• Home
  • Services
  • About
  • Contact
  • Blog
  • 知財活動のROICへの貢献
  • 生成AIを活用した知財戦略の策定方法
  • 生成AIとの「壁打ち」で、新たな発明を創出する方法

​
​よろず知財コンサルティングのブログ

特許サーチャーを知財アナリストに移行させる

25/12/2024

0 Comments

 
特許調査業務を行っている担当者を知財アナリストに移行させることは、知財部門にとっては急務となっています。それぞれの会社で苦労されていますが、生成AIに問いかけてみました。参考になる部分となんだという部分がありますが、ご参考まで。

  • 特許サーチャーを知財アナリストに移行させるためにはどうしたら良いか、論点を洗い出したい。
  • 特許サーチャーを知財アナリストへ移行させるために考慮すべき主な論点を踏まえ、特許サーチャーを知財アナリストに移行させるための方策を提言してください。
  • 時間軸を入れた提言としてください。
  • この提言を実行するにあたり、予想される問題点、対応策をピックアップしてください。
  • 特許サーチャーを知財アナリストに移行させる取り組みの成功事例、失敗事例があれば、紹介してください。
 
同じテーマで、バランスの取れた議論をするための最適なペルソナ3人を用意して議論させるという手法も試してみました。なかなか面白い議論になっています。
 
 
Transitioning Patent Searchers to Intellectual Property Analysts
 
Transitioning personnel engaged in patent search operations to intellectual property (IP) analysts has become an urgent priority for IP departments. While many companies are struggling with this transition, we posed the question to generative AI. Although some suggestions were insightful and others questionable, we share them here for your reference.
 
Identify and organize the key issues involved in transitioning patent searchers to IP analysts.
Propose strategies for transitioning patent searchers to IP analysts, considering the main issues identified.
Incorporate a timeline into the proposed strategies.
Highlight anticipated challenges and countermeasures associated with implementing the proposed strategies.
Provide examples of both successful and unsuccessful cases related to efforts in transitioning patent searchers to IP analysts.
 
 
I also tried a method of preparing three optimal personas to have a discussion on the same theme in order to have a balanced discussion. It turned out to be quite an interesting discussion.
Your browser does not support viewing this document. Click here to download the document.
Your browser does not support viewing this document. Click here to download the document.
0 Comments

AI時代の競争力を生む知財エコシステム

24/12/2024

1 Comment

 
これからのAI時代における企業競争力強化を目的として、2024年12月18日に「AI孔明」の製品発表会が『データと知財の融合で未来を創る!「AI孔明」製品発表会~AIネイティブ『AI孔明』を活用した企業競争力の新たな基盤~』と題して開催されました。
知財エコシステム セッション「AI時代の競争力を生む知財エコシステム」(Tokkyo.Ai株式会社取締役 COO 平井 智之氏)の部分を視聴しましたが、「AI孔明」という社内のクローズドデータにアクセスし要約や検索を効率化するLLMベースのツールと、「Tokkyo.Ai」の組合せで、新たな発明やビジネスモデルが生まれる可能性があり、アイデア創出・特許出願、事業戦略・知財戦略の立案などがさらに広がる可能性があると感じています。
 
 
AOSデータ社 データと知財の融合で未来を創る!「AI孔明」製品発表会の開催レポート
https://webinarabc.jp/new-webinar/aikomei/
 
AI時代の競争力を生む知財エコシステム
https://www.youtube.com/watch?v=XtRv35dxUWg
 
 
以下、平井氏講演をChatGPT-4oに要約してもらいました。
 
AI時代の競争力を生む知財エコシステム
この講演では、AI技術を活用した知財エコシステムの構築と活用について、具体例を交えながら詳しく説明されています。以下は講演内容を本人の話し方や言い回しを活かしてまとめたものです。


1. 自己紹介と背景
講演者は特許AI株式会社の平井智之氏です。特許AI株式会社はリーガルテックの子会社として2021年に設立され、知財の大衆化を理念に掲げています。「知財をもっと身近にしよう」という思いから、AIツールやプラットフォームを開発し、効率的な知財管理・活用を支援しています。
平井氏は、法律系大学院を卒業後、リーガルテックに新卒入社し、法務や第三者委員会関連の業務を経験。その後、事業全体の開発やセールスを統括する立場に就きました。この経験を活かして、知財管理を根本から効率化しようという取り組みを進めています。


2. 知財エコシステムとAIの役割
知財エコシステムとは、知的財産の創出、保護、活用を通じてイノベーションや経済成長を促進する仕組みです。これまで企業は、アイデアを社会実装するためのサイクルを回してきましたが、ここにAI技術が加わったことで劇的な効率化が進んでいます。
特に2022年秋にChatGPTが登場して以降、AIを搭載した製品が次々と発表されました。AIを使って、経営者がアイデア出しをする、特許保護の戦略を考える、事業展開をシミュレーションするなど、AIは今や欠かせない存在になっています。


3. AI技術の進化:従来型AIとLLMの比較
AI技術は、従来型のルールベースAIから大規模言語モデル(LLM)へと進化しました。
LLMと従来型AIの違い
  • データ規模: 従来は数千件から数百万件のデータを使っていたが、LLMは数兆件のデータを学習。
  • 柔軟性: 従来は決められたルールに従って動作していたが、LLMは文脈や指示に応じて柔軟に対応。
  • 応用範囲: 特許検索、文章生成、要約、分析など多様なタスクに対応。
平井氏は、従来型AIを「ガラケー」、LLMを「スマートフォン」に例え、拡張性の違いを強調しました。スマートフォンがアプリで機能を拡張できるように、LLMもあらゆるタスクに柔軟に対応できる点が大きな特徴です。


4. 実践的なAIツールの活用事例
ツールの機能:
  • 特許文案作成:メタバースなどのキーワードを入力するだけでAIが短時間で文書を生成。
  • 類似特許検索:過去の特許を即座に調査し、類似特許やトレンドを分析。
  • 競合分析:企業情報や市場動向を自動分析。
導入効果:
  • 書類作成や調査に要する時間を10時間から1時間以内に短縮。
  • 研究者や技術者が直接ツールを使用して特許戦略を策定。
  • 特許出願前に類似技術を特定し、無駄な出願を回避。
特に、発明の文案作成から類似特許の検索、権利化までAIがサポートすることで、研究者自身が効率的に知財戦略を立案できるようになっています。


5. AI孔明:社内データの活用と新しいアイデア創出
AI孔明とは? 社内のクローズドデータにアクセスし、要約や検索を効率化するLLMベースのツールです。
主な機能:
  • 社内文書の分析:ドキュメント内の記述を要約・整理。
  • 知識共有と検索:クラウド上で安全にデータ管理。
  • 新規アイデア提案:既存データと新技術を組み合わせて価値を創出。
「社内データにはウェブには載っていない価値ある情報がたくさん眠っている」と平井氏は指摘します。AI孔明はこのデータを最大限に活用し、アイデア創出や事業戦略の立案を支援します。


6. 特許マーケットプレイスと新たな収益モデル
特許マーケットプレイスの概要:
  • 特許やアイデアの掲載と取引。
  • AIによる分析を活用してライセンスや売買を効率化。
  • 新しい技術と既存技術を組み合わせた発明を創出。
ブロックチェーン技術の活用:
  • 製品の真正性証明:QRコードを利用した認証。
  • NFT技術を活用したブランド管理。
AI分析を取り入れることで、ライセンスや売買における組み合わせ提案も可能となり、新たな発明やビジネスモデルが生まれる可能性が広がります。


7. まとめと今後の展望
この講演では、AI技術を活用して知財エコシステムを効率化する可能性が強調されました。特にLLMやAI公明を活用することで、データ管理から発明の創出、権利化、収益化まで一貫した支援が可能になります。
平井氏は「AIなしでは生きていけない時代がすぐそこまで来ている」と述べ、AIが今後の知財管理の標準ツールになることを確信しています。
 
 
 
Intellectual Property Ecosystem Driving Competitiveness in the AI Era
 
To enhance corporate competitiveness in the upcoming AI era, the product launch event for "AI Koumei" was held on December 18, 2024, under the theme: "Shaping the Future through the Integration of Data and Intellectual Property! 'AI Koumei' Product Launch Event—A New Foundation for Corporate Competitiveness Utilizing AI-Native 'AI Koumei'."
I attended the Intellectual Property Ecosystem session, "Intellectual Property Ecosystem Driving Competitiveness in the AI Era," presented by Mr. Tomoyuki Hirai, COO of Tokkyo.Ai Inc.
The combination of "AI Koumei," an LLM-based tool that enhances summarization and search efficiency by accessing closed internal data, and "Tokkyo.Ai" has the potential to generate new inventions and business models. This synergy could further expand possibilities in idea creation, patent applications, and the planning of business and intellectual property strategies.
 
 
Summary of Mr. Hirai’s Lecture by ChatGPT-4o
 
Intellectual Property Ecosystem Driving Competitiveness in the AI Era
This lecture provides a detailed explanation of building and utilizing an intellectual property (IP) ecosystem powered by AI technologies, including specific examples. The following is a summary preserving Mr. Hirai’s speaking style and expressions.
 
1. Introduction and Background
The speaker, Mr. Tomoyuki Hirai, is the COO of Tokkyo.Ai Inc. Tokkyo.Ai was established in 2021 as a subsidiary of a legal tech company, promoting the democratization of intellectual property with the vision of making IP more accessible. The company develops AI tools and platforms to support efficient IP management and utilization.
 
Mr. Hirai graduated from a law-focused graduate school and joined a legal tech company as a new graduate, gaining experience in legal affairs and third-party committee work. Later, he took charge of overall business development and sales. Leveraging this experience, he has been driving initiatives to fundamentally streamline IP management.
 
