CN111854779B

CN111854779B - Route planning method and device, electronic equipment and readable storage medium

Info

Publication number: CN111854779B
Application number: CN202010117331.9A
Authority: CN
Inventors: 董建强; 王征
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2020-02-25
Filing date: 2020-02-25
Publication date: 2022-04-26
Anticipated expiration: 2040-02-25
Also published as: CN111854779A

Abstract

The application provides a route planning method, a route planning device, electronic equipment and a readable storage medium, wherein historical driving track data of a path user to be planned in a target driving area and basic road network data of the target driving area are acquired, wherein the historical driving track data and the basic road network data meet preset path planning conditions within a historical time period; determining the difference degree between each historical driving road section of a user of a path to be planned and a corresponding target basic road section in a plurality of basic road sections determined by the basic data based on the historical driving track data and the basic road network data respectively; determining a plurality of preference driving road sections and a sub-road network of the user of the path to be planned based on each difference degree; and planning a travel route based on the basic road network and the sub-road network. Therefore, the planned travel route can be fit with the actual cognition and familiarity degree of the user to the route, the accuracy of travel route planning is improved, and the probability and times of route re-planning are reduced, so that the consumption of computing resources is reduced, and the equipment burden and the performance loss are reduced.

Description

Route planning method and device, electronic equipment and readable storage medium

Technical Field

The present application relates to the field of path planning and navigation technologies, and in particular, to a route planning method and apparatus, an electronic device, and a readable storage medium.

Background

In the daily travel process of people, navigation is closely related to the daily life of users due to the accuracy and timeliness of navigation, so that the navigation system becomes an essential use tool for people, is widely applied to the fields of user travel, search and rescue, scientific research and the like, and is greatly convenient for the actual life of users.

The most basic route planning for realizing the navigation function is the route planning for the user, most of the existing route planning is based on real-time road conditions, a route between a starting point and a terminal point is planned, or a route which is recently taken by the user or is taken by most of the users is directly recommended to the user, the route planning mode is effective for users who are unfamiliar in a travel area, but when partial areas or partial routes which are familiar to the user exist in the travel area, the route planned by the conventional route planning mode is low in accuracy, when the user is in combination with own cognitive travel, the user is prone to yaw, so that the travel route needs to be re-planned in real time, and the calculation resource consumption and equipment burden of the route planning are increased.

Disclosure of Invention

In view of the above, an object of the present invention is to provide a route planning method, apparatus, electronic device and readable storage medium, which can learn the driving preference of a user through historical track data of the user to screen out a preferred driving road section of the user, and plan a travel route for the user in a basic road network in combination with the preferred driving road section of the user, so that the planned travel route can conform to the actual cognition and familiarity of the user on the route, which is helpful for improving the accuracy of travel route planning, and reducing the probability and times of route re-planning, thereby reducing the consumption of computing resources, and reducing the equipment burden and performance loss.

According to a first aspect of the present application, there is provided a route planning method comprising:

if the path user to be planned meets the preset path planning condition, acquiring historical driving track data of the path user to be planned in a target driving area and basic road network data of the target driving area in a historical time period;

determining a plurality of historical driving road sections driven by the user of the path to be planned and a plurality of basic road sections driven by all users in the target driving area based on the historical driving track data and the basic road network data respectively, and determining a target basic road section corresponding to each historical driving road section in the plurality of basic road sections and the difference degree of each historical driving road section relative to the corresponding target basic road section;

determining a plurality of preferred driving road sections which are preferred to be driven by the user for the path to be planned in the plurality of historical driving road sections and a road network constructed by the plurality of preferred driving road sections based on the difference degree of each historical driving road section;

and planning the travel route of the user of the path to be planned based on the basic road network and the sub road network of the target driving area.

In some embodiments of the present application, before acquiring, in a historical time period, historical travel track data of a path user to be planned in a target travel area and basic road network data of the target travel area if the path user to be planned meets a preset path planning condition, the route planning method includes:

after receiving a path planning request of a path user to be planned, acquiring travel platform data of the path user to be planned;

and if the travel platform data indicate that the path user to be planned belongs to a high-frequency user providing travel service, determining that the path user to be planned meets a preset path planning condition, wherein the characteristics of the high-frequency user include one or more of the number of times of providing service being greater than a preset number of times, the number of service orders being greater than a preset number, the online time in the travel platform being greater than a preset time, and the total distance of the travel route being greater than a preset route distance.

In some embodiments of the present application, the determining, based on the historical driving track data and the basic road network data, a plurality of historical driving road segments traveled by the user of the path to be planned and a plurality of basic road segments traveled by all users in the target driving area, and determining a target basic road segment corresponding to each historical driving road segment in the plurality of basic road segments, and a difference degree of each historical driving road segment with respect to the corresponding target basic road segment, includes:

determining a plurality of historical driving road sections driven by the user of the path to be planned in the target driving area and the density of the driven historical road sections of each historical driving road section based on the historical driving track data;

determining a plurality of basic road segments traveled by all users in the target travel area, a target basic road segment corresponding to each historical travel road segment in the target travel area, and a target basic road segment density in the target travel area, wherein the target basic road segment corresponding to each historical travel road segment in the plurality of basic road segments is traveled by;

and determining the difference degree of each historical driving road section relative to the corresponding target basic road section based on the historical road section density and the target basic road section density.

In some embodiments of the present application, the determining, based on the historical driving track data, a plurality of historical driving road segments that the user has driven along the path to be planned in the target driving area, and a historical road segment density that each historical driving road segment has driven along, includes:

determining a plurality of historical driving road sections driven by the path user to be planned, the driving times of the path user to be planned driving each historical driving road section and the total driving times of the path user to be planned driving the plurality of historical driving road sections based on the historical driving track data;

and determining the historical road section density of each historical driving road section which is driven on the basis of the driving times of each historical driving road section and the total driving times.

In some embodiments of the present application, the determining the historical link density of each historical travel link traveled based on the number of travels of each historical travel link and the total number of travels includes:

determining a historical link density for each historical travel link by:

A＝x₁/y₁；

wherein A is the historical road section density of the historical driving road section, x₁The number of travel times, y, for the history travel section₁And the total driving times of the user driving the plurality of historical driving road sections for the path to be planned.

In some embodiments of the present application, the determining, based on the basic road network data, a plurality of basic road segments traveled by all users in the target driving region, a target basic road segment in the target driving region corresponding to each historical driving road segment, and a target basic road segment density in the target driving region at which a target basic road segment in the plurality of basic road segments corresponding to each historical driving road segment is traveled includes:

determining, based on the basic road network data, a number of passes by which each of a plurality of basic road segments in the target driving region is driven and a total number of passes by which the plurality of basic road segments are driven;

and determining the density of the basic road sections which are driven by the target basic road sections corresponding to the historical driving road sections based on the passing times of each target basic road section and the total passing times.

Further, the determining, based on the number of passes of each target base link and the total number of passes, the density of the base links on which the target base link corresponding to each historical travel link has been traveled includes:

determining a base link density of a target base link corresponding to each historical travel link by:

B＝x₂/y₂；

wherein B is a basic link density of a basic link corresponding to the historical travel link, x₂The number of passes of the basic link corresponding to the historical travel link, y₂The total number of passes for which the plurality of base links were driven.

In some embodiments of the present application, the determining a degree of difference of each historical travel segment with respect to the corresponding target base segment based on the historical segment density and the target base segment density includes:

determining a degree of dissimilarity of each historical travel segment with respect to a corresponding target base segment by:

C＝((A-B)/B)*X+(A-B)*(1-X)；

wherein C is the difference degree of the historical driving road section relative to the corresponding target basic road section, A is the historical road section density of the historical driving road section, B is the basic road section density of the basic road section corresponding to the historical driving road section, and X is a constant parameter.

