公开(公告)号：US20210109939A1

公开(公告)日：2021-04-15

申请号：US16600993

申请日：2019-10-14

申请人： Airbnb, Inc.

发明人： Malay Haldar

IPC分类号： G06F16/2457 ,  G06F16/9538 ,  G06N3/08 ,  G06N3/04

摘要： A position debiased search system can avoid bias towards top-ranked search results using a position-trained machine-trained model. Past positions for listings can be input into the model with added noise and low-ranked results to train the model to generate rankings that do not exhibit position bias. A network site can implement the position debiased search system to generate network site results that can generate accurate user results in real time as users browse the network site.

公开(公告)号：US20190311044A1

公开(公告)日：2019-10-10

申请号：US15949834

申请日：2018-04-10

申请人： AIRBNB, Inc.

发明人： Tao Xu ,  Haibin Cheng ,  Malay Haldar ,  Brendan Marshall Collins

IPC分类号： G06F17/30 ,  G06Q10/02 ,  G06N99/00

摘要： An online reservation system is configured to receive requests from a guest for searching property listings and to return property listings that satisfy the search criteria of the requests. The online reservation system uses a machine learning system to rank the property listings returned by the search. The machine learning system uses objective functions to determine parameters for each property listing and assign a ranking based on the parameters. A first objective function generates a parameter indicating an extent to which a property listing matches preferences of the guest, and is based on data about the guest's interactions with the reservation system. A second objective function generates another parameter indicating an extent to which the search request matches the preferences of the host associate with the property listing, and is based on data about the host's responses to reservation requests.

公开(公告)号：US20210349908A1

公开(公告)日：2021-11-11

申请号：US17382837

申请日：2021-07-22

申请人： Airbnb, Inc.

发明人： Malay Haldar

IPC分类号： G06F16/2457 ,  G06N3/04 ,  G06N3/08 ,  G06F16/248

摘要： Systems and methods are provided for search result optimization using machine learning models. A search system uses machine learning models generate a target vector based on query features of a search query and a set of listing vectors based on listing features of listings identified as part of the search query. The target vector represents an estimated optimal listing for the search query and each listing vector represents a corresponding listing identified as part of the search query. The search system determines distances (e.g., Euclidian distance) between each listing vector and the target vector. The determined distances indicate how similar each listing is to the estimated optimal listing for the search query. The search system ranks the listings based on the distances such that listings that are similar to the estimated optimal listing are ranked higher than listing that are not similar to the estimated optimal listing.

公开(公告)号：US20240152986A1

公开(公告)日：2024-05-09

申请号：US17983294

申请日：2022-11-08

申请人： Airbnb, Inc.

发明人： Malay Haldar ,  Liwei He ,  Tamara Tan ,  Reid Anderson

IPC分类号： G06Q30/0601 ,  G06Q30/0201

CPC分类号： G06Q30/0627 ,  G06Q30/0201 ,  G06Q30/0641

摘要： There is provided a method that includes receiving, from a client device, a search request for a set of listings, the search request including search parameters defining a search query. The method further includes generating a set of listings based on the search query and the search parameters and extracting price-indicative and non-price-indicative features. The method also includes computing a probability of booking and an estimate of quality, by inputting the price-indicative features and non-price-indicative features to trained machine learning models. The trained machine learning models predict (i) an affordability metric based on the price-indicative features and (ii) a quality metric based on the non-price-indicative features, separately. The affordability metric and the quality metric are representative of the probability of booking, and the quality metric is representative of the estimate of quality. The method further includes ranking the set of listings based on the booking probability and the quality estimate.

公开(公告)号：US11836139B2

公开(公告)日：2023-12-05

申请号：US15949834

申请日：2018-04-10

申请人： AIRBNB, Inc.

发明人： Tao Xu ,  Haibin Cheng ,  Malay Haldar ,  Brendan Marshall Collins

IPC分类号： G06F16/2457 ,  G06N20/00 ,  G06Q10/02 ,  G06N3/04 ,  G06N5/00 ,  G06N20/20

CPC分类号： G06F16/24578 ,  G06N20/00 ,  G06Q10/02

摘要： An online reservation system is configured to receive requests from a guest for searching property listings and to return property listings that satisfy the search criteria of the requests. The online reservation system uses a machine learning system to rank the property listings returned by the search. The machine learning system uses objective functions to determine parameters for each property listing and assign a ranking based on the parameters. A first objective function generates a parameter indicating an extent to which a property listing matches preferences of the guest, and is based on data about the guest's interactions with the reservation system. A second objective function generates another parameter indicating an extent to which the search request matches the preferences of the host associate with the property listing, and is based on data about the host's responses to reservation requests.

公开(公告)号：US11782933B2

公开(公告)日：2023-10-10

申请号：US17382837

申请日：2021-07-22

申请人： Airbnb, Inc.

发明人： Malay Haldar

IPC分类号： G06F16/2457 ,  G06F16/248 ,  G06N3/04 ,  G06N3/08 ,  G06N3/045

CPC分类号： G06F16/24578 ,  G06F16/248 ,  G06N3/045 ,  G06N3/08

摘要： Systems and methods are provided for search result optimization using machine learning models. A search system uses machine learning models generate a target vector based on query features of a search query and a set of listing vectors based on listing features of listings identified as part of the search query. The target vector represents an estimated optimal listing for the search query and each listing vector represents a corresponding listing identified as part of the search query. The search system determines distances (e.g., Euclidian distance) between each listing vector and the target vector. The determined distances indicate how similar each listing is to the estimated optimal listing for the search query. The search system ranks the listings based on the distances such that listings that are similar to the estimated optimal listing are ranked higher than listing that are not similar to the estimated optimal listing.

公开(公告)号：US11645290B2

公开(公告)日：2023-05-09

申请号：US16600993

申请日：2019-10-14

申请人： Airbnb, Inc.

发明人： Malay Haldar

IPC分类号： G06F16/2457 ,  G06N3/04 ,  G06N3/08 ,  G06F16/9538

CPC分类号： G06F16/24578 ,  G06F16/9538 ,  G06N3/0454 ,  G06N3/08

摘要： A position debiased search system can avoid bias towards top-ranked search results using a position-trained machine-trained model. Past positions for listings can be input into the model with added noise and low-ranked results to train the model to generate rankings that do not exhibit position bias. A network site can implement the position debiased search system to generate network site results that can generate accurate user results in real time as users browse the network site.

公开(公告)号：US20240362211A1

公开(公告)日：2024-10-31

申请号：US18383611

申请日：2023-10-25

申请人： Airbnb, Inc.

发明人： Adam James Shutsa ,  Ang Li ,  Clarence Chin-wei Quah ,  Devansh Gupta ,  Shuoyuan Lin ,  Hongru Hou ,  Hongwei Zhang ,  Malay Haldar ,  Kedar Bellare ,  Shanni Weilert ,  Sherry Therese Chen ,  Soumyadip Banerjee ,  Surbhi Sethi ,  Vivek Bhardwaj ,  Xiaotang Wang ,  Yonghua Xu

IPC分类号： G06F16/9538 ,  G06F3/04817 ,  G06F3/04842 ,  G06F16/9535

CPC分类号： G06F16/245 ,  G06F3/04817 ,  G06F3/04842 ,  G06F16/252

摘要： A system that enables searching for representing listings for accommodation reservations on a map is described. The system receives, by a network site of a listing network platform, input comprising search criteria associated with a geographical region and identifies a plurality of listings matching the search criteria. The system identifies a first subset listings of the plurality of listings that is each associated with a respective location that is within a boundary associated with the geographical region and a second subset listings of the plurality of listings that is each associated with a respective location that is outside the boundary associated with the geographical region. The system visually distinguishes the first subset of listings from the second subset of listings on a map-based graphical user interface (GUI) that represents the plurality of listings matching the search criteria.

公开(公告)号：US11100117B2

公开(公告)日：2021-08-24

申请号：US16441952

申请日：2019-06-14

申请人： Airbnb, Inc.

发明人： Malay Haldar

IPC分类号： G06F16/2457 ,  G06N3/04 ,  G06N3/08 ,  G06F16/248

摘要： Systems and methods are provided for search result optimization using machine learning models. A search system uses machine learning models generate a target vector based on query features of a search query and a set of listing vectors based on listing features of listings identified as part of the search query. The target vector represents an estimated optimal listing for the search query and each listing vector represents a corresponding listing identified as part of the search query. The search system determines distances (e.g., Euclidian distance) between each listing vector and the target vector. The determined distances indicate how similar each listing is to the estimated optimal listing for the search query. The search system ranks the listings based on the distances such that listings that are similar to the estimated optimal listing are ranked higher than listing that are not similar to the estimated optimal listing.