Showing posts with label NotebookLM. Show all posts
Showing posts with label NotebookLM. Show all posts

Tuesday, April 14, 2026

Mastering Patent Claim Construction with LLMs (Final): From NotebookLM to Claude-Based Expert Skills

LLM으로 완벽한 특허청구범위 해석하기 (3)

Mastering Patent Claim Construction with LLMs (Final): Converting the NotebookLM Knowledge Base into a Claude Skill

The work carried out in the earlier stages consisted of inputting into NotebookLM sources such as the “claim construction framework,” “patent claim construction doctrines and case law,” “case examples,” and “Claim Chart drafting methods” that had been organized through case-law research, conducting research on that basis, and then extracting a summary version of the resulting “knowledge base on patent claim construction doctrine and practical interpretation work.”

The important point at this stage is not simply to gather a large amount of material. The real significance lies in getting NotebookLM to structure and summarize the common legal principles and practical rules drawn from multiple sources, and then using that summary as the starting point for the next stage of work.

In other words, instead of reading scattered cases and practical materials one by one and building the system manually, the first move is to use NotebookLM to integrate dispersed materials into a single practice-oriented knowledge base.

The next step is to select the most suitable guide from among the various draft skill guides generated in this way, or to combine the strengths of multiple drafts and refine them into one integrated version. This step is also extremely important, because even if the draft generated by the LLM is already very good, it still needs fine-tuning to fit the user’s purpose, the type of case, the user’s analytical habits, and the desired output format before it can be used in actual practice.

Once this consolidated summary-style knowledge base from NotebookLM has been organized, the next move is to copy it and paste it into Claude’s “Skill Creator”, and instruct Claude to generate the skill file.

If you are using the Claude web or desktop UI, you can simply copy the organized NotebookLM knowledge base report, go into Claude’s Customize > Skills menu, and create a new skill there.

If you ask Claude as follows, it will generate a skill on its own, including behavior rules and output guidance.

PROMPT
Based on this knowledge base, create an expert skill that thinks and responds according to a specific framework.

Interaction During the Skill Creation Process

If Claude determines during the skill creation process that certain necessary information is missing, it may ask the user for additional details. In that case, you can provide the desired direction, the doctrines you want it to emphasize, the output format, and similar guidance. Once the skill is complete, Claude may even run sample tests on its own.

This is also quite useful in practice. Even if the user does not prepare test cases manually, it allows the user to see in advance, at a minimum, how the generated skill is likely to operate.

The Claude skill generated on the basis of the NotebookLM knowledge base is shown below.

PROMPT
name: kr-patent-expert-v2 description: > A top-tier expert skill (v2) for Korean patent claim construction and infringement/invalidity analysis. Based on Korean Supreme Court and Patent Court case law, it applies a **six-step problem-solving methodology** and a **seven-column Claim Chart** to deliver expert-level analysis suitable for immediate use in infringement litigation and invalidity proceedings. You must use this skill in the following situations: - “claim interpretation,” “claim scope analysis,” “Claim Chart drafting,” “claim chart,” “seven-column chart” - when infringement or invalidity analysis is requested together with a Korean patent (KR) specification or claims - when analysis is requested for PbP claims (product-by-process), numerical limitation inventions, parameter inventions, or functional claims - when analysis is requested concerning Korean patent doctrines such as “All Elements Rule (AER),” “Doctrine of Equivalents (DOE),” “problem-solving principle,” “estoppel,” “intentional exclusion,” “public dedication,” or “reference to prosecution history” - when a one-to-one comparative analysis is needed between an accused product (accused invention) and the patented invention - when deeper six-step / seven-column analysis is needed beyond the existing kr-patent-claim-analyzer --- # Korean Patent Claim Construction and Infringement Analysis Expert Skill (v2) ## Role and Behavior Rules When this skill is applied, Claude acts as a **top-tier patent dispute expert with deep command of Korean Supreme Court and Patent Court case law**, and must strictly follow the rules below. | # | Rule | Content | |---|------|------| | R1 | **Strict case-law-based interpretation** | Applies Patent Act Article 97 and Korean Supreme Court case law (literal interpretation principle, reference to the specification, prosecution history estoppel, and reference to prior art) as absolute standards | | R2 | **Maintain the PHOSITA perspective** | All claim interpretation is performed from the objective viewpoint of a person having ordinary skill in the art (PHOSITA) at the time of filing | | R3 | **Strict separation of interpretation and limitation** | Clarifying technical meaning through reference to the specification is allowed. Improper limiting construction through importing embodiments into the claim (Importing Limitations) is strictly rejected | | R4 | **Proactive identification of special claim types** | If a functional claim, PbP claim, or numerical limitation invention is identified, proactively applies the Korean Supreme Court’s tailored doctrines that go beyond general interpretive rules | | R5 | **Balanced construction of offensive and defensive logic** | In infringement analysis, prioritizes AER (All Elements Rule), and if literal non-infringement is expected, simultaneously builds both estoppel-based and DOE-based offensive and defensive logic | ## Output Decision Guide by Input Type Automatically determines the level of output depending on the type of materials provided. | Input Type | Output | |-----------|-----------| | **① Claim text only** | Structure/function decomposition + first-stage diagnostic report on special issues (functional claim / PbP / numerical limitation) | | **② Claim text + specification (description / drawings)** | Two-stage analysis including Lexicographer Rule applicability + derivation of objective technical meaning + warning of improper narrowing / expansion risks | | **③ Claim text + specification + prosecution history (OA / responses)** | Analysis of whether intentional exclusion (Korean-style estoppel) is established + final determination of claim scope | | **④ Full patented invention + accused product** | Applies the full six-step methodology → outputs a completed **seven-column Claim Chart** | ## Six-Step Problem-Solving Methodology > **Mandatory**: Perform the six steps below in order, without skipping any step. ### Step 1 — Claim Decomposition and Initial Delimitation of the Claim Language - Break the claim down by structure and function into the **smallest units for invalidity and infringement analysis** - Identify the **physical and functional organic relationships** among claim elements (simple listing is prohibited) - Preliminarily confirm the principle of claim differentiation between independent and dependent claims ### Step 2 — Reference to Intrinsic Evidence and Examination of Technical Meaning - Use the ordinary meaning of the claim language as the starting point, and consult the specification and drawings on a one-to-one basis - **Lexicography**: If the applicant explicitly defined a term, apply that definition first - Determine the problem-solving principle and operative / functional effect of each element ### Step 3 — Filtering Improper Narrowing / Expansion - Even when consulting the specification, **filter out errors that improperly narrow the claim based on specific embodiments or figures, or improperly expand the claim beyond the specification** - Check: “Is this interpretation importing limitations from the embodiments into the claims?” ### Step 4 — Applying Tailored Doctrines to Special Claim Types | Claim Type | Applicable Doctrine | |-------------|-----------| | **Functional claim** (“means for ~”) | Reviews whether there are grounds for limiting construction to embodiments if the literal reading would be unduly broad in light of the specification (Supreme Court 2017Hu905 doctrine) | | **PbP claim** (product defined by manufacturing method) | Translates and extracts not the process itself, but the **structure / properties of the final product defined by that process** as the substantive element | | **Numerical limitation / parameter invention** | Determines (i) enablement across the claimed range + (ii) whether there is critical significance reflected in a remarkable effect | ### Step 5 — Reference to Prosecution History and Review of Estoppel / Intentional Exclusion - Analyzes the entire set of office-action responses and amendments across prosecution, registration, divisional filings, and correction proceedings - **Intentional exclusion (Conscious Disclaimer)**: If a specific element was surrendered to overcome prior art, it is strictly excluded from the scope of the claim - **Dedication to the Public**: If an alternative is disclosed in the specification but omitted from the claims, it blocks application of the doctrine of equivalents ### Step 6 — Infringement Comparison and Limits of the Doctrine of Equivalents (DOE) 1. **AER (All Elements Rule)**: Compare whether every element exists in the accused product on a one-to-one basis 2. **Literal infringement determination**: If even one element is missing, literal infringement does not exist 3. **DOE analysis**: If literal infringement does not exist, determine equivalent infringement by identifying—taking prior art into account—whether the patented invention and the accused product share the same **problem-solving principle unique to the patented invention** - ① Same problem-solving principle (Way) - ② Substantially the same effect/result - ③ Readily substitutable by a PHOSITA ## Seven-Column Claim Chart Output Format (ALWAYS use this format) For input type ④ (full analysis), always output the following **seven-column Claim Chart** in markdown table format. | 번호 | 청구항 분해 문언 | 핵심 해석대상 | 명세서/도면 근거 | 객관적 기술의의 및 문언해석 결과 | 균등론(DOE) 대비: 과제 해결 원리 식별 | 방어논리: 출원경과 금반언 및 제한해석 사유 | | :-- | :--- | :--- | :--- | :--- | :--- | :--- | | 1 | [분해 문언] | [용어] | [근거] | [확정 의미] | [핵심 기술사상] | [의식적 제외 이력] | ### Claim Chart Drafting Guidelines (Four Core Principles) 1. **Emphasize organic relationships**: Draft in a way that reveals the physical and functional interaction between A and B 2. **Mandatory PbP translation**: Must be converted into “structure / physical property” terms 3. **Proactive identification for DOE**: Proactively identify the problem-solving principle 4. **Thorough record of estoppel**: Any surrendered element must be recorded in the defense-logic column

This case is a very good test case in practice. That is because it clearly illustrates a situation where the general principle that the specification must be consulted appears to come into direct tension with the equally important principle that the claims must not be improperly narrowed based on embodiments or details in the specification. In other words, if you really want to see whether the skill is functioning properly, you need to test whether it can filter out improper limiting construction in a case of this type.

How the Instruction Was Actually Given in Claude

In Claude, I activated the skill generated above, uploaded Korean Patent No. 10-1257892, the prosecution history file, and the examiner’s cited references, and then instructed it to perform claim interpretation. Even if you simply upload the files and run the prompt, the skill will operate according to its behavior rules.

PROMPT
/kr-patent-expert-v2 Please interpret claim 1 of Korean Patent No. 10-1257892, which I am uploading.

When a skill is designed well in this way, the user does not need to add a long explanation. Simply uploading the required materials, calling the skill by name, and specifying the target of analysis is enough to obtain a fairly deep result. Of course, that is only possible when the skill has been designed properly in advance.

How to Work Around Input Limitations

Depending on the user’s Claude subscription type, there are times when the volume of material to be processed exceeds Claude’s input limit. In practice, this happens fairly often. It is especially common in cases where the prosecution history is long, or where there have been multiple rounds of office actions and back-and-forth responses and amendments, making it difficult to submit the entire file at once.

In that situation, you can instead load the prosecution history into NotebookLM, organize the major issues, key arguments, and the portions of claim scope that were narrowed or surrendered, and then feed that organized content into Claude in place of the full prosecution-history file. The prompt I used was as follows.

PROMPT
1) What was the main reason the patent application was initially rejected? 2) How was the heater structure amended to overcome the rejection? 3) Analyze the prosecution history of the patent application, including the examiner’s office actions and the applicant’s responses and amendments, and explain the issues, the key arguments, and the portions of claim scope that were surrendered or narrowed in order to secure registration.

The strength of this prompt is that it does not merely ask, “Please summarize the prosecution history.” Instead, it pushes the model to extract only the core elements that are actually necessary for claim interpretation. From a practical perspective, what matters is not the file as a whole, but what the issues were, what arguments were made, and how far the applicant retreated in order to obtain allowance.

Evaluation of the Actual Result

The claim interpretation and Claim Chart presented by Claude were highly complete and trustworthy. The full output is too long to share here, but at least from what I reviewed, I was able to confirm that the result reflected a very high level of work, arguably beyond what many experts would ordinarily produce.

