CN116753971A

CN116753971A - Navigation method, training method of virtual user creation model and storage medium

Info

Publication number: CN116753971A
Application number: CN202310461650.5A
Authority: CN
Inventors: 王岩
Original assignee: Alibaba China Co Ltd
Current assignee: Alibaba China Co Ltd
Priority date: 2023-04-25
Filing date: 2023-04-25
Publication date: 2023-09-15

Abstract

The application provides a navigation method, a training method of a virtual user creation model and a storage medium, wherein the navigation method comprises the following steps: acquiring a first-selected recommended navigation route aiming at a target starting point and a target ending point and at least one alternative recommended navigation route; configuring a corresponding first virtual user for the at least one alternative recommended navigation route; controlling the first virtual user to simulate a traveling process from the target starting point to the target ending point according to the corresponding alternative recommended navigation route; acquiring travel data corresponding to a virtual user and travel data corresponding to the target user; and training a navigation route recommendation model at least based on the travel data corresponding to the virtual user and the travel data corresponding to the target user. According to the scheme provided by the application, the navigation route recommendation model obtained through training can recommend the navigation route which meets the travel data requirement of the target user, so that the target user can be improved to have better navigation experience.

Description

Navigation method, training method of virtual user creation model and storage medium

Technical Field

The present application relates to the field of navigation technologies, and in particular, to a navigation method, a training method for creating a model by a virtual user, and a storage medium.

Background

With the rapid development of computer technology and the rapid popularization of intelligent terminals, people's daily trips become more and more dependent on application software with map navigation function. In the process of navigating by using the application software with the map navigation function, the application software with the map navigation function often uses a navigation route recommendation model to recommend a plurality of navigation routes for the user aiming at the target starting point and the target ending point determined by the user so as to be selected by the user.

In the process of navigating by using the application software with the map navigation function, the navigation route recommendation model can recommend a navigation route which meets the requirement of the user on the travel data, which is a key factor for guaranteeing the user to have better navigation experience, and in order to enable the navigation route recommendation model to recommend the navigation route which meets the requirement of the user on the travel data, the navigation route recommendation model is often trained by continuously utilizing the travel data corresponding to the navigation route. Therefore, how to train the navigation route recommendation model by using the travel data corresponding to the navigation route becomes a problem to be solved by those skilled in the art.

Disclosure of Invention

The embodiment of the application provides a navigation method, a training method of a virtual user creation model and a storage medium, which are used for solving one or more of the technical problems.

In a first aspect, an embodiment of the present application provides a navigation method, including:

acquiring a first-selected recommended navigation route aiming at a target starting point and a target ending point and at least one alternative recommended navigation route;

when a target user selects a preferred recommended navigation route to initiate navigation, configuring a corresponding first virtual user for at least one alternative recommended navigation route; the advancing process of the first virtual user simulates an advancing decision mode of the target user;

controlling a first virtual user to simulate a traveling process from a target starting point to a target ending point according to the corresponding alternative recommended navigation route;

acquiring travel data corresponding to a virtual user and travel data corresponding to a target user; the virtual users at least comprise first virtual users, the first virtual users generate travel data according to alternative recommended navigation routes, and the target users generate travel data according to actual navigation routes from a target starting point to a target ending point;

training a navigation route recommendation model at least based on the travel data corresponding to the virtual user and the travel data corresponding to the target user; the navigation route recommendation model is used for recommending navigation routes for target users.

In a second aspect, an embodiment of the present application provides a training method for creating a model by using a virtual user, including:

acquiring a travel feature set of a sample and a travel decision mode of a corresponding label; the sample travel feature set comprises at least one travel feature corresponding to a plurality of sample users and travel features corresponding to a plurality of sample user groups; the travel characteristics are used for representing historical travel behaviors;

training a virtual user creation model by using the sample travel feature set and a travel decision mode of the corresponding label, wherein the virtual user creation model is used for generating a virtual user based on travel features corresponding to a target user when the navigation method provided by the embodiment of the application is executed.

In a third aspect, an embodiment of the present application provides a navigation device, including:

the navigation route recommendation module is used for acquiring a first-selected navigation route aiming at the target starting point and the target ending point and at least one alternative navigation route;

the first virtual user configuration module is used for configuring a corresponding first virtual user aiming at least one alternative recommended navigation route when the target user selects the preferred recommended navigation route to initiate navigation; the advancing process of the first virtual user simulates an advancing decision mode of the target user;

The advancing process simulation module is used for controlling the first virtual user to simulate an advancing process from a target starting point to a target ending point according to the corresponding alternative recommended navigation route;

the journey data acquisition module is used for acquiring journey data corresponding to the virtual user and journey data corresponding to the target user; the virtual users at least comprise first virtual users, the first virtual users generate travel data according to alternative recommended navigation routes, and the target users generate travel data according to actual navigation routes from a target starting point to a target ending point;

the recommendation model training module is used for training a navigation route recommendation model at least based on the travel data corresponding to the virtual user and the travel data corresponding to the target user; the navigation route recommendation model is used for recommending navigation routes for target users.

In a fourth aspect, embodiments of the present application provide a computer readable storage medium having a computer program stored therein, the computer program when executed by a processor implementing a method according to any of the preceding claims.

Compared with the related art, the application has the following advantages:

according to the navigation method provided by the embodiment of the application, when the target user selects the preferred recommended navigation route to initiate navigation, the corresponding first virtual user is configured for at least one alternative recommended navigation route, then the first virtual user is controlled to simulate the advancing process from the target starting point to the target ending point according to the corresponding alternative recommended navigation route, the travel data corresponding to the virtual user and the travel data corresponding to the target user are further acquired, and the navigation route recommendation model is trained.

Because the virtual users at least comprise the first virtual users, and the travelling process of the first virtual users simulates the travelling decision mode of the target users, the travel data corresponding to the first virtual users can be regarded as travel data generated by the target users travelling from the target starting point to the target ending point according to the alternative recommended navigation route. That is, the obtaining of the trip data corresponding to the virtual user and the trip data corresponding to the target user may be regarded as obtaining the trip data respectively generated by the target user from the target start point to the target end point according to the preferred recommended navigation route and the at least one alternative recommended navigation route in the same time period. Under the condition that the time period, the starting point and the ending point are the same, the stroke data corresponding to different navigation routes can better reflect the influence of the different navigation routes on the stroke data. Therefore, the navigation route recommendation model is trained by utilizing the travel data respectively generated by the target user from the target starting point to the target ending point according to different navigation routes in the same time period, so that the navigation route recommendation model obtained through training can recommend the navigation route which meets the travel data requirements of the target user, and the better navigation experience of the target user can be improved. That is, the route data corresponding to the virtual target user and the route data corresponding to the target user are obtained, and the navigation route recommendation model is trained, so that the navigation route recommendation model obtained through training can recommend the navigation route which meets the travel data requirement of the target user, and the navigation experience of the target user can be improved.

