Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2025
|
| Online Access: | https://doi.org/10.5281/zenodo.17498292 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866901716476100608 |
|---|---|
| author | Zhang, Jincheng |
| author_facet | Zhang, Jincheng |
| contents | <p><span>With the rapid development of artificial intelligence (AI) technology, AI is increasingly being applied in the legal and judicial fields, encompassing areas such as case judgment prediction, contract review, legal text retrieval, and intelligent question-answering. Traditional legal AI systems, when processing legal knowledge and case studies, face challenges such as legal clause conflicts, nonlinear dependency on judgments, and insufficient risk sensitivity. This paper proposes a heuristic optimization algorithm based on legal semantics guidance (LSGO). By introducing a legal semantic conflict (LSC) mechanism, combined with case fact vectorization, legal knowledge graph path reasoning, and risk-penalty gradients, LSGO achieves multi-objective optimization across legal case prediction, contract clause optimization, and legal text retrieval. The algorithm's fitness function, candidate solution iterative update mechanism, weight adaptive adjustment, and conflict gradient calculation formula are all presented in plain text mathematical form, highlighting the unique features of AI applications in the legal and judicial fields.</span></p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17498292 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Application of Artificial Intelligence in Law and Judicial Systems: A Legal Semantic Guided Optimization Approach Zhang, Jincheng <p><span>With the rapid development of artificial intelligence (AI) technology, AI is increasingly being applied in the legal and judicial fields, encompassing areas such as case judgment prediction, contract review, legal text retrieval, and intelligent question-answering. Traditional legal AI systems, when processing legal knowledge and case studies, face challenges such as legal clause conflicts, nonlinear dependency on judgments, and insufficient risk sensitivity. This paper proposes a heuristic optimization algorithm based on legal semantics guidance (LSGO). By introducing a legal semantic conflict (LSC) mechanism, combined with case fact vectorization, legal knowledge graph path reasoning, and risk-penalty gradients, LSGO achieves multi-objective optimization across legal case prediction, contract clause optimization, and legal text retrieval. The algorithm's fitness function, candidate solution iterative update mechanism, weight adaptive adjustment, and conflict gradient calculation formula are all presented in plain text mathematical form, highlighting the unique features of AI applications in the legal and judicial fields.</span></p> |
| title | Application of Artificial Intelligence in Law and Judicial Systems: A Legal Semantic Guided Optimization Approach |
| url | https://doi.org/10.5281/zenodo.17498292 |