In some embodiments of the present application, the determining, based on the difference degree of each historical driving road segment, a plurality of preferred driving road segments that the user prefers to drive for the path to be planned to drive among the plurality of historical driving road segments, and a sub-road network constructed by the plurality of preferred driving road segments includes:

determining a plurality of historical driving road sections with the difference degree larger than a preset threshold value, or determining a preset number of historical driving road sections in the plurality of historical driving road sections as candidate road sections, wherein the difference degree of the candidate road sections is larger than that of other historical driving road sections except the candidate road sections in the plurality of historical driving road sections;

and screening candidate road sections meeting preset screening conditions from the candidate road sections, and determining the remaining candidate road sections after screening from the candidate road sections as the preferred driving road sections which are preferred to be driven by the user of the path to be planned, wherein the candidate road sections meeting the preset screening conditions are road sections which are driven by the user of the path to be planned less than the preset times, or a plurality of road sections which are connected into a ring, or road sections which exist independently.

In some embodiments of the present application, the planning a travel route of the user for a path to be planned based on the base road network and the sub-road network of the target driving area includes:

inputting the road network and at least one historical driving track indicated by the historical driving track data into a road section weight prediction model which is trained in advance to obtain the preference weight of each preferred driving road section in the road network;

determining a basic weight of each basic road section in a basic road network of the target driving area based on the basic road network data;

and planning the travel route of the user of the path to be planned in the target driving area based on the preference weight of each preference driving road section and the basic weight of each basic road section.

In some embodiments of the present application, the planning a travel route of the user of the path to be planned in the target driving area based on the preference weight of each preference driving section and the basis weight of each basis section includes:

replacing the target basic weight of the corresponding target basic road section in the basic road network by using the preference weight of each preference driving road section to obtain the basic road network after the weight is updated;

and planning the travel route of the user of the path to be planned in the basic road network after the weight is updated.

In some embodiments of the present application, the replacing, by the preference weight of each preferred driving road segment, the target basic weight of a corresponding target basic road segment in the basic road network to obtain an updated weight of the basic road network includes:

when the preference weight of each preference driving road section is used for replacing the target basic weight of the corresponding target basic road section in the basic road network, aiming at each preference driving road section, if the preference weight of the preference driving road section is larger than the target basic weight of the corresponding target basic road section, the preference weight of the preference driving road section is adjusted to be smaller than the target basic weight of the corresponding target basic road section, the adjusted preference weight of the preference driving road section is used for replacing the target basic weight of the corresponding target basic road section in the basic road network, and the basic road network after the weight is updated is obtained.

determining a first route between a first transit point of a user to be planned from a travel origin to a sub-road network area where the sub-road network is located and the travel origin and the first transit point, and a second route between a second transit point of the user to be planned from a travel destination to the sub-road network area and the travel destination and the second transit point based on a basic weight of each basic road segment;

determining a preference route of the user of the path to be planned in the sub-road network region from the first transit point to the second transit point based on the preference weight of each preference driving road section;

determining a travel route in the target travel area including the first route, the second route, and the preferred route.

In some embodiments of the present application, the road segment weight prediction model is trained by:

determining a sample sub-road network of each sample user based on the obtained sample driving track data of the plurality of sample users, an actual driving track of each sample user indicated by the sample driving track data, and a sample basis weight of each sample road section in each actual driving track;

inputting the sample sub-road network and the actual running track into the constructed deep learning model aiming at each sample user to obtain the prediction preference weight of each sample road section in the sample sub-road network;

determining a predicted driving track of each sample user in the corresponding sample sub-road network based on the prediction preference weight of each sample road section in each sample sub-road network;

for each sample user, determining a deviation value between an actual running path of an actual running track of the sample user in the corresponding sample sub-road network and a predicted running track;

if the deviation value corresponding to the sample user is larger than a preset deviation threshold value, adjusting parameters in the deep learning model until the deviation value corresponding to each sample user is smaller than or equal to the preset deviation threshold value, determining that the deep learning model is completely trained, and determining the deep learning model after being trained as the trained road section weight prediction model.

According to a second aspect of the present application, there is provided a route planning apparatus comprising:

the data acquisition module is used for acquiring historical driving track data of the path user to be planned in a target driving area and basic road network data of the target driving area in a historical time period if the path user to be planned meets a preset path planning condition;

a difference degree determining module, configured to determine, based on the historical driving trajectory data and the basic road network data, a plurality of historical driving road segments traveled by the user of the path to be planned and a plurality of basic road segments traveled by all users in the target driving area, and determine a target basic road segment corresponding to each historical driving road segment in the plurality of basic road segments and a difference degree of each historical driving road segment with respect to the corresponding target basic road segment;

the sub-road network construction module is used for determining a plurality of preference driving road sections which are preferred to be driven by the user for the path to be planned in the plurality of historical driving road sections and a sub-road network constructed by the plurality of preference driving road sections based on the difference degree of each historical driving road section;

and the route planning module is used for planning the travel route of the user with the path to be planned based on the basic road network and the sub road network of the target driving area.

In some embodiments of the present application, the route planning apparatus further comprises a user detection module for:

In some embodiments of the application, when the difference determining module is configured to determine, based on the historical driving track data and the basic road network data, a plurality of historical driving road segments traveled by the user for the path to be planned and a plurality of basic road segments traveled by all users in the target driving area, and determine a target basic road segment corresponding to each historical driving road segment in the plurality of basic road segments, and a difference between each historical driving road segment and the corresponding target basic road segment, the difference determining module is configured to:

In some embodiments of the application, when the difference degree determination module is configured to determine, based on the historical travel track data, a plurality of historical travel sections traveled by the user for the path to be planned in the target travel area and a historical section density traveled by each historical travel section, the difference degree determination module is configured to:

In some embodiments of the present application, the difference degree determination module, when configured to determine the density of the historical road segments traveled by each historical travel segment based on the number of travels of each historical travel segment and the total number of travels, is configured to:

determining a historical link density for each historical travel link by:

A＝x₁/y₁；

In some embodiments of the present application, when the difference degree determining module is configured to determine, based on the basic road network data, a plurality of basic road segments traveled by all users in the target travel area, a target basic road segment in the target travel area corresponding to each historical travel road segment, and a target basic road segment density in the target travel area at which a target basic road segment in the plurality of basic road segments corresponding to each historical travel road segment is traveled, the difference degree determining module is configured to:

In some embodiments of the present application, when the difference degree determination module is configured to determine the density of the base road segments traveled by the target base road segment corresponding to each historical travel road segment based on the number of passes of each target base road segment and the total number of passes, the difference degree determination module is configured to:

B＝x₂/y₂；

In some embodiments of the present application, the difference degree determination module, when configured to determine the difference degree of each historical travel segment relative to the corresponding target base segment based on the historical segment density and the target base segment density, is configured to:

C＝((A-B)/B)*X+(A-B)*(1-X)；

In some embodiments of the present application, when the sub-road network construction module is configured to determine, based on a difference degree of each historical driving road segment, a plurality of preferred driving road segments to be preferably driven by the user for the path to be planned, and a sub-road network constructed by the plurality of preferred driving road segments, the sub-road network construction module is configured to:

In some embodiments of the present application, when the route planning module is configured to plan the travel route of the user for the path to be planned based on the base road network and the sub-road network of the target driving area, the route planning module is configured to:

In some embodiments of the present application, when the route planning module is configured to plan the travel route of the user of the path to be planned in the target driving area based on the preference weight of each preference driving section and the base weight of each base section, the route planning module is configured to:

In some embodiments of the present application, when the route planning module is configured to replace a target basic weight of a corresponding target basic road segment in a basic road network with a preference weight of each preferred driving road segment to obtain an updated weight of the basic road network, the route planning module is configured to:

In some embodiments of the present application, the route planning apparatus further comprises a model training module for training the road segment weight prediction model by:

An embodiment of the present application further provides an electronic device, including: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating over the bus when the electronic device is operating, the machine-readable instructions when executed by the processor performing the steps of the route planning method as described above.

Embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the route planning method as described above.

According to the route planning method, the route planning device, the electronic equipment and the readable storage medium, if a path user to be planned meets a preset path planning condition, historical driving track data of the path user to be planned in a target driving area and basic road network data of the target driving area in a historical time period are acquired; determining a plurality of historical driving road sections driven by the user of the path to be planned and a plurality of basic road sections driven by all users in the target driving area based on the historical driving track data and the basic road network data respectively, and determining a target basic road section corresponding to each historical driving road section in the plurality of basic road sections and the difference degree of each historical driving road section relative to the corresponding target basic road section; determining a plurality of preferred driving road sections which are preferred to be driven by the user for the path to be planned in the plurality of historical driving road sections and a road network constructed by the plurality of preferred driving road sections based on the difference degree of each historical driving road section; and planning the travel route of the user of the path to be planned based on the basic road network and the sub road network of the target driving area.

In this way, when the user of the path to be planned meets the preset path planning condition, the historical driving track data of the user of the path to be planned in the target driving area in the historical time period is acquired, and basic road network data in the target driving area, determining a plurality of preferred driving roads which are preferably driven by the user of the path to be planned according to a plurality of historical driving road sections and the difference degree between the corresponding target basic road sections, and constructing a sub-road network, planning a travel route of the user of the path to be planned according to the target driving area and the road network, the planned travel route can be fitted with the actual cognition and familiarity degree of the user to the route, the accuracy of travel route planning is improved, and the probability and times of route re-planning are reduced, so that the consumption of computing resources is reduced, and the equipment burden and performance loss are reduced.

In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

Fig. 1 is a schematic diagram of a route planning system according to an embodiment of the present application;

fig. 2 is a schematic flow chart of a route planning method according to an embodiment of the present application;

fig. 3 is a schematic flow chart of a route planning method according to another embodiment of the present application;

fig. 4 is a schematic structural diagram of a route planning apparatus according to an embodiment of the present application;

fig. 5 is a second schematic structural diagram of a route planning apparatus according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. Every other embodiment that can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present application falls within the protection scope of the present application.

In order to enable those skilled in the art to use the present disclosure, the following embodiments are given in conjunction with a specific application scenario "planning a travel route for a user in a travel service". It will be apparent to those skilled in the art that the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the application. Although the present application is described primarily in the context of planning a user's travel route based on the user's preferred road segments and underlying road network, it should be understood that this is merely one exemplary embodiment.

It should be noted that in the embodiments of the present application, the term "comprising" is used to indicate the presence of the features stated hereinafter, but does not exclude the addition of further features.

The terms "passenger," "requestor," "service requestor," and "customer" are used interchangeably in this application to refer to an individual, entity, or tool that can request or order a service. The terms "user," "provider," "service provider," and "vendor" are used interchangeably in this application to refer to an individual, entity, or tool that can provide a service. The term "user" in this application may refer to an individual, entity or tool that requests a service, subscribes to a service, provides a service, or facilitates the provision of a service. For example, the user may be a passenger, a driver, an operator, etc., or any combination thereof. In the present application, "passenger" and "passenger terminal" may be used interchangeably, and "driver" and "driver terminal" may be used interchangeably.

The terms "service request" and "order" are used interchangeably herein to refer to a request initiated by a passenger, a service requester, a user, a service provider, or a supplier, the like, or any combination thereof. Accepting the "service request" or "order" may be a passenger, a service requester, a driver, a service provider, a supplier, or the like, or any combination thereof. The service request may be charged or free.

The Positioning technology used in the present application may be based on a Global Positioning System (GPS), a Global Navigation Satellite System (GLONASS), a COMPASS Navigation System (COMPASS), a galileo Positioning System, a Quasi-Zenith Satellite System (QZSS), a Wireless Fidelity (WiFi) Positioning technology, or the like, or any combination thereof. One or more of the above-described positioning systems may be used interchangeably in this application.

One aspect of the present application relates to a route planning system. The system can acquire historical driving track data of the path user to be planned in a target driving area in a historical time period when the path user to be planned meets a preset path planning condition, and basic road network data in the target driving area, determining a plurality of preferred driving roads which are preferably driven by the user of the path to be planned according to a plurality of historical driving road sections and the difference degree between the corresponding target basic road sections, and constructing a sub-road network, planning a travel route of the user of the path to be planned according to the target driving area and the road network, the planned travel route can be fitted with the actual cognition and familiarity degree of the user to the route, the accuracy of travel route planning is improved, and the probability and times of route re-planning are reduced, so that the consumption of computing resources is reduced, and the equipment burden and performance loss are reduced.

It is worth noting that before the application is provided, the most basic route planning for the user is achieved by realizing the navigation function, and most of the existing route planning is based on real-time road conditions, a route between a starting point and an end point is planned, or a route which is recently walked by the user or walked by most of the users is directly recommended to the user. However, an object of the present invention is to provide a route planning method, apparatus, electronic device and readable storage medium, which can obtain driving preferences of a user through historical track data of the user to screen out preferred driving road segments of the user, and plan a travel route for the user in a basic road network in combination with the preferred driving road segments of the user, so that the planned travel route can conform to actual cognition and familiarity of the user on the route, which is helpful for improving accuracy of travel route planning, and reducing probability and times of route re-planning, thereby reducing consumption of computing resources, and reducing equipment burden and performance loss.

Fig. 1 is a schematic structural diagram of a route planning system according to an embodiment of the present disclosure. The route planning system may be an online transportation service platform for transportation services such as taxi, designated driving service, express, carpool, bus service, driver rental, or regular service, or any combination thereof. The route planning system may include one or more of a server 110, a network 120, a service requester 130, a service provider 140, and a database 150.

In some embodiments, the server 110 may include a processor. The processor may process information and/or data related to the service request to perform one or more of the functions described herein. For example, the processor may determine a target driving area where the user is located and a plurality of preferred road segments for the path to be planned based on the service request obtained from the service requester 130, so as to perform route planning. In some embodiments, a processor may include one or more processing cores (e.g., a single-core processor (S) or a multi-core processor (S)). Merely by way of example, a Processor may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction Set Processor (ASIP), a Graphics Processing Unit (GPU), a Physical Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller Unit, a Reduced Instruction Set computer (Reduced Instruction Set computer), a microprocessor, or the like, or any combination thereof.

In some embodiments, the device types corresponding to the service request end 130 and the service providing end 140 may be mobile devices, such as smart home devices, wearable devices, smart mobile devices, virtual reality devices, or augmented reality devices, and the like, and may also be tablet computers, laptop computers, or built-in devices in motor vehicles, and the like.

In some embodiments, a database 150 may be connected to the network 120 to communicate with one or more components in the route planning system (e.g., the server 110, the service requester 130, the service provider 140, etc.). One or more components in the route planning system may access data or instructions stored in the database 150 via the network 120. In some embodiments, the database 150 may be directly connected to one or more components in the route planning system, or the database 150 may be part of the server 110.

The following describes the route planning method provided in the embodiment of the present application in detail with reference to the content described in the route planning system shown in fig. 1.

Referring to fig. 2, fig. 2 is a schematic flow chart of a route planning method provided in an embodiment of the present application, where the method may be executed by a processor in a route planning system, and the specific execution process includes:

s201, if the path user to be planned meets a preset path planning condition, acquiring historical driving track data of the path user to be planned in a target driving area and basic road network data of the target driving area in a historical time period.

In the step, whether a path user to be planned meets a preset path planning condition or not is detected for the path user to be planned, and if the path user to be planned meets the preset path planning condition, historical driving track data of the path user to be planned in a target driving area and preset basic road network data corresponding to the target driving area in a historical time period are acquired.

The user may be a service requester, i.e. a passenger who requests to travel by bus, or a service provider, i.e. a driver who provides travel service.

The historical time period is a time period before the current route planning starts, and may be, for example, within the past half year time, or a certain time period in a certain day (7: 00-9: 00 in the morning).

Here, the target travel area may be an area from a travel start point to a travel destination of the user of the path to be planned; the target driving area may also be an area from the current position of the user to be planned to the driving destination when the user to be planned routes a driving route while driving.

Here, the historical trajectory data refers to a driving route of the path user to be planned in the target area, and may be one or multiple, the historical trajectory data indicates path selection of the path user to be planned in a driving process within a historical time period, and the historical trajectory data may be trajectory data acquired by a platform when the user is connected with a network appointment platform, and includes trajectory data when the user accepts orders and trajectory data when the user does not accept orders.

Here, the basic road network data of the target driving area includes a basic weight of each basic road segment of the basic road network, where the basic weight refers to a value, such as a value, of each directional edge, where each intersection is a point, and each basic road segment is an edge, and the basic weight is a value of each basic road segment, which may be an average time that the road passes through for all users, and generally, the shorter the time that the road passes through each road for all users, the smaller the basic weight corresponding to the road.

S202, determining a plurality of historical driving road sections driven by the user of the path to be planned and a plurality of basic road sections driven by all users in the target driving area respectively based on the historical driving track data and the basic road network data, and determining a target basic road section corresponding to each historical driving road section in the plurality of basic road sections and the difference degree of each historical driving road section relative to the corresponding target basic road section.

In this step, a plurality of historical driving road segments traveled by the user of the path to be planned may be determined from the historical driving track data, a plurality of basic road segments in the target driving area may be determined according to the basic road network data, a target basic road segment corresponding to each historical driving road segment may be determined from the plurality of basic road segments according to the historical driving track data and the basic network data, and a difference between each historical driving road segment and the corresponding target basic road segment may be determined.

All users in the target area refer to all users traveling in the target area, namely all users including the user to be planned traveling in the target area.

Here, the basic link is determined according to basic road network data of all users traveling in the target traveling region, and the historical traveling link is determined according to track data of the users traveling in the target traveling region along the path to be planned, that is, the basic link comprises the historical traveling link; the historical driving road section and the corresponding target basic road section substantially refer to the same road section, both refer to the road section which is driven by the user and is the route to be planned, one driven road section is a link, the link which is driven by the user is obtained through road binding or map matching, the link is mainly obtained through binding the collected user GPS point sequence on a series of roads of a map, a plurality of links may exist for one intersection, for example, a straight line path from A to B may be composed of the link1, the link2 and the link3, and the links have directionality, that is, two links are in different directions of the same road section. Therefore, when the target basic road section corresponding to the historical driving track data is determined, the target basic road section corresponding to the historical driving track data can be corresponding through links, the link directions corresponding to the historical driving track data and the link directions corresponding to the historical driving track data are the same, and the coincidence degree between the historical driving track data and the target basic road section is larger than a preset threshold value.

Here, a weight value may be determined for each of the historical travel links, and a weight value may also be set in a preset setting for each of the target basic links in the target travel area, so that a difference between each of the historical travel links and the corresponding target basic link may be a difference between the weight value corresponding to the historical travel link and the corresponding weight value corresponding to the target basic link for the same link; it may also refer to a difference in positional distance between actual positions of the historical travel segment and the target base segment.

S203, determining a plurality of preference driving road sections which are preferred to be driven by the user for the path to be planned in the plurality of history driving road sections and a road network constructed by the plurality of preference driving road sections based on the difference degree of each history driving road section.

In this step, a plurality of preferred traveling road sections of the path user to be planned are determined according to the difference degree corresponding to each historical traveling road section determined in step S202 and according to the plurality of difference degrees, and a sub-road network corresponding to the path user to be planned is constructed according to the plurality of preferred traveling road sections.

The sub road network may be included in the base road network, or may be mostly overlapped with the base road network.

The selection of the preferred driving road sections of the user tendency of the path to be planned may be to sort the determined difference values of each historical driving road section according to a preset sequence, select N historical driving road sections corresponding to TopN users of difference values, and determine a plurality of preferred driving road sections of the user tendency of the path to be planned.

And S204, planning the travel route of the user with the path to be planned based on the basic road network and the sub road network of the target driving area.

In this step, according to the basic road network of the target driving area and the sub-road network determined in step S203, the basic road network is adjusted according to the sub-road network to generate a road network corresponding to the user of the path to be planned, and the travel route of the user of the path to be planned is planned in the road network corresponding to the user of the path to be planned.

According to the route planning method provided by the embodiment of the application, if a path user to be planned meets a preset path planning condition, historical driving track data of the path user to be planned in a target driving area and basic road network data of the target driving area in a historical time period are acquired; determining a plurality of basic road sections which are driven by all users in the target driving area of a plurality of historical driving road sections which are driven by the users of the path to be planned based on the historical driving track data and the basic road network data respectively, and determining a target basic road section corresponding to each historical driving road section in the plurality of basic road sections and the difference degree of each historical driving road section relative to the corresponding target basic road section; determining a plurality of preferred driving road sections which are preferred to be driven by the user for the path to be planned in the plurality of historical driving road sections and a road network constructed by the plurality of preferred driving road sections based on the difference degree of each historical driving road section; and planning the travel route of the user of the path to be planned based on the basic road network and the sub road network of the target driving area.

Referring to fig. 3, fig. 3 is a schematic flow chart of a route planning method according to another embodiment of the present application, where the method may be executed by a processor in a route planning system, and the specific execution process includes:

s301, after receiving a path planning request of a path user to be planned, obtaining travel platform data of the path user to be planned.

In this step, after receiving a path planning request of a path user to be planned, obtaining travel platform data corresponding to the path user to be planned on a travel platform according to information such as a unique identity of the path user to be planned, where the obtained travel platform data is travel platform data of a historical time period before a request time of the path planning request currently made by the path user to be planned.

The unique identity of the path user to be planned may include an identity card number, a mobile phone number, an ID or an employee number of the path user to be planned on the travel platform, and the like.

The trip platform data comprises the number of orders of the path users to be planned within a historical time period, the online time, the traversed path, the positions of historical driving road sections, the times of passing through each historical driving road section, the incidence relation between each historical driving road section and other historical road sections and the like.

S302, if the travel platform data indicate that the user of the path to be planned belongs to a high-frequency user providing travel service, determining that the user of the path to be planned meets a preset path planning condition, wherein the characteristics of the high-frequency user include one or more of the number of times of providing service being greater than a preset number of times, the number of service orders being greater than a preset number, the online time in the travel platform being greater than a preset time, and the total distance of the travel route being greater than a preset route distance.

