公开(公告)号：US20230283582A1

公开(公告)日：2023-09-07

申请号：US18316458

申请日：2023-05-12

申请人： Microsoft Technology Licensing, LLC

发明人： Jonathan Ray BATES ,  Shoou-Jiun WANG ,  Jaclyn Ruth Elizabeth PHILLIPS ,  Tracy My Tuyen NGUYEN ,  YI ZHANG ,  Thinesh Thangakumar Abimanyu RATHINAVELU ,  Jennifer Olivia EDE

IPC分类号： H04L51/21 ,  G06F40/35 ,  G06F18/22 ,  G06F40/237 ,  H04L51/02

CPC分类号： H04L51/21 ,  G06F18/22 ,  G06F40/237 ,  G06F40/35 ,  H04L51/02

摘要： Embodiments are provided for detecting overlapping topics in a messaging system. In an example system, a plurality of trigger phrases is received, where each trigger phrase is configured to trigger a bot that receives the trigger phrase to select a corresponding topic for conversation. For each trigger phrase, a vector representation is generated. Measures of similarity are generated based at least on the vector representations, where each measure of similarity represents a degree of similarity between a respective pair of vector representations. A topic overlap is detected based on a pair of vector representations having a measure of similarity above a similarity threshold, where the topic overlap indicates two trigger phrases that are overlapping. The topic overlap is provided to an authoring tool that comprises one or more interactive elements to enable a user to change at least one of the two trigger phrases that are overlapping.

公开(公告)号：US20230281389A1

公开(公告)日：2023-09-07

申请号：US17744243

申请日：2022-05-13

申请人： Microsoft Technology Licensing, LLC

发明人： Webber Po-Wei LEE ,  Daniil SOKOLOV ,  Jaclyn Ruth Elizabeth PHILLIPS ,  Yi ZHANG ,  Jennifer Oliva EDE ,  Shoou-Jiun WANG ,  Tracy My Tuyen NGUYEN

IPC分类号： G06F40/279

CPC分类号： G06F40/279

摘要： Embodiments are provided for suggesting topics in a messaging system. A set of queries is received from a chat transcript history, where the set of queries includes a set of unhandled queries, and each unhandled query comprises a query for which a bot did not identify a corresponding topic (e.g., queries that did not trigger selection of a topic by the bot). A vector representation is generated for each unhandled query in the set of unhandled queries. The vector representations for the set of unhandled queries are clustered to generate one or more clusters of vector representations, each cluster corresponding to a group of unhandled queries. A corresponding suggested topic is generated for each cluster and provided to an authoring tool that comprises one or more interactive elements to enable an author to select at least one of the suggested topics for implementation in the bot.

公开(公告)号：US20210117448A1

公开(公告)日：2021-04-22

申请号：US16659017

申请日：2019-10-21

申请人： Microsoft Technology Licensing, LLC

发明人： Shean WANG ,  Jiayuan HUANG ,  Weizhu CHEN ,  Changhong YUAN ,  Ankit SARAF ,  Xiaoying GUO ,  Eslam K. ABDELREHEEM ,  Yunjing MA ,  Yuantao WANG ,  Justin Carl WONG ,  Nan ZHAO ,  Chao LI ,  Tsuyoshi WATANABE ,  Jaclyn Ruth Elizabeth PHILLIPS

IPC分类号： G06F16/28

摘要： In some examples, iterative sampling based dataset clustering may include sampling a dataset that includes a plurality of items to identify a specified number of sampled items. The sampled items may be clustered to generate a plurality of clusters. Un-sampled items may be assigned from the plurality of items to the clusters. Remaining un-sampled items that are not assigned to the clusters may be identified. A ratio associated with the remaining un-sampled items and the plurality of items may be compared to a specified threshold. Based on a determination that the ratio is greater than the specified threshold, an indication of completion of clustering of the plurality of items may be generated.