The foregoing description is only an overview of the present application, and is intended to provide a better understanding of the technical means of the present application, as it is embodied in the present specification, and is intended to provide a better understanding of the above and other objects, features and advantages of the present application, as it is embodied in the following description.

Drawings

In the drawings, the same reference numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified. The figures are not necessarily drawn to scale. It is appreciated that these drawings depict only some embodiments according to the application and are not therefore to be considered limiting of its scope.

FIG. 1 shows a schematic diagram of an application example of a navigation solution provided in an embodiment of the present application;

FIG. 2 illustrates a schematic diagram of a navigation route provided in an embodiment of the present application;

FIG. 3 shows a flow chart of a navigation method provided in an embodiment of the present application;

FIG. 4 is a flowchart of a training method for creating a model by a virtual user, which is provided in an embodiment of the present application;

FIG. 5 shows a block diagram of a navigation device provided in an embodiment of the present application;

FIG. 6 is a block diagram of a training apparatus for creating a model for a virtual user according to an embodiment of the present application; and

Fig. 7 shows a block diagram of an electronic device for implementing an embodiment of the application.

Detailed Description

Hereinafter, only certain exemplary embodiments are briefly described. As will be recognized by those skilled in the pertinent art, the described embodiments may be modified in numerous different ways without departing from the spirit or scope of the present application. Accordingly, the drawings and description are to be regarded as illustrative in nature, and not as restrictive.

In order to facilitate understanding of the technical solutions of the embodiments of the present application, the following describes related technologies of the embodiments of the present application. The following related technologies may be optionally combined with the technical solutions of the embodiments of the present application, which all belong to the protection scope of the embodiments of the present application.

The embodiment of the application relates to a navigation scheme and a training scheme of a virtual user creation model. After the preferred navigation route aiming at the target starting point and the target ending point and at least one alternative navigation route are obtained, when the target user selects the preferred navigation route to initiate navigation, a corresponding first virtual user is configured for the at least one alternative navigation route, then the first virtual user is controlled to simulate the advancing process from the target starting point to the target ending point according to the corresponding alternative navigation route, and the travel data corresponding to the virtual user and the travel data corresponding to the target user are further obtained to train the navigation route recommendation model.

The preferred planned navigation route is generally a planned navigation route selected by default from among a plurality of planned navigation routes recommended to the target user by the application software having the map navigation function from the target start point to the target end point, and the alternative planned navigation route is other navigation routes than the preferred planned navigation route among the plurality of planned navigation routes recommended to the target user by the application software having the map navigation function.

The virtual users at least comprise a first virtual user, and can also comprise other virtual users, such as a second virtual user, a third virtual user and the like, wherein the travelling process of the virtual users simulates the travelling decision mode of the target user. The first virtual user generates travel data according to the alternative recommended navigation route, and because the virtual user at least comprises the first virtual user, the travel data corresponding to the virtual user at least comprises travel data corresponding to the first virtual user, that is, the travel data corresponding to the virtual user at least comprises travel data generated when the first virtual user travels from the target starting point to the target ending point according to the alternative recommended navigation route.

In addition, the target user generating the travel data according to the actual navigation route from the target start point to the target end point means that the travel data corresponding to the target user includes the target user generating the travel data according to the actual navigation route from the target start point to the target end point.

The first virtual user, the second virtual user, the third virtual user and other virtual users are configured according to the travel characteristics corresponding to the target user, and the travel characteristics corresponding to the target user are used for representing the historical travel behaviors of the target user, so that the virtual user configured according to the travel characteristics corresponding to the target user can be regarded as having the same historical travel behaviors as the target user. The travel behavior of the target user is determined by the travel decision mode of the target user to a great extent, so that when the virtual user configured according to the travel characteristics corresponding to the target user is regarded as having the same historical travel behavior as the target user, the travel process of the virtual user can be further considered to simulate the travel decision mode of the target user.

The travel decision refers to how to travel according to the currently traveling road segment and the corresponding road condition decision. For example, when the current road section has an expressway entrance and the road condition allows driving into the expressway entrance, a decision is made as to whether to drive into the expressway, when the front road section is congested and the congestion duration is long, a decision is made as to whether to change the road, when the front road section needs to pass through a large number of traffic light intersections, a decision is made as to whether to change the road, a decision is made as to at what speed to drive on the expressway section, and the like. The travel decision mode is used for representing which travel decision the target user can make in the current travel section and the corresponding road condition.

And carrying out feature extraction on travel features corresponding to the target users based on the historical travel data corresponding to the target users. Travel characteristics include frequent early and late peak travel, roads with high level of customary walkways, travel speeds typically controlled at 60km/h (kilometers per hour), customary handrails, avoidance of congestion, routes with shorter time consuming customary walkways, avoidance of toll roads, and the like. The travel data comprises at least one of road condition, navigation route and travel time consumption, travel expense, road grade of road sections passing through in the travel process, travel speed of road sections passing through traffic lights of different road grades, time length waiting for the traffic lights, travel oil consumption, the ratio of the road sections of each road grade, travel time and the like, wherein the road condition comprises at least one of traffic flow condition, congestion condition, traffic light condition, emergency condition, speed limiting condition and the like of a road. In an example, the travel characteristics corresponding to the target user include at least one of a high-grade road, a short-time route, and an unaccustomed road lamp.

In an example, the travel characteristics corresponding to the target user include a road with a high grade of usual early and late peak travel, a route with a short travel time, an unaccustomed road lamp, etc., where the travel decision mode of the target user may include decision to enter the expressway when the current road section has an expressway entrance and the road condition allows entering the expressway entrance, decision to change the road when the road section in front needs to pass through a large number of traffic light intersections, etc.

In the embodiment of the application, in order to improve the configuration efficiency of the virtual user and reduce the human resources required to be consumed in the configuration process of the virtual user, the virtual user can be configured by utilizing the virtual user creation model. Taking the configuration of the corresponding first virtual user for the at least one alternative recommended navigation route as an example, when the corresponding first virtual user is configured for the at least one alternative recommended navigation route, the corresponding first virtual user may be configured by inputting the travel characteristics into the virtual user creating model.

The configuration of the corresponding first virtual user for at least one candidate recommended navigation route means that the corresponding first virtual user is configured for each candidate recommended navigation route.

In addition, the virtual users such as the first virtual user, the second virtual user, and the third virtual user may be configured in advance by related personnel based on travel characteristics corresponding to the users, or may be copied by using generated virtual users, for example, the third virtual user may be configured first, and then the first virtual user and the second virtual user may be obtained by copying the third virtual user.

