Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Content query method and device, electronic equipment and storage medium

A technology of content query and storage media, applied in the field of smart devices, can solve the problems of long links and lack of convenience and instant search, and achieve the effect of optimizing time-consuming

Pending Publication Date: 2021-06-01
GUANGDONG XIAOTIANCAI TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The scheme and device allow students to return to paper books, which not only provides more convenient query operations, but also allows users to reduce contact with electronic products to achieve the purpose of eye protection. However, the current technical scheme has the following defects: from speaking to recognition It takes 2 seconds or more to get the results, and then to return to the search and display the results. The whole link is long, and it takes 2 seconds or more, which does not play a convenient role in searching and getting it immediately.

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
  • Content query method and device, electronic equipment and storage medium
  • Content query method and device, electronic equipment and storage medium
  • Content query method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] Such as figure 1 , the present invention provides an embodiment of a content query method, comprising steps:

[0050] S100: When acquiring the voice instruction, match the high-frequency question list with the voice instruction.

[0051] Exemplarily, when the smart device acquires the voice command issued by the user, the backend of the smart device matches the high-frequency question list with the voice command collected in real time, and checks whether there is such a voice command in the high-frequency question list.

[0052] S200 When the matching is successful, perform content query based on the predicted intention information obtained by the voice command and the touched position on the learning page after receiving the voice command.

[0053] Exemplarily, if there is a voice instruction in the high-frequency question list, the intention information corresponding to the high-frequency question list pair is used as the predicted intention information of the voice ...

Embodiment 2

[0061] Based on the above-mentioned embodiment, the parts that are the same as those in the above-mentioned embodiment in this embodiment will not be described one by one, such as figure 2 As shown, this embodiment provides a content query method, which specifically includes:

[0062] S100: When acquiring the voice instruction, match the high-frequency question list with the voice instruction.

[0063] S201 When the matching between the initial intention information and the predicted intention information fails, use the initial intention information of the voice query to obtain the first content to be recognized.

[0064] Exemplarily, in order to avoid the inaccuracy of the predicted intention information, the initial intention information is calculated in real time. The initial intent information is used to perform matching verification on the predicted intent information, and when the matching verification fails, the initial intent information is used to directly query the...

Embodiment 3

[0080] Based on the above-mentioned embodiments, the parts that are the same as the above-mentioned embodiments in this embodiment will not be described one by one. This embodiment provides a content query method, which specifically includes:

[0081] The original technical solution of Wisdom Eye query is as follows:

[0082] Step 1. Wake up the voice assistant: the user calls "Xiaobu Xiaobu" to wake up the voice assistant.

[0083] Step 2. Recognize voice commands: the user speaks voice commands and recognizes them in real time through ASR technology, such as "what does this word mean?".

[0084] Step 3. Understand the user's intention: understand the user's intention through NLP technology, for example, the intention of "what does this word mean?" is "query new words".

[0085] Step 4. Fingertip positioning: After the user finishes speaking, Smart Eye takes a photo and recognizes the coordinates of the user's finger, and frames the content to be recognized according to the ...

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 belongs to the field of intelligent equipment, and discloses a content query method and device, electronic equipment and a storage medium, and the method comprises the steps: when a voice instruction is obtained, matching a high-frequency question method list with the voice instruction; when the matching is successful, performing content query based on prediction intention information obtained based on the voice instruction and a touch position on a learning page after the voice instruction is received; matching initial intention information obtained by recognizing the voice instruction with the predicted intention information; and when the matching is successful, carrying out content query. In combination with the characteristic that a high-frequency voice instruction is relatively fixed and regular when a user uses a smart eye to query, in the voice instruction recognition process, a voice recognition result is matched with a high-frequency instruction list in real time to predict the voice instruction intention of the user in advance, and the time consumption of a whole link is optimized in a mode of preposing the processes of fingertip positioning, content recognition, searching and the like.

Description

technical field [0001] The invention relates to the field of smart devices, in particular to a content query method, device, electronic device and storage medium. Background technique [0002] The tutoring machine is an Android tablet that provides high-quality educational resources. By installing a mirror on the front camera of the tutoring machine to form a smart eye, it forms a tablet base, a tablet, a smart eye, and query solutions for users’ words and phrases in paper books. The product form It is: the tablet is placed vertically on the bracket; the mirror is installed on the front camera of the tablet and on the top of the Android tablet; the book is placed in front of the tablet, and the top of the book is aligned with the bracket; through the wisdom composed of the front camera and the mirror eye, which can take pictures of books and homework placed in front of the tablet; users can send instructions by pointing at the contents of the book and voice instructions, suc...

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): G06F16/33G06K9/00G10L15/22
CPCG06F16/334G10L15/22G06V30/40
Inventor 张明云
Owner GUANGDONG XIAOTIANCAI TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products