Path selection method and device, equipment and storage medium

Abstract

The invention provides a path selection method and device, equipment and a storage medium, and relates to the technical field of vehicle navigation. The method comprises the following steps: acquiring a plurality of travelable paths between a starting place and a destination and traffic data of the paths; predicting the blockage degree of the drivable path after the preset time period; for each travelable path, determining a path cost value of the travelable path based on the congestion degree; and selecting the drivable path corresponding to the minimum path cost value as a target path. According to the technical scheme, the congestion degree of the travelable path can be predicted in advance according to the traffic data, the loss of the cost value of the path possibly caused by moving towards the travelable path is determined, the path corresponding to the lowest cost value is selected, and when a real-time event occurs in the path, the real-time event of the path is detected. By adopting the technical scheme of the invention, the possible traffic jam path can be predicted in time, the path which is easy to pass is selected, and the jam is avoided.

Description

Technical Field

[0001] The present application relates to the field of vehicle navigation technology, and in particular to a path selection method, device, equipment and storage medium. Background Art

[0002] With the continuous increase in road mileage and the popularization of navigation systems, users are increasingly dependent on real-time route planning. Related technologies can recommend routes to users based on factors such as driving distance and number of traffic lights. However, when faced with real-time events, they often do not react quickly enough and the recommended routes are not accurate enough, which may cause problems such as incorrect route recommendations. Summary of the invention

[0003] In view of this, the present application provides a path selection method, device, equipment and storage medium, the main purpose of which is to be able to promptly detect when congestion occurs on the path to be traveled, and recommend other drivable paths to avoid possible traffic congestion in advance.

[0004] To achieve the above objectives, the present application discloses a path prediction method in a first aspect, comprising:

[0005] Acquire multiple drivable paths between a starting point and a destination, and traffic data of each drivable path within a preset time period;

[0006] For each of the drivable paths, the traffic data is input into a preset congestion prediction model to predict the congestion degree of the drivable path after the preset time period;

[0007] For each of the drivable paths, determining a path cost value of the drivable path based at least on the congestion degree, wherein the path cost value is used to represent a cost that will be incurred if the vehicle selects the drivable path;

[0008] The plurality of path cost values ​​are compared, and a drivable path corresponding to a minimum path cost value is selected as a target path.

[0009] Optionally, the traffic data includes at least one of traffic flow, average vehicle speed and road congestion;

[0010] The congestion prediction model includes at least one of a long short-term memory network model, a gated recurrent unit model, or an autoregressive integrated moving average model.

[0011] Optionally, for each of the drivable paths, the traffic data is input into a preset congestion prediction model to predict the congestion degree of the drivable path after the preset time period, including:

[0012] When an emergency event is acquired, acquiring emergency event data of the emergency event, wherein the emergency event data includes the emergency event type, emergency event location and start time;

[0013] By inputting the emergency data and the traffic data into at least one of a graph convolutional network, a random forest algorithm, or a decision tree regression algorithm, a first impact factor of the emergency data on the traffic data within a preset time period is obtained, and the first impact factor is used to adjust the traffic data;

[0014] updating the traffic data within the preset time period according to the first influencing factor;

[0015] By inputting the updated traffic data into at least one of the long short-term memory network model, the gated recurrent unit model or the autoregressive integrated moving average model, a congestion degree representing the congestion condition of the drivable path after a preset period of time is obtained.

[0016] Optionally, for each of the drivable paths, the traffic data is input into a preset congestion prediction model to predict the congestion degree of the drivable path after the preset time period, including:

[0017] When the emergency event is a meteorological event, obtaining meteorological information of the meteorological event, the meteorological information including meteorological type, duration and precipitation information;

[0018] By inputting the meteorological information and the traffic data into at least one of a distributed gradient boosting library or a gradient boosting decision tree, a second impact factor of the meteorological information on the traffic data within a preset time period is obtained, and the second impact factor is used to adjust the traffic data;

[0019] updating the traffic data within the preset time period according to the second influencing factor;

[0020] By inputting the updated traffic data into at least one of the long short-term memory network model, the gated recurrent unit model or the autoregressive integrated moving average model, a congestion degree representing the congestion condition of the drivable path after a preset period of time is obtained.

[0021] Optionally, for each of the drivable paths, determining a path cost value of the drivable path based at least on the congestion degree includes:

[0022] For each of the drivable paths, determining the time consumption value when passing through the drivable path corresponding to the congestion degree;

[0023] determining the energy consumption value when passing through the drivable path corresponding to the congestion degree;

[0024] The time consumption value and the energy consumption value are weightedly calculated to determine the path cost value.

[0025] Optionally, the determining of a plurality of drivable paths connecting a starting point and a destination and traffic data of the drivable paths includes:

[0026] Determining first location information of a starting point and second location information of the destination at preset time intervals;

[0027] Upon receiving update information of the location information, determining the updated first location information of the starting point;

[0028] Determine a plurality of drivable paths connecting the updated first location information and the second location information, and traffic data of the drivable paths.

[0029] Optionally, the vehicle includes an on-board navigation display screen, and after selecting the drivable path corresponding to the minimum path cost value as the target path, the method further includes:

[0030] Pushing and displaying the target path through the vehicle navigation display screen;

[0031] In response to a confirmation instruction from the user, navigation information of the target path is displayed on the in-vehicle navigation display screen.

[0032] The second aspect of the present application discloses a path selection device, characterized by comprising:

[0033] A determination module, used to determine a plurality of drivable paths connecting a starting point and a destination and traffic data of the drivable paths;

[0034] A first acquisition module, used to obtain a congestion degree indicating a congestion condition of the drivable path after the preset time period by using a change value of the traffic data within the preset time period in the traffic data;

[0035] A second acquisition module is used to acquire a path cost value consumed when passing through the drivable path corresponding to the congestion degree, wherein the path cost value at least includes a time consumption value and an energy consumption value of passing through the drivable path;

[0036] The selection module is used to select a path corresponding to a minimum path cost value from the plurality of drivable paths as a target path based on the size relationship of the plurality of path cost values.

[0037] In a third aspect of the present application, an electronic device is provided, including:

[0038] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method disclosed in the first aspect.

[0039] In a fourth aspect of the present application, an embodiment provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0040] In summary, according to the technical solution disclosed in this application, in order to solve the problem that the relevant technology cannot respond to real-time events in a timely manner, this application discloses a path selection method, which obtains multiple drivable paths between the starting point and the destination, and the traffic data of each drivable path within a preset time period; for each drivable path, the traffic data is input into the preset congestion prediction model to predict the congestion degree of the drivable path after the preset time period; for each drivable path, the path cost value of the drivable path is determined based on the congestion degree, and the path cost value is used to characterize the cost that will be incurred if the vehicle chooses the drivable path; multiple path cost values ​​are compared, and the drivable path corresponding to the minimum path cost value is selected as the target path. The technical solution of this application can predict the congestion degree of the drivable path in advance based on the traffic data within a certain time period, and determine the path cost value loss that may be caused when moving to the drivable path. This application selects the path corresponding to the lowest cost value. When a real-time event occurs on the path, the technical solution of this application can timely predict the path that may be congested, and select a path that is easier to pass through to avoid congestion.

[0041] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0044] Figure 1A flow chart of a path selection method provided by an embodiment of the present application is shown;

[0045] Figure 2 A structural diagram of a path selection device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0046] In order to better understand the technical solutions provided by the embodiments of this specification, the technical solutions of the embodiments of this specification are described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0047] In this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or equipment. In the absence of more restrictions, the elements limited by the statement "comprise one..." do not exclude the existence of other identical elements in the process, method, article or equipment including the elements. The term "more than two" includes two or more than two situations.

[0048] Related technologies can push routes to users based on the current traffic data of each route. However, when users move along the pushed route and the route changes in real time, it is difficult for users to obtain the changes in the route in time and adjust the route in time.

[0049] To solve the above problems, this application proposes a path selection method, such as Figure 1 As shown, it can be executed in the vehicle-mounted system of the vehicle computer, including:

[0050] Step 101, obtaining a plurality of drivable paths between a starting point and a destination, and traffic data of each drivable path within a preset time period.

[0051] Determine the location of the vehicle as the starting point, and determine the destination to be reached by the vehicle. After determining the destination and the starting point, a path planning algorithm can be used to find all possible paths connecting the starting point and the destination, and determine the traffic data of each drivable path. Traffic data may include road length and width, real-time traffic flow, traffic congestion, vehicle speed, etc. Among them, traffic data is collected through a traffic monitoring system, that is, from equipment such as a city traffic monitoring platform and road condition cameras. Crowdsourced data collected by a vehicle-mounted global positioning system (GPS) device or a mobile phone application can also be used. Exemplarily, traffic data can represent at least one of traffic flow, average vehicle speed, and road congestion.