In the embodiment of the application, training the navigation route recommendation model at least based on the travel data corresponding to the virtual user and the travel data corresponding to the user means that the travel data corresponding to the virtual user and the travel data corresponding to the user are taken as travel data samples, and the navigation route recommendation model is trained by utilizing the travel data samples so as to adjust model parameters of the navigation route recommendation model and obtain the trained navigation route recommendation model.

In order to train to obtain the virtual user creation model, the embodiment of the application also provides a training scheme of the virtual user creation model, when the virtual user creation model is trained, the training scheme of the virtual user creation model can firstly obtain a sample travel feature set and a corresponding labeled travel decision mode, and then train the virtual user creation model by utilizing the sample travel feature set and the corresponding labeled travel decision mode. The sample travel feature set comprises at least one travel feature corresponding to a plurality of sample users and travel features corresponding to a plurality of sample user groups, wherein the travel features are used for representing historical travel behaviors, and specifically, the travel features corresponding to the sample users are used for representing the historical travel behaviors of the sample users, and the travel features corresponding to the sample user groups are used for representing the historical travel behaviors of the sample user groups.

In order to more clearly show the navigation method provided in the embodiment of the present application, an application example of the navigation method provided in the embodiment of the present application is first described. The specific implementation of this example can be seen with reference to fig. 1, which shows the navigation procedure as follows:

in the process that the target user drives from the target starting point (such as the place A) to the target ending point (such as the place B), the target user can navigate by using a client (for example, a mobile phone provided with the application software with the map navigation function) provided with the application software with the map navigation function, specifically, the target user can open the application software with the map navigation function by operating the client, after the application software with the map navigation function is started, an input box for inputting the starting point and an input box for inputting the ending point are displayed on a route generation page, and meanwhile, various traffic modes such as driving, subway buses and walking are displayed under the input box. When the target user inputs a starting point as a place A and an ending point as a place B in two input boxes respectively, and determines a traffic mode as driving, the application software with the map navigation function can conduct route planning in response to the place A and the place B input by the target user, generate a plurality of navigation routes from the place A to the place B, display a plurality of navigation routes from the place A to the place B, and the plurality of navigation routes from the place A to the place B comprise a preferred recommended navigation route and at least one alternative recommended navigation route.

In the following, an application example of the navigation method provided in the embodiment of the present application will be described by taking an example that a plurality of navigation routes from the location a to the location B include a preferred recommended navigation route and an alternative recommended navigation route. Fig. 2 is a schematic diagram of a navigation route, where a first planned navigation route needs to pass through a location point a, a location point B, a location point c, a location point d, a location point e, and a location point B, and a second planned navigation route needs to pass through a location point a, a location point f, a location point d, a location point e, and a location point B.

When the target user selects the preferred recommended navigation route to initiate navigation, the client side firstly acquires travel characteristics corresponding to the target user, then inputs the travel characteristics corresponding to the target user into the virtual target user creation model, and acquires a first virtual user output by the virtual target user creation model based on the travel characteristics corresponding to the target user.

After the first virtual user is acquired, the client further controls and controls the first virtual user to simulate a traveling process from the target starting point to the target ending point according to the corresponding alternative recommended navigation route.

In addition, the client detects whether yaw occurs during the target user's travel from the target start point to the target end point. If the target user is detected to yaw, the navigation route of the target user after each yaw is obtained to serve as an actual navigation route, and when the target user yaw occurs each time, a corresponding second virtual user is configured according to the navigation route used by the target user before yaw.

Specifically, in the process that the target user proceeds from the target starting point to the target ending point, one or more yaw actions may occur, and obtaining the navigation route after each yaw of the target user as the actual navigation route generally refers to taking the navigation route after each yaw of the target user as the actual navigation route when each yaw of the target user occurs, and taking the navigation route after the last yaw of the target user as the actual navigation route if the target user performs multiple yaw. Configuring a corresponding second virtual user for a navigation route used before yaw of the target user when the target user is yawed each time generally means configuring one second virtual user for the navigation route used before yaw of the target user when the target user is yawed each time, and if the target user is yawed a plurality of times, configuring a plurality of second virtual users correspondingly.

For example, in the process that the target user proceeds from the target starting point to the target ending point according to the preferred navigation route, a first yaw occurs at the position point b (i.e., the position point b is the yaw point of the first yaw), at which time the navigation route used before the yaw of the target user is the preferred navigation route, in which case, a corresponding second virtual user needs to be configured for the navigation route used before the yaw of the target user (i.e., the preferred navigation route).

After configuring a corresponding second virtual user for the navigation route used before yaw of the target user, the client may further control the second virtual user to simulate a travel process from a yaw point when yaw of the user occurs to a target termination point according to the navigation route used before yaw of the user. For example, after configuring the corresponding second virtual user for the navigation path (i.e., the preferred recommended navigation route) used before the yaw of the target user, the client may control the second virtual user to continue to pass through the position point c, the position point d, and the position point e in order from the yaw point (position point B) to the position point B according to the navigation path (i.e., the preferred recommended navigation route) used before the yaw of the target user.

The client also re-plans the yaw navigation route for the yaw point when the user yaws and the target termination point each time the target user yaws. For example, when the target user yaw for the first time at the location point B, the client re-plans the yaw navigation route for the location point B and the location point B, and the yaw navigation route needs to pass through the location point B, the location point e and the location point B, and at this time, the actual navigation route needs to pass through the location point a, the location point B, the location point e and the location point B.

In the process that the target user continues to travel from the yaw point to the target end point, a second yaw, a third yaw or more times of yaw can also occur, at this time, the client still configures a corresponding second virtual user for a navigation route used before yaw of the target user each time the target user yaw occurs, and controls the second virtual user to simulate a travel process from the yaw point when yaw occurs to the target end point according to the navigation route used before yaw of the user. In this application example, the navigation method provided in the embodiment of the present application will be described by taking only an example in which a yaw behavior occurs once in the process of the target user traveling from the target start point to the target end point.

After the target user moves from the target starting point to the target ending point according to the actual navigation route, the client of the application software with the map navigation function can acquire the travel data corresponding to the target user. Specifically, the trip data corresponding to the target user includes trip time of 23 minutes and trip cost of 3 yuan.

After the first virtual user proceeds from the target starting point to the target ending point according to the alternative recommended navigation route, the client of the application software with the map navigation function can acquire the travel data corresponding to the first virtual user. Specifically, the trip data corresponding to the first virtual user includes trip time of 22 minutes and trip cost of 3 yuan. It should be noted that, the client of the application software having the map navigation function may only acquire the trip data corresponding to the first virtual user and add the trip data to the trip data corresponding to the virtual user, that is, the trip data corresponding to the virtual user may only include the trip data corresponding to the first virtual user.

Because the advancing process of the first virtual user simulates the advancing decision mode of the target user, the travel data corresponding to the first virtual user can be regarded as travel data generated by the target user advancing from the target starting point to the target ending point according to the alternative recommended navigation route. That is, the obtaining of the trip data corresponding to the virtual user and the trip data corresponding to the target user may be regarded as obtaining the trip data respectively generated by the target user from the target start point to the target end point according to the preferred recommended navigation route and the at least one alternative recommended navigation route in the same time period. Under the condition that the time period, the starting point and the ending point are the same, the stroke data corresponding to different navigation routes can better reflect the influence of the different navigation routes on the stroke data. Therefore, the navigation route recommendation model is trained by utilizing the travel data respectively generated by the target user from the target starting point to the target ending point according to different navigation routes in the same time period, so that the navigation route recommendation model obtained through training can recommend the navigation route which meets the travel data requirements of the target user, and the better navigation experience of the target user can be improved. That is, the route data corresponding to the virtual target user and the route data corresponding to the target user are obtained, and the navigation route recommendation model is trained, so that the navigation route recommendation model obtained through training can recommend the navigation route which meets the travel data requirement of the target user, and the navigation experience of the target user can be improved.

In addition, in order to further enrich the data size of the travel data corresponding to the virtual user, after the second virtual user travels from the target starting point to the target ending point according to the alternative recommended navigation route, the client of the application software with the map navigation function may acquire the travel data corresponding to the second virtual user (that is, the travel data of the second virtual user traveling from the target starting point to the target ending point according to the navigation route used before the user yaw), and add the travel data to the travel data corresponding to the virtual user. Specifically, the trip data corresponding to the second virtual user includes trip time of 17 minutes and trip cost of 9 yuan.

In order to quickly acquire the travel data of the second virtual user from the target starting point to the target ending point according to the navigation route used before the yaw of the user, and better compare the difference between the travel data of the target user and the travel data of the virtual user from the target starting point to the target ending point of the same navigation route, so as to adjust the virtual user, thereby enabling the travel process of the virtual user to more accurately simulate the travel decision mode of the target user, and also enabling the third virtual user to be configured for the target user first, and then controlling the third virtual user to simulate the travel process from the target starting point to the target ending point along the actual navigation route of the target user. Meanwhile, when acquiring the travel data of the second virtual user from the target starting point to the target ending point according to the navigation route used before the user yaw, the travel data of the third virtual user from the target starting point to the yaw point according to the navigation route used before the user yaw can be acquired first, then the travel data of the second virtual user from the yaw point to the target ending point according to the navigation route used before the user yaw is acquired, and then the travel data of the second virtual user from the target starting point to the target ending point is determined according to the travel data of the third virtual user from the target starting point to the yaw point and the travel data of the second virtual user from the yaw point to the target ending point. The advancing process of the third virtual user simulates an advancing decision mode of the target user.

Specifically, the client may first obtain the travel feature corresponding to the target user, then input the travel feature corresponding to the target user into the virtual user creation model, obtain a third virtual user output by the virtual user creation model based on the travel feature corresponding to the user, and obtain the second virtual user by copying the third virtual user when configuring the corresponding second virtual user for the navigation route used before yaw of the target user. Since the travel process of the third virtual user simulates the travel decision mode of the target user, the travel process of the second virtual user can also simulate the travel decision mode of the target user. Meanwhile, the second virtual user is obtained by copying the third virtual user, so that the generation efficiency of the second virtual user can be improved, and the processing resources of the client are saved.

After the third virtual user is configured for the target user, the client controls the third virtual user to simulate the advancing process from the target starting point to the target ending point along the actual navigation route of the target user, acquires the travel data corresponding to the third virtual user, and adds the travel data to the travel data corresponding to the virtual user, wherein the travel data corresponding to the third virtual user refers to travel data generated by the third virtual user according to the actual navigation route from the target starting point to the target ending point. At this time, the trip data corresponding to the virtual user includes trip data corresponding to the first virtual user, trip data corresponding to the second virtual user, and trip data corresponding to the third virtual user.

And adding the travel data corresponding to the second virtual user and the travel data corresponding to the third virtual user to the travel data corresponding to the virtual user can enrich the data volume of the travel data corresponding to the virtual user. Because the advancing process of the second virtual user and the third virtual user also simulate the advancing decision mode of the target user, the travel data corresponding to the second virtual user and the travel data corresponding to the third virtual user can be respectively regarded as the travel data of the target user from the target starting point to the target ending point according to the navigation route used before the yaw of the user, and the target user generates the travel data according to the actual navigation route from the target starting point to the target ending point. Therefore, the data quantity of the travel data corresponding to the virtual user is enriched, the travel data respectively generated by the target user from the target starting point to the target ending point according to different navigation routes in the same time period can be enriched, at this time, the navigation route recommendation model is trained at least based on the travel data corresponding to the virtual user and the travel data corresponding to the user, and the navigation route recommendation model can be trained to recommend the navigation route which meets the travel data requirement of the target user more.

In addition, after the trip data corresponding to the virtual user and the trip data corresponding to the target user are obtained, the trip data can be further used as the historical trip data corresponding to the target user, and the historical trip data corresponding to the target user is subjected to feature extraction to obtain the trip feature corresponding to the target user. After the travel characteristics corresponding to the target user are obtained, the travel characteristics corresponding to the target user can be put into the sample travel characteristic set for model training of the virtual user creation model.

It should be noted that the above application examples of the navigation method provided in the embodiments of the present application are for ease of understanding and are not intended to limit the navigation method provided in the embodiments of the present application. Specifically, the application scenario of the navigation method provided in the embodiment of the present application is not specifically limited.

The application provides a navigation scheme and a training scheme for creating a model by a virtual user, wherein an execution subject of the navigation scheme is a client side configured with application software (such as an electronic map) with a map navigation function, such as a mobile phone, a tablet computer or other electronic equipment configured with the electronic map with the map navigation function. The execution subject of the training scheme of the virtual user creation model may be an application, a service, an instance, a functional module in a software form, a virtual machine, a container, a cloud server, or the like, or a hardware device (such as a server) or a hardware chip having a processing function of travel information. The hardware chip may be a CPU (Central Processing Unit ), GPU (Graphics Processing, graphics processor), FPGA (Field Programmable Gate Array ), NPU (Neural-network Processing Unit, network processor), AI (Artificial Intelligence ) accelerator card, DPU (Data Processing Unit, data processor), or the like. The training device for implementing the virtual user creation model may be deployed on a local computing device or a cloud computing platform for providing computing power, storage and network resources, and the mode of the cloud computing platform for providing services to the outside may be IaaS (Infrastructure as a Service ), paaS (Platform as a Service, platform as a service), saaS (Software-as-a-service), or DaaS (Data-as-a-service). Taking the example that the platform provides Software-as-a-Service (SaaS), the cloud computing platform can provide the training function of the virtual user creation model by utilizing own computing resources, and a specific application architecture can be built according to Service requirements.

