ADOBE had no grants in ecommerce as a theme in Q2 2024.

Recent Patents

Application: Predictive agents for multi-round conversational recommendations of bundled items (Patent ID: US20240169410A1)

The patent filed by ADOBE Inc. describes techniques for predicting and recommending item bundles in a multi-round conversation to identify a target item bundle that would be accepted by a client. The method involves receiving input responses, updating a state model, applying machine-learning modules to determine actions, generating different item bundles, and recommending the second item bundle based on the selection of a recommendation action.

The system outlined in the patent includes components such as a memory storing a state model, machine-learning modules for generating item bundles and determining actions, and a modeling module for updating the state model based on input responses. The method and system involve updating candidate pools, attributes, and categories in the state model, removing rejected items, and adding accepted items to a short-term context. The process includes training the machine-learning modules jointly through offline pre-training and online fine-tuning to enhance the accuracy of predicting and recommending item bundles in a conversational setting.

To know more about GlobalData’s detailed insights on ADOBE, 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.

Be better informed