Patent search ap:("Meta Platforms Page Inc.") AND inv:"Fuchun Peng"

1.

发明授权
Contextual auto-completion for assistant systems 有权

公开(公告)号：US12131522B2

公开(公告)日：2024-10-29

申请号：US17077316

申请日：2020-10-22

Applicant: Meta Platforms, Inc.

Inventor： Jiedan Zhu , Fuchun Peng , Benoit F. Dumoulin , Xiaohu Liu , Rajen Subba , Mohsen Agsen , Michael Robert Hanson

IPC: G06F16/338 , G06F3/01 , G06F3/16 , G06F7/14 , G06F9/451 , G06F16/176 , G06F16/22 , G06F16/23 , G06F16/242 , G06F16/2455 , G06F16/2457 , G06F16/248 , G06F16/33 , G06F16/332 , G06F16/903 , G06F16/9032 , G06F16/9038 , G06F16/904 , G06F16/951 , G06F16/9535 , G06F18/2411 , G06F40/205 , G06F40/295 , G06F40/30 , G06F40/40 , G06N3/006 , G06N3/08 , G06N7/01 , G06N20/00 , G06Q50/00 , G06V10/764 , G06V10/82 , G06V20/10 , G06V40/20 , G10L15/02 , G10L15/06 , G10L15/07 , G10L15/16 , G10L15/18 , G10L15/183 , G10L15/187 , G10L15/22 , G10L15/26 , G10L17/06 , G10L17/22 , H04L5/02 , H04L12/28 , H04L41/00 , H04L41/22 , H04L43/0882 , H04L43/0894 , H04L51/02 , H04L51/18 , H04L51/216 , H04L51/52 , H04L67/306 , H04L67/50 , H04L67/5651 , H04L67/75 , H04W12/08 , G10L13/00 , G10L13/04 , H04L51/046 , H04L67/10 , H04L67/53

CPC classification number: G06V10/82 , G06F3/011 , G06F3/013 , G06F3/017 , G06F3/167 , G06F7/14 , G06F9/453 , G06F16/176 , G06F16/2255 , G06F16/2365 , G06F16/243 , G06F16/24552 , G06F16/24575 , G06F16/24578 , G06F16/248 , G06F16/3323 , G06F16/3329 , G06F16/3344 , G06F16/338 , G06F16/90332 , G06F16/90335 , G06F16/9038 , G06F16/904 , G06F16/951 , G06F16/9535 , G06F18/2411 , G06F40/205 , G06F40/295 , G06F40/30 , G06F40/40 , G06N3/006 , G06N3/08 , G06N7/01 , G06N20/00 , G06Q50/01 , G06V10/764 , G06V20/10 , G06V40/28 , G10L15/02 , G10L15/063 , G10L15/07 , G10L15/16 , G10L15/1815 , G10L15/1822 , G10L15/183 , G10L15/187 , G10L15/22 , G10L15/26 , G10L17/06 , G10L17/22 , H04L5/02 , H04L12/2816 , H04L41/20 , H04L41/22 , H04L43/0882 , H04L43/0894 , H04L51/02 , H04L51/18 , H04L51/216 , H04L51/52 , H04L67/306 , H04L67/535 , H04L67/5651 , H04L67/75 , H04W12/08 , G06F2216/13 , G10L13/00 , G10L13/04 , G10L2015/223 , G10L2015/225 , H04L51/046 , H04L67/10 , H04L67/53

Abstract: In one embodiment, a method includes receiving a first user input from a first user, wherein the first user input comprises a partial request, presenting one or more suggested intent auto-completions corresponding to the partial request, receiving a selection by the first user of a first suggested intent auto-completion of the suggested intent auto-completions and a second user input, presenting one or more suggested slot auto-completions corresponding to one or more candidate slot-hypotheses corresponding to the second user input, respectively, wherein each of the candidate slot-hypotheses comprise a slot-suggestion, and wherein each suggested slot auto-completion comprises the second user input and the corresponding candidate slot-hypothesis, receiving a selection by the first user of a first suggested slot auto-completion of the suggested slot auto-completions, and presenting execution results of one or more tasks corresponding to the first suggested intent auto-completion and the first suggested slot auto-completion.

2.

发明授权
Suggestions for fallback social contacts for assistant systems 有权

公开(公告)号：US11908179B2

公开(公告)日：2024-02-20

申请号：US17718146

申请日：2022-04-11

Applicant: Meta Platforms, Inc.

