Retrieval System Research Articles

Women's perspectives on mHealth behavior change interventions for the management of overweight, obesity, or gestational diabetes: A qualitative meta-synthesis.

mHealth interventions play an increasingly important role in health behavior change for gestational diabetes or peripartum obesity management. This qualitative systematic review and meta-synthesis aims to explore women's perceptions of mHealth behavior change interventions for gestational diabetes and/or overweight/obesity management during pregnancy and the postpartum period. Cumulative Index of Nursing and Allied Health Literature (CINAHL), Cochrane, Excerpta Medica Database (EMBASE), Medical Literature Analysis and Retrieval System Online (MEDLINE), and Psychological Information Database (PsycINFO) databases were searched using a Sample, Phenomenon of Interest, Design, Evaluation and Research type (SPIDER) concept framework through to February 2024. Included studies were quality assessed using the Critical Appraisal Skills Programme checklist. Study findings were evaluated using reflexive thematic analysis and GRADE-Confidence in the Evidence from Reviews of Qualitative Research (CERQual) checklist. We identified 29 studies, representing 604 women's views from one upper middle-income and nine high-income countries. Two themes were generated: mHealth as a supportive tool; and mHealth as a personalizable tool. Women highlighted the importance of self-monitoring, information trustworthiness, peer support, motivational tools (goal setting, risk awareness, and problem solving) and convenience in achieving behavior change using mHealth technology. They suggest mHealth programs incorporate these elements to support user engagement and improved health outcomes. Understanding what women want as mHealth users is particularly important for effective interventions in gestational diabetes, weight management, and chronic disease prevention. Creating a better, more woman-centered experience by addressing central engagement issues should result in improved maternal health outcomes.

The usefulness of patient-reported outcome measures in decision making in Chagas cardiomyopathy: a scoping review.

Chagas cardiomyopathy (ChC) presents many biopsychosocial complexities, highlighting the need to have patient self-report questions. This study demonstrates the scope of the use of patient-reported outcome measures (PROMs) in patients with ChC and highlights the main research gaps. This is a scoping review and the search strategy was performed in the Online Medical Literature Analysis and Retrieval System (MEDLINE), Excerpta Medica database (EMBASE), Accumulated Index of Nursing and Allied Health Literature (CINAHL), Cochrane Central, Latin American Literature and Caribbean in Health Sciences (LILACS) and Diagnostic Test Accuracy (DITA). The search identified 4484 studies and 20 studies met the inclusion criteria. The Short-Form of 36 items (SF-36) had potential prognostic value and the ability to identify systolic dysfunction. The Human Activity Profile was able to screen for functional impairment, and the New York Heart Association showed potential prognostic value. The SF-36 and Minnesota Living with Heart Failure Questionnaire were responsive to interventions. The pharmaceutical care affected adherence to treatment as assessed by the Morisky score and also for SF-36. Despite the increased use of PROMs, there are still a large number of gaps in the literature, and further studies using PROMs are needed.

Factors associated with suicidal ideation among puerperal women in the context of public health: integrative review

Objective: To synthesize scientific evidence about the factors associated with suicidal ideation in the puerperal period in the context of public health. Methods: Integrative review conducted by the guidelines of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses protocol, carried out in July 2022, in the Medical Literature Analysis and Retrieval System Online, Web of Science, Latin American and Caribbean Literature in Health Sciences, Nursing Database, Spanish Bibliographic Index of Health Sciences, PsycINFO and Cumulative Index to Nursing and Allied Health Literature. Results: Seven studies were selected to compose this review. Factors associated with suicidal ideation in the puerperal period were younger, single, unemployed women, having an unemployed partner, having experienced intimate partner violence, having faced stressful events during pregnancy, previous experiences of abortion and marital dissatisfaction, depressive symptoms and other mental disorders (mood disorders, hypomanic symptoms, neuroticism and psychoticism). High self-esteem aimed to reduce ideas of suicide during the postpartum period. Being primigravid, having a harmonious relationship with the mother-in-law, and marital satisfaction were presented as protective factors. Conclusion: The synthesis of the studies showed the association of psychosocial, physiological and sociodemographic factors with suicidal ideation among puerperal women, as well as protective factors.

