本文關(guān)鍵詞： 科技查新 檢索詞 關(guān)鍵詞抽取 網(wǎng)絡(luò)爬蟲(chóng)　出處：《現(xiàn)代圖書(shū)情報(bào)技術(shù)》2016年11期 　論文類(lèi)型：期刊論文

【摘要】：【目的】解決科技查新領(lǐng)域檢索詞選擇時(shí)的主觀性強(qiáng)、手工工作量大、不規(guī)范、費(fèi)時(shí)費(fèi)力的問(wèn)題�！緫�(yīng)用背景】為了實(shí)現(xiàn)檢索詞抽取過(guò)程的自動(dòng)化、智能化、規(guī)范化,本文提出利用科技查新過(guò)程檢出的實(shí)時(shí)相關(guān)語(yǔ)料作為領(lǐng)域知識(shí)的來(lái)源,并對(duì)語(yǔ)料組成類(lèi)型與關(guān)鍵詞抽取效果之間的關(guān)系進(jìn)行討論。【方法】通過(guò)關(guān)鍵詞抽取、領(lǐng)域特征擴(kuò)展相結(jié)合的遞進(jìn)式迭代抽取方式實(shí)現(xiàn)科技查新領(lǐng)域檢索詞的智能抽取�！窘Y(jié)果】通過(guò)與實(shí)際查新案例所采用的檢索詞對(duì)比,發(fā)現(xiàn)使用本方法兩次迭代后抽取10個(gè)檢索詞,召回率達(dá)到80%�！窘Y(jié)論】基于查新過(guò)程中檢出文獻(xiàn)構(gòu)成的動(dòng)態(tài)相關(guān)語(yǔ)料進(jìn)行檢索詞的迭代抽取有助于快速、準(zhǔn)確鎖定絕大部分檢索詞,提高檢索的效率和效果。
[Abstract]:[objective] to solve the problem of strong subjectivity, heavy manual work, non-standard, time-consuming and laborious selection of keywords in the field of scientific and technological novelty retrieval. [application background] in order to realize the automation and intelligence of the extraction process of search words. Standardization, this paper proposes to use the real-time correlation data from the process of science and technology retrieval as the source of domain knowledge. The relationship between the type of corpus and the effect of keyword extraction is discussed. [methods] keyword extraction is carried out through keyword extraction. A progressive iterative extraction method combined with domain feature expansion is used to realize intelligent extraction of search words in science and technology novelty retrieval field. [results] by comparing with the actual retrieval cases, the search terms are compared. It is found that this method is used to extract 10 search words after two iterations, and the recall rate is 80%. [conclusion] iterative extraction of search words based on the dynamic correlation-related data formed in the process of retrieval is helpful to speed up the retrieval. Lock most of the search words accurately to improve the efficiency and effect of retrieval.
【作者單位】： 中國(guó)科學(xué)院軟件研究所;中國(guó)科學(xué)院大學(xué);
【基金】：國(guó)家自然科學(xué)基金項(xiàng)目“云計(jì)算環(huán)境下的隱蔽信道機(jī)理研究”(項(xiàng)目編號(hào):61170072)、國(guó)家自然科學(xué)基金青年科學(xué)基金項(xiàng)目“移動(dòng)智能終端隱蔽信道機(jī)理研究”(項(xiàng)目編號(hào):61303057) 中國(guó)科學(xué)院、國(guó)家外國(guó)專(zhuān)家局創(chuàng)新團(tuán)隊(duì)國(guó)際合作項(xiàng)目“安全攸關(guān)軟件理論和構(gòu)造方法”的研究成果之一
【分類(lèi)號(hào)】：TP391.3;G252.62
【正文快照】： 1引言科技查新是一種通過(guò)文獻(xiàn)檢索、對(duì)比和分析,查證查新項(xiàng)目新穎性的信息咨詢服務(wù)工作。根據(jù)查新時(shí)的檢索范圍,可分為國(guó)內(nèi)查新、國(guó)外查新和國(guó)際查新三類(lèi)。其中,文獻(xiàn)檢索是科技查新的基礎(chǔ),涉及檢索式的組配,其中檢索詞的選定對(duì)檢索結(jié)果起著關(guān)鍵性的作用,是影響科技查新質(zhì)量的，

本文編號(hào)：1467705