In this project, we design a search query optimization system based on the user’s relevance feedback by generating customized query strings for existing patent alerts. Firstly, the Rocchio algorithm is used to generate a search string by analyzing the characteristics of related patents and unrelated patents. Then the collaborative filtering recommendation algorithm is used to rank the query results, which considering the previous relevance feedback and patent features, instead of only considering the similarity between query and patents as the traditional method. In order to further explore the performance of the optimization system, we design and conduct a series of evaluation experiments regarding TF-IDF as a baseline method. Experiments show that, with the use of generated search strings, the proportion of unrelated patents in search results is significantly reduced over time. In 4 months, the precision of the retrieved results is optimized from 53.5% to 72%. What’s more, the rank performance of the method we proposed is better than the baseline method. In terms of precision, top10 of recommendation algorithm is about 5 percentage points higher than the baseline method, and top20 is about 7.5% higher. It can be concluded that the approach we proposed can effectively optimize patent search results by learning relevance feedback.

Design-by-Analogy is a powerful tool to augment the traditional methods of concept generation and offers avenues to develop innovative and novel design solutions. Few tools exist to assist designers in systematically seeking and identifying analogies from within design repositories such as the United States Patent and Trademark Office patent database. A new tool for extracting functional analogies from patents has been developed to perform this task utilizing a Vector Space Model algorithm to quantitatively evaluate the functional similarity between design problems and patent descriptions of products. Initially, a Boolean Search approach was evaluated and several limitations were identified such as a lack of quantitative metrics for determining search result relevancy ranking as well as inadequate query mapping methods. Next, a Vector Space Model search tool was developed which includes extensive expansion of the Functional Basis using human-based term classification and automated document indexing techniques. The resulting functional patent controlled vocabulary consists of approximately 2,100 unique functions extracted from 65,000 randomly selected patents. The patent search database was generated by indexing 275,000 patents selected from the over 4 million patents available in digital form. A graphical user interface was developed to facilitate query vector generation, and the accompanying search result viewing interface provides data clustering and relevancy ranking. Two case studies are conducted to evaluate the efficacy of the search engine. The first case study successfully replicated the functional similarity results of a classic Design-by-Analogy problem of the guitar pickup winder. The second case study is an original design problem consisting of an automated window washer, and the results illustrate the range of analogically distant solutions that can be extracted ranging from very near-field, literal solutions to the far-field cross domain solutions. Finally, the search tool’s efficacy with regard to increasing quantity and novelty of ideas produced during Concept Generation is experimentally evaluated. The two factors evaluated are first whether analogies improved performance and second how the functionality level of the analogy impacted performance. The experimental results showed an increase in novelty for high functionality analogies compared with the control and other experimental groups. No statistically significant difference was found with regard to quantity of ideas generated. / text

本研究利用專利檢索與分析來探討靈芝產業中專利佈局情況，技術領域現況及發展重點，產業中的競爭者、合作者及廠商，以及得知靈芝於全球、區域或不同國家的產品應用情況。研究範圍以廣泛使用之靈芝（Ganoderma lucidum）及松杉靈芝（Ganoderma tsugae）為主要研究對象，分析範圍包括其子實體、菌絲體及擔孢子各部位外，亦包含其所含之各種活性成分及各類相關應用。 透過分析PCT、美國、台灣及中國大陸之靈芝相關專利，將專利件數、國際專利分類表分析（又稱為IPC分類分析）及專利權人分析等結果製成圖表並對照產業資訊後可得知：（1）韓國及中國大陸為主要的靈芝消費市場，其中中國大陸消費市場正逐年擴大，且產品種類繁多，為全球最重要的靈芝消費市場；（2）靈芝普遍以醫藥品開發及保健產品應用為最主要的技術發展方向，而醫藥品研發則以抗腫瘤及治療免疫或過敏疾病為主要治療的疾病；（3）不同國家靈芝研發領域有些許差異，美國及歐洲國家主要針對特定細胞株或特定疾病之醫藥品開發，而韓國或中國大陸則是以靈芝保健食品開發或傳統複方製劑為主要產品開發方向；（4）靈芝產業中的競爭國家有美國、日本、中國大陸及韓國；（5）台灣有數家廠商於不同國家進行專利佈局，其中中央研究院內靈芝多醣體團隊其專利產出最為亮眼，為國際上具有相當研發能力之機構；（6）台灣靈芝相關的研發能力仍優於中國大陸，專利品質較佳，故於靈芝產業中台灣廠商仍具有相當之優勢；（7）靈芝醫藥品開發之專利佈局以美國最為完整，而中國大陸則是在靈芝子實體栽種及茶代用品的專利數量較其他兩國家為多。 / This study is to explore the use of patent search and patent analysis in understanding the situation of current patent portfolio, technology mainstream development, competitors, collaborators, and their applications within the Ganaderma industry at the national, regional as well as international levels. Ganoderma lucidum and Ganoderma tsugae are the subjects in this study. The areas of investigation included different forms of fruiting bodies, mycelium, basidiospores, their active components as well as their respective applications. In this study, Ganoderma related patents in US, Taiwan, China as well as international patents under PCT (Patent Corporation Treaty) were searched and studied. By incorporating the industrial information together with visual display of the related patent information using tables and graphs, the following conclusions can be obtained: (1) Korea and China are the main consumer markets of Ganoderma in the world, especially China market is expanding every year with various categories of product; (2) the mainstream technologies are health related products such as dietary supplements and medicinal preparations for the use as antineoplastic, immunological or allergic agents; (3) Ganoderma is investigated in various fields among varous countries; for example, the focus of United States and European countries are concentrated in medicinal use