Accenture has patented a method using data cleansing, natural language processing, and machine learning to identify mappings between work items in a project. The device processes work item data, synonyms, and keywords to determine confidence scores for the mappings, enabling more efficient project management. GlobalData’s report on Accenture 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 Accenture, was a key innovation area identified from patents. Accenture's grant share as of May 2024 was 47%. Grant share is based on the ratio of number of grants to total number of patents.
Machine learning model for mapping work items with confidence
A recently granted patent (Publication Number: US12014140B2) outlines a method and device for improving work item data processing through a series of innovative steps. The method involves receiving work item data related to various project elements, such as user stories, defects, test cases, and requirements, and then cleansing this data by removing repetitive, stop, and vague words. Natural language processing is then applied to identify synonyms and replace abbreviations with full text, resulting in a final set of work item data. A machine learning model, trained on historical project data, synonyms, and keywords, is utilized to identify mappings between work items and determine confidence scores, providing a measure of similarity between items. The model includes a fuzzy component, such as Levenshtein distance, to enhance accuracy in identifying mappings.
The device described in the patent includes processors and memories configured to execute the method steps, from data cleansing to processing with the machine learning model. Additional functionalities include generating word embeddings, providing mappings and confidence scores to user devices, identifying work items needing attention, determining software release dates based on mappings, and incorporating user feedback to modify mappings. The device can also recalibrate mappings if confidence scores fall below a set threshold. The patent further extends to a non-transitory computer-readable medium storing instructions for executing the method, emphasizing the importance of data cleansing, natural language processing, and machine learning in enhancing work item data processing efficiency and accuracy. The patent's innovative approach aims to streamline project management processes and improve decision-making based on work item data analysis.
To know more about GlobalData’s detailed insights on Accenture, 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.
