Causality-Driven Patent Valuation: Integrating Domain Knowledge and Language Models in a Structured Interview-Like Selection Process

Chuan Wei Kuo; Wen Chih Peng; Hsin Ning Su

doi:10.1007/978-981-96-4589-3_8

Causality-Driven Patent Valuation: Integrating Domain Knowledge and Language Models in a Structured Interview-Like Selection Process

Chuan Wei Kuo, Wen Chih Peng^*, Hsin Ning Su

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Patents are essential for securing market leadership and protecting intellectual property, but traditional valuation methods often fail to fully capture their strategic value. This paper introduces a causality-driven framework for patent valuation that integrates domain expertise with advanced language models in a structured interview-like process. By analyzing semiconductor patents filed between 1997 and 2007-a pivotal period of technological transformation-our approach employs Directed Acyclic Graphs (DAGs) and Structural Equation Models (SEMs) to reveal causal relationships, providing precise value attribution. This integration enhances the analysis of complex patent data, offering a powerful tool for aligning technological innovation with market and legal strategies.

Original language	English
Title of host publication	Technologies and Applications of Artificial Intelligence - 29th International Conference, TAAI 2024, Proceedings
Editors	Wei-Ta Chu, Chih-Ya Shen, Hong-Han Shuai
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	109-123
Number of pages	15
ISBN (Print)	9789819645886
DOIs	https://doi.org/10.1007/978-981-96-4589-3_8
State	Published - 2025
Event	29th International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2024 - Hsinchu, Taiwan Duration: 6 Dec 2024 → 7 Dec 2024

Publication series

Name	Communications in Computer and Information Science
Volume	2414 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	29th International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2024
Country/Territory	Taiwan
City	Hsinchu
Period	6/12/24 → 7/12/24

Keywords

Causality-Driven Analysis
Patent Valuation
Pre-Trained Language Models
Semiconductor Industry
Structured Interview Process

Access to Document

10.1007/978-981-96-4589-3_8

Cite this

Kuo, C. W., Peng, W. C., & Su, H. N. (2025). Causality-Driven Patent Valuation: Integrating Domain Knowledge and Language Models in a Structured Interview-Like Selection Process. In W.-T. Chu, C.-Y. Shen, & H.-H. Shuai (Eds.), Technologies and Applications of Artificial Intelligence - 29th International Conference, TAAI 2024, Proceedings (pp. 109-123). (Communications in Computer and Information Science; Vol. 2414 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-96-4589-3_8

Kuo, Chuan Wei ; Peng, Wen Chih ; Su, Hsin Ning. / Causality-Driven Patent Valuation : Integrating Domain Knowledge and Language Models in a Structured Interview-Like Selection Process. Technologies and Applications of Artificial Intelligence - 29th International Conference, TAAI 2024, Proceedings. editor / Wei-Ta Chu ; Chih-Ya Shen ; Hong-Han Shuai. Springer Science and Business Media Deutschland GmbH, 2025. pp. 109-123 (Communications in Computer and Information Science).

@inproceedings{239fcd35d7614de087ac14ab427c10ed,

title = "Causality-Driven Patent Valuation: Integrating Domain Knowledge and Language Models in a Structured Interview-Like Selection Process",

abstract = "Patents are essential for securing market leadership and protecting intellectual property, but traditional valuation methods often fail to fully capture their strategic value. This paper introduces a causality-driven framework for patent valuation that integrates domain expertise with advanced language models in a structured interview-like process. By analyzing semiconductor patents filed between 1997 and 2007-a pivotal period of technological transformation-our approach employs Directed Acyclic Graphs (DAGs) and Structural Equation Models (SEMs) to reveal causal relationships, providing precise value attribution. This integration enhances the analysis of complex patent data, offering a powerful tool for aligning technological innovation with market and legal strategies.",

keywords = "Causality-Driven Analysis, Patent Valuation, Pre-Trained Language Models, Semiconductor Industry, Structured Interview Process",

author = "Kuo, \{Chuan Wei\} and Peng, \{Wen Chih\} and Su, \{Hsin Ning\}",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.; 29th International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2024 ; Conference date: 06-12-2024 Through 07-12-2024",