2. The Role of AI in the IP Ecosystem
An IP ecosystem facilitates innovation and economic growth through the creation, protection, and utilization of intellectual property. Companies have traditionally operated cycles to implement ideas in society, but integrating AI has dramatically improved efficiency.
 
Since the emergence of ChatGPT in fall 2022, AI-powered products have rapidly entered the market. AI now plays an essential role in brainstorming ideas, formulating patent protection strategies, and simulating business developments.
 
3. Evolution of AI Technology: Traditional AI vs. LLMs
AI technology has evolved from rule-based systems to large language models (LLMs).
 
Differences between Traditional AI and LLMs:
 
Data Scale: Traditional AI utilized thousands to millions of data points, whereas LLMs are trained on trillions.
Flexibility: Traditional AI followed predefined rules, while LLMs adapt flexibly to context and instructions.
Applications: LLMs support tasks such as patent searches, text generation, summarization, and analysis.
Mr. Hirai compared traditional AI to a “feature phone” and LLMs to a “smartphone,” emphasizing their scalability. Just as smartphones can expand functionalities with apps, LLMs can flexibly handle a wide range of tasks.
 
4. Practical Use Cases of AI Tools
Key Features of the Tools:
 
Patent Document Creation: Generates drafts based on keywords like “metaverse” within a short time.
Similar Patent Search: Instantly analyzes past patents and identifies trends.
Competitive Analysis: Automatically evaluates company data and market trends.
Implementation Benefits:
 
Reduces document preparation and research time from 10 hours to less than 1 hour.
Enables researchers and engineers to directly use tools for patent strategy formulation.
Identifies similar technologies before filing patents to avoid redundant applications.
By supporting tasks from drafting inventions to patent searches and commercialization, AI enables researchers to efficiently plan IP strategies.
 
5. AI Koumei: Leveraging Internal Data for Idea Generation
What is AI Koumei?
AI Koumei is an LLM-based tool designed to enhance summarization and search efficiency by accessing internal closed data.
 
Main Features:
 
Internal Document Analysis: Summarizes and organizes content within documents.
Knowledge Sharing and Search: Manages data securely in the cloud.
New Idea Proposals: Combines existing data and new technologies to create value.
Mr. Hirai highlighted that “valuable information often remains hidden in internal data not available online.” AI Koumei maximizes the use of this data, supporting idea generation and business strategy development.
 
6. Patent Marketplaces and New Revenue Models
Overview of Patent Marketplaces:
 
Lists and trades patents and ideas.
Uses AI analysis to streamline licensing and sales.
Creates new inventions by combining existing and emerging technologies.
Utilization of Blockchain Technology:
 
Product Authenticity Verification: Uses QR codes for certification.
Brand Management via NFT Technology.
By incorporating AI analysis, the platform facilitates proposals for combinations in licensing and sales, expanding the possibilities for new inventions and business models.
 
7. Conclusion and Future Outlook
The lecture emphasized the potential for AI technologies to enhance IP ecosystems efficiently. By leveraging tools like LLMs and AI Koumei, companies can receive comprehensive support—from data management and idea generation to patent protection and monetization.
 
Mr. Hirai concluded by stating, “We are approaching an era where living without AI will be impossible,” expressing confidence that AI will soon become the standard tool for IP management.
1 Comment

関西知的財産セミナー「AIと知財」

23/12/2024

0 Comments

 
12月20日行われた「関西知的財産セミナー」(主催:大阪工業大学 知的財産学部・知的財産研究科)の「AIと知財」と題する知的財産戦略推進事務局参事官 白鳥綱重氏の講演をWEBで視聴しました。
「AI時代における知的財産権検討会」でのAIと知財の関係についての検討結果がは本年5月に「中間とりまとめ」として公表され、11月には「AI時代の知的財産権検討会 中間とりまとめの概要」と「AI時代の知的財産権検討会 中間とりまとめの手引き(権利者向け)」が公表されています。講演では、「中間とりまとめ」が示す考え方の紹介がされました。
若干新しい内容も含まれていましたが、内容の転送などは禁じられているため、ほとんど同じ資料が掲載されている3つの資料を下記に示すにとどめます。
 
AI時代の知的財産権検討会 中間とりまとめの手引き(権利者向け)
https://www.kantei.go.jp/jp/singi/titeki2/chitekizaisan2024/2411_tebiki.pdf
 
AI時代の知的財産権検討会 中間とりまとめの概要
https://www.kantei.go.jp/jp/singi/titeki2/chitekizaisan2024/2411_gaiyou.pdf
 
第2回構想委員会 資料2:IPトランスフォーメーション
https://www.kantei.go.jp/jp/singi/titeki2/tyousakai/kousou/2025/dai2/siryou2.pdf
 
 
 
Kansai Intellectual Property Seminar: "AI and Intellectual Property"
 
I watched the online broadcast of the lecture titled "AI and Intellectual Property," delivered by Mr. Tsunashige Shiratori, Counselor at the Intellectual Property Strategy Promotion Office, during the "Kansai Intellectual Property Seminar" held on December 20 (organized by the Faculty of Intellectual Property and the Graduate School of Intellectual Property at Osaka Institute of Technology).
The results of discussions on the relationship between AI and intellectual property, conducted by the "Study Group on Intellectual Property Rights in the AI Era," were published as an "Interim Report" in May of this year. In November, two additional documents were released: "Overview of the Interim Report by the Study Group on Intellectual Property Rights in the AI Era" and "Guide to the Interim Report by the Study Group on Intellectual Property Rights in the AI Era (For Rights Holders)."
During the lecture, the concepts presented in the "Interim Report" were introduced.
Although some new content was included, redistribution of the material is prohibited. Therefore, I will only list below the three documents, which contain almost identical content to the lecture.

0 Comments

特許検索式作成における生成AIの活用方法

22/12/2024

0 Comments

 
生成AI(OpenAI o1)に、『特許検索式作成における生成AIの活用方法』というタイトルで、企業の研究者・技術者向けの新書を書かせてみました。
プロンプトは、「『特許検索式作成における生成AIの活用方法』というタイトルで企業の研究者・技術者向けの新書を10万字で書きたいと思いますので、よろしくお願いします。」というものです。
生成AI(OpenAI o1)からの提案に対して、いくつか指示を出し、生成AI(OpenAI o1)の提案を求めるという作業を行っています。生成AI(OpenAI o1)の提案する考え方は、それなりによくわかるのですが、私の意図とは異なる方向なので、この方向で完成するのは止めました。
従って、やり取りは途中までになっていますが、参考になればと思い、そのプロセスを添付しましたので、ご参照ください。
 
【本書タイトル】
『特許検索式作成における生成AIの活用方法』
対象読者:
•     企業の研究者・技術者
•     知財部門担当者
•     特許情報調査や競合技術調査を行う担当者
•     AIを活用した業務効率化に興味のあるビジネスパーソン
本書の目的:
•     研究開発・知財の実務で必要となる特許検索において、生成AI(例:ChatGPTなど)をどのように活用できるかを包括的に解説する。
•     特許検索の精度を高めるための検索式作成手法、AIのプロンプト設計ノウハウ、注意点やリスクマネジメントなどを体系的にまとめる。
•     実務での具体的な事例や運用形態を示すことで、読者が実際に取り入れやすいようにする。
________________________________________
【目次】
1. はじめに
1.1 特許検索の重要性
1.2 生成AIがもたらすイノベーション
1.3 本書の構成と読み方
2. 特許検索の基礎知識
2.1 特許検索の目的とプロセス
2.2 特許分類とIPC/ステート・オブ・ジ・アート調査の基本
2.3 検索データベースの種類と特徴
2.4 検索式作成の一般的なフロー
3. 生成AIの概要と特許分野における可能性
3.1 生成AIとは何か
3.2 ChatGPTをはじめとした大規模言語モデルの仕組み
3.3 特許文書と自然言語処理の相性
3.4 生成AIが特許検索にもたらすメリット・デメリット
4. 特許検索式の作成技法:従来手法と課題
4.1 キーワードベースの検索式の限界
4.2 類義語・シノニム対応の難しさ
4.3 特許分類の複雑さと組み合わせ
4.4 特許クレーム・明細書の構造への対応
5. 生成AIを用いた検索式作成の基本プロセス
5.1 検索意図の明確化とAIへの指示(プロンプト設計)の重要性
5.2 ステップ1:検索目的の設定・整理
5.3 ステップ2:キーワード候補の抽出
5.4 ステップ3:生成AIによる類義語や関連用語のリストアップ
5.5 ステップ4:分類シンボルや関連分野の把握
5.6 ステップ5:実際の検索式への落とし込み
5.7 ステップ6:ノイズ除去と再検証
6. 実務事例1:自社コア技術に関する特許検索式の作成
6.1 ケース概要(例:自動車部品メーカーによるEV駆動系部品の特許調査)
6.2 生成AIによるキーワード洗い出しと評価
6.3 分類(IPC・CPC等)との組み合わせ方
6.4 必要に応じたノイズ除去ルール
6.5 実際の検索式例
6.6 得られた結果と考察
7. 実務事例2:競合製品動向調査のための特許検索式
7.1 ケース概要(例:食品メーカーによる植物由来タンパク質の技術動向調査)
7.2 生成AIを活用した文献リストアップ
7.3 分析ツールとの連携と可視化
7.4 クレーム・明細書の読解支援へのAI応用
7.5 検索結果から見出せる知見
8. 実務事例3:海外特許調査と多言語検索への展開
8.1 グローバル調査における課題と生成AIの活用
8.2 多言語キーワード抽出・翻訳と留意点
8.3 現地語特有の用語・慣習の吸い上げ
8.4 AI翻訳サービスとの連携で得られる利点とリスク
8.5 海外調査の検索式と実例
9. プロンプトエンジニアリング:生成AIを最大限活用するために
9.1 プロンプト設計の基礎と考え方
9.2 特許領域での具体的なプロンプト例
9.3 プロンプト分割・リカレント手法・チェーンオブソート
9.4 ノイズや誤情報が出る場合の対処法
10. 知財リスクマネジメントとコンプライアンス
10.1 AIが生成する情報の真偽と取り扱い方
10.2 機密情報の取り扱いと社内ルール整備
10.3 AIの利用に関する法的・倫理的側面
10.4 特許取得戦略との整合性
11. 今後の展望:特許検索の自動化と知財戦略の高度化
11.1 AIによる高度なクレーム解析と要約技術
11.2 パテントポートフォリオ最適化への応用
11.3 ゲノム編集・量子コンピュータなど先端領域でのAI活用
11.4 実務スキルとAI活用のハイブリッド化
12. 結論:生成AIと共創する特許検索の未来
12.1 研究者・技術者が身につけるべき新しいリテラシー
12.2 組織全体での導入・教育への提言
12.3 AI時代の特許戦略に求められる柔軟性
13. 付録
o        AI関連用語集
o        特許検索データベース一覧
o        ChatGPT等の生成AIで使える主なプロンプト例
o        参考文献と関連サイト
 
 
 
Utilizing Generative AI for Patent Search Query Formulation
 
I had Generative AI (OpenAI o1) create a draft of a new book titled "Utilizing Generative AI for Patent Search Query Formulation," targeted at corporate researchers and engineers.
The prompt I provided was:
"I would like to write a 100,000-character book titled 'Utilizing Generative AI for Patent Search Query Formulation,' aimed at corporate researchers and engineers. Please assist with this project."
In response to suggestions from the Generative AI (OpenAI o1), I provided feedback and requested further suggestions. Although the AI's proposals made sense, they diverged from my intended direction, so I decided not to complete the project along that path.
Nevertheless, I have attached the partial process as a reference, which I hope you will find helpful.


[Book Title]
Utilizing Generative AI for Patent Search Query Formulation
Target Audience:
  • Corporate researchers and engineers
  • Intellectual property (IP) department staff
  • Personnel responsible for patent information research and competitor technology analysis
  • Business professionals interested in improving work efficiency through AI
Purpose of the Book:
  • Provide a comprehensive explanation of how to utilize generative AI (e.g., ChatGPT) in patent searches required for R&D and IP practices.
  • Systematically summarize methods for creating effective search queries, designing AI prompts, and managing associated risks.
  • Offer practical examples and operational approaches to ensure easy adoption by readers.


[Table of Contents]
1. Introduction
1.1 Importance of Patent Searches
1.2 Innovations Brought by Generative AI
1.3 Book Structure and How to Read It
2. Basics of Patent Searches
2.1 Purpose and Process of Patent Searches
2.2 Patent Classification and Basics of IPC/State-of-the-Art Surveys
2.3 Types and Features of Search Databases
2.4 General Workflow for Query Formulation
3. Overview of Generative AI and Its Potential in the Patent Field
3.1 What Is Generative AI?
3.2 Mechanisms of Large Language Models Like ChatGPT
3.3 Compatibility Between Patent Documents and Natural Language Processing
3.4 Pros and Cons of Generative AI in Patent Searches
4. Query Formulation Techniques: Traditional Methods and Challenges
4.1 Limitations of Keyword-Based Queries
4.2 Challenges in Handling Synonyms and Related Terms
4.3 Complexity and Combinations of Patent Classifications
4.4 Addressing Patent Claims and Specification Structures
5. Basic Process for Query Formulation Using Generative AI
5.1 Clarifying Search Intent and Importance of AI Prompt Design
5.2 Step 1: Setting and Organizing Search Objectives
5.3 Step 2: Extracting Keyword Candidates
5.4 Step 3: Generative AI Suggestions for Synonyms and Related Terms
5.5 Step 4: Identifying Classification Symbols and Related Fields
5.6 Step 5: Incorporating Keywords into Actual Search Queries
5.7 Step 6: Noise Removal and Revalidation
6. Case Study 1: Creating Patent Queries for Core Technologies
6.1 Case Overview (e.g., EV Drive System Components by an Automotive Manufacturer)
6.2 Generative AI-Driven Keyword Extraction and Evaluation
6.3 Combining Keywords with Classifications (IPC/CPC, etc.)
6.4 Defining Rules for Noise Removal
6.5 Example of a Search Query
6.6 Results and Observations
7. Case Study 2: Competitive Product Trend Analysis
7.1 Case Overview (e.g., Plant-Based Protein Research by a Food Manufacturer)
7.2 Generative AI for Listing Relevant Documents
7.3 Integration with Analytical Tools and Visualization
7.4 AI Applications for Claims and Specification Analysis
7.5 Insights from Search Results
8. Case Study 3: International Patent Search and Multilingual Expansion
8.1 Challenges in Global Searches and AI Utilization
8.2 Multilingual Keyword Extraction, Translation, and Key Considerations
8.3 Extracting Language-Specific Terms and Practices
8.4 Advantages and Risks of Using AI Translation Services
8.5 Search Queries and Examples for Overseas Searches
9. Prompt Engineering: Maximizing Generative AI Capabilities
9.1 Basics and Concepts of Prompt Design
9.2 Practical Prompt Examples for Patent Searches
9.3 Techniques: Prompt Splitting, Recurrent Methods, and Chain-of-Thought
9.4 Handling Noise and Misinformation
10. IP Risk Management and Compliance
10.1 Verifying and Handling AI-Generated Information
10.2 Managing Confidential Information and Establishing Internal Rules
10.3 Legal and Ethical Aspects of AI Utilization
10.4 Alignment with Patent Acquisition Strategies
11. Future Prospects: Patent Search Automation and Advanced IP Strategies
11.1 Advanced Claim Analysis and Summarization by AI
11.2 Applications for Patent Portfolio Optimization
11.3 AI Utilization in Cutting-Edge Fields Like Genome Editing and Quantum Computing
11.4 Hybridization of Practical Skills and AI Utilization
12. Conclusion: The Future of Patent Searches with Generative AI
12.1 New Literacies Researchers and Engineers Should Acquire
12.2 Recommendations for Organization-Wide Implementation and Education
12.3 Flexibility Needed for Patent Strategies in the AI Era
13. Appendix
  • Glossary of AI-Related Terms
  • List of Patent Search Databases
  • Examples of Prompts for Generative AI Tools Like ChatGPT
  • References and Related Websites
 

Your browser does not support viewing this document. Click here to download the document.
0 Comments

OpenAI、新世代モデル「o3」、「o3 mini」を発表

22/12/2024

0 Comments

 
12月20日、OpenAI連続発表会の12日目に「o3」、「o3 mini」の登場が発表されました。
「o3」は高度な推論力を持ち、数学・プログラミング・科学分野で人間専門家水準を上回る性能を達成しています。
人間が容易に解けるのに大規模言語モデル(LLM)が解けなかった「ARC-AGI」と呼ばれるベンチマークテストで、「o3」は飛躍的に性能を向上させました。GPT-3が0%(2020年)、GPT-4oが5%(2024年)だったのが、計算リソースを抑えつつ実行した場合75.7%、大量の計算資源を投入した場合87.5%で、人間の水準(85%)を上回る正解率となっています。
「o3 mini」は、コスト効率を重視した軽量版モデルで、2025年1月末に、続いてo3も一般公開予定とのことです。
現状、OpenAIでは、2024年5月からの「ChatGPT-4o」、2024年12月からの「OpenAI o1」、「OpenAI o1 pro」、「OpenAI o1 mini」を用途により使い分ける使い方になります。
Googleでは、2024年2月からの「Gemini 1.5 Pro」、「Gemini 1.5 Flash」(2024年9月にいずれもアップデート)に加え、2024年12月11日「Gemini2.0 Flash Experimental」、12月19日新たな推論AIモデル「Gemini 2.0 Flash Thinking」が発表され、現在使えるようになっています。
Anthropicでは、2024年3月に発表された「Claude 3 Opus」、2024年6月に発表された「Claude 3.5 Sonnet」(2024年10月アップグレード)、2024年10月発表された「Claude 3.5 Haiku」が現在使えます。
これら3社以外にも、次々と新しい大規模言語モデル(LLM)が発表されていますので、用途に応じて使い分けることが出来る時代になってきたと言えます。
 
 
o3 preview & call for safety researchers
https://openai.com/12-days/
 
【転換点直前】o1を越える「o3」登場。性能・特徴を徹底解説
https://chatgpt-lab.com/n/nc3c0040035c1
 
 
 
OpenAI Unveils New Generation Models "o3" and "o3 mini"
 
On December 20, the 12th day of OpenAI's consecutive announcement event, the release of "o3" and "o3 mini" was announced.
The "o3" model boasts advanced reasoning capabilities, achieving performance levels that surpass human experts in fields such as mathematics, programming, and science. It demonstrated remarkable improvements in the ARC-AGI benchmark test, which measures tasks that are easy for humans but challenging for large language models (LLMs).
While GPT-3 achieved a 0% accuracy rate in 2020 and GPT-4o reached 5% in 2024, "o3" recorded a 75.7% accuracy rate when executed with limited computational resources. When provided with extensive computational resources, it achieved an 87.5% accuracy rate, surpassing the human benchmark of 85%.
The "o3 mini" is a lightweight version designed with cost-efficiency in mind. It is scheduled for public release by the end of January 2025, followed by the general release of "o3."
Currently, OpenAI offers the "ChatGPT-4o" since May 2024, and "OpenAI o1," "OpenAI o1 pro," and "OpenAI o1 mini" starting from December 2024, which can be used based on specific purposes.
Google has also introduced models like "Gemini 1.5 Pro" and "Gemini 1.5 Flash" since February 2024, both of which were updated in September 2024. Additionally, the "Gemini 2.0 Flash Experimental" was announced on December 11, 2024, and is now available.
Anthropic offers "Claude 3 Opus," released in March 2024, "Claude 3.5 Sonnet," launched in June 2024 and upgraded in October 2024, and "Claude 3.5 Haiku," introduced in October 2024.
Besides these three companies, numerous new large language models (LLMs) continue to be released, allowing users to select models that best suit their specific needs.
 

0 Comments

新たな推論AIモデル「Gemini 2.0 Flash Thinking」

21/12/2024

0 Comments

 
Googleは12月19日、新たな推論AIモデル「Gemini 2.0 Flash Thinking」を発表し、Experimental(実験)モデルをGoogle AI Studioで公開しました。12月11日に登場したばかりのGemini 2.0 Flashの派生モデルです。
Gemini 2.0 Flash Thinkingは、回答時に「思考プロセス(thinking process)」を生成、ベースとした「Gemini 2.0 Flash」よりも高度な推論が可能ということで、OpenAI o1のライバルと言えそうです。
各種テストでOpenAIのo1-previewやGPT-4oを超える性能という評価や、Gemini 2.0 Flash ThinkingとOpenAI o1を比較してみた結果、OpenAI o1の圧勝だったという報告もあります。
性能競争が新たな段階に入ったようです。
 
 
Googleが思考プロセスを導入して推論を強化したAIモデル「Gemini 2.0 Flash Thinking」を公開、各種テストでOpenAIのo1-previewやGPT-4oを超える性能
https://gigazine.net/news/20241220-google-gemini-flash-thinking/
 
GoogleのGemini 2.0 Flash Thinkingを徹底検証!思考プロセスが生む推論力とは? 2024-12-20
https://weel.co.jp/media/tech/gemini-2-flash-thinking/
 
Google、「Gemini 2.0 Flash Thinking」公開 「o1」競合の“思考過程を示す”推論AIモデル
https://www.itmedia.co.jp/news/articles/2412/20/news108.html
 
 
 
New Inference AI Model "Gemini 2.0 Flash Thinking"
 
On December 19, Google announced a new inference AI model called "Gemini 2.0 Flash Thinking" and released an experimental version in Google AI Studio. This model is a derivative of "Gemini 2.0 Flash," which was introduced just recently on December 11.
Gemini 2.0 Flash Thinking is said to enable more advanced reasoning compared to its predecessor, "Gemini 2.0 Flash," by generating a "thinking process" during responses. It is expected to rival OpenAI's o1 model.
Performance evaluations indicate that it has surpassed OpenAI's o1-preview and GPT-4o in various tests. However, there are also reports that OpenAI's o1 achieved overwhelming victories when directly compared with Gemini 2.0 Flash Thinking.
It seems the competition in AI performance has entered a new phase.
 

0 Comments

USPTOの特許審査品質向上に向けたAI活用の取り組み

21/12/2024

0 Comments

 
USPTOが、特許審査の品質向上に向けた取り組みを公表しています。ウェブサイトのキャシー・ヴィダル長官のブログ記事の中では、特許審査の品質を向上させるためのツールの開発にAIが活用されていることが気になりました。
日本の特許庁のAI活用の検討より幅広い範囲でAI活用が検討されているようです。
 
『審査官が最良の先行技術を効率的に特定できる最良のツールを提供しなければなりません。すべての特許審査官が特許審査エンドツーエンド(PE2E)検索スイートを使用しており、半数以上の審査官が「この文書に似たもの」や「類似性検索」などのPE2Eの人工知能(AI)検索機能を日常的に使用しています。2022年9月以降、審査官はこれらのAI機能を使用して150万件以上のPE2Eクエリを実行しています。
また、審査官が外国出願で特定された先行技術や、関連出願に対する特許審判・不服審判部(PTAB)の審理中に特定された技術から学ぶことができるプロセスも用意しています。さらに現在、先行技術調査やその他の特許審査機能を改善するために、AIの他の用途を調査する作業も進めています。
We must provide examiners the best tools to efficiently identify the best prior art. All patent examiners use the Patents End-to-End (PE2E) Search suite, and more than half regularly use PE2E’s artificial intelligence (AI) search features, including “More Like This Document” and “Similarity Search.” Since September 2022, examiners have run more than 1.5 million PE2E queries using these AI-powered features.
We also have processes through which examiners can learn from prior art identified in foreign applications or art identified during Patent Trial and Appeal Board (PTAB) challenges in related applications. And we are currently working to investigate other uses of AI to improve the prior art search and other functions in patent examination.』
 
 
 
 
USPTO、特許審査の品質向上に向けた取り組みを公表
2024 年 12 月 16 日
https://www.jetro.go.jp/ext_images/_Ipnews/us/2024/20241216.pdf
 
Quality U.S. patents drive our economy and solve world problems
Kathi Vidal
December 9, 2024
https://www.uspto.gov/blog/quality-us-patents-drive-our-economy-and-solve-world-problems
 
 
 
USPTO Efforts to Improve Patent Examination Quality Using AI
 
The USPTO has announced its efforts to improve the quality of patent examination. In Director Cathy Vidal's blog post on the website, I was interested to see that AI is being used to develop tools to improve patent examination quality.
It seems that AI is being considered for use in a broader range of areas than the Japanese Patent Office's consideration of AI use.
0 Comments

特許の審査、サーチにおけるAIの活用

20/12/2024

0 Comments

 
日本知財学会、韓国知識財産学会、中国知識産権研究会が2012年より年に1回三カ国交代でシンポジウムを開催していますが、今年は特許庁および日本弁理士会と共催し、「日中韓連携知的財産シンポジウム2024」として、12月19日に東京大学 伊藤謝恩ホールで開催されました。テーマ4つのうちの2つがAIに関するものでした。「特許の審査、サーチにおけるAIの活用」と「大規模言語モデル技術の審査メカニズムへの挑戦」ですが、日本、中国、韓国の取り組みの違いも参考になりました。
日本特許庁の講演「特許の審査とサーチにおけるAIの活用」は、が2024年11月7日の「第8回特許情報シンポジウム」での講演とほぼ同じ内容でしたが、「生成AIの活用」というスライド1枚が付け加わっていました。生成AIによる自然文の理解支援として、特許審査における、審査対象の発明の理解、調査対象の文献の理解、外国庁での審査経過の理解などに有用であり、特に外国語で書かれた審査経過を要約させて分散した情報の集約、整理に活用していることが話されました。また、タスクごとに理解支援への活用を検討していて、より審査に有用な要約のさせ方、例えば、技術の概要把握に適した要約とか特定の技術観点に注目した要約など、判断材料の収集、整理に活用できる可能性を、現在進行形で研究中であることが話されました。
これらの知見が特許庁内だけでなく民間にも早く開放されることを期待しています。
 
 
 
 
●共通テーマ「特許の審査、サーチにおけるAIの活用」
◆講演
 「特許の審査とサーチにおけるAIの活用」
五十嵐康弘氏(特許庁 審査第一部 調整課審査企画室 企画調査官)
 「特許審査及び検索における AI の応用」
彭学龍氏(中南財経政法大学 知識産権研究センター 主任・教授)
 「IP 行政における AI: KIPO の経験」
Lee Chang Kyo氏(韓国特許庁 産業財産情報システム課)
●テーマ1:「大規模言語モデル技術の審査メカニズムへの挑戦」
 AI 生成内容の「現有技術」属性審査
崔国斌氏(清華大学法学院 教授)
 討論文:人工知能生成物に対する「従来技術」属性の審査
Kim, Kwan-Shik氏(韓南大学 法学部 教授)
大規模言語モデル技術の審査メカニズムへの挑戦
~大規模言語モデル技術をどの様に特許審査に活用していくか~
 河野英仁氏(河野特許事務所 所長・弁理士)
<モデレータ>
 上野剛史氏(一般社団法人日本知的財産協会 専務理事)
●テーマ2: 「標準必須特許とライセンス」
●テーマ3: 「女性活躍とイノベーション」
 
日中韓連携知的財産シンポジウム2024
https://www.ipaj.org/symposium/2024/jck_symposium_2024.html
 
特許庁におけるAIの活用
9/11/2024
https://yorozuipsc.com/blog/ai3916471
 
 
 
 
Utilization of AI in Patent Examination and Search
 
Since 2012, the Intellectual Property Association of Japan, the Korean Intellectual Property Society, and the China Intellectual Property Research Association have held an annual symposium on a rotating basis among the three countries. This year, in collaboration with the Japan Patent Office and the Japan Patent Attorneys Association, the event was held as the Japan-China-Korea Collaborative Intellectual Property Symposium 2024 at the Ito Hall, University of Tokyo, on December 19.
Two of the four themes focused on AI: “Utilization of AI in Patent Examination and Search” and “Challenges of Large Language Model Technology in Examination Mechanisms.” The differences in approaches among Japan, China, and Korea provided valuable insights.
The Japan Patent Office's lecture, “Utilization of AI in Patent Examination and Search,” delivered at the 8th Patent Information Symposium on November 7, 2024, had content largely similar to a previous lecture. However, a single additional slide on the “Utilization of Generative AI” was included.
It was discussed that generative AI is useful for supporting the comprehension of natural language, specifically in patent examination. This includes understanding the invention under examination, understanding the documents being searched, and understanding examination procedures at foreign patent offices. In particular, it is being used to summarize examination procedures written in foreign languages, consolidating and organizing dispersed information.
Additionally, the lecture mentioned ongoing research into applying generative AI for comprehension support on a task-by-task basis. This involves exploring more effective ways of generating summaries that are useful for examination, such as summaries tailored to understanding a technology's overview or summaries that focus on specific technical perspectives. The goal is to collect and organize information for decision-making more effectively.
There is hope that these insights will soon be made available not only within the Patent Office but also to the private sector.
Your browser does not support viewing this document. Click here to download the document.
0 Comments

旭化成の2024年「無形資産戦略説明会」

19/12/2024

0 Comments

 
12月13日に行われた旭化成の2024年「無形資産戦略説明会」のアーカイブ動画が公開されました。
説明会では、旭化成がソリューション型事業やライセンス型事業など「無形資産が価値の中心となるビジネスモデル」を強化し、企業価値向上に向けて取り組んでいる実績や今後の方向がトップ自らの言葉で説明されていました。
工藤社長は中期経営計画2024の進捗状況と、無形資産活用の重要性について説明。久世副社長は具体的な事業事例を通じて無形資産の活用状況を解説。西川執行役員は人材戦略の観点から無形資産の強化について説明しました。
「無形資産が価値の中心となるビジネスモデル」として、自動車内装材事業、イオン交換膜事業、クリティカルケア事業、海外住宅事業における無形資産の活用事例が紹介され、各事業でのROIC(投資収益率)が9%以上を達成していることが報告されました。
また、新しいビジネスモデルとしてTBC(テクノロジーバリュービジネスクリエーション)の展開について説明があり、2030年近傍で100-200億円の利益規模を目指すことが示されました。
旭化成は、知財戦略、DX戦略などのテーマで説明会を行ってきましたが、無形資産をまとめた形で説明会を行ったのは画期的と言えるのではないかと思います。
 
2024年「無形資産戦略説明会」を開催
https://www.asahi-kasei.com/jp/news/2024/ze241217.html
 
無形資産戦略説明会 資料
無形資産が価値の中心となるビジネスモデルの強化
https://www.asahi-kasei.com/jp/ir/library/business/pdf/241213.pdf
動画
https://www.irwebmeeting.com/asahi-kasei/vod/20241213/N5mfAvYd/meeting_01_ja/index.html
 
旭化成の久世副社長、生成AI全社展開で「3領域またぎ無形資産活用」
https://xtech.nikkei.com/atcl/nxt/column/18/00001/10072/
 
生成AIを新規用途探索の自動化や製造現場の技術伝承において活用開始
無形資産の活用を加速し、競争力強化を目指す
2024年12月9日 旭化成株式会社
https://www.asahi-kasei.com/jp/news/2024/ze241209.html
 
旭化成の素材/化学の無形資産戦略、技術やノウハウのマネタイズ手法とは?
https://monoist.itmedia.co.jp/mn/articles/2412/16/news078.html
 
 
 
Asahi Kasei's 2024 "Intangible Asset Strategy Briefing"
 
The archived video of Asahi Kasei's 2024 Intangible Asset Strategy Briefing held on December 13 has been made available.
During the briefing, top executives explained Asahi Kasei’s efforts and achievements in enhancing “business models where intangible assets are at the core of value,” such as solution-based and license-based businesses, as part of their initiatives to increase corporate value.
President Kudo presented the progress of the Mid-Term Management Plan 2024 and emphasized the importance of leveraging intangible assets. Vice President Kuze provided specific examples of how intangible assets are being utilized in various business operations. Executive Officer Nishikawa discussed the reinforcement of intangible assets from the perspective of human resource strategy.
Examples of intangible asset utilization were introduced within business models centered on intangible assets, such as the automotive interior materials business, ion-exchange membrane business, critical care business, and overseas housing business. It was reported that these businesses achieved a Return on Invested Capital (ROIC) of over 9%.
Additionally, a new business model, Technology Value Business Creation (TBC), was discussed, with a goal of achieving a profit scale of 10-20 billion yen by around 2030.
While Asahi Kasei has previously held briefings on themes such as intellectual property strategy and DX strategy, this briefing, which comprehensively covered intangible assets, can be seen as groundbreaking.

Your browser does not support viewing this document. Click here to download the document.
0 Comments

IPランドスケープ:知財情報をビジネスに役立てる

18/12/2024

0 Comments

 
YouTubeのINPIT Channelで、2024年10月30日、31日に開催された、IPランドスケープをご紹介するセミナーのアーカイブ動画が公開されました。①IPランドスケープ概論、②パネルディスカッション、③IPランドスケープ支援事業のご紹介、を視聴しました。
知財情報をビジネスに役立てるということの重要性がしっかり伝わる「IPランドスケープ概論」、「パネルディスカッション」でした。
 
【IPランドスケープ概論】中小企業等におすすめ!知財情報を経営判断に活かすIPランドスケープのご紹介(約28分)
https://www.youtube.com/watch?v=9iOI0np19zY
 
【パネルディスカッション】中小企業等におすすめ!知財情報を経営判断に活かすIPランドスケープのご紹介(約30分)
https://www.youtube.com/watch?v=dS2Yh3RO918
 
【IPランドスケープ支援事業のご紹介】中小企業等におすすめ!知財情報を経営判断に活かすIPランドスケープのご紹介(約9分半)
https://www.youtube.com/watch?v=6adISz6FT2A
 
 
IP Landscape: Leveraging Intellectual Property Information for Business
The archived video of a seminar introducing IP landscape, held on October 30th and 31st, 2024, on the INPIT Channel on YouTube, has been released. I watched the following segments: (1) Overview of IP Landscape, (2) Panel Discussion, and (3) Introduction to the IP Landscape Support Program.
The "Overview of IP Landscape" and the "Panel Discussion" effectively conveyed the importance of leveraging intellectual property information for business.
 

Your browser does not support viewing this document. Click here to download the document.
Your browser does not support viewing this document. Click here to download the document.
0 Comments

生成AIを使い特許調査の効率と精度を上げる

17/12/2024

0 Comments

 
生成AI(OpenAI o1)に、『生成AIを使い特許調査の効率と精度を上げる』というタイトルで、企業知財担当者向けの新書を書かせてみました。プロンプトは、「『生成AIを使い特許調査の効率と精度を上げる』というタイトルで特許調査の初心者向けの新書を10万字で書いてください。」という簡単なものです。
出来上がりは、それぞれの方が判断していただければと思います。
 
【本書タイトル】
生成AIを使い特許調査の効率と精度を上げる
――初心者のための実践的新書
【目次】
はじめに
序章:特許調査と生成AIの出会い
第1章:特許調査の基礎理解
第2章:特許公報とデータベースの基礎
第3章:生成AIとは何か
第4章:生成AIを用いた特許文献解析の基礎
第5章:特許分類とクレーム解析への生成AI活用
第6章:既存キーワード検索と生成AI活用の統合
第7章:類似特許検索と生成AIによる概念展開
第8章:競合他社調査と生成AIによる俯瞰分析
第9章:生成AIツール導入時のポイントと留意点
第10章:ケーススタディ:実際の特許課題への応用
第11章:今後の展望と課題
終章:生成AIを活用した新時代の特許調査
付録:参考文献・関連ツール一覧
 
 
 
Using Generative AI to Improve the Efficiency and Accuracy of Patent Searches
—A Practical Introductory Guide for Beginners--

 
I tried having a generative AI (OpenAI o1) write a new introductory book aimed at corporate intellectual property staff, titled "Using Generative AI to Improve the Efficiency and Accuracy of Patent Searches." The prompt was as simple as: "Please write an introductory book for beginners, titled 'Using Generative AI to Improve the Efficiency and Accuracy of Patent Searches,' in 100,000 characters."
As for the final result, I’ll leave it to each of you to judge.
 
Title of this Book
Using Generative AI to Improve the Efficiency and Accuracy of Patent Searches
—A Practical Introductory Guide for Beginners--
Table of Contents
Introduction
Prologue: The Encounter Between Patent Searches and Generative AI
Chapter 1: Fundamentals of Patent Searches
Chapter 2: Basics of Patent Publications and Databases
Chapter 3: What Is Generative AI?
Chapter 4: Fundamentals of Patent Document Analysis Using Generative AI
Chapter 5: Utilizing Generative AI for Patent Classification and Claim Analysis
Chapter 6: Integrating Existing Keyword Searches with Generative AI
Chapter 7: Similar Patent Searches and Concept Expansion Through Generative AI
Chapter 8: Competitive Intelligence and Panoramic Analyses Enabled by Generative AI
Chapter 9: Key Points and Considerations for Implementing Generative AI Tools
Chapter 10: Case Studies: Applying Generative AI to Actual Patent Issues
Chapter 11: Future Outlook and Challenges
Epilogue: A New Era of Patent Searches Powered by Generative AI
Appendix: List of References and Related Tools
 

Your browser does not support viewing this document. Click here to download the document.
0 Comments

『生成AIの知財業務への活用』―企業知財担当者のための戦略的新基盤

16/12/2024

0 Comments

 
生成AI(OpenAI o1)に、『生成AIの知財業務への活用』というタイトルで、企業知財担当者向けの新書を書かせてみました。プロンプトは、「『生成AIの知財業務への活用』というタイトルで企業知財担当者向けの新書を10万字で書いてください。」という簡単なものです。
出来上がりは、それぞれの方が判断していただければと思います。
 
【全体構成】
  • 序章:生成AI時代と知財部門の新たな挑戦
  • 第1章:生成AIとは何か
    • 1-1:生成AIの基本原理
    • 1-2:自然言語処理・画像生成技術の基礎
    • 1-3:近年の爆発的進歩とその要因
    • 1-4:知財分野への潜在的インパクト
  • 第2章:生成AIと特許実務
    • 2-1:アイデア創出支援としての生成AI
    • 2-2:先行技術調査の効率化
    • 2-3:特許明細書作成支援ツールとしての活用
    • 2-4:審査過程・拒絶理由通知への対応自動化
  • 第3章:生成AIと商標・意匠
    • 3-1:ネーミング支援・ブランド構築への応用
    • 3-2:類似商標・類似意匠の自動検出
    • 3-3:画像生成AIによるロゴ・パッケージデザイン案出
  • 第4章:著作権と生成AI
    • 4-1:生成AIが生み出す成果物の著作権問題
    • 4-2:学習用データセットの使用に関する法的課題
    • 4-3:契約スキーム構築とリスクヘッジ
  • 第5章:企業経営戦略と生成AI活用
    • 5-1:知財戦略全体像への組込み方策
    • 5-2:異業種連携・オープンイノベーション促進
    • 5-3:社内教育・ガバナンス体制構築
  • 第6章:海外法制度・グローバル展開への視点
    • 6-1:米国・欧州・中国における法制動向
    • 6-2:WIPOなど国際機関のスタンスと標準化動向
    • 6-3:グローバル知財戦略と生成AI
  • 第7章:倫理・社会的責任と知財実務者の将来像
    • 7-1:公正競争・公平性・透明性の確保
    • 7-2:ジェネレーティブAIによる社会的インパクトと責任
    • 7-3:知財担当者のキャリアモデルとスキルセット
  • 終章:生成AIを活かした知財イノベーションの可能性
 
 
 
“Utilizing Generative AI in Intellectual Property Operations" — A New Strategic Foundation for Corporate IP Professionals
 
I attempted to have Generative AI (OpenAI o1) write a new book for corporate IP professionals, titled "Utilizing Generative AI in Intellectual Property Operations," by using a simple prompt: "Please write a new book for corporate IP professionals, titled 'Utilizing Generative AI in Intellectual Property Operations,' with a length of 100,000 characters."
Each individual may judge the quality of the final product for themselves.
 
Overall Structure
  • Introduction: The Era of Generative AI and New Challenges for IP Departments
  • Chapter 1: What is Generative AI?
    • 1-1: The Basic Principles of Generative AI
    • 1-2: Fundamentals of Natural Language Processing and Image Generation Technologies
    • 1-3: The Recent Explosive Progress and Its Underlying Factors
    • 1-4: Potential Impact on the Intellectual Property Field
  • Chapter 2: Generative AI and Patent Practice
    • 2-1: Generative AI as an Ideation Support Tool
    • 2-2: Increasing Efficiency in Prior Art Searches
    • 2-3: Utilizing Generative AI as a Patent Specification Drafting Support Tool
    • 2-4: Automating Responses to Examination Procedures and Office Actions
  • Chapter 3: Generative AI and Trademarks/Designs
    • 3-1: Applications in Naming Support and Brand Building
    • 3-2: Automatic Detection of Similar Trademarks and Designs
    • 3-3: Proposing Logo and Package Design Concepts via Image-Generating AI
  • Chapter 4: Copyright and Generative AI
    • 4-1: Copyright Issues Surrounding Outputs Produced by Generative AI
    • 4-2: Legal Challenges in Utilizing Training Datasets
    • 4-3: Structuring Contractual Schemes and Risk Mitigation
  • Chapter 5: Corporate Management Strategy and the Use of Generative AI
    • 5-1: Strategies for Integrating AI into the Overall IP Framework
    • 5-2: Encouraging Cross-Industry Collaboration and Open Innovation
    • 5-3: Internal Training and Governance Framework Development
  • Chapter 6: Perspectives on Foreign Legal Systems and Global Expansion
    • 6-1: Legislative Trends in the US, Europe, and China
    • 6-2: Positions of International Organizations like WIPO and Standardization Trends
    • 6-3: Global IP Strategies and Generative AI
  • Chapter 7: Ethics, Social Responsibility, and the Future Role of IP Professionals
    • 7-1: Ensuring Fair Competition, Fairness, and Transparency
    • 7-2: The Social Impact and Responsibilities of Generative AI
    • 7-3: Career Models and Skill Sets for IP Professionals
  • Conclusion: The Potential for IP Innovation Harnessing Generative AI
 
Your browser does not support viewing this document. Click here to download the document.
0 Comments

OpenAI o1のIQは133?

15/12/2024

0 Comments

 
本年9月に登場したOpenAIの「OpenAI o1-preview」が、12月5日にアップデートされ正式版「OpenAI o1」になり「OpenAI o1 Pro」も加わりました。
TRACKING AIによれば、ノルウェーMensa IQテストにおいて、正式版「Open o1」のIQは133で、「OpenAI o1-preview」(120)より13ポイント上昇したということです。ただ、高性能なはずの「OpenAI o1 Pro」は118となっていて、正式版「Open o1」より低いということで、よくわかりません。
別の評価「オフラインテスト」では、「OpenAI o1 Pro」が110、「OpenAI o1-preview」が97、正式版「Open o1」が90と全体的に低くなっています。
ちょっと古いですが、今年の9月に公表されているARC-AGI(Abstraction and Reasoning Corpus for Artificial General Intelligence)における各AIモデルのスコアは以下の通りとなっています。
  • OpenAI o1-preview: 21.2%(公的評価)
  • Claude 3.5 Sonnet: 21%(公的評価)
  • OpenAI o1-mini: 12.8%(公的評価)
  • GPT-4o: 9%(公的評価)
  • Gemini 1.5: 8%(公的評価)
IQテストの結果は、テスト方法やデータの影響により大きく変動するため、複数の評価基準でAIの能力を判断することが重要だと思いますが、評価軸が複数あり、低いスコアにとどまっている指標があるので、まだまだ性能向上による進化が続くと思われます。
 
 
TRACKING AI
Monitoring Bias in Artificial Intelligence Chatbots
https://trackingai.org/IQ
 
OpenAI o1 Results on ARC-AGI-Pub
https://arcprize.org/blog/openai-o1-results-arc-prize
 
 
Is Open o1's IQ 133?
OpenAI's "OpenAI o1-preview," which was introduced this September, was updated on December 5 to become the official "OpenAI o1," and "OpenAI o1 Pro" was also added.
According to TRACKING AI, the official version "Open o1" scored an IQ of 133 on the Norwegian Mensa IQ test, marking a 13-point increase from "OpenAI o1-preview" (120). However, the supposedly higher-performing "OpenAI o1 Pro" scored 118, which is lower than the official "Open o1," making this somewhat confusing.
In another evaluation, the "Offline Test," "OpenAI o1 Pro" scored 110, "OpenAI o1-preview" scored 97, and the official "Open o1" scored 90, showing overall lower scores.
Although a bit dated, the scores for various AI models in the ARC-AGI (Abstraction and Reasoning Corpus for Artificial General Intelligence) released this September are as follows:
  • OpenAI o1-preview: 21.2% (official evaluation)
  • Claude 3.5 Sonnet: 21% (official evaluation)
  • OpenAI o1-mini: 12.8% (official evaluation)
  • GPT-4o: 9% (official evaluation)
  • Gemini 1.5: 8% (official evaluation)
Since IQ test results can vary significantly depending on the test methods and data, it is important to assess AI capabilities using multiple evaluation criteria. Given the presence of multiple evaluation axes and some indicators showing low scores, it seems that further performance improvements and evolution are still underway.
 

Your browser does not support viewing this document. Click here to download the document.
0 Comments

カシオ、不正競争訴訟で中国企業に勝訴

15/12/2024

0 Comments

 
カシオ計算機は12月12日、G-SHOCKの類似品を作った中国の企業2社に対し、不正競争を争う裁判で勝訴したと発表しました。広東省最高裁判所は、中国企業2社の行為が不正競争行為に当たるとして、損害賠償金300万元(約6500万円、1元21円で換算)の支払いを中国の企業に命じたということです。
中国で、意匠権が切れた商品デザインに関して不正競争防止法の保護が裁判で認められたのは珍しいようで、今後の模倣品対策に活かされることになりそうです。
 
2024年12月12日
中国における不正競争訴訟の勝訴について
https://www.casio.co.jp/release/2024/1212-ga110/
 
カシオ、G-SHOCK“類似品”裁判で中国企業に勝訴 意匠権切れでも「影響力を持つ商品の装飾」と判断
2024年12月12日
https://www.itmedia.co.jp/news/articles/2412/12/news145.html
 
カシオ-9日続伸 中国における不正競争訴訟で勝訴
12/12
https://finance.yahoo.co.jp/news/detail/0f3f1596ae4cd36955d07dd9bbdbcaaf18c28c6b
 
 
Casio Wins Unfair Competition Lawsuit Against Chinese Companies
 
On December 12, Casio Computer Co., Ltd. announced that it had won an unfair competition lawsuit against two Chinese companies that produced imitation G-SHOCK products. The Guangdong High Court ruled that the actions of these two Chinese companies constituted unfair competition and ordered them to pay damages of 3 million yuan (approximately 65 million yen, based on an exchange rate of 21 yen per yuan).
It is rare for a court in China to recognize protection under the Anti-Unfair Competition Law for product designs whose design rights have expired. This ruling is expected to strengthen future measures against counterfeit products.

