Innovation Dataset Vectorization for Trend Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing approaches for deep technology innovation management struggle with cross-pollinating innovation datasets to form cohorts of innovators, effectively reuse innovations, assets, and code, and build focused monetization models, due to the complexity and confidentiality of the data.
Innovation Solution
A system that extracts context-based keywords from innovation datasets by transforming them into vectors, searches for semantically relevant keywords, clusters the data to identify frequent keywords, determines weighted keywords, and classifies them to identify emerging innovation trends. The system also recommends relevant content, teams, cohorts, and experts, creates private channels for collaboration, and provides innovation insights to create a semantic knowledge network.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If AI-based or NLP-based approaches are used to extract keywords from the innovation dataset, then the keyword extraction process becomes automated, but the system cannot directly process the dense and abstract nature of the dataset with multiple dimensions, free text data, multiple languages, acronyms, and emojis
Solution Approach 1:
The patent introduces a vector representation as an intermediary between the raw innovation dataset and the keyword extraction process. The dataset is first transformed into vectors through embedding models that can handle multiple languages, acronyms, and emojis, making the data accessible to AI-based keyword extraction algorithms without requiring direct processing of the complex original format.
Solution Approach 2:
The patent changes the representation parameters of the innovation dataset by transforming it into vector space. This parameter transformation converts the dense and abstract multi-dimensional data into a format that can be effectively processed by machine learning models for keyword extraction, thereby enabling automation while managing complexity.
2Ease of operation
If conventional keyword search strategies are used, then the search process is simple, but the system cannot effectively handle the dense and abstract nature of the innovation dataset with multiple dimensions
Solution Approach 1:
The patent replaces conventional mechanical keyword matching with AI-based semantic search using vector embeddings. This substitution allows the system to handle the dense and abstract nature of the innovation dataset by transforming keywords and concepts into vector representations that capture semantic meaning, enabling both simple user interaction and precise relevance measurement.
3Reliability
If the innovation dataset is accessed from multiple distinct systems to maintain confidentiality, then data security is improved, but extensive user collaboration is required to build a team for cross-pollination
Solution Approach 1:
The patent introduces a centralized vector embedding system as an intermediary that can process data from multiple distinct systems while maintaining their confidentiality. The system extracts and transforms keywords from each system into vector representations without requiring direct access to the original data, enabling cross-pollination while preserving security and reducing collaboration complexity.
Data Source
AI summary
Systems and methods for deep technology innovation management by cross-pollinating innovations dataset are disclosed. A system extracts context-based keyword from an innovation dataset by transforming the innovation dataset to a vector. Further, the system searches semantically relevant keywords for the extracted context-based keyword, by extracting an entity and a key phrase from the extracted a context-based keyword. Furthermore, system clusters the vector, by identifying frequent keywords in the semantically relevant keywords to obtain cluster centroids of the frequent keywords. Thereafter, the system determines weighted keywords in each cluster using the obtained cluster centroids, and classifies the weighted keywords to identify emerging innovation trends relevant to the innovation in the innovation dataset. The system forms cohorts of innovators to explore the reuse of innovations, assets, code, and build focused monetization model.