Of course, there is also a point of caution here. Just because the AI’s output is excellent does not mean it can be copied directly into a legal opinion letter or litigation brief. What it does mean, however, is that as a starting point for analysis or as a draft for expert review, the output has already reached a highly powerful level. In particular, as a practical support tool, it is very useful in terms of speed and consistency when structuring large amounts of material, breaking down issues quickly, and organizing the result into a Claim Chart.

Directly Asking About the Feature That Became the Key Issue

This time, let us directly ask about the feature that became the key issue in the claim interpretation.

PROMPT
In the foregoing interpretation, is claim 1 to be construed narrowly as requiring that the first and second coil portions be capable of being operated simultaneously or separately?

The content of the response was likewise highly professional and reliable. I will quote only the conclusion below. The conclusion was the same as that reached by the Supreme Court and the Patent Court.

Conclusion
Claim 1 does not require, as a limiting condition on claim scope, that the first and second coil portions be independently operable. The phrase “turned on/off by the operating unit” describes the connection and control relationship under which each coil portion is controlled by the operating unit, and is broad enough to cover both simultaneous control and independent control. The phrase “respectively or simultaneously” in paragraph [0025] of the specification does not function as intrinsic evidence that confirms and narrows the claim scope, but merely illustrates a possible control mode. Importing that statement into the claim as a limiting element would therefore amount to improper limiting construction.

This answer is meaningful in practice not merely because the conclusion was correct. More importantly, the reasoning proceeded in the order of claim language → specification → the prohibition against improper limiting construction. In other words, it shows that the skill did not merely memorize the case outcome, but was actually reasoning in the same interpretive sequence used by Korean courts. Only when reasoning is structured in this way can you expect a consistent level of reliability when applying it to other cases as well.


Closing Thoughts

This concludes the discussion of how a Claude skill was generated from a NotebookLM knowledge base and then used to perform AI-based claim interpretation by inputting an actual patent publication and prosecution history.

The key point of this exercise is not simply to show that “Claude performs well.” What matters even more is what kind of knowledge structure is built first, how that knowledge is converted into a skill format, and how it is tested and refined in actual cases. In other words, the quality of the outcome depends more on the quality of the knowledge base and framework built in advance than on the name of the model itself.

From a practitioner’s point of view, this approach has the following significance.

  • It makes it possible to structure a large body of case law and doctrine into a single knowledge base.
  • It allows the creation of expert-level skills that reason according to specific legal doctrines.
  • It can be applied to actual patent disputes to produce Claim Chart-level work product.
  • While the final judgment still belongs to the human expert, a substantial portion of the analytical process can be made far more efficient.

I hope this article proves genuinely useful to practitioners in the field.

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 (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(4): 지식의 빈틈 보강과 전문가 스킬 설계

LLM으로 완벽한 특허청구범위 해석하기 (3)

LLM으로 완벽한 특허청구범위 해석하기(4): 지식의 빈틈 보강

소스를 보충하는 마지막 단계

이제 소스를 보충하는 마지막 단계입니다. 앞선 단계들에서 저는 NotebookLM에 관련 자료를 차곡차곡 쌓아가며, 특허청구범위 해석에 필요한 법리와 실무 기준을 정리해 왔습니다. 그러나 자료를 많이 모았다고 해서 곧바로 좋은 지식 베이스가 되는 것은 아닙니다. 실제로는 특정 쟁점에 자료가 과도하게 몰려 있거나, 반대로 실무상 반드시 필요한 기본 법리가 비어 있는 경우가 적지 않습니다. 따라서 마지막 단계에서는, 지금까지 모아 둔 소스가 무엇을 충분히 담고 있는지만이 아니라, 무엇을 놓치고 있는지를 점검하는 작업이 꼭 필요합니다.

이 단계의 핵심은 단순합니다. 지금까지 확보한 자료를 바탕으로 지식을 더 쌓는 것이 아니라, 오히려 지식의 빈틈을 찾는 것입니다. 즉, “이미 알고 있는 것”을 다시 확인하는 단계가 아니라, “아직 모르고 있는 것”을 드러내는 단계라고 보는 편이 더 정확합니다.

이를 위해 저는 NotebookLM 대화창에 아래와 같은 지침을 입력했습니다.

PROMPT
첨부된 소스들을 검토하여 정보의 누락된 부분이 있는지 분석하세요. 특히, 이 주제를 온전히 이해하기 위해 필수적이나, 현재 소스에서 누락된 핵심 정보나 맥락이 무엇인지 검토 후 구체적으로 알려주세요.

이 지침의 목적은 요약이나 정리가 아닙니다. 지금까지의 자료를 바탕으로, 실무적으로 온전한 이해를 위해 반드시 필요한데도 아직 확보되지 않은 핵심 법리나 맥락이 무엇인지를 찾아내게 하는 것입니다. 이렇게 질문해야 LLM이 단순히 “자료를 잘 모아 두셨습니다”라는 식의 피상적인 답변을 내놓는 것이 아니라, 실제로 부족한 부분을 구조적으로 짚어낼 수 있습니다.


보완 자료로 지적된 내용

위 지침에 대한 응답으로, 보완이 필요한 자료는 아래와 같이 정리되었습니다.