Modified LDA vector and feedback analysis for short query Information Retrieval systems

Abstract Information Retrieval systems benefit from the use of long queries containing a large volume of search-relevant information. This situation is not common, as users of such systems tend to use very short and precise queries with few keywords. In this work we propose a modification of the Latent Dirichlet Allocation (LDA) technique using data from the document collection and its vocabulary for a better representation of short queries. Additionally, a study is carried out on how the modification of the proposed LDA weighted vectors increase the performance using relevant documents as feedback. The work shown in this paper is tested using three biomedical corpora (TREC Genomics 2004, TREC Genomics 2005 and OHSUMED) and one legal corpus (FIRE 2017). Results prove that the application of the proposed representation technique, as well as the feedback adjustment, clearly outperforms the baseline methods (BM25 and non-modified LDA).

Individual dipeptidyl peptidase-4 inhibitors and acute kidney injury in patients with type 2 diabetes: A systematic review and network meta-analysis.

This network meta-analysis of randomized controlled trials aimed to determine whether any individual dipeptidyl peptidase-4 (DPP-4) inhibitors increase the risk of acute kidney injury (AKI). The Medical Literature Analysis and Retrieval System Online via PubMed, the Cochrane Central Register of Controlled Trials and ClinicalTrials.gov were systematically searched to identify relevant studies. The primary outcome was AKI. A frequentist network meta-analysis was performed using a random-effects model to account for heterogeneity. Twenty-nine studies involving 56 117 participants were included. There were 918 cases of AKI (1.63%). The risk of bias was generally considered to be low. The only DPP-4 inhibitor that significantly increased the frequency of AKI when compared with placebo was sitagliptin (risk ratio 1.65, 95% confidence interval 1.22-2.23). However, because one study showed significant outliers in the funnel plot, in a highly heterogeneous population composed solely of patients undergoing surgery for coronary artery bypass graft, we conducted a post-hoc sensitivity analysis to exclude this study. The results showed no statistically significant difference in the risk of AKI between sitagliptin and placebo. Individual DPP-4 inhibitors do not appear to increase the risk of AKI. However, sitagliptin may be associated with AKI in patients with underlying severe cardiovascular disease.

SEMANTIC SEGMENTATION AND CONTENT-BASED RETRIEVAL IN MULTIMEDIA IMAGE DATABASES

Brain tumors, particularly gliomas, pose a significant threat to global health, necessitating accurate and efficient diagnostic methods. Magnetic Resonance Imaging (MRI) serves as a crucial tool for diagnosing glioma grades, but interpretation is subject to variability, hindering treatment planning. Intra and inter-observer variability in radiological image interpretation impede effective therapeutic strategies for brain tumor patients. Accessing relevant images from vast medical databases for comparison and treatment planning is cumbersome and time-consuming. This paper proposes a Content-Based Medical Image Retrieval (CBIR) system utilizing Convolutional Neural Network (CNN)-based feature extraction, specifically employing the AlexNet architecture. The system employs KNN clustering for indexing the feature map database and implements Gain-based feature selection to reduce feature vector dimensionality. The proposed system underwent evaluation using BraTS 2018 and 2020 datasets with five-fold cross-validation. Achieving state-of-the-art performance, the system demonstrated a mean Average Precision of 98% and Precision of 97%, showcasing its efficacy in accurately retrieving similar pathological MRI brain images.

Clinical and Economic Value of a Biosimilar Portfolio to Stakeholders: An Integrative Literature Review.

While the value of individual biosimilars is evident, little is known about the value of a biosimilar portfolio beyond the cost savings between biosimilars and originators. Stakeholders may consider the value of a manufacturer's biosimilar portfolio, especially when negotiating portfolio-based contracts or other rebate programs. However, little is known about what other types of value, in addition to financial benefits, decision-makers perceive regarding a manufacturer with a biosimilar portfolio compared to those without one. The objective of this integrative literature review was to describe a conceptual framework consisting of themes that may help define the value of a biosimilar portfolio. An integrative literature review was conducted using Excerpta Medica Database (Embase) and Medical Literature Analysis and Retrieval System Online (MEDLINE). Grey literature searches of search engines, journals not indexed in Embase or MEDLINE, healthcare payers, health technology assessment bodies, value frameworks, and non-pharmaceutical industry analogs were also conducted. Eligible studies reported on the value of a biosimilar portfolio in decision-making by stakeholders. Apart from the literature, insights were gained from clinical experience and observation. No studies investigating biosimilar portfolio value were identified; however, several themes were identified that may help define the value of a biosimilar portfolio: Manufacturing; procurement, inventory, and storage; administration; education; and transaction costs. Several non-pharmaceutical industry analogs were identified: Product line length and single-supplier versus multiple-supplier procurement. Several themes were identified through other sources: Science credibility and research. Based on these themes, we developed a conceptual framework for biosimilar portfolio value. To our knowledge, this is the first study to systematically assess and create a framework for biosimilar portfolio value. The conceptual framework described here could be tested to quantify the clinical and economic value associated with a biosimilar portfolio.