Inventor： Jason Schissel , Emmanouil Koukoumidis , Shane Haladuick , Nicholas Robin , Fuchun Peng , Aleksey Sergeyevich Fadeev

IPC: G06F16/00 , G06V10/82 , G06F9/451 , G10L15/18 , G10L15/183 , G10L15/22 , G06F16/338 , G06F16/332 , G06F16/33 , G06N20/00 , G06F16/9535 , G06Q50/00 , H04L67/306 , G06F16/176 , G10L15/06 , G10L15/16 , G06F3/01 , G06F16/9032 , G06F16/2457 , H04L51/02 , G06F3/16 , G06N3/08 , G10L15/26 , G06F16/9038 , G06F16/904 , G06F40/30 , G06F40/40 , G06F16/22 , G06F16/23 , G06F7/14 , H04L43/0882 , H04L43/0894 , H04L12/28 , H04L41/00 , H04L41/22 , H04W12/08 , G10L15/07 , G10L17/22 , G06N3/006 , G10L17/06 , G06F16/248 , G06F16/951 , G06F16/242 , G06F16/2455 , G10L15/02 , G10L15/187 , G06V20/10 , G06V40/20 , G06F40/295 , H04L51/52 , H04L51/216 , H04L67/50 , H04L67/5651 , H04L51/18 , H04L67/75 , G06F16/903 , G06F40/205 , G06F18/2411 , G06N7/01 , G06V10/764 , H04L67/10 , H04L51/046 , G10L13/00 , G10L13/04 , H04L67/53

CPC classification number: G06V10/82 , G06F3/011 , G06F3/013 , G06F3/017 , G06F3/167 , G06F7/14 , G06F9/453 , G06F16/176 , G06F16/2255 , G06F16/2365 , G06F16/243 , G06F16/248 , G06F16/24552 , G06F16/24575 , G06F16/24578 , G06F16/338 , G06F16/3323 , G06F16/3329 , G06F16/3344 , G06F16/904 , G06F16/9038 , G06F16/90332 , G06F16/90335 , G06F16/951 , G06F16/9535 , G06F18/2411 , G06F40/205 , G06F40/295 , G06F40/30 , G06F40/40 , G06N3/006 , G06N3/08 , G06N7/01 , G06N20/00 , G06Q50/01 , G06V10/764 , G06V20/10 , G06V40/28 , G10L15/02 , G10L15/063 , G10L15/07 , G10L15/16 , G10L15/183 , G10L15/187 , G10L15/1815 , G10L15/1822 , G10L15/22 , G10L15/26 , G10L17/06 , G10L17/22 , H04L12/2816 , H04L41/20 , H04L41/22 , H04L43/0882 , H04L43/0894 , H04L51/02 , H04L51/18 , H04L51/216 , H04L51/52 , H04L67/306 , H04L67/535 , H04L67/5651 , H04L67/75 , H04W12/08 , G06F2216/13 , G10L13/00 , G10L13/04 , G10L2015/223 , G10L2015/225 , H04L51/046 , H04L67/10 , H04L67/53

Abstract: In one embodiment, a method includes, by a client system, receiving a user input from the first user of an online social network, where the user input is associated with a subject and an intent, determining whether one or more agents associated with the intent are able to resolve the user input, identifying, responsive to determining that the one or more agents are not able to resolve the user input, one or more entities related to the subject, where each identified entity is connected to the first user via the online social network, and presenting, at the client system, one or more recommendations to the first user corresponding to the one or more entities.

3.

发明公开
GENERATING CONTEXTUALLY RELEVANT TEXT TRANSCRIPTS OF VOICE RECORDINGS WITHIN A MESSAGE THREAD 审中-公开

公开(公告)号：US20230223026A1

公开(公告)日：2023-07-13

申请号：US18172960

申请日：2023-02-22

Applicant: Meta Platforms, Inc.

Inventor： James Matthew Grichnik , Chetan Parag Gupta , Fuchun Peng , Yinan Zhang , Si Chen

IPC: G10L15/26 , H04W4/21 , G10L15/08 , H04L51/216 , H04L51/52 , G06Q50/00 , H04L67/306

CPC classification number: G10L15/26 , H04W4/21 , G10L15/08 , H04L51/216 , H04L51/52 , G06Q50/01 , H04L67/306

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating contextually relevant transcripts of voice recordings based on social networking data. For instance, the disclosed systems receive a voice recording from a user corresponding to a message thread including the user and one or more co-users. The disclosed systems analyze acoustic features of the voice recording to generate transcription-text probabilities. The disclosed systems generate term weights for terms corresponding to objects associated with the user within a social networking system by analyzing user social networking data. Using the contextually aware term weights, the disclosed systems adjust the transcription-text probabilities. Based on the adjusted transcription-text probabilities, the disclosed systems generate a transcript of the voice recording for display within the message thread.

4.

