Artificial intelligence-based searching error correction method and apparatus

A technology of artificial intelligence and error correction method, applied in the field of information retrieval, can solve the problems of low error correction efficiency and accuracy, and achieve the effect of improving error correction and user experience

Active Publication Date: 2017-03-22
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF6 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in this error correction method, due to the large number of homonyms or near-form characters, more choices are made during error correction, resulting in lower error correction efficiency and accuracy.

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
  • Artificial intelligence-based searching error correction method and apparatus
  • Artificial intelligence-based searching error correction method and apparatus
  • Artificial intelligence-based searching error correction method and apparatus

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0035] According to the historical behavior characteristics of the first query statement, it is judged whether the first query statement satisfies the error correction condition.

[0036] Among them, the historical behavior characteristics include: the number of historical searches, the number of historical clicks and the length of reading. Specifically, the historical retrieval information of each query statement can be stored in the retrieval error correction device, such as data such as the number of times of retrieval, the number of clicks, and the length of reading, so that after receiving the first query statement, it can be judged by querying historical data. Whether the number of retrieval times of the statement is greater than a certain value, and whether the number of times the user clicks on the query result corresponding to the first query statement is sufficient, or whether the user's reading time for the query result corresponding to the first query statement is l...

example 2

[0039] According to the language model value of the first query sentence, it is judged whether the first query sentence satisfies the error correction condition.

[0040] Specifically, the retrieval error correction device can determine the language model value of the first query sentence by judging whether the first query sentence has the same or similar description in the historical query sentences. For example, the retrieval error correction device determines a language model by making statistics on historical query sentences and titles of search results in the retrieval database, and then inputs the first query sentence into the language model to calculate the language model value of the first query sentence.

[0041] It should be noted that the above error correction strategy is just an example, and can be set or adjusted according to actual application needs.

[0042] Step 102, if the first query sentence satisfies the error correction condition, determine the first partic...

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 provides an artificial intelligence-based searching error correction method and apparatus. The method comprises the steps of receiving a first query statement input by a user, and determining whether the first query statement satisfies an error correction condition or not according to a preset error correction strategy; if the first query statement satisfies the error correction condition, determining to-be-error-corrected first word segmentations from the first query statement; obtaining respective first candidate results corresponding to the first word segmentations according to a preset candidate recall strategy; determining an error correction result corresponding to the first word segmentations according to quality characteristic values of the respective first candidate results; and performing error correction on the first query statement based on the error correction result to generate a second query statement. By adoption of the artificial intelligence-based searching error correction method, whether the query needs to be subjected to error correction or not is accurately determined based on historical data, and the error correction candidate results are accurately screened to determine the error correction result, so that the error correction efficiency and accuracy of a search engine are improved, inquiring time of the user is reduced, and user experience is improved.

Description

technical field [0001] The present application relates to the technical field of information retrieval, and in particular to an artificial intelligence-based retrieval error correction method and device. Background technique [0002] Artificial Intelligence (Artificial Intelligence), the English abbreviation is AI. It is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a manner similar to human intelligence. Research in this field includes robotics, language recognition, image recognition, natural language processing and expert systems, etc. [0003] With the popularization of the Internet, the information on the Internet is becoming more and more abundant, and now people can easily obtain t...

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): G06F17/30G06F17/27
CPCG06F16/951G06F40/205G06F16/2453G06F16/243G06F40/232G06N5/048
Inventor 付志宏曾增烽肖求根何径舟石磊李朋凯
Owner BEIJING BAIDU NETCOM SCI & TECH CO 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