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

Text error correction method

A text error correction and target text technology, applied in text database query, unstructured text data retrieval, natural language data processing, etc., can solve the problem of reducing user experience, affecting consultation recognition, and dialogue systems that cannot reply to sentences with typos, etc. problem, to avoid collection and sorting, reduce errors, and correct the effect of high accuracy

Pending Publication Date: 2020-07-24
XIAMEN KUAISHANGTONG TECH CORP LTD
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In the development of dialogue systems, due to the professionalism of the field, visitors often inadvertently send some typos, which often affect the recognition effect of the natural language understanding model, and the dialogue system cannot reply to these sentences with typos
For example, in the development of a task-based dialogue system for medical andrology, visitors unintentionally send some typos: "Thank you early", "Impotent", "Baojing", etc. These typos will affect the consultation recognition, resulting in the dialogue system being unable to reply, which in turn reduces user experience

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 error correction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0031] The content of the present invention will be described in detail below in conjunction with the examples.

[0032] refer to figure 1 As shown, it is a flowchart of a text error correction method provided by an embodiment of the present invention. This method mainly uses the TF-IDF algorithm and the N-gram model to correct the text with typos in the dialogue system. details as follows:

[0033] (1) The TF-IDF algorithm involved:

[0034] TF-ID is the abbreviation of term frequency–inverse document frequency. This algorithm uses a statistical method to measure the importance of a word in a text, and is often used in information extraction, text mining and other scenarios. The core of the algorithm is to calculate the tf value and idf value of a word in a text.

[0035] TF is the abbreviation of term frequenc...

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 error correction method. The method comprises the steps of S1, obtaining a session language material; S2, constructing a pinyin library for the session language materialbased on a TF-IDF algorithm; S3, training the session language material by using an N-gram language model to obtain a frequency model; and S4, performing error correction on a target text in combination with the pinyin library and the frequency model. According to the invention, error correction can be carried out on texts with wrongly written characters, so that consultation of users in a dialogue system can be identified, and accurate response can be realized.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a text error correction method. Background technique [0002] In the development of dialogue systems, due to the professionalism of the field, visitors often inadvertently send some typos. These typos often affect the recognition effect of the natural language understanding model, and the dialogue system cannot reply to these sentences with typos. For example, in the development of a medical andrology task-based dialogue system, visitors unintentionally send some typos: "Thank you early", "Impotent", "Baojing", etc. These typos will affect the consultation recognition, resulting in the dialogue system being unable to reply, thereby reducing the user experience. Contents of the invention [0003] The technical problem to be solved by the present invention is to provide a text error correction method for the deficiencies of the above-mentioned prior art, so as to correct...

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): G06F16/33G06F16/332G06F40/232G06F40/289
CPCG06F16/3329G06F16/3332
Inventor 李威肖龙源廖斌李稀敏刘晓葳
Owner XIAMEN KUAISHANGTONG TECH CORP 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