0 Comments

第50回特許制度小委員会議事録

14/12/2024

0 Comments

 
11月6日に行われた「産業構造審議会知的財産分科会 第 50 回特許制度小委員会」の議事録が公開されました。「特許制度等に関する検討課題について」と題する特許庁の報告に対して活発な質疑が行われた様子がわかります。
 
 
産業構造審議会知的財産分科会 第 50 回特許制度小委員会(令和6年11月6日) 議事録
https://www.jpo.go.jp/resources/shingikai/sangyo-kouzou/shousai/tokkyo_shoi/document/index/newtokkyo_050.pdf
 
資料1 特許制度等に関する検討課題について
産業構造審議会知的財産分科会 第50回特許制度小委員会
https://www.jpo.go.jp/resources/shingikai/sangyo-kouzou/shousai/tokkyo_shoi/document/50-shiryou/03.pdf
 
 
 
Minutes of the 50th Meeting of the Subcommittee on the Patent System
 
The minutes of the 50th Meeting of the Subcommittee on the Patent System, held on November 6th, have been made public. You can see that there was a lively exchange of questions and answers in response to the JPO's report, entitled “Issues for Consideration Regarding the Patent System, etc.”.
Your browser does not support viewing this document. Click here to download the document.
0 Comments

「知的財産推進計画2025」に向けた検討

14/12/2024

0 Comments

 
Paragraph. 編集するにはここをクリック.​12月13日 「知的財産推進計画2025」に向けた検討
 
12月12日第2回構想委員会が開かれ、「知的財産推進計画2025」に向けた検討が進められています。
​「知的財産推進計画2025」の策定に向けた意見募集の受付締切日が2024年12月20日に迫っています。とりまとめをされている方々ご苦労様です。
 
 
第2回構想委員会 配付資料
資料1  :       第1回構想員会での御指摘事項
資料2  :       IPトランスフォーメーション
資料3  :       AI時代の知的財産権検討会「中間とりまとめ」-権利者のための手引き-
資料4  :       DX時代にふさわしい産業財産権制度について
資料5  :       特許庁における大学・スタートアップ支援策について
資料6  :       我が国における外国人材呼び込み施策について
資料7  :       グローバル・スタートアップ・キャンパス構想
資料8  :       日本経済団体連合会提言「Entertainment Contents ∞ 2024」概要
資料9  :       日本経済団体連合会提言「Entertainment Contents ∞ 2024」
資料10 :       村松委員提出資料
 
 
第2回構想委員会 議事次第
https://www.kantei.go.jp/jp/singi/titeki2/tyousakai/kousou/2025/dai2/gijisidai.html
 
「知的財産推進計画2025」の策定に向けた意見募集
https://public-comment.e-gov.go.jp/servlet/Public?CLASSNAME=PCMMSTDETAIL&id=095240660&Mode=0
受付締切日時      2024年12月20日23時59分
 
Consideration of the "Intellectual Property Strategic Program 2025
 
The second meeting of the Planning Committee was held on December 12, and consideration of the Intellectual Property Strategic Program 2025 is progressing.
The deadline for receiving comments on the formulation of the IP Strategic Program 2025 is approaching on December 20, 2024. Thank you to everyone involved in this process.
Your browser does not support viewing this document. Click here to download the document.
Your browser does not support viewing this document. Click here to download the document.
0 Comments

旭化成の生成AI活用

13/12/2024

0 Comments

 
旭化成は、材料の新規用途探索や製造現場の技術伝承において生成AIの活用を開始したことをプレスリリースしました。過去のデータやノウハウなど、これまで蓄積された無形資産の活用を生成AIによってさらに加速し、競争力強化や事業上のリスク低減を目指すとしています。
これまでに得られた成果としては、下記が挙げられています。
「すでに膨大な文献データから6,000以上の用途候補を考案したほか、ある材料では候補の選別にかかる時間を従来の約40%に短縮することができました。」
「従来は個人の経験をもとにリスクを予知していましたが、過去事例のデータを読み込ませた生成AIを活用することで、経験の浅い従業員でも抜け漏れなくリスクと対応策を洗い出し、安全性と効率性を高めるとともに、技術伝承を加速できるようになりました。」
「書類作成や社内資料検索などに生成AIを活用し、業務全体として2,157時間/月の時間短縮」
「書類監査対応において、ニーズに合わせた生成AI開発によりプロセスを効率化し、年間1,820時間の時間短縮」
 
 
 
生成AIを新規用途探索の自動化や製造現場の技術伝承において活用開始
無形資産の活用を加速し、競争力強化を目指す
2024年12月9日 旭化成株式会社
https://www.asahi-kasei.com/jp/news/2024/ze241209.html
 
生成AIを新規用途探索の自動化や製造現場の技術伝承で活用開始
旭化成は、材料の新規用途探索や製造現場の技術伝承で生成AI(人工知能)の活用を開始した。
2024年12月10日
https://monoist.itmedia.co.jp/mn/articles/2412/10/news074.html
 
旭化成、生成AIの活用状況を発表--競争力強化とリスク低減へ
NO BUDGET 2024-12-10
https://japan.zdnet.com/article/35227126/
 
 
 
Asahi Kasei's Use of Generative AI
 
Asahi Kasei announced in a press release that it has begun utilizing generative AI in exploring new applications for materials and passing down technical knowledge at manufacturing sites. By further accelerating the use of accumulated intangible assets, such as past data and expertise, through generative AI, the company aims to strengthen competitiveness and reduce business risks.
The achievements reported so far include the following:
  • "From a vast amount of literature data, we have already generated over 6,000 potential applications. Additionally, for certain materials, we have reduced the time needed for candidate selection by approximately 40% compared to conventional methods."
  • "Previously, risk prediction relied on individual experience. However, by leveraging generative AI trained on past case data, even less-experienced employees can comprehensively identify risks and countermeasures, thereby enhancing safety, efficiency, and accelerating knowledge transfer."
  • "By using generative AI for tasks such as document preparation and internal data searches, we have achieved a total time reduction of 2,157 hours per month across operations."
  • "In document audit responses, the development of generative AI tailored to specific needs has streamlined processes, reducing time by 1,820 hours annually."
0 Comments

NGB「生成AIを活用して特許公報を読む」第2弾

13/12/2024

0 Comments

 
12月12日に公開された、NGB知財チャンネルの生成AI×特許調査シリーズ:「生成AIを活用して特許公報を読む」第2弾(約22分)では、公報の読み込みに生成AIを活用することを検討しています。
本動画では、生成AIに公報のテキスト情報を貼り付ける手法を検討しています。内容的には、もう少し工夫して使ってよという感じがありますが、初心者向けには、わかりやすいと思います。
 
 
生成AI×特許調査 第2弾(前編)
https://www.youtube.com/watch?v=PPtViR7D2PI&t=21s
 
 
 
NGB “Reading Patent Gazettes Using Generative AI” Part 2
 
The second installment (approx. 22 min.) of the Generative AI x Patent Search series on the NGB Intellectual Property Channel on YouTube, which was released on December 12, examines the use of generative AI to read patent gazettes.
In this video, NGB examines a method for pasting the text information of patent gazettes into generative AI. The content is a little more complicated than it could be, but it's easy to understand for beginners.
Your browser does not support viewing this document. Click here to download the document.
0 Comments

知財実務オンライン:進歩性の重要論点

12/12/2024

0 Comments

 
12月11日に行われたYouTube第219回知財実務オンライン:「進歩性の重要論点を書籍原稿から先出し解説 ~上位概念化、阻害要因など~」のアーカイブ動画を視聴しました。
来年発刊予定の書籍原稿から進歩性の重要論点を先出し解説ということで、今回は、上位概念化を田中弁理士が、阻害要因を谷弁理士が、それぞれ解説し、質疑応答が行われました。
書籍の完成が楽しみです。
 
【第219回】知財実務オンライン
「進歩性の重要論点を書籍原稿から先出し解説 ~上位概念化、阻害要因など~」
https://www.youtube.com/watch?v=kxmLC6eyAfw
■ゲスト
IPTech弁理士法人 代表弁理士/公認会計士 安高 史朗
弁理士 田中 研二
プロフィック特許事務所 代表弁理士 谷 和紘
■ 運営
日本橋知的財産総合事務所  代表弁理士   加島 広基
弁理士法人IPX         代表弁理士CEO 押谷 昌宗
 
 
IP Practice Online: Important Issues of Inventive Step
 
The archived video of the 219th IP Practice Online: “Explanation of Important Issues of Inventive Step from Book Manuscripts - Superior Conceptualization, Inhibitory Factors, etc.” held on YouTube on December 11, 2024 was viewed.
In the video, Patent Attorney Tanaka and Patent Attorney Tani explained about the higher conceptualization and the inhibiting factors, respectively, and had a Q&A session.
I look forward to the completion of the book.
Your browser does not support viewing this document. Click here to download the document.
0 Comments

特許の現存率の推移と特許出願件数動向

11/12/2024

0 Comments

 
産業構造審議会知的財産分科会第9回財政点検小委員会(2024年11月22日)の議事録が公開されました。
配布資料1「特許特別会計の財政運営状況等」の8頁(特許の現存率の推移)、12頁(特許出願件数動向)が気になっていたのですが、下記のような説明と質疑があったことで、よく理解できました。
特許の現存率の推移については、詳細な検討結果を待たなければいけませんが、議論されている要因だけではないような気がしています。
特許出願動向で、今年の7,8月に大きく増えているのが、特定のAI関連の企業からの出願によるものという説明で納得しました。
 
産業構造審議会知的財産分科会第9回財政点検小委員会(2024年11月22日)の議事録
https://www.jpo.go.jp/resources/shingikai/sangyo-kouzou/shousai/zaiseitenken_shoi/document/index/09_gijiroku.pdf
 
【資料1】特許特別会計の財政運営状況等
https://www.jpo.go.jp/resources/shingikai/sangyo-kouzou/shousai/zaiseitenken_shoi/document/09-shiryou/siryo01.pdf
 