[0052] In some embodiments, when determining multiple drivable paths and traffic data between a starting point and a destination, the vehicle may be in a non-moving state. When the vehicle is in a non-moving state, the drivable paths and traffic data may be used to select a path with less congestion.

[0053] When the vehicle is in motion, as shown in one embodiment, the process includes:

[0054] At preset time intervals, determine the first location information of the starting point and the second location information of the destination; when receiving update information of the first location information, determine the updated first location information of the starting point; determine multiple drivable paths connecting the updated first location information and the second location information, and traffic data of the drivable paths.

[0055] When the vehicle is in motion, the system can continuously obtain the location of the vehicle and the coordinate information of the location. This information is transmitted to the background server of the navigation system in real time through the Internet interface or wireless communication technology (such as 5G, vehicle networking, etc.). During the movement of the vehicle, the system continuously updates the drivable path between the vehicle and the destination, as well as traffic data. During the driving process of the vehicle, there may already be a road connecting the destination and the starting point. During the movement along this road, it may be difficult to continue to pass this road due to factors such as traffic jams and traffic accidents. Therefore, when the vehicle system obtains traffic jam information or accident information, it dynamically updates the user's current location information, and recalculates and optimizes the path suggestions based on the latest traffic data to ensure that users always get the most accurate and efficient navigation service.

[0056] Step 102: for each drivable path, input the traffic data into a preset congestion prediction model to predict the congestion level of the drivable path after a preset period of time.

[0057] After acquiring the traffic data, since the traffic data is updated in real time, the change of the same traffic data within a certain period of time can be determined, thereby serving as the change value of the real-time traffic data, wherein the preset time period can be calculated based on the time required for a vehicle to reach a certain location.

[0058] The congestion degree is used to indicate the congestion of a route in a certain period of time in the future. Common congestion degrees include: congestion index, which calculates a comprehensive congestion index. Congestion probability, which predicts the probability of congestion on a route in a certain period of time in the future. The congestion degree can be used to calculate the degree of congestion that may occur on a road when a vehicle arrives at the road. The greater the congestion degree, the higher the possibility and severity of congestion.

[0059] In some embodiments, the congestion prediction model includes at least one of a long short-term memory network model, a gated recurrent unit model, or an autoregressive integrated moving average model. The long short-term memory network model or the gated recurrent unit model can capture the long-term trend and short-term fluctuations of traffic flow, and predict future traffic flow through the input of multiple time steps. For example, during the morning rush hour on weekdays, the long short-term memory network model predicts the traffic flow of the main road in the next hour based on the historical data of the previous few days and the current real-time data. The autoregressive integrated moving average model is a classic time series prediction method that is suitable for time series data with obvious regularities. For example, urban roads often show relatively stable traffic flow changes between weekdays and weekends, morning and evening rush hours and non-peak hours. Exemplarily, the autoregressive integrated moving average model predicts the traffic density in the next 30 minutes by analyzing the daily traffic flow changes on the main road, and determines the degree of congestion of the path based on the traffic density.

[0060] In some embodiments, for each drivable path, the traffic data is input into a preset congestion prediction model to predict the congestion level of the drivable path after a preset period of time, including:

[0061] When an emergency event is acquired, the emergency event data of the emergency event is acquired, the emergency event data including the emergency event type, the emergency event location and the start time;

[0062] By inputting emergency data and traffic data into at least one of a graph convolutional network, a random forest algorithm, or a decision tree regression algorithm, a first impact factor of the emergency data on the traffic data within a preset time period is obtained, and the first impact factor is used to adjust the traffic data;

[0063] updating the traffic data within a preset time period according to the first influencing factor;

[0064] By inputting updated traffic data into at least one of a long short-term memory network model, a gated recurrent unit model or an autoregressive integrated moving average model, a congestion degree representing a congestion condition of a drivable path after a preset period of time is obtained.

[0065] In this embodiment, when an emergency occurs in a drivable path, the emergency may affect the degree of congestion of the path in the future time period. For example, the emergency may be an emergency such as a traffic accident or road construction. For example, when a traffic accident occurs, the accident vehicle occupies the lane, causing the speed of vehicles passing through the road section to slow down. When the traffic volume is large, it is easy to cause congestion. In this embodiment, when the occurrence of an emergency is received, the impact factor of the event on the surrounding area can be directly determined. Since the paths are interconnected, each path can be regarded as a road grid. When an emergency occurs at a certain point in the grid, the emergency will affect the path where the emergency is located, as well as the traffic data connected to or around the path. The more closely the path is connected to the path where the emergency occurs, the greater the impact it will receive. In this embodiment, when an emergency occurs, the impact degree value of the traffic data of the surrounding paths when the emergency occurs is calculated by at least one algorithm of a graph convolutional network, a random forest algorithm, or a decision tree regression algorithm.

[0066] Graph convolutional networks (GCN) are good at processing graph-structured data such as road networks. Roads can be viewed as nodes in a graph, and the edges between nodes represent connected paths. GCN can effectively model the impact of a traffic event at a certain point in a road network on the surrounding road network. For example, if a traffic accident occurs on a highway, the GCN model will predict the regional traffic congestion that may be caused by the accident and how long it will take for the impact to dissipate by analyzing the connection between the road and adjacent roads.

[0067] Random Forest or decision tree regression is suitable for handling classification and regression problems. It can predict the specific impact and duration of surrounding traffic flow based on different emergencies (such as accidents, road closures, construction) and their severity. For example, if a road section is closed due to construction, the random forest algorithm can analyze historical similar event data to evaluate the specific impact of the road closure on the surrounding road network and predict the increase in surrounding traffic flow during the closure period.

[0068] For a certain drivable path, traffic data is processed through at least one of a long short-term memory network model, a gated recurrent unit model, or an autoregressive integrated moving average model, and a prediction result of the congestion degree of the drivable path in the future period of time can be obtained. When an emergency occurs on the drivable path, the event affects the prediction of the congestion degree. In order to determine the specific impact value of the emergency, in this embodiment, at least one of a graph convolutional network, a random forest algorithm, or a decision tree regression algorithm is used to determine a first influencing factor for updating traffic data, and the traffic data is updated based on the first influencing factor. After the traffic data is updated, the updated traffic data is input into the long short-term memory network model, the gated recurrent unit model, or the autoregressive integrated moving average model again to realize the prediction of the future congestion degree.

[0069] By adopting the technical solution of this embodiment, it is possible to respond promptly to the occurrence of emergencies and adjust the prediction method of the degree of congestion in a timely manner to ensure the reliability of the parameters input into the long short-term memory network model, the gated recurrent unit model or the autoregressive integrated moving average model.

[0070] In some embodiments, for each drivable path, the traffic data is input into a preset congestion prediction model to predict the congestion level of the drivable path after a preset period of time, including:

[0071] When the emergency event is a meteorological event, obtain meteorological information of the meteorological event, which includes meteorological type, duration and precipitation information;

[0072] By inputting meteorological information and traffic data into at least one of a distributed gradient boosting library or a gradient boosting decision tree, a second impact factor of meteorological information on traffic data within a preset time period is obtained, and the second impact factor is used to adjust the traffic data;

[0073] updating the traffic data within a preset time period according to the second influencing factor;

[0074] By inputting updated traffic data into at least one of a long short-term memory network model, a gated recurrent unit model or an autoregressive integrated moving average model, a congestion degree representing a congestion condition of a drivable path after a preset period of time is obtained.

[0075] In this embodiment, the update of traffic data is not only related to emergencies on the road, but also to the weather. In abnormal weather, such as rain, snow or fog, the number and speed of vehicles on the road are different from those on sunny days, which causes changes in traffic data. At the same time, if the weather type is precipitation, water may accumulate on the road, which further affects the traffic data.

[0076] In this embodiment, in order to determine the impact of meteorological events on traffic data, this embodiment obtains meteorological information of meteorological events, and the meteorological information may at least include meteorological type, duration and precipitation information. This embodiment provides a trained tree model algorithm, such as a distributed gradient boosting library or a decision tree based on gradient boosting, which can analyze the impact of different weather, festivals, and time on the degree of congestion through historical traffic data. By inputting meteorological information and traffic data into at least one of the distributed gradient boosting library or the decision tree based on gradient boosting, the second influencing factor is obtained, and the second influencing factor is updated on the traffic data. After the traffic data is updated, the updated traffic data is input again into the long short-term memory network model, the gated recurrent unit model or the autoregressive integral moving average model to predict the future degree of congestion.