A novel approach for identification of zoonotic trypanosome utilizing deep metric learning and vector database-based image retrieval system

Trypanosomiasis, a significant health concern in South America, South Asia, and Southeast Asia, requires active surveys to effectively control the disease. To address this, we have developed a hybrid model that combines deep metric learning (DML) and image retrieval. This model is proficient at identifying Trypanosoma species in microscopic images of thin-blood film examinations. Utilizing the ResNet50 backbone neural network, a trained-model has demonstrated outstanding performance, achieving an accuracy exceeding 99.71 % and up to 96 % in recall. Acknowledging the necessity for automated tools in field scenarios, we demonstrated the potential of our model as an autonomous screening approach. This was achieved by using prevailing convolutional neural network (CNN) applications, and vector database based-images returned by the KNN algorithm. This achievement is primarily attributed to the implementation of the Triplet Margin Loss function as 98 % of precision. The robustness of the model demonstrated in five-fold cross-validation highlights the ResNet50 neural network, based on DML, as a state-of-the-art CNN model as AUC >98 %. The adoption of DML significantly improves the performance of the model, remaining unaffected by variations in the dataset and rendering it a useful tool for fieldwork studies. DML offers several advantages over conventional classification model to manage large-scale datasets with a high volume of classes, enhancing scalability. The model has the capacity to generalize to novel classes that were not encountered during training, proving particularly advantageous in scenarios where new classes may consistently emerge. It is also well suited for applications requiring precise recognition, especially in discriminating between closely related classes. Furthermore, the DML exhibits greater resilience to issues related to class imbalance, as it concentrates on learning distances or similarities, which are more tolerant to such imbalances. These contributions significantly make the effectiveness and practicality of DML model, particularly in in fieldwork research.

A Study on E-Commerce Warehousing Dynamics Navigating Order Fulfilment and Returns

The e-commerce over the past decade has experienced remarkable growth, reshaping shopping habits and challenging traditional supply chain methods. This surge in online shopping has compelled e-commerce firms to enhance their warehousing and order fulfilment strategies to meet rising consumer expectations for swift deliveries and hassle-free returns. Effective management of order fulfilment and reverse logistics has become essential for competitiveness in this industry. This study investigates e-commerce warehousing dynamics, emphasizing the optimization of order speed, delivery times, operational costs, and return management. Through industry reports, academic literature, and case studies, we identify best practices in five key areas: warehouse design and automation, demand forecasting, inventory control, order picking and packing processes, transportation strategies, last-mile delivery models, and reverse logistics for returns. Our research underscores the significance of highly automated warehouses equipped with advanced technologies such as robotics, automated storage and retrieval systems (ASRS), automated guided vehicles (AGVs), and intelligent software for material flow management. These innovations empower e-commerce firms to boost throughput, enhance operational flexibility, and adapt to changing demands effectively.

Advancements in Neural Machine Translation: Methodological Innovations and Empirical Insights for Cross-Linguistic Discourse Preservation

Abstract: Natural Language Processing (NLP), in the form recognizable today, really began to take hold in the 1980s, when machine learning helped propel it to soaring heights. However, due to a lack of processing power, machine learning, and to an extent, NLP, started slowing down in innovation and ideas and had almost ground to a relative halt, until the last decade, when a sudden increase in both productivity and interest in the machine learning helped increase the amount of knowledge in the space itself. This review provides several different case studies using different methodologies. The first paper was a deep analysis on how researchers were able to use Tesseract and Google Vision in tandem with automatic data mining methods to enrich the Cherokee language database in order to preserve it from extinction. The second paper takes a query translation-based approach toward translating English to Indian languages and utilizes a Multilingual Cross-Language Information Retrieval (MLCIR) system with tools such as Part of Speech Tagger (POST), Stop-Word, and Porter Stemmer. The third paper presents CoVe, which transfers knowledge from machine translation to improve performance on NLP tasks like sentiment analysis and question answering by using contextualized word vectors along with word embeddings, achieving new state-of-the-art results on some datasets. The fourth paper aims to translate English to Pakistan Sign Language (PSL) and also uses POST and goes through dependency analysis, sentence classification, and PSL using PLS trees. The fifth paper uses a Multilingual Neural Machine Translation (NMT) system for LowResource languages and incorporates two main models: a recurrent NMT and a transformer NMT. The sixth paper analyzes how a fine-tuned transformer model seems to work better than transformer models trained from scratch on high-resource languages, while vice-versa seems to occur for low-resource languages. The seventh paper adds to this by talking about how multilingual translation seems to work better than a back-translation model. Given the diverse array of approaches that could be used, we aim to identify the most efficient and correct methodology for future researchers to use in their work, based on the papers in this literature review.