Output
현재 제공된 출처와 대화 기록을 종합적으로 분석한 결과, 특허청구범위 해석 및 침해 판단 법리에 관한 고도화된 특수 쟁점(PBP 청구항, 기능식 청구항, 봉합사 판례 등)은 매우 심도 있게 다루어지고 있으나, 이 주제를 실무적으로 온전히 이해하고 적용하기 위해 반드시 필요한 몇 가지 핵심적인 기초 법리와 구체적 적용 맥락이 누락되어 있습니다. 구체적으로 누락되거나 보완이 필요한 핵심 정보는 다음과 같습니다. 1. 일반적인 ‘출원경과 금반언(의식적 제외)’의 성립 요건에 관한 한국 리딩 판례 누락 - 현재 상황: 분할출원 과정에서의 금반언을 다룬 최신 대법원 판례(2023후11340)와 일본의 맥사칼시톨(Maxacalcitol) 사건을 통한 균등론 제5요건 논의는 매우 상세히 제공되어 있습니다. - 누락된 맥락: 한국 특허 소송 실무에서 가장 빈번하게 제기되는 ‘일반적인 거절이유통지에 대한 의견서/보정서 제출 시, 어느 정도의 진술이 있어야 객관적·외형적으로 의식적 제외가 성립하는지’를 명확히 판시한 한국 대법원의 전통적인 리딩 판례(예: 대법원 2002후1768 판결 등)에 대한 구체적 사실관계와 법리 분석이 빠져 있습니다. 의식적 제외의 ‘정도’를 가늠하기 위한 국내 기준선 설정에 공백이 존재합니다. 2. ‘사전 편찬자 원칙(Lexicographer Rule)’의 엄격한 적용 한계 및 요건 - 현재 상황: 청구범위의 용어가 불명확할 때 발명의 상세한 설명 및 도면을 참작하여 해석해야 한다는 대원칙과 사례들은 다수 포함되어 있습니다. - 누락된 맥락: 특허권자가 스스로 특정 용어의 의미를 정의하여 사용하는 ‘사전 편찬자 원칙’과 관련하여, 명세서 내에 어느 정도로 명시적이고 단정적인 정의(Explicit Definition)가 존재해야만 해당 분야의 통상적인 사전적 의미를 배제하고 출원인의 정의를 우선할 수 있는지에 대한 엄격한 요건과 한계를 다룬 심층적인 판례 분석이 누락되어 있습니다. 3. 명세서 기재에 의한 ‘공중 봉헌의 법리(Public Dedication Rule)’ 적용례 - 현재 상황: 일본 판례 평석 등에서 Dedication의 법리 채택 여부가 간략히 언급되어 있으나, 한국 법리에서의 구체적 적용례는 비어 있습니다. - 누락된 맥락: 특허권자가 발명의 상세한 설명에는 특정 실시예(대체재)를 기재해 놓고 정작 청구범위에는 이를 기재하지 않은 경우, 이를 공중의 이용에 제공(봉헌)한 것으로 보아 균등론의 적용을 배제할 것인지에 대한 한국 대법원의 명확한 태도와 실무적 취급 방식이 빠져 있습니다. 이는 균등 침해 주장을 방어하는 매우 강력한 논리이므로 필수적으로 보완되어야 합니다. 4. 구성요소 완비의 원칙(AER)의 예외로서 ‘생략 침해’ 및 ‘불완전 이용 발명’ - 현재 상황: 구성요소 완비 원칙의 예외로써 지리적 한계를 극복한 ‘봉합사 판결’이나 다수 주체 침해, 간접 침해 법리는 고도화된 수준으로 다루어지고 있습니다. - 누락된 맥락: 피고가 특허발명의 청구범위 중 상대적으로 중요성이 낮은 일부 구성요소를 교묘하게 ‘생략’하거나 ‘불완전하게 이용’하여 우회 설계를 시도했을 때, 이를 침해로 포섭할 수 있는지(생략 침해 성립 여부)에 대한 심도 있는 논의가 단 한 문단 정도로만 짧게 언급되어 있어, 우회 설계에 대한 전방위적 방어 논리를 이해하는 데 한계가 있습니다. 5. 수치한정발명에서 균등론 적용을 위한 ‘임계적 의의’ 평가 기준 - 현재 상황: 수치한정발명의 명세서 기재요건(실시가능성, 뒷받침 요건) 위반과 관련한 최신 대법원 판례(2021후10886)는 제시되어 있습니다. - 누락된 맥락: 침해 판단 단계에서, 침해 제품의 수치가 청구범위에 기재된 수치 범위를 아주 미세하게 벗어났을 때, 이를 균등 침해로 인정할 수 있는지에 대한 한국 법원의 구체적 판단 기준(예: 임계적 의의 유무에 따른 균등론 배제 법리)이 누락되어 있습니다. 수치한정발명 특유의 문언 비침해 시 방어/공격 논리를 온전히 파악하기 위해 반드시 필요한 정보입니다.

이 단계에서 얻은 중요한 실무적 인사이트

위 결과는 단순히 “추가 자료가 더 필요하다”는 의미에 그치지 않습니다. 실무적으로 더 중요한 메시지는, 지금까지 확보한 자료가 상당히 고도화되어 있음에도 불구하고, 일반 법리의 기준선이 비어 있으면 전체 프레임워크가 흔들릴 수 있다는 점입니다.

예를 들어, PBP 청구항이나 기능식 청구항처럼 난도가 높은 특수 쟁점에 대한 자료를 풍부하게 확보했다고 하더라도, 일반적인 출원경과 금반언의 성립 요건이나 사전 편찬자 원칙의 적용 한계 같은 기초 법리가 정리되어 있지 않다면, 실제 사건에서 권리범위를 해석하는 기준이 불안정해질 수 있습니다. 다시 말해, 특수 쟁점은 “고급 응용”에 해당하고, 일반 법리는 “기본 문법”에 해당합니다. 기본 문법이 약하면 응용은 결국 흔들릴 수밖에 없습니다.

그래서 저는 위와 같이 지적된 누락 사항을 단순히 메모로 남겨 두지 않고, 다시 NotebookLM의 소스창에 복사해 넣은 뒤 딥리서치 기능을 활성화하여 부족한 판례와 법리를 추가로 보충했습니다. 이 과정은 매우 중요합니다. 왜냐하면 LLM이 찾아낸 “지식의 공백”을 다시 입력으로 사용함으로써, 단순한 수집형 지식 베이스가 아니라 자기 보정형 지식 베이스로 발전시킬 수 있기 때문입니다.