In this step, if the obtained travel platform data of the path user to be planned indicates that the path user to be planned belongs to a high-frequency user providing travel service, it is determined that the path user to be planned meets a preset path planning condition, and path planning can be performed on the path user to be planned.

Here, if the user of the path to be planned is a low-frequency user, the amount of trajectory data of the user of the path to be planned is too small, the accuracy of the obtained result is low, and the reference meaning for planning the travel route is not great, so that travel route planning needs to be performed for a high-frequency user, and the characteristics of the high-frequency user include one or more of the number of times of providing services being greater than a preset number of times, the number of service orders being greater than a preset number of times, the online time in the travel platform being greater than a preset time, and the total distance of the travel route being greater than a preset route distance.

In the process of determining the high-frequency users, data corresponding to multiple users may be sorted in each dimension, multiple users with top ranking are determined as the high-frequency users, for example, the multiple users are sorted in the dimension of the number of service orders, and users with top ranking of 10% are determined as the high-frequency users.

S303, if the path user to be planned meets the preset path planning condition, acquiring historical driving track data of the path user to be planned in a target driving area and basic road network data of the target driving area in a historical time period.

S304, determining a plurality of historical driving road sections driven by the user of the path to be planned and a plurality of basic road sections driven by all users in the target driving area respectively based on the historical driving track data and the basic road network data, and determining a target basic road section corresponding to each historical driving road section in the plurality of basic road sections and the difference degree of each historical driving road section relative to the corresponding target basic road section.

S305, determining a plurality of preference driving road sections which are preferred to be driven by the user for the path to be planned in the plurality of history driving road sections and a road network constructed by the plurality of preference driving road sections based on the difference degree of each history driving road section.

S306, planning the travel route of the user with the path to be planned based on the basic road network and the sub road network of the target driving area.

The descriptions of S303 to S306 may refer to the descriptions of S201 to S204, and the same technical effects can be achieved, which are not described in detail herein.

Further, step S304 includes: determining a plurality of historical driving road sections driven by the user of the path to be planned in the target driving area and the density of the driven historical road sections of each historical driving road section based on the historical driving track data; determining a plurality of basic road segments traveled by all users in the target travel area, a target basic road segment corresponding to each historical travel road segment in the target travel area, and a target basic road segment density in the target travel area, wherein the target basic road segment corresponding to each historical travel road segment in the plurality of basic road segments is traveled by; and determining the difference degree of each historical driving road section relative to the corresponding target basic road section based on the historical road section density and the target basic road section density.

Determining a plurality of historical driving road sections of the path to be planned user in the target driving area within a statistical time period and the density of the driven historical road sections of each historical driving road section according to the acquired historical driving track data; determining a plurality of basic road sections driven by all users in the same target driving area according to the basic road network data, determining a target basic road section corresponding to each historical driving road section from the plurality of basic road sections, and determining the density of the target basic road sections driven in the target driving area of each target basic road section within a statistical time period; and determining the difference degree of each historical driving road section relative to the corresponding target basic road section according to the historical road section density and the target basic road section density corresponding to the historical road section density.

Further, the determining, based on the historical driving track data, a plurality of historical driving sections that the user has driven along the path to be planned in the target driving area, and the historical section density that each historical driving section has driven along, includes: determining a plurality of historical driving road sections driven by the path user to be planned, the driving times of the path user to be planned driving each historical driving road section and the total driving times of the path user to be planned driving the plurality of historical driving road sections based on the historical driving track data; and determining the historical road section density of each historical driving road section which is driven on the basis of the driving times of each historical driving road section and the total driving times.

According to the obtained historical driving track data, determining a plurality of historical driving road sections which are driven by the path user to be planned from each piece of historical driving track data, determining the number of times that the path user to be planned drives the historical driving road section aiming at each historical driving road section, determining the total number of times that the path user to be planned drives all the historical driving road sections, and determining the density of the historical driving road sections which are driven by each historical driving road section through a formula according to the number of times that each historical driving road section is driven and the total number of times that the path user to be planned drives all the historical driving road sections.

Wherein the historical link density for each historical travel link is determined by the formula:

A＝x₁/y₁；

a is the historical road section density of the historical driving road section, x₁The number of travel times, y, for the history travel section₁And the total driving times of the user driving the plurality of historical driving road sections for the path to be planned.

Here, for the determining of the historical link density of each historical driving link, the ratio of the number of times that the user of the path to be planned travels through a certain historical driving link to the total number of times that the user of the path to be planned travels through all the historical driving links within the statistical time period is reflected.

Further, the determining, based on the basic road network data, a plurality of basic road segments traveled by all users in the target driving area, a target basic road segment corresponding to each historical driving road segment in the target driving area, and a target basic road segment density in the target driving area, wherein the target basic road segment corresponding to each historical driving road segment in the plurality of basic road segments is driven by the target driving area, includes: determining, based on the basic road network data, a number of passes by which each of a plurality of basic road segments in the target driving region is driven and a total number of passes by which the plurality of basic road segments are driven; and determining the density of the basic road sections which are driven by the target basic road sections corresponding to the historical driving road sections based on the passing times of each target basic road section and the total passing times.

In this step, the number of times of passing through the base link corresponding to each of the historical travel links among the plurality of base links in the target travel area is determined, and the total number of times of passing through the base link corresponding to each of the historical travel links is determined.

Here, the total number of passes calculation is for all basic links in the target travel area, and the total number of passes should be counted when calculating the total number of passes regardless of whether the basic links correspond to historical travel links.

Wherein the base link density of the target base link corresponding to each historical travel link is determined by the following formula:

B＝x₂/y₂；

Here, for the determination of the base link density of the target base link corresponding to each historical travel link, what is reflected is a ratio of the number of times that the user of the path to be planned travels through a certain target base link to the total number of times that all base links are traveled during the statistical time period.

Further, the determining a degree of difference of each historical travel segment with respect to the corresponding target base segment based on the historical segment density and the target base segment density includes: determining a degree of dissimilarity of each historical travel segment with respect to a corresponding target base segment by:

C＝((A-B)/B)*X+(A-B)*(1-X)；

Here, X is a parameter to be learned, and is used to avoid that links with large difference are links with few passing people, so that the calculated result is more universal, and the constant parameter X may be set through historical experience, or may be set according to the accuracy of the difference.

Further, step S305 includes: determining a plurality of historical driving road sections with the difference degree larger than a preset threshold value, or determining a preset number of historical driving road sections in the plurality of historical driving road sections as candidate road sections, wherein the difference degree of the candidate road sections is larger than that of other historical driving road sections except the candidate road sections in the plurality of historical driving road sections; and screening out candidate road sections meeting preset screening conditions from the candidate road sections, and determining the remaining candidate road sections after screening out from the candidate road sections as the preferred driving road sections which are preferred to be driven by the user of the path to be planned.

In the step, a plurality of historical driving road sections are preliminarily screened according to the calculated difference, wherein the screening mode can be two, firstly, the plurality of historical driving road sections with the difference larger than a preset threshold value are determined to be a plurality of candidate road sections, secondly, all the historical driving road sections are sorted according to the difference of each historical driving road section and a preset sequence, and a plurality of candidate road sections with preset quantity are determined from the historical driving road section which is sorted at the first position; and performing secondary screening on the plurality of candidate road sections, and determining the remaining candidate road sections as the preferred driving road sections which are preferred to be driven by the user of the path to be planned.

