公开(公告)号：US20190102397A1

公开(公告)日：2019-04-04

申请号：US15860597

申请日：2018-01-02

Applicant: Apple Inc.

Inventor： John M. Hornkvist ,  Anubhav Malhotra ,  Rene Chan ,  Stanley Hung

IPC: G06F17/30

Abstract: Methods and systems for client side search ranking improvements are disclosed. In one example, a search query is received from a user on a client device. The local search results are filtered based on the received search query and one or more local ranking rules. Features for each filtered local search result are computed. The computed features of each filtered local search result are input to one or more machine learning (ML) models. Each ML model can generate a score for each filtered local search result. The filtered local search results are ranked based on the generated score within a category. In one example, local search results and remote server search results are obtained. The local search results and remote server search results are ranked using at least one machine learning (ML) ranking model. The ranked local search results and remote server search results are displayed on the client device by category.

公开(公告)号：US20220365939A1

公开(公告)日：2022-11-17

申请号：US17710483

申请日：2022-03-31

Applicant: Apple Inc.

Inventor： John M. Hornkvist ,  Anubhav Malhotra ,  Rene Chan ,  Stanley Hung

IPC: G06F16/2457 ,  G06F16/2458 ,  G06F16/9535

Abstract: Methods and systems for client side search ranking improvements are disclosed. In one example, a search query is received from a user on a client device. The local search results are filtered based on the received search query and one or more local ranking rules. Features for each filtered local search result are computed. The computed features of each filtered local search result are input to one or more machine learning (ML) models. Each ML model can generate a score for each filtered local search result. The filtered local search results are ranked based on the generated score within a category. In one example, local search results and remote server search results are obtained. The local search results and remote server search results are ranked using at least one machine learning (ML) ranking model. The ranked local search results and remote server search results are displayed on the client device by category.

公开(公告)号：US11294911B2

公开(公告)日：2022-04-05

申请号：US15860597

申请日：2018-01-02

Applicant: Apple Inc.

Inventor： John M. Hornkvist ,  Anubhav Malhotra ,  Rene Chan ,  Stanley Hung

IPC: G06F16/2457 ,  G06F16/9535 ,  G06F16/2458

Abstract: Methods and systems for client side search ranking improvements are disclosed. In one example, a search query is received from a user on a client device. The local search results are filtered based on the received search query and one or more local ranking rules. Features for each filtered local search result are computed. The computed features of each filtered local search result are input to one or more machine learning (ML) models. Each ML model can generate a score for each filtered local search result. The filtered local search results are ranked based on the generated score within a category. In one example, local search results and remote server search results are obtained. The local search results and remote server search results are ranked using at least one machine learning (ML) ranking model. The ranked local search results and remote server search results are displayed on the client device by category.

公开(公告)号：US20170357725A1

公开(公告)日：2017-12-14

申请号：US15616875

申请日：2017-06-07

Applicant: Apple Inc.

Inventor： John M. Hornkvist ,  Stanley Hung ,  Hon Yuk Chan ,  Anubhav Malhotra ,  Ted Cui ,  Vipul Ved Prakash

IPC: G06F17/30

CPC classification number: G06F16/2423 ,  G06F16/148 ,  G06F16/164 ,  G06F16/2428 ,  G06F17/28

Abstract: Described is a system and technique for providing search results in response to a search query for content items. The system may search for content items based on searching metadata associated with the content items. The system may rank the search results based on various criteria to display the search results in an intuitive and relevant manner within a search application. For example, in instances where the search application displays sample text (or a snippet) of the content item as part of a search result, the system may prioritize content items that contain the search query as part of the sample text.