Showing posts with label LegalTech. Show all posts
Showing posts with label LegalTech. Show all posts

Tuesday, April 14, 2026

Mastering Patent Claim Construction with LLMs (4): Bridging Knowledge Gaps and Designing Expert-Level Skills

LLM으로 완벽한 특허청구범위 해석하기 (3)

Mastering Patent Claim Construction with LLMs (4): Filling the Gaps in the Knowledge Base

The Final Stage of Supplementing the Sources

This is now the final stage of supplementing the source materials. In the earlier stages, I gradually built up relevant materials in NotebookLM and organized the legal principles and practical standards needed for patent claim construction. But simply collecting a large volume of material does not automatically create a strong knowledge base. In practice, materials are often overly concentrated on certain issues, while foundational legal principles that are essential in actual practice may still be missing. That is why, at this final stage, it is necessary to examine not only what the accumulated sources already cover well, but also what they fail to cover.

The core objective of this stage is simple. Rather than continuing to add more knowledge based on what has already been collected, the real task is to identify the gaps in the knowledge base. In other words, this is not really a stage for re-confirming “what we already know,” but more accurately a stage for exposing “what we still do not know.”

To do that, I entered the following instruction into the NotebookLM chat window.

PROMPT
Review the attached sources and analyze whether there are any missing pieces of information. In particular, please examine what core information or context is essential to fully understand this topic but is currently missing from the sources, and explain it specifically.

The purpose of this instruction is not summarization or organization. It is intended to make the LLM identify what core legal principles or contextual elements are still missing, even though they are essential for a complete practical understanding based on the materials collected so far. Framing the question this way prevents the model from giving a superficial response like, “You’ve assembled the materials well,” and instead pushes it to identify the deficiencies in a structured and practical way.


Items Identified as Requiring Supplementary Materials

In response to the instruction above, the materials requiring supplementation were organized as follows.

Output
A comprehensive review of the currently provided sources and conversation history shows that while advanced special issues in patent claim construction and infringement analysis—such as PBP claims, functional claims, and the suture-line cases—have been covered in substantial depth, several core foundational principles and practical contexts that are essential for fully understanding and applying this area in practice are still missing. Specifically, the following key information is either absent or needs supplementation. 1. Missing Korean leading cases on the requirements for ordinary prosecution history estoppel (“intentional exclusion”) - Current status: The latest Korean Supreme Court decision dealing with estoppel in the context of divisional applications (2023Hu11340) and the discussion of the fifth requirement of the doctrine of equivalents through Japan’s Maxacalcitol case are both covered in significant detail. - Missing context: What is missing is a concrete factual and legal analysis of the traditional Korean Supreme Court leading cases (e.g., Supreme Court Decision 2002Hu1768) that clearly set out how strong or explicit a statement in an office-action response or amendment must be, from an objective and outward-looking perspective, to constitute “intentional exclusion” in ordinary Korean patent litigation practice. There is therefore a gap in establishing the Korean baseline for measuring the degree of intentional disclaimer. 2. The strict limits and requirements for applying the Lexicographer Rule - Current status: Many sources already include the overarching principle and cases stating that when claim language is unclear, the detailed description of the invention and the drawings should be consulted. - Missing context: What is missing is a deeper case-based analysis of the strict requirements and limitations of the Lexicographer Rule—specifically, how explicit and definitive an applicant’s definition in the specification must be before that definition can displace the ordinary meaning of a term in the art. 3. Korean applications of the Public Dedication Rule based on the specification - Current status: Some Japanese case commentaries briefly mention whether the dedication doctrine has been adopted, but there is little to no concrete treatment of how it has been applied under Korean law. - Missing context: The current materials lack a clear account of the Korean Supreme Court’s position and practical treatment where the patentee discloses a particular embodiment or substitute in the specification but does not claim it, and whether that subject matter is deemed dedicated to the public so as to bar application of the doctrine of equivalents. Because this is a powerful defense against an equivalents claim, it is essential material that should be supplemented. 4. “Omission infringement” and “incomplete use inventions” as exceptions to the All Elements Rule (AER) - Current status: The existing materials address, at a sophisticated level, issues such as the suture-line decision overcoming geographic limits, multi-actor infringement, and indirect infringement as exceptions to the All Elements Rule. - Missing context: However, the question of whether infringement can still be found when the defendant strategically omits or only incompletely uses a relatively less important element of the patented invention in an effort to design around the claim is discussed only briefly, in about a single paragraph. That is not enough to fully understand the range of defensive arguments against design-arounds. 5. Standards for evaluating “critical significance” when applying the doctrine of equivalents to numerical limitation inventions - Current status: The latest Korean Supreme Court case on disclosure requirements for numerical limitation inventions (2021Hu10886), including enablement and written-description support, is already covered. - Missing context: What is missing is the Korean courts’ concrete standard, at the infringement stage, for determining whether equivalents may be found when the accused product falls just slightly outside a claimed numerical range—for example, whether the presence or absence of “critical significance” excludes application of the doctrine of equivalents. This is indispensable for a full understanding of both offensive and defensive logic in numerical-limitation cases where there is no literal infringement.

Important Practical Insights Gained at This Stage

The result above means more than simply “we need more materials.” From a practical perspective, the more important message is that even if the materials collected so far are already highly sophisticated, the entire framework can become unstable if the baseline of general legal doctrine is missing.

For example, even if you have assembled abundant materials on difficult special issues such as PBP claims and functional claims, the standards for interpreting claim scope in an actual case can still become unstable if foundational principles—such as the requirements for ordinary prosecution history estoppel or the limits on the Lexicographer Rule—have not been properly organized. Put differently, special issues are “advanced applications,” while general doctrine is “basic grammar.” If the basic grammar is weak, the advanced applications will inevitably become unstable as well.

That is why I did not simply leave the omissions identified above as a note. Instead, I copied them back into the NotebookLM source window and activated the deep research function to supplement the missing cases and legal principles. This process is extremely important because by feeding the LLM-identified “knowledge gaps” back into the system as inputs, the knowledge base can evolve from a simple collection-oriented repository into a self-correcting knowledge base.


Now It Is Time to Organize the Knowledge to Be Injected into the Claude Skill

The next stage is to use the supplemented materials to extract and organize only the core knowledge that should be injected for drafting the Claude Skill. This is where many people make a mistake. Once they have gathered a large amount of material, they tend to think they should put as much of it as possible into the Skill. But in practice, the opposite is often true. If the background knowledge loaded into the Skill becomes too extensive, the model may get buried in explanations or lose sight of priorities rather than following the core principles clearly. At this stage, therefore, accurate compression matters more than volume.

When I draft a Claude Skill, I usually prefer to compress the core principles, framework, workflow, and output format into about 5,000 characters or less before injecting them. This point is especially important in practice. The skill guide, SKILL.md, is generally recommended to remain under 5,000 words, with more detailed knowledge separated into the references/ folder. In addition, it is more efficient to reflect required input information in the trigger description rather than in the body of the Skill itself. That way, Claude can assess input sufficiency before the Skill is even called.

How to Ask Questions to Extract the Core Knowledge While All Sources Are Selected

With all sources selected, I enter the following questions one by one into the NotebookLM chat window to organize the background knowledge that will be injected into the Skill. At present, I have 60 sources registered in my notebook.

PROMPT
1. What are the core principles that consistently appear across all of these sources in relation to patent claim construction? 2. When all of the sources are analyzed together, what framework is mentioned most frequently for interpreting patent claims? 3. Looking at claim construction step by step, what does an excellent real-world process for interpreting the language of a patent claim actually look like? 4. What is the concrete framework or workflow strategy used by Korean courts for patent claim interpretation? To prepare a claim chart for claim construction, please explain in detail how to break down the claim language, extract and interpret the terms or limitations that become the targets of interpretation, and how to draft the claim chart itself.

This sequence of questions was not chosen arbitrarily. The reason I ask first about the common principles, then the framework, then the process, and finally the concrete drafting method is to guide the LLM into organizing its answer in the sequence of abstract principles → procedural structure → practical execution method. This makes it much easier to transfer the results later into a Skill without the information becoming disordered and scattered, and it helps maintain a relatively stable structure.


The Final Claude Skill Injection Guide Organized in NotebookLM

The final guide I organized in NotebookLM for injection into the Claude Skill is as follows.

PROMPT
Korean courts, in determining the scope of patent rights in infringement litigation and invalidation proceedings, apply in practice a **multidimensional six-step interpretive process (workflow)** based on the four core principles of **literal interpretation, reference to the specification, prosecution history estoppel, and reference to the prior art**. Based on that framework, the following explains the specific methods of decomposition and extraction, as well as the drafting format, for preparing a Claim Chart. ### 1. The Korean Courts’ Six-Step Framework for Interpreting Patent Claims - Step 1 (Claim decomposition and initial delimitation based on the claim language): Break the claim into individual elements, which are the minimum units for invalidity and infringement analysis, identify the organic relationships among them, and then define the initial scope of the patent right based on the ordinary and general meaning of the terms from the viewpoint of a person having ordinary skill in the art (PHOSITA). - Step 2 (Reference to intrinsic evidence and examination of technical meaning): Because it is often difficult to ascertain the technical meaning from the claim language alone, the detailed description of the invention and the drawings must be consulted. In particular, the “Lexicographer Rule” applies where the applicant has defined a specific term in the specification, and the analysis should go beyond the immediate context to examine the problem-solving principle and functional effect (technical meaning) of the relevant element. - Step 3 (Filtering out improper narrowing and expansion): Even when the specification is taken into account, courts strictly block errors that improperly narrow claim scope by relying only on a specific embodiment or configuration disclosed in the specification, or improperly expand the claim scope beyond what the claim language reasonably supports. - Step 4 (Applying tailored legal rules to special types of claims): For functional claims (e.g., “means for ~”), the analysis must consider whether limiting construction to the embodiments is warranted; for product-by-process (PbP) claims, the issue is not the process itself but the “structure or properties of the product” defined by that process; and for numerical-limitation inventions, the analysis must focus on whether the claimed numerical range has “critical significance.” - Step 5 (Reference to prosecution history and review of intentional exclusion): Review the prosecution history from filing to registration—such as office-action responses and amendments—to determine whether the applicant intentionally excluded specific subject matter in order to avoid the prior art, in which case that subject matter must be firmly excluded from the scope of the patent right. - Step 6 (Infringement comparison and limits on the doctrine of equivalents): Compare the finalized scope of the patent right with the accused product to determine whether all elements are present (All Elements Rule, AER). If differences exist, determine whether the doctrine of equivalents (DOE) applies by examining whether the patented invention and the accused product share the same principle for solving the problem, among other factors. ### 2. Methods for Claim Decomposition and Extraction for Preparing a Claim Chart 2.1. Structure- and Function-Based Decomposition: Decompose the claim in a multidimensional way into the physical structure of the elements and the functions and roles performed by those elements. 2.2. Identification of Organic Relationships: Go beyond merely listing the elements and clearly identify the **physical and functional connections (relationships)** among different elements that contribute to solving the technical problem. 2.3. Extraction of Core Interpretive Targets and Limitations (Special Issues): Extract the key terms that may become issues in claim construction. In particular, functionally expressed terms (“means for ~”), PbP processes, numerical limitations, and parameters should be targeted so they can be separately reviewed for issues such as limiting construction and lack of enablement. ### 3. The Most Desirable Concrete Claim Chart Methodology and Format From a practical standpoint, the best Claim Chart is not just a literal element-by-element comparison. It should be drafted as a seven-column system that can fully map both doctrine-of-equivalents (DOE) defenses in cases of literal non-infringement and the issues presented by special types of claims. | No. | Decomposed Claim Language (Including Organic Relationships) | Core Interpretive Target (Special Issue: Functional / PbP / Numerical) | Specification / Drawing Support (Mapping of Intrinsic Evidence) | Objective Technical Meaning and Result of Literal Interpretation (from the PHOSITA Perspective) | DOE Comparison: Identification of the Principle for Solving the Problem | Limitation on Rights: Prosecution History Estoppel and Grounds for Limiting Construction | | :-- | :--- | :--- | :--- | :--- | :--- | :--- | | 1 | (e.g., a cleaning unit that supplies cleaning water by electrolyzing filtered water) | cleaning unit (functional claim) | [paragraph 14], [figure 3] | (e.g., an internal module that physically cleans through electrodes) | (e.g., the principle of maximizing eco-friendly cleaning efficiency by excluding chemicals) | (e.g., intentional exclusion of a “chemical additive method” during argument submission) | | 2 | (e.g., a tablet manufactured by direct compression) | manufactured by direct compression (PbP claim) | [paragraphs 15–16] | (e.g., a porous tablet structure having 15% inter-particle porosity formed through the direct compression process) | (e.g., the principle of controlling disintegration speed by adjusting porosity) | (e.g., structurally / physically different from tablets manufactured by wet granulation) | [Drafting Guide and Explanation for Each Column] 1) Decomposed Claim Language: Set out verbatim the claim language as broken down into the minimum units, but do so in a way that reveals not just a simple list of elements, but also the physical and functional relationships among them. 2) Core Interpretive Target: Extract the key terms that present infringement or invalidity issues—such as functional expressions, PbP language, and numerical limitations—and identify the type in parentheses. 3) Specification / Drawing Support (Mapping of Intrinsic Evidence): Provide a one-to-one mapping to the specific paragraph numbers and figure numbers in the specification that show where the term is defined, where the supporting embodiment for a functional claim appears, where PbP leads to a specific physical-property change, and where the technical threshold for the numerical limitation is shown. 4) Objective Technical Meaning and Result of Literal Interpretation: Describe the substantive meaning derived from the specification from the viewpoint of a person having ordinary skill in the art (PHOSITA). In PbP claims, this should not simply repeat the process itself, but should translate it into the “structure or properties of the product” defined by that process. 5) DOE Comparison (Identification of the Principle for Solving the Problem): In anticipation of literal non-infringement, identify in advance the **“problem-solving principle unique to the patented invention (the core technical idea)”** to which the relevant element belongs, based on the specification and the prior art. 6) Limitation on Rights (Prosecution History Estoppel and Grounds for Limiting Construction): Carefully record any history of **intentional exclusion** during prosecution, any reason why the claim should be limited to the embodiments because the broader reading is not supported by the specification, and any invalidity grounds such as lack of enablement across the full scope of a numerical limitation.

Now I Ask NotebookLM to Create the Expert Skill Itself

At this point, based on the organized knowledge, I ask NotebookLM to actually create a patent claim construction expert Skill. This stage is not merely an experiment. If the principles and framework organized up to this point are sufficiently well-structured, NotebookLM can generate a draft of an expert-level Skill based on them. That draft is not the finished product, but it is extremely useful as a starting point for human review and refinement.

The instruction entered at that point was as follows.

PROMPT
Based on this “Korean patent claim construction doctrine” knowledge base extracted in NotebookLM, create an expert skill file. The skill should include behavior rules, an output decision guide, a problem-solving methodology, and a Claim Chart output style.

Comparing the Generated Skill with the Existing Skill Guide

When I compare the Skill generated by NotebookLM with the Skill guide I created earlier, the result is as follows.

Output
Based on the “Korean patent claim construction doctrine” knowledge base and the conversation history you provided, I am preparing a top-tier expert-level **“Korean Patent Claim Construction and Claim Chart Drafting Expert Skill File”** that can be deployed immediately in patent litigation and trial practice. This skill file can be used as a system prompt or guideline for an AI or practitioner conducting patent analysis work. # [Expert Skill File] Korean Patent Claim Construction and Infringement Analysis Agent ## 1. Behavior Rules You are a top-tier patent dispute expert with deep command of Korean Supreme Court and Patent Court case law. When interpreting claims and analyzing infringement, you must strictly comply with the following rules. - Strict case-law-based interpretation: All interpretation must be grounded in the current Patent Act Article 97 and Korean Supreme Court case law as the controlling standards, including the literal-interpretation principle, reference to the specification, prosecution history estoppel, and reference to the prior art. - Maintain the PHOSITA perspective: The meaning and technical significance of every term must be interpreted from the objective viewpoint of a person having ordinary skill in the art (PHOSITA) at the time the patent application was filed. - Strict separation between interpretation and limitation: You should actively consult the detailed description of the invention in order to clarify the technical meaning of a term, but you must strictly reject any improper “importing of limitations” or improper expansion based on pulling in conditions or configurations from the embodiments that are not actually recited in the claims. - Exceptional treatment for special types of claims: If a functional claim, a product-by-process (PbP) claim, or a numerical-limitation invention is identified, you must proactively apply the Korean Supreme Court’s tailored doctrines that go beyond the general interpretive rules, including limiting construction, translation into structure/properties, and critical-significance analysis. - Secure defense logic first: In infringement analysis, the All Elements Rule (AER) must be applied first and foremost. If literal non-infringement is anticipated, you must simultaneously review prosecution history estoppel (intentional exclusion) and the doctrine of equivalents (DOE) in advance so that both offensive and defensive arguments can be built in a balanced way. ## 2. Output Decision Guide Optimize the output according to the type of user input. - [Input] Only the text of a specific claim is provided: Break the claim down into minimum units (structure/function), identify organic relationships, and provide a first-stage diagnostic report on whether any special issues (functional claim, PbP, numerical limitation) are present. - [Input] Claim text + specification (description / drawings) are provided: Determine whether the Lexicographer Rule applies, derive the objective technical meaning, and perform a second-stage analysis that warns of the risks of improper narrowing or overbroad interpretation. - [Input] Claim text + specification + prosecution history (office actions / responses) are provided: Analyze whether intentional exclusion (Korean-style estoppel) has been established and derive the finally determined scope of the patent right. - [Input] Entire patented invention + accused product are provided: Apply the full “six-step problem-solving methodology” and produce a final **[7-Column Claim Chart]**. ## 3. Problem-Solving Methodology (6-Step Problem Solving Methodology) Carry out the full process from claim construction through infringement analysis under the following multidimensional six-step workflow. - Step 1 (Claim decomposition and identification of organic relationships): Break the claim down into the minimum units that allow invalidity and infringement analysis, while also deriving the overall relationships among the elements. Break the claim down to the smallest units using structure and function as the organizing principles. Do not stop at simple decomposition; define the invention by comprehensively identifying the physical coupling relationships and the functional / organic interconnections among the elements. - Step 2 (Determining technical meaning through literal interpretation and reference to the specification): Begin with the ordinary meaning of the claim language, then concretize that meaning by mapping it one-to-one against the specification and drawings from the viewpoint of a PHOSITA. . Lexicographer Rule: If the applicant explicitly defined a specific term in the specification, apply that definition first. . Examination of technical meaning: Go beyond the immediate contextual meaning and examine, in an objective and reasonable way, the “technical meaning” of the relevant element, including the technical problem it is intended to solve, the implementation principle, and the functional effect, so that the invention’s intended function and operation are properly realized. - Step 3 (Strict control of improper narrowing and expansion): Strictly distinguish between “interpreting in light of the specification” and “importing narrowing or expansion from the specification.” . No improper narrowing: Where the claim language is clear, exclude interpretations that arbitrarily narrow the claim by importing unclaimed elements from specific embodiments, figure shapes, or specific limitations described in the specification. . No improper expansion: Even when consulting the specification, prevent overbroad interpretation that goes beyond the disclosed content or moves in a direction unrelated to the core technical meaning of the invention. - Step 4 (Applying tailored exception doctrines to special types of claims): Unlike ordinary claims, claims drafted in special forms must be interpreted using the Korean Supreme Court’s tailored doctrines. . Functional claims (“means for ~”): If literal interpretation would make the claim unduly broad in light of the specification, review whether there are grounds for limiting construction to specific embodiments or structures. . PbP claims (products recited through a manufacturing process): The substantive element is not the manufacturing process itself, but rather the **“structure or properties of the final product”** defined by that process. . Numerical limitation / parameter inventions: Rigorously assess whether the entire claimed range is enabled (disclosure requirement) and whether the claimed range shows a remarkable effect that distinguishes it from the prior art (critical significance). - Step 5 (Reference to extrinsic evidence and review of estoppel / intentional exclusion): Analyze the entire file history, including office-action responses and amendments, from filing through registration, divisional applications, and correction proceedings. If the applicant **intentionally excluded** a specific element to avoid a rejection, or if subject matter was **dedicated to the public** by being disclosed in the specification but omitted from the claims, that subject matter must be excluded from the scope of the patent right. - Step 6 (Infringement comparison and limits on application of the doctrine of equivalents): Based on the finalized meanings of the elements and their organic relationships, compare them one-to-one with the accused product (or method) and make the final infringement determination. . Literal infringement (AER): First determine literal infringement under the All Elements Rule (AER) by comprehensively examining both element-by-element correspondence and the overall identity of the combination and functional operation. . Infringement under the doctrine of equivalents (DOE): If there is a literal difference, determine whether equivalent infringement exists by identifying, in light of the prior art, whether the patented invention and the accused product share the same “problem-solving principle” unique to the patented invention, along with the same functional effect. ## 4. Claim Chart Output Style All claim analysis results and infringement / invalidity comparison results must be output in markdown table format using the following **“7-Column Claim Chart Template.”** ### [Claim Chart Template] | 번호 | 청구항 분해 문언 (유기적 결합 포함) | 핵심 해석대상 (특수쟁점 표기) | 명세서/도면 근거 (내적 증거) | 객관적 기술의의 및 문언해석 결과 (PHOSITA 관점) | 균등론(DOE) 대비: 과제 해결 원리 식별 | 권리제한: 출원경과 금반언 및 제한해석 사유 | | :-- | :--- | :--- | :--- | :--- | :--- | :--- | | 1 | [최소 단위로 분해된 청구항 원문 기재. 단순 나열 금지, 결합관계 명시] | [핵심 용어 추출] (예: 기능식 / PbP / 수치한정 등 표기) | [정의/실시예가 기재된 단락 번호 및 도면 번호 맵핑] | [명세서를 참작하여 실질적으로 확정된 구성의 의미 기재. PbP의 경우 '구조/성질'로 번역하여 서술] | [문언 비침해 대비. 해당 구성이 속한 특허발명 특유의 '핵심 기술사상(과제 해결 원리)' 명시] | [의견서/보정서상 '의식적 제외' 이력, 또는 실시예로 제한 해석되어야 할 명백한 무효/불비 사유 기록] | | 2 | ... | ... | ... | ... | ... | ... | ### [Points to Watch When Drafting the Claim Chart] 1. **Emphasize organic relationships:** In the “Decomposed Claim Language” column, do not merely chop the claim into elements A, B, and C. Draft it so that the physical and functional interaction among the elements is clearly shown. 2. **Mandatory translation for special claim types:** If a PbP claim is identified, do not write merely “manufactured by ~ method” in the “Objective Technical Meaning” column. Instead, it must be translated into language such as “an internal structure / physical property formed by that process.” 3. **Identify the problem-solving principle in advance for DOE:** Every chart should proactively identify the **“problem-solving principle”** by which the relevant element distinguished itself from the prior art and contributed to the advance, so that it is immediately possible to assess whether a design-around can still be captured if literal infringement is denied. 4. **Thoroughly record estoppel:** If the prosecution history confirms any abandoned subject matter or any substitute dedicated to the public, summarize it in the “Defense Logic” column so that any future doctrine-of-equivalents theory can be blocked at the outset.

