Product Design, Manufacturing & Innovation Resources

최신 간행물 – Prompt Engineering의 특허

프롬프트 엔지니어링

팁: 아래 선택 항목 외에도, 저희가 제공하는 두 개의 전체 데이터베이스를 검색하고 필터링할 수 있습니다.

> 무료 간행물 검색 도구 < 저자, 주제, 키워드, 날짜 또는 저널별로 검색.

> 무료 특허 검색 도구 < 유럽 ​​특허청의 영문 특허를 참조하십시오.

다음은 프롬프트 엔지니어링, 프롬프트 설계, 컨텍스트화, 프롬프트 가변성, 하이퍼파라미터 튜닝, 편향 완화, 제로샷 학습 및 퓨샷 학습에 초점을 맞춰 분류하고 집중적으로 다룬 전 세계 영어 논문 및 특허 목록입니다. 다양한 온라인 과학 저널에 게재된 자료들을 포함합니다.

Cross directional hyperparameter tuning

Patent published on the 2026-07-02 in US under Ref US20260187481 by AMERICAN EXPRESS INNOVATION LAB LIMITD [IE] (Duggal Manmeet Singh [us], Jangir Rahul [sg], Bansal Hemanshu [in], Kumar Rohit [in], Chanan Shivam [ca], Gupta Saurabh [us], Verma Nishkam [in], Hansda Saptaka [in], Mathur Sumita [in], U Man Chon [us], Shekhawat Ajay Singh [us])

Abstract: Disclosed herein are system, method, and computer program product embodiments for using cross directional hyperparameter tuning. A system identifies a hyperparameter set to configure a first machine learning model, a first evaluation data set, and a machine learning evaluation process. The system determines a first tuned hyperparameter set for the first machine learning model by performing cross directional hyperparameter tuning, including iterating over the set of hyperparameters. At each itera[...]


Our summary: The system identifies a hyperparameter set for a machine learning model and an evaluation data set. It performs cross directional hyperparameter tuning by iterating over selected hyperparameters and their value ranges. The system updates and saves the hyperparameter that yields the highest evaluation score.

hyperparameter tuning, machine learning, evaluation process, optimization

Patent

Statistical methods and large language models for root cause analysis

Patent published on the 2026-07-01 in EP under Ref EP4770028 by JUNIPER NETWORKS INC [US] (Shan Alexander Zhang [us], Singh Rahul [us], Kaur Jasleen [us], Sridhar Thayumanavan [us], Yavatkar Raj [us], Banka Tarun [us])

Abstract: [0001] Techniques are disclosed for using prompt engineering and statistical root cause analysis (RCA) to increase the accuracy of machine learning RCA. In an example, a computing system generates a prompt for root cause analysis of an application-layer anomaly within system of elements across a plurality of layers. The prompt comprises a cross-layer topology graph of the elements across the plurality of layers, diagnostics information for the elements, and a list of the elements and correspondi[...]


Our summary: Techniques utilize prompt engineering and statistical methods for effective root cause analysis. A computing system generates prompts based on cross-layer topology graphs and diagnostics information. The system then employs a machine learning model to identify the root cause of application-layer anomalies.

Root Cause Analysis, Machine Learning, Prompt Engineering, Statistical Methods

Patent

Systems and methods for machine learning operations

Patent published on the 2026-06-04 in WO under Ref WO2026117696 by FIDELITY INFORMATION SERVICES LLC [US] (Ghosh Ranadhir [us], Kumar Gautam [us], Platais John [us])

Abstract: A computer-implemented method for automatically retraining a machine learning system, the method including: receiving a plurality of data objects, the plurality of data objects corresponding to information technology event data and representing an occurrence of an event; processing the plurality of data objects; evaluating whether to perform hyperparameter tuning of a first model of a first machine learning system based on characteristics of the plurality of data objects; training the first mode[...]


Our summary: The method automates the retraining of a machine learning system using IT event data. It processes data objects to evaluate the need for hyperparameter tuning. Finally, it trains and stores a retrained model based on the processed data.

machine learning, retraining, hyperparameter tuning, data processing

Patent

Input/output-component (io-component) for a control device for controlling a device or system

Patent published on the 2026-04-15 in EP under Ref EP4726483 by SIEMENS AG [DE] (Haneder Thomas [de], Lindemann Lars [de], Rost Julian [de])

Abstract: [0001] The present invention describes an input/output-component (IO-component) for a control device for controlling a device or system, wherein the IO-component is designed and set up - for input and/or output of IO control data into and/or out of the control device via a communication link using a communication protocol, - and for connection to a middleware component of the control device, and wherein the IO-component is designed and set up for converting IO control data received via the commu[...]


Our summary: The invention describes an IO-component for a control device that manages input and output of control data. It converts IO control data into middleware variables independent of the communication protocol. The conversion process includes normalization, standardization, logical structuring, and contextualization of the data.

