Method, apparatus, device and storage medium for determining point of interest area

Patent metadata

Field	Value
Publication number	US-11740102-B2
Application number	US-202016864648-A
Country	US
Kind code	B2
Filing date	May 1, 2020
Priority date	Oct 10, 2019
Publication date	Aug 29, 2023
Grant date	Aug 29, 2023

Abstract

The present disclosure discloses a method, an apparatus, a device, and a storage medium for determining a point of interest area, and relates to the field of automatic driving. The implementation solution is that the method is applied to an electronic device, and includes: receiving a point of interest area determination request input by a first user, the point of interest area determination request including a target area coverage; and acquiring grid data of at least one block within the target area coverage in response to the point of interest area determination request; acquiring, for each block, positioning data of a second user within each preset time period and number of parent points of interest; clustering corresponding grid data according to the positioning data, the grid data and the number of the parent points of interest; determining at least one POI area in each block according to a clustering result.

First claim

What is claimed is:

1. A method for determining a point of interest area, wherein the method is applied to an electronic device, and the method comprises:
receiving a point of interest area determination request input by a first user, the point of interest area determination request comprising a target area coverage;
acquiring grid data of at least one block within the target area coverage in response to the point of interest area determination request, wherein each of the at least one block is divided uniformly into grids and grid data of the each of the at least one block is constructed from position coordinates of each grid;
acquiring, for each block, positioning data of a second user within each of a plurality of preset time periods and a number of parent points of interest; clustering corresponding grid data according to the positioning data, the grid data and the number of the parent points of interest; and
determining at least one POI area in each block according to a clustering result;
wherein the clustering the corresponding grid data according to the positioning data, the grid data and the number of parent points of interest comprises:
generating a corresponding positioning contribution relationship graph according to the positioning data and the grid data;
determining the number of parent points of interest to be corresponding number of clustering centers; and
clustering the corresponding grid data according to the positioning contribution relationship graph and the number of clustering centers;
wherein the generating a corresponding positioning contribution relationship graph according to the positioning data and the grid data comprises:
generating nodes of the corresponding positioning contribution relationship graph according to the grid data;
determining whether there is an undirected edge between any two nodes according to the positioning data;
when there is an undirected edge between two nodes, determining a weight of the undirected edge according to the positioning data; and
generating the corresponding positioning contribution relationship graph according to the nodes and the weight of the undirected edge.

2. The method according to claim 1 , wherein the acquiring grid data of at least one block within the target area coverage comprises:
acquiring road data within the target area coverage;
generating corresponding road network data according to the road data;
determining each polygon in the road network data as each block;
performing grid division on the each block to acquire the corresponding grid data.

3. The method according to claim 1 , wherein the determining whether there is an undirected edge between any two nodes according to the positioning data comprises:
when it is determined according to the positioning data that the second user has successively visited two nodes within a preset time period, determining that there is an undirected edge between the two nodes;
when it is determined according to the positioning data that the second user has when it is determined according to the positioning data that the second user has not visited the two nodes successively in each preset time period, determining that there is no undirected edge between the two nodes.

4. The method according to claim 3 , wherein the determining the weight of the undirected edge according to the positioning data comprises:
determining the weight of the undirected edge according to a frequency of successively visiting the two nodes in each preset time period;
wherein the frequency has a positive correlation with the weight of the undirected edge.

5. The method according to claim 4 , wherein the clustering the corresponding grid data according to the positioning contribution relationship graph and the number of clustering centers comprises:
determining at least one clustering parameter value of each grid data in a preset clustering model according to the positioning contribution relationship graph;
filtering out clustering center grid data from the grid data according to the clustering parameter value, wherein number of the clustering center grid data is the same as number of the clustering centers;
determining a matching relationship value between each grid data and each clustering center grid data; and
determining a category of each grid data according to the matching relationship value.

6. The method according to claim 5 , wherein the preset clustering model is a density peak clustering model;
the determining at least one clustering parameter value of each grid data in a preset clustering model according to the positioning contribution relationship graph comprises:
determining a first clustering parameter value of grid data of a starting point of the undirected edge according to the weight of the undirected edge in the positioning contribution relationship graph and a distance between the two nodes corresponding to the undirected edge; and
according to a distance between each node and a corresponding preset high-density node in the positioning contribution relationship graph, determining a second clustering parameter value of grid data corresponding to the node.

7. The method according to claim 5 , wherein the filtering out clustering center grid data from the grid data according to the clustering parameter value comprises:
ranking the grid data according to a first clustering parameter value and a second clustering parameter value respectively;
acquiring first M grid data whose the first clustering parameter value and the second clustering parameter value are both ranked in the first M;
filtering out N grid data from the first M grid data according to a product value of the first cluster parameter value and the second cluster parameter value; and
determining the N grid data to be the clustering center grid data.

8. The method according to claim 6 , wherein the matching relationship value is a weight of a corresponding undirected edge;
the determining the category of each grid data according to the matching relationship value comprises:
determining a category of the clustering center grid data corresponding to a largest weight of the undirected edge to be the category of the grid data.

9. The method according to claim 1 , wherein the determining at least one POI area in each block according to a clustering result comprises:
determining the area where the grid data of each category in each block is located to be the POI area of the corresponding category.

10. The method according to claim 1 , wherein after determining at least one POI area in each block according to the clustering result, the method further comprises:
verifying the clustering result according to a parent point of interest and a child point of interest comprised in the POI area.

11. The method according to claim 1 , wherein after determining at least one POI area in each block according to the clustering result, the method further comprises:
smoothing a boundary of the POI area.

12. The method according to claim 10 , wherein after verifying the clustering result according to the parent point of interest and the child point of interest comprised in the POI area, the method further comprises:
if the clustering result passes the verification, outputting at least one POI area in each block; and
displaying each POI area with a corresponding display strategy.

13. An apparatus for determining a point of interest area, where the apparatus is in an electronic device, and the apparatus comprises at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at le

Assignees

• Beijing Baidu Netcom Sci & Tech Co Ltd

Inventors

• Lu Xinjiang
• Li Yanyan
• Duan Jianguo
• Xiong Hui
• Du Guanglei

Classifications

• G01C21/3682 Primary

  output of POI information on a road map (G01C21/3614, G01C21/3685 take precedence) · CPC title