发明授权
Combining machine-learning and social data to generate personalized recommendations 有权

公开(公告)号：US11514333B2

公开(公告)日：2022-11-29

申请号：US15966203

申请日：2018-04-30

Applicant: Meta Platforms, Inc.

Inventor： Kun Han , Fuchun Peng , Benoit Dumoulin , Bo Zeng

IPC: G06N5/02 , G06N20/00 , G06F16/2457

Abstract: A computing device receives a message including a request for a recommendation. A representation of a hypothetical ideal recommendation to provide in response to the message is determined based on the message content. Data regarding entities that are potential recommendations are retrieved from a data store, the data regarding each entity including a representation of the entity (e.g., a vector) derived from factual information about the entity and opinions of other users of the entity. Ranking scores are determined for at least a subset of the entities based on the difference between the entity representations and the representation of the hypothetical ideal recommendation. An entity to recommend is selected based on the ranking scores and a reply to the message is sent that identifies the selected entity.

5.

发明授权
Content suggestions for content digests for assistant systems 有权

公开(公告)号：US11887359B2

公开(公告)日：2024-01-30

申请号：US17375473

申请日：2021-07-14

Applicant: Meta Platforms, Inc.

Inventor： Zheng Zhou , Kun Han , Fuchun Peng

IPC: G06V10/82 , G10L15/18 , G06F16/33 , G06F16/90 , G06F16/24 , G06F16/95 , G06N20/00 , G06V20/10 , G06F9/451 , G10L15/183 , G10L15/22 , G06F16/338 , G06F16/332 , G06F16/9535 , G06Q50/00 , H04L67/306 , G06F16/176 , G10L15/06 , G10L15/16 , G06F3/01 , G06F16/9032 , G06F16/2457 , H04L51/02 , G06F3/16 , G06N3/08 , G10L15/26 , G06F16/9038 , G06F16/904 , G06F40/30 , G06F40/40 , G06F16/22 , G06F16/23 , G06F7/14 , H04L43/0882 , H04L43/0894 , H04L12/28 , H04L41/00 , H04L41/22 , H04W12/08 , G10L15/07 , G10L17/22 , G06N3/006 , G10L17/06 , G06F16/248 , G06F16/951 , G06F16/242 , G06F16/2455 , G10L15/02 , G10L15/187 , G06V40/20 , G06F40/295 , H04L51/52 , H04L51/216 , H04L67/50 , H04L67/5651 , H04L51/18 , H04L67/75 , G06F16/903 , G06F40/205 , G06F18/2411 , G06N7/01 , G06V10/764 , H04L67/10 , H04L51/046 , G10L13/00 , G10L13/04 , H04L67/53

CPC classification number: G06V10/82 , G06F3/011 , G06F3/013 , G06F3/017 , G06F3/167 , G06F7/14 , G06F9/453 , G06F16/176 , G06F16/2255 , G06F16/2365 , G06F16/243 , G06F16/248 , G06F16/24552 , G06F16/24575 , G06F16/24578 , G06F16/338 , G06F16/3323 , G06F16/3329 , G06F16/3344 , G06F16/904 , G06F16/9038 , G06F16/90332 , G06F16/90335 , G06F16/951 , G06F16/9535 , G06F18/2411 , G06F40/205 , G06F40/295 , G06F40/30 , G06F40/40 , G06N3/006 , G06N3/08 , G06N7/01 , G06N20/00 , G06Q50/01 , G06V10/764 , G06V20/10 , G06V40/28 , G10L15/02 , G10L15/063 , G10L15/07 , G10L15/16 , G10L15/183 , G10L15/187 , G10L15/1815 , G10L15/1822 , G10L15/22 , G10L15/26 , G10L17/06 , G10L17/22 , H04L12/2816 , H04L41/20 , H04L41/22 , H04L43/0882 , H04L43/0894 , H04L51/02 , H04L51/18 , H04L51/216 , H04L51/52 , H04L67/306 , H04L67/535 , H04L67/5651 , H04L67/75 , H04W12/08 , G06F2216/13 , G10L13/00 , G10L13/04 , G10L2015/223 , G10L2015/225 , H04L51/046 , H04L67/10 , H04L67/53

Abstract: In one embodiment, a method includes, by one or more computing systems, receiving, from a client system via an assistant xbot, a first audio input from a user, parsing the first audio input to identify a request for a content digest from an online social network, retrieving a plurality of content objects from the online social network, each of the content objects being accessible by the user, generating a customized newsfeed summary based on a determined semantical meaning of each of the plurality of content objects, and sending, to the client system via the assistant xbot, instructions for presenting an audio clip to the user responsive to the request for the content digest, wherein the audio clip comprises the customized newsfeed summary.

