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

Intelligent prompt method, module and system for search

An intelligent, historical search technology, applied in the field of keyword search

Active Publication Date: 2014-03-12
JIANGSU WISEDU INFORMATION TECH
View PDF3 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The problem to be solved by the present invention is the problem of the rationality of the prompt words in the search engine

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
  • Intelligent prompt method, module and system for search
  • Intelligent prompt method, module and system for search

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0109] In this embodiment, the foregoing step S3 is realized through the following steps:

[0110] S31: The server splits the initial string according to the tokenizer to obtain prefixes and suffixes;

[0111] S32: The server searches the thesaurus according to the prefixes and suffixes to obtain prefix synonyms and suffix synonyms;

[0112] S33: The server traverses the hotword suffix tree to find hotwords matching prefixes and / or suffixes, and obtains a candidate word information list.

[0113] In this embodiment, the thesaurus is a database used by the server to store synonymous associations between keywords. Thesaurus is usually provided by commercial dictionaries, or you can build your own.

[0114] In this embodiment, step S31 is implemented by a word segmentation module or device. The word segmentation module or device is also the aforementioned word segmenter. Those skilled in the art understand that the prefix and suffix processed in step S31 may be the same. In ...

Embodiment 2

[0120] This embodiment is based on Embodiment 1. Specifically, a step is added after Step S33 in Embodiment 1, that is, Step S34: the server calculates the probability of each candidate word according to the analysis of the user history search behavior database.

[0121] Step S34 of this embodiment is realized by a historical behavior analysis device or device. The problem to be solved is to obtain the probability that the user intends to input the candidate word under the condition that the user enters the initial character string through the statistical analysis of the user's historical search for a specific candidate word. . The input of this embodiment is the candidate word information list obtained in step S33, and the output is also the candidate word information list, but the candidate word information in the output candidate word information list increases the probability of candidate words.

[0122] The calculation of the probability of the candidate words is obtained...

Embodiment approach 1

[0124] It is assumed that historical behavior information includes original character strings, click hot words and click frequency. The server searches the user's historical search behavior database for historical behavior information in which the original character string is the same as the initial character string and the clicked hot words are the same as the candidate words. The click frequency in historical behavior information can be used as the probability of candidate words. Since the click frequency is an integer greater than 0, and the probability in the general sense is a value between 0 and 1, for this reason, the click frequency of each candidate word can be normalized as the probability of the candidate word, and the click frequency is normalized The chemical processing can refer to the following method: suppose K candidate words are included in the candidate word information list, and the click frequency of each candidate word is respectively: , then the probab...

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 an intelligent prompt method, an intelligent prompt module and an intelligent prompt system for search. According to the method disclosed by the invention, a server executes the following steps of distinguishing prefix words and suffix words by a tokenizer; carrying out synonymy expansion to form a prefix synonym list and a suffix synonym list; then traversing a hot word suffix tree to search hot words of prefix matches and / or suffix matches to obtain candidate words; and analyzing and calculating probability of each candidate word by historical search behaviors of a user. According to the method, a client executes the following steps of calculating load relevance of each candidate word; and calculating a click-on predicted value of each candidate word and then selecting the candidate words to display according to the click-on predicted values. In the invention, prompt words are obtained by matching between the prefix words and the suffix words, synonyms are combined, mass of search intentions of the user are integrated and the local relevance is combined, so that the prompt words are more approximate to the search intentions of the user.

Description

technical field [0001] The present invention relates to keyword search in data search and data mining, and in particular to artificial intelligence in keyword input. Background technique [0002] Smart hints are a method to help users clarify input intentions, facilitate users to quickly input, and improve user experience. Smart prompts are mainly used in search engines and development platforms, and can automatically prompt users through different presentation forms such as drop-down boxes or labels according to user input. [0003] At present, the mainstream search engines mainly count the user search history data saved on the server side first, and build a popular word dictionary according to the search frequency of the search word. Candidate prompt words, and then screen the prompt words according to the search frequency, and display them at the bottom of the search box in turn. This kind of intelligent prompt uses string prefix matching to find candidate prompt words,...

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): G06F17/30
CPCG06F16/2425G06F16/2457
Inventor 罗晶尹岩严敏
Owner JIANGSU WISEDU INFORMATION TECH
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

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