IO-component, control device, communication protocol, middleware variables

Patent

A Method for 3D Building Individualization Integrating SAMPolyBuild and Multiple Spatial-Geometric Features

Published on 2026-02-03 by Lianshuai Cao, Yi Cheng, Zheng Zhang, Ge Zhu, Kunyang Ma, Xinyue Xu @MDPI

Abstract: Individualization of buildings is one of the key issues in the establishment of three-dimensional (3D) building models. Most existing individualization methods rely on inefficient manual separation, while deep learning approaches require extensive pre-training and are highly influenced by the spatial structure of the models. To address these issues, this paper proposes a novel method for 3D building individualization that integrates SAMPolyBuild with multiple spatial-geometric features. Leveragi[...]


Our summary: This paper presents a method for 3D building individualization that integrates SAMPolyBuild with spatial-geometric features. The approach utilizes zero-shot learning for initial extraction and refines accuracy through statistical parameters. Experiments show effective extraction of building models, achieving an F1-score of about 0.83.

3D Building Individualization, SAMPolyBuild, Spatial-Geometric Features, Zero-Shot Learning

Publication

Deep Reinforcement Learning-Driven Adaptive Prompting for Robust Medical LLM Evaluation

Published on 2026-02-02 by Dong Ding, Wang Xi, Zenghui Ding, Jianqing Gao @MDPI

Abstract: The accurate and reliable evaluation of large language models (LLMs) in medical domains is critical for real-world clinical deployment, automated medical reasoning, and patient safety. However, the evaluation process is highly sensitive to prompt design, and prevalent reliance on fixed or randomly sampled prompt policies often fails to dynamically adapt to clinical context, question complexity, or evolving safety requirements. This article presents a novel reinforcement learning-based framework [...]


Our summary: This article introduces a reinforcement learning-based framework for adaptive prompt selection in medical LLM evaluation. It formulates prompt selection as a Markov Decision Process and utilizes a deep Q-Network to enhance evaluation metrics. Experiments show consistent improvements in accuracy, safety, and medical terminology coverage across multiple datasets.

Reinforcement Learning, Prompt Optimization, Medical LLM, Evaluation Framework

Publication

Weak-to-Strong Honesty Alignment via Group-Relative Policy Optimization

Published on 2026-01-30 by Jie Zhang, Yunfan Xie, Wen Zou @MDPI

Abstract: Ensuring that Large Language Models align with human values of honesty is a critical challenge, particularly due to the scarcity of labeled data for distinguishing known versus unknown knowledge boundaries. We propose a weak-to-strong generalization framework utilizing Group Relative Policy Optimization (GRPO). Unlike standard supervised fine-tuning or prompt engineering, our framework trains a lightweight &amp;ldquo;honest head&amp;rdquo; to rank response candidates based on multifacete[...]


Our summary: We propose a weak-to-strong generalization framework for aligning large language models with human honesty values. Our method utilizes Group Relative Policy Optimization to train an "honest head" that ranks response candidates based on honesty scores. Experiments show significant performance improvements over existing methods in honesty alignment across various datasets.

Honesty Alignment, Group Relative Policy Optimization, Large Language Models, Self-labeling

Publication

Tuning for Precision Forecasting of Green Market Volatility Time Series

Published on 2026-01-29 by Sonia Benghiat, Salim Lahmiri @MDPI

Abstract: In recent years, the green financial market has been exhibiting heightened volatility daily, largely due to policy changes and economic shifts. To explore the broader potential of predictive modeling in the context of short-term volatility time series, this study analyzes how fine-tuning hyperparameters in predictive models is essential for improving short-term forecasts of market volatility, particularly within the rapidly evolving domain of green financial markets. While traditional econometri[...]


Our summary: This study analyzes the impact of hyperparameter tuning on predictive models for short-term volatility in green financial markets. It compares machine-learning and deep-learning approaches using various models on daily volatility data. Results show that deep-learning models with optimized hyperparameters significantly improve predictive accuracy.

Hyperparameter tuning, Predictive modeling, Green financial markets, Deep learning

Publication

다룬 주제: 신속한 엔지니어링, 신속한 설계, 맥락화, 신속한 가변성, 하이퍼파라미터 튜닝, 편향 완화, 제로샷 학습, 퓨샷 학습, 증강 현실, 머신 러닝, 이상 탐지, 도시 디지털 트윈, 식물 질병 분류, 언어적 모호성, 텍스트-이미지 모델, ISO/IEC 25010, ISO 9241, ISO/IEC 27001, ISO 9001.

역사적 맥락

2000
2002
2010
2013
2000
2000
2003
2010
2013-09-24

(날짜를 알 수 없거나 관련이 없는 경우, 예를 들어 "유체역학"의 경우, 주목할 만한 등장 시기를 대략적으로 추정하여 제공합니다.)

고화질 이미지 및 다운로드는 등록된 회원에게만 100% 무료로 제공됩니다.

> 로그인 <