顯示具有 JP patent 標籤的文章。 顯示所有文章
顯示具有 JP patent 標籤的文章。 顯示所有文章

2025年3月7日 星期五

日本的AI發明趨勢

報告來自日本專利局「Recent Trends in AI-related Inventions」網頁:https://www.jpo.go.jp/e/system/patent/gaiyo/ai/ai_shutsugan_chosa.html,當中的報告連結:https://www.jpo.go.jp/e/system/patent/gaiyo/ai/document/ai_shutsugan_chosa/report.pdf

先定義何謂「AI-related inventions」,其中包含了(1)AI核心發明,以及(2)AI應用發明。

(1)AI核心發明
這類發明特徵在於數學與統計資訊處理技術,為AI發展的基礎科技,如知識型模型、模糊邏輯(fuzzy logic),以及機器學習技術(machine learning technology),如神經網路(neural networks)、深度學習(deep learning)、支援向量機器(support vector machine)、強化學習(reinforcement)等。

(2)AI應用發明
這類發明特徵在於數學或統計資訊處理技術的應用,如影像處理(image processing)、語音處理(speech processing)、自然語言處理(natural language processing)、設備控制(equipment  control)與機器人(robotics)、診斷(diagnosis)、偵測(detection)、預測(prediction)與最佳化系統(optimization system)等。


本篇揭露的統計數據是日本以及PCT進入日本的專利申請案。技術類別包括IPC的G06N與日本專利檢索系統的FI類別,搭配WIPO的AI技術趨勢報告(可參考前篇)中關於AI的關鍵字與專利說明書中摘要、問題解決等欄位進行檢索。

從1988年到2022年的AI相關發明申請案(專利早期公開為申請日起18個月,因此最近兩年內的數據不準)(下圖表中顯示AI申請案逐年上漲,這幾年突飛猛進,但日本專利申請案總量卻明顯下降)


幾個AI核心發明的個別趨勢(黃色是總量,其中應有專利涵蓋兩個以上的類別):


從機器學習技術的專利獲准率來看,日本專利局對於AI演算法相關技術的接受度頗高。


AI相關發明的細部分類,從2022年申請案得出:


AI相關發明中,涉及深度學習技術的申請案最多:


在日本,提出AI相關發明申請案的公司是Fujitsu Ltd.,其次是NTT,再來是Canon...。


表面上看來,Fujitsu Ltd.也是提出AI核心技術專利申請案最多的公司之一,另外還有NEC、IBM、Toshiba等。


統計至2021年,日本申請案中,關於神經網路技術類別的申請案比例最多的是美國,其次是韓國。


Ron

2024年11月29日 星期五

禁止多重附屬項依附多重附屬項的日本專利筆記

筆記

真是寫完就忘了,過去曾有網友在「引用記載形式獨立項筆記(https://enpan.blogspot.com/2019/09/blog-post.html)」文中回應日本專利局已經禁止多附多的專利範圍寫法,當時還回覆說會去找資料,其實之前早早在2022年就已經有相關分享,但仍感謝網友回應。

過去的報導:
-日本自April 1, 2022後不再接受多項依附多項附屬項(補充資料)(https://enpan.blogspot.com/2023/09/april-1-2022.html
-JPO修法禁止「multi-multi claim」,包括各國筆記(https://enpan.blogspot.com/2022/04/jpomulti-multi-claim.html

既然是新PO文,還是要來點東西,但也是舊東西,本篇參考日本專利局關於「Restriction of Multi-Multi Claims」內容(https://www.jpo.go.jp/e/system/patent/shinsa/multimulticlaims.html)。

日本專利局禁止多附多寫法後的一些狀態:

在日本專利局禁止多附多的寫法之前(April 1, 2022禁止實施),有65%專利申請案包括有多附多的申請專利範圍,而禁止日之後,直接掉到5%,再過一年再掉到3%。

面對多附多申請案,日本專利局建議:在提出實審請求之前提出主動修正,這可以避免日本專利局針對多附多請求向發出的通知,如果沒有解決多附多問題,可能就會駁回專利申請案;在日後審查答辯過程,要時時檢查是否有多附多請求項的存在。

如果接獲日本專利申請案稿件,看不懂日文沒關係,除了運用工具翻譯外,JPO提供檢查是否有多附多請求項的工具:


Ron

2024年9月27日 星期五

JPO提供的專利侵權訴訟要領 - 一些摘要

Patent Infringement Litigation in Japan


Part 1 - How to Deal with a Warning Letter
專利侵權訴訟經常開始於專利權人發出的警告信,接獲警告信的標準處理流程:


接獲警告信的人可提出專利無效的動作,有兩種程序:

(1)在侵權訴訟程序中,專利權人提出禁制令、損害賠償的同時,被告侵權對象可以提出無效抗辯;
(2)在日本專利局提出無效程序。

=>案件在之後可能會進入智慧財產法院、最高法院。


解釋專利範圍並評斷是否有侵權可能是接收警告信的人最在乎的事,這裡提到幾個解釋專利範圍的原則:從請求項文字表面的意思解釋專利範圍(literal),如果這樣都有侵權疑慮,就要注意;如果字面看來似乎不侵權,就看其解釋上的等效範圍(equivalents)。根據以上原則評估之後,可以看看是間接侵權或是直接侵權,這時需要判斷自己所處的產業鏈位置。

對自身的檢驗包括,(1)查自己擁有的專利權;(2)是否有先使用權(prior user right);(3)是否有實驗上的使用(experimental use),在實驗上的使用或是科學上的測試可免除專利侵權;(4)是否有強制許可(compulsory licenses)。

若有侵權疑慮,應(1)停止侵權行為;(2)尋求授權協議;(3)迴避設計。

若沒有侵權問題,應(1)回應沒有侵權;(2)對專利提出無效程序;(3)若確認沒有侵權,收到警告信的人可以在法院提起宣告式判決訴訟(Declaratory judgment action),通過法院確認沒有侵權的事實。

以上措施可以參考下圖流程:

Part 2 - Court Proceedings
在日本,僅兩個法院處理專利侵權爭議:Tokyo and Osaka District Courts

法院系統:

訴訟程序:
1. 提交訴狀(complaint)
2. 相關救濟(remedy),包括主訴(main suit,包括損害賠償與永久禁制令)與初步禁制令(preliminary injunction)
3. 聽證(first hearing)
4. 後續程序,包括審判、言詞辯論、專家作證等程序。
5. 侵權判斷與損害賠償為兩個程序。
6. 和解
7. 損害賠償計算
8. 宣判
9. 上訴

(更多細節可參考JPO網站與本文)

Ron

2024年8月29日 星期四

日本AI發明專利的適格性筆記之三 - 日本軟體/AI發明的專利適格性 (Open Edition)

本篇筆記用Google搜尋到的一篇文章:https://books.openedition.org/putc/15392?lang=en(出自大阪大學助理教授Etsuko Yoshida的書 - Artificial Intelligence-related invention in Japan and its disclosure with a focus on human intervention p. 225-247)

一些筆記。

保護人類智慧財產與科技進步的專利法隨著科技的演變也應與時俱進,如已經發展多年的資通訊的技術,到現在人工智慧科技(AI),人工智慧特別是基於人類資料分析的需求,並成為決策的重要依據,與AI一起演進的技術還有IoT、機器人與大數據等。

之前最受注目與爭議的案子就是AI/DABUS,本部落格也有不少的案例報導,爭點是AI本身是否可以是發明人?如果是可以的,或許表達了這是一個趨勢,不過在專利系統中,仍需要發明內容,以及人類可理解的技術內容,短時間內這些都無法獲得解答。

因此,專利法目前主要探討的是,與AI相關的人類獨創的發明,首先會面對的是專利適格性/可專利性議題,一般判斷可專利性是檢查發明是否使用自然律(law of nature)並整體上實施技術思想(technical idea)。

【AI相關發明】則是涉及電腦實現的發明,因此判斷標準就如各國都會針對電腦實現發明(軟體發明)所制定的審查基準,如同在日本,判斷AI相關發明的專利適格性就是檢查通過軟體處理的資訊是否由硬體資源實踐("whether information processing by the software is specifically implemented by using hardware resources?");更準確地說,根據申請專利範圍的描述,是否是實現基於預期使用(intended use)的軟硬體協作的計算或資訊處理("based on the statement of the claims, whether or not specific calculation or processing of information depending on the intended use is implemented by specific means or procedures on which software and hardware resources cooperate?"),如果是,就是屬於可專利標的

範例A:Data Structure of Dialogue Scenarios in a Voice Interactive System
資料結構涉及資訊處理技術,其中執行流程包括:(1)輸出對話單元的訊息;(2)取得使用者回答的答案;(3)指定根據使用者的回答候選答案;(4)根據候選答案與通訊模式的資訊選擇分支資訊;以及(5)從伺服器接收後續對話。

(1) outputting a message included in the current dialogue unit; 
(2) acquiring an answer from the user in response to the message; 
(3) specifying the said candidate answer based on the answer from the user; 
(4) selecting the branch information based on the candidate answer and information on communication mode; and 
(5) receiving from the server a following dialogue unit indicated by the selected branch information.