of Ganoderma for specific cell line and treatment of diseases whereas China and Korea are concentrated in the dietary supplements and classical complex mixture preparation development; (4) the United States, Japan, China and Korea are the major marketers as well competitors among each other in Ganoderma industry; (5) several firms in Taiwan own patent portfolio in more than one country, and among them Academia Sinica is considered one of the best in the world; (6) the quality and strength of Taiwan patents is considered better than China; as such Taiwan Ganoderma industry should have superior capability in technology development compared to China; (7) in the field of medicinal product development and treatment of diseases, United States is the distinct leader in the patent landscape whereas China patents are concentrated in Ganoderma fruit body cultivation and their use as tea substitutes.

Ericsson’s Region IPR & Licensing (RIPL) receives about 3000 thousands Invention Disclosures (IvDs) every year submitted by researchers as a result of their R&D activities. To decide whether an IvD has a good business value and a patent application should be filed; a rigorous evaluation process is carried out by a selected Patent Attorney (PA). One of most important elements of the evaluation process is to find prior art similar, including similar IvDs that have been evaluated before. These documents are not public and therefore can’t be searched using available search tools. For now the process of finding prior art is done manually (without the help of any search tools) and takes up significant amount of time. The aim of this Master’s thesis is to develop and test an information retrieval search engine as a proof of concept to find similar Invention Disclosure documents and related patent applications. For this purpose, a SOLR database server is setup with up to seven thousand five hundred (7500) IvDs indexed. A similarity algorithm is implemented which is customized to weight different fields. LUCENE is then used to query the server and display the relevant documents in a web application.

The patent domain is a very important source of scientific information that is currently not used to its full potential. Searching for relevant patents is a complex task because the number of existing patents is very high and grows quickly, patent text is extremely complicated, and standard vocabulary is not used consistently or doesn’t even exist. As a consequence, pure keyword searches often fail to return satisfying results in the patent domain. Major companies employ patent professionals who are able to search patents effectively, but even they have to invest a lot of time and effort into their search. Academic scientists on the other hand do not have access to such resources and therefore often do not search patents at all, but they risk missing up-to-date information that will not be published in scientific publications until much later, if it is published at all. Document search on PubMed, the pre-eminent database for biomedical literature, relies on the annotation of its documents with relevant terms from the Medical Subject Headings ontology (MeSH) for improving recall through query expansion. Similarly, professional patent searches expand beyond keywords by including class codes from various patent classification systems. However, classification-based searches can only be performed effectively if the user has very detailed knowledge of the system, which is usually not the case for academic scientists. Consequently, we investigated methods to automatically identify relevant classes that can then be suggested to the user to expand their query. Since every patent is assigned at least one class code, it should be possible for these assignments to be used in a similar way as the MeSH annotations in PubMed. In order to develop a system for this task, it is necessary to have a good understanding of the properties of both classification systems. In order to gain such knowledge, we perform an in-depth comparative analysis of MeSH and the main patent classification system, the International Patent Classification (IPC). We investigate the hierarchical structures as well as the properties of the terms/classes respectively, and we compare the assignment of IPC codes to patents with the annotation of PubMed documents with MeSH terms. Our analysis shows that the hierarchies are structurally similar, but terms and annotations differ significantly. The most important differences concern the considerably higher complexity of the IPC class definitions compared to MeSH terms and the far lower number of class assignments to the average patent compared to the number of MeSH terms assigned to PubMed documents. As a result of these differences, problems are caused both for unexperienced patent searchers and professionals. On the one hand, the complex term system makes it very difficult for members of the former group to find any IPC classes that are relevant for their search task. On the other hand, the low number of IPC classes per patent points to incomplete class assignments by the patent office, therefore limiting the recall of the classification-based searches that are frequently performed by the latter group. We approach these problems from two directions: First, by automatically assigning additional patent classes to make up for the missing assignments, and second, by automatically retrieving relevant keywords and classes that are proposed to the user so they can expand their initial search. For the automated assignment of additional patent classes, we adapt an approach to the patent domain that was successfully used for the assignment of MeSH terms to PubMed abstracts. Each document is assigned a set of IPC classes by a large set of binary Maximum-Entropy classifiers. Our evaluation shows good performance by individual classifiers (precision/recall between 0:84 and 0:90), making