Amazon Technologies, Inc. patent applications on April 3rd, 2025
Patent Applications by Amazon Technologies, Inc. on April 3rd, 2025
Amazon Technologies, Inc.: 14 patent applications
Amazon Technologies, Inc. has applied for patents in the areas of G06N3/0455 (2), G06F9/50 (2), G10L15/22 (1), H04L9/40 (1), G06F40/20 (1) G06F9/5027 (1), G06F9/5077 (1), G06F16/3344 (1), G06F21/629 (1), G06F40/205 (1)
With keywords such as: language, computing, natural, data, generative, knowledge, machine, request, learning, and application in patent application abstracts.
Patent Applications by Amazon Technologies, Inc.
Inventor(s): Deepti Laxman RAGHA of Sunnyvale CA US for amazon technologies, inc., Pratyush Kumar RANJAN of Arlington VA US for amazon technologies, inc., Michael PHAM of Seattle WA US for amazon technologies, inc., Maximiliano MACCANTI of Redmond WA US for amazon technologies, inc.
IPC Code(s): G06F9/50
CPC Code(s): G06F9/5027
Abstract: techniques for caching in a machine learning model (ml) hosting service are described. ml model usage data is aggregated from host usage data provided from each host of a first set of hosts, the ml model usage data including, for a particular ml model, a number of inference requests to the particular ml model. a priority order of hosts in a second set of hosts to service an inference request for the particular ml model is calculated. based on the ml model usage data and the priority order, a set of ml models to load to a particular host in the second set of hosts is determined. the particular host is caused to load the set of ml models. a router is updated to direct ml model inference requests amongst the second set of hosts.
Inventor(s): Hari Ohm Prasath Rajagopal of Tracy CA US for amazon technologies, inc., Shivendra Panicker of Seattle WA US for amazon technologies, inc., Prashant Kumar Singh of Seattle WA US for amazon technologies, inc., Amit Gupta of Bellevue WA US for amazon technologies, inc.
IPC Code(s): G06F9/50
CPC Code(s): G06F9/5077
Abstract: systems and methods are provided for an on-demand code execution service comprising a set of computing devices for on-demand execution of function code while continuing to facilitate executing long-running background processes. a subset of resources may be initialized based, at least in part, on the application configuration data including at least a request-response process, a background process, and a lesser set of computing resources for the background process. after the execution of the background process has begun, a first request may be received. the on-demand code execution service may increase computing resources to a larger set of computing resources to generate a first response to the first request. the first response may then be provided to an external set of computing resources. after determining that the queue contains no additional requests, the on-demand code execution service may decrease the level of computing resources to the lesser set of computing resources.
Inventor(s): Karthik Saligrama Shreeram of Bothell WA US for amazon technologies, inc., Varun Sembium Varadarajan of Redmond WA US for amazon technologies, inc., Sanjukta Ghosh of Chatham Township NJ US for amazon technologies, inc., Nidish Rajendran Nair of Brooklyn NY US for amazon technologies, inc., Sachin Bangalore Raj of Black Diamond WA US for amazon technologies, inc., En Lin of Flushing NY US for amazon technologies, inc., Jeff Gregory Registre of Elmsford NY US for amazon technologies, inc., Jaydeep Ramani of New York NY US for amazon technologies, inc., Inan Tainwala of Brooklyn NY US for amazon technologies, inc., Kartik Mittal of Jersey City NJ US for amazon technologies, inc., Pankhuri Gupta of West New York NJ US for amazon technologies, inc., Tiejun Zhao of Skillman NJ US for amazon technologies, inc.
IPC Code(s): G06F16/33, G06F16/332
CPC Code(s): G06F16/3344
Abstract: distributed orchestration of data retrieval for generative machine learning model may be performed. when a natural language request to perform a natural language task is received that is associated with a generative application, one or more data retrievers may be selected to access associated data repositories according to a previously specified retrieval configuration for the generative natural language application. the data may then be obtained by the selected data retrievers and used to generate a prompt to a generative machine learning model. a result of the generative machine learning model may then be used to provide a response to the natural language request to perform the natural language task.