The following describes the technical scheme of the present application and how the technical scheme of the present application solves the above technical problems in detail with specific embodiments. The following related technologies may be optionally combined with the technical solutions of the embodiments of the present application, which all belong to the protection scope of the embodiments of the present application, and the same or similar concepts or processes may not be described in some embodiments.

Fig. 3 shows a flow chart of a navigation method 300 provided in an embodiment of the application, which may include steps S301-S305.

In step S301, a preferred recommended navigation route and at least one alternative recommended navigation route for a target start point and a target end point are obtained.

In the navigation method provided by the embodiment of the application, after the preferred recommended navigation route and at least one alternative recommended navigation route are obtained, step S302 is required to be further executed, and in step S302, when the target user selects the preferred recommended navigation route to initiate navigation, a corresponding first virtual user is configured for the at least one alternative recommended navigation route; the travel process of the first virtual user simulates the travel decision mode of the target user.

When the corresponding first virtual users are configured for at least one alternative recommended navigation route, travel characteristics corresponding to the target users can be acquired first, and then the corresponding first virtual users are respectively configured for each alternative recommended navigation route according to the travel characteristics corresponding to the target users. The travel characteristics corresponding to the target user are used for representing the historical travel behaviors of the target user. Because the travel characteristics corresponding to the target user are used for representing the historical travel behaviors of the target user, the first virtual user configured according to the travel characteristics corresponding to the target user can be regarded as having the same historical travel behaviors as the target user. The travel behavior of the target user is determined by the travel decision mode of the target user to a great extent, so that when the first virtual user configured according to the travel characteristics corresponding to the target user is regarded as having the same historical travel behavior as the target user, the travel process of the first virtual user can be further considered to simulate the travel decision mode of the target user.

In one possible implementation manner, in order to improve the configuration efficiency of the first virtual user and reduce the human resources required to be consumed in the configuration process of the first virtual user, the first virtual user may be configured by using a virtual user creation model. Specifically, when the corresponding first virtual users are respectively configured for each candidate recommended navigation route according to the travel characteristics corresponding to the target user, the first virtual users configured according to the travel characteristics of the target user can be obtained for each candidate recommended navigation route, and the first virtual users generate the target user by inputting the travel characteristics into the virtual user creation model.

In order to configure the first virtual user by using the virtual user creation model, the virtual user creation model may be trained first, and when the virtual user creation model is trained, a sample travel feature set and a travel decision mode corresponding to the label may be acquired first, and then, the virtual user creation model is trained by using the sample travel feature set and the travel decision mode corresponding to the label. The sample travel feature set comprises at least one travel feature corresponding to a plurality of sample users and travel features corresponding to a plurality of sample user groups, wherein the travel features are used for representing historical travel behaviors, and specifically, the travel features corresponding to the sample users are used for representing the historical travel behaviors of the sample users, and the travel features corresponding to the sample user groups are used for representing the historical travel behaviors of the sample user groups.

In the navigation method provided in the embodiment of the present application, after configuring a corresponding first virtual user for at least one candidate recommended navigation route, step S303 needs to be further executed, and in step S303, the first virtual user is controlled to simulate a traveling process from a target starting point to a target ending point according to the corresponding candidate recommended navigation route.

Because the traveling process of the first virtual user simulates the traveling decision mode of the target user, the traveling process of the first virtual user from the target starting point to the target ending point according to the corresponding alternative recommended navigation route can be regarded as the traveling process of the first virtual user from the target starting point to the target ending point according to the corresponding alternative recommended navigation route.

In the navigation method provided by the embodiment of the application, after the first virtual user is controlled to simulate the advancing process from the target starting point to the target ending point, the step S304 is further required to be executed, and in the step S304, the travel data corresponding to the virtual user and the travel data corresponding to the target user are obtained; the virtual users at least comprise first virtual users, the first virtual users generate travel data according to alternative recommended navigation routes, and the target users generate travel data according to actual navigation routes from a target starting point to a target ending point.

After the target user selects the preferred recommended navigation route to initiate navigation, no yaw may occur during travel from the target starting point to the target ending point. That is, the target user may travel from the target start point to the target end point according to the preferred recommended navigation route, at which point the actual navigation route is the preferred recommended navigation route.

One or more yaw events may also occur during travel from the target start point to the target end point after the target user selects the preferred recommended navigation route to initiate navigation. In the case that the target user yaw occurs one or more times, the navigation route used after the last yaw occurs by the target user is the actual navigation route. Therefore, in order to accurately acquire the travel data corresponding to the target user, when the travel data corresponding to the target user is acquired, whether the target user yaw occurs in the process of travelling from the target starting point to the target ending point can be detected, then when the yaw of the target user is detected, the navigation route after yaw of the target user is acquired as an actual navigation route, and the travel data corresponding to the actual navigation route is acquired as the travel data corresponding to the target user.

In one possible implementation manner, in order to enrich the data amount of the travel data corresponding to the virtual user, if it is detected that the target user is yawed, a corresponding second virtual user may be configured for a navigation route used before yawing of the target user when the target user is yawed, then the second virtual user is controlled to simulate a travel process from a yaw point to a target end point when the target user is yawed according to the navigation route used before yawing of the target user, travel data (recorded as travel data corresponding to the second virtual user) of the second virtual user from the target start point to the target end point according to the navigation route used before yawing of the target user is obtained, and the travel data is added to the travel data corresponding to the virtual user. The advancing process of the second virtual user simulates an advancing decision mode of the target user.

Because the traveling process of the second virtual user simulates the traveling decision mode of the target user, the traveling process of the second virtual user from the yaw point when the yaw occurs to the target ending point can be considered as the traveling process of the second virtual user from the yaw point when the yaw occurs to the target ending point according to the navigation route used before the yaw of the target user, and the traveling process of the second virtual user from the yaw point when the yaw occurs to the target ending point can be considered as the traveling process of the second virtual user from the yaw point when the yaw occurs to the target ending point according to the navigation route used before the yaw of the target user. Meanwhile, the travel data corresponding to the second virtual user can be regarded as travel data of the target user from the target starting point to the target ending point according to the navigation route used before the user yaw.

When acquiring the travel data of the second virtual user from the target starting point to the target ending point according to the navigation route used by the target user before yaw, the travel data of the target user from the target starting point to the yaw point according to the navigation route used by the target user before yaw can be acquired first, then the travel data of the second virtual user from the yaw point to the target ending point according to the navigation route used by the target user before yaw is acquired, and then the travel data of the second virtual user from the target starting point to the yaw point (namely, the travel data corresponding to the second virtual user) according to the travel data of the target user from the target starting point to the yaw point and the travel data of the second virtual user from the yaw point to the target ending point are determined.

In one possible implementation manner, in order to quickly acquire the travel data of the second virtual user from the target starting point to the target ending point according to the navigation route used before the yaw of the user, and better compare the difference between the travel data of the target user and the travel data of the virtual user from the target starting point to the target ending point of the same navigation route, so as to adjust the virtual user, so that the travel process of the virtual user can more accurately simulate the travel decision mode of the target user, and a third virtual user can be configured for the target user first, and then the third virtual user is controlled to simulate the travel process from the target starting point to the target ending point along the actual navigation route of the target user. Meanwhile, when acquiring the travel data of the second virtual user from the target starting point to the target ending point according to the navigation route used before the user yaw, the travel data of the third virtual user from the target starting point to the yaw point according to the navigation route used before the user yaw can be acquired first, then the travel data of the second virtual user from the yaw point to the target ending point according to the navigation route used before the user yaw is acquired, and then the travel data of the second virtual user from the target starting point to the target ending point is determined according to the travel data of the third virtual user from the target starting point to the yaw point and the travel data of the second virtual user from the yaw point to the target ending point. The advancing process of the third virtual user simulates an advancing decision mode of the target user.

In an example, the travel feature corresponding to the target user may be obtained first, then, the travel feature corresponding to the target user is input into the virtual user creation model, a third virtual user output by the virtual user creation model based on the travel feature corresponding to the user is obtained, and when the corresponding second virtual user is configured for the navigation route used before yaw of the target user, the second virtual user may be obtained by copying the third virtual user. Since the travel process of the third virtual user simulates the travel decision mode of the target user, the travel process of the second virtual user can also simulate the travel decision mode of the target user. Meanwhile, the second virtual user is obtained by copying the third virtual user, so that the generation efficiency of the second virtual user can be improved, and corresponding processing resources are saved.

And adding the travel data corresponding to the second virtual user to the travel data corresponding to the virtual user can enrich the data quantity of the travel data corresponding to the virtual user. Because the advancing process of the second virtual user also simulates the advancing decision mode of the target user, the travel data corresponding to the second virtual user can be regarded as the travel data of the target user from the target starting point to the target ending point according to the navigation route used before the yaw of the user. Therefore, the data quantity of the travel data corresponding to the virtual user is enriched, the travel data respectively generated by the target user from the target starting point to the target ending point according to different navigation routes in the same time period can be enriched, at this time, the navigation route recommendation model is trained at least based on the travel data corresponding to the virtual user and the travel data corresponding to the user, and the navigation route recommendation model can be trained to recommend the navigation route which meets the travel data requirement of the target user more.

In order to further enrich the data volume of the travel data corresponding to the virtual user, after the third virtual user is controlled to simulate the travel process from the target starting point to the target ending point along the actual navigation route of the target user, the travel data corresponding to the third virtual user can be further acquired and added to the travel data corresponding to the virtual user.

Because the travelling process of the third virtual user also simulates the travelling decision mode of the target user, the travel data corresponding to the third virtual user can be regarded as the travel data generated by the target user according to the actual navigation route travelling from the target starting point to the target ending point. Therefore, the data quantity of the travel data corresponding to the virtual user is further enriched, the travel data respectively generated by the target user from the target starting point to the target ending point according to different navigation routes in the same time period can be further enriched, at this time, the navigation route recommendation model is trained at least based on the travel data corresponding to the virtual user and the travel data corresponding to the user, and the navigation route recommendation model can be trained to recommend the navigation route which meets the travel data requirement of the target user more.

In addition, in the process that the first virtual user and the second virtual user travel to the target ending point, one or more yaw may occur, in order to further enrich the travel data corresponding to the virtual user, when the first virtual user and the second virtual user each time yaw occurs, a corresponding fourth virtual user may be configured according to a navigation route used after the yaw of the user, then the fourth virtual user is controlled to simulate the travel process from the yaw point when the yaw occurs to the target ending point according to the navigation route used before the yaw of the first virtual user or the second virtual user, and the travel data from the target starting point to the target ending point according to the navigation route used before the yaw of the first virtual user or the second virtual user of the fourth virtual user is obtained and added to the travel data corresponding to the virtual user. The advancing process of the fourth virtual user simulates an advancing decision mode of the target user.

After the route data corresponding to the virtual user and the route data corresponding to the target user are obtained, the navigation method provided by the embodiment of the application needs to further execute step S305, and in step S305, a navigation route recommendation model is trained at least based on the route data corresponding to the virtual user and the route data corresponding to the target user; the navigation route recommendation model is used for recommending navigation routes for target users.

Training the navigation route recommendation model at least based on the travel data corresponding to the virtual user and the travel data corresponding to the user means that the travel data corresponding to the virtual user and the travel data corresponding to the user are taken as travel data samples, and the navigation route recommendation model is trained by utilizing the travel data samples so as to adjust model parameters of the navigation route recommendation model, and the trained navigation route recommendation model is obtained.

The embodiment of the present application further provides a training method for a virtual user creation model, and as shown in fig. 4, a flowchart of a training method 400 for a virtual user creation model according to another embodiment of the present application may include steps S401 to S402.

In step S401, a travel feature set of a sample and a travel decision mode of a corresponding label are obtained; the sample travel feature set comprises at least one travel feature corresponding to a plurality of sample users and travel features corresponding to a plurality of sample user groups; the travel characteristics are used to characterize historical travel behavior.

In step S402, a virtual user creation model is trained using the sample travel feature set and the travel decision mode of the corresponding label, and the virtual user creation model is used for generating a virtual user based on travel features corresponding to the target user when the navigation method provided in the embodiment of the present application is executed.

According to the training method for the virtual user creation model, provided by the embodiment of the application, a sample travel characteristic set and a travel decision mode result corresponding to the label are obtained. And then training a virtual user creation model for generating a virtual user based on the travel characteristics corresponding to the target user when the navigation method provided by the embodiment of the application is executed by utilizing the sample travel characteristic set and the travel decision mode corresponding to the label.

The training is used for generating a virtual user creation model of the virtual user based on travel characteristics corresponding to the target user when the navigation method provided by the embodiment of the application is executed, so that the speed of configuring the virtual user can be improved, the manpower resources required to be consumed in the configuration process of the virtual user are reduced, and further, the execution of the navigation method provided by the embodiment of the application is better ensured.