Creating Search Engine Using Machine Learning Methods

Abstract: The vast and ever-expanding amount of information available in the WWW has led to the widespread usage of search engines for data retrieval. It can be challenging to locate information that is actually relevant and helpful, even while ordinary search engines offer users an intuitive interface for entering queries and retrieving web page links as results. To rectify that problem, which paper presents a novel search engine that work ML techniques. The target is to come up users with most relevant web sites when they query the engine. The suggested search engine improves the relevancy and accuracy of search results by utilizing machine learning algorithms. This system seeks to grasp user intent, adjust to individual preferences, and deliver contextually relevant information by going beyond the bounds of traditional search engines. By using machine learning models, the search engine may learn dynamically and enhance the standard of its results over time by continuously refining its understanding. More sophisticated and adaptable search engines are being developed as an outcome of these combination of state-of-the-art machine learning libraries, tools for processing natural language, and effective indexing systems. The target of the research is too advance information retrieval systems by providing a more advanced and user-focused method of tackling the difficulties presented by the WWW's immense scope

An Efficient Search on Cloud Images with Blockchain Technology

A key task in computer vision is image retrieval, which has wide-ranging applications across multiple domains. Using query picture features, this abstract proposes an image retrieval approach that focuses on the widely used Scale-Invariant Feature Transform (SIFT) algorithm for feature extraction and distance calculation. The suggested method starts by extracting SIFT features from a set of photos, building a keypoints and descriptor database. By capturing the unique qualities of nearby image regions, these features enable reliable matching and retrieval. The security of private cloud data, which includes query queries, the search tree, and outsourced photographs, is another major issue. Use a feature extraction method first for integrated picture features, which are composed of fundamental components like colour and shape. In particular, because the proposed method uses a balancing index tree, it can achieve logarithmic search time. Second, the picture and query feature are encrypted using the secure inner product. Include a system for determining duplicate picture material as well. When given a query image, SIFT feature extraction is applied to it, producing keypoints and descriptors that correspond to its visual characteristics. Next, a distance computation method like Euclidean distance is used to compare the features of the database photos with the query image features. The similarity between the query image and the database images is measured through this comparison. The retrieved photos are ranked in order of similarity to the query image based on the calculated distances. Search results with lesser distances between images are deemed more similar and are displayed first. To locate visually related images in huge databases, the image retrieval system that uses SIFT feature extraction and distance calculation provides a reliable and effective solution. It contributes to developments in multimedia retrieval, visual analytics, and picture understanding by enabling applications like content-based image search, image recommendation systems, and image clustering.

Smart Video Surveillance Using Deep Learning

Abstract: There is a lot of assessment happening in the business about video observation among them; the occupation of CCTV accounts has been blocked. CCTV cameras are put all around the spots for perception and security. In today's digital age, the increasing availability of data and advancements in computer vision have paved the way for numerous applications of object detection. This powerful technology has found its significance in various domains, including video surveillance and image retrieval systems. Object detection enables machines to identify and locate objects within images or video frames, providing valuable insights and aiding in decision-making processes. This article explores the applications, challenges, techniques, and future trends of object detection in the context of video surveillance and image retrieval systems. Object detection is a computer vision technique that involves identifying and localizing objects within images or video frames. Unlike image classification, which assigns a single label to an entire image, object detection goes a step further by detecting and delineating the individual objects present. It enables computers to comprehend visual data and interact with the world, much like humans do

The adoption of ICT and robotic automation systems in the pharmaceutical industry

