Unlock instant, AI-driven research and patent intelligence for your innovation.

A method and device for extracting and analyzing image information based on voice input

A technology of image information and information extraction, which is applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problem of heavy user interaction burden and achieve the effect of reducing interaction burden

Active Publication Date: 2018-03-30
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, such application software can only achieve a certain type of image information extraction, and at the same time requires clear operating instructions based on the user. With the increase in the number of applications, the user's interaction burden is also increasing. Providing convenient one-stop interactive services is an urgent problem to be effectively solved

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
  • A method and device for extracting and analyzing image information based on voice input
  • A method and device for extracting and analyzing image information based on voice input
  • A method and device for extracting and analyzing image information based on voice input

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] figure 1 It is a flow chart of the voice input-based image information extraction and analysis method provided in Embodiment 1 of the present invention, as shown in figure 1 As shown, the method includes:

[0039] S101. Obtain the information extraction intention of the user according to the voice input by the user.

[0040] Acquire the voice input by the user by using an acoustic sensor, and then convert the acquired voice input by the user into corresponding text information through voice recognition technology, and use the obtained text information as the user's information extraction intention.

[0041] Furthermore, in order to obtain the matching image information extraction scene more accurately, the text information obtained after speech recognition can be further processed, specifically, it can include: word segmentation processing for the text information obtained after speech recognition, and then semantic Analyze and extract the keyword groups, such as "com...

Embodiment 2

[0054] image 3 It is a schematic diagram of an image information extraction and analysis device based on voice input provided in Embodiment 2 of the present invention, as shown in image 3 As shown, the device includes: a preprocessing unit 10 , a matching unit 20 , and an analysis unit 30 .

[0055] The preprocessing unit 10 is configured to obtain the user's information extraction intention according to the voice input by the user.

[0056] The preprocessing unit 10 uses the acoustic sensor to acquire the voice input by the user, and then converts the acquired voice input by the user into corresponding text information through voice recognition technology, and uses the obtained text information as the user's information extraction intention.

[0057] Furthermore, in order to obtain the matching image information extraction scene more accurately, the preprocessing unit 10 may further process the text information obtained after the speech recognition, which may specifically ...

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 present invention provides an image information extraction and analysis method and device based on voice input, wherein the method includes: pre-establishing an image information extraction scene library; S1, obtaining the user's information extraction intention according to the voice input by the user; S2, according to the According to the information extraction intention of the user, query the image information extraction scene library, match with each text description tag, and obtain the image information extraction scene corresponding to the matched text description tag; S3, perform the target image according to the acquired image information extraction scene The target object is recognized, and the recognition result is returned to the user. The present invention can integrate the functions of various types of image information extraction software, and at the same time, can intelligently extract and analyze the corresponding information in the target image according to the voice input by the user, thereby significantly reducing the interactive burden of the user.

Description

【Technical field】 [0001] The invention relates to image information extraction technology, in particular to an image information extraction and analysis method and device based on voice input. 【Background technique】 [0002] With the wide application of image recognition technology and mobile Internet, a large number of image information extraction software has emerged, allowing users to query relevant information in specified images anytime and anywhere. Existing image information extraction software is usually designed for different types of user needs. For example, application software for text information extraction can extract and recognize text in images, and application software for specific commodity element extraction can extract and identify The QR code of the product in the image or the logo of the product, and the face recognition application software can recognize the face in the image. However, such application software can only achieve a certain type of image...

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 Patents(China)
IPC IPC(8): G06F17/30
Inventor 韩钧宇
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD