Aggregation retrieval method and device based on multivariate data, equipment and storage medium

A multivariate data and data technology, applied in the computer field, can solve problems such as inability to retrieve relevant data, lack of accurate judgment of user search intentions, and low retrieval accuracy

Pending Publication Date: 2021-01-05
CHINA CONSTRUCTION BANK
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, most search engines are built based on traditional search technologies, which have information overload, return too many search results, have many search results irrelevant to search intentions, and lack accurate judgments on users' actual search inte

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
  • Aggregation retrieval method and device based on multivariate data, equipment and storage medium
  • Aggregation retrieval method and device based on multivariate data, equipment and storage medium
  • Aggregation retrieval method and device based on multivariate data, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0092]Figure 1a It is a flow chart of an aggregated retrieval method based on multivariate data in the first embodiment of the present invention. This embodiment can be applied to the case of aggregated retrieval based on multiple types of data. This method can be implemented by an aggregated retrieval device based on multivariate data. To execute, the device can be implemented by hardware and / or software, and generally can be integrated in an electronic device that provides data retrieval services. Such asFigure 1a As shown, the method includes:

[0093]Step 110: Obtain the target question to be retrieved, and perform intent recognition processing on the target question to obtain weighted word segmentation.

[0094]In this embodiment, the target question may be a question that is input by the user and waiting to be retrieved. In order to accurately obtain the content that the user wants to retrieve, the target question may be identified first, and the content of the target question that ...

Embodiment 2

[0111]Figure 2a It is a flowchart of a method for aggregation and retrieval based on multivariate data in the second embodiment of the present invention. This embodiment is further refined on the basis of the above-mentioned embodiment, and provides specific steps for retrieval using a graph inference engine, as well as general The specific steps for the search engine to search. Combine belowFigure 2a The method for aggregation and retrieval based on multivariate data provided in the second embodiment of this application is described, including the following steps:

[0112]Step 210: Obtain the target question to be retrieved, and perform intent recognition processing on the target question to obtain weighted word segmentation.

[0113]In this embodiment, the user may manually input the target question, or may input the target question through a microphone voice, or may select the target question from the provided question selection list.

[0114]Step 220: Invoke the interface of the question...

Embodiment 3

[0144]image 3 It is a schematic structural diagram of a multivariate data-based aggregation retrieval device in the third embodiment of the present invention. This embodiment is applicable to the case of performing aggregation retrieval based on multiple types of data. The device can be implemented by hardware and / or software. , And can generally be integrated in electronic equipment that provides data retrieval services. Such asimage 3 As shown, the device includes:

[0145]The obtaining module 310 is used to obtain the target question to be retrieved, and perform intent recognition processing on the target question to obtain the weighted word segmentation;

[0146]The retrieval module 320 is used to retrieve the weighted word segmentation by using multiple retrieval engines to obtain retrieval results corresponding to each retrieval engine. The retrieval engines include: a question and answer engine matching question and answer pairs, and a graph inference engine matching structured gra...

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 aggregation retrieval method and device based on multivariate data, equipment and a storage medium. The method comprises the steps of obtaining a to-be-retrieved target question, and performing intention recognition processing on the target question to obtain weight segmented words; using multiple retrieval engines to retrieve the weight segmented words, obtaining retrieval results corresponding to the retrieval engines, and the retrieval engines comprising a question and answer engine matched with the question and answer pair, a graph reasoning engine matched with the structured graph data and a universal retrieval engine matched with the unstructured document data; and performing confidence scoring on the retrieval results corresponding to the retrieval enginesaccording to the weights of the weight segmentation words by adopting an aggregation engine, and sequentially displaying the retrieval results of which the scores are greater than a preset thresholdvalue to the user. According to the technical scheme of the embodiment of the invention, aggregation retrieval is carried out on various types of data, the support range of retrieval data is expanded,and the retrieval accuracy is improved.

Description

Technical field[0001]The embodiments of the present invention relate to the field of computer technology, and in particular, to an aggregation retrieval method, device, equipment and storage medium based on multivariate data.Background technique[0002]With the continuous increase of the amount of information in various fields, the demand of users for information retrieval is also increasing. At present, most search engines are built based on traditional search technology, there is information overload, too many search results are returned, there are many search results that have nothing to do with the search intent, and there is a lack of accurate judgment of the user's actual search intent. The accuracy of retrieval is not high. At the same time, the search results are in a single form, and it is impossible to retrieve all the related data of multiple types and multiple structures in the vertical field, resulting in a higher frequency of secondary searches by users.Summary of the in...

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): G06F16/33G06F16/335G06F16/332G06F16/901G06F16/9035
CPCG06F16/3329G06F16/3334G06F16/335G06F16/9024G06F16/9035
Inventor 蒲柯锐李昱王全礼王斌孙昊
Owner CHINA CONSTRUCTION BANK
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap