公开(公告)号：US11463387B1

公开(公告)日：2022-10-04

申请号：US17384614

申请日：2021-07-23

申请人： FMR LLC

发明人： Manikanta Panati ,  Allen Detmer ,  Keith Pepin ,  Amanda Bedard ,  Byung Chun

IPC分类号： H04L51/02 ,  G06F3/0484 ,  G06F9/54 ,  G06F9/451 ,  H04L65/1069

摘要： Methods and apparatuses are described for capturing and utilizing context data in virtual assistant communication sessions. A chat-based communication session is established between a virtual assistant application and a remote device. An event manager captures a first data event of the virtual assistant application. A parent software application receives the first data event and selects one or more session context data elements using a callback function of the first data event. The event manager captures a second data event of the parent software application comprising the session context data elements. The virtual assistant receives the second data event and inserts one or more messages comprising the session context data elements from the second data event into the chat-based communication session.

公开(公告)号：US11847565B1

公开(公告)日：2023-12-19

申请号：US18109373

申请日：2023-02-14

申请人： FMR LLC

发明人： Hua Hao ,  Tieyi Guo ,  Byung Chun ,  Yachao He ,  Ou Li ,  Chao Yu

IPC分类号： G06N3/08 ,  G06F16/35 ,  G06F16/901

CPC分类号： G06N3/08 ,  G06F16/353 ,  G06F16/9024

摘要： Methods and apparatuses are described for automatic refinement of intent classification for virtual assistant applications. A computing device creates utterance groups comprising messages. The device determines, using a first machine learning (ML) classifier, a first predicted intent associated with each utterance group and determines, using a second ML classifier, a second predicted intent associated with each utterance group. The device combines the first and second predicted intents to generate a final predicted intent, determines, for each incomprehensible utterance group, whether the final predicted intent overlaps with the final predicted intent for other utterance groups, and selects messages having no overlapping intent to create new intents. The device determines, for each comprehensible utterance group, whether the final predicted intent overlaps with a preassigned intent for other utterance groups and combines the messages that have an overlapping intent to create and label a new utterance group with the overlapping intent.

公开(公告)号：US20220164683A1

公开(公告)日：2022-05-26

申请号：US17105131

申请日：2020-11-25

申请人： FMR LLC

发明人： Hua Hao ,  Tieyi Guo ,  Byung Chun ,  Wenbin Ren ,  Yan Yu

IPC分类号： G06N5/04 ,  G06N5/02 ,  G06N3/08 ,  G06F40/295 ,  G06F16/25 ,  G06F16/93

摘要： Methods and apparatuses are described for generating a domain-specific knowledge graph from unstructured computer text. A computing device extracts unstructured computer text associated with pairs of entities from domain-independent documents, and trains an entity relationship classification model using a domain-independent knowledge graph and the extracted text. The computing device extracts other unstructured text associated with a first domain from domain-specific documents. The computing device identifies pairs of entities contained within the text for the first domain, and executes the trained model to determine a relationship between the entities in each pair of entities identified from the text for the first domain. The computing device generates a domain-specific knowledge graph using (i) the pairs of entities identified from the text for the first domain and (ii) the relationships between the entities in each pair of entities identified from the text for the first domain.

公开(公告)号：US20190124403A1

公开(公告)日：2019-04-25

申请号：US16164162

申请日：2018-10-18

申请人： FMR LLC

发明人： David Favicchio ,  Christopher Lackey ,  Veronica Grigoras ,  Philipp Hanes ,  Byung Chun ,  Chad Iverson

IPC分类号： H04N21/488 ,  H04N21/44 ,  H04N21/45 ,  H04N21/466 ,  H04N21/431 ,  H04N21/2187

摘要： Methods and systems are described for generating integrated intelligent content overlays for media content streams. A server computing device receives a video content stream from a video data source. The server extracts a corpus of machine-recognizable text from the video content stream, the corpus of machine-recognizable text corresponding to at least one of audio or closed captioning text associated with the video content stream. The server identifies one or more entity names contained in the corpus of machine-recognizable text. The server determines a set of content keywords associated with each of the identified entity names. The server generates a content overlay for the video content stream comprising one or more layers that include graphical content relating to at least one of the sets of content keywords. The server integrates the content overlay into the video content stream to generate a customized video content stream.

公开(公告)号：US11907673B1

公开(公告)日：2024-02-20

申请号：US18115496

申请日：2023-02-28

申请人： FMR LLC

发明人： Hua Hao ,  Chen Bi ,  Tieyi Guo ,  Byung Chun ,  Wenbin Ren ,  Hao Fu ,  Pengrui Sun

IPC分类号： G06F15/16 ,  G06F40/40 ,  H04L51/02 ,  G06F16/35

CPC分类号： G06F40/40 ,  G06F16/35 ,  H04L51/02

摘要： Methods and apparatuses are described for enhancing chatbot recognition of user intent through graph analysis. A computing device classifies user messages associated with a chat session as either comprehensible user messages that are mapped to a user intent or incomprehensible utterances that are not mapped to a user intent. The computing device arranges the comprehensible messages into first clusters and arranges the incomprehensible messages into second clusters. The computing device generates a first sub-graph for each first cluster and generates a second sub-graph for each second cluster. The computing device calculates a graph kernel matrix using the sub-graphs and trains a classification model using the graph kernel matrix. The computing device executes the trained classification model using the graph kernel matrix as input to generate a predicted intent identifier for the incomprehensible messages.

公开(公告)号：US20220215405A1

公开(公告)日：2022-07-07

申请号：US17143505

申请日：2021-01-07

申请人： FMR LLC

发明人： Byung Chun ,  Lincoln Roach ,  Christopher Yu ,  Divya Mahajan ,  Benjamin Dixon

IPC分类号： G06Q30/02 ,  G06F16/901 ,  G06F16/21

摘要： Systems and methods for synchronizing user activity across digital channels. The method includes receiving a first request corresponding to a first user activity on a first digital channel via a user device. The method also includes storing a first real-time activity record corresponding to the first request in a database. The method further includes updating a user profile based on the first real-time activity record. The method also includes receiving a second request corresponding to a second user activity on a second digital channel via the user device. The method further includes determining an intended transaction corresponding to the second request using a semantic knowledge graph. The method also includes generating a customized digital activity based on the user profile and determined intended transaction. The method further includes generating for display the customized digital activity on the user device.