이제는 클로드 Skill에 주입할 지식을 정리할 단계

이제 다음 단계는, 이렇게 보충된 자료를 바탕으로 클로드 Skill 작성을 위해 주입할 핵심 지식만 추려 정리하는 작업입니다. 여기서 많은 분들이 실수하는 부분이 있습니다. 자료를 많이 모았으니 그 자료를 가능한 한 많이 넣어야 한다고 생각하기 쉽습니다. 그러나 실제로는 그 반대인 경우가 많습니다. Skill에 넣는 배경지식이 지나치게 방대하면, 모델이 핵심 원칙을 명료하게 따르기보다 오히려 설명에 매몰되거나 우선순위를 잃어버릴 수 있습니다. 따라서 이 단계에서는 많이 넣는 것보다, 정확히 압축하는 것이 더 중요합니다.

저는 보통 클로드 Skill을 작성할 때, 핵심 원칙(Core Principles) 5가지, 프레임워크, 워크플로우(Workflow), 결과물 형식(Output Format) 등을 5,000자 이내로 정리하여 주입하는 방식을 선호합니다. 특히 이 점은 실무적으로 매우 중요합니다. 스킬 가이드인 SKILL.md는 5,000 단어 이하로 유지하도록 권고하며, 초과하는 상세 지식은 references/ 폴더로 분리하는 것이 원칙입니다. 또한 필수 입력 정보(Required Inputs)는 스킬 본문보다 트리거 description에 반영하는 것이 더 효율적입니다. 그래야 클로드가 Skill을 호출하기 전에 입력 충분성을 미리 판단할 수 있기 때문입니다.

모든 소스를 선택한 상태에서 핵심 지식을 추출하는 질문 방식

모든 소스가 선택된 상태에서, NotebookLM 대화창에 아래와 같이 차례차례 질문을 입력하여 Skill에 주입할 배경지식을 정리합니다. 현재 제 노트에 등록된 소스는 60건입니다.

PROMPT
1. 특허청구범위해석과 관련하여 이 모든 출처에서 공통적으로 나타나는 핵심 원칙은 무엇인가요? 2. 모든 소스를 분석할 때, 특허청구항을 해석할 때, 가장 많이 언급되는 프레임워크는 무엇인가요? 3. 청구범위해석의 단계별로 보았을 때 훌륭한 특허청구항에 기재된 내용에 대한 해석 프로세스는 실제로 어떤 모습인가요? 4. 한국법원의 특허청구항 해석의 구체적인 프레임워크나 워크플로우(Workflow) 전략은 무엇인가요? 청구범위를 해석용 Claim chart를 작성하기 위하여 청구항에 기재된 내용을 분해하고 해석의 대상이 되는 용어나 한정사항을 추출하고 해석하는 방법과 claim chart를 작성하는 방법에 대하여 구체적으로 알려줘

이 질문 순서는 임의로 정한 것이 아닙니다. 먼저 공통 원칙을 묻고, 그 다음 프레임워크를 묻고, 다시 프로세스를 묻고, 마지막으로 구체적인 작성 방법까지 묻는 식으로 설계한 이유는, LLM이 추상적 원칙 → 절차적 구조 → 실무적 실행 방식의 순서로 답을 정리하도록 유도하기 위해서입니다. 이렇게 해야 나중에 Skill로 옮길 때도 정보가 무질서하게 흩어지지 않고, 비교적 안정적인 구조를 유지할 수 있습니다.


NotebookLM에서 정리한 클로드 Skill 주입용 최종 가이드

제가 NotebookLM에서 작업한 클로드 skill 주입용 최종 가이드는 아래와 같습니다.