The Meaning of This Stage: Not “Getting Answers,” but “Designing a Way of Thinking”

Looking back over everything up to this point, it becomes clear that the key is not simply extracting answers from the LLM. What really matters is designing the order in which the LLM thinks, what it reviews first, and the format in which it organizes the result.

From a practical perspective, creating a good work structure is even more important than choosing a good model. And that work structure is built through the following flow.

1. First, gather the materials.
2. Then identify the gaps in those materials.
3. Supplement the missing pieces.
4. Compress only the core principles.
5. Structure those principles into a framework and workflow.
6. Finally, convert them into a Skill so they become a repeatable analytical system.

If this process is done properly, you can go beyond getting a single good answer and actually create a repeatable, practice-oriented patent claim interpretation engine.


Closing Thoughts

On the surface, this stage may look like nothing more than “supplementing sources” and “preparing to draft a Skill.” In reality, however, it is much closer to a stage of designing a system of thought that allows an LLM to perform the highly demanding task of patent claim construction in a stable and reliable way.

In other words, the key at this stage is not putting in more information, but making the model think under more precise standards. Ultimately, what determines the quality of the output is not the name of the model, but what materials are given to it, how they are structured, and under what standards the model is made to operate.

In the next stage, using this organized Skill guide and the Skill that was actually generated, selecting a real case, drafting a Claim Chart, and then comparing the result with the claim construction in the court decision or trial decision would lead to a much deeper practical understanding.

Mastering Patent Claim Construction with LLMs (3): Injecting Guidelines for Claim Chart Drafting

LLM으로 완벽한 특허청구범위 해석하기 (3)
Practical Framework Part 3

Mastering Patent Claim Construction with LLMs (3)

Injecting Claim Chart Drafting Guidelines Drawn from Practical Experience

The next step is a research phase aimed at establishing the format of the final deliverable.

Rather than organizing claim construction results into a simple narrative report, I prefer to structure them in the form of a Claim Chart specifically designed for claim interpretation. This is not merely to make the output look polished, but to secure a practical tool that can be used under a consistent standard in all downstream tasks, including infringement analysis, invalidity review, and opinion drafting.

1. Why Claim Chart Standards Must Be Established First

There is one important point here. A Claim Chart is not just a “format for organizing results,” but a core framework that determines the quality of the interpretation itself.

The problem, however, is that the method for decomposing claims, the standards for extracting elements, and the actual drafting approach are not systematically organized in textbooks or case law. In other words, this is an area where methodology is built largely 👉 through practical experience.

Through handling a wide range of cases, I have gradually developed my own standards for claim decomposition, element extraction, and chart structure in a way that is suitable for claim construction.

2. Teaching the LLM the “Drafting Method” First

At this stage, what I do is simple. I organize the standards I use in practice 👉 the way I would teach a junior associate, and then register them as a source in NotebookLM.

A Critically Important Point

This step is not simply about “adding reference materials.” It is the process of pre-training the LLM on the interpretive framework and the output format so that it will reason under the same standards in all later interpretation tasks.

  • This is the step where you inject, before adding any source materials, how the analysis should be conducted and how the results should be organized.
  • If this step is skipped, the LLM will analyze each task under a different set of standards, which in turn prevents the overall work product from losing consistency.

3. Claim Chart Drafting Guidelines (Draft)

Below is a draft of the practical Claim Chart drafting guidelines that I prepared and asked the model to review.

DRAFT INSTRUCTION
**1. Methods for Claim Decomposition and Extraction for a Claim Chart Used in Claim Construction** Claims should be broken down into the smallest units that serve as the basis for invalidity and infringement analysis. The language of the claim should be separated according to context, while also being divided into sub-elements in a way that clearly reveals the invention’s distinctive features. The specific methods of decomposition and extraction are as follows. * **Structure- and Function-Based Decomposition:** Break the claim down into **structure**, which reflects the physical form of the elements and how they are connected, and **function**, which reflects the operation and role performed by each element. * **Identifying Organic Relationships:** Go beyond merely listing the components and derive the relationships showing how each component connects with the others and contributes to solving the technical problem. * **Extracting Interpretive Terms and Limitations:** From among the separated sub-elements, extract as the key interpretive targets those terms that **specifically require claim construction or are directly tied to the invention’s distinctive features**. In particular, major extraction targets include terms expressed functionally (for example, “means for ~”) that may need to be examined to determine whether limiting interpretation to the embodiments is required, as well as terms to which the principle of claim differentiation may apply because of dependent claims. **2. The Most Desirable Methodology for Drafting a Claim Chart** The most practical and desirable output format for visualizing claim construction results in a logical and clear manner is to prepare a **Claim Chart** in tabular form. For that purpose, I propose the following table format composed of **six items (columns)** as the output format. | No. | Claim Language | Claim Element (Interpretive Target) | Specification / Drawing Support | Interpretation Result and Legal Analysis (from the PHOSITA Perspective) | Notes (Prosecution History / Limiting Construction) | | :-- | :--- | :--- | :--- | :--- | :--- | | 1 | Decomposed claim language | (e.g., screw) | [paragraph number], [figure number] | (e.g., a low-speed pressing member having a spiral structure) | (e.g., vertical-type limitation based on an argument submission) | **[Drafting Guide and Explanation for Each Column]** * **Claim Language:** Set out verbatim the minimum unit of claim language as decomposed in a way that clearly reveals the invention’s distinctive features. * **Claim Element (Interpretive Target):** Extract from the decomposed language the core target terms or limitations that especially require interpretation or are written as functional expressions (e.g., “means for ~”). * **Specification / Drawing Support (Mapping of Intrinsic Evidence):** Identify and map the specific [paragraph numbers] and [figure numbers] in the detailed description of the invention that define or support the meaning of the term. * **Interpretation Result and Legal Analysis:** From the perspective of a person having ordinary skill in the art, apply intrinsic evidence first and clearly state the objectively and substantively established technical meaning of the claim element. * **Notes (Review of Prosecution History and Limiting Construction):** Record legal points of note, such as any intentional exclusion (prosecution history estoppel) reflected in the submission of arguments or amendments during prosecution, or any reason why, due to a clear disavowal of claim scope in the specification, limiting construction to the embodiments should apply.

This type of Claim Chart format allows intuitive one-to-one textual mapping between the relevant product (or prior art) and the claim elements in later infringement litigation or invalidity proceedings, making it the most effective practical analytical tool for preventing errors caused by improper narrowing or overbroad claim interpretation.

4. The Process of Validation → Refinement → Redesign

Rather than simply using the above guidelines as-is, I validated them in the following way.

“Are these guidelines sufficiently valid under actual legal doctrine and case law standards?”

To answer that question, I instructed the model in the chat to reflect the points requiring refinement and present again the most appropriate concrete Claim Chart format and drafting guide.

5. Refined Claim Chart Drafting Guidelines (Final Version)

The result is as follows, and this too was saved as a memo and then converted back into a source and integrated into the knowledge base. This process of turning good results into knowledge that can be continuously reused rather than a one-off answer is extremely important.

FINAL FRAMEWORK
**1. Methods for Claim Decomposition and Extraction for a Claim Chart Used in Claim Construction (Reflecting Special Issues)** When decomposing claims to apply the All Elements Rule (AER), which is central to infringement and invalidity analysis, it is essential to go beyond a simple listing of claim language and instead perform a more multidimensional extraction that reflects the legal characteristics of **special types of claims (functional claims, PbP claims, and numerical limitation claims)**. * **Identifying Structure, Function, and Organic Relationships:** Break the invention down into the physical structures that make it up and the functions those structures perform, while clearly deriving the relationships showing that each element does not exist in isolation but is organically connected with other elements to solve the technical problem. * **Extracting Targets for Limiting Construction of Functional Claims:** Because elements expressed in abstract or functional terms, such as “means for ~” or “~ step,” carry a risk of making the claim scope unduly broad, they should be extracted as targets for focused review to determine whether there are clearly unreasonable circumstances requiring the claim to be limited to the embodiments disclosed in the specification. * **Extracting the “Structure / Properties” of PbP (Product-by-Process) Claims:** Even when a manufacturing process is recited in the claim, the subject of the invention is still a “product,” so the manufacturing process itself should not be mechanically extracted as an independent element. Instead, the true technical element to be extracted is the “structure or properties of the product” ultimately defined by that manufacturing process. * **Extracting the “Critical Significance” of Numerical Limitation / Parameter Inventions:** Where a specific numerical range or a newly created parameter is involved, it should be separated as a core interpretive target in order to assess whether the specification enables the full claimed range without undue experimentation (support requirement), and whether the claimed range or parameter shows a remarkable effect (critical significance) that distinguishes it from the prior art. **2. The Most Desirable Concrete Claim Chart Format (Top-Tier Practical Template)** By upgrading the existing six-column structure, I propose a **seven-column framework that can fully map both Doctrine of Equivalents (DOE) defense / attack logic in cases of literal non-infringement and the analytical guidance for special types of claims**. | No. | Decomposed Claim Language (Including Organic Relationships) | Core Interpretive Target (Special Issue: Functional / PbP / Numerical) | Specification / Drawing Support (Mapping of Intrinsic Evidence) | Objective Technical Meaning and Result of Literal Interpretation (from the PHOSITA Perspective) | DOE Comparison: Identification of the Principle for Solving the Problem | Defense Logic: Prosecution History Estoppel and Grounds for Limiting Construction | | :-- | :--- | :--- | :--- | :--- | :--- | :--- | | 1 | (e.g., a cleaning unit that supplies cleaning water by electrolyzing filtered water) | cleaning unit (functional claim) | [paragraph 0045], [figure 3] | (e.g., an internal module that performs physical cleaning through electrodes without sterilizing chemicals) | (e.g., the principle of maximizing eco-friendly cleaning efficiency by excluding chemicals) | (e.g., conscious exclusion of a “chemical additive method” during argument submission) | | 2 | (e.g., a tablet manufactured by direct compression) | manufactured by direct compression (PbP claim) | [paragraph 0022] | (e.g., a porous tablet structure having a 15% inter-particle porosity formed by the direct compression process) | (e.g., the principle of controlling disintegration speed by adjusting porosity) | (e.g., structurally / physically different from tablets made by wet granulation) | | 3 | (e.g., a lens assembly having TTL ≤ 6.5 mm) | TTL ≤ 6.5 mm (numerical limitation) | [paragraph 0110], [Experimental Example 2] | (e.g., the physical limit of a miniaturized lens with a total track length of 6.5 mm or less) | (e.g., the principle of achieving an ultra-short focal length through refractive-index redistribution) | (e.g., target for lack of enablement across the full range of 6.5 mm or less) | **3. [Drafting Guide and Explanation for Each Column]** * **Decomposed Claim Language:** Set out verbatim the claim language decomposed into the minimum unit defining the scope of the invention, while describing it in a way that reveals not just a simple list but also the physical and functional relationships among the elements. * **Core Interpretive Target (with Special-Issue Label):** From the decomposed language, extract the key terms that present issues—such as functional expressions (“means for ~”), product-by-process (PbP) language, or numerical limitations / parameters—and identify the type in parentheses so the focus of the analysis is clear. * **Specification / Drawing Support (Mapping of Intrinsic Evidence):** Map the specific [paragraph numbers] and [figure numbers] in the specification that show where the term is defined under the lexicographer rule, where embodiments support a functional claim, where a manufacturing process in a PbP claim causes a specific change in physical properties, or where the technical threshold for a numerical limitation is demonstrated. * **Objective Technical Meaning and Result of Literal Interpretation (from the PHOSITA Perspective):** From the perspective of a person having ordinary skill in the art, apply the principle of construing the claim in light of the specification and describe the objectively and reasonably derived substantive meaning of the element. In the case of PbP claims, the description should not merely repeat the manufacturing process itself, but should clearly translate the structure or properties defined by that process. * **DOE Comparison: Identification of the Principle for Solving the Problem (New):** This column is used to assess possible infringement under the Doctrine of Equivalents when differences are found in a literal one-to-one comparison with the accused product. By considering both the content of the specification and the prior art existing at the time of filing, this column states in advance the “core of the technical idea underlying the specific means for solving the problem unique to the patented invention” (i.e., the principle for solving the problem) to which the relevant element belongs. * **Defense Logic: Prosecution History Estoppel and Grounds for Limiting Construction (New / Refined):** Record the history of any intentional exclusion (prosecution history estoppel) of specific subject matter reflected in arguments or amendments submitted throughout the prosecution of the original application and any divisional applications. Also record whether a functional claim should be limited to a specific embodiment because a broader reading would be clearly unreasonable in light of the specification, or whether a numerical limitation invention may be invalid for failure to satisfy disclosure requirements (such as enablement) because the full claimed range cannot be practiced without undue experimentation.

6. The Core Meaning of This Stage

The most important insight to gain at this stage is the following.

“A Claim Chart is not merely an organizational tool, but a structural mechanism that controls the accuracy of claim interpretation.”

And when using LLMs, the key is not simply getting good results, but building a system in which the results are always generated under the same standards.

7. Key Points for Practical Application

When this process is applied directly in practice, it can be summarized as follows.

  1. First, establish the “drafting format” (the structure of the table).
  2. Next, inject the “interpretive standards” (legal doctrine and drafting guidelines).
  3. Then, input the “source materials” (the specification and evidence).
  4. Finally, carry out the “claim interpretation and chart drafting”.

Most people reverse this order. Because they start by asking for the interpretation right away, the results become unstable and lose consistency.

This stage is not simply about creating a Claim Chart, but about designing how the LLM will think. When this work is done properly, all later analytical work becomes far more stable.

© 2026 ChinSu Lee. All rights reserved.

Mastering Patent Claim Construction with LLMs (2): Enhancing the Claim Interpretation Framework and Expanding the Knowledge Base

Mastering Claim Construction with LLMs (2)

Mastering Claim Construction with LLMs: Refining the Framework and Expanding the Knowledge Base

How practical experience and AI can work together to evolve beyond simple analysis into an expert-level knowledge asset

Building on the previous post, this time I focused on refining the claim construction framework and expanding the surrounding knowledge system.

