Text recognition method, device and system

A text recognition and text data technology, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve problems such as difficulty in determining thresholds, low recognition accuracy, and difficulty in raising, and achieve low recognition accuracy. , improve the recognition accuracy, improve the effect of generalization ability

Pending Publication Date: 2020-06-16
ALIBABA GRP HLDG LTD
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, because the detection target of the first recognition method is often very ambiguous, its words are not significantly different from those of general texts, so it is difficult to propose very representative words, and it is also difficult to determine the corresponding threshold; the second recognition method Whether the method is to manually extract fe

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
  • Text recognition method, device and system
  • Text recognition method, device and system
  • Text recognition method, device and system

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0023] Example 1

[0024] According to an embodiment of the present invention, an embodiment of a text recognition method is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and, Although a logical sequence is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than here.

[0025] The method embodiment provided in Embodiment 1 of the present application may be executed in a mobile terminal, a computer terminal, or a similar computing device. figure 1 Shows a hardware structure block diagram of a computer terminal (or mobile device) used to implement a text recognition method. Such as figure 1 As shown, the computer terminal 10 (or mobile device 10) may include one or more (shown in the figure as 102a, 102b, ..., 102n) processor 102 (the processor 102 may include, but is not limited to, a mic...

Example Embodiment

[0060] Example 2

[0061] According to an embodiment of the present invention, there is also provided a text recognition device for implementing the above text recognition method, such as Figure 4 As shown, the device 400 includes: a first acquisition module 42, a second acquisition module 44, and an identification module 46.

[0062] Among them, the first obtaining module 42 is used to obtain text data; the second obtaining module 44 is used to obtain the word vector corresponding to the text data; the recognition module 46 is used to recognize the word vector using the recognition model to obtain the recognition result of the text data, where , The recognition model is used to identify whether there is illegal content in the text data, and the recognition model is obtained through confrontation training.

[0063] Specifically, the above-mentioned text data may be text data of literary works that need to be recognized for pornographic content. In this embodiment of the application,...

Example Embodiment

[0082] Example 3

[0083] According to an embodiment of the present invention, a text recognition system is also provided, including:

[0084] Processor; and

[0085] The memory, connected to the processor, is used to provide the processor with instructions for processing the following processing steps: obtaining text data; obtaining the word vector corresponding to the text data; using the recognition model to recognize the word vector to obtain the recognition result of the text data, where, The recognition model is used to identify whether there is illegal content in the text data, and the recognition model is obtained through confrontation training.

[0086] Based on the solution provided by the above-mentioned embodiment of the application, after the text data is obtained, the word vector corresponding to the text data is first obtained, and the word vector is further recognized by the recognition model, and the recognition result of the text data is obtained to achieve the recog...

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 text recognition method, device and system. The method comprises the steps of obtaining text data; obtaining a word vector corresponding to the text data; and recognizing theword vector by using a recognition model to obtain a recognition result of the text data, the recognition model being used for recognizing whether illegal content exists in the text data, and the recognition model being obtained through adversarial training. According to the invention, the technical problem of low recognition accuracy of a text recognition method in the prior art is solved.

Description

technical field [0001] The present invention relates to the field of natural language processing, in particular to a text recognition method, device and system. Background technique [0002] At present, there are some pornographic plots in some literary works, especially online literary works. These pornographic plots will greatly damage the physical and mental health of young readers, and will also make most adult readers feel uncomfortable. Therefore, how to accurately identify the pornographic fragments in the novel is very important to realize the rectification of pornographic novels. However, under the influence of the existing review mechanism, some authors gradually discard obscene words that can be clearly identified by the review mechanism in the pornographic fragments of their novels, and instead use a large number of language techniques similar to metaphors, using frequently used words words to describe erotic scenes. This greatly affects the accuracy of the re...

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): G06F40/289G06F40/30G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/24
Inventor 贺国秀康杨杨高喆孙常龙刘晓钟司罗
Owner ALIBABA GRP HLDG 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap