Capital One Financial. has filed a patent for systems and methods enabling database search using word embeddings. The technology involves generating vector representations of words in input documents, determining similarity metrics with stored documents, and displaying a ranked list of relevant documents in response to a search query. GlobalData’s report on Capital One Financial gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Capital One Financial, Virtual banking assistant was a key innovation area identified from patents. Capital One Financial's grant share as of January 2024 was 53%. Grant share is based on the ratio of number of grants to total number of patents.

Database search method using word embeddings for similarity ranking

Source: United States Patent and Trademark Office (USPTO). Credit: Capital One Financial Corp

A patent application (Publication Number: US20240037326A1) describes a method and system for improving search query results by utilizing word embeddings and similarity metrics. The method involves receiving a search query with an input document, generating initial word embeddings, updating them based on predicted and actual words, determining an average input document word embedding vector, accessing stored documents with their own average word embeddings, and using a similarity model to rank and display the most relevant stored documents in response to the search query. The system includes a processor executing software instructions to perform these steps, enhancing search accuracy and user experience.

Furthermore, the patent application details additional features such as utilizing a word vectorization model, receiving user feedback on similarity metrics, calculating similarity errors, training parameters for optimization, generating similarity alerts, and executing activities based on ranked stored documents. The system can handle various document types, including regulatory requirements and business controls, and incorporates clustering models and k-d trees for efficient document retrieval. By storing new documents with associated word embeddings and optimizing similarity metrics, the method and system aim to provide users with more accurate and relevant search results, ultimately enhancing information retrieval processes and decision-making based on the ranked list of stored documents.

To know more about GlobalData’s detailed insights on Capital One Financial, buy the report here.

Premium Insights


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.