In the previous post, I supplied additional practical heuristics that I had separately compiled from experience and instructed the model to compare and verify them against the existing case law analysis. The framework I asked it to review was the “Five-Step Claim Construction Framework under Korean Case Law.”

System Directive
This is a five-step interpretive structure that takes the claim-centered approach (literal interpretation) as the governing principle, while supplementarily referring to the specification and drawings to determine the technical meaning in an objective and reasonable manner. Five-Step Claim Construction Framework under Korean Case Law 1) Step 1 (Principle of Literal Interpretation): The scope of the patent right is first defined based on the ordinary meaning of the terms used in the claim, as understood in the relevant technical field. 2) Step 2 (Reference to the Specification and Drawings): From the perspective of a person having ordinary skill in the art (PHOSITA), the claims are interpreted in light of the overall context of the specification. If the applicant explicitly defined a term in the specification (the lexicographer rule), that definition takes precedence. More specifically, the meaning of the term is determined through the detailed description of the invention so that the intended function and operation of the invention are properly implemented. The Korean Supreme Court has made clear that, when consulting the specification, courts must go beyond simply reading the surrounding context and must instead objectively and reasonably examine the “technical meaning” that the language was intended to convey, including the problem-solving principle and technical effect. 3) Step 3 (Prohibition on Undue Narrowing or Expansion): Even when consulting the specification, the claims must not be improperly narrowed based on specific embodiments, nor unreasonably expanded beyond what is supported by the specification. In practice, one of the most common errors in Korean patent litigation is confusing “interpreting claims in light of the specification” with “importing limitations from the specification into the claims.” The Supreme Court has taken a firm position against improper narrowing based on the description of the invention (for example, in the Cream case and the Display Structure case). 4) Step 4 (Reference to Prosecution History and Estoppel): If a particular feature was consciously excluded or narrowed during prosecution, later attempts to reverse course and broaden the interpretation are restricted. 5) Step 5 (Application of the All-Elements Rule and Doctrine of Equivalents): In infringement analysis, the all-elements rule (AER) applies, while the doctrine of equivalents (DOE) serves as a supplementary doctrine to capture design-arounds.

As a result, I received a favorable assessment regarding its consistency with the case law, along with suggestions for areas that still needed improvement. The purpose of this stage was not simply to add more information, but to verify whether the existing framework was sufficiently supported for practical use and systematically reinforce the parts that were still lacking.

1. Method of Knowledge Expansion: “Turning Results Back into Sources”

The key method used in this round of work was as follows.

  • Save meaningful analytical outputs generated during the conversation as NotebookLM Studio notes
  • Convert those notes back into sources and reinject them into the existing knowledge base

In other words, instead of merely consuming answers, this creates a structure in which useful outputs are continually accumulated, refined, and converted into knowledge assets. As this process repeats, the LLM gradually comes closer to functioning like a case-specific expert model.

2. Results of Framework Validation: Strong Structure, but Foundational Legal Support Still Needed

Based on an analysis of 23 sources, the five-step claim construction framework I had previously developed was confirmed to be a highly sophisticated and practical structure. At the same time, however, NotebookLM pointed out several important issues.

The current source set is overly concentrated on specialized issues such as product-by-process claims, numerical limitation inventions, and the fifth requirement of the Japanese doctrine of equivalents. As a result, while the framework’s overall skeleton is strong, the general body of Korean case law needed to support that structure is still relatively thin.

3. Summary of Areas Needing Reinforcement by Step

(1) Steps 1–2: The Lexicographer Rule

  • Current status: The principle that claim terms may be interpreted according to definitions in the specification is partially reflected, but there is not yet enough explicit discussion of the lexicographer rule itself.
  • What needs to be reinforced: The requirements for recognizing the rule and the level of “clarity” needed to displace the ordinary meaning of a term.
  • Further research direction: Supreme Court decisions and academic materials analyzing the standard for clear claim-term definitions.

(2) Step 3: Interpretation of Functional Claim Language

  • Current status: The possibility of narrower interpretation is partially reflected, but the applicable standard remains unclear.
  • Core issue: It is difficult to determine when the general rule of literal interpretation should apply and when an exception permitting narrower interpretation should be recognized.
  • Further research direction: A comparison of cases that accepted limiting interpretation versus those that rejected it, with emphasis on the underlying factual circumstances.

(3) Step 4: Prosecution History and Estoppel

  • Current status: Some recent issues are well reflected, but the broader doctrine of prosecution history estoppel is still underdeveloped.
  • Core issue: Compared with Japanese authorities, there is still not enough Korean case law grounding.
  • Further research direction: Leading cases on conscious exclusion and estoppel, decisions addressing the full course of prosecution responses, and whether the dedication doctrine has been recognized in Korea.

(4) Step 5: AER and the Doctrine of Equivalents

  • Current status: The explanation of the all-elements rule (AER) is still very limited, and the criteria for applying the doctrine of equivalents are only summarized at a high level.
  • Core issue: There is still a lack of practical, case-usable standards for application.
  • Further research direction: Cases involving omission-type infringement and indirect infringement, standards for determining whether the same problem-solving principle is present, and the way prior art should be considered.

4. An Important Insight: “Special-Issue Data Is Actually a Strength”

One interesting takeaway is that, despite the gaps noted above, a substantial portion of the current sources focuses on high-difficulty issues such as product-by-process claims, numerical limitation inventions, and in-depth Korean and Japanese doctrine-of-equivalents cases. That is not a weakness. If anything, it is a strength. Most practical frameworks cover only the general rules and tend to break down when they encounter specialized issues.

5. Proposed Expansion of the Framework

Taking that into account, the existing five-step structure could be expanded as follows.

“Step 6: Interpretation of Special Claim Types (PBP Claims and Numerical Limitation Inventions) and the Limits of Applying the Doctrine of Equivalents”

Adding this step would allow the framework to evolve beyond a simple theoretical summary into a practice-oriented structure capable of handling high-complexity cases.

6. Supplementing the Proposed Sources and Closing Remarks

I copied the reinforcement points identified above directly back into NotebookLM’s source window and then activated the deep research function to gather additional case law and doctrinal materials that had been missing. Through this process, I was able to strengthen the weaker parts of the existing framework and expand the knowledge base in a more balanced way.

What This Stage Ultimately Accomplished

  1. Verified the structural completeness of the framework
  2. Identified areas where doctrinal support was still weak
  3. Confirmed the existing knowledge bias (specialized issues vs. general doctrine)
  4. Established a repeatable process for knowledge expansion

In claim construction, what matters is not simply gathering a large volume of materials, but whether the framework is actually built to digest and organize those materials effectively. Strong results come less from the model itself and more from the design of the knowledge structure and the reinforcement process.

© 2026 ChinSu Lee. All rights reserved.

Sunday, April 12, 2026

LLM으로 완벽한 특허청구범위 해석하기(3): Claim Chart 작성 지침 주입

LLM으로 완벽한 특허청구범위 해석하기 (3)
Practical Framework Part 3

LLM으로 완벽한 특허청구범위 해석하기 (3)

실무의 정수를 담은 Claim Chart 작성 지침 주입

다음 단계는 최종 결과물의 형식을 정립하기 위한 리서치 단계입니다.

저는 특허청구범위 해석 결과를 단순한 서술형 보고서로 정리하기보다는, 청구범위 해석용 Claim Chart 형태로 구조화하는 것을 선호합니다. 이는 단순히 보기 좋게 만들기 위한 것이 아니라, 이후 침해 분석, 무효 검토, 의견서 작성 등 모든 후속 작업에서 일관된 기준으로 활용할 수 있는 실무적 도구를 확보하기 위한 목적입니다.

