Supercharge Your Innovation With Domain-Expert AI Agents!

Formula identification method and device

A formula recognition and formula technology, applied in the field of data processing, can solve the problem that the machine learning model cannot accurately identify the formula, and achieve the effect of accurate output

Pending Publication Date: 2021-12-31
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved in this application is that the machine learning model cannot accurately identify the formula in the long formula track, and a formula recognition method and device are provided

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
  • Formula identification method and device
  • Formula identification method and device
  • Formula identification method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0099] In order to enable those skilled in the art to better understand the solution of the application, the technical solution in the embodiment of the application will be clearly and completely described below in conjunction with the drawings in the embodiment of the application. Obviously, the described embodiment is only It is a part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0100] The inventors of the present application have found through research that when using a machine learning model to identify formula trajectories, the decoder can process the feature sequence encoded by the encoder based on the attention map when decoding, wherein the attention map can indicate each decoding moment The weight of each feature in the feature sequence. However, as th...

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 formula identification method, which can utilize a formula identification model to identify a to-be-processed formula track to obtain a target formula. Specifically, the formula identification model can process a to-be-processed formula trajectory to obtain a first feature sequence, and decodes the first feature sequence based on a first attention map (map) to obtain the output of the formula identification model. The formula identification model can also obtain each character in the formula to be processed according to the trajectory of the formula to be processed. Further, the formula recognition model can adjust the first attention map according to each character and the output of the formula recognition model in the decoding process. Therefore, by utilizing the scheme provided by the embodiment of the invention, the adjusted first attention map is relatively accurate. Therefore, even if the length of the to-be-processed formula track is relatively long, the formula identification model can accurately identify the to-be-processed formula track so as to obtain the target formula.

Description

technical field [0001] The present application relates to the field of data processing, in particular to a formula recognition method and device. Background technique [0002] Currently, a machine learning model can be used to identify the formula trajectory, so as to obtain the formula corresponding to the formula trajectory. In one example, the machine learning model may include an attention-based decoder. However, as the length of the formula trajectory grows, the semantic information and feature position information become weaker and weaker, which is not conducive to the decoding of the decoder based on the attention mechanism. As a result, the machine learning model cannot accurately identify the formulas in the long formula track. The formula track mentioned in this application includes the track points that make up the formula. [0003] Therefore, there is an urgent need for a solution that can accurately identify the formula corresponding to the formula track even...

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): G06K9/62G06F40/111G06N3/04G06N3/08G06N20/00
CPCG06F40/111G06N3/08G06N20/00G06N3/045G06F18/22
Inventor 刘水辛晓哲
Owner BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com