Jumio’s patent involves computer systems and methods for training a machine learning system to make authentication decisions and provide corresponding explanation information. The system receives authentication requests, updates the authentication model based on validation information, and displays explanation information to the user device. GlobalData’s report on Jumio gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Jumio, Biometric transaction authentication was a key innovation area identified from patents. Jumio's grant share as of April 2024 was 60%. Grant share is based on the ratio of number of grants to total number of patents.

Machine learning system for authentication decision with explanation information

Source: United States Patent and Trademark Office (USPTO). Credit: Jumio Corporation

A recently granted patent (Publication Number: US11968194B2) outlines a computer-implemented method for authentication processes. The method involves receiving authentication information from a user device, including images of identification documents, and sending this information to a validation system. Based on the received data, an image fault indicator is displayed, prompting manual input of specific image faults. The system then receives validation information corresponding to the images, including authentication decisions and explanation information. This data is stored and used to update an authentication model, which is subsequently utilized to determine validation information for future authentication requests. The system provides users with detailed explanations corresponding to authentication decisions, enhancing transparency and user understanding.

Furthermore, the patent details the process of updating the authentication model using supervised, unsupervised, and adversarial training methods. The model associates authentication decisions and explanation information with images, training itself based on this data to improve accuracy and efficiency in authentication processes. The system distinguishes between manual review processes and automated model-based determinations, ensuring independence and reliability in decision-making. The method also includes a predefined set of image faults, such as digital copies or manipulated images, to aid in authentication decision-making. By incorporating machine learning techniques and user-friendly interfaces, this patented system aims to enhance security and user experience in authentication procedures, setting a new standard in the field.

To know more about GlobalData’s detailed insights on Jumio, 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

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.