所示資料結構可參考原文,評估範例A的專利適格性,包括判斷claim 1描述的資料結構是一種資訊處理,其中的對話是對話單元產生的語音對話,其中資訊處理是通過電腦軟硬體的協作,已經符合上述日本專利局訂出可專利性標的的原則:使用自然律的技術思想,因此符合日本專利法定義的發明

範例B:AI inventions including learning models
神經網路的結構相似於執行電腦程序的程式,因此也是屬於日本專利法保護的標的。進一步地,學習模型是電腦程式與訓練參數的組合,並且特別地是利用硬體資源實現,因為是建構於使用自然律的技術思想,為可專利標的

此例請求項1記載運用神經網路訓練可以量化住宿名聲的訓練模組,其中技術就是很標準的神經網路訓練得出可以分析住宿名稱的模型,是通過軟硬體協作實現基於預期應用的資訊處理系統,這是基於自然律的技術思想的創作,因此是符合專利法的發明。

範例C:Invention of business method using IoT
此例是一個使用IoT的商業方法,然而商業方法在日本是不能取得專利的,但是,如果是軟硬體協作實現的商業方法,則是有可能取得專利。以「配置無人駕駛車輛的方法與系統」為例(編按,這是一種叫車/無人駕駛車的技術),這裡提到兩種Claim態樣:

Type 1:
Claim 1涉及的系統包括:車輛配置伺服器、使用者操作的可攜式終端,以及無人駕駛車輛,其中可攜式裝置傳送使用者ID與車輛配置位置給伺服器,伺服器利用使用者ID得到使用者的臉部影像,伺服器傳送臉部資訊與車輛配置位置的資訊至無人駕駛車輛無人駕駛車輛進行使用者臉部認證,以及根據車輛配置位置驅動車輛到達位置。

分析:Type 1的請求項內容包括軟硬體協同作業的特徵,並描述了資訊處理的過程,看來並沒有不可專利的因子(但與AI關聯不大)。

Type 2:
Claim 2涉及的系統包括車輛配置伺服器、可攜式終端,以及無人駕駛車輛,其中伺服器接收車輛配置至指定位置的請求,伺服器即依照請求配置車輛給使用者。

分析:同樣是叫車服務,Type 2僅界定發出請求與執行配置兩個動作,是用軟體流程描述的系統,但沒有描述資訊處理的細節,因為沒有軟硬體協同作業的特徵在日本專利實務中並不屬於發明範疇

以上兩種態樣的專利範圍都屬於商業方法(軟體流程都可廣泛地定義為商業方法/business method),根據以上分析,顯然,至少在日本,軟體流程與硬體的關聯/協同作業成為具有專利適格性很重要的判斷依據

日本專利適格性規範在日本專利法第2條第1項:
Article 2(1)The term "invention" as used in this Act means a highly advanced creation of technical ideas utilizing the laws of nature.


【AI發明的進步性】
判斷發明是否有進步性,標準的判斷是相關領域技術人員(person skilled in the art)依據先前技術是否可輕易實現該發明。

在日本,如何判斷是否可輕易實現該發明?(在此忽略一些細瑣的內容)

AI相關發明與一般軟體發明仍有基本的差異,一般軟體發明主要是通過程式設定一些規則而產生軟體流程,軟體發明的適格性就如上述範例,軟硬體的協作為符合專利適格性的要件。

不同地,AI相關發明是以數據為基礎,通過學習數據得出相關模型執行相關流程,因此,AI相關發明需要界定學習模型,成為判斷專利適格性的要件,也會是判斷發明是否具有進步性的依據,並且在判斷進步性要件時,AI相關發明若採用了已知/公開的AI系統,訓練模型的技術相對申請當下技術水平是否顯而易知(obvious)成為進步性判斷關鍵。

【AI發明的揭露要求】
判斷AI發明專利適格性如軟體發明,主要是依據是否揭露了相關模型的技術內容,且判斷進步性時,說明書揭露內容將成為判斷關鍵。

專利說明書揭露程度的基本要求是讓相關領域技術人員可以據以實施(enablement)。然而,在AI相關發明中,常見卻是缺乏AI的揭露內容(形成黑盒子),日本專利法規定揭露內容要能據以實施:

Article 36(4)(i):
(4)The statement of the detailed explanation of the invention referred to in item (iii) of the preceding paragraph must comply with each of the following items: 
(i)as provided by Order of the Ministry of Economy, Trade and Industry, it is clear and sufficient to enable a person ordinarily skilled in the art of the invention to work the invention.

