公开(公告)号：US11657094B2

公开(公告)日：2023-05-23

申请号：US16552559

申请日：2019-08-27

Applicant: Meta Platforms Technologies, LLC

Inventor： Seungwhan Moon ,  Pararth Paresh Shah ,  Anuj Kumar ,  Rajen Subba

IPC: G06N3/04 ,  G06F16/9032 ,  G06N3/049 ,  G06F16/9035 ,  G06N20/00 ,  G06N3/084 ,  G06N5/022 ,  G06N3/042 ,  G06N3/044

CPC classification number: G06F16/90332 ,  G06F16/9035 ,  G06N3/042 ,  G06N3/044 ,  G06N3/049 ,  G06N3/084 ,  G06N5/022 ,  G06N20/00

Abstract: In one embodiment, a method includes receiving a query from a user from a client system associated with the user, determining one or more initial memory slots based on the query, accessing a memory graph associated with the user which comprises a plurality of nodes and a plurality of edges connecting the nodes, and wherein one or more of the nodes correspond to one or more episodic memories of the user, respectively, and wherein each edge corresponds to a relationship between the connected nodes, selecting one or more candidate nodes from the memory graph by one or more machine-learning models based on the initial memory slots, generating a response based on the initial memory slots and episodic memories corresponding to the selected candidate nodes, and sending instructions for presenting the response to the client system in response to the query.

公开(公告)号：US20240112008A1

公开(公告)日：2024-04-04

申请号：US16815960

申请日：2020-03-11

Applicant: Meta Platforms Technologies, LLC

Inventor： Kshitiz Malik ,  Seungwhan Moon ,  Honglei Liu ,  Anuj Kumar ,  Hongyuan Zhan ,  Ahmed Aly

IPC: G06N3/08 ,  G06F40/295 ,  G06F40/30 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06F40/295 ,  G06F40/30 ,  G06N3/04

Abstract: In one embodiment, a method includes receiving, by a first client system, from one or more remote servers, a current version of a neural network model including multiple model parameters, training the neural network model on multiple examples retrieved from a local data store to generate multiple updated model parameters, wherein each of the examples includes one or more features and one or more labels, calculating a user valuation associated with the first client system, wherein the user valuation represents a measure of utility of training the neural network model on the multiple examples, and sending, to one or more of the remote servers, the trained neural network model and the user valuation, wherein the user valuation is associated with a likelihood of the first client system being selected for a subsequent training of the neural network model.

公开(公告)号：US11442992B1

公开(公告)日：2022-09-13

申请号：US16557055

申请日：2019-08-30

Applicant: Meta Platforms Technologies, LLC

Inventor： Seungwhan Moon ,  Pararth Paresh Shah ,  Anuj Kumar ,  Rajen Subba

IPC: G06F16/9032 ,  G06N20/00 ,  G06Q50/00 ,  G06N3/04 ,  G06F16/901

Abstract: In one embodiment, a method includes receiving a query from a user from a client system associated with the user, accessing a knowledge graph comprising a plurality of nodes and edges connecting the nodes, wherein each node corresponds to an entity and each edge corresponds to a relationship between the entities corresponding to the connected nodes, determining one or more initial entities associated with the query based on the query, selecting one or more candidate nodes by a conversational reasoning model from the knowledge graph corresponding to one or more candidate entities, respectively, wherein each candidate node is selected based on the nodes corresponding to the initial entities, dialog states associated with the query, and a context associated with the query, generating a response based on the initial entities and the candidate entities, and sending instructions for presenting the response to the client system in response to the query.