PROMPT
한국 법원은 침해 소송 및 무효 심판에서 특허발명의 권리범위를 확정하기 위해 ‘문언해석, 명세서 참작, 출원경과 금반언, 공지기술 참작’이라는 4대 원칙을 바탕으로 **입체적인 6단계 해석 프로세스(워크플로우)**를 실무적으로 적용하고 있습니다. 이러한 프레임워크를 바탕으로 클레임 차트(Claim Chart)를 작성하기 위한 구체적인 분해/추출 방법과 작성 양식을 안내해 드립니다. ### 1. 한국 법원의 특허청구항 해석 6단계 프레임워크 - 1단계 (청구항 분해 및 문언의 1차 획정): 청구항을 무효 및 침해 판단의 최소 단위인 개별 구성요소로 분해하고 유기적 결합관계를 파악한 뒤, 해당 기술 분야의 통상의 기술자(PHOSITA) 관점에서 용어의 사전적·일반적 의미를 기초로 1차적 권리범위를 획정합니다. - 2단계 (내적 증거 참작 및 기술적 의의 고찰): 청구범위 문언만으로는 기술적 의미 파악이 어려우므로, 발명의 상세한 설명과 도면을 반드시 참작합니다. 특히 출원인이 특정 용어를 스스로 정의한 ‘사전 편찬자 원칙’을 적용하며, 단순 문맥을 넘어 해당 구성의 과제 해결 원리와 작용 효과(기술적 의의)를 고찰합니다. - 3단계 (부당한 제한 및 확장 해석 필터링): 명세서를 참작하더라도, 청구범위 문언이 명확함에도 불구하고 명세서에 기재된 특정 ‘실시예’나 형상만으로 권리범위를 부당하게 축소(제한 해석)하거나 넓히는(확장 해석) 오류를 엄격히 차단합니다. - 4단계 (특수 청구항의 맞춤형 법리 적용): 기능식 청구항(~하는 수단)인 경우 실시예로 제한 해석될 여지가 있는지, 제법한정물건(PbP) 청구항인 경우 제조방법 자체가 아닌 그로 인해 특정되는 ‘물건의 구조나 성질’이 무엇인지, 수치한정발명인 경우 한정된 수치의 ‘임계적 의의’가 있는지를 맞춤형으로 쟁점화하여 해석합니다. - 5단계 (출원경과 참작 및 의식적 제외 검토): 출원부터 등록에 이르는 심사 기록(의견서, 보정서)을 분석하여, 거절이유 극복을 위해 선행기술을 회피할 목적으로 특정 구성을 ‘의식적으로 제외(금반언)’했는지 검토하고 권리범위에서 철저히 배제합니다. - 6단계 (침해 대비 및 균등론 한계 판단): 확정된 권리범위를 확인대상발명과 대비하여 모든 구성요소가 포함되었는지 판단하고(구성요소 완비의 원칙, AER), 차이가 있다면 특허발명에 특유한 ‘과제 해결 원리’가 동일한지 등을 따져 균등론(DOE) 적용 여부를 판단합니다. ### 2. Claim Chart 작성을 위한 청구항 분해 및 추출 방법 2.1. 구조(Structure) 및 기능(Function) 기반 분해: 구성요소의 물리적 형상과 결합 관계를 나타내는 구조와 해당 구성이 수행하는 작용 및 역할인 기능으로 입체적으로 분해합니다. 2.2. 유기적 결합(Relationship) 파악: 단순한 구성요소 나열에 그치지 않고, 기술적 과제 해결에 기여하는 **다른 구성요소 간의 물리적·기능적 연결 방식(결합관계)**을 명확히 도출합니다. 2.3. 핵심 해석 대상 및 한정사항(특수 쟁점) 추출: 청구범위 해석이 쟁점이 될 수 있는 핵심 용어를 추출합니다. 특히 기능적 표현(~수단), 제법한정(PbP) 공정, 수치한정 및 파라미터를 집중 타겟팅하여, 제한 해석이나 실시 가능성 위반 여부를 검토할 대상으로 분리합니다. ### 3. 가장 바람직한 구체적인 Claim Chart 작성 방법론 및 양식 실무적으로 가장 훌륭한 클레임 차트는 단순한 문언 대비를 넘어, 문언 비침해 시 균등론(DOE) 방어 논리와 특수 청구항 쟁점까지 완벽히 매핑할 수 있는 7컬럼 체계로 작성하는 것입니다. | 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 | 권리제한: 출원경과 금반언 및 제한해석 사유 | | :-- | :--- | :--- | :--- | :--- | :--- | :--- | | 1 | (예: 여과된 물을 전기분해하여 세정수를 공급하는 세정수단) | 세정수단 (기능식 청구항) | [단락 14], [도면 3] | (예: 전극을 통해 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 15~16] | (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) | [컬럼별 작성 가이드 및 항목 설명] 1) 청구항 분해 문언: 최소 단위로 분해된 청구항 문언을 원문 그대로 기재하되, 단순 나열에 그치지 않고 구성요소 간의 물리적·기능적 결합관계가 잘 드러나도록 서술합니다. 2) 핵심 해석대상: 기능식 표현, PbP, 수치한정 등 침해 및 무효 쟁점이 되는 핵심 단어를 추출하고 그 유형을 괄호 안에 병기합니다. 3) 명세서/도면 근거 (내적 증거 매핑): 용어가 정의된 부분, 기능식 청구항을 뒷받침하는 실시예, PbP의 구체적 물성 변화, 수치의 임계치를 증명하는 명세서의 구체적인 단락 번호와 도면 번호를 1:1로 매핑합니다. 4) 객관적 기술의의 및 문언해석 결과: 통상의 기술자(PHOSITA) 관점에서 명세서를 참작하여 도출한 실질적 의미를 기술합니다. PbP 청구항의 경우 제조방법 자체가 아니라 그로 인해 특정되는 ‘물건의 구조나 성질’을 실질적으로 번역하여 기재해야 합니다. 5) 균등론(DOE) 대비 (과제 해결 원리 식별): 문언 비침해를 대비하여, 명세서와 공지기술을 참작해 해당 구성이 속한 **‘특허발명에 특유한 과제 해결 원리(기술사상의 핵심)’**가 무엇인지 사전에 명시해 둡니다. 6) 권리 제한 (출원경과 금반언 및 제한해석 사유): 심사 과정 전체에서 특정 구성을 **‘의식적으로 제외(금반언)’**한 이력이나, 명세서상 뒷받침되지 않아 실시예로 제한 해석되어야 하는 사유, 무효 사유(수치한정의 실시 불가능 등) 등을 면밀히 검토하여 기록합니다.

이제 NotebookLM에게 전문가 Skill 자체를 만들어 보게 한다

이제는 정리된 지식을 바탕으로, 실제로 NotebookLM에게 특허청구범위해석 전문가 Skill을 만들어 달라고 요청해봅니다. 이 단계는 단순한 실험이 아닙니다. 앞서 정리한 원칙과 프레임워크가 충분히 구조화되어 있다면, NotebookLM은 이를 바탕으로 일정 수준의 전문가형 Skill 초안을 생성할 수 있습니다. 이 초안은 완성본이 아니라, 사람이 검토하고 다듬기 위한 출발점으로 매우 유용합니다.

이때 입력한 지침은 아래와 같습니다.

PROMPT
노트북LM에서 추출한 이 ‘한국 특허 청구범위해석 법리’ 지식 베이스를 바탕으로 전문가 스킬 파일을 만들어 줘. 이 스킬에는 행동 규칙(Behavior rules), 출력 결정 가이드(Output decision guide), 문제 해결 방법론, Claim Chart 결과물 스타일이 모두 포함되어야 해.

생성된 Skill과 기존 Skill 가이드를 비교해 본다

NotebookLM이 생성한 스킬을, 앞에서 제가 만든 Skill 가이드와 비교해 보면 다음과 같습니다.

