公开(公告)号：US20170075891A1

公开(公告)日：2017-03-16

申请号：US15261556

申请日：2016-09-09

Applicant: Google Inc.

Inventor： Tolga Bozkaya ,  Armand Joseph Dijamco

IPC: G06F17/30

CPC classification number: G06F17/3043 ,  G06F17/30401 ,  G06F17/30554 ,  G06F17/30654

Abstract: One of the methods includes, obtaining a natural language query from a user; while converting the natural language query into structured operations to be performed on structured application programming interfaces (APIs) of a knowledge base: responsive to detecting a linguistic ambiguity associated with the converting, wherein the linguistic ambiguity identifies two or more interpretations of a word included in the natural langue query: resolving the linguistic ambiguity by selecting an interpretation of the word, from the two or more interpretations of the word, based on one or more join paths that have been generated based on a data schema of the knowledge base; modifying the converting in accordance with the selected interpretation of the word, to generate one or more structured operations; performing the one or more structured operations on the structured APIs of the knowledge base; and returning search results matching the natural language query results to the user.

Abstract translation: 其中一种方法包括从用户获取自然语言查询; 同时将自然语言查询转换为在知识库的结构化应用程序编程接口（API）上执行的结构化操作：响应于检测与转换相关联的语言模糊性，其中语言歧义识别包括在一个词中的词的两个或更多个解释 自然语言查询：基于基于知识库的数据模式生成的一个或多个连接路径，通过从该词的两个或更多个解释中选择该词的解释来解决语言模糊性; 根据所选词的解释修改转换，以生成一个或多个结构化操作; 对知识库的结构化API执行一个或多个结构化操作; 并将与自然语言查询结果相匹配的搜索结果返回给用户。

公开(公告)号：US10032145B1

公开(公告)日：2018-07-24

申请号：US15229542

申请日：2016-08-05

Applicant: Google Inc.

Inventor： Shenaz Zack ,  Shishir Samir Mehrotra ,  Lin Shi ,  Rui Chen ,  Armand Joseph Dijamco ,  Yannet Interian ,  Aaron Kwong Yue Lee ,  Jeffrey Lee-Chan ,  Jianliang Zhao ,  Chetan Hari Narain

IPC: G06F21/00 ,  G06Q20/10 ,  G06Q50/00

Abstract: A system and method for sharing revenue associated with a video is disclosed. The method includes generating a popularity score for a first video based at least in part on first popularity data. The popularity score is indicative of present and future popularity of the first video. The method also includes retrieving historical data includes historical popularity and profitability of multiple videos submitted by an owner of the first video, in response to determining that the popularity score for the first video is greater than a predetermined value. The method also includes determining that the first video is eligible to participate in a revenue sharing program based at least in part on the retrieved historical data. The method includes generating a message for a client device associated with the owner of the first video to invite the owner of the first video to participate in the revenue sharing program.

公开(公告)号：US20170132659A1

公开(公告)日：2017-05-11

申请号：US14153860

申请日：2014-01-13

Applicant: Google Inc.

Inventor： William Martin Dirks ,  Stephen John Andrew Tracy ,  Armand Joseph Dijamco ,  Philippe Farhi ,  Romit Jadhwani ,  Gabriel Jason Kronstadt ,  Eli Spencer Danziger

IPC: G06Q30/02

CPC classification number: G06Q30/0247

Abstract: A method, executed on a processor, for computing potential revenue from video program views, includes receiving ad availabilities in video programs; receiving an identification of each of one or more ad requests based on an ad availability in a video program, each ad request defined by one or more factors i and an ad format m of an ad requested, the ad requests defining the video program as one or more monetizable views; receiving, or each of the one or more factors i, a revenue term; and determining, based on the ad format m and the revenue term, total potential revenue from an advertisement served in the ad availability.

公开(公告)号：US20170075953A1

公开(公告)日：2017-03-16

申请号：US15261538

申请日：2016-09-09

Applicant: Google Inc.

Inventor： Tolga Bozkaya ,  Armand Joseph Dijamco ,  Tran Bui ,  Andy Chu-I Yu

IPC: G06F17/30 ,  G06F17/27

CPC classification number: G06F16/243 ,  G06F16/24522 ,  G06F17/2775

Abstract: Systems, methods, and computer storage media for handling failures in generating structured queries from natural language queries. One of the methods includes obtaining, through a natural language front end, a natural language query from a user; converting the natural language query into structured operations to be performed on structured application programming interfaces (APIs) of a knowledge base, comprising: parsing the natural language query, analyzing the parsed query to determine dependencies, performing lexical resolution, forming a concept tree based on the dependencies and lexical resolution; analyzing the concept tree to generate a hypergraph, generate virtual query based on the hypergraph, and processing the virtual query to generate one or more structured operations; performing the one or more structured operations on the structured APIs of the knowledge base; and returning search results matching the natural language query to the user.

Abstract translation: 用于处理从自然语言查询生成结构化查询中的故障的系统，方法和计算机存储介质。 其中一种方法包括通过自然语言前端获得用户的自然语言查询; 将自然语言查询转换为在知识库的结构化应用程序编程接口（API）上执行的结构化操作，包括：解析自然语言查询，分析解析的查询以确定依赖性，执行词法分辨率，基于 依赖和词汇分辨率; 分析概念树以生成超图，基于超图生成虚拟查询，并处理虚拟查询以生成一个或多个结构化操作; 对知识库的结构化API执行一个或多个结构化操作; 并将与自然语言查询匹配的搜索结果返回给用户。