Background: South African pharmacies face challenges like cost reduction, inventory management, and employee efficiency. Balancing dispensing error rates and customer satisfaction, along with ensuring accurate medication dispensing, is also crucial. An effective solution to these challenges is adopting automatic robotic dispensing systems, which enhance stock inventory management, integrated systems, and accurate dispensing capabilities.Objectives: The study delved into IT and robotic automation in South African pharmaceutical dispensing, assessing current methods and advocating for integrated IT and Automated Storage and Retrieval Systems in retail and hospital pharmacies.Method: The research used a quantitative approach to gather data from public and private hospital pharmacy employees, aiming to understand their requirements and expectations. It assessed the potential improvements that could result from adopting a new system.Results: The study found that most government and private pharmacies in South Africa prefer automated dispensing systems to reduce errors, lower costs, improve customer service, and enhance inventory management. Benefits also included minimising medication errors, improving operational efficiency, and ensuring patient safety.Conclusion: The study holds importance as it underscores the necessity of integrating Information Technology (IT) and Robotic Automation in the pharmaceutical sector to address prevailing issues. It identifies factors contributing to medication dispensing errors and demonstrates the potential of automated robotic systems in mitigating these errors.Contribution: South Africa’s pharmaceutical sector must enhance efficiency and competitiveness by adopting integrated IT and Robotic Automation Systems. The study identified key factors for future implementation and emphasized the need for clear pre-implementation policies outlining functions and benefits.

The Detection and Classification from the Multimodal Images using Artificial Intelligence for Lung Diseases

Lung cancer is a disease in which healthy cells in the body gradually convert into tumour cells, resulting in a variety of medical issues. A standard dataset exists for lung cancer. With the rising incidence of lung cancer and the exponential growth of CT pictures, having a quick and effective way to evaluate CT scans can help physicians or surgeons develop an early treatment plan. In this research, two approaches are investigated for lung cancer prediction. One approach is based on training machine learning model on the features extracted from image processing techniques. And the other approach involves Artificial Intelligence models for lung cancer detection. Computed Tomography (CT) pictures are useful for determining the stage of lung cancer in a patient. As a result, CT images of the lung region are explored in this study by constructing a content-based image retrieval system using various machine learning and Artificial Intelligence techniques. For medical photos, texture analysis is critical. As a result, algorithms such as the K-Means clustering method and morphological operations such as erosion, dilation, and so on are used

Spiders in Thailand (SIT) via spiderthailand.info: Thailand spider data retrieval system for geographical occurrence and photographic identification.

High biodiversity in the tropics is good for ecosystem services; however, challenges in taxonomy and identification usually come from such high biodiversity. Spiders are no exception to the challenges. Identifying spiders in tropical places like Thailand is difficult and time consuming. To reduce the difficulty of identifying Thai spiders, a data retrieval system for geographical occurrence and photographic identification was conducted to deploy on an online platform, Spiders in Thailand (SIT) via the website "spiderthailand.info". This allows professional arachnologists and amateur spider lovers to visit and check the geographical distribution of Thai spiders and to quickly access pictures for comparative photographic identification. To facilitate Thai spider identification, there were two parts, the database and the website, which are connected to each other. Data of Thai spiders were extracted from the World Spider Catalog to build a database comprising geographical occurrence and pictures of spider species in Thailand. The database was then linked with the website to display data. The dataset of pictures and illustrations extracted from taxonomic literature of the World Spider Catalog were included in the database for connecting with the online platform, Spiders in Thailand (SIT) via the website "spiderthailand.info" which facilitated access to pictures and illustrations, expediting the identification of Thai spider specimens. Geographical occurrences of Thai spiders consisted of 1419 records belonging to 670 species of 228 genera and 50 families. Amongst those, 461 species from 133 genera of 41 families were distributed only in Thailand. Around Thailand, 756 geographical localities were reported for spider occurrences. From 76 provinces and one additional special administrative area (Bangkok), 58 provinces showed occurrence records of spiders and 18 provinces showed non-occurrence records. Those provinces of non-occurrence records of spiders were Amnat Charoen, Ang Thong, Bueng Kan, Chai Nat, Maha Sarakham, Mukdahan, Nakhon Phanom, Nong Bua Lam Phu, Nonthaburi, Phayao, Phichit, Phra Nakhon Si Ayutthaya, Samut Prakan, Samut Sakhon, Si Sa Ket, Sing Buri, Uthai Thani and Yasothon. Most spiders were reported from Chiang Mai Province.

