Zuora has been granted a patent for a method to create a custom artificial neural network (ANN) architecture for video data stream analysis. The method involves selecting existing ANN architectures and datasets, calculating similarities, and obtaining a custom architecture for tasks like object detection in autonomous driving. GlobalData’s report on Zuora gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Zuora, Social media analytics was a key innovation area identified from patents. Zuora's grant share as of February 2024 was 77%. Grant share is based on the ratio of number of grants to total number of patents.

Custom artificial neural network architecture for video data stream inference

Source: United States Patent and Trademark Office (USPTO). Credit: Zuora Inc

A recently granted patent (Publication Number: US11908193B2) outlines a method for obtaining a custom artificial neural network (ANN) architecture tailored for performing an inference task on a specific dataset from a video data stream while meeting defined performance criteria. The method involves selecting existing ANN architectures and datasets of the same type as the target dataset, calculating architecture fingerprints and pairwise similarities, determining centrality scores, and obtaining performance scores. By interpolating among existing architectures using calculated weights, a custom ANN architecture is derived. This custom architecture is then utilized to sense, detect, categorize, track objects in a video data stream, and control an autonomous driving car based on the identified objects.

Furthermore, the patent describes a system for an autonomous car that implements the method outlined in the claims. The system includes cameras for sensing video data, a database, computing devices connected to the database, and memory with instructions for executing the method. The system selects existing ANN architectures and datasets, calculates fingerprints, similarities, centrality scores, and performance scores, and derives a custom ANN architecture through interpolation. This custom architecture enables object detection, categorization, tracking in the video data stream, and subsequent control of the autonomous driving car based on the identified objects. The system's performance scores provide insights into accuracy, computing speed, memory size, and other characteristics relevant to the inference calculation process.

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

Premium 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.