the retrieval of additional relevant documents for specific IPC classes feasible. The assignment of additional classes to specific documents is more problematic, since the precision of our classifiers is not high enough to avoid false positives. However, we propose filtering methods that can help solve this problem. For the guided patent search, we demonstrate various methods to expand a user’s initial query. Our methods use both keywords and class codes that the user enters to retrieve additional relevant keywords and classes that are then suggested to the user. These additional query components are extracted from different sources such as patent text, IPC definitions, external vocabularies and co-occurrence data. The suggested expansions can help unexperienced users refine their queries with relevant IPC classes, and professionals can compose their complete query faster and more easily. We also present GoPatents, a patent retrieval prototype that incorporates some of our proposals and makes faceted browsing of a patent corpus possible.

The patent domain is a very important source of scientific information that is currently not used to its full potential. Searching for relevant patents is a complex task because the number of existing patents is very high and grows quickly, patent text is extremely complicated, and standard vocabulary is not used consistently or doesn’t even exist. As a consequence, pure keyword searches often fail to return satisfying results in the patent domain. Major companies employ patent professionals who are able to search patents effectively, but even they have to invest a lot of time and effort into their search. Academic scientists on the other hand do not have access to such resources and therefore often do not search patents at all, but they risk missing up-to-date information that will not be published in scientific publications until much later, if it is published at all. Document search on PubMed, the pre-eminent database for biomedical literature, relies on the annotation of its documents with relevant terms from the Medical Subject Headings ontology (MeSH) for improving recall through query expansion. Similarly, professional patent searches expand beyond keywords by including class codes from various patent classification systems. However, classification-based searches can only be performed effectively if the user has very detailed knowledge of the system, which is usually not the case for academic scientists. Consequently, we investigated methods to automatically identify relevant classes that can then be suggested to the user to expand their query. Since every patent is assigned at least one class code, it should be possible for these assignments to be used in a similar way as the MeSH annotations in PubMed. In order to develop a system for this task, it is necessary to have a good understanding of the properties of both classification systems. In order to gain such knowledge, we perform an in-depth comparative analysis of MeSH and the main patent classification system, the International Patent Classification (IPC). We investigate the hierarchical structures as well as the properties of the terms/classes respectively, and we compare the assignment of IPC codes to patents with the annotation of PubMed documents with MeSH terms. Our analysis shows that the hierarchies are structurally similar, but terms and annotations differ significantly. The most important differences concern the considerably higher complexity of the IPC class definitions compared to MeSH terms and the far lower number of class assignments to the average patent compared to the number of MeSH terms assigned to PubMed documents. As a result of these differences, problems are caused both for unexperienced patent searchers and professionals. On the one hand, the complex term system makes it very difficult for members of the former group to find any IPC classes that are relevant for their search task. On the other hand, the low number of IPC classes per patent points to incomplete class assignments by the patent office, therefore limiting the recall of the classification-based searches that are frequently performed by the latter group. We approach these problems from two directions: First, by automatically assigning additional patent classes to make up for the missing assignments, and second, by automatically retrieving relevant keywords and classes that are proposed to the user so they can expand their initial search. For the automated assignment of additional patent classes, we adapt an approach to the patent domain that was successfully used for the assignment of MeSH terms to PubMed abstracts. Each document is assigned a set of IPC classes by a large set of binary Maximum-Entropy classifiers. Our evaluation shows good performance by individual classifiers (precision/recall between 0:84 and 0:90), making the retrieval of additional relevant documents for specific IPC classes feasible. The assignment of additional classes to specific documents is more problematic, since the precision of our classifiers is not high enough to avoid false positives. However, we propose filtering methods that can help solve this problem. For the guided patent search, we demonstrate various methods to expand a user’s initial query. Our methods use both keywords and class codes that the user enters to retrieve additional relevant keywords and classes that are then suggested to the user. These additional query components are extracted from different sources such as patent text, IPC definitions, external vocabularies and co-occurrence data. The suggested expansions can help unexperienced users refine their queries with relevant IPC classes, and professionals can compose their complete query faster and more easily. We also present GoPatents, a patent retrieval prototype that incorporates some of our proposals and makes faceted browsing of a patent corpus possible.

