Map retrieval method and point-of-information POI semantic vector calculation method and device

A technology for retrieving information and information points, applied in geographic information databases, calculations, semantic analysis, etc., can solve problems such as poor recall effect, achieve the effect of improving accuracy and confidence, rich expression, and improving basic recall rate

Pending Publication Date: 2020-10-16
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the current semantic recall method, the POI vector index is usually established according to the POI name. For the map retrieval information input by the user, only the similarity between the semantic vector of the map retrieval information and the semantic vector of the POI name is considered. When the map retrieval information Differences in information lead to poor recall

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
  • Map retrieval method and point-of-information POI semantic vector calculation method and device
  • Map retrieval method and point-of-information POI semantic vector calculation method and device
  • Map retrieval method and point-of-information POI semantic vector calculation method and device

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0036] Such as figure 1 As shown, the application provides a map retrieval method, comprising the following steps:

[0037] Step 101: Calculate the semantic vector of the map retrieval information.

[0038] The above map retrieval information may be understood as map retrieval information input by the user, and the English expression of the map retrieval information may be "query".

[0039] In this step, the semantic vector of the map retrieval information can be calculated through the pre-trained semantic model. Specifically, after receiving the map retrieval information input by the user, the map retrieval information is input into the pre-trained semantic model for calculation. Get the semantic vector of the map retrieval information. The semantic vector of the map retrieval information may be, for example but not limited to, an Embedding (distributed embedding) representation.

[0040] In this application, the existing semantic model can be used to calculate the semanti...

no. 2 example

[0098] Such as Figure 7 As shown, the present application provides a calculation method of a POI semantic vector, comprising the following steps:

[0099] Step 201: Obtain the graph semantic feature of the target POI, wherein the graph semantic feature of the target POI aggregates the semantic features between the target POI and N neighbor nodes, where N is an integer greater than 1;

[0100] Step 202: Calculate the semantic vector of the target POI according to the graph semantic features of the target POI.

[0101] Optionally, the acquiring the graph semantic features of the target POI includes:

[0102] Obtain N neighbor nodes of the target POI;

[0103] Respectively obtain the semantic association between the target POI and each neighbor node to obtain N semantic features;

[0104] The N semantic features are aggregated to obtain the graph semantic features of the target POI.

[0105] Optionally, the N neighbor nodes retrieve information for N maps, and the N map retr...

no. 3 example

[0121] Such as Figure 8 As shown, the present application provides a map retrieval device 300, including:

[0122] The first calculation module 301 is used to calculate the semantic vector of the map retrieval information;

[0123] The search module 302 is configured to search for the semantic vector of the target POI that matches the semantic vector of the map retrieval information according to the pre-created information point POI semantic vector index library; wherein, the semantic vector of the target POI is based on the target POI The graph semantic feature of the POI is calculated, and the graph semantic feature of the target POI aggregates semantic features between the target POI and N neighbor nodes, where N is an integer greater than 1.

[0124] Optionally, the map retrieval device 300 also includes:

[0125] A first acquiring module, configured to acquire N neighbor nodes of the target POI;

[0126] The second obtaining module is used to separately obtain the sem...

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 a map retrieval method and a point-of-information POI semantic vector calculation method and device, relates to the technical field of map retrieval, and can be applied to thecloud field and the deep learning field. The map retrieval method comprises the following steps of: calculating a semantic vector of map retrieval information; and searching for a target POI semanticvector matched with the semantic vector of the map retrieval information according to a pre-created point-of-information POI semantic vector index library, wherein the semantic vector of the target POI is calculated according to the graph semantic features of the target POI, and the graph semantic features of the target POI aggregate the semantic features between the target POI and N neighbor nodes. According to the invention, the generation of the POI semantic vector is optimized, so that the expression of the POI semantic vector is richer, the accuracy and confidence of the POI semantic vector can be improved, the retrieval prompt can be recalled more accurately, the basic recall rate is effectively improved, the recall effect is improved, and the problems in the prior art are solved.

Description

technical field [0001] The present application relates to data processing technology, in particular to the field of map retrieval technology, in particular to a map retrieval method, a method and a device for calculating semantic vectors of information points POI. Background technique [0002] In the map retrieval technology, the recall of a retrieval suggestion (suggestion, sug for short) can be implemented in a manner of semantic recall. However, in the current semantic recall method, the POI vector index is usually established according to the POI name. For the map retrieval information input by the user, only the similarity between the semantic vector of the map retrieval information and the semantic vector of the POI name is considered. When information is discrepant, it leads to poor recall. Contents of the invention [0003] The present application provides a map retrieval method, a calculation method and a device for an information point POI semantic vector. [0...

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): G06F16/29G06F16/9537G06F40/30G06N3/04G06N3/08
CPCG06F16/29G06F16/9537G06F40/30G06N3/08G06N3/045
Inventor 臧文华范淼卓安
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

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