KBC Group has been granted a patent for a computer-implemented method that determines the category of a user request by analyzing natural language text. The system uses word vector representations and similarity measures to generate an action signal for policyholder or customer service devices. GlobalData’s report on KBC Group 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 KBC Group, Digital lending was a key innovation area identified from patents. KBC Group's grant share as of May 2024 was 19%. Grant share is based on the ratio of number of grants to total number of patents.
Determining request category based on natural language text
A recently granted patent (Publication Number: US11972490B2) discloses a computer-implemented method for determining the category of a request provided by a policyholder through a policyholder device. The method involves receiving a request description, identifying component words, obtaining word vector representations, determining a request vector, and using a model to calculate a similarity value with previously categorized requests. Based on this similarity value, the server determines the category of the request, generates an action signal, and transmits it to a second device for appropriate action. The method also includes a feedback loop to update the vocabulary associated with categorized requests and adapt the machine learning algorithm based on human interference.
Furthermore, the patent describes a system that implements this method, comprising a server with access to categorized requests and word vector representations, a policyholder device for user input, and a screen, facilitating the interaction between the policyholder and the server. The system executes steps such as identifying component words, determining request vectors, calculating similarity values, and generating action signals based on the determined category of the request. The system is designed to differentiate between actions to be performed by the policyholder device and a customer service device based on the generated action signal, ensuring efficient handling of requests and categorization processes. The method also includes provisions for indicating uncertainty in category determination, triggering human operator intervention, and displaying notifications on the user device for enhanced user experience.
To know more about GlobalData’s detailed insights on KBC Group, 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.