由於專利說明書內容需要支持專利範圍,因此內容應超越專利範圍更多,並且內容需要讓相關領域技術人員可以理解,並解決相應的技術問題。

以AI發明來看,原則就是避免黑盒子,說明書應揭露AI模型的數據、機器學習演算方法、模型產生的技術,以及前後關聯性,並揭露訓練模型的方法流程,如軟體發明,揭露到可據以實施的程度。


日本專利法英文版:

關於AI/DABUS,可參考:
- 英國最高法院否決A.I.發明人 - [2023] UKSC 49(https://enpan.blogspot.com/2024/01/ai-2023-uksc-49.html
- 歐洲專利局駁回AI為發明人的專利申請案(https://enpan.blogspot.com/2020/09/ai.html
- A.I.發明人Dabus的申請案以及澳洲聯邦法院案例(https://enpan.blogspot.com/2021/08/aidabus.html)
- A.I.發明人現況 - DABUS / Thaler v. Vidal(https://enpan.blogspot.com/2023/04/ai-dabus-thaler-v-vidal.html
- AI不是法律上之「人」- 110年度行專訴字第3號(https://enpan.blogspot.com/2021/09/ai-1103.html
- A.I.發明人!Mr. A.I.(https://enpan.blogspot.com/2020/04/aimr-ai.html
- A.I.不能是發明人;或說發明人不能是非人類 - Thaler v. Hirshfeld, App No. 21-02347 (Fed. Cir. 2022)(https://enpan.blogspot.com/2023/04/ai-thaler-v-hirshfeld-app-no-21-02347.html

Ron

2024年6月29日 星期六

日本AI發明專利的適格性筆記之二 - JPO 2024年更新範例

延續前篇,本篇筆記JPO與時俱進更新的AI相關發明指南與範例:https://www.jpo.go.jp/e/system/laws/rule/guideline/patent/document/ai_jirei_e/jirei_add2024_e.pdf

定義AI-related技術是以機器學習通過IoT技術收集到的大數據,機器學習如一種深度學習演算法,用以訓練模型,可以針對已知/未知的數據產生結果。


列舉三個範例,分別是針對可實施性、可專利性,以及明確性的案例。

Case 5:
可實施性、說明書支持要件

發明提出一個通過機器學習法學習化學結構與已知成分(Fluorescent Compoun)的特性形成的訓練集,預測出一些具有特定特性的新的成分(A, B),其中成分A已經獲得驗證,但成分B沒有。

Claim 1描述的是通過模型預測出具有特定特性的新的成分,附屬項界定A與B兩個不同的成分。而這樣的發明專利被駁回,駁回理由是說明書並未敘明產生這些成分的方法,相關領域技術人員基於已知技術也無法理解,因此違反可實施性要件。也就是通過訓練得出的模型預測出的成分並非一般知識可以達成。


下圖顯示發明關於利用機器學習法學習化學結構與特性形成的訓練集,形成模型,經輸入螢光特性後,可以輸出新的成分。

核駁理由主要是以申請時該領域知識無法理解如何以訓練出的模型預測新的模型的技術,因此有部分是不符可實施性要件,然而有一項範圍是沒有遭遇核駁的,即Claim 2,主要理由是Claim 2描述的成分A有經過實驗證實,並且說明書的描述是可以據以實施Claim 2。


Case 8:專利適格性要件

一開始即說明AI相關發明中Claim 1所描述的“訓練集/training data”本身僅是資訊表示(mere presentation of information),不滿足專利適格性要求。而Claim 2描述了產生形成訓練集的影像的方法,可以理解的是運用硬體以軟體處理資訊是具體的技術,也就滿足專利適格性要求。以下圖式中的流程圖就是Claim 2特徵。

(編按,也就是說,至少日本專利局,認為只要講清楚AI如何運作就會具備專利適格性,如以下示意圖。)

Claim 1僅屬於資訊表示,因此不具專利適格性。Claim 2描述了產生訓練集的方法,其中需要軟硬體一起完成,具有專利適格性。

列舉Claim 2:
[Claim 2] A method for generating images for training data for training a discriminator that determines the area of surgical instruments in target images when the target images are input, the method comprising 
a step of obtaining radiological images including the human body and surgical instrument images indicating surgical instruments; and a step of generating images for training data corresponding to the target images by combining the surgical instrument images with the radiological images, performed by an image generation device for training data.


Case 10:明確性要件

專利請求項僅記載訓練模型,但沒有提到電腦,不清楚這個訓練集是一個程式指令,且沒有描述一個方法範圍或是產品範圍,因此不明確。

以下有專利範圍的解釋,也就是此例的Claim 1或2界定一個訓練集是不明確的。


此案例要克服明確性,請求項可以改寫:"The computer incorporated in the copier comprises a CPU and a memory that stores the trained model trained by the learning device, and if the trained model is a program module, the trained model may be stored in the memory.",這解決了專利標的不明確的問題。


Ron

2024年6月26日 星期三

日本AI發明專利的適格性筆記之一 - ChatGPT問答錄

前言:

其實說到AI發明,也僅是搭上目前很夯的話題,AI有個特色是 - "說不清楚",但本質上就是"軟體發明",也就是常說的"電腦實現的發明/computer-implemented invention/CII",因此有關軟體發明的專利適格性議題應該都適用在AI相關的發明。但無論如何,AI相關發明的專利適格性仍是值得一談的議題,畢竟AI還是有點意思。

AI相關發明在日本專利實務有何見解?大哉問,先問ChatGPT:

這些可參考,問了「ChatGPT」,它給我的答案算是很嚴肅的一般知識加上一些常識,也就是軟體發明該注意的,仍有一些可參考資料,如下標註:

 

In Japan, the patentability of AI-related inventions follows the general principles of patent law, but there are specific considerations to keep in mind:

1. **Statutory Requirements**: To be patentable, an AI-related invention must meet the three basic requirements: novelty, inventive step (non-obviousness), and industrial applicability.
(常識)

2. **Technical Aspect**: The invention must be a "creation of technical ideas utilizing a law of nature." Pure mathematical algorithms, abstract ideas, or mental acts are not patentable unless they have a technical character or are implemented in a way that produces a technical effect.
(還算可以,就是要有技術效果的特徵)

3. **AI Algorithms**: AI algorithms themselves, if claimed as such, are generally not patentable unless they are part of a specific technical application or contribute to a technical improvement. For example, a machine learning algorithm used in a medical imaging device to improve diagnostic accuracy may be patentable.
(還算不錯的答案)

4. **Application Format**: The Japan Patent Office (JPO) encourages applicants to describe AI-related inventions in terms of their technical problem and solution. Detailed descriptions of how the AI contributes to solving a technical problem and the specific technical implementation can enhance the chances of patentability.
(要解決技術問題)

5. **Examples of Patentable AI Inventions**:
(我覺得是不錯的說明)
- AI used in a new type of control system for machinery.
- AI algorithms implemented in a specific hardware environment that results in a technical improvement.
- Specific applications of AI in fields like healthcare, manufacturing, or transportation that demonstrate a technical effect.

6. **Examination Guidelines**: The JPO provides examination guidelines specific to AI-related inventions. These guidelines help in assessing whether an AI invention meets the criteria for patentability, emphasizing the importance of a detailed technical description and the demonstration of a technical effect.

7. **Patent Strategy**: When filing an AI-related patent in Japan, it's crucial to:
(很不錯的結論)
- Clearly define the technical problem being solved.
- Detail the technical means by which the AI solution is implemented.
- Highlight any technical effects or improvements resulting from the AI implementation.

In summary, while AI algorithms as standalone inventions are generally not patentable in Japan, AI-related inventions that demonstrate a clear technical contribution and solve a specific technical problem can be patented. The focus should be on the practical application and technical details of the AI solution.


繼續問以上答案是否有來源?ChatGPT給我以下內容(我希望它用email寄給我,但是目前尚無此功能):


Subject: Information on Patentability of AI-Related Inventions in Japan

Hi Ronpan,

Here is the information on the patentability of AI-related inventions in Japan:

1. **Japan Patent Office (JPO) Official Website**:
- The JPO provides comprehensive guidelines and resources regarding patent examination, including specific guidelines for AI and software-related inventions.
- [Japan Patent Office (JPO)](https://www.jpo.go.jp/e/)

2. **JPO Examination Guidelines**:
- The JPO has published examination guidelines that cover various aspects of patentability, including specific sections on AI and software inventions.
- [JPO Examination Guidelines](https://www.jpo.go.jp/e/system/laws/rule/guideline/patent/index.html)

3. **Intellectual Property High Court of Japan**:
- For legal precedents and interpretations related to AI patents, you might find relevant case law from the Intellectual Property High Court of Japan.
- [Intellectual Property High Court](http://www.ip.courts.go.jp/eng/)

4. **Japanese Patent Attorneys and Law Firms**:
- Consulting with Japanese patent attorneys or law firms specializing in intellectual property can provide personalized and detailed advice.
- Some well-known firms include:
- Nakamura & Partners: [Nakamura & Partners](http://www.nakapat.gr.jp/english/)
- Aoyama & Partners: [Aoyama & Partners](http://www.aoyamapat.gr.jp/)

5. **Academic and Industry Publications**:
- Research papers, articles, and industry reports on AI and IP law can provide deeper insights.
- Websites like Google Scholar or legal databases such as LexisNexis and Westlaw can be useful.

6. **Professional Organizations and Conferences**:
- Organizations like the International Association for the Protection of Intellectual Property (AIPPI) often hold seminars and publish papers on the latest trends in IP law, including AI-related patents.
- [AIPPI Japan](https://www.aippi.org/aippi-japan/)

I hope this helps with your research and any AI-related patent endeavors!

Best regards,


整理以上來源:

[Japan Patent Office (JPO)](https://www.jpo.go.jp/e/)


[JPO Examination Guidelines](https://www.jpo.go.jp/e/system/laws/rule/guideline/patent/index.html)


[Intellectual Property High Court](http://www.ip.courts.go.jp/eng/)


Nakamura & Partners: [Nakamura & Partners](http://www.nakapat.gr.jp/english/)


Aoyama & Partners: [Aoyama & Partners](http://www.aoyamapat.gr.jp/)


[AIPPI Japan](https://www.aippi.org/aippi-japan/)



-------------------------------------------------------------------

問Google,則看到一篇不錯的內容:https://books.openedition.org/putc/15392?lang=en,看不出來本篇撰寫日期,但其中有引用2021年案例,應該還算新的知識。


-------------------------------------------------------------------


(以上僅筆記,編排有點混亂,加上內容很多,需要時間消化,會需要分幾篇來寫!)

Ron

2023年9月12日 星期二

日本自April 1, 2022後不再接受多項依附多項附屬項(補充資料)

本部落格之前的報導:JPO修法禁止「multi-multi claim」,包括各國筆記(https://enpan.blogspot.com/2022/04/jpomulti-multi-claim.html


還是要感謝網友「正義龍CYL」在本部落格「引用記載形式獨立項筆記(https://enpan.blogspot.com/2019/09/blog-post.html)」的回應(抱歉現在才看到,網友針對某篇地回應我只會在該文"跳出"到排行版才會看到~~~)。

該篇部落格提到「歐洲、日本是允許多項附屬項間之直接或間接引用」,但網友提醒「日本已經於2022.04禁止了多項附屬項依附多項附屬項 (包含直接或是間接)」。

再複習與提醒自己(我自己都忘了),日本專利局對於April 1, 2022當日或之後發明與新型專利申請案中多項附屬多項的請求項,將不審理其新穎性、進步性與明確性。

根據JPO官網公告修訂審查基準(examination guidelines)https://www.jpo.go.jp/e/system/laws/rule/guideline/patent/kaitei/rev_202204.html),從April 1, 2022之後將不接受「multi-multi」請求項。

The draft revision of the Examination Guidelines for Patent and Utility Model in Japan (hereinafter, simply referred to as the “Examination Guidelines”) has been prepared based on the discussions at the 16th meeting of the Working Group on the Patent Examination Standards supervised by the Patent System Subcommittee under the Intellectual Property Committee of the Industrial Structure Council. The public comments were invited from February 10 to March 11, 2022.

The Examination Guidelines related to Multi-Multi Claim Restriction is revised in light of the public comments.

