Semantic mining method and system

A semantic mining and semantic technology, applied in semantic analysis, natural language data processing, instruments, etc., can solve problems such as restricting the use of user voice functions, low ability to understand intentions, and inability to enjoy convenience, and achieve the effect of improving understanding ability

Pending Publication Date: 2022-05-06
CHONGQING CHANGAN AUTOMOBILE CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In-vehicle voice interaction is extremely important in the smart cockpit. However, the current in-vehicle intelligent voice system has a relatively low ability to understand the user's intentions, and can only recognize some instructions that were set in advance at the beginning of the design. However, it is impossible for

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
  • Semantic mining method and system
  • Semantic mining method and system

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0022] The present invention will be further described below in conjunction with the accompanying drawings.

[0023] like figure 1 As shown, the embodiment of the present invention provides a method and a system for mining semantics for a speech recognition function. The system includes: a user primitive acquisition system 1; a skill configuration module 2; an unrecognized primitive data analysis module 3; a statistical presentation module 4; Query module 5.

[0024] In this embodiment, refer to figure 1 , the method performs the following process:

[0025] Step 101, user primitive collection

[0026] The primitive acquisition system 1 uploads and saves the user primitive data input by the microphone to the server through the vehicle-machine network.

[0027] Step 102, skill configuration

[0028] On the skill configuration module 2, set keywords corresponding to each skill section of the speech recognition function as required. The skill configuration module can query t...

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 provides a semantic mining method and system. The method comprises the following steps: collecting a user corpus; the method comprises the following steps: analyzing unrecognized corpora or unpreset corpora which enter a chat and the like, and recognizing a real intention of a user; a skill plate to which the user corpus belongs is actively recommended, and keywords can be flexibly set according to needs; contextual query is provided to assist in analyzing the real intention of the user. According to the invention, the understanding capability of the voice recognition function on the corpus of the user can be improved, and the user can simply and flexibly transmit the instruction to the voice assistant.

Description

technical field [0001] The invention relates to a vehicle-mounted intelligent voice system, in particular to mining semantics by analyzing unrecognized user primitives, increasing the voice recognition function's understanding of user intentions, and allowing users to express their intentions flexibly. Background technique [0002] Voice interaction is one of the important ways of human-computer interaction at present. Saying goodbye to the traditional manual operation interaction mode, voice interaction liberates human hands in a sense, and realizes long-distance interaction between human and computer, providing convenience for people's life. . [0003] In-vehicle voice interaction is extremely important in the smart cockpit. However, the current in-vehicle intelligent voice system has a relatively low ability to understand the user's intentions, and can only recognize some instructions that were set in advance at the beginning of the design. However, it is impossible for 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
Owner CHONGQING CHANGAN AUTOMOBILE 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