DOI: 10.1016/j.cie.2025.111190

Peide Liu , Zixin He , Xin Dong , Peng Wang

{"title":"A social trust network-based classification consensus decision-making method with incomplete information: cross-classification adjustment perspective","authors":"Peide Liu , Zixin He , Xin Dong , Peng Wang","doi":"10.1016/j.cie.2025.111190","DOIUrl":"10.1016/j.cie.2025.111190","url":null,"abstract":"<div><div>The consensus decision-making problem based on classification requires placing alternatives in a predetermined category in a specific order, occupying an important position in group decision-making. To achieve a high level of group identification with the output results, the current research primarily focuses on modifying expert evaluation opinions to indirectly adjust the classification of alternatives, which may result in a significant deviation between the revised and initial opinions. Consequently, this paper constructs a classification consensus decision method with incomplete information from the perspective of cross-classification adjustment and social network analysis technology. Firstly, the node strength in the PageRank algorithm is used to acquire the weight of experts, and incomplete information is supplemented based on social trust network and opinion evolution. Secondly, the classification threshold model of the maximum group consensus is established, and the unified classification threshold of alternatives is calculated. In addition, the consensus-reaching process is achieved through the optimization model of cross-classification minimum adjustment, which directly adjusts the classification of the alternatives and avoids excessive modification of opinions. Further, taking the rating of green tourist scenic area buildings as an example, the applicability of the proposed method is tested. Ultimately, the efficacy and advantage of the presented approach are demonstrated via sensitivity analysis and contrast with current methodologies.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"205 ","pages":"Article 111190"},"PeriodicalIF":6.7,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143917560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Balancing human–robot collaborative assembly lines: A constraint programming approach 平衡人机协作装配线：一种约束编程方法

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-05-03 DOI: 10.1016/j.cie.2025.111154

Amir Nourmohammadi , Taha Arbaoui , Masood Fathi , Alexandre Dolgui

{"title":"Balancing human–robot collaborative assembly lines: A constraint programming approach","authors":"Amir Nourmohammadi , Taha Arbaoui , Masood Fathi , Alexandre Dolgui","doi":"10.1016/j.cie.2025.111154","DOIUrl":"10.1016/j.cie.2025.111154","url":null,"abstract":"<div><div>The advent of Industry 5.0 and advancements in collaborative robot (cobot) technology have driven many industries to adopt human–robot collaboration (HRC) in their assembly lines. This collaborative approach, which combines human expertise with robotic precision, necessitates an optimized method for balancing and scheduling tasks and operators across stations. This study proposes various constraint programming (CP) models tailored to straight and U-shaped assembly layouts, with objectives such as minimizing the number of stations, reducing cycle time, and minimizing costs. To enhance real-world applicability, the models consider the presence of diverse humans and cobots with varying skills and energy requirements working collaboratively or concurrently on assembly tasks. Additionally, practical constraints are addressed, including robot tool changes, zoning, and technological needs. Computational results demonstrate the superior efficiency of the proposed CP models over state-of-the-art mixed-integer programming models, validated through a case study and a comprehensive set of test problems. The results indicate that U-shaped layouts offer greater flexibility than straight-line configurations, particularly in reducing cycle time. Furthermore, higher HRC levels, including more humans and cobots, can significantly improve the number of stations, cycle time, and cost by up to 50%, 29%, and 36%, respectively.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"205 ","pages":"Article 111154"},"PeriodicalIF":6.7,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143905864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A bi-objective two-stage stochastic optimization for designing a resilient humanitarian relief chain considering hybrid contracts, public donations, and item perishability 考虑混合合同、公共捐赠和物品易腐性，设计弹性人道主义救济链的双目标两阶段随机优化

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-05-02 DOI: 10.1016/j.cie.2025.111147

Dorsa Taghvaei, Tina Ghods, Masoud Rabbani

{"title":"A bi-objective two-stage stochastic optimization for designing a resilient humanitarian relief chain considering hybrid contracts, public donations, and item perishability","authors":"Dorsa Taghvaei, Tina Ghods, Masoud Rabbani","doi":"10.1016/j.cie.2025.111147","DOIUrl":"10.1016/j.cie.2025.111147","url":null,"abstract":"<div><div>This paper presents a bi-objective, two-stage stochastic programming (TSSP) model for designing a resilient humanitarian relief chain (HRC). The model considers uncertainties in demand, public donations, and disruption risks while integrating decisions in both the pre- and post-crisis stages. This model optimizes critical decisions such as supplier selection, establishing contracts, pre-positioning items, inventory management, and distribution of perishable and non-perishable items. It aims to minimize the total network costs and the maximum average travel time to each demand point. To tackle disruptions in network facilities and links, several resilience strategies were adopted, including inventory pre-positioning and holding safety stock, as well as backup suppliers. Additionally, a hybrid supply contract was established, consisting of quantity flexibility contracts (QFCs) and option contracts (OPCs) between the governmental relief organization (GRO) and the main and backup suppliers, ensuring an acceptable level of responsiveness in the relief network. The epsilon-constraint method is utilized in GAMS software to illustrate different numerical instances and a case study of Tabriz City in Iran, demonstrating its applicability.The findings reveal that resilience strategies significantly enhance cost efficiency and response times, with pre-positioning improving overall costs by 28.42% and response times by 84.79% as the most influential strategy. The results review and sensitivity analysis provided valuable managerial insights for designing a functional and effective HRC.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"205 ","pages":"Article 111147"},"PeriodicalIF":6.7,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143936437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Developing Tech2Vec: A new embedding approach of technology information using a triple layer 开发Tech2Vec：利用三层技术信息嵌入的新方法

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-04-30 DOI: 10.1016/j.cie.2025.111163

Suyeong Lee , Sunhye Kim , Daye Lee , Byungun Yoon

{"title":"Developing Tech2Vec: A new embedding approach of technology information using a triple layer","authors":"Suyeong Lee , Sunhye Kim , Daye Lee , Byungun Yoon","doi":"10.1016/j.cie.2025.111163","DOIUrl":"10.1016/j.cie.2025.111163","url":null,"abstract":"<div><div>The recent increase in the number of patent applications highlights the urgent need for an effective embedding technique to automatically analyze enormous patent datasets. Extensive research is being conducted on the application of high-performance artificial intelligence (AI) technology to enhance patent analysis tasks. However, these studies do not consider various types of data. Instead, they examine technological information from a single perspective, such as technological terminology, patent functions, and goods. To cover all aspects, namely, technological system, function, and technology, a technological information analysis model that exploits both structured and unstructured data from previous patent filings is required. Therefore, this study proposes a new embedding approach called Tech2Vec to conduct function-oriented patent searches that can use the function and technological information of patent documents. More precisely, various types of technological information included in patent applications are organized into a triple layer, that is, the system, function, and component layers; vectorized layer by layer; and concatenated into a single technology vector. For example, by leveraging the patents and papers of three sectors, namely electric vehicles, displays and industrial robots, Tech2Vec is effectively applied and mapped to the technological latent space. Additionally, a function-oriented patent search is performed by comparing the query vectors entered by a user in natural language rather than the search query format. This study may be used as a reference for a range of technology management activities, such as document categorization, technological opportunity identification, and technology evolution analysis.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"205 ","pages":"Article 111163"},"PeriodicalIF":6.7,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143895808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0