Amazon Technologies, Inc.

Bharath Bhimanaik Kumar

Fred Torok

Gonzalo Alvarez Barrio

Daniel Wade Hitchcock

Yogesh Vilas Golwalkar

Shantanu Vikas Kurhekar

Dharinee Gupta

Frederic J Deramat

Apoorv Naik

Kevin J Steuer, Jr

Matthew Todd Kaufman

Chenlei Guo

Abraham Martin Passaglia

Xing Fan

Ganesha Batta

Natalie Thuy-Tien Nguyen

Kerry Hammil

Naresh Narayanan

Anurag Sharma

Da Teng

Fnu Palak

Zhengyang Wu

Gilles-Arnaud Bleu-Laine

John Charles Howard

Alok Upadhyay

Choong Ryeol Lee

Sixing Lu

Puyang Xu

Long Zhang

Carlos Leija

Sharad Chaurasia

Chetan Kishor Rathod

Nibha Dadheech

Dinesh Malla

Roy Lee Scott

Raghuvir Mukeshkumar Songhela

Muhammad Bilal Khokhar

Mihail C Dinescu

Shilong Yao

Ajay Gowribidanur Ramesh

Techniques for determining user identification and attributing the user identification to a touch input received at a touch screen enabled electronic device are described. Some embodiments may include a touch screen enabled electronic device performing facial recognition to determine the identification of a user providing a touch input to the touch screen enabled electronic device. In some embodiments, the user identification is determined from a group of users associated with the electronic device. The touch input may correspond to an action or request, such as selecting an icon on the touch screen. In some embodiments, output data may be generated for display on the touch screen in response to the selected action or request. The user identification determined from the facial recognition may be used to personalize or customize, such as based on user preferences, the output data for display on the touch screen.

User identification attribution for touch interactions

Techniques for generating tasks to be completed in order to perform an action responsive to a user input and, for a given task, shortlisting available components to those that are relevant for the task are described. The system processes a user input to determine tasks to be completed in order to perform an action responsive to the user input. The system determines a priority of the tasks and selects a top-ranked task. The system determines descriptions of processing performable by components that are semantically similar to the current task, and requests a description of the function the corresponding components would perform for the current task. Based on the received descriptions, the system selects one or more components to perform the task. Thereafter, the system causes the action to be performed and outputs a response to the user input.

Natural language processing

Disclosed are various embodiments for person-based authorization for shared account systems. In one embodiment, a service receives a user request from a client device associated with an account to perform an action using an application. The service then identifies a user originating the user request. The service generates a token that includes an account identifier corresponding to the account and a person identifier corresponding to the user. The service sends the user request and the token to a provider of the application.

Person-based authorization for shared account systems

Systems and methods for pairing-less device connectivity are disclosed. For example, a group of primary devices are authorized to establish a non-bonded connection with a given secondary device. When the secondary device is in proximity of at least one of the group of primary devices, that primary device may receive a wireless beacon from the secondary device. The system may identify the primary device as an authorized device, perform user presence confirmation processes, and send a command to the primary device to establish the non-bonded connection. Encryption using a network layer or a presentation layer and an application layer of a computer network, instead of a link layer, is utilized for secure data transmission over the non-bonded connection.

Pairing-less device connectivity

Systems and methods for presence-based application invocation are disclosed. For example, presence of a personal device and/or user associated with a personal device is detected at a primary device. When account data associated with the personal device and the primary device correspond, checks are performed to determine if automatic invocation of an application associated with the personal device should be performed. Those checks include determining whether one or more conditions are satisfied, determining current usage of the application and/or the primary device indicates desirability to automatically invoke the application, and/or whether the application has been enabled for use on the primary device.

Presence-based application invocation

Systems and methods for integration of speech processing functionality with organization systems are disclosed. For example, a voice interface application may be created to enable a voice interface functionality for devices associated with an organization. Space identifiers of spaces of the organization may be created and associated with the voice interface application. Devices associated with the space identifiers may be enabled for utilizing the voice interface application and may be set up utilizing wireless network identifiers associated with the spaces and/or the organization.

Integration of speech processing functionality with organization systems

Techniques for prioritizing resources of various users, associated with a device, when responding to a user input received from the device are described. When a user input is received from a device, a system may generate a resource list for a group profile (e.g., a household profile) and each user profile (including any guest user profile) associated with the device. Each resource list may include the catalogs of resources (e.g., songs of a playlist, contacts of a contact list, etc.) of the group profile or user profile. The system may also generate a weight matrix including a respective weight for each catalog of each resource list. Various processing components (e.g., an automatic speech recognition component, a natural language understanding component, and an entity resolution component) may process using the resource lists and the weight matrix to determine an output responsive to the user input.

Resource selection for processing user inputs

Disclosed are various embodiments for determining authentication assurance from a combination of historical and runtime-provided inputs. An authentication request associated with an account is received. A composite measure of authentication assurance is determined from a combination of a historical measure of authentication assurance and a runtime measure of authentication assurance. A response to the authentication request is generated based at least in part on the composite measure of authentication assurance.

Determining authentication assurance from historical and runtime-provided inputs

Disclosed are various embodiments for determining authentication assurance using algorithmic decay. In an embodiment, an authentication request associated with an account is received. At least one historical authentication event associated with the account is determined. A measure of authentication assurance is determined based at least in part on applying an exponential time decay to at least one authentication assurance value individually corresponding to the historical authentication event(s). A response to the authentication request is generated based at least in part on the measure of authentication assurance.

Determination of authentication assurance via algorithmic decay

Disclosed are various embodiments for determining authentication assurance based on both user-level and account-level indicators. An authentication request associated with an account is received responsive to an input from a user via a user interface. A user-level measure of authentication assurance corresponding to the user is determined. An account-level measure of authentication assurance corresponding to the account is determined. A composite measure of authentication assurance is then determined from a combination of the user-level measure of authentication assurance and the account-level measure of authentication assurance. A response to the authentication request is generated based at least in part on comparing the composite measure of authentication assurance to a threshold.

Determining authentication assurance from user-level and account-level indicators

This disclosure is directed to techniques and systems to enable customers to make secure electronic payments to entities (e.g., merchants, vending machines, etc.). The entities may be at brick-and-mortar locations or other locations where the entities are 'offline' and may not readily receive payments from customers that have payment accounts stored and managed by a host. In various embodiments, a customer may direct the host to transfer a payment to a merchant after the customer and merchant exchange a code that includes a payment instruction. The code may be used in place of usernames, passwords, or other personal information and may be difficult for others (e.g., bystanders, etc.) to intercept. After the exchange of the code, the customer may authorize the host to a transfer payment to the merchant based on the payment instruction.

Offline payment processing

Disclosed are various embodiments of systems, methods, and programs embodied in computer readable mediums for generating item purchase recommendations. To provide such a recommendation, first data is accessed using a server, the first data comprising an interaction history of an entity with respect to at least one network site. Also, second data is accessed using the server, the second data comprising a record of use of media by the entity on at least one media device remote to the server. An item recommendation is generated in the server for the entity based on the first and second data.

Generating item recommendations

Growing community of inventors

Sammamish, WA, United States of America

Bharath Bhimanaik Kumar