Method and apparatus for displaying map points of interest, and electronic device

Patent metadata

Field	Value
Publication number	US-11893073-B2
Application number	US-202217729282-A
Country	US
Kind code	B2
Filing date	Apr 26, 2022
Priority date	Jun 30, 2021
Publication date	Feb 6, 2024
Grant date	Feb 6, 2024

Abstract

The present disclosure discloses a method and apparatus for displaying map points of interest, and an electronic device, relates to the field of artificial intelligence, and in particular to intelligent transportation. A specific implementation solution includes: acquiring features corresponding to multiple candidate points of interest; determining predicted popularity of the multiple candidate points of interest according to a mapping relation between each feature and each popularity and the features of the multiple candidate points of interest, and the mapping relation is determined based on the frequency of operations performed by a user for each sample point of interest in a historical time period; and displaying the candidate points of interest of which predicted popularity meets a preset popularity condition in a map. Therefore, the accuracy of the displayed points of interest may be enhanced.

First claim

What is claimed is:

1. A method for displaying map points of interest, the method comprising:
acquiring features corresponding to a plurality of candidate points of interest;
determining predicted popularity of each of the plurality of candidate points of interest according to a mapping relation between each feature and each popularity and the features of the plurality of candidate points of interest, wherein the mapping relation is determined based on the frequency of operations performed by a user for each sample point of interest in a historical time period; and
displaying the candidate points of interest of which predicted popularity meets a preset popularity condition in a map;
wherein the mapping relation is determined in advance by using the following method, the method comprising:
acquiring features corresponding to a plurality of sample points of interest; obtaining observed popularity of each of the plurality of sample points of interest based on the frequency of operations performed by the user for the plurality of sample points of interest in the historical time period; and determining a mapping relation between each feature and each observed popularity based on the features corresponding to the plurality of sample points of interest and the observed popularity of each of the plurality of sample points of interest.

2. The method as claimed in claim 1 , wherein obtaining the observed popularity of each of the plurality of sample points of interest based on the frequency of operations performed by the user for the plurality of sample points of interest in the historical time period comprises:
for each of the plurality of sample points of interest, determining the frequency of user operations for this sample point of interest in the user operations within the historical time period; and
sorting the plurality of sample points of interest based on the frequency to obtain a sample point of interest sequence for expressing the observed popularity of each of the plurality of sample points of interest.

3. The method as claimed in claim 1 , wherein determining the mapping relation between each feature and each observed popularity based on the features corresponding to the plurality of sample points of interest and the observed popularity of each of the plurality of sample points of interest comprises:
performing training to obtain a sorting model for expressing the mapping relation between each feature and each observed popularity based on the features corresponding to the plurality of sample points of interest, the sample point of interest sequence, and a preset sorting learning algorithm.

4. The method as claimed in claim 1 , wherein the features comprise at least some of user-side features, scene features, and point of interest features, the user-side features are used for characterizing each user using a map, the scene features are used for characterizing scenes at which each user uses the map, and the point of interest features are used for characterizing the points of interest corresponding to the features.

5. The method as claimed in claim 2 , wherein determining the mapping relation between each feature and each observed popularity based on the features corresponding to the plurality of sample points of interest and the observed popularity of each of the plurality of sample points of interest comprises:
performing training to obtain a sorting model for expressing the mapping relation between each feature and each observed popularity based on the features corresponding to the plurality of sample points of interest, the sample point of interest sequence, and a preset sorting learning algorithm.

6. The method as claimed in claim 1 , wherein places expressed by the candidate points of interest are located in an area displayed in the map.

7. The method as claimed in claim 1 , wherein the predicted popularity of the candidate points of interest is expressed in a manner of using a popularity value, or the predicted popularity of the candidate points of interest is expressed by using a relative comparison.

8. The method as claimed in claim 1 , wherein a feature type corresponding to the sample points of interest is the same as a feature type corresponding to the candidate points of interest.

9. The method as claimed in claim 1 , wherein the frequency is expressed in the form of a numerical value, or the frequency is expressed in the form of the relative comparison.

10. An electronic device, comprising:
at least one processor, and
a memory, in communication connection with the at least one processor, wherein
the memory is configured to store instructions capable of being performed by the at least one processor, and the instructions are performed by the at least one processor to perform the following steps:
acquiring features corresponding to a plurality of candidate points of interest;
determining predicted popularity of each of the plurality of candidate points of interest according to a mapping relation between each feature and each popularity and the features of the plurality of candidate points of interest, wherein the mapping relation is determined based on the frequency of operations performed by a user for each sample point of interest in a historical time period; and
displaying the candidate points of interest of which predicted popularity meets a preset popularity condition in a map;
wherein the mapping relation is determined in advance by using the following method, the method comprising: acquiring features corresponding to a plurality of sample points of interest obtaining observed popularity of each of the plurality of sample points of interest based on the frequency of operations performed by the user for the plurality of sample points of interest in the historical time period; and determining a mapping relation between each feature and each observed popularity based on the features corresponding to the plurality of sample points of interest and the observed popularity of each of the plurality of sample points of interest.

11. The electronic device as claimed in claim 10 , wherein obtaining the observed popularity of each of the plurality of sample points of interest based on the frequency of operations performed by the user for the plurality of sample points of interest in the historical time period comprises:
for each of the plurality of sample points of interest, determining the frequency of user operations for this sample point of interest in the user operations within the historical time period; and
sorting the plurality of sample points of interest based on the frequency to obtain a sample point of interest sequence for expressing the observed popularity of each of the plurality of sample points of interest.

12. The electronic device as claimed in claim 10 , wherein determining the mapping relation between each feature and each observed popularity based on the features corresponding to the plurality of sample points of interest and the observed popularity of each of the plurality of sample points of interest comprises:
performing training to obtain a sorting model for expressing the mapping relation between each feature and each observed popularity based on the features corresponding to the plurality of sample points of interest, the sample point of interest sequence, and a preset sorting learning algorithm.

13. The electronic device as claimed in claim 10 , wherein the features comprise at least some of user-side features, scene features, and point of interest features, the user-side features are used for characterizing each user using a map, the scene features are used for characterizing scenes at which each user uses the

Assignees

• Beijing Baidu Netcom Sci & Tech Co Ltd

Inventors

• Li Yanyan
• Jiang Airong
• Wu Shilin
• Dou Dejing

Classifications

• G06F16/9538 Primary

  Presentation of query results · CPC title

• G06F16/29 Primary

  Geographical information databases · CPC title

• G06F16/9537 Primary

  Spatial or temporal dependent retrieval, e.g. spatiotemporal queries · CPC title

• G06N20/00

  Machine learning · CPC title

• G06N3/08

  Learning methods · CPC title