國立虎尾科技大學 |

Language: English

Back

基於專利領域預訓練結合大型語言模型以評估專利文本與生成 = = Asse...

朱翔筠

基於專利領域預訓練結合大型語言模型以評估專利文本與生成 = = Assessing Patent Texts and Generating Patents Based on Patent Domain Pre-training Combined with Large Language Model /

Record Type:	Language materials, printed : Monograph/item
Title/Author:	基於專利領域預訓練結合大型語言模型以評估專利文本與生成 =/ 朱翔筠.
Reminder of title:	Assessing Patent Texts and Generating Patents Based on Patent Domain Pre-training Combined with Large Language Model /
remainder title:	Assessing Patent Texts and Generating Patents Based on Patent Domain Pre-training Combined with Large Language Model.
Author:	朱翔筠
Published:	雲林縣 :國立虎尾科技大學 , : 民113.06.,
Description:	[9], 78面 :圖, 表 ; : 30公分.;
Notes:	指導教授: 許乙清.
Subject:	專利. -
Online resource:	電子資源

基於專利領域預訓練結合大型語言模型以評估專利文本與生成 = = Assessing Patent Texts and Generating Patents Based on Patent Domain Pre-training Combined with Large Language Model /
朱翔筠

基於專利領域預訓練結合大型語言模型以評估專利文本與生成 =Assessing Patent Texts and Generating Patents Based on Patent Domain Pre-training Combined with Large Language Model /Assessing Patent Texts and Generating Patents Based on Patent Domain Pre-training Combined with Large Language Model.朱翔筠. - 初版. - 雲林縣 :國立虎尾科技大學 ,民113.06. - [9], 78面 :圖, 表 ;30公分.

指導教授: 許乙清.

碩士論文--國立虎尾科技大學資訊工程系碩士班.

含參考書目.

政府制定專利法以保障創意，但申請專利過程繁複，在專利申請前，不僅需了解發明、新型和設計三類專利的區別，且各類別的申請文件撰寫特點不同，不僅要清楚表達創意，還需符合產業利用性、新穎性及進步性三大專利要件。此外，需使用中華民國專利資訊檢索系統（Taiwan Patent Search System）進行查詢，以避免與現有專利雷同。上述問題若因選擇不當、未符合專利要件或與現有專利雷同，都可能導致申請被駁回。為了改善撰寫問題及提升申請效率與成功率，本論文蒐集中華民國專利資訊檢索系統中的公開專利文本，建置專利領域預訓練模型（Patent domain pre-trained BERT, PBERT），提升BERT模型對專利領域的理解能力，根據實驗結果，PBERT模型的混淆度可達1.5，相比其他預訓練模型降低了1.03。預訓練完畢後，以PBERT模型分別建置專利類別預測模型（Patent Category Prediction BERT, PCPBERT）和專利要件預測模型（Patentability Prediction BERT, PPBERT），評估文本的專利類別與是否滿足專利要件特性，在多元分類任務中，PCPBERT的準確率達到93.19%，而在多標籤任務中，PPBERT模型的準確率達到96.72%，兩者模型顯著優於其他未經專利領域訓練的模型；當文本未滿足任意特性時，使用專利文本生成模型（PatentLLAMA）修改文本以滿足專利要件特性，根據實驗結果顯示，PatentLLAMA在生成滿足專利要件的文本方面，成功率達到95.2%，已充分提高了撰寫效率。隨後為提升申請效率及成功率，建置LSI模型，比對自己的文本或想法，找尋相似的專利文本，避免遭到駁回。上述所有模型建置完畢後，以聊天機器人作為使用介面，結合先前所建置的四大模型。當使用者輸入對應之文本時，便可根據設定之功能改善撰寫專利時常遇到的問題，提升申請效率及成功率，讓需要相關資源的發明人降低被駁回機率。.

(平裝)Subjects--Topical Terms:

839994
專利.

基於專利領域預訓練結合大型語言模型以評估專利文本與生成 = = Assessing Patent Texts and Generating Patents Based on Patent Domain Pre-training Combined with Large Language Model /
LDR:05609cam a2200241 i 4500 001 1129700
008 241015s2024 ch ak erm 000 0 chi d
035 $a (THES)112NYPI0392014
040 $a NFU $b chi $c NFU $e CCR
041 0 # $a chi $b chi $b eng
084 $a 008.163M $b 2588 113 $2 ncsclt
100 1 $a 朱翔筠 $3 1448760
245 1 0 $a 基於專利領域預訓練結合大型語言模型以評估專利文本與生成 = $b Assessing Patent Texts and Generating Patents Based on Patent Domain Pre-training Combined with Large Language Model / $c 朱翔筠.
246 1 1 $a Assessing Patent Texts and Generating Patents Based on Patent Domain Pre-training Combined with Large Language Model.
250 $a 初版.
260 # $a 雲林縣 : $b 國立虎尾科技大學 , $c 民113.06.
300 $a [9], 78面 : $b 圖, 表 ; $c 30公分.
500 $a 指導教授: 許乙清.
500 $a 學年度: 112.
502 $a 碩士論文--國立虎尾科技大學資訊工程系碩士班.
504 $a 含參考書目.
520 3 $a 政府制定專利法以保障創意，但申請專利過程繁複，在專利申請前，不僅需了解發明、新型和設計三類專利的區別，且各類別的申請文件撰寫特點不同，不僅要清楚表達創意，還需符合產業利用性、新穎性及進步性三大專利要件。此外，需使用中華民國專利資訊檢索系統（Taiwan Patent Search System）進行查詢，以避免與現有專利雷同。上述問題若因選擇不當、未符合專利要件或與現有專利雷同，都可能導致申請被駁回。為了改善撰寫問題及提升申請效率與成功率，本論文蒐集中華民國專利資訊檢索系統中的公開專利文本，建置專利領域預訓練模型（Patent domain pre-trained BERT, PBERT），提升BERT模型對專利領域的理解能力，根據實驗結果，PBERT模型的混淆度可達1.5，相比其他預訓練模型降低了1.03。預訓練完畢後，以PBERT模型分別建置專利類別預測模型（Patent Category Prediction BERT, PCPBERT）和專利要件預測模型（Patentability Prediction BERT, PPBERT），評估文本的專利類別與是否滿足專利要件特性，在多元分類任務中，PCPBERT的準確率達到93.19%，而在多標籤任務中，PPBERT模型的準確率達到96.72%，兩者模型顯著優於其他未經專利領域訓練的模型；當文本未滿足任意特性時，使用專利文本生成模型（PatentLLAMA）修改文本以滿足專利要件特性，根據實驗結果顯示，PatentLLAMA在生成滿足專利要件的文本方面，成功率達到95.2%，已充分提高了撰寫效率。隨後為提升申請效率及成功率，建置LSI模型，比對自己的文本或想法，找尋相似的專利文本，避免遭到駁回。上述所有模型建置完畢後，以聊天機器人作為使用介面，結合先前所建置的四大模型。當使用者輸入對應之文本時，便可根據設定之功能改善撰寫專利時常遇到的問題，提升申請效率及成功率，讓需要相關資源的發明人降低被駁回機率。.
520 3 $a The government formulates patent laws to safeguard creativity, but the process of patent application is intricate. Prior to applying for a patent, one not only needs to understand the distinctions among invention, utility model, and design patents but also the unique characteristics of drafting documents for each category. It is imperative to clearly articulate the innovation while ensuring compliance with the three major patent criteria: industrial applicability, novelty, and inventive step.Additionally, one needs to utilize the Taiwan Patent Search System to conduct searches to avoid similarities with existing patents. Failure to choose appropriate options, meet patent criteria, or avoid similarity with existing patents can result in application rejection. To address these writing issues and enhance application efficiency and success rates, this paper collects publicly available patent texts from the Taiwan Patent Search System to establish a Patent domain pre-trained BERT (PBERT) model.This model enhances BERT's understanding of the patent domain. According to experimental results, the confusion degree of the PBERT model can reach 1.5, reducing by 1.03 compared to other pre-trained models. After pre-training, the PBERT model is used to build Patent Category Prediction BERT (PCPBERT) and Patentability Prediction BERT (PPBERT) models to evaluate text for patent category and patentability characteristics.In multi-class classification tasks, PCPBERT achieves an accuracy rate of 93.19%, while in multi-label tasks, PPBERT achieves an accuracy rate of 96.72%. Both models significantly outperform other models not trained in the patent domain. When the text does not meet any characteristic, the PatentLLAMA model is used to generate text that satisfies patent criteria. According to experimental results, PatentLLAMA achieves a success rate of 95.2% in generating text that meets patent criteria, significantly improving writing efficiency.Subsequently, an LSI model is constructed to compare one's own text or ideas with similar patent texts to avoid rejection. After establishing all the aforementioned models, a chatbot is employed as the user interface, integrating the four major models built previously. When users input corresponding text, they can improve common issues encountered in patent writing based on the set functions, enhancing application efficiency and success rates, thus reducing the probability of rejection for inventors in need of relevant resources..
563 $a (平裝)
650 # 7 $a 專利. $2 lcstt $3 839994
650 # 4 $a 深度學習. $3 1127425
650 # 4 $a 自然語言處理. $3 1151298
650 # 4 $a 聊天機器人. $3 1218289
650 # 4 $a 生成式AI. $3 1451480
650 # 4 $a Patent. $3 1348760
650 # 4 $a Deep Learning. $3 1127423
650 # 4 $a Natural Language Processing. $3 812048
650 # 4 $a BERT. $3 1420167
650 # 4 $a Chatbot. $3 1218292
650 # 4 $a Generative AI. $3 1451481
856 7 # $u https://handle.ncl.edu.tw/11296/2q96r8 $z 電子資源 $2 http