Browse Prior Art Database

system and methods for recommending personalized multilingual content based on individual preference

IP.com Disclosure Number: IPCOM000246145D
Publication Date: 2016-May-12
Document File: 3 page(s) / 63K

Publishing Venue

The IP.com Prior Art Database

Abstract

This article presents a new method of refined individual preference template management, integrated with real time sentiment analysis and biometric analysis inputs, for enhancing customized translation assistant

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 52% of the total text.

Page 01 of 3

system and methods for recommending personalized multilingual content based on individual preference


1) The more and more people go aboard to travel all over the world each year. In 2014 the global overseas tourists reached 138 million people. According to the world tourism trends and outlook report from The United Nations World Tourism Organization, by 2030, the number of global tourism will reach 1.8 billion people.

2) The world is so big that it is impossible for the tourism to understand the local language, customs and habits of the region. They are unable to communicate

with the local people and it brings a lot of inconvenience to travel, especially in restaurant, shopping center, airport, and other public areas.

The invented disclosure will provide a system and method of refined individual preference template management, integrated with real time sentiment analysis and biometric analysis inputs, for enhancing customized translation assistant

Key components include: 1) receiving request: receive a request from end users during their conversation in a special scenario 2) identifying and tracking preference: identify and track personal preferences information from conversation responses in first and second languages from social network.

3) categorizing preference: categorize the personal preferences and response conversation corpus based
culture background,
native languages
geo-location,
education,
income,

habit,
consuming histories

expectation ...

4) learning: learn similarity of personal preferences from tracked preferences and response in each typical category
5) modeling: created linguistic models (in both 1st and 2nd languages) for each specific personal preferences in specific conversation scenario.
6) analyzing context: analyze current speaking context in the 2nd language
7) sele...