公开(公告)号：US11977577B2

公开(公告)日：2024-05-07

申请号：US18331245

申请日：2023-06-08

Applicant: Spotify AB

Inventor： James E. McInerney ,  Benjamin Lacker ,  Samantha Hansen ,  Aloïs Gruson ,  Rishabh Mehrotra ,  Hugues Bouchard

IPC: G06F16/00 ,  G06F16/635 ,  G06F16/638 ,  G06F18/21

CPC classification number: G06F16/637 ,  G06F16/639 ,  G06F18/217

Abstract: Methods, systems and computer program products are provided personalizing recommendations of items with associated explanations. The example embodiments described herein use contextual bandits to personalize explainable recommendations (“recsplanations”) as treatments (“Bart”). Bart learns and predicts satisfaction (e.g., click-through rate, consumption probability) for any combination of item, explanation, and context and, through logging and contextual bandit retraining, can learn from its mistakes in an online setting.

公开(公告)号：US20240281445A1

公开(公告)日：2024-08-22

申请号：US18171247

申请日：2023-02-17

Applicant: Spotify AB

Inventor： Enrico Palumbo ,  Rui André Augusto Ferreira ,  Hugues Bouchard ,  Humberto Jesús Corona Pampín

IPC: G06F16/2457 ,  G06F16/28

CPC classification number: G06F16/24573 ,  G06F16/285

Abstract: An electronic device generates training data to train a classifier to classify a respective search query as complete or incomplete, including: obtaining a first search query input by a first user; determining a media content item selected by the first user from the first search query; comparing metadata associated with the media content item with the first search query input by the first user; and labeling the first search query as complete or incomplete based on the comparison. The electronic device trains the classifier, using the generated training data, to classify a respective search query as complete or incomplete and uses the trained classifier to determine whether a second search query is complete or incomplete. The electronic device provides, for display, for a second user, one or more complete search queries as recommendations for a received search query, including the second search query if second search query is complete.

公开(公告)号：US20240346079A1

公开(公告)日：2024-10-17

申请号：US18298988

申请日：2023-04-11

Applicant: Spotify AB

Inventor： Gustavo Penha ,  Enrico Palumbo ,  Maryam Aziz ,  Alice Wang ,  Hugues Bouchard

IPC: G06F16/9032

CPC classification number: G06F16/90324

Abstract: An electronic device provides, to a model trained to generate synthetic queries, information corresponding to a first media content item and a first value for a parameter indicative of query specificity. The device receives, from the model trained to generate synthetic queries, a first query corresponding to the first media content item, wherein the first query is generated in accordance with the first value for the parameter indicative of query specificity. The device provides, to a client device for display at the client device, the first query and receives user selection of the first query. In response to the user selection of the first query, the device provides a first result set of media content items for the first query.

公开(公告)号：US20230376529A1

公开(公告)日：2023-11-23

申请号：US18331245

申请日：2023-06-08

Applicant: Spotify AB

Inventor： James E. McInerney ,  Benjamin Lacker ,  Samantha Hansen ,  Aloïs Gruson ,  Rishabh Mehrotra ,  Hugues Bouchard

IPC: G06F16/635 ,  G06F16/638 ,  G06F18/21

CPC classification number: G06F16/637 ,  G06F16/639 ,  G06F18/217

Abstract: Methods, systems and computer program products are provided personalizing recommendations of items with associated explanations. The example embodiments described herein use contextual bandits to personalize explainable recommendations (“recsplanations”) as treatments (“Bart”). Bart learns and predicts satisfaction (e.g., click-through rate, consumption probability) for any combination of item, explanation, and context and, through logging and contextual bandit retraining, can learn from its mistakes in an online setting.

公开(公告)号：US20220237226A1

公开(公告)日：2022-07-28

申请号：US17687773

申请日：2022-03-07

Applicant: Spotify AB

Inventor： James E. McInerney ,  Benjamin Lacker ,  Samantha Hansen ,  Aloïs Gruson ,  Rishabh Mehrotra ,  Hugues Bouchard

IPC: G06F16/635 ,  G06K9/62 ,  G06F16/638

Abstract: Methods, systems and computer program products are provided personalizing recommendations of items with associated explanations. The example embodiments described herein use contextual bandits to personalize explainable recommendations (“recsplanations”) as treatments (“Bart”). Bart learns and predicts satisfaction (e.g., click-through rate, consumption probability) for any combination of item, explanation, and context and, through logging and contextual bandit retraining, can learn from its mistakes in an online setting.

公开(公告)号：US12118040B1

公开(公告)日：2024-10-15

申请号：US18298988

申请日：2023-04-11

Applicant: Spotify AB

Inventor： Gustavo Penha ,  Enrico Palumbo ,  Maryam Aziz ,  Alice Wang ,  Hugues Bouchard

IPC: G06F16/9032

CPC classification number: G06F16/90324

Abstract: An electronic device provides, to a model trained to generate synthetic queries, information corresponding to a first media content item and a first value for a parameter indicative of query specificity. The device receives, from the model trained to generate synthetic queries, a first query corresponding to the first media content item, wherein the first query is generated in accordance with the first value for the parameter indicative of query specificity. The device provides, to a client device for display at the client device, the first query and receives user selection of the first query. In response to the user selection of the first query, the device provides a first result set of media content items for the first query.

公开(公告)号：US11709886B2

公开(公告)日：2023-07-25

申请号：US17687773

申请日：2022-03-07

Applicant: Spotify AB

Inventor： James E. McInerney ,  Benjamin Lacker ,  Samantha Hansen ,  Alois Gruson ,  Rishabh Mehrotra ,  Hugues Bouchard

IPC: G06F16/00 ,  G06F16/635 ,  G06F16/638 ,  G06F18/21

CPC classification number: G06F16/637 ,  G06F16/639 ,  G06F18/217

Abstract: Methods, systems and computer program products are provided personalizing recommendations of items with associated explanations. The example embodiments described herein use contextual bandits to personalize explainable recommendations (“recsplanations”) as treatments (“Bart”). Bart learns and predicts satisfaction (e.g., click-through rate, consumption probability) for any combination of item, explanation, and context and, through logging and contextual bandit retraining, can learn from its mistakes in an online setting.

公开(公告)号：US11301513B2

公开(公告)日：2022-04-12

申请号：US16502975

申请日：2019-07-03

Applicant: Spotify AB

Inventor： James E. McInerney ,  Benjamin Lacker ,  Samantha Hansen ,  Aloïs Gruson ,  Rishabh Mehrotra ,  Hugues Bouchard

IPC: G06F16/00 ,  G06F16/635 ,  G06K9/62 ,  G06F16/638

Abstract: Methods, systems and computer program products are provided personalizing recommendations of items with associated explanations. The example embodiments described herein use contextual bandits to personalize explainable recommendations (“recsplanations”) as treatments (“Bart”). Bart learns and predicts satisfaction (e.g., click-through rate, consumption probability) for any combination of item, explanation, and context and, through logging and contextual bandit retraining, can learn from its mistakes in an online setting.