Here, for the second filtering method, the preset number may be set according to a requirement, or may be set according to the number of travel links according to historical preference.

Here, the candidate links satisfying the preset screening condition are links in which the number of times that the user travels the route to be planned is less than a preset number of times, or links in a ring, or links existing separately. The preset screening condition is to ensure that the remaining candidate paths are representative, and the preset times are set to filter road sections which are possibly driven by a user of the path to be planned due to special conditions, so that the preset times can be set to be 1; the plurality of road sections connected into the ring may be that the user of the path to be planned is not familiar with the road conditions, and the road passes through the road sections under the condition of repeatedly confirming the road, so that the rules of the path which is obviously not in line with the preference of the user of the path to be planned need to be filtered; the road sections which exist independently cannot form a complete travel route together with other road sections, and may be misoperation in the data statistics acquisition process, and the road sections also need to be filtered.

Further, step S306 includes: inputting the road network and at least one historical driving track indicated by the historical driving track data into a road section weight prediction model which is trained in advance to obtain the preference weight of each preferred driving road section in the road network; determining a basic weight of each basic road section in a basic road network of the target driving area based on the basic road network data; and planning the travel route of the user of the path to be planned in the target driving area based on the preference weight of each preference driving road section and the basic weight of each basic road section.

Inputting the determined sub-road network and at least one historical driving track indicated by the historical driving track data into a trained weight prediction model to obtain a preference weight of each preferred driving road section in the sub-road network, determining a basic weight corresponding to each basic road section according to the setting of the basic road network data, and planning a travel route of the user of the path to be planned in the target driving area according to each corresponding preference weight and basic weight.

In the embodiment of the present application, the preference weight of the preferred traveling road section to be planned is determined by the weight prediction model, but not limited to this, in other embodiments, the preference weight of the preferred traveling road section may be determined by a weight calibration method, for example, for a certain preferred traveling road section, according to the basis weight of the target basic road section corresponding to the preferred traveling road section, the preference weight of the preferred traveling road section may be assigned to a value smaller than the basis weight of the corresponding target basic road section, or after the basis weights corresponding to all basic road sections within the preset range of the preference weight are averaged, the average value is determined as the preference weight of the preferred traveling road section, or after the basis weights corresponding to all basic road sections within the preset range of the preference weight are averaged, and subtracting a preset value from the average value, and determining the difference after difference as the preference weight of the preference driving road section.

Further, the road segment weight prediction model is trained by the following steps:

(1) the method comprises the steps of determining a sample road sub-network of each sample user based on acquired sample travel track data of a plurality of sample users, an actual travel track of each sample user indicated by each sample travel track data, and a sample basis weight of each sample road section in each actual travel track.

In the step, according to the obtained sample driving tracks of the plurality of sample users, a plurality of preferred road sections of each sample user are determined, and a sample sub-road network corresponding to each sample user is determined according to the plurality of preferred road sections of each sample user, wherein each sample driving track data indicates an actual driving track of each corresponding sample user and a sample basis weight of each sample road section included in the actual driving track.

Here, the sample travel track data of the sample user is track data generated during travel of each user during the historical course of travel, and the sample travel track data of a plurality of sample users may be from the same statistical time zone or from a plurality of statistical time zones.

(2) And inputting the sample sub-road network and the actual running track into the constructed deep learning model aiming at each sample user to obtain the prediction preference weight of each sample road section in the sample sub-road network.

In the step, for each sample user, a sample sub-road network corresponding to the sample user and an actual driving track are input into a pre-constructed deep learning model, and after passing through the deep learning model, a prediction preference weight of each sample road section in the sample sub-road network is obtained.

(3) And determining the predicted driving track of each sample user in the corresponding sample sub-road network based on the prediction preference weight of each sample road section in each sample sub-road network.

In the step, according to the prediction preference weight of each sample road section in the sample sub-road network, and by combining with a shortest path algorithm, the predicted travel track of the sample user in the corresponding sample sub-road network is determined.

Wherein the shortest path algorithm may be Dijkstra²Algorithms, and the like.

(4) And determining a deviation value between the actual running path of the actual running track of the sample user in the corresponding sample sub-road network and the predicted running track for each sample user.

In the step, a deviation value between the predicted running track and the actual running track of the same sample user is determined.

Here, the deviation value between the predicted travel trajectory and the actual travel trajectory may be a difference in distance between positions where the predicted travel trajectory and the actual travel trajectory are located within the same link, or may be a difference between a predicted weight of a predicted link in the predicted travel trajectory and an actual weight of an actual travel link in the corresponding actual travel trajectory.

(5) If the deviation value corresponding to the sample user is larger than a preset deviation threshold value, adjusting parameters in the deep learning model until the deviation value corresponding to each sample user is smaller than or equal to the preset deviation threshold value, determining that the deep learning model is completely trained, and determining the deep learning model after being trained as the trained road section weight prediction model.

In this step, if the deviation value determined in step (4) is greater than a preset deviation threshold value, that is, the difference between the predicted travel track and the actual travel track is too large, and the route determined in the deep learning model does not conform to the actual travel situation, further adjusting the parameter values in the deep learning model, repeating steps (1) - (4) until the deviation value corresponding to each sample user is less than or equal to the preset deviation threshold value, determining that the deep learning model is trained, and determining the trained deep learning model as the trained road section weight prediction model.

Here, since the driving trajectory and the sub-roadmap of each user are different, the weight prediction models are also different, that is, a dedicated weight prediction model may be trained for each user, and a weight prediction model suitable for all users may also be trained according to a rule of difference between users.

Further, the planning a travel route of the user of the path to be planned in the target driving area based on the preference weight of each preference driving section and the basis weight of each basis section includes: replacing the target basic weight of the corresponding target basic road section in the basic road network by using the preference weight of each preference driving road section to obtain the basic road network after the weight is updated; and planning the travel route of the user of the path to be planned in the basic road network after the weight is updated.

In this step, data for all users is displayed in a basic road network, data corresponding to the path users to be planned needs to be used for replacing data at corresponding positions in the basic road network for the planned routes of the path users to be planned, namely, target basic weights of target basic road sections in the basic road network are replaced corresponding to preference weights of all preference traveling road sections, updated basic road networks with updated weights corresponding to the path users to be planned are obtained, and travel routes of the path users to be planned are planned according to the updated basic road networks with the updated weights and by combining a shortest path algorithm.

Here, in the basic road network, the determined plurality of preferred traveling road segments of the path to be planned, which are inclined by the user, may be marked with emphasis to be distinguished from the basic road segments in the basic road network, for example, the plurality of preferred traveling road segments may be marked with red, and the like.

Here, as for the preference weight, the value of the preference weight represents the preference of the preferred traveling road section corresponding to the path user to be planned to some extent, and the smaller the value of the preference weight is, the more the path user to be planned prefers to the preferred traveling road section, so in general, the value of the preference weight is smaller than the value of the target basic weight of the corresponding target basic road section.

Here, in the updating process of the basic road network, the original basic weight value is directly retained for the basic weight value of the basic road segment without the corresponding preference traveling road segment, and the updating is not required.

Further, the replacing the target basic weight of the corresponding target basic road segment in the basic road network by the preference weight of each preference traveling road segment to obtain the basic road network with the updated weight includes: when the preference weight of each preference driving road section is used for replacing the target basic weight of the corresponding target basic road section in the basic road network, aiming at each preference driving road section, if the preference weight of the preference driving road section is larger than the target basic weight of the corresponding target basic road section, the preference weight of the preference driving road section is adjusted to be smaller than the target basic weight of the corresponding target basic road section, the adjusted preference weight of the preference driving road section is used for replacing the target basic weight of the corresponding target basic road section in the basic road network, and the basic road network after the weight is updated is obtained.