year = "2025",

doi = "10.1007/978-981-96-4589-3\_8",

language = "English",

isbn = "9789819645886",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "109--123",

editor = "Wei-Ta Chu and Chih-Ya Shen and Hong-Han Shuai",

booktitle = "Technologies and Applications of Artificial Intelligence - 29th International Conference, TAAI 2024, Proceedings",

address = "德國",

}

Kuo, CW, Peng, WC & Su, HN 2025, Causality-Driven Patent Valuation: Integrating Domain Knowledge and Language Models in a Structured Interview-Like Selection Process. in W-T Chu, C-Y Shen & H-H Shuai (eds), Technologies and Applications of Artificial Intelligence - 29th International Conference, TAAI 2024, Proceedings. Communications in Computer and Information Science, vol. 2414 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 109-123, 29th International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2024, Hsinchu, Taiwan, 6/12/24. https://doi.org/10.1007/978-981-96-4589-3_8

Causality-Driven Patent Valuation: Integrating Domain Knowledge and Language Models in a Structured Interview-Like Selection Process. / Kuo, Chuan Wei; Peng, Wen Chih ; Su, Hsin Ning.
Technologies and Applications of Artificial Intelligence - 29th International Conference, TAAI 2024, Proceedings. ed. / Wei-Ta Chu; Chih-Ya Shen; Hong-Han Shuai. Springer Science and Business Media Deutschland GmbH, 2025. p. 109-123 (Communications in Computer and Information Science; Vol. 2414 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Causality-Driven Patent Valuation

T2 - 29th International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2024

AU - Kuo, Chuan Wei

AU - Peng, Wen Chih

AU - Su, Hsin Ning

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

PY - 2025

Y1 - 2025

N2 - Patents are essential for securing market leadership and protecting intellectual property, but traditional valuation methods often fail to fully capture their strategic value. This paper introduces a causality-driven framework for patent valuation that integrates domain expertise with advanced language models in a structured interview-like process. By analyzing semiconductor patents filed between 1997 and 2007-a pivotal period of technological transformation-our approach employs Directed Acyclic Graphs (DAGs) and Structural Equation Models (SEMs) to reveal causal relationships, providing precise value attribution. This integration enhances the analysis of complex patent data, offering a powerful tool for aligning technological innovation with market and legal strategies.

AB - Patents are essential for securing market leadership and protecting intellectual property, but traditional valuation methods often fail to fully capture their strategic value. This paper introduces a causality-driven framework for patent valuation that integrates domain expertise with advanced language models in a structured interview-like process. By analyzing semiconductor patents filed between 1997 and 2007-a pivotal period of technological transformation-our approach employs Directed Acyclic Graphs (DAGs) and Structural Equation Models (SEMs) to reveal causal relationships, providing precise value attribution. This integration enhances the analysis of complex patent data, offering a powerful tool for aligning technological innovation with market and legal strategies.

KW - Causality-Driven Analysis

KW - Patent Valuation

KW - Pre-Trained Language Models

KW - Semiconductor Industry

KW - Structured Interview Process

UR - https://www.scopus.com/pages/publications/105003858972

U2 - 10.1007/978-981-96-4589-3_8

DO - 10.1007/978-981-96-4589-3_8

M3 - Conference contribution

AN - SCOPUS:105003858972

SN - 9789819645886

T3 - Communications in Computer and Information Science

SP - 109

EP - 123

BT - Technologies and Applications of Artificial Intelligence - 29th International Conference, TAAI 2024, Proceedings

A2 - Chu, Wei-Ta

A2 - Shen, Chih-Ya

A2 - Shuai, Hong-Han

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 6 December 2024 through 7 December 2024

ER -

Kuo CW, Peng WC , Su HN. Causality-Driven Patent Valuation: Integrating Domain Knowledge and Language Models in a Structured Interview-Like Selection Process. In Chu WT, Shen CY, Shuai HH, editors, Technologies and Applications of Artificial Intelligence - 29th International Conference, TAAI 2024, Proceedings. Springer Science and Business Media Deutschland GmbH. 2025. p. 109-123. (Communications in Computer and Information Science). doi: 10.1007/978-981-96-4589-3_8