Method, device and system for natural language content title disambiguation

A natural language and content technology, applied in the field of title disambiguation of natural voice content, can solve the problems of being unable to understand the real meaning of the user, reducing the accuracy of user intent recognition, and affecting the user's voice interaction experience.

Active Publication Date: 2017-09-22
BEIJING MORAN COGNITIVE TECH CO LTD
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At this time, the device receiving the user's natural language input cannot understand the real meaning of the

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method, device and system for natural language content title disambiguation
  • Method, device and system for natural language content title disambiguation
  • Method, device and system for natural language content title disambiguation

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[1088] Such as image 3 As shown, in the first embodiment, the system 100 includes a first device 110 . A method for title disambiguation of natural language content includes the following steps:

[1089] In step 301, the first device 110 receives a natural language command input by a user.

[1090] When users interact with the device by voice, they tend to use more natural and simple expressions. For example, users may directly issue a natural language command "play Jay Chou's unspeakable secret", or even directly send a natural language command "unspeakable Secret", "The First AI Conference", etc.

[1091] Step 303, after receiving the natural language command, the first device 110 converts the natural language command into a content title, wherein the text corresponding to the content title has multiple meaning items.

[1092] Specifically, the first device 100 can collect the natural language command input by the user through a sound collection device such as a micropho...

no. 2 example

[1108] Such as Figure 4 As shown, in the second embodiment, the system 100 includes a first device 110 , a network device 130 and a network 140 . A method for title disambiguation of natural language content includes the following steps:

[1109] In step 401, the first device 110 receives a natural language command input by a user.

[1110] When users interact with the device by voice, they tend to use more natural and simple expressions. For example, users may directly issue a natural language command "play Jay Chou's unspeakable secret", or even directly send a natural language command "unspeakable Secret", "The First AI Conference", etc.

[1111] In step 409, the first device 110 sends the natural language command to the network device 130 after receiving the natural language command.

[1112] Optionally, the first device 110 also sends its own device type information to the network device 130 .

[1113] In step 403, the network device 130 converts the natural language...

no. 3 example

[1139] Such as Figure 5 As shown, in the third embodiment, the system 100 includes a first device 110 , a network device 130 and a network 140 . A method for title disambiguation of natural language content includes the following steps:

[1140] Step 501, the first device 110 receives a natural language command input by a user;

[1141] When users interact with the device by voice, they tend to use more natural and simple expressions. For example, the user may directly issue a natural language command "play Jay Chou's unspeakable secret", or even directly send a natural language command such as "can't say Secrets", "The First AI Conference".

[1142] Step 503, the first device 110 converts the natural language command into a content title and sends it to the network device 130; wherein, the text corresponding to the content title has multiple meaning items;

[1143] For example, "The Unspeakable Secret" can represent the music "The Unspeakable Secret" or the movie "The Uns...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention aims to provide a method, a device and a system for natural language content title disambiguation. Specifically, actual meaning information corresponding to a content title obtained after a natural language command of a user is converted is determined from multiple pieces of meaning information according to device type information of an output device, and content corresponding to the content title is output according to the actual meaning information. Therefore, when the meaning expressed by the user in a natural language is converted into a meaning which is expressed clearly but the content indicated by the meaning is uncertain, the true meaning of the user can be understood, the graph recognition accuracy of the user is improved, and the speech interactive experience of the user is also improved.

Description

technical field [0001] The present invention relates to the technical field of speech recognition, and more particularly to a method, device and system for disambiguation of natural speech content titles. Background technique [0002] The interaction between the user and the device includes button control, remote control, somatosensory control, touch control, etc. With the development of NLP (natural language processing, natural language processing) technology, another interaction mode has been added between the user and the device, that is, voice interactive control. [0003] Users use natural language to interact with the device, hoping that the device can understand the user's intention to the maximum extent. However, when humans express through natural language, words with uncertain meanings such as omitted words and pronouns often appear. Existing speech Recognition technology usually uses context to determine the specific meaning of omitted words and pronouns in the u...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F17/28G10L15/26G10L15/30
CPCG06F16/3344G06F40/258G06F40/30G10L15/26G10L15/30
Inventor 袁志伟戴帅湘李龙飞
Owner BEIJING MORAN COGNITIVE TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap