Salesforce, Inc. patent applications on February 13th, 2025
Patent Applications by Salesforce, Inc. on February 13th, 2025
Salesforce, Inc.: 2 patent applications
Salesforce, Inc. has applied for patents in the areas of G06N3/0455 (1), G06N3/084 (1), G06Q30/0601 (1), G06N3/047 (1), G06N3/092 (1) G06N3/0455 (1), G06N3/047 (1)
With keywords such as: embeddings, controller, based, user, environment, item, neural, network, data, and performed in patent application abstracts.
Patent Applications by Salesforce, Inc.
Inventor(s): Liangwei Yang of Palo Alto CA (US) for salesforce, inc., Shelby Heinecke of San Francisco CA (US) for salesforce, inc., Jianguo Zhang of San Jose CA (US) for salesforce, inc., Rithesh Murthy of San Francisco CA (US) for salesforce, inc., Huan Wang of Palo Alto CA (US) for salesforce, inc., Caiming Xiong of Menlo Park CA (US) for salesforce, inc., Zhiwei Liu of Palo Alto CA (US) for salesforce, inc.
IPC Code(s): G06N3/0455, G06N3/084, G06Q30/0601
CPC Code(s): G06N3/0455
Abstract: embodiments described herein provide a method for training a recommendation neural network model using multiple data sources. the method may include: receiving, via a data interface, time series data indicating a user-item interaction history; transforming the time series data into a user-item graph; encoding, by a neural network encoder, the user-item graph into user embeddings and item embeddings; generating a plurality of losses according to a plurality of training tasks performed based on the user embeddings and, item embeddings; training the recommendation neural network model by updating the user embeddings and the item embeddings via backpropagation based on a weighted sum of gradients of the plurality of losses; and generating, by a neural network decoder, one or more recommended items for a given user based on the updated user embeddings and the updated item embeddings.
Inventor(s): Zhiwei Liu of Palo Alto CA (US) for salesforce, inc., Weiran Yao of San Francisco CA (US) for salesforce, inc., Jianguo Zhang of San Jose CA (US) for salesforce, inc., Le Xue of Mountain View CA (US) for salesforce, inc., Shelby Heinecke of San Francisco CA (US) for salesforce, inc., Rithesh Murthy of San Francisco CA (US) for salesforce, inc., Yihao Feng of Austin TX (US) for salesforce, inc., Zeyuan Chen of Mountain View CA (US) for salesforce, inc., Juan Carlos Niebles Duque of Mountain View CA (US) for salesforce, inc., Devansh Arpit of San Francisco CA (US) for salesforce, inc., Ran Xu of Pacifica CA (US) for salesforce, inc., Lik Mui of San Francisco CA (US) for salesforce, inc., Huan Wang of Palo Alto CA (US) for salesforce, inc., Caiming Xiong of Menlo Park CA (US) for salesforce, inc., Silvio Savarese of Palo Alto CA (US) for salesforce, inc.
IPC Code(s): G06N3/047, G06N3/092
CPC Code(s): G06N3/047
Abstract: embodiments described herein provide a method of predicting an action by a plurality of language model augmented agents (laas). in at least one embodiment, a controller receives a task instruction to be performed using an environment. the controller receives an observation of a first state from the environment. the controller selects a laa from the plurality of laas based on the task instruction and the observation. the controller obtains an output from the selected laa generated using an input combining the task instruction, the observation, and an laa-specific prompt template. the controller determines the action based on the output. the controller causes the action to be performed on the environment thereby causing the first state of the environment to change to a second state.