Inventor(s): Karthik Saligrama Shreeram of Bothell WA US for amazon technologies, inc., Varun Sembium Varadarajan of Redmond WA US for amazon technologies, inc., Sanjukta Ghosh of Chatham Township NJ US for amazon technologies, inc., Nidish Rajendran Nair of Brooklyn NY US for amazon technologies, inc., Surya Ram of Brooklyn NY US for amazon technologies, inc., Ashwin Shukla of Jersey City NJ US for amazon technologies, inc., Sachin Bangalore Raj of Black Diamond WA US for amazon technologies, inc., Ishaan Berry of Maple Valley WA US for amazon technologies, inc., Ji Hoon Kim of New York NY US for amazon technologies, inc., Kartik Mittal of Jersey City NJ US for amazon technologies, inc., Pankhuri Gupta of West New York NJ US for amazon technologies, inc., Tiejun Zhao of Skillman NJ US for amazon technologies, inc.
IPC Code(s): G06F21/62
CPC Code(s): G06F21/629
Abstract: intent classification is performed for executing a retrieval augmented generation pipeline for natural language tasks using a generative machine learning model. a natural language generative application with associated data repositories may submit a natural language task. a classification machine learning model is used to determine an intent for the natural language request. a number of iterations of a retrieval pipeline may be determined to perform the natural language task based on the intent. the natural language request may be processed through a retrieval pipeline according to the determined number of iterations before returning a result to the request.
Inventor(s): Zhiheng Huang of Sunnyvale CA US for amazon technologies, inc., Yue Yang of Redmond WA US for amazon technologies, inc., Lan Liu of Santa Clara CA US for amazon technologies, inc.
IPC Code(s): G06F40/205, G06F40/284, G06N3/0455
CPC Code(s): G06F40/205
Abstract: an index is created with split documents to retrieve and augment generation of a response to a natural language request using a generative machine learning model. when a natural language request is received, a search representation is generated and used to retrieve candidate portions of documents from the index. a relevancy ranking is performed to identify relevant portions of documents from the candidates and provide the relevant portions to prompt a generative machine learning model to provide a result for the natural language request.
Inventor(s): Samuel Bayless of Seattle WA US for amazon technologies, inc., Nadia Labai of Redmond WA US for amazon technologies, inc., Ora Yrjo Lassila of Hollis NH US for amazon technologies, inc.
IPC Code(s): G06N3/042, G06N3/006, G06N3/0455
CPC Code(s): G06N3/042
Abstract: techniques for a knowledge-graph system to use large language models (llms) to build knowledge graphs to answer queries submitted to a chatbot by users. the knowledge-graph system builds the knowledge graph using answers produced by an llm for novel queries. the chatbot will continue to use the llm to answer novel queries, but the chatbot may harness the knowledge graph to answer repeat questions to gain various efficiencies over llm-backed chatbots. for example, the knowledge-graph system may easily debug or otherwise improve the answers in knowledge graphs, store provenance information in knowledge graphs, and augment the knowledge graphs using other data sources. thus, the reliability and correctness of chatbots will be improved as the bugs and inaccuracies in answers provided by the llm will be corrected in the knowledge graphs, but the chatbots can still harness the abilities of llms to provide answers across various subject-matter domains.
Inventor(s): Robert JONES of Beaverton OR US for amazon technologies, inc., Aaron Robert BRADLEY of Boulder CO US for amazon technologies, inc., Leah Corene DANIELS of Portland OR US for amazon technologies, inc., Leonardo Mendonça DE MOURA of Redmond WA US for amazon technologies, inc.
IPC Code(s): G06N3/08, G06N3/0475
CPC Code(s): G06N3/08
Abstract: generative pre-trained large language models (llms) can create domain-specific text answers in various formats like json, xml, html, sql, or programming languages. however, llms may “hallucinate,” generating incorrect or nonsensical answers that diverge from reality, thus eroding trust in their outputs or worse. disclosed techniques use a sampling-based approach and an equivalence checker. multiple answers (samples) to a prompt are generated by the llm; if they are equivalent, the llm is likely answering correctly. if the samples disagree or contradict, it's more likely that the llm is hallucinating, or the prompt is ambiguous. an automated reasoning equivalence checker is utilized to verify the samples' functional equivalency, providing a method to detect and possibly rectify hallucination issues in llm-generated answers.
