-
公开(公告)号：US20220343336A1
公开(公告)日：2022-10-27
申请号：US17237827
申请日：2021-04-22
Applicant: Microsoft Technology Licensing, LLC
Inventor： Dongyang Wang , Li Zhou , Cheng Deng , Yu Wang
Abstract: Described herein is a technique for establishing an overall company-level confidence score based on analyzing data from various data sources. The overall score is derived using a machine learned model that takes as input a set of sub-scores, with each sub-score representing a measure of how frequently a domain name occurs within the same data record as a company name. The model used to combine the several sub-scores is trained using training data that includes a variety of sub-scores for company and domain names that have already been verified to be associated with one another.
-
公开(公告)号：US11979360B2
公开(公告)日：2024-05-07
申请号：US17278632
申请日：2018-10-25
Applicant: Microsoft Technology Licensing, LLC
Inventor： Li Zhou
Abstract: The present disclosure provides method and apparatus for responding in a voice conversation by an electronic conversational agent. A voice input may be received in an audio upstream. In response to the voice input, a primary response and at least one supplementary response may be generated. A primary voice output may be generated based on the primary response. At least one supplementary voice output may be generated based on the at least one supplementary response. The primary voice output and the at least one supplementary voice output may be provided in an audio downstream, wherein the at least one supplementary voice output is provided during a time period adjacent to the primary voice output in the audio downstream.
-
公开(公告)号：US09965569B2
公开(公告)日：2018-05-08
申请号：US14657142
申请日：2015-03-13
Applicant: Microsoft Technology Licensing, LLC
Inventor： Qingwei Guo , Fangpeng Guo , Li Zhou
IPC: G06F17/30 , G06F3/01 , G06F3/0488 , G06F17/27
CPC classification number: G06F17/30973 , G06F3/018 , G06F3/0488 , G06F17/276 , G06F17/3064 , G06F17/30864 , G06F17/3097
Abstract: A computer device may reduce user error when constructing a search query. The computing device may display one or more search terms within a search box based on user input. The computing device may display initial autosuggest candidates and detect a user-selected initial autosuggest candidate. The computing device may display the user-selected initial autosuggest candidate within the search box as a preliminary search query, without automatically initiating a web search for the preliminary search query. The computing device may receive new autosuggest candidates having the preliminary search query as a common prefix, generate truncated autosuggest candidates by removing the common prefix from each new autosuggest candidate, and display the truncated autosuggest candidates.
-
公开(公告)号：US11593613B2
公开(公告)日：2023-02-28
申请号：US16316095
申请日：2017-07-04
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
Inventor： Bowen Wu , Baoxun Wang , Shuang Peng , Min Zeng , Li Zhou
Abstract: Non-limiting examples of the present disclosure describe a convolutional neural network (CNN) architecture configured to evaluate conversational relevance of query-response pairs. A CNN model is provided that can include a first branch, a second branch, and multilayer perceptron (MLP) layers. The first branch includes convolutional layers with dynamic pooling to process a query. The second branch includes convolutional layers with dynamic pooling to process candidate responses for the query. The query and the candidate responses are processed in parallel using the CNN model. The MLP layers are configured to rank query-response pairs based on conversational relevance.
-
公开(公告)号：US20220038398A1
公开(公告)日：2022-02-03
申请号：US17278632
申请日：2018-10-25
Applicant: Microsoft Technology Licensing, LLC
Inventor： Li Zhou
Abstract: The present disclosure provides method and apparatus for responding in a voice conversation by an electronic conversational agent. A voice input may be received in an audio upstream. In response to the voice input, a primary response and at least one supplementary response may be generated. A primary voice output may be generated based on the primary response. At least one supplementary voice output may be generated based on the at least one supplementary response. The primary voice output and the at least one supplementary voice output may be provided in an audio downstream, wherein the at least one supplementary voice output is provided during a time period adjacent to the primary voice output in the audio downstream.
-
Patent Agency Ranking
6.发明授权公开(公告)号：US11075916B2
公开(公告)日：2021-07-27
申请号：US16455750
申请日：2019-06-28
Applicant: Microsoft Technology Licensing, LLC
Inventor： Li Zhou , Armen N. Hamstra , Caleb T. Johnson , Yixiao Lu , Sumanth Kolar
Abstract: In an embodiment, the disclosed technologies include storing, in one or more searchable digital data structures, a set of digital entitlements; where an entitlement of the set of digital entitlements identifies a distinct computer functionality and a downstream service that can perform the distinct computer functionality using digital data; storing, in the one or more searchable digital data structures, a digital data entity; where the digital data entity includes a subset of the set of digital entitlements; storing, in the one or more searchable digital data structures, a digital mapping that associates digital data entities with entitlements of the set of digital entitlements; exposing the set of digital entitlements for use by the downstream service; exposing the digital data entity for use by an upstream service; in response to a creation of or an update of an instance of digital data via the upstream service, using the digital mapping to determine to perform the distinct computer functionality using the instance of digital data or to determine not to perform the distinct computer functionality using the instance of the digital data.
-
公开(公告)号：US20190206397A1
公开(公告)日：2019-07-04
申请号：US16124077
申请日：2018-09-06
Applicant: Microsoft Technology Licensing, LLC
Inventor： Li Zhou
CPC classification number: G10L15/22 , G10L13/00 , G10L13/08 , G10L15/18 , G10L15/26 , G10L15/28 , G10L15/34
Abstract: The present disclosure provides a technical solution related to full duplex communication for voice conversation between chatbot and human beings. More particularly, by using such technique, the conventional conversation mode with message as center in the art is subverted so as to realize a conversation mode in full duplex mode. The entire expression that a user intents to express may be predicted when obtaining intermediate result of speech recognition, and response messages may be generated in advance based on the predicted whole expression so that the generated response message may be output immediately when a response condition is satisfied, e.g., it is determined that a user has finished a paragraph of talking. With such technical solution, the latency from the end of voice input of a user and the start of speech output of a chatbot may be minimized.
-
公开(公告)号：US20200005243A1
公开(公告)日：2020-01-02
申请号：US16020640
申请日：2018-06-27
Applicant: Microsoft Technology Licensing, LLC
Inventor： Wai Lim W. Pong , Viman Deb , Manish Baldua , Shidong Yan , Li Zhou , Tao Zheng
Abstract: The disclosed embodiments provide a system for processing data. During operation, the system stores, in a repository, a set of configurable rules for managing hiring workflows in an applicant tracking system, wherein each configurable rule in the set of configurable rules includes a trigger representing activity associated with an online network, a condition to be evaluated in response to the trigger, and an action to be performed when the condition is met. Next, the system matches recent activity associated with a candidate in an applicant tracking system to the trigger in a configurable rule from the repository. Next, the system evaluates the condition from the configurable rule using attributes associated with the candidate. When the condition is met by the attributes, the system automatically performs the action specified in the configurable rule to advance the candidate through the hiring workflow in the applicant tracking system.
-
公开(公告)号：US20190188624A1
公开(公告)日：2019-06-20
申请号：US15844887
申请日：2017-12-18
Applicant: Microsoft Technology Licensing, LLC
Inventor： Wai Lim W. Pong , Li Zhou , Wei Luo
CPC classification number: G06Q10/063112 , G06Q10/1053
Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains, for a set of interviews with a candidate, a set of constraints that includes availabilities of a set of interviewers, a set of available time slots, and a time period spanned by the set of interviews. Next, the system generates, using the set of constraints, an interview schedule that includes an assignment of the set of interviewers to a subset of the available time slots in the time period by sequentially matching each time slot in the subset of the available time slots to the availabilities of the set of interviewers. The system then schedules the set of interviews according to the interview schedule.
-
公开(公告)号：US20160267200A1
公开(公告)日：2016-09-15
申请号：US14657142
申请日：2015-03-13
Applicant: Microsoft Technology Licensing, LLC
Inventor： Qingwei Guo , Fangpeng Guo , Li Zhou
IPC: G06F17/30 , G06F3/0488 , G06F3/01
CPC classification number: G06F17/30973 , G06F3/018 , G06F3/0488 , G06F17/276 , G06F17/3064 , G06F17/30864 , G06F17/3097
Abstract: A computer device may reduce user error when constructing a search query. The computing device may display one or more search terms within a search box based on user input. The computing device may display initial autosuggest candidates and detect a user-selected initial autosuggest candidate. The computing device may display the user-selected initial autosuggest candidate within the search box as a preliminary search query, without automatically initiating a web search for the preliminary search query. The computing device may receive new autosuggest candidates having the preliminary search query as a common prefix, generate truncated autosuggest candidates by removing the common prefix from each new autosuggest candidate, and display the truncated autosuggest candidates.
Abstract translation: 计算机设备可以在构造搜索查询时减少用户错误。 计算设备可以基于用户输入在搜索框内显示一个或多个搜索项。 计算设备可以显示初始自动建立候选者并且检测用户选择的初始自动申请候选者。 计算设备可以在搜索框内显示用户选择的初始自动建立候选者作为初步搜索查询，而不自动发起初步搜索查询的网络搜索。 计算设备可以接收具有初步搜索查询的新的自动建议候选者作为公共前缀，通过从每个新的自动申请候选者中移除公共前缀来生成截断的自动申请候选者，并显示截断的自动申请候选者。
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.046 seconds)