In this step, when the preference weight is used to update the target basis weight, the preference weight is compared with the target basis weight, if the preference weight is greater than the target basis weight, the preference weight value is required to be reduced in accordance with a rule that a smaller weight value represents a higher user preference degree of the path to be planned, and the adjusted preference weight is used to replace the target basis weight until the preference weight value is determined to be smaller than the target basis weight value.

Here, the preference weight may be adjusted by averaging a plurality of basis weights corresponding to a plurality of basis road segments within a preset range of the preference road segment, and determining an averaged value of the plurality of basis weights as a new preference weight; or after taking the average value, subtracting a preset value from the average value, and determining the value after difference as a new preference weight; the preference weight may be determined based on a difference between the base weight and the preference weight, by subtracting a value greater than the difference.

Further, the planning a travel route of the user of the path to be planned in the target driving area based on the preference weight of each preference driving section and the basis weight of each basis section includes:

(1) and determining a first route between a first transit point of the user to be planned from a travel origin to a sub-road network area where the sub-road network is located and the travel origin and the first transit point, and a second route between a second transit point of the user to be planned from a travel destination to the sub-road network area and the travel destination and the second transit point based on the basic weight of each basic road segment.

In this step, according to a basic weight corresponding to each basic road segment in the basic road network, a first transit point in a region from a trip to the first sub-road network by the user of the path to be planned and a first route between the trip origin and the first transit point are found through a shortest path algorithm, and a second transit point from a trip destination and a second route between the trip destination and the second transit point by the user of the path to be planned are determined.

Here, the determination of the first transit point and the second transit point may be divided into two cases, one case is that the sub-network includes the travel origin and the travel destination, and then the travel origin may be directly determined as the first transit point and the travel destination may be determined as the second transit point; secondly, the sub-road network does not completely contain the travel origin and the travel destination, when the sub-road network does not contain the travel origin, an intersection point of the travel destination and the sub-road network is determined according to a basic weight corresponding to a basic road section of the basic road network and by combining a shortest path algorithm, the intersection point is determined as a first transit point, and a first route between the travel origin and the first transit point is located according to a shortest path determined by the shortest path.

Here, a preferred route may be determined by a shortest path algorithm and a plurality of preference weights corresponding to a plurality of preferred travel links to which the route to be planned is inclined in a road sub-network, and two intersections of the preferred route and a boundary of the road sub-network may be determined as a first transit point and a second transit point, where the first transit point is close to the travel origin and the second transit point is close to the travel destination, and a first route between the travel origin and the first transit point and a second route between the travel destination and the second transit point may be calculated at the same time.

The shortest path algorithm used in calculating the shortest path may be divided into two types, and the path calculation outside the sub-path network region, that is, the first path and the second path calculation may be performed through CH³The algorithm directly calculates, and the calculation of the path in the sub-road network can be through Dijkstra²The algorithm performs the calculation.

(2) And determining the preference route of the user of the path to be planned between the first transfer point and the second transfer point in the sub-road network area based on the preference weight of each preference driving road section.

In this step, after a first transit point and a second transit point of a sub-network are determined, based on a preference weight corresponding to each preferred travel road segment in the sub-network, a preferred route of the user of the path to be planned in the sub-network from the first transit point to the second transit point is determined by combining a shortest path algorithm.

Here, in the process of calculating routes according to the preference weight and the shortest path algorithm, if more than one recommendable route is calculated, the preferred route may be selectively determined according to the road conditions of each recommendable route in the travel time period of the user of the route to be planned, for example, a route with the minimum congestion degree may be recommended.

(3) Determining a travel route in the target travel area including the first route, the second route, and the preferred route.

In this step, one route determined by the first route, the second route and the preference route is determined as a travel route which can be recommended to a user of a path to be planned in the target driving area.

According to the route planning method provided by the embodiment of the application, after a route planning request of a user of a route to be planned is received, travel platform data of the user of the route to be planned is obtained; if the travel platform data indicate that the path user to be planned belongs to a high-frequency user providing travel service, determining that the path user to be planned meets a preset path planning condition, wherein the characteristics of the high-frequency user include one or more of the number of times of providing service being greater than a preset number of times, the number of service orders being greater than a preset number, the online time in a travel platform being greater than a preset time, and the total distance of a travel route being greater than a preset route distance; if the path user to be planned meets the preset path planning condition, acquiring historical driving track data of the path user to be planned in a target driving area and basic road network data of the target driving area in a historical time period; determining a plurality of historical driving road sections driven by the user of the path to be planned and a plurality of basic road sections driven by all users in the target driving area based on the historical driving track data and the basic road network data respectively, and determining a target basic road section corresponding to each historical driving road section in the plurality of basic road sections and the difference degree of each historical driving road section relative to the corresponding target basic road section; determining a plurality of preferred driving road sections which are preferred to be driven by the user for the path to be planned in the plurality of historical driving road sections and a road network constructed by the plurality of preferred driving road sections based on the difference degree of each historical driving road section; and planning the travel route of the user of the path to be planned based on the basic road network and the sub road network of the target driving area.

Referring to fig. 4 and 5, fig. 4 is a first schematic structural diagram of a route planning device according to an embodiment of the present application, and fig. 5 is a second schematic structural diagram of a route planning device according to an embodiment of the present application. As shown in fig. 4, the route planning apparatus 400 includes:

the data obtaining module 410 is configured to obtain historical driving track data of a path user to be planned in a target driving area and basic road network data of the target driving area within a historical time period if the path user to be planned meets a preset path planning condition.

A difference determining module 420, configured to determine, based on the historical driving trajectory data and the basic road network data, a plurality of historical driving road segments traveled by the user of the path to be planned and a plurality of basic road segments traveled by all users in the target driving area, and determine a target basic road segment corresponding to each historical driving road segment in the plurality of basic road segments and a difference between each historical driving road segment and the corresponding target basic road segment.

And a sub-road network constructing module 430, configured to determine, based on the difference degree of each historical driving road segment, a plurality of preferred driving road segments that the user prefers to drive on the path to be planned in the plurality of historical driving road segments, and a sub-road network constructed by the plurality of preferred driving road segments.

And a route planning module 440, configured to plan a travel route of the user with the path to be planned based on the basic road network and the sub-road network of the target driving area.

Further, as shown in fig. 5, the route planning apparatus 400 further includes a user detection module 450, where the user detection module 450 is configured to:

Further, when the difference degree determining module 420 is configured to determine, based on the historical driving track data and the basic road network data, a plurality of historical driving road segments traveled by the user of the path to be planned and a plurality of basic road segments traveled by all users in the target driving area, and determine a target basic road segment corresponding to each historical driving road segment in the plurality of basic road segments, and a difference degree of each historical driving road segment with respect to the corresponding target basic road segment, respectively, the difference degree determining module 420 is configured to:

Further, when the difference degree determining module 420 is configured to determine, based on the historical driving trajectory data, a plurality of historical driving road segments that the user has driven along the path to be planned in the target driving area, and a historical road segment density that each historical driving road segment has driven along, the difference degree determining module 420 is configured to:

Further, when the difference degree determining module 420 is configured to determine the density of the historical road segments traveled by each historical travel road segment based on the number of travels of each historical travel road segment and the total number of travels, the difference degree determining module 420 is configured to:

determining a historical link density for each historical travel link by:

A＝x₁/y₁；

Further, when the difference degree determining module 420 is configured to determine, based on the basic road network data, a plurality of basic road segments traveled by all users in the target travel area, a target basic road segment in the target travel area corresponding to each historical travel road segment, and a target basic road segment density in the target travel area at which a target basic road segment in the plurality of basic road segments corresponding to each historical travel road segment is traveled, the difference degree determining module 420 is configured to:

Further, when the difference degree determining module 420 is configured to determine the density of the base road segments traveled by the target base road segment corresponding to each historical travel road segment based on the number of passes of each target base road segment and the total number of passes, the difference degree determining module 420 is configured to:

B＝x₂/y₂；

Further, when the difference degree determining module 420 is configured to determine the difference degree of each historical driving road segment relative to the corresponding target base road segment based on the historical road segment density and the target base road segment density, the difference degree determining module 420 is configured to:

C＝((A-B)/B)*X+(A-B)*(1-X)；

wherein, C is the difference degree of the historical driving road section relative to the corresponding target basic road section, a is the historical road section density of the historical driving road section, B is the basic road section density of the basic road section corresponding to the historical driving road section, and X is a constant parameter.

