Twilio has filed a patent for a computer-implemented method that estimates if a user belongs to an audience category. The method involves accessing events generated at a website, providing event information and user information to an audience machine-learning model, generating a score indicating the probability that the user belongs to the audience, and determining the user’s audience membership based on the score. GlobalData’s report on Twilio 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 Twilio, Intelligent contact centers was a key innovation area identified from patents. Twilio's grant share as of September 2023 was 67%. Grant share is based on the ratio of number of grants to total number of patents.
Estimating user audience category using machine learning model
A recently filed patent (Publication Number: US20230298055A1) describes a computer-implemented method for analyzing user behavior on a website and determining if a user belongs to a specific audience. The method involves accessing events generated by users on the website and providing this event information, along with information about a specific user, to an audience machine-learning (ML) model. The ML model is trained with data that includes event features, user information features, and audience labels. The model then generates a score indicating the probability that the user belongs to the target audience, and based on this score, it is determined if the user belongs to the audience.
The patent also outlines various features that can be used as event features and user information features. Event features include the number of orders, items ordered, items added to cart, page views, cart views, days since last order, and total value of purchases within a specific time window. User information features include the user's email, telephone number, and internet protocol (IP) address.
Additionally, the method includes calculating audience labels in the training data based on a predefined rule. The events that can be analyzed include accessing a product webpage, ordering a product, adding a product to a shopping cart, adding a product to a wish list, and viewing the shopping cart.
The patent also describes the generation of a forecast for users who belong to the target audience. Furthermore, the method involves analyzing the events generated on the website and determining a persona identifier for each event. This persona identifier is associated with a user and includes user traits such as email address, IP address, and telephone number.
The patent also includes a system and a tangible machine-readable storage medium that can perform the same operations as described in the method.
In summary, this patent describes a computer-implemented method, system, and storage medium for analyzing user behavior on a website and determining if a user belongs to a specific audience. The method utilizes machine learning models trained with event and user information features to generate a score indicating the probability of user belonging to the target audience. The patent also includes features for calculating audience labels, generating forecasts, and determining persona identifiers for users.
To know more about GlobalData’s detailed insights on Twilio, 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.
