BlackRock. has filed a patent for a system and method to generate embeddings using a machine learning framework. The process involves creating a fully connected network from word data, converting correlations into distances, generating sentence structures, and using a neural network to create embeddings for relationship analysis. GlobalData’s report on BlackRock gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on BlackRock, Insurance pricing automation was a key innovation area identified from patents. BlackRock's grant share as of January 2024 was 64%. Grant share is based on the ratio of number of grants to total number of patents.
Generating word embeddings using machine learning framework
The patent application (Publication Number: US20240012997A1) describes a method for generating embeddings using a fully connected network associated with words. The method involves converting correlations into distances, converting the network into a sparse network, traversing nodes to generate sentence structures, and using a neural network to create embeddings in an embedded space. The embeddings are then analyzed to determine relationships between nodes. Additionally, the method includes determining numerical values associated with words at different points in time, calculating logarithmic returns, and determining correlations based on these returns. The system and computer-readable medium described in the patent application also outline similar operations for generating embeddings using a machine learning framework, correlation matrices, distance matrices, and algorithms to traverse networks and generate embeddings.
Overall, the patent application presents a comprehensive method and system for generating embeddings that capture relationships between words based on correlations and distances in a fully connected network. By utilizing sparse algorithms, neural networks, and specific algorithms for traversing networks, the method aims to create embeddings that represent syntactic relationships among words. The application also extends to generating embeddings for stocks based on price correlations. The system and computer-readable medium provide a framework for implementing these operations efficiently. The patent application showcases a novel approach to generating embeddings that could have applications in various fields requiring the analysis of relationships between entities based on correlations and distances.
To know more about GlobalData’s detailed insights on BlackRock, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
