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

A demand-based data retrieval method and device

A demand and demand description technology, applied in the field of demand-based data retrieval methods and devices, can solve problems such as inability to map, waste of resources, and inability to recall search results, and achieve the effect of avoiding multiple retrievals and saving retrieval resources.

Active Publication Date: 2015-09-09
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, if the demand description key of a structured data resource that provides weather information is "weather forecast", if the input user query is "what's the weather like recently", it may not be mapped to the structured data resource that provides weather information, thus It is impossible to recall the search results that accurately reflect the user's needs, and the user can only try to enter the query multiple times, resulting in a waste of resources

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
  • A demand-based data retrieval method and device
  • A demand-based data retrieval method and device
  • A demand-based data retrieval method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0073] When establishing the semantic vector of the requirement description key corresponding to each data resource, the requirement description key needs to be preprocessed first. The preprocessing may include at least one of the following processes: converting into a preset uppercase or lowercase form, and converting into a preset encoding form.

[0074] The purpose of preprocessing the requirement description key is to make the user query and the semantic vector of the requirement description key consistent in form, so as to facilitate subsequent calculation of the similarity between the user query and the semantic vector of the requirement description key. It can be pre-agreed that both the user query and the requirement description key should be in uppercase or lowercase, or that the user query and the requirement description key should be in a unified encoding format, for example, the international extension code of Chinese characters (GBK).

[0075] The semantic vector ...

Embodiment 2

[0089] figure 2 The flow chart of the method for selecting data resources provided by Embodiment 2 of the present invention, such as figure 2 As shown, the method may include the following steps:

[0090] Step 201: Receive user query.

[0091] The user query is the query input by the user received by the search engine.

[0092] Step 202: Calculate the similarity between the user query and the semantic vector of the requirement description key of each data resource.

[0093] In this step, when calculating the similarity, the following steps S1 and S2 can be performed for the semantic vectors of each requirement description key:

[0094] S1: Match the user query with the semantic vector of the demand description key, determine the contents hit by the user query in the semantic vector, and then calculate the ratio of the hit length of the user query to the length of the user query in each hit content ; and / or, calculate the similarity between the semantic vector of the user...

Embodiment 3

[0115] image 3 The flow chart of the method for selecting data resources provided by Embodiment 3 of the present invention, such as image 3 As shown, the method may include the following steps:

[0116] Step 301: Receive user query.

[0117] The user query is the query input by the user received by the search engine.

[0118] Step 302: Find the pre-established mapping relationship between user query and demand description key, wherein the mapping relationship is after calculating the similarity between each user query and the semantic vector of each demand description key in the search log, select the similarity to meet the preset The requirement description of the similarity requirement is established by the key and user query.

[0119] In this embodiment, the mapping relationship between the user query and the requirement description key is pre-established. After receiving the user query, the mapping relationship is directly searched to determine the requirement descrip...

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 a method and a device for data retrieval based on demands. The method includes: respectively establishing and storing a semantic vector corresponding to a demand description keyword of each data resource in advance; selecting the data resource corresponding to each demand description keyword, wherein the similarity between a user search query and the semantic vector of each demand description keyword meets a preset similarity requirement; and retrieving in the selected data resources aiming at user queries. Compared with the prior art, the method and the device can recall search results accurately reflecting user demands, so that multiple retrievals are avoided, and retrieval resources are saved.

Description

【Technical field】 [0001] The invention relates to the field of computer technology, in particular to a demand-based data retrieval method and device. 【Background technique】 [0002] When a user uses a search engine to obtain information, in many cases the demand is relatively clear. The search engine should search the data resources corresponding to the demand for the search term (query) input by the user to search for information matching the query and return it to the user. Among them, when determining the data resource corresponding to the requirement, match the query with the requirement description keyword (key) corresponding to the data resource, but the requirement description key corresponding to the data resource is often single, which requires the user query and the requirement description key The corresponding data resources can only be found in the same way of expression, but the user queries used by users to express the same demand are diverse, which may cause i...

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 Patents(China)
IPC IPC(8): G06F17/30
Inventor 施少杰刘建柱
Owner BEIJING BAIDU NETCOM SCI & TECH CO 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

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