Cross-regional travel recommendation method and apparatus, electronic device and storage medium

Patent metadata

Field	Value
Publication number	US-11802776-B2
Application number	US-202117212251-A
Country	US
Kind code	B2
Filing date	Mar 25, 2021
Priority date	Jun 11, 2020
Publication date	Oct 31, 2023
Grant date	Oct 31, 2023

Abstract

A cross-regional travel recommendation method and apparatus, an electronic device and a storage medium are provided, which relates to the fields of intelligent transportation and deep learning. A specific implementation solution is: acquiring a travel request of a user, the travel request comprising a start point and an end point which are located in different regions; extracting user features according to the travel request of the user; and recommending at least one travel plan to the user according to the user features and a pre-trained cross-regional travel recommendation model. The technical solutions can make up for the deficiency of the existing technology, provide a cross-regional travel plan recommendation under a large-space scale and a multimodal environment through a pre-trained cross-regional travel recommendation model and user features extracted based on a travel request of a user, and can satisfy a cross-regional travel request of the user, and is highly practical.

First claim

What is claimed is:

1. A computer-implemented cross-regional travel recommendation method, wherein the method comprises:
acquiring, by a terminal device a travel request of a user, the travel request comprising a start point and an end point which are located in different regions, wherein a distance between the start point and the end point is greater than a preset distance threshold and multiple modes of transportation means are available between the start point and the end point;
extracting user features according to the travel request of the user; and
recommending, by the terminal device, at least one travel plan to the user according to the user features and a pre-trained cross-regional travel recommendation model,
wherein the extracting user features according to the travel request of the user comprises:
extracting at least one of travel plan features, personalized features and situational features of the user according to the travel request,
and/or the travel plan comprises at least one means of transportation of driving, high-speed trains, planes, ships, electric vehicles, motorcycles, bicycles and urban public transportation,
wherein the extracting travel plan features of the user according to the travel request comprises:
calculating a plurality of travel plans from the start point to the end point in the travel request by using an underlying routing engine; and
extracting at least one of an average distance, a minimum distance and a maximum distance of all the plurality of travel plans, at least one of an average price, a minimum price and a maximum price of all the plurality of travel plans, at least one of an average elapsed time, a minimum elapsed time and a maximum elapsed time of all the plurality of travel plans, at least one of a difference between a distance of each travel plan and the average distance, a difference between the distance and the minimum distance and a difference between the distance and the maximum distance, at least one of a difference between a price of each travel plan and the average price, a difference between the price and the minimum price and a difference between the price and the maximum price, and at least one of a difference between an elapsed time of each travel plan and the average elapsed time, a difference between the elapsed time and the minimum elapsed time and a difference between the elapsed time and the maximum elapsed time, and performing feature enhancing on the extracted features, to form the travel plan features of the user.

2. The method according to claim 1 , wherein the extracting personalized features of the user according to the travel request comprises:
collecting at least one of gender, age, type of work, level of education, income level, consumption level and marital status of the user of the travel request, and performing feature enhancing on the extracted features, to obtain the personalized features of the user.

3. The method according to claim 2 , wherein after the extracting user features according to the travel request and before the recommending at least one travel plan to the user according to the user features and a pre-trained cross-regional travel recommendation model, the method further comprises:
processing null-value, category-type and/or numerical-type features in the user features.

4. The method according to claim 1 , wherein the extracting situational features of the user according to the travel request comprises:
collecting at least one of a total distance between the start point and the end point, a current moment, a current weak, a current position, a city ID of the start point and the end point, a current province ID, a network type, a network operator category, and weather information in the travel request, and performing feature enhancing on the extracted features, to form the situational features of the user.

5. The method according to claim 4 , wherein after the extracting user features according to the travel request and before the recommending at least one travel plan to the user according to the user features and a pre-trained cross-regional travel recommendation model, the method further comprises:
processing null-value, category-type and/or numerical-type features in the user features.

6. The method according to claim 1 , wherein after the extracting user features according to the travel request and before the recommending at least one travel plan to the user according to the user features and a pre-trained cross-regional travel recommendation model, the method further comprises:
processing null-value, category-type and/or numerical-type features in the user features.

7. The method according to claim 1 , wherein after the extracting user features according to the travel request and before the recommending at least one travel plan to the user according to the user features and a pre-trained cross-regional travel recommendation model, the method further comprises:
processing null-value, category-type and/or numerical-type features in the user features.

8. The method according to claim 1 , wherein after the extracting user features according to the travel request and before the recommending at least one travel plan to the user according to the user features and a pre-trained cross-regional travel recommendation model, the method further comprises:
processing null-value, category-type and/or numerical-type features in the user features.

9. A computer-implemented method for training a cross-regional travel recommendation model, wherein the method comprises:
collecting a plurality of pieces of cross-regional travel information of a user from a software-integrated application running on a terminal device based on a historical travel log, the cross-regional travel information comprising travel request of the user having a start point and an end point which are located in different regions, wherein a distance between the start point and the end point is greater than a preset distance threshold and multiple modes of transportation means are available between the start point and the end point;
extracting a plurality of pieces of training data based on the plurality of pieces of cross-regional travel information of the user; and
training the cross-regional travel recommendation model by using the plurality of pieces of training data wherein the extracting a plurality of pieces of training data based on the plurality of pieces of cross-regional travel information of the user comprises:
extracting corresponding user features based on each of the plurality of pieces of cross-regional travel information of the user; and marking probabilities of corresponding travel plans as 1 to form the training data; and obtaining the plurality of pieces of training data in total,
wherein the extracting corresponding user features based on each of the plurality of pieces of cross-regional travel information of the user comprises:
extracting at least one of corresponding travel plan features, personalized features and situational features of the user according to each of the plurality of pieces of cross-regional travel information of the user.

10. An electronic device, comprising:
at least one processor; and
a memory communicatively connected with the at least one processor;
wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform a cross-regional travel recommendation method, wherein the method comprises:
acquiring, by a terminal device, a travel request of a user, the travel request comprising a start point and an end point which are located in different regions, wherein a distance between the

Assignees

• Beijing Baidu Netcom Sci & Tech Co Ltd

Inventors

• Liu Hao
• Zhang Panpan
• Duan Jianguo
• Xiong Hui

Classifications

• G01C21/3484 Primary

  Personalized, e.g. from learned user behaviour or user-defined profiles · CPC title

• G01C21/343

  Calculating itineraries (travelling salesman problem G06Q10/04; optimisation of routes G06Q10/047) · CPC title

• G01C21/3423

  Multimodal routing · CPC title

• G06Q10/02 Primary

  Reservations, e.g. for tickets, services or events · CPC title

• G06Q50/14

  Travel agencies · CPC title