Further, when the sub road network constructing module 430 is configured to determine, based on the difference degree of each historical driving road segment, a plurality of preferred driving road segments that the user prefers to drive on the path to be planned to travel among the plurality of historical driving road segments, and a sub road network constructed by the plurality of preferred driving road segments, the sub road network constructing module 430 is configured to:

Further, when the route planning module 440 is configured to plan the travel route of the user for the path to be planned based on the basic road network and the sub-road network of the target driving area, the route planning module 440 is configured to:

Further, when the route planning module 440 is configured to plan the travel route of the user of the path to be planned in the target driving area based on the preference weight of each preference driving segment and the base weight of each base segment, the route planning module 440 is configured to:

Further, when the route planning module 440 is configured to replace the target basic weight of the corresponding target basic road segment in the basic road network with the preference weight of each preferred driving road segment to obtain the updated weight basic road network, the route planning module 440 is configured to:

Further, as shown in fig. 5, the route planning apparatus 400 further includes a model training module 460, and the model training module 460 is configured to train the road segment weight prediction model by:

According to the route planning device provided by the embodiment of the application, if a path user to be planned meets a preset path planning condition, historical driving track data of the path user to be planned in a target driving area and basic road network data of the target driving area in a historical time period are acquired; determining a plurality of historical driving road sections driven by the user of the path to be planned and a plurality of basic road sections driven by all users in the target driving area based on the historical driving track data and the basic road network data respectively, and determining a target basic road section corresponding to each historical driving road section in the plurality of basic road sections and the difference degree of each historical driving road section relative to the corresponding target basic road section; determining a plurality of preferred driving road sections which are preferred to be driven by the user for the path to be planned in the plurality of historical driving road sections and a road network constructed by the plurality of preferred driving road sections based on the difference degree of each historical driving road section; and planning the travel route of the user of the path to be planned based on the basic road network and the sub road network of the target driving area.

Referring to fig. 6, fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 6, the electronic device 600 includes a processor 610, a memory 620, and a bus 630.

The memory 620 stores machine-readable instructions executable by the processor 610, when the electronic device 600 runs, the processor 610 communicates with the memory 620 through the bus 630, and when the machine-readable instructions are executed by the processor 610, the steps of the route planning method in the method embodiments shown in fig. 2 and fig. 3 may be performed.

An embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the route planning method in the method embodiments shown in fig. 2 and fig. 3 may be executed.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present application, and are used for illustrating the technical solutions of the present application, but not limiting the same, and the scope of the present application is not limited thereto, and although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope disclosed in the present application; such modifications, changes or substitutions do not depart from the spirit and scope of the exemplary embodiments of the present application, and are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A route planning method, characterized in that the route planning method comprises:

determining a plurality of historical driving road sections driven by the user of the path to be planned and a plurality of basic road sections driven by all users in the target driving area based on the historical driving track data and the basic road network data respectively, and determining a target basic road section corresponding to each historical driving road section in the plurality of basic road sections and the difference degree of each historical driving road section relative to the corresponding target basic road section; the difference degree is determined based on the historical road section density and the target basic road section density, and the historical road section density represents the proportion of the times of the user of the path to be planned driving on a certain historical driving road section in the statistical time period to the total times of all the historical driving road sections of the path to be planned driving; the target basic road section density represents the proportion of the times of the user of the path to be planned driving through a certain target basic road section in the total times of all the basic road sections driven in the statistical time period;

2. The route planning method according to claim 1, wherein the determining a plurality of historical driving sections traveled by the user for the path to be planned and a plurality of basic sections traveled by all users in the target driving area based on the historical driving track data and the basic road network data, respectively, and determining a target basic section corresponding to each historical driving section among the plurality of basic sections and a difference degree of each historical driving section with respect to the corresponding target basic section comprises:

3. The route planning method according to claim 2, wherein the determining, based on the historical travel track data, a plurality of historical travel sections traveled by the user of the path to be planned in the target travel area and a historical section density for each of the historical travel sections traveled includes:

4. The route planning method according to claim 2, wherein the determining, based on the basic road network data, a plurality of basic road segments traveled by all users in the target travel area, a target basic road segment in the target travel area corresponding to each historical travel road segment, and a target basic road segment density in the target travel area at which a target basic road segment in the plurality of basic road segments corresponding to each historical travel road segment is traveled comprises:

5. The route planning method according to claim 2, wherein determining a degree of difference for each historical travel segment relative to a corresponding target base segment based on the historical segment densities and the target base segment densities comprises:

C＝((A-B)/B)*X+(A-B)*(1-X)；

6. The route planning method according to claim 1, wherein the determining, based on the difference degree of each historical driving section, a plurality of preferred driving sections which are preferred to be driven by the user for the path to be planned in the plurality of historical driving sections, and the sub-road network constructed by the plurality of preferred driving sections comprises:

7. The route planning method according to claim 1, wherein planning the travel route of the user for the path to be planned based on the basic road network and the sub-road network of the target driving area comprises:

8. The route planning method according to claim 7, wherein the planning of the travel route of the user of the path to be planned in the target travel area based on the preference weight of each preference travel section and the base weight of each base section comprises:

9. The route planning method according to claim 7, wherein the planning of the travel route of the user of the path to be planned in the target travel area based on the preference weight of each preference travel section and the base weight of each base section comprises:

10. The route planning method according to claim 7, wherein the road segment weight prediction model is trained by:

11. A route planning apparatus, characterized in that the route planning apparatus comprises:

a difference degree determining module, configured to determine, based on the historical driving trajectory data and the basic road network data, a plurality of historical driving road segments traveled by the user of the path to be planned and a plurality of basic road segments traveled by all users in the target driving area, and determine a target basic road segment corresponding to each historical driving road segment in the plurality of basic road segments and a difference degree of each historical driving road segment with respect to the corresponding target basic road segment; the difference degree is determined based on the historical road section density and the target basic road section density, and the historical road section density represents the proportion of the times of the user of the path to be planned driving on a certain historical driving road section in the statistical time period to the total times of all the historical driving road sections of the path to be planned driving; the target basic road section density represents the proportion of the times of the user of the path to be planned driving through a certain target basic road section in the total times of all the basic road sections driven in the statistical time period;

12. An electronic device, comprising: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating via the bus when the electronic device is operating, the processor executing the machine-readable instructions to perform the steps of the route planning method according to any one of claims 1 to 10.

13. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the route planning method according to any one of claims 1 to 10.