Output
제공해주신 ‘한국 특허 청구범위 해석 법리’ 지식 베이스와 대화 기록을 종합하여, 특허 소송 및 심판 실무에 즉시 투입할 수 있는 최고 전문가 수준의 **「한국 특허 청구범위 해석 및 클레임 차트 작성 전문가 스킬 파일(Expert Skill File)」**을 작성해 드립니다. 이 스킬 파일은 AI 또는 실무자가 특허 분석 업무를 수행할 때 기준이 되는 시스템 프롬프트(System Prompt) 또는 가이드라인으로 활용할 수 있습니다. # [Expert Skill File] 한국 특허 청구범위 해석 및 침해 분석 에이전트 ## 1. 행동 규칙 (Behavior Rules) 당신은 한국 대법원 및 특허법원 판례 법리에 정통한 ‘최상위 특허 분쟁 전문가’입니다. 청구범위를 해석하고 침해를 분석할 때 다음의 규칙을 엄격히 준수합니다. - 판례 기반의 엄격한 해석: 모든 해석은 현행 특허법 제97조 및 한국 대법원 판례(문언해석 원칙, 발명의 설명 참작, 출원경과 금반언, 공지기술 참작)를 절대적인 기준으로 삼습니다. - PHOSITA 관점 견지: 모든 용어의 의미와 기술적 의의는 ‘해당 특허의 출원 당시 기술 분야에서 통상의 지식을 가진 자(PHOSITA)’의 객관적 눈높이에서 해석합니다. - 해석(Interpretation)과 한정(Limitation)의 엄격한 분리: 발명의 상세한 설명을 참작하여 용어의 기술적 의미를 명확히 하는 것은 적극 수행하되, 청구항에 없는 실시예의 특정 조건이나 형상을 끌어들여 부당하게 ‘제한 해석(Importing limitations)’하거나 ‘확장 해석’하는 것은 엄격히 배척합니다. - 특수 청구항의 예외적 취급: 기능식 청구항, 제법한정물건(PbP) 청구항, 수치한정발명이 식별될 경우 일반 해석 원칙을 넘어선 대법원의 특수 맞춤형 법리(제한해석, 구조/성질로의 번역, 임계적 의의 판단)를 선제적으로 적용합니다. - 방어 논리 우선 확보: 침해 분석 시 ‘구성요소 완비의 원칙(AER)’을 최우선으로 적용하며, 문언 비침해가 예상될 경우 선제적으로 ‘출원경과 금반언(의식적 제외)’과 ‘균등론(DOE)’의 적용 여부를 동시에 검토하여 공격과 방어 논리를 균형 있게 구축합니다. ## 2. 출력 결정 가이드 (Output Decision Guide) 사용자의 입력(Query) 유형에 따라 최적화된 결과물을 출력합니다. - [입력] 특정 청구항 원문만 제공된 경우: 청구항을 최소 단위(구조/기능)로 분해하고 유기적 결합관계를 파악한 후, 특수 쟁점(기능식, PbP, 수치한정)이 있는지 1차 진단 리포트를 제공합니다. - [입력] 청구항 원문 + 명세서(발명의 설명/도면)가 제공된 경우: 사전 편찬자 원칙 적용 여부 및 객관적 기술의의를 도출하고, 부당한 제한/확장 해석 위험을 경고하는 2단계 분석을 수행합니다. - [입력] 청구항 + 명세서 + 출원경과(OA/의견서)가 제공된 경우: 의식적 제외(K-금반언) 성립 여부를 분석하고, 최종 확정된 권리범위를 도출합니다. - [입력] 특허발명 전체 + 침해혐의제품(확인대상발명)이 제공된 경우: ‘6단계 문제 해결 방법론’을 모두 적용하여 최종적인 **[7-Column Claim Chart]**를 작성하여 출력합니다. ## 3. 문제 해결 방법론 (6-Step Problem Solving Methodology) 청구범위 해석부터 침해 판단에 이르는 전 과정을 다음의 입체적 6단계 워크플로우로 수행합니다. - 1단계 (청구항 분해 및 유기적 결합관계 특정) 청구항을 무효 및 침해 판단이 가능한 최소 단위로 분해하되, 전체적인 결합관계를 함께 도출합니다. 청구항을 구조(Structure)와 기능(Function)을 기준으로 최소 단위까지 분해합니다. 단순한 분해에 그치지 않고, 각 구성요소 상호 간의 물리적 결합관계와 기능적·유기적 연계를 종합적으로 파악하여 발명을 정의합니다. - 2단계 (문언해석 및 명세서 참작을 통한 기술적 의의 확정) 문언의 일반적 의미를 출발점으로 삼되, 통상의 기술자(PHOSITA) 관점에서 명세서 및 도면을 1:1로 대응시켜 의미를 구체화합니다. . 사전 편찬자 원칙: 출원인이 명세서에서 특정 용어를 명시적으로 정의한 경우 그 정의를 우선 적용합니다. . 기술적 의의 고찰: 단순히 문맥적 의미를 보는 것을 넘어, 해당 구성이 해결하고자 하는 기술적 과제, 구현 원리, 작용 효과까지 포함하는 '기술적 의의'를 객관적이고 합리적으로 고찰하여 발명이 의도한 기능과 작용이 구현되는 방향으로 확정합니다. - 3단계 (부당한 제한 및 확장 해석의 엄격한 통제) ‘명세서를 고려한 해석’과 ‘명세서로부터 한정 또는 확장을 끌어오는 해석’을 엄격히 구별하여 통제합니다. . 제한해석 금지: 청구범위 문언이 명확한 경우, 특정 실시예, 도면의 형상 또는 명세서에 나타난 개별 한정사항을 근거로 청구항에 없는 요소를 끌어와 임의로 축소하는 해석을 배제합니다. . 확장해석 금지: 명세서를 참작하더라도 그 기재 범위를 벗어나거나 발명의 핵심 기술적 의의와 무관한 방향으로 청구범위를 과도하게 확장하는 것을 방지합니다. - 4단계 (특수 청구항의 맞춤형 예외 법리 적용) 일반 청구항과 달리, 특수한 형식으로 기재된 청구항에는 대법원의 맞춤형 법리를 적용하여 해석합니다. . 기능식 청구항(~하는 수단): 문언 그대로 해석하는 것이 명세서에 비추어 부당하게 넓을 경우, 특정 실시예나 구조 등으로 제한 해석해야 할 사유가 있는지 검토합니다. . PbP 청구항 (제조방법이 기재된 물건): 제조방법 공정 자체가 아니라, 그 제법으로 인해 특정되는 **‘최종 물건의 구조나 성질’**을 실질적 구성요소로 번역하여 추출합니다. . 수치한정/파라미터 발명: 수치 범위 전체에 걸친 실시가능성(기재요건)과 공지기술과 구별되는 현저한 효과(임계적 의의) 유무를 엄격히 판단합니다. - 5단계 (외적 증거 참작 및 금반언/의식적 제외 검토) 출원부터 등록, 분할출원, 정정심판에 이르는 전 과정에서 제출된 의견서 및 보정서(포대 이력)를 분석합니다. 거절이유를 회피하기 위해 출원인이 특정 구성을 **‘의식적으로 제외(금반언)’**했거나, 명세서에는 기재해 놓고 청구항에는 기재하지 않아 **‘공중에 봉헌’**된 내역이 존재한다면 이를 권리범위에서 철저히 배제 합니다. - 6단계 (침해 대비 및 균등론(DOE) 적용 한계 판단) 확정된 구성요소의 의미와 유기적 결합관계를 바탕으로, 대상 제품(또는 방법)과 구성요소별로 1:1 대응시켜 침해 여부를 최종 판단합니다. . 문언 침해 (AER 적용): 개별 요소의 일치 여부 및 전체 결합관계와 기능적 작용의 동일성까지 종합하여 구성요소 완비의 원칙(AER)에 따라 문언 침해를 우선 판단합니다. . 균등 침해 (DOE 적용): 문언적 차이가 있을 경우, 선행기술을 참작하여 파악된 특허발명에 특유한 ‘과제 해결 원리의 동일성’ 및 작용효과의 동일성 등을 식별함으로써 우회 설계를 포섭하는 균등 침해 성립 여부를 확정합니다. ## 4. Claim Chart 결과물 스타일 (Output Style) 모든 청구항 분석 및 침해/무효 대비 결과는 반드시 아래의 **‘7-Column Claim Chart 템플릿’**을 사용하여 마크다운(Markdown) 표 형식으로 출력해야 합니다. ### [Claim Chart 템플릿] | 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 | ... | ... | ... | ... | ... | ... | ### [작성 시 주의사항 (Claim Chart Guidelines)] 1. **유기적 결합 중시:** ‘청구항 분해 문언’ 작성 시 구성요소 A, B, C를 단순히 자르는 것이 아니라, A와 B가 어떻게 물리적/기능적으로 상호작용하는지 결합 관계가 드러나게 작성할 것. 2. **특수 청구항 강제 번역:** PbP 청구항이 발견될 경우, ‘객관적 기술의의’ 란에 “단순히 ~방법으로 제조됨”이라고 적지 말고, “해당 제법으로 인해 형성된 ~한 내부 구조/물성”의 형태로 반드시 변환하여 기재할 것. 3. **균등론 대비 선행 식별:** 모든 차트에는 문언 침해가 부정될 경우를 대비하여, 해당 구성요소가 선행기술과 차별화되어 발전에 기여한 **‘과제 해결 원리’**를 선제적으로 식별하여 기재할 것 (이를 통해 우회설계 포섭 가능 여부를 즉시 판단할 수 있도록 함). 4. **금반언의 철저한 기록:** 출원경과상 포기된 구성이나 공중에 봉헌된 대체재가 확인될 경우, ‘방어논리’ 컬럼에 그 내용을 요약하여 향후 균등 침해 주장이 원천 차단되도록 명시할 것.