 
○田岡総務課長の説明
8ページをお願いいたします。令和5年度における歳入増(現存率の上昇)についてです。令和5年度の歳入増の要因として、先ほどお示しした反動減の影響はほとんど生じていないという点のほかに、近年、設定登録から10年から13年経過した特許の権利の現存率、これは特許権の登録件数に対する現存件数の割合を示しますけれども、ここ数年で3%から8%程度上昇したことが挙げられます。10年目から13年目にかけての現存率が高いということは、10年から13年前に生まれた権利が長く使われているということでありまして、その要因は正確には把握が難しいのですけれども、1つ考えられるのは、従来より真に質の高い権利が多数生まれた可能性があるというものです。
10年から13年前には特許査定率が向上しております。これは審査請求期間の短縮化、審査請求料の引上げの施策を行ったことにより、出願人が真に権利化すべきものを適正に審査請求するようになったことによるものと考えられます。特許権の維持に必要な特許料収入は、歳入の約46%を占めておりまして、引き続き現存率の推移については注視してまいりたいと思っております。・・・
12ページをお願いいたします。まず特許の出願件数動向についてです。棒グラフが月ごとの件数、折れ線グラフが月ごとの年度の累計件数の推移となります。青が2022年度、黄色が2023年度、緑が2024年度、今年度分でございます。今年度の上半期は、昨年9月に引き続きまして、7月、8月に特定の企業の大量出願がございました。それもありまして、年度の累計件数が前年度同期比でプラス0.6%と横ばいになっております。前年度から大きな変更はございません。
 
 
○亀坂委員  とても丁寧に説明していただいて、ありがとうございます。ずっと私たち委員は、もっとこれを開示してくださいとか、もっと詳しくこれも出してくださいといろいろな注文を、とてもハードルが高い注文を出し続けてきたのですけれども、コメントをさせていただいたことをどんどん追加で情報提供してくださって、できる限りの分析をしてくださって、本当にありがとうございます。
まず、資料の中で気になったところをスライドのページ順にコメントさせていただきたいのですけれども、まず確認に近いことになってしまうと思うのですが、スライドの12ページのグラフが気になりました。このグラフを見ると、2023年度は黄色というかオレンジのような色で9月が突出していて、2024年度の黄緑色の棒グラフも7月、8月がやや突出しているように見えるのですけれども、これは特定企業の特許出願による一時的な棒グラフの変化であって、特許庁全体の歳出入にはほとんど影響がないものと考えて良いのかというのが1点目の質問です。
○小林委員長  では、まず1点目の質問について、事務局お願いします。
○田岡総務課長  御指摘のとおり、昨年の9月と今年の7月、8月には特定企業からの大量出願が1万件とかそういう単位で出てきたわけでございますが、特許の出願料は14,000円でございますので、歳入へのインパクトはそれをかけ算した程度だと思います。
 
 
○滝澤委員  ありがとうございます。御説明ありがとうございました。
私からは2点お伺いしたいことといいますか、コメントに近いものかもしれませんけれ   ども、8ページ目の特許の現存率の推移の図、非常に興味深いと思って拝見しておりました。この図をどのように見るかですけれども、例えば2020年と2023年の11年目辺りですと、現存率10%ぐらい差が出ていて、かなり大きいという印象があるのですが、これは2020年の11年前というと、リーマンショックの直後辺りなので、例えば2020年の青い線の方がユニークな集団なのか、それとも今回の歳入増の要因として指摘されていますが、2023年の赤い線の方がユニークなのかというのが少し読みにくいのかなというのを拝見していました。2019年以前の状態が分かれば判断しやすいところもあるかと思うのですが、どちらがユニークなのかということを図を見ていてちょっと思いました。
以上、感想です。
もう一点は、従前お伺いしておけばよかったのですけれども、12ページ目の特許の出願件数の動向でして、特定企業の大量出願を除くとおおむね前年同様というような話でしたが、この出願主体についてはどうだったのかということ。例えば、長官もおっしゃいましたけれども、スタートアップとか大学とか、そういったところのイノベーションを期待したいというようなこともありましたが、この出願されている主体がどうなっているのかをもし御存じでしたら、御教示いただければと思います。
以上です。
○小林委員長  では、事務局、お願いいたします。
○田岡総務課長  まず先に後ろの方の、2問目の御質問の特許出願件数での特定企業、これは会社名は伏せさせていただきますけれども、AI関連の企業からの出願でございます。かなり大きな企業の大量出願があったということでございます。
1つ目の8ページの現存率の上昇の分析につきましては、私どもも今回、新しく試みをしたものもございますので、さらにそれを遡ってのトレンドがどうであったかというところは、改めて私ども追ってみたいと思っております。
以上でございます。
 
○滝澤委員  2点目なのですけれども、その特定企業のところを除いた出願の動向のこと
をお伺いしていて、内訳はあまり変わっていないかどうかというところです。大学が増えたとか、スタートアップが増えたとか。
○小林委員長  事務局から回答をお願いいたします。
○中野調整課長  私からお答えします。おっしゃる点に関しましては、それほど大きなトレンドの変化はございません。ただ、業界別に見ますと、ソフトウエア関連が少し増えたり、機械関連が少し減ったり、そういうところは中にはございますけれども、大きなトレンドの変化はございません。
 
 
○戸田オブザーバー 日本知的財産協会の戸田です。オブザーバー参加で僭越ですけれども、発言させていただきます。
当初から特許特別会計の剰余金の推移ですとか、料金値上げを含む各種施策に関わってきた者として、現在、V字回復基調にある状況を大変うれしく思っています。特許庁長官をはじめ、関係者の皆様の御尽力に深く敬意を表したいと思います。
幾つかコメントを申し上げます。
1つ目ですが、私も8ページ目の特許設定登録後10年から13年が経過した現存率が上昇しているというところに注目しています。
先ほど滝澤委員からもご指摘がございましたけれども、このような現象が、どのような分野で、どんな権利者に起因するものなのか。分解能を高めて調査・分析してみる必要があるのではないかと思っています。あくまでも私見ですけれども、10年以上前に出願したというものの特許の現存率が高まるということは、特許ポートフォリオの新陳代謝がうまく機能していないという可能性もあるのではないかと思っています。
近年、よく言われていますけれども、発明が小粒化して、改良型のものが増えており、過去の基本的な発明の価値が相対的に高まったが故に、過去の特許の権利を維持しているのではないかという仮説も成り立つと思われます。
このような状況が進むとすれば、研究開発や発明の現場に対して警鐘を鳴らすとか、先ほど小野長官からもお話がございましたけれども、もっとチャレンジングな研究テーマやイノベーションの創出に取り組むべき、との発信を行うことも重要になってくるかもしれません。
 
 
○山内委員  明治大学の山内です。オンラインで失礼します。
途中、大学の用事の方で中座してしまいまして、資料1の方に話が戻ってしまうのですけれども、2点、全体としてコメントさせていただきたいと思っております。
1つは、現存率の上昇のメカニズムの話でして、既に恐らく議論されたのかとも思うのですけれども、本来は、値上げをすれば現存率は下がるというのが自然な流れなわけですが、出願時点で既に厳選されたということであれば、今後、出願は微減で、現存率が上昇することで、財政にはかなりのプラスになると考えられますし、逆に、もし企業内の知財の予算の制約で厳選しているということであれば、企業の方で予算、財政の影響が一番大きな年金の支払いなわけですから、当然近々これを減らすという形で維持する特許も厳選していくということになりますので、そういう意味では、どちらが大きいのか。収支に対して、どういう影響があるのかというのは、引き続き検討が必要かと思っております。
先ほどちょっと途中で抜けてしまったのですけれども、審査請求料の値上げとか、そう   いったことで厳選が進んでいるのではないかみたいなお話をされていましたが、あとは審査請求期間が短くなったりもしていますので、そういう意味では、厳選する期間が短くなって、質の方にも影響があった可能性もありますし、査定率の上昇というのも出願が厳選した影響なのか、あるいは権利化すべきでないものがある程度交ざってきているのかとか、そういったものも含めて引き続き調査を進めていっていただければと思います。
 
○          小林委員長  ありがとうございます。現存率については、いろいろな御意見がありましたので、これからますますいろいろな観点から分析を進めていただくということをお願いしたいと思います。
 
 
Trends in Patent Survival Rates and Patent Application Numbers
 
The minutes of the 9th Fiscal Review Subcommittee of the Intellectual Property Committee of the Industrial Structure Council (held on November 22, 2024) have been released.
I was particularly interested in Page 8 of Document 1: Financial Management Status of the Special Patent Account (Trends in Patent Survival Rates) and Page 12 (Trends in Patent Application Numbers). The following explanations and Q&A helped me understand these topics better.
Regarding the trends in patent survival rates, we will need to await detailed examination results. However, I feel there might be factors beyond those currently discussed.
Concerning the trends in patent applications, I was convinced by the explanation that the significant increase in July and August this year was due to filings from specific AI-related companies.

Your browser does not support viewing this document. Click here to download the document.
0 Comments
<<Previous
Forward>>

    著者

    萬秀憲

    アーカイブ

    July 2025
    June 2025
    May 2025
    April 2025
    March 2025
    February 2025
    January 2025
    December 2024
    November 2024
    October 2024
    September 2024
    August 2024
    July 2024
    June 2024
    May 2024
    April 2024
    March 2024
    February 2024
    January 2024
    December 2023
    November 2023
    October 2023
    September 2023
    August 2023
    July 2023
    June 2023
    May 2023
    April 2023
    March 2023
    February 2023
    January 2023
    December 2022
    November 2022
    October 2022
    September 2022
    August 2022
    July 2022
    June 2022
    May 2022
    April 2022
    March 2022
    February 2022
    January 2022
    December 2021
    November 2021
    October 2021
    September 2021
    August 2021
    July 2021
    June 2021
    May 2021
    April 2021
    March 2021
    February 2021
    January 2021
    December 2020
    November 2020
    October 2020
    September 2020
    August 2020
    July 2020
    June 2020

    カテゴリー

    All

    RSS Feed

Copyright © よろず知財戦略コンサルティング All Rights Reserved.
サイトはWeeblyにより提供され、お名前.comにより管理されています
  • Home
  • Services
  • About
  • Contact
  • Blog
  • 知財活動のROICへの貢献
  • 生成AIを活用した知財戦略の策定方法
  • 生成AIとの「壁打ち」で、新たな発明を創出する方法