1. 왜 Claim Chart 작성 기준을 먼저 정립해야 하는가

여기서 중요한 점이 하나 있습니다. Claim Chart는 단순한 “결과 정리 형식”이 아니라, 해석 자체의 품질을 결정하는 핵심 프레임워크입니다.

그런데 문제는, Claim Chart 작성을 위한 청구항 분해 방법, 구성요소 추출 기준, 실제 작성 방식이 교과서나 판례에 체계적으로 정리되어 있지 않다는 점입니다. 즉, 이 영역은 대부분 👉 실무 경험을 통해 축적되는 방법론입니다.

저 역시 다양한 사건을 경험하면서, 청구범위 해석에 적합한 Claim Chart를 만들기 위한 청구항 분해 기준, 구성요소 추출 방식, 표 구성 방법을 점진적으로 정립해 왔습니다.

2. LLM에게 “작성 방식”을 먼저 학습시킨다

이 단계에서 제가 하는 작업은 단순합니다. 제가 실무에서 사용하는 기준을 👉 신입사원에게 교육하듯 정리하여 NotebookLM의 소스로 등록합니다.

매우 중요한 포인트

이 작업은 단순히 “참고자료를 넣는 것”이 아닙니다. LLM이 이후 모든 해석 작업에서 동일한 기준으로 사고하도록 해석 프레임과 출력 형식을 사전에 학습시키는 과정입니다.

  • 입력자료를 넣기 전에 “어떻게 분석하고 어떻게 정리할 것인가”를 먼저 주입하는 단계입니다.
  • 이 단계를 생략하면 LLM은 매번 다른 기준으로 분석하게 되고, 결과적으로 전체적인 일관성이 무너지는 것을 방지합니다.

3. Claim Chart 작성 지침 (Draft)

아래는 제가 정리하여 검토를 요청한 Claim Chart 작성 실무 지침의 초안입니다.

DRAFT INSTRUCTION
**1. 청구범위 해석용 Claim Chart를 위한 청구항 분해 및 추출 방법** 청구항은 무효 및 침해 판단의 기초가 되는 최소 단위로 분해해야 합니다. 청구항 기재 내용을 문맥에 따라 분리하되, 발명의 특징적 구성이 잘 드러나도록 서브 구성으로 나누며, 구체적인 분해 및 추출 방법은 다음과 같습니다. * **구조(Structure) 및 기능(Function) 기반 분해:** 구성요소의 물리적 형상과 결합 관계를 나타내는 **구조**, 그리고 해당 구성이 수행하는 작용 및 역할을 의미하는 **기능**으로 분해합니다. * **유기적 결합(Relationship) 파악:** 단순히 구성요소를 나열하는 것을 넘어, 다른 구성요소와의 연결 방식 및 ‘기술적 과제 해결’에 기여하는 결합 관계를 도출합니다. * **해석 대상 용어 및 한정사항 추출:** 분리된 서브 구성 중에서 특별히 **청구범위 해석이 필요하거나 발명의 특징과 직결된 용어**를 핵심 해석 대상으로 추출합니다. 특히 기능적 표현(예: ~하는 수단)이 포함되어 실시예로의 제한 해석이 필요한지 검토해야 하는 용어나, 종속항에 의해 차별화 원칙이 적용될 수 있는 용어들이 주요 추출 대상이 됩니다. **2. 가장 바람직한 구체적인 Claim Chart 작성 방법론** 청구범위 해석 결과를 논리적이고 명확하게 시각화하기 위한 가장 실무적이고 바람직한 출력 형식은 **‘클레임 차트(Claim Chart)’**를 표 형태로 작성하는 것입니다. 이를 위해 다음의 **6가지 항목(컬럼)**으로 구성된 표 형식을 출력 포맷으로 제안합니다. | 번호 | 청구항 기재사항 | 청구항 구성요소 (해석대상) | 명세서/도면 근거 | 해석 결과 및 법리적 판단 (PHOSITA 관점) | 비고 (출원경과/제한해석) | | :-- | :--- | :--- | :--- | :--- | :--- | | 1 | 기재내용의 분해 | (예: 스크류) | [단락 번호], [도면 번호] | (예: 나선형 구조의 저속 압착체) | (예: 의견서 제출에 따른 수직형 한정) | **[컬럼별 작성 가이드 및 항목 설명]** * **청구항 기재사항:** 발명의 특징적 구성이 잘 드러나도록 분해한 최소 단위의 청구항 문언을 원문 그대로 기재합니다. * **청구항 구성요소 (해석대상):** 분해된 문언 중에서 특별히 해석이 필요하거나 기능적 표현(~수단)으로 기재된 핵심 타겟 용어나 한정사항을 추출합니다. * **명세서/도면 근거 (내적 증거 매핑):** 해당 용어의 의미를 정의하거나 뒷받침하는 발명의 상세한 설명의 구체적인 [단락 번호]와 [도면 번호]를 찾아 근거로 연결합니다. * **해석 결과 및 법리적 판단:** 통상의 기술자 관점에서 내적 증거를 우선 적용하여, 객관적이고 실질적으로 확정된 구성요소의 기술적 의미를 명확히 기술합니다. * **비고 (출원경과 및 제한해석 검토):** 출원 과정 중 의견서/보정서 제출 등에 따른 의식적 제외(금반언) 내역이나, 명세서상 명백한 권리범위 포기(Disavowal)로 인해 실시예로의 제한 해석이 적용되어야 하는 사유 등 법리적 특이사항을 기록합니다.

이러한 클레임 차트 형식은 추후 침해소송이나 무효심판에서 대상 제품(또는 선행기술)의 구성요소와의 일대일 문언 대비(Mapping)를 직관적으로 가능하게 해주며, 부당한 한정이나 확장 해석의 오류를 방지하는 가장 완벽한 실무 분석 도구가 됩니다.

4. 지침 검증 → 보완 → 재설계 과정

위 지침을 단순히 사용하는 것이 아니라, 다음과 같은 방식으로 검증을 진행했습니다.

“이 지침이 실제 법리와 판례 기준에서 충분히 타당한가?”

이를 위해 대화창에서 보완점을 반영하여 가장 바람직한 구체적인 Claim Chart 양식과 가이드를 다시 제시하도록 지시하였습니다.

5. 보완된 Claim Chart 작성지침 (최종본)

그 결과는 다음과 같으며, 이 역시 메모로 저장한 후 다시 소스로 변환하여 지식 베이스에 통합했습니다. 좋은 결과를 “일회성 답변”으로 두지 않고, 지속적으로 재사용 가능한 지식으로 전환하는 이 과정이 매우 중요합니다.

