NBN has been granted a patent for a computer-implemented method and system for processing workorder evidence. The method involves validating an image to determine if it is associated with the workorder, comparing image attributes to workorder attributes, and detecting objects of interest in the image. The workorder evidence is then classified based on the validity of the image and the detection of objects of interest. GlobalData’s report on NBN gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
According to GlobalData’s company profile on NBN, Power over Ethernet (PoE) was a key innovation area identified from patents. NBN's grant share as of June 2023 was 1%. Grant share is based on the ratio of number of grants to total number of patents.
Classification of workorder evidence based on image validation and object detection
A recently granted patent (Publication Number: US11663296B2) describes a computer-implemented method for classifying workorder evidence. The method involves validating an image associated with a workorder by comparing it to available image metadata or previous images stored in an image storage. The image is considered valid if it meets the comparison criteria. The method also includes detecting whether the image depicts at least one object of interest using an object detection algorithm. Based on the validity of the image and the detection of the object of interest, the workorder evidence is classified as satisfying the workorder.
The patent further details additional steps and features of the method. For example, step b) of the validation process involves determining whether the image is an exact duplicate of any previous image. The comparison of images can be performed using image feature vectors, and a trained deep learning neural network model can be utilized for calculating these vectors. The method also allows for manipulating the image through cropping, zooming, rotating, and stretching to create a set of manipulated images for comparison with previous images.
The patent also mentions the use of an OCR program to read text on the image as image attributes and compares them to workorder attributes. The image metadata, such as location and date/time, can be compared to the corresponding workorder attributes. The object detection algorithm can be a trained neural network that determines a confidence value indicating the likelihood of the object of interest being depicted in the image. Based on this confidence value, the system can make determinations or flag uncertain cases for further analysis.
In cases where multiple images are provided as workorder evidence, the method includes comparing each image with each other image to identify exact duplicates and remove them from further processing. The patent also describes a workorder processing system that includes a processor and memory for executing the steps of the method.
Overall, the granted patent outlines a computer-implemented method and system for classifying workorder evidence based on image validation and object detection. The method incorporates various comparison steps, image manipulation techniques, and the use of deep learning neural networks to improve the accuracy and efficiency of the classification process.
To know more about GlobalData’s detailed insights on NBN, 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.