It should be noted that, the user information (including but not limited to user location information, navigation route used by the user, etc.) and the data (including but not limited to user trip characteristics, historical behavior data, displayed data, etc.) related to the present application are information and data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region, and provide corresponding operation entries for the user to select authorization or rejection.

Corresponding to the application example of the method and the navigation method provided by the embodiment of the application, the embodiment of the application also provides a navigation device. As shown in fig. 5, which is a block diagram illustrating a navigation device 500 according to an embodiment of the present application, the device 500 may include:

A recommended navigation route obtaining module 501, configured to obtain a preferred recommended navigation route and at least one alternative recommended navigation route for a target starting point and a target ending point;

the first virtual user configuration module 502 is configured to configure a corresponding first virtual user for at least one candidate recommended navigation route when the target user selects the preferred recommended navigation route to initiate navigation; the advancing process of the first virtual user simulates an advancing decision mode of the target user;

a traveling process simulation module 503, configured to control the first virtual user to simulate a traveling process from the target starting point to the target ending point according to the corresponding alternative recommended navigation route;

the trip data obtaining module 504 is configured to obtain trip data corresponding to the virtual user and trip data corresponding to the target user; the virtual users at least comprise first virtual users, the first virtual users generate travel data according to alternative recommended navigation routes, and the target users generate travel data according to actual navigation routes from a target starting point to a target ending point;

a recommendation model training module 505, configured to train a navigation route recommendation model based at least on the trip data corresponding to the virtual user and the trip data corresponding to the target user; the navigation route recommendation model is used for recommending navigation routes for target users.

In one possible implementation, the trip data acquisition module 504 includes:

the yaw detection sub-module is used for detecting whether yaw occurs in the process that a target user moves from a target starting point to a target ending point;

the actual navigation route determining sub-module is used for acquiring the navigation route of the target user after yaw as an actual navigation route when yaw of the target user is detected;

and the first data acquisition sub-module is used for acquiring journey data corresponding to the actual navigation route as journey data corresponding to the target user.

In one possible implementation, the trip data acquisition module 504 further includes:

the second virtual user configuration sub-module is used for configuring a corresponding second virtual user aiming at a navigation route used before the target user yaw when the target user yaw each time if the target user yaw is detected; the advancing process of the second virtual user simulates an advancing decision mode of the target user;

the second virtual user control sub-module is used for controlling the second virtual user to simulate a traveling process from a yaw point to a target termination point when the target user yaw occurs according to a navigation route used before the target user yaw;

And the journey data adding sub-module is used for acquiring journey data of the second virtual user from the target starting point to the target ending point according to the navigation route used before the target user yaw, and adding the journey data to the journey data corresponding to the virtual user.

the third virtual user configuration submodule is used for configuring a third virtual user for the target user, and the advancing process of the third virtual user simulates an advancing decision mode of the target user;

and the third virtual user control sub-module is used for controlling the third virtual user to simulate a traveling process from the target starting point to the target ending point along the actual navigation route of the target user.

In one possible implementation, the trip data addition submodule includes:

the second data acquisition sub-module is used for acquiring travel data of a third virtual user from a target starting point to a yaw point according to a navigation route used before the target user yaw;

the third data acquisition sub-module is used for acquiring travel data of the second virtual user from the yaw point to the target termination point according to a navigation route used before the target user yaw;

and the fourth data acquisition sub-module is used for determining the travel data of the second virtual user from the target starting point to the target ending point according to the travel data of the third virtual user from the target starting point to the yaw point and the travel data of the second virtual user from the yaw point to the target ending point, wherein the travel data of the second virtual user from the target starting point to the target ending point is used for the navigation route before the yaw of the target user.

In one possible implementation, the first virtual user configuration module 502 includes:

the trip characteristic acquisition sub-module is used for acquiring trip characteristics corresponding to the target user; the travel characteristics corresponding to the target user are used for representing the historical travel behaviors of the target user;

the first virtual user configuration sub-module is used for respectively configuring corresponding first virtual users for each alternative recommended navigation route according to travel characteristics corresponding to the target user.

In one possible implementation, the first virtual user configuration sub-module includes:

the first virtual user acquisition sub-module acquires a first virtual user configured according to travel characteristics of the target user aiming at each alternative recommended navigation route, and the first virtual user generates the target user by inputting the travel characteristics into the virtual user creation model.

The functions of each module in each device of the embodiment of the present application may be referred to the corresponding descriptions in the above methods, and have corresponding beneficial effects, which are not described herein.

Corresponding to the application example of the method and the training method of the virtual user creation model provided by the embodiment of the application, the embodiment of the application also provides a training device of the virtual user creation model. Referring to fig. 6, which is a block diagram illustrating a training apparatus 600 for creating a model for a virtual user according to an embodiment of the present application, the apparatus 600 may include:

The data acquisition module 601 is configured to acquire a travel feature set of a sample and a travel decision mode of a corresponding label; the sample travel feature set comprises at least one travel feature corresponding to a plurality of sample users and travel features corresponding to a plurality of sample user groups; the travel characteristics are used to characterize historical travel behavior.

The model training module 602 is configured to train a virtual user creation model by using the sample travel feature set and the travel decision mode of the corresponding label, where the virtual user creation model is configured to generate a virtual user based on travel features corresponding to the target user when the navigation method provided in the embodiment of the present application is executed.

Fig. 7 is a block diagram of an electronic device used to implement an embodiment of the application. As shown in fig. 7, the electronic device includes: a memory 701 and a processor 702, the memory 701 storing a computer program executable on the processor 702. The processor 702, when executing the computer program, implements the methods of the embodiments described above. The number of memories 701 and processors 702 may be one or more.

The electronic device further includes:

and the communication interface 703 is used for communicating with external equipment and performing data interaction transmission.

If the memory 701, the processor 702, and the communication interface 703 are implemented independently, the memory 701, the processor 702, and the communication interface 703 may be connected to each other and perform communication with each other through buses. The bus may be an industry standard architecture (Industry Standard Architecture, ISA) bus, an external device interconnect (Peripheral Component Interconnect, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in fig. 7, but not only one bus or one type of bus.

Alternatively, in a specific implementation, if the memory 701, the processor 702, and the communication interface 703 are integrated on a chip, the memory 701, the processor 702, and the communication interface 703 may communicate with each other through internal interfaces.

The embodiment of the application provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the method provided in the embodiment of the application.

The embodiment of the application also provides a chip, which comprises a processor and is used for calling the instructions stored in the memory from the memory and running the instructions stored in the memory, so that the communication equipment provided with the chip executes the method provided by the embodiment of the application.