(Note) The term "Multi-Multi Claim" as restricted by the revised Ministerial Ordinance means "any dependent claim that refers to more than one other claim in the alternative ("multiple dependent claim") which depends from any other multiple dependent claim."

The revised Examination Guidelines is applied to examination of the applications filed on or after April 1, 2022.


根據「Part II Chapter 2 Section 5 Ministerial Ordinance Requirement on Statement of Claims」(https://www.jpo.go.jp/e/system/laws/rule/guideline/patent/kaitei/document/rev_202204/02-02-5.pdf)規定,多項附屬項直接或間接依附另一多項附屬項將導致專利範圍不容易辨識的問題,即限制這類申請專利範圍。


違反規定的範例:



查詢到的相關網頁包括:



本部落格之前的報導:JPO修法禁止「multi-multi claim」,包括各國筆記(https://enpan.blogspot.com/2022/04/jpomulti-multi-claim.html

Ron

連續動畫設計、衍生設計筆記

為了要回應客戶有關設計專利規劃的需求(設計-申請-權利主張)的一些筆記。

關於連續動畫的美國設計專利範例:
[設計範例一]:D881929(連續動畫)

[設計範例二]:D765,180

為了要讓審委明白,申請時補上說明附件:

[設計範例三]:D978908


法院案例分享:
[案例一]:
設計專利侵權判斷應排除功能性元件 - 案例Richardson v. Stanley討論(http://enpan.blogspot.tw/2015/08/richardson-v-stanley.html

本案例確認「一般觀察者測試」:
在一般觀察者(較佳為"
熟悉相關先前技術的人")查看系爭專利與被告侵權產品時,係以整體設計來判斷是否會被混淆(欺騙),但在判斷之前,卻要先釐清何謂"功能性元件",觀地排除功能性元件,才針對其中視覺上的差異比對。觀念:設計要有意識地將非功能元件置入設計中,才能稱為設計,才能算是創作。

[案例二]:
設計專利侵權討論 - Apple v. Samsung案例(https://enpan.blogspot.com/2015/08/apple-v-samsung.html

引用上述案例Richardson案中專利範圍解釋時整體上並沒有排除功能元件,反而包括了這些元件中的裝飾元素,該案外觀設計中:榔頭的外觀就是因為其功能目的、夾東西的鉗口、圓頸...等)形成其整體外觀的一部分,因此不認為應該因為設計中的功能性元素而排除其相關的結構外觀(structural aspect),因為這些功能性元素已經透過專利範圍解釋為「裝飾性設計(ornamental design)」。

關於「真實欺騙(actual deception)」判斷,設計專利的侵權判斷時,有個要件就是普通消費者視覺上是否造成混淆或欺騙為購買某物時以為是另一有設計專利的產品,如果是,侵權成立。

[案例三]:
仿冒者勝訴的關鍵 - Lanard Toys Limited v. Dolgencorp LLC and Ja-Ru (Fed. Cir. 2020)(https://enpan.blogspot.com/2020/05/lanard-toys-limited-v-dolgencorp-llc.html

對於設計侵權判斷,採用兩部分測試:(1)解釋設計的保護範圍;(2)比對設計的保護範圍與被告產品設計,其中採用一般觀察者(ordinary observer)測試,也就是,以一般觀察者來看系爭設計與被告產品是否實質相同(substantially the same)?如果一般觀察者購買被告產品時,會以為是買了另一個,兩者為"實質相同"。

CAFC採用「一般觀察者/普通觀察者」測試法,比對設計與被告侵權物,兩者很像,共用了許多特徵,但仍須考量設計中的「功能性元素」以及相關先前設計的特徵,當將這些特徵提醒一般觀察者注意,就得出被告侵權產品與系爭設計之間的明顯差別,使得法院最後判定系爭設計與被告侵權物並非「實質相同」。

關於外觀商標(trade dress): 要證明trade dress侵權,要證明三件事:(1)系爭設計與被告物之間有混淆的相似性;(2)外觀商標的主特徵為非功能特徵;(3)外觀商標具有第二含意(second meaning/secondary meaning),也就是系爭設計讓大眾建立了一種識別性。


文件重點補充:
  1. 對於多件近似重複的設計規劃:


  2. 現行衍生設計:


  3. 衍生設計的申請與期限:


  4. 日本關聯意匠:


  5. 美國多實施例申請:


TIPO檔案 - 111.11 智慧財產權月刊 VOL.287:衍生設計專利制度的探討與分析


Ron