[0077] In some embodiments, when an emergency includes both a traffic accident and a meteorological event, the first influencing factor of the traffic data can be obtained through at least one of a graph convolutional network, a random forest algorithm, or a decision tree regression algorithm, and the second influencing factor can be obtained through a distributed gradient boosting library or a gradient boosting decision tree. In this embodiment, the first influencing factor and the second influencing factor obtained by different models can be integrated, and a weighted average or voting mechanism can be used to determine the final prediction of the congestion degree.

[0078] Step 103 : for each drivable path, determine a path cost value of the drivable path based on the congestion level. The path cost value is used to represent the cost that will be incurred if the vehicle selects the drivable path.

[0079] The path cost value is used to evaluate the quality of the path. After determining the degree of congestion, the path cost value can be calculated according to the weight value corresponding to the degree of congestion. In some embodiments, other factors may also be considered, such as the length of the path, the number of traffic lights, the speed limit of the road, etc. Each factor can be assigned a weight.

[0080] In some embodiments, the path cost value may be calculated by:

[0081] For each drivable path, determine the time consumption value when passing through the drivable path corresponding to the congestion degree; determine the energy consumption value when passing through the drivable path corresponding to the congestion degree; weightedly calculate the time consumption value and the energy consumption value to determine the path cost value.

[0082] The time consumption value indicates the time required to pass a certain path, which is usually affected by the length of the path and the degree of congestion. The energy consumption value indicates the energy required to pass a certain path, which is usually affected by the type of vehicle, the length of the path and the degree of congestion. The path cost value is used to evaluate the quality of the path, usually taking into account the time consumption value and the energy consumption value, and assigning different weights. According to the time consumption value and the energy consumption value and the corresponding weight values, the weight and value are calculated, and the final result is used as the path cost value. This embodiment can be implemented when multiple drivable paths are included, and the cost of passing each path is judged by the path cost value. The path cost value can be used as an important indicator for selecting a path.

[0083] Step 104 , compare multiple path cost values, and select the drivable path corresponding to the minimum path cost value as the target path.

[0084] When determining the cost of each path, the path cost value is used as a reference indicator, and the path with the lowest cost when passing through is selected as the target path. The cost paid can be time cost, distance cost or danger possibility, etc.

[0085] By adopting the path selection method of this embodiment, the route can be adjusted dynamically when an emergency (such as an accident, congestion, weather change, etc.) occurs on the current driving route or the congestion level of the future route is high. When adjusting, priority is given to areas with low congestion levels, and combined with the forward-looking information generated by the congestion prediction model, unobstructed or low-risk paths are selected to avoid congested paths, thereby improving user experience.

[0086] In some embodiments, the vehicle includes an onboard navigation display screen, and after selecting the drivable path corresponding to the minimum path cost value as the target path, the method further includes:

[0087] Push and display the target path through the vehicle navigation display screen;

[0088] In response to the user's confirmation instruction, navigation information of the target path is displayed on the in-vehicle navigation display screen.

[0089] After the target path is determined by the minimum path cost, the target path is pushed to the driver through the vehicle display screen, specifically, through a pop-up window or voice, etc. The driver can choose whether to view or use the target path.

[0090] The user can issue a confirmation command through the touch screen, voice command or other means to confirm viewing or using the target path. Once the user confirms, the in-vehicle navigation system will display detailed navigation information on the display screen, including but not limited to: real-time map, turn instructions, distance prompts, estimated arrival time or road condition information, etc. This embodiment can realize the execution of the target path replacement and display logic according to the user's confirmation command when the path change can be executed, thereby improving the user's experience.

[0091] This application proposes a path selection device, such as Figure 2 As shown, including:

[0092] An acquisition module 21 is used to acquire a plurality of drivable paths between a starting point and a destination, and traffic data of each of the drivable paths within a preset time period;

[0093] A prediction module 22, for inputting the traffic data into a preset congestion prediction model for each of the drivable paths, and predicting the congestion degree of the drivable paths after the preset time period;

[0094] A determination module 23, configured to determine, for each of the drivable paths, a path cