公开(公告)号：EP4280148A1

公开(公告)日：2023-11-22

申请号：EP23199881.6

申请日：2023-09-26

Applicant: Lemon Inc. ,  BEIJING YOUZHUJU NETWORK TECHNOLOGY CO. LTD.

Inventor： TON, Jean-Francois ,  KLOCHKOV, Yegor ,  LIU, Yang ,  LI, Hang

IPC: G06Q30/06 ,  G06Q30/0601

Abstract: A method of explaining why an item has been recommended to a user comprises determining a value for the preference of the user for the recommended item based on data relating to the user and the item. This may be in the form of an interaction score. The user data is then modified to reduce the determined preference value such that the recommended item would not be recommended to the user. The modified user data is then used to determine preference values for items with which the user has interacted. These will be different from previously determined preference values based on the unmodified user data. From these preference values it is then possible to identify one or more items with which the user has interacted, for which the determined preference values differ most from previously determined preference values. It can be concluded that the interaction of the user with these identified item(s) is the antecedent for the recommended item being recommended.

公开(公告)号：EP4557180A1

公开(公告)日：2025-05-21

申请号：EP23210772.2

申请日：2023-11-17

Applicant: Lemon Inc. ,  Oxford University Innovation Limited

Inventor： TON, Jean-Francois ,  TAUFIQ, Muhammad Faaiz ,  DOUCET, Arnaud ,  CORNISH, John Robert Macaulay

IPC: G06N7/00 ,  G06N20/00

Abstract: A computer-implemented method of policy evaluation for a contextual decision-making policy, wherein the contextual decision-making policy is used to make one or more decisions, where the outcome of each decision depends upon a context in which the decision is made, the method comprising: obtaining an existing contextual decision-making policy; obtaining a first dataset of decisions made using the existing contextual decision-making context, wherein the first dataset further includes the respective outcome and context of each decision; obtaining a to-be-evaluated contextual decision-making policy; using machine learning to train an outcome model for the to-be-evaluated contextual decision-making policy, based on the existing contextual decision-making policy, the to-be-evaluated contextual decision-making policy and the first dataset; and estimating an expectation for the to-be-evaluated contextual decision-making policy, based on the outcome model.

公开(公告)号：EP4488879A1

公开(公告)日：2025-01-08

申请号：EP23183596.8

申请日：2023-07-05

Applicant: Lemon Inc.

Inventor： TON, Jean-Francois ,  YANG, Mengyue

IPC: G06N3/045 ,  G06N3/0455 ,  G06N3/047 ,  G06N3/088 ,  G06N3/094 ,  H04N21/482 ,  G06Q30/0241

Abstract: Present approach includes methods, computer readable medium, systems, devices for debiasing data. Debiased data is received by or for training a recommendation system. The present approach includes steps of receiving data comprising sensitive-correlated information; obtaining sensitivity representations of the sensitive-correlated information from the data using a plurality of neural networks trained in relation to a set of predetermined context features; deriving a learned representation from the sensitivity representations; and generating a balanced fair prediction from the recommendation system based on the learned representation.