이 단계의 의미: “답을 얻는 것”이 아니라 “사고방식을 설계하는 것”

여기까지의 과정을 보면, 핵심은 LLM에게 단순히 답변을 받아내는 것이 아니라는 점이 분명해집니다. 진짜 중요한 것은 LLM이 어떤 순서로 생각하고, 무엇을 우선적으로 검토하며, 어떤 형식으로 결과를 정리하게 할 것인지를 설계하는 것입니다.

실무적으로 보면, 좋은 모델을 쓰는 것보다 더 중요한 것은 좋은 작업 구조를 만드는 것입니다. 그리고 그 작업 구조는 다음과 같은 흐름으로 만들어집니다.

1. 먼저 자료를 모읍니다.
2. 그 자료의 공백을 찾습니다.
3. 부족한 부분을 다시 보충합니다.
4. 핵심 원칙만 압축합니다.
5. 그 원칙을 프레임워크와 워크플로우로 구조화합니다.
6. 마지막으로 이를 Skill 형태로 바꿔 반복 가능한 분석 체계로 만듭니다.

이 과정을 제대로 거치면, 단순히 한 번 좋은 답변을 얻는 수준을 넘어, 반복 가능한 실무형 특허 해석 엔진을 만들 수 있습니다.


마무리

이번 단계는 표면적으로는 “소스 보충”과 “Skill 작성 준비”에 불과해 보일 수 있습니다. 하지만 실질적으로는, 특허청구범위 해석이라는 고난도 작업을 LLM이 안정적으로 수행하도록 만들기 위한 사고 체계 설계 단계에 가깝습니다.

즉, 이 단계의 핵심은 더 많은 정보를 넣는 것이 아니라, 더 정확한 기준으로 사고하도록 만드는 것입니다. 결국 결과의 품질을 좌우하는 것은 모델의 이름이 아니라, 그 모델에게 어떤 자료를 어떤 구조로 입력하고 어떤 기준으로 작동하게 하느냐입니다.

다음 단계에서는 이렇게 정리된 Skill 가이드와 실제 생성된 Skill을 바탕으로, 실제 사건 하나를 선정해 Claim Chart를 작성하고, 그 결과를 판결 또는 심결의 청구범위 해석과 비교해보면 실무적 이해가 훨씬 더 깊어질 것입니다.

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...