Meta Platforms had 13 patents in ecommerce during Q4 2023. Meta Platforms Inc has filed patents for an online system that ranks content based on user interaction likelihood, attributing origination to content creators, generating cluster groups for content eligibility, facilitating creation of objects for artificial reality environments, and predicting life events for gift suggestions on social networking platforms. These patents aim to enhance user experience, engagement, and content creation on social media platforms. GlobalData’s report on Meta Platforms gives a 360-degreee 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.
Meta Platforms grant share with ecommerce as a theme is 23% in Q4 2023. Grant share is based on the ratio of number of grants to total number of patents.
Recent Patents
Application: Balancing an improvement in a predicted likelihood of user interaction with content in an online system against a latency required to obtain the improved prediction (Patent ID: US20230376809A1)
The patent filed by Meta Platforms Inc. describes an online system that ranks content for users based on predictions made by general and specific models regarding user interaction likelihood. The specific model, despite higher latency, offers more accurate predictions. The system balances accuracy and latency by determining which prediction to use for ranking, outputting the predicted likelihood, ranking content items, and selecting items for user presentation. The system logs predicted likelihoods, outputted predictions, and content item performance information.
The method involves training a general model and a specific model to predict user interaction likelihood with content items, identifying opportunities to present content, predicting user interaction likelihood using both models, outputting predictions based on a control setting, passing predictions to a content selection process, and logging predicted likelihoods. The system further accesses and compares logged predictions, computes accuracy metrics, determines control settings based on accuracy, historical performance information, and random selection processes, sends selected content items for presentation, and logs performance information. The general model uses general embeddings based on features of content-providing users, while the specific model uses specific embeddings based on features from content-providing users. The higher latency of the specific model is offset by increased accuracy, and the predicted likelihood from the specific model refines the general model's prediction.
To know more about GlobalData’s detailed insights on Meta Platforms, 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.
