Browse Prior Art Database

Ubiquitous passive listening process and system based on user interactions

IP.com Disclosure Number: IPCOM000241706D
Publication Date: 2015-May-23
Document File: 3 page(s) / 132K

Publishing Venue

The IP.com Prior Art Database

Abstract

An ubiquitous passive listening process/system that customizes actions based on customer requests tailored to the audience involved is disclosed. The system connects to the user's devices and/or services in order to take automatic actions for the user.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 44% of the total text.

Page 01 of 3

Ubiquitous passive listening process and system based on user interactions

Disclosed is an ubiquitous passive listening process/system that customizes actions based on customer requests tailored to the audience involved. The system connects to the user's devices and/or services in order to take automatic actions for the user. In addition, the system may detects who is in the room (or involved) at the moment of the action in order to customize the actions.

The system may be configured to passively listening to the user and react according to the appropriate context. The system may be on continuously. The system can detect the presence of other people by voice, Global Positioning System (GPS) , Near field communication (NFC), sensors and the like while passive listening. The system may also connected to the user's devices (i.e. television, digital video recorder, radio, phone, tablets, PCs, etc) and services and can take some actions upon those services or devices. The system performs actions and reacts according to the voice stream, rules, and filters applied based on user profile.

The passive listening system can use speech recognition to identify users within audible range to register them with the

device. Each passive listening device can also register users that have not spoken with the system. Once registered, the passive listening device continues to process streams of voice data in the cloud and performs actions on each stream based on the registered users profile. Upon identification with a passive listening device the users public profile data is available and their preferences can be communicated with other devices connected to the passive listening device. After

the user is registered, due to location or voice activation, filters and rules for each profile can be exercised based on their voice stream. Each user may have a profile that contain rules including but not limited to adding items to a shopping cart or wish list, downloading content to paired devices, providing likes and dislikes. From the profiles, custom recommendations can be created to fit the needs and requests of all registered users with the passive listening device.

The passive listening device separates voices into streams and sends each stream to the cloud. This may occur by first by identifying and registering the user with the passive listening device by voice. After registering, continued processing of the stream may occur based on the registered users account. The cloud preforms Natural Language Processing (NLP) on each stream applying rules and filters, and takes actions based on the users profile. The cloud provides connections to other cloud services each user has allowed access to such as email, retail services, etc.

In an example embodiment, the system recognizes voices to follow in people conversations or instructions (the user(s) can train the system to recognize personal voice(s)) (Note: This embodiment can be expanded to use other methods...