The embodiment of the application also provides a chip, which comprises: the input interface, the output interface, the processor and the memory are connected through an internal connection path, the processor is used for executing codes in the memory, and when the codes are executed, the processor is used for executing the method provided by the application embodiment.

It should be appreciated that the processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or any conventional processor or the like. It is noted that the processor may be a processor supporting an advanced reduced instruction set machine (Advanced RISC Machines, ARM) architecture.

Further alternatively, the memory may include a read-only memory and a random access memory. The memory may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), programmable ROM (PROM), erasable Programmable ROM (EPROM), electrically Erasable EPROM (EEPROM), or flash Memory, among others. Volatile memory can include random access memory (Random Access Memory, RAM), which acts as external cache memory. By way of example, and not limitation, many forms of RAM are available. For example, static RAM (SRAM), dynamic RAM (Dynamic Random Access Memory, DRAM), synchronous DRAM (SDRAM), double Data Rate Synchronous DRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), and Direct RAM (DR RAM).

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions in accordance with the present application are fully or partially produced. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. Computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another.

In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.

Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.

Any process or method described in flow charts or otherwise herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process. And the scope of the preferred embodiments of the present application includes additional implementations in which functions may be performed in a substantially simultaneous manner or in an opposite order from that shown or discussed, including in accordance with the functions that are involved.

Logic and/or steps described in the flowcharts or otherwise described herein, e.g., may be considered a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions.

It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the methods of the embodiments described above may be performed by a program that, when executed, comprises one or a combination of the steps of the method embodiments, instructs the associated hardware to perform the method.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing module, or each unit may be physically present separately, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules described above, if implemented in the form of software functional modules and sold or used as a stand-alone product, may also be stored in a computer-readable storage medium. The storage medium may be a read-only memory, a magnetic or optical disk, or the like.

The above description is merely an exemplary embodiment of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think of various changes or substitutions within the technical scope of the present application, and these should be covered in the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.

Claims

1. A navigation method, comprising:

when a target user selects the preferred recommended navigation route to initiate navigation, configuring a corresponding first virtual user for the at least one alternative recommended navigation route; the advancing process of the first virtual user simulates an advancing decision mode of the target user;

controlling the first virtual user to simulate a traveling process from the target starting point to the target ending point according to the corresponding alternative recommended navigation route;

acquiring travel data corresponding to a virtual user and travel data corresponding to the target user; the virtual user at least comprises a first virtual user, the first virtual user generates travel data according to the alternative recommended navigation route, and the target user generates travel data according to an actual navigation route from the target starting point to the target ending point;

Training a navigation route recommendation model at least based on the travel data corresponding to the virtual user and the travel data corresponding to the target user; the navigation route recommendation model is used for recommending navigation routes for the target user.

2. The method of claim 1, wherein the trip data corresponding to the target user is obtained by:

detecting whether yaw occurs in the process that the target user travels from the target starting point to the target ending point;

if the target user is detected to yaw, acquiring a navigation route of the target user after yaw as an actual navigation route;

and acquiring journey data corresponding to the actual navigation route as journey data corresponding to the target user.

3. The method of claim 2, wherein the virtual user further comprises a second virtual user, the method further comprising:

if the target user is detected to yaw, configuring a corresponding second virtual user for a navigation route used before the target user yaw when the target user yaw each time; the advancing process of the second virtual user simulates an advancing decision mode of the target user;

Controlling the second virtual user to simulate a traveling process from a yaw point when yaw occurs to the target user to the target end point according to a navigation route used before yaw of the target user;

and acquiring travel data of the second virtual user from the target starting point to the target ending point according to a navigation route used before yaw of the target user, and adding the travel data to the travel data corresponding to the virtual user.

4. A method according to claim 3, further comprising:

configuring a third virtual user for the target user, wherein the advancing process of the third virtual user simulates an advancing decision mode of the target user;

and controlling the third virtual user to simulate a traveling process from the target starting point to the target ending point along the actual navigation route of the target user.

5. The method of claim 4, wherein the obtaining travel data for the second virtual user to travel from the target start point to the target end point in accordance with a navigation route used before yaw of the target user comprises:

acquiring travel data of a third virtual user from the target starting point to the yaw point according to a navigation route used before yaw of the target user;

Acquiring travel data of the second virtual user from the yaw point to the target termination point according to a navigation route used before yaw of the target user;

and determining the travel data of the second virtual user from the target starting point to the target ending point according to the navigation route used by the second virtual user before yaw of the target user according to the travel data of the third virtual user from the target starting point to the yaw point and the travel data of the second virtual user from the yaw point to the target ending point.

6. The method of claim 1, wherein the generating a corresponding first virtual user for the at least one alternative recommended navigation route comprises:

acquiring travel characteristics corresponding to the target user; the travel characteristics corresponding to the target user are used for representing the historical travel behaviors of the target user;

and respectively configuring corresponding first virtual users for each alternative recommended navigation route according to the travel characteristics corresponding to the target users.

7. The method of claim 6, wherein the configuring the corresponding first virtual user for each candidate recommended navigation route according to the travel characteristic corresponding to the target user includes:

And aiming at each alternative recommended navigation route, acquiring a first virtual user configured according to the travel characteristics of the target user, wherein the first virtual user generates the target user by inputting the travel characteristics into a virtual user creation model.

8. A training method for a virtual user creation model, comprising:

training a virtual user creation model by using the sample travel feature set and a travel decision mode of a corresponding label, wherein the virtual user creation model is used for generating the virtual user based on travel features corresponding to the target user when executing the method of any one of claims 1-7.

9. A navigation device, comprising:

the first virtual user configuration module is used for configuring a corresponding first virtual user aiming at the at least one alternative recommended navigation route when the target user selects the preferred recommended navigation route to initiate navigation; the advancing process of the first virtual user simulates an advancing decision mode of the target user;

The advancing process simulation module is used for controlling the first virtual user to simulate an advancing process from the target starting point to the target ending point according to the corresponding alternative recommended navigation route;

the journey data acquisition module is used for acquiring journey data corresponding to the virtual user and journey data corresponding to the target user; the virtual user at least comprises a first virtual user, the first virtual user generates travel data according to the alternative recommended navigation route, and the target user generates travel data according to an actual navigation route from the target starting point to the target ending point;

the recommendation model training module is used for training a navigation route recommendation model at least based on the travel data corresponding to the virtual user and the travel data corresponding to the target user; the navigation route recommendation model is used for recommending navigation routes for the target user.

10. A computer readable storage medium having stored therein a computer program which, when executed by a processor, implements the method of any of claims 1-8.