Automated Storage and Retrieval System for Warehouse

Manual picking and retrieval of items from storage locations can be time-consuming, leading to delays in order fulfillment. This can negatively impact customer satisfaction and the overall responsiveness of the supply chain. In addition, manual data entry and tracking systems are prone to human errors, resulting in discrepancies between recorded and actual inventory levels. This can lead to stockouts, overstocking, and difficulties in maintaining accurate inventory records. Therefore, a fully automated storage and retrieval system is proposed to tackle this problem. The overall system consists of infrared sensor as presence of item stored, LEDs indicator, warehouse model with compartments and stepper motors act as actuator to pick and place the item. This project aims to automate the storage and retrieval system with the assist of monitoring system for accurate tracking of inventory and space savings. The use of Programmable Logic Controller (PLC) in this project is a good representation of integrated automation technology in automated storage system design. Furthermore, monitoring system connected to a web-based system will be used to remotely monitor and operate the facility. Implementing an Automated Storage and Retrieval System (ASRS) in the warehouse can address these challenges by automating the storage, retrieval, and tracking of inventory.

Data mining algorithm in the identification of accounting fraud by smart city information technology

The identification of accounting fraud is an important measure to safeguard the interests of stakeholders and ensure the long-term development of the company. The current traditional methods for identifying accounting fraud rely on manual review and judgment, lacking objectivity and accuracy. In order to improve the accuracy of accounting fraud identification, improve identification efficiency and objectivity, this article combines smart city information technology to conduct in-depth research on data mining algorithms for accounting fraud identification. This article first provides a brief overview of smart cities and information technology, then introduces the basic theory of accounting fraud identification, and finally implements accounting fraud identification through k-means clustering mining algorithm. The data is divided into k clusters, and abnormal clusters are identified by checking the characteristics and attributes of each cluster. Compared with traditional rule-based and pattern based methods, this approach can more flexibly adapt to different types and forms of fraud, and can discover unknown patterns of fraud. In the experiment, this article used electronic data collection, analysis, and retrieval systems on the websites of the Shanghai Stock Exchange and Shenzhen Stock Exchange to collect 641 annual reports and financial characteristics from 62 listed companies that engaged in financial statement fraud and 84 companies that were not reported to have financial statement fraud from 2012 to 2021 as test samples. The results were tested and analyzed from several aspects, including the number of misjudgments, misjudgment rate, and ROC curve. The final test results show that compared to traditional accounting fraud identification methods, the comprehensive misjudgment rate of data mining algorithms based on smart cities has decreased by 3 %. The conclusion indicates that data mining algorithms used in smart city information technology to identify accounting fraud can help improve the accuracy of accounting fraud, improve audit objectivity and effectiveness.

Fetal Kidney Grafts and Organoids from Microminiature Pigs: Establishing a Protocol for Production and Long-Term Cryopreservation.

Fetal organs and organoids are important tools for studying organ development. Recently, porcine organs have garnered attention as potential organs for xenotransplantation because of their high degree of similarity to human organs. However, to meet the prompt demand for porcine fetal organs by patients and researchers, effective methods for producing, retrieving, and cryopreserving pig fetuses are indispensable. Therefore, in this study, to collect fetuses for kidney extraction, we employed cesarean sections to preserve the survival and fertility of the mother pig and a method for storing fetal kidneys by long-term cryopreservation. Subsequently, we evaluated the utility of these two methods. We confirmed that the kidneys of pig fetuses retrieved by cesarean section that were cryopreserved for an extended period could resume renal growth when grafted into mice and were capable of forming renal organoids. These results demonstrate the usefulness of long-term cryopreserved fetal pig organs and strongly suggest the effectiveness of our comprehensive system of pig fetus retrieval and fetal organ preservation, thereby highlighting its potential as an accelerator of xenotransplantation research and clinical innovation.

A patent retrieval method and system based on double classification

As one of the most prominent carriers of knowledge, patents can provide masses of cross-domain knowledge to support the innovative design process of products. However, there is a major problem faced by most patent-aided innovation design systems, that is, identifying and providing patents related to design requirements from a multitude of cross-domain patents. To address this problem, a patent retrieval method based on double classification is proposed in this study, and a corresponding patent-aided innovative design prototype system is also developed. Firstly, the functional attributes are extracted from design requirements and expanded to different fields based on functional bases, by which the primary patent sets are constructed via classifying cross-domain patents. Secondly, technical features are mined from the primary patent sets with the topic model, which is used to classify the primary patent sets in turn and construct the secondary patent sets, hence, corresponding patents can be obtained to solve the design problems. Finally, a patent-aided prototype system is developed based on the proposed method. On the basis of the system, the hole plug of irradiated samples of nuclear reactor pressure vessel has undergone innovative design, which verifies the feasibility and practicability of both the method and system.