Inventor(s): Zhiheng Huang of Sunnyvale CA US for amazon technologies, inc., Yue Yang of Redmond WA US for amazon technologies, inc., Lan Liu of Santa Clara CA US for amazon technologies, inc., Yuhao Zhang of San Jose CA US for amazon technologies, inc., Peng Qi of Newcastle WA US for amazon technologies, inc.
IPC Code(s): G06N20/00, G06F40/30, G06F40/40
CPC Code(s): G06N20/00
Abstract: template-based tuning is performed on a generative machine learning model where a shared template is used to tune the generative machine learning model across multiple natural language tasks. when a natural language request to perform a natural language task is received, portions of a shared template to complete are identified as part of generating a prompt. the generative machine learning model is instructed according to the generated prompt and a response to the request is returned based on a result of the generative machine learning model.
Inventor(s): John Baker of Bellevue WA US for amazon technologies, inc., Anubhav Mishra of Seattle WA US for amazon technologies, inc., Bangrui Liu of Seattle WA US for amazon technologies, inc., Christopher Michael Hittner of Seattle WA US for amazon technologies, inc., Sravan Babu Bodapati of Redmond WA US for amazon technologies, inc., Harshal Pimpalkhute of Redmond WA US for amazon technologies, inc., Katrin Kirchhoff of Seattle WA US for amazon technologies, inc., Anuj Gautam Surana of Mountlake Terrace WA US for amazon technologies, inc., Yilai Su of Mercer Island WA US for amazon technologies, inc., Brandon Louis Mendez of Seattle WA US for amazon technologies, inc., Chengshun Zhang of Seattle WA US for amazon technologies, inc.
IPC Code(s): G10L15/22, G10L13/027, G10L15/08
CPC Code(s): G10L15/22
Abstract: a set of alternative vocal input styles for specifying a parameter of a dialog-driven application is determined. during execution of the application, an audio prompt requesting input in one of the styles is presented. a value of the parameter is determined by applying a collection of analysis tools to vocal input obtained after the prompt is presented. a task of the application is initiated using the value.
20250111857. UNIFIED AUDIO SUPPRESSION MODEL_simplified_abstract_(amazon technologies, inc.)
Inventor(s): Ritwik Giri of Redwood City CA US for amazon technologies, inc., Zhepei Wang of Santa Clara CA US for amazon technologies, inc., Devansh Shah of Sunnyvale CA US for amazon technologies, inc., Jean-Marc Valin of Montreal CA for amazon technologies, inc., Michael Mark Goodwin of Scotts Valley CA US for amazon technologies, inc.
IPC Code(s): G10L21/0208, G10L25/30, H04M3/56
CPC Code(s): G10L21/0208
Abstract: examples herein provide an approach to enhance an audio mixture of a teleconference application by switching between noise suppression modes using a single model. specifically, a machine learning (ml) model may be configured to, in response to receiving an audio mixture representation as input, suppress either a background noise of the audio mixture or suppress all noise of the audio mixture except a user's voice. in some examples, the ml model may be trained on speech and background noise training data during a training phase. in addition, the ml model may be trained on a user's voice during an enrollment phase. in addition, during an inference phase, the ml model may enhance the audio mixture by suppressing a portion of the audio mixture.
Inventor(s): Ryan Hegar of Happy Valley OR US for amazon technologies, inc., Gregory Truax of Portland OR US for amazon technologies, inc., Michael Cronk of Sherwood OR US for amazon technologies, inc., Paul S. Nahlous of San Anselmo CA US for amazon technologies, inc., Orlando Maldonado of Bellevue WA US for amazon technologies, inc.
IPC Code(s): H04L45/24, H04L45/12
CPC Code(s): H04L45/24
Abstract: approaches are disclosed for providing path diversity in a data transmission network. a primary transmission path can be selected through a network, such as a backbone network, based on factors such as cost of transmission. at least one waypoint can be selected that is to be included in a secondary transmission path. the waypoint(s) can be selected such that the secondary transmission path will have few, if any, network components in common with the primary transmission path, providing significant path diversity. the waypoint(s) can be selected based on a cost ratio or other such factor. in the event of a failure of transmission of a data packet over one of the transmission paths, a second transmission attempt can be performed using the same path or the other transmission path, or both.
Inventor(s): Samuel Bayless of Seattle WA US for amazon technologies, inc., Nadia Labai of Redmond WA US for amazon technologies, inc., Ora Yrjo Lassila of Hollis NH US for amazon technologies, inc.
IPC Code(s): H04L51/02, G06F40/20
CPC Code(s): H04L51/02
Abstract: techniques for a knowledge-graph system to use large language models (llms) to build knowledge graphs to answer queries submitted to a chatbot by users. the knowledge-graph system builds the knowledge graph using answers produced by an llm for novel queries. the chatbot will continue to use the llm to answer novel queries, but the chatbot may harness the knowledge graph to answer repeat questions to gain various efficiencies over llm-backed chatbots. for example, the knowledge-graph system may easily debug or otherwise improve the answers in knowledge graphs, store provenance information in knowledge graphs, and augment the knowledge graphs using other data sources. thus, the reliability and correctness of chatbots will be improved as the bugs and inaccuracies in answers provided by the llm will be corrected in the knowledge graphs, but the chatbots can still harness the abilities of llms to provide answers across various subject-matter domains.
Inventor(s): Hari Ohm Prasath Rajagopal of Tracy CA US for amazon technologies, inc., Prashant Kumar Singh of Seattle WA US for amazon technologies, inc.
IPC Code(s): H04L9/40
CPC Code(s): H04L63/105
Abstract: systems and methods are provided for managing computing services for an application comprising a plurality of virtual computing components executing on one or more host computing devices, wherein a service virtual computing component is to perform application functionality, and wherein a system computing component is to perform system functionality including management of the application virtual computing component; determining the service virtual computing component is to execute using a first access credential to provide a first computing service to the application virtual computing component, and the service virtual computing component is to execute using a second access credential to provide a second computing service to the system computing component, wherein the first access credential is assigned a different set of computing resource access permissions than the second access credential.
20250113160. RETROACTIVE GEOFENCE EVENTS_simplified_abstract_(amazon technologies, inc.)
Inventor(s): Swagata Prateek of Vancouver CA for amazon technologies, inc., Olivier Joseph Serge Durand de Gevigney of Squamish CA for amazon technologies, inc., Cory Eden of Vancouver CA for amazon technologies, inc.
IPC Code(s): H04W4/021
CPC Code(s): H04W4/021
Abstract: a plurality of location indications may be received that indicate locations of an object at a plurality of times. a plurality of geofence indications that indicate that the object is within a geofence may be generated based on the plurality of location indications. a plurality of notifications of a plurality of geofence events corresponding to the object may be provided, to an account, based on the plurality of geofence indications. the plurality of geofence events may include a geofence entering event and a geofence exiting event. an out-of-order location indication may be detected within the plurality of location indications. a retroactive geofence event regarding which the account has not yet been notified may be determined based on the out-of-order location indication. an additional notification of the retroactive geofence event may be provided to the account.
Amazon Technologies, Inc. patent applications on April 3rd, 2025
- Amazon Technologies, Inc.
- G06F9/50
- CPC G06F9/5027
- Amazon technologies, inc.
- CPC G06F9/5077
- G06F16/33
- G06F16/332
- CPC G06F16/3344
- G06F21/62
- CPC G06F21/629
- G06F40/205
- G06F40/284
- G06N3/0455
- CPC G06F40/205
- G06N3/042
- G06N3/006
- CPC G06N3/042
- G06N3/08
- G06N3/0475
- CPC G06N3/08
- G06N20/00
- G06F40/30
- G06F40/40
- CPC G06N20/00
- G10L15/22
- G10L13/027
- G10L15/08
- CPC G10L15/22
- G10L21/0208
- G10L25/30
- H04M3/56
- CPC G10L21/0208
- H04L45/24
- H04L45/12
- CPC H04L45/24
- H04L51/02
- G06F40/20
- CPC H04L51/02
- H04L9/40
- CPC H04L63/105
- H04W4/021
- CPC H04W4/021