在二十一世紀中， LED發光二極體更是備受期待的節能產品。過去背光源一直是LED主要應用項目，而漸漸地照明也開始採用LED產品，甚至各國已宣布將禁用白熾燈。然而，在各國政府及業者大力推廣及投入LED產業之際，目前LED產品尚未能實現市場替代效應之事實卻不容忽視。細究其可能原因，是否LED產品仍有技術功能缺陷，抑或其價格無法競爭，又者消費者對產品認知不足、終端通路尚未成熟、品牌塑造尚待建立等因素，讓消費者暫時裹足不前? 鑒於台灣在LED產業中已有完整的上中下游布局，不但是下游封裝的全球最大供應中心，近年更也逐步紮根中游晶粒產品，甚至切入上游單晶基板、磊晶產品製程。故此，本研究希冀探查現有LED產品所遭遇之困難，以功能品質及經濟價值等角度，找尋可突破市場瓶頸之關鍵因素，並針對其中可進行專利檢索及分析的較具技術性因素：LED單晶基板，以中國大陸此成長最為顯著之市場作為專利檢索及分析之核心地理區域，探討LED單晶片基板之專利發展趨勢以及研發參考目標及方向。 在進行專利檢索之前，本研究將先行剖析現有LED單晶片基板的應有功能、重點特性、4大類基板材料選擇與其最新研發優勢，包含藍寶石、碳化矽、矽、氮化鎵，以助於後續專利檢索及分析結果之觀察思考。本研究的結論與建議將分別針對不同的LED單晶片基板材料選擇，以專利分析結果對照其市場發展近況，向台灣業者提出藍寶石、碳化矽已係過度競爭、不宜進入的項目，並在最後建議台灣業者仍可持續投入研發LED矽、氮化鎵基板材料，以及額外以技術與應用創新增加其產品的市場連結度及應用產業競爭利基。 / Nowadays LED has become a future mainstream of highly expected energy-saving product. Back-lighting has been the main application for LED, such as in monitors, and furthermore lighting has grown its market size into significance. However, it should draw attention that LED products has not yet fully replace conventional lighting as expected, due to a number of possible factors, including functions, prices, consumer awareness, channeling, and/or branding. In light of the fully established LED industry in Taiwan, including the largest downstream packaging supply source, mature middle-stream wafer production and leading upstream epitaxy and substrate manufacturing, this study aims to seek and find the patent searchable and analyzable part of the current LED obstacles in product quality and economic value perspective. As a result, single crystal substrate falls into abovementioned criteria, including four major substrate materials: sapphire, silicon carbonate, silicon, and gallium nitrite. This study further concentrates the patent search and analysis on China, the fastest growing LED market among all regions and the biggest opportunity for Taiwan players. Before patent search, this study gives a detailed elucidation about four substrate materials on functions, important traits, different types and respective R&D updates and breakthrough, followed by interpretation of and association with patent search and analysis. At the end of this study, conclusions and suggestions are given, based on Taiwan players’ current relative strength and weakness. In sum, sapphire substrates and silicon carbonate substrate have overly competitive patent and market situation, and silicon substrates and gallium nitrite substrate may allow Taiwan players to continue and/or reinforce R&D investment. Additionally, technology and application innovation could increase product-market linkage and competitive edge in LED application industry.