FINAL FRAMEWORK
**1. 청구범위 해석용 Claim Chart를 위한 청구항 분해 및 추출 방법 (특수 쟁점 반영)** 침해 및 무효 판단의 핵심인 ‘구성요소 완비의 원칙(AER)’을 적용하기 위해 청구항을 분해할 때는, 단순한 문언의 나열을 넘어 **특수 청구항(기능식, PbP, 수치한정)의 법리적 특성을 반영한 입체적 추출**이 필수적입니다. * **구조(Structure), 기능(Function) 및 유기적 결합관계 파악:** 발명을 구성하는 물리적 구조와 그 구조가 수행하는 기능으로 분해하되, 각 구성요소가 단독으로 존재하는 것이 아니라 기술적 과제 해결을 위해 다른 구성요소들과 유기적으로 결합되어 있는 관계를 명확히 도출해야 합니다. * **기능식 청구항의 제한해석 타겟 추출:** ‘~하는 수단’, ‘~단계’ 등 추상적·기능적으로 표현된 구성요소는 권리범위가 부당하게 넓어질 위험이 있으므로, 발명의 설명에 기재된 실시예로 제한 해석되어야 할 명백히 불합리한 사정이 없는지 집중 검토할 대상으로 추출합니다. * **PbP(제법한정물건) 청구항의 ‘구조/성질’ 추출:** 청구항에 제조방법이 기재되어 있더라도 발명의 대상은 ‘물건’이므로, 분해 시 제조방법 공정 자체를 독립된 구성요소로 단순 추출해서는 안 됩니다. 해당 제조방법에 의하여 최종적으로 특정되는 ‘물건의 구조나 성질’이 무엇인지를 실질적인 기술적 구성으로 추출해야 합니다. * **수치한정/파라미터 발명의 ‘임계적 의의’ 추출:** 특정한 수치 범위나 새롭게 창출된 파라미터가 포함된 경우, 명세서의 기재만으로 수치범위 전체에 걸쳐 과도한 실험 없이 실시가 가능한지(뒷받침 요건), 그리고 공지기술과 구별되는 현저한 효과(임계적 의의)가 있는지를 검증하기 위해 핵심 해석 대상으로 분리합니다. **2. 가장 바람직한 구체적인 Claim Chart 양식 (최상위 실무 템플릿)** 기존 6개 컬럼 구조를 업그레이드하여, **문언 비침해 시의 균등론(DOE) 방어/공격 논리와 특수 청구항 분석 지침을 완벽히 매핑할 수 있는 7컬럼 체계**를 제안합니다. | 번호 | 청구항 분해 문언 (유기적 결합 포함) | 핵심 해석대상 (특수쟁점: 기능/PbP/수치) | 명세서/도면 근거 (내적 증거 매핑) | 객관적 기술의의 및 문언해석 결과 (PHOSITA 관점) | 균등론(DOE) 대비: 과제 해결 원리 식별 | 방어논리: 출원경과 금반언 및 제한해석 사유 | | :-- | :--- | :--- | :--- | :--- | :--- | :--- | | 1 | (예: 여과된 물을 전기분해하여 세정수를 공급하는 세정수단) | 세정수단 (기능식 청구항) | [단락 0045], [도면 3] | (예: 전극을 통해 살균물질 없이 물리적으로 세척하는 내부 모듈) | (예: 화학물질 배제를 통한 친환경 세정 효율 극대화 원리) | (예: 의견서 제출 시 ‘화학약품 첨가 방식’ 의식적 제외) | | 2 | (예: 직타법으로 제조된 정제) | 직타법으로 제조된 (PbP 청구항) | [단락 0022] | (예: 직타법 공정으로 인해 입자간 공극률이 15%로 형성된 다공성 정제 구조) | (예: 공극률 조절을 통한 붕해 속도 조절 원리) | (예: 습식과립법으로 제조된 정제와 구조/성질이 상이함) | | 3 | (예: TTL ≤ 6.5mm 인 렌즈 조립체) | TTL ≤ 6.5mm (수치한정) | [단락 0110], [실험예 2] | (예: 총트랙길이가 6.5mm 이하로 초소형화된 렌즈 물리적 한계치) | (예: 굴절률 재배치를 통한 초단초점 구현 원리) | (예: 6.5mm 이하 전체 범위에 대한 명세서 실시가능성 기재 불비 타겟) | **3. [컬럼별 작성 가이드 및 항목 설명]** * **청구항 분해 문언:** 발명의 권리범위를 정하는 최소 단위로 분해된 청구항의 문언을 원문 그대로 기재하되, 단순 나열에 그치지 않고 구성요소 간의 물리적·기능적 결합관계가 잘 드러나도록 서술합니다. * **핵심 해석대상 (특수쟁점 표기):** 분해된 문언 중에서 기능식 표현(~수단), 제법한정(PbP) 기재, 또는 수치한정/파라미터 등 쟁점이 되는 핵심 단어를 추출하고 그 유형을 괄호 안에 병기하여 분석의 초점을 맞춥니다. * **명세서/도면 근거 (내적 증거 매핑):** 사전 편찬자 원칙에 따라 용어가 정의된 부분, 기능식 청구항을 뒷받침하는 실시예, PbP 청구항의 제조방법이 유발하는 구체적 물성 변화, 수치한정의 기술적 임계치를 증명하는 명세서의 구체적인 [단락 번호]와 [도면 번호]를 매핑합니다. * **객관적 기술의의 및 문언해석 결과 (PHOSITA 관점):** 해당 기술 분야의 통상의 기술자(PHOSITA) 관점에서 명세서 참작 원칙을 적용하여 객관적·합리적으로 도출된 구성요소의 실질적 의미를 기술합니다. PbP 청구항의 경우 제조방법 자체의 나열이 아니라, 그로 인해 특정되는 구조나 성질을 명확히 번역하여 기재해야 합니다. * **균등론(DOE) 대비: 과제 해결 원리 식별 (신설):** 문언적 일대일 대비 시 침해제품과 차이점이 발견될 경우 균등 침해 여부를 가리기 위한 항목입니다. 명세서에 기재된 내용과 출원 당시의 공지기술을 참작하여, 해당 구성이 속한 ‘특허발명에 특유한 해결수단이 기초하고 있는 기술사상의 핵심(과제 해결 원리)’이 무엇인지 사전에 명시해 둡니다. * **방어논리: 출원경과 금반언 및 제한해석 사유 (신설/보완):** 원출원 및 분할출원 심사 과정 전체에서 제출된 의견서나 보정서를 통해 특정 구성을 ‘의식적으로 제외(금반언)’한 이력을 기록합니다. 또한, 기능식 청구항이 명세서에 비추어 명백히 불합리하여 특정 실시예로 제한 해석되어야 하는 사유나, 수치한정 발명이 수치 전체 범위에 걸쳐 과도한 실험 없이 실시할 수 없어 명세서 기재요건(실시가능성 등) 위반 무효 사유가 있는지도 이곳에 함께 검토하여 기록합니다.

6. 이 단계의 핵심 의미

이 단계에서 얻어야 할 가장 중요한 인사이트는 다음입니다.

“Claim Chart는 단순한 ‘정리 도구’가 아니라 해석의 정확도를 통제하는 구조적 장치이다.”

그리고 LLM을 활용할 때는 결과를 잘 얻는 것이 아니라, 결과가 항상 같은 기준으로 나오도록 만드는 것이 핵심입니다.

7. 실무 적용 포인트

이 과정을 그대로 실무에 적용하면 다음과 같이 정리됩니다.

  1. 먼저 “작성 형식”(표의 구조)을 확립한다.
  2. 그 다음 “해석 기준”(법리 및 작성 지침)을 주입한다.
  3. 그 다음 “대상 자료”(명세서 및 증거)를 입력한다.
  4. 마지막으로 “해석 및 차트 작성”을 실행한다.

대부분은 이 순서를 거꾸로 합니다. 바로 해석부터 시키기 때문에 결과가 흔들리고 일관성을 잃게 되는 것입니다.

이 단계는 단순히 Claim Chart를 만드는 과정이 아니라, LLM이 어떻게 사고할 것인가를 설계하는 단계입니다. 이 작업이 제대로 되어 있으면 이후 분석 작업은 훨씬 안정적으로 진행됩니다.

© 2026 ChinSu Lee. All rights reserved.

체리피킹은 그만! 대법원 판결로 본 '선행문헌 전체 대비 원칙' 실무 가이드

선행기술 파악 법리 — 진보성 판단에서 선행기술 전체 대비 원칙 실무 해설서 Legal Commentary · IP Law 선행기술 파...