公开(公告)号：US20240346629A1

公开(公告)日：2024-10-17

申请号：US18301671

申请日：2023-04-17

申请人： ADOBE INC.

发明人： Midhun Harikumar ,  Venkata Naveen Kumar Yadav Marri ,  Ajinkya Gorakhnath Kale ,  Pranav Vineet Aggarwal ,  Vinh Ngoc Khuc

IPC分类号： G06T5/00 ,  G06F40/279 ,  G06T5/50

CPC分类号： G06T5/73 ,  G06F40/279 ,  G06T5/50

摘要： Systems and methods for image processing are described. Embodiments of the present disclosure obtain a text prompt for text guided image generation. A multi-modal encoder of an image processing apparatus encodes the text prompt to obtain a text embedding. A diffusion prior model of the image processing apparatus converts the text embedding to an image embedding. A latent diffusion model of the image processing apparatus generates an image based on the image embedding, wherein the image includes an element described by the text prompt.

公开(公告)号：US20240346103A1

公开(公告)日：2024-10-17

申请号：US18632779

申请日：2024-04-11

申请人： Content Square SAS

发明人： Charif Chaibainou ,  Gregory Riberon

IPC分类号： G06F16/957 ,  G06F16/901 ,  G06F40/279

CPC分类号： G06F16/9577 ,  G06F16/9027 ,  G06F40/279

摘要： The subject technology receives a snapshot of a webpage. The subject technology identifies a first set of targets included in the snapshot. The subject technology selects nodes corresponding to the identified first set of targets. The subject technology determines, based on a selected metric, metrics for the selected nodes. The subject technology determines a second set of nodes by filtering a number of nodes having a highest set of values of the metrics. The subject technology generates a first set of zones based on the second set of nodes. The subject technology provides the generated first set of zones for display on a client device.

公开(公告)号：US12118307B2

公开(公告)日：2024-10-15

申请号：US17746349

申请日：2022-05-17

申请人： SAP SE

发明人： Dilip Mamidela ,  Janaki Raam Vaidhyanathan

IPC分类号： G06F40/279 ,  H04L51/02

CPC分类号： G06F40/279 ,  H04L51/02

摘要： Various embodiments for a chatbot improvement system are described herein. An embodiment operates by receiving input from a user via a chatbot interface. A first vertical corresponding to the user is identified. The input from the user is interpreted based on a first set of keywords corresponding to the first vertical. A first confidence score is calculated for the first vertical based on the interpretation of the input using the first set of keywords. It is determined whether the first confidence score exceeds a threshold. If the threshold is exceeded, a response to the input is generated based on the first set of keywords. If the threshold is not exceeded, the response to the input based on the second set of keywords. The generated response is provided for display via the chatbot interface.

公开(公告)号：US12112132B2

公开(公告)日：2024-10-08

申请号：US17808214

申请日：2022-06-22

申请人： Optum Services (Ireland) Limited

发明人： Suman Roy ,  Ayan Sengupta ,  Michael Bridges ,  Amit Kumar

IPC分类号： G06F40/279 ,  G06F40/30 ,  G06F40/40 ,  G06N20/00

CPC分类号： G06F40/279 ,  G06F40/40 ,  G06N20/00 ,  G06F40/30

摘要： Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing natural language processing operations using an attention-based text encoder machine learning model that is trained using a multi-task training routine that is associated with two or more training tasks (e.g., a multi-task training routine that is associated with two or more sequential training tasks, a multi-training routine that is associated with two or more concurrent training tasks, and/or the like).

公开(公告)号：US12112131B2

公开(公告)日：2024-10-08

申请号：US17588043

申请日：2022-01-28

申请人： Salesforce, Inc.

发明人： Benjamin Newman ,  Nazneen Rajani ,  Prafulla Kumar Choubey

IPC分类号： G06F40/30 ,  G06F3/08 ,  G06F40/126 ,  G06F40/279 ,  G06N3/044

CPC分类号： G06F40/279 ,  G06F40/126 ,  G06N3/044

摘要： Embodiments described herein provide a system and method for extracting factual information. The system transforms a query into a natural language prompt in a format of a query subject and a queried relation. The system encodes, via an embedding layer of a pre-trained language model, the natural language prompt into a first embedding. The system encodes, via the adapter model, the first embedding into a second embedding based on a probability that the second embedding returns the factual information when the second embedding is fed the first attention layer of the pre-trained language model. The system decodes, by the first attention layer of the pre-trained language mode, the second embedding into a response to the query. The system extracts the factual information from the decoded response to the query.

公开(公告)号：US12112129B2

公开(公告)日：2024-10-08

申请号：US17527167

申请日：2021-11-16

申请人： Fujitsu Limited

发明人： Nuria Garcia Santa ,  Kendrick Cetina

IPC分类号： G10L15/16 ,  G06F18/214 ,  G06F40/169 ,  G06F40/226 ,  G06N3/04 ,  G10L15/06 ,  G10L15/07 ,  G10L15/18 ,  G06F40/279 ,  G06F40/295 ,  G10L15/183

CPC分类号： G06F40/226 ,  G06F18/214 ,  G06F40/169 ,  G06N3/04 ,  G10L15/063 ,  G10L15/075 ,  G10L15/16 ,  G10L15/18 ,  G06F40/279 ,  G06F40/295 ,  G10L2015/0635 ,  G10L15/1822 ,  G10L15/183

摘要： A method of training a neural network as a natural language processing, NLP, model, comprises: inputting annotated training data to first architecture portions of the neural network, the first architecture portions being executed respectively in a plurality of distributed client computing devices in communication with a server computing device, the training data being derived from text data private to the client computing device in which the first architecture portion is executed, the server computing device having no access to any of the private text data; deriving from the training data, using the first architecture portions, weight matrices of numeric weights which are decoupled from the private text data; concatenating the weight matrices, in a second architecture portion of the neural network executed in the server computing device, to obtain a single concatenated weight matrix; and training, on the second architecture portion, the NLP model using the concatenated weight matrix.

公开(公告)号：US20240330599A1

公开(公告)日：2024-10-03

申请号：US18738974

申请日：2024-06-10

申请人： GOOGLE LLC

发明人： Ilya Gennadyevich Gelfenbeyn ,  Artem Goncharuk ,  Pavel Aleksandrovich Sirotin

IPC分类号： G06F40/35 ,  G06F40/279 ,  G10L15/22 ,  G10L15/26

CPC分类号： G06F40/35 ,  G06F40/279 ,  G10L15/22 ,  G10L15/26 ,  G10L2015/228

摘要： A method for context-based natural language processing is disclosed herein. The method comprises maintaining a plurality of dialog system rules, receiving a user request from a Dialog System Interface, receiving one or more attributes associated with the user request from the Dialog System Interface or a user device, and identifying a type of context associated with the user request based on the user request and the one or more attributes. A context label is assigned to the user request associated with the type of context. Based on the context label and the user request, a particular dialog system rule is selected from the plurality of dialog system rules. A response to the user request is generated by applying the dialog system rule to at least a part of the user request.

公开(公告)号：US20240330570A1

公开(公告)日：2024-10-03

申请号：US18190557

申请日：2023-03-27

申请人： ATLASSIAN PTY LTD. ,  ATLASSIAN (US)LLC

发明人： Atri MANDAL ,  Prabu PALANISAMY

IPC分类号： G06F40/151 ,  G06F40/166 ,  G06F40/205 ,  G06F40/253 ,  G06F40/279 ,  G06F40/30

CPC分类号： G06F40/151 ,  G06F40/166 ,  G06F40/205 ,  G06F40/253 ,  G06F40/279 ,  G06F40/30

摘要： Apparatus, methods, and computer program products for generating UGC transformed alert data from a monitoring service alert are provided. An apparatus may include program code configured to cause the apparatus to retrieve a monitoring service alert, including a text string and user generated content (UGC) text. In addition, the example apparatus may be configured to programmatically parse the text string of the monitoring service alert to segregate the monitoring service alert into an alert message problem component and an alert auxiliary details component. Further, the apparatus may be configured to generate an alert message problem embedding and an alert message description embedding by applying feature extraction to the alert message problem component and the alert auxiliary details component, respectively. The example apparatus may further be configured to output UGC transformed alert data based on the alert message problem embedding and the alert message description embedding.

公开(公告)号：US12106383B2

公开(公告)日：2024-10-01

申请号：US18135366

申请日：2023-04-17

申请人： Capital One Services, LLC

发明人： Anh Truong ,  Galen Rafferty ,  Jeremy Goodsitt ,  Vincent Pham ,  Austin Walters ,  Alvin Hua

IPC分类号： G06Q40/00 ,  G06F16/2455 ,  G06F40/279 ,  G06Q30/016 ,  G06Q40/12

CPC分类号： G06Q40/12 ,  G06F16/2455 ,  G06F40/279 ,  G06Q30/016

摘要： Methods, systems, and apparatuses for correlating electronic communications related to financial transactions. A computing device may receive a first communication related to an update to a past financial transaction. The computing device may identify a second communication by querying, based on the first communication, a communications database. The first communication and second communication may be correlated using one or more natural language processing algorithms. Based on correlating the first communication and second communication, the computing device may identify a portion of the second communication corresponding to the at least one good or service of the past financial transaction by processing, using the one or more natural language processing algorithms, the second communication. The computing device may then cause output of data indicating a correlation between the first communication and the second communication, and the indication of the change to the at least one good or service.

公开(公告)号：US12105610B2

公开(公告)日：2024-10-01

申请号：US17486293

申请日：2021-09-27

申请人： ATLASSIAN PTY LTD. ,  ATLASSIAN US, INC.

发明人： Karthik Muralidharan ,  Sri Vardhamanan A ,  Aneesh Kundu

IPC分类号： G06F11/34 ,  G06F40/279 ,  G06N20/00

CPC分类号： G06F11/3409 ,  G06N20/00 ,  G06F40/279

摘要： Systems and methods provide techniques for more effective and efficient predictive monitoring of a software application framework. In response, embodiments of the present invention provide methods, apparatuses, systems, computing devices, and/or the like that are configured to enable effective and efficient predictive monitoring of a software application framework using incident signatures for the software application that are generated by using a natural language processing machine learning framework, a structured data processing machine learning model, and an incident severity level detection machine learning model.