The Royal Bank of Canada has patented a system for predicting interdependence between data objects using natural language processing and machine learning. The system extracts entity names and economic relationships from text strings to identify potential interdependencies. It generates an output data structure with linkages between entities. GlobalData’s report on Royal Bank of Canada 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 Royal Bank of Canada, Social commerce was a key innovation area identified from patents. Royal Bank of Canada's grant share as of January 2024 was 87%. Grant share is based on the ratio of number of grants to total number of patents.
Predicting interdependence between entities based on text data
A computer system has been granted a patent for a tool that automatically generates predictions related to interdependence detection between various data objects based on unstructured text inputs. The system includes a data receiver, a computer processor equipped with natural language processing and machine learning engines, and memory. The processor processes text strings to extract entity names and estimated economic relationships, aggregates these relationships to identify potential interdependence, and generates an output data structure with linkages between entities. The machine learning engine converts text into vector representations, pre-processes them, and optimizes hyperparameters for term frequency-inverse document frequency representations.
Furthermore, the system utilizes a Stanford Named Entity Recognizer for natural language processing, decision trees for machine learning, and a white-box estimator trained against a black-box estimator. It appends metadata to vector representations, cross-references output data against client names using a cosine similarity algorithm, and filters out pairs below a threshold value. The method involves receiving text strings, extracting entity names and economic relationships, aggregating them, and generating an output data structure. The system optimizes hyperparameters, utilizes decision trees, and includes a white-box estimator trained with perturbed samples. It also appends metadata to vector representations and cross-references data against client names using cosine similarity. The non-transitory computer-readable medium stores instructions for executing the method, which involves processing text, extracting entity names and economic relationships, aggregating them, and generating an output data structure with linkages between entities. The system optimizes hyperparameters, pre-processes vector representations, and utilizes term frequency-inverse document frequency representations.
To know more about GlobalData’s detailed insights on Royal Bank of Canada, 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.
