公开(公告)号：US12141536B1

公开(公告)日：2024-11-12

申请号：US18122301

申请日：2023-03-16

Applicant: Amazon Technologies, Inc.

Inventor： Sopan Khosla ,  Rashmi Gangadharaiah

IPC: G06F40/284 ,  G06F40/126 ,  G06F40/35 ,  G06N20/00 ,  H04L51/02

Abstract: Techniques for chatbot utterance routing in a provider network include jointly training a service classifier and a plurality of auxiliary classifiers based on a mixed service set of labeled chatbot utterance training examples to yield a trained service classifier. When a particular chatbot user utterance is received, the trained service classifier can be used to determine if the utterance is in-scope or out-of-scope, and if in-scope, to determine which service of a set of services in the provider network to which to route the utterance for further processing. By jointly training the service classifier with the auxiliary classifiers, the accuracy of the in-scope/out-of-scope determination by the trained service classifier is improved as well as its accuracy in routing the utterance to the appropriate service for processing the utterance as intended by the user.

公开(公告)号：US11863643B1

公开(公告)日：2024-01-02

申请号：US18193891

申请日：2023-03-31

Applicant: Amazon Technologies, Inc.

Inventor： Narjessadat Seyeditabari ,  Vinayshekhar Bannihatti Kumar ,  Rashmi Gangadharaiah ,  Deepak Seetharam Nadig ,  Ankit Kapoor ,  Fayun Luo

IPC: H04L67/50 ,  G06F40/284 ,  H04L67/306

CPC classification number: H04L67/535 ,  G06F40/284 ,  H04L67/306

Abstract: Clusters of users of networked services are defined based on tasks performed by such users during such networked services. Activities of the users during sessions of the networked services are tracked, and representations of such users or such activities are used to train a model to predict activities of users in the future, including but not limited to services utilized by such users, or pages visited by such users. Subsequently, when a user accesses a networked service during a session, activities of the user may be determined, and a representation of the session is provided as an input to the model, along with contextual information such as an identifier of the persona of the user. A next action, e.g., a service or a page utilized by the user, may be predicted based on outputs received from the model.

公开(公告)号：US20240202587A1

公开(公告)日：2024-06-20

申请号：US18344419

申请日：2023-06-29

Applicant: Amazon Technologies, Inc.

Inventor： Vinayshekhar Bannihatti Kumar ,  Rashmi Gangadharaiah ,  Dan Roth

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: Methods and systems are disclosed for a machine learning (ML) model training system that can remove the influence of specific data points in an efficient way. An ML training system can train multiple instances of a machine learning model on disjoint shards of data. Upon receiving a request to remove a specific data point, the ML training system can expunge the data point from its corresponding shard and only retrain the model instance for that specific shard. Each shard can be further divided into data slices, with each slice containing a portion of the data from the shard. During the training of each instance of the machine learning model, the ML training system can save model checkpoints after completion of training for each slice. Upon receiving a removal request, the related data point is removed from its respective slice, and the relevant model instance can be retrained starting from the last checkpoint before that slice had been previously used for training.

公开(公告)号：US11997177B1

公开(公告)日：2024-05-28

申请号：US18193876

申请日：2023-03-31

Applicant: Amazon Technologies, Inc.

Inventor： Narjessadat Seyeditabari ,  Vinayshekhar Bannihatti Kumar ,  Rashmi Gangadharaiah ,  Deepak Seetharam Nadig ,  Ankit Kapoor ,  Fayun Luo

IPC: H04L67/50 ,  G06F40/284 ,  H04L67/51

CPC classification number: H04L67/535 ,  G06F40/284 ,  H04L67/51

Abstract: Clusters of users of networked services are defined based on tasks performed by such users during such networked services. Activities of the users during sessions of the networked services are tracked, and representations of such users or such activities are used to train a model to predict activities of users in the future, including but not limited to services utilized by such users, or pages visited by such users. Subsequently, when a user accesses a networked service during a session, activities of the user may be determined, and a representation of the session is provided as an input to the model, along with contextual information such as an identifier of the persona of the user. A next action, e.g., a service or a page utilized by the user, may be predicted based on outputs received from the model.

公开(公告)号：US11818004B1

公开(公告)日：2023-11-14

申请号：US17936746

申请日：2022-09-29

Applicant: Amazon Technologies, Inc.

Inventor： Vinayshekhar Bannihatti Kumar ,  Rashmi Gangadharaiah ,  Sonia Ramnani ,  Grace Kitzmiller ,  Logan Douglas

IPC: G06F15/177 ,  H04L41/082 ,  H04L41/0866 ,  H04L41/084

CPC classification number: H04L41/082 ,  H04L41/0843 ,  H04L41/0866

Abstract: The present disclosure relates to systems and methods for providing a network-based service infrastructure configuration for a plurality of network-based services. A configuration service may identify one or more network-based services and actions required for the services based on analyzing customer input. After processing the customer input, the configuration service may automatically configure the infrastructure configuration based on analyzing the customer input. The configuration service may identify and verify attributes required by each identified service and its associated property values. The configuration service may configure the infrastructure configuration by selecting a template from the plurality of templates stored in a datastore.

公开(公告)号：US11580968B1

公开(公告)日：2023-02-14

申请号：US16455165

申请日：2019-06-27

Applicant: Amazon Technologies, Inc.

Inventor： Arshit Gupta ,  Peng Zhang ,  Rashmi Gangadharaiah ,  Garima Lalwani ,  Roger Scott Jenke ,  Hassan Sawaf ,  Mona Diab ,  Katrin Kirchhoff ,  Adel A. Youssef ,  Kalpesh N. Sutaria

IPC: G10L15/08 ,  G10L15/16 ,  G10L15/22 ,  H04L67/02 ,  G10L15/18 ,  G10L15/02

Abstract: Techniques are described for a contextual natural language understanding (cNLU) framework that is able to incorporate contextual signals of variable history length to perform joint intent classification (IC) and slot labeling (SL) tasks. A user utterance provided by a user within a multi-turn chat dialog between the user and a conversational agent is received. The user utterance and contextual information associated with one or more previous turns of the multi-turn chat dialog is provided to a machine learning (ML) model. An intent classification and one or more slot labels for the user utterance are then obtained from the ML model. The cNLU framework described herein thus uses, in addition to a current utterance itself, various contextual signals as input to a model to generate IC and SL predictions for each utterance of a multi-turn chat dialog.

公开(公告)号：US10963819B1

公开(公告)日：2021-03-30

申请号：US15716987

申请日：2017-09-27

Applicant: Amazon Technologies, Inc.

Inventor： Rashmi Gangadharaiah ,  Charles Elkan ,  Balakrishnan Narayanaswamy

IPC: G06Q10/02 ,  G06N3/04 ,  G06F40/44 ,  G06F40/56 ,  H04L12/58

Abstract: A goal-oriented dialog system interacts with a user over one or more turns of dialog to determine a goal expressed by the user; the dialog system may then act to fulfill the goal by, for example, calling an application-programming interface. The user may supply dialog via text, speech, or other communication. The dialog system includes a first trained model, such as a translation model, to encode the dialog from the user into a context vector; a second trained model, such as another translation model, determines a plurality of candidate probabilities of items in a vocabulary. A language model determines responses to the user based on the input from the user, the context vector, and the plurality of candidate probabilities.