Manish Verma

Manish Verma, Vivek Sharma, Vishal Singh

This paper presents the development of an AI powered software platform that leverages advanced large language models (LLMs) to transform technology scouting and solution discovery in industrial R&D. Traditional approaches to solving complex research and development challenges are often time consuming, manually driven, and heavily dependent on domain specific expertise. These methods typically involve navigating fragmented sources such as patent repositories, commercial product catalogs, and competitor data, leading to inefficiencies and incomplete insights. The proposed platform utilizes cutting edge LLM capabilities including semantic understanding, contextual reasoning, and cross-domain knowledge extraction to interpret problem statements and retrieve high-quality, sustainable solutions. The system processes unstructured patent texts, such as claims and technical descriptions, and systematically extracts potential innovations aligned with the given problem context. These solutions are then algorithmically organized under standardized technical categories and subcategories to ensure clarity and relevance across interdisciplinary domains. In addition to patent analysis, the platform integrates commercial intelligence by identifying validated market solutions and active organizations addressing similar challenges. This combined insight sourced from both intellectual property and real world product data enables R&D teams to assess not only technical novelty but also feasibility, scalability, and sustainability. The result is a comprehensive, AI driven scouting engine that reduces manual effort, accelerates innovation cycles, and enhances decision making in complex R&D environments.

Manish Verma, Vivek Sharma, Vishal Singh

This paper introduces a novel, multi stage hybrid intelligence framework for pruning patent portfolios to identify high value assets for technology transfer. Current patent valuation methods often rely on retrospective indicators or manual, time intensive analysis. Our framework automates and deepens this process by combining a Learning to Rank (LTR) model, which evaluates patents against over 30 legal and commercial parameters, with a unique "Need-Seed" agent-based system. The "Need Agent" uses Natural Language Processing (NLP) to mine unstructured market and industry data, identifying explicit technological needs. Concurrently, the "Seed Agent" employs fine tuned Large Language Models (LLMs) to analyze patent claims and map their technological capabilities. The system generates a "Core Ontology Framework" that matches high potential patents (Seeds) to documented market demands (Needs), providing a strategic rationale for divestment decisions. We detail the architecture, including a dynamic parameter weighting system and a crucial Human in the-Loop (HITL) validation protocol, to ensure both adaptability and real-world credibility.

Tikaram Sanyashi, M. Bhargav Sri Venkatesh, Kapil Agarwal et al.

LWE-based cryptosystems are an attractive alternative to traditional ones in the post-quantum era. To minimize the storage cost of part of its public key - a $256 \times 640$ integer matrix, $\textbf{T}$ - a binary version of $\textbf{T}$ has been proposed. One component of its ciphertext, $\textbf{c}_{1}$ is computed as $\textbf{c}_{1} = \textbf{Tu}$ where $\textbf{u}$ is an ephemeral secret. Knowing $\textbf{u}$, the plaintext can be deduced. Given $\textbf{c}_{1}$ and $\textbf{T}$, Galbraith's challenge is to compute $\textbf{u}$ with existing computing resources in 1 year. Our hybrid approach guesses and removes some bits of the solution vector and maps the problem of solving the resulting sub-instance to the Closest Vector Problem in Lattice Theory. The lattice-based approach reduces the number of bits to be guessed while the initial guess based on LP relaxation reduces the number of subsequent guesses to polynomial rather than exponential in the number of guessed bits. Further enhancements partition the set of guessed bits and use a 2-step application of LP. Given the constraint of processor cores and time, a one-time training algorithm learns the optimal combination of partitions yielding a success rate of 9\% - 23\% with 1000 - 100,000 cores in 1 year. This compares favourably with earlier work that yielded 2\% success with 3000 cores.