Method for off-line voice retrieval of products under network-free condition

A technology without network and voice, applied in the field of voice search, it can solve the problems of inability to meet the needs of search, low accuracy of search results, troublesome use of voice recognition, etc., to reduce the number of repeated voice input, clear thinking, and strong applicability Effect

Pending Publication Date: 2021-08-06
上海适享文化传播有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a method for offline voice search products under the condition of no network, which can effectively solve the problem that the current voice search technology in the offline state is not mature enough in the above-mentioned background technology, and the use of voice recognition in the disconnected state is relatively troublesome. The search range is limited, and the data processing speed is slow, resulting in low accuracy of the search results, which has a certain impact on the search and cannot meet the needs of the search.

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 for off-line voice retrieval of products under network-free condition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0037] Example: such as figure 1 As shown, the present invention provides a technical solution, a method for offline voice retrieval of products without a network, including the following search steps:

[0038] S1. First, use the Android SDK to develop and integrate the offline database, and download the voice, text and special scene knowledge graphs available for recognition in the database, and classify the offline database;

[0039] S2. The user receives the voice through the voice receiving device, matches the voice with the offline database, recognizes and converts the voice, and matches the knowledge graph of the special scene according to the text;

[0040] S3. According to the knowledge map and error correction system of the special scene, correct the text that has been recognized and converted;

[0041] S4, mark and replace the text after error correction, and display;

[0042] S5. After the error correction is completed, use the special scene knowledge map to mark ...

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 discloses a method for off-line voice retrieval of a product under a network-free condition, and the method comprises the following steps: S1, developing and integrating an off-line database by using an Android SDK, downloading voice, characters and a special scene knowledge graph which can be identified in the database, and classifying the off-line database; S2, enabling a user to receive the voice through a voice receiving device; enabling the voice to be matched with an offline database, recognizing and converting the voice, and matching a knowledge graph of a special scene according to characters. According to the method, the offline classification database is set through the Android SKD device, the corresponding content is downloaded in the database, and the data in different scenes are independently stored; during the voice recognition, the voice is firstly converted into the characters, then the converted content is classified, and the content is searched in the corresponding classification database, so that the offline voice recognition classification is clear, the range needing to be searched is quickly positioned during recognition, and the range selection is quicker.

Description

technical field [0001] The invention relates to the technical field of voice search, in particular to a method for offline voice search for products without a network. Background technique [0002] Voice search refers to allowing the use of mobile phones and computers to search by speaking to the mobile phone or computer, that is, the content uploaded by the device is recognized by the server, and then information is searched based on the recognition results. Voice search technology has become a daily routine. The more important part enables users to conduct voice control anytime and anywhere, bringing greater convenience to people's lives; [0003] However, the current voice search technology in the offline state is not mature enough, the use of voice recognition in the disconnected state is more troublesome, the search range in the offline state is limited, and the processing speed of data is slow, resulting in low accuracy of search results , which has a certain impact o...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/33G06F16/35G06F16/36G06F40/232
CPCG06F16/3343G06F16/35G06F16/367G06F40/232
Inventor 李抒雁沙涛
Owner 上海适享文化传播有限公司
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