Method and system for automatically correcting character strings
A string, automatic technology, applied in the fields of electronic digital data processing, natural language data processing, instruments, etc., can solve the problems of high cost of anti-fraud risk control, reduced e-commerce efficiency, and difficulty in automatic correction.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0068] In the character string automatic correcting method of the present embodiment, in a character string database, store a plurality of verified character strings and a plurality of preset first-type words, and each verified character string includes several first-type words. word. refer to figure 1 As shown, the string automatic correction method includes the following steps:
[0069] S 1 , from the plurality of character strings, extracting other words separated by the first type of words as the second type of words, and the phrase formed by each of the second type of words and the immediately adjacent first type of words together as a preset phrase, and then A keyword database is generated, and there are multiple first-type words, second-type words, preset phrases, and a sequence of words in the keyword database. The sorting order of setting;
[0070] S 2 , generate a phrase permutation statistical table, the permutation probability that each preset phrase appears a...
Embodiment 2
[0091] Compared with Embodiment 1, the character string automatic correction method of the present embodiment differs only in that:
[0092] Also store the weight value of each first category word in this character string database, S 9 by S 9a Substitute, S 9a for:
[0093] Query the phrase permutation statistics table to obtain the permutation probabilities of the effective phrases at the beginning of the output string and adjacent valid phrases, and calculate the weighted average of the obtained permutation probabilities as the accuracy, where the weight of each permutation probability is equal to the output character The weight value of the first type of word in the first effective phrase in the string, or the weight value of the first type of word in the subsequent effective phrase in the adjacent effective phrase.
[0094] And, in S 6 Then execute S 61 , S 61 For: select the phrase that includes the first category of words from the invalid word part as the unknown p...
Embodiment 3
[0103] refer to figure 2 As shown, the character string automatic correction system of the present embodiment comprises:
[0104] Character string database module 1, is used for storing verified multiple character strings and a plurality of preset first-type words, and each verified character string includes several first-type words;
[0105] The keyword database module 2 is used to extract other words separated by the first type of words as the second type of words from the plurality of character strings, and each of the second type of words and the next first type of words to form together The phrase is used as a preset phrase, and then a keyword database is generated, and the first type of words, the second type of words, the default phrase and a row of words are recorded in the keyword database, and the sequence of the words is The preset arrangement order of each first-class word;
[0106] Phrase permutation statistical module 3, for calculating and recording the permu...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com