6.

发明公开
Systems and Methods for Implementing Smart Assistant Systems 审中-公开

公开(公告)号：US20230245654A1

公开(公告)日：2023-08-03

申请号：US18157413

申请日：2023-01-20

Applicant: Meta Platforms, Inc.

Inventor： Akshat Shrivastava , Shrey Desai , Anchit Gupta , Ali Elkahky , Aleksandr Livshits , Alexander Kolmykov-Zotov , Ahmed Aly , Jinsong Yu , Manali Anand Naik , Shuhui Yang , Baiyang Liu , Surya Teja Appini , Tarun Vir Singh , Hang Su , Jiedan Zhu , Fuchun Peng , Shoubhik Bhattacharya , Kshitiz Malik , Shreyan Bakshi , Akash Bharadwaj , Harish Srinivas , Xiao Yang , Zhuangqun Huang , Gil Keren , Duc Hoang Le , Ahmed Kamal Atwa Mohamed , Zhe Liu , Pranab Mohanty

IPC: G10L15/22 , G10L15/18 , G10L15/30 , G10L15/06 , G10L15/197 , H04L9/40

CPC classification number: G10L15/22 , G10L15/1815 , G10L15/30 , G10L15/063 , G10L15/197 , H04L63/0428 , G10L2015/223 , G10L2015/086

Abstract: In one embodiment, a system includes an automatic speech recognition (ASR) module, a natural-language understanding (NLU) module, a dialog manager, one or more agents, an arbitrator, a delivery system, one or more processors, and a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to receive a user input, process the user input using the ASR module, the NLU module, the dialog manager, one or more of the agents, the arbitrator, and the delivery system, and provide a response to the user input.

7.

发明授权
Assisting users with efficient information sharing among social connections 有权

公开(公告)号：US11429649B2

公开(公告)日：2022-08-30

申请号：US16011062

申请日：2018-06-18

Applicant: Meta Platforms, Inc.

Inventor： Jinsong Yu , Zhengping Zuo , Guowei Shieh , Fuchun Peng

IPC: G06F16/332 , H04L67/306 , G06F9/451 , G10L15/18 , G10L15/183 , G10L15/22 , G06F16/338 , G06F16/33 , G06N20/00 , G06F16/9535 , G06Q50/00 , H04L67/50 , G06F16/176 , G10L15/06 , G10L15/16 , G06F3/01 , G06F16/9032 , G06F16/2457 , H04L51/02 , G06F3/16 , G06K9/62 , G06N3/08 , G10L15/26 , G06F16/9038 , G06F16/904 , G06F40/30 , G06F40/40 , G06F16/22 , G06F16/23 , G06F7/14 , H04L43/0882 , H04L43/0894 , H04L67/5651 , H04L12/28 , H04L41/00 , H04L41/22 , H04W12/08 , G10L15/07 , G10L17/22 , H04L51/00 , G06N3/00 , G10L17/06 , G06F16/248 , G06F16/951 , G06F16/242 , G06F16/2455 , G10L15/02 , G06F16/903 , G06F40/205 , G10L15/187 , G06V20/10 , G06V40/20 , G06F40/295 , H04L51/52 , H04L67/53 , H04L67/10 , H04L51/046 , G10L13/00 , G10L13/04

Abstract: In one embodiment, a method includes receiving a sharing request to share content generated during a current dialog session from a client system associated with a first user, identifying one or more content objects associated with the sharing request based on a natural-language understanding module, wherein the one or more content objects were previously generated during the current dialog session, determining one or more second users the sharing request is directed to based on a user profile associated with first user, and sending instructions for accessing one or more of the identified content objects to one or more client systems associated with the one or more second users.

8.

发明授权
Private language model adaptation for speech recognition 有权

公开(公告)号：US12136416B1

公开(公告)日：2024-11-05

申请号：US17857384

申请日：2022-07-05

Applicant: Meta Platforms, Inc.

Inventor： Zhe Liu , Ke Li , Fuchun Peng

IPC: G10L15/16 , G10L15/06 , G10L15/30 , G10L15/32

Abstract: In one embodiment, a method includes accessing a decoded hypothesis corresponding to an utterance, computing a predicted probability of observing each token in the decoded hypothesis by having a local first machine-learning model process the decoded hypothesis, computing a confidence score for each token in the decoded hypothesis by having a second machine-learning model process the decoded hypothesis, where the confidence score indicates a degree of confidence for the token to be observed at its position, calculating a loss for the computed predicted probabilities of observing tokens in the decoded hypothesis based on the computed confidence scores, and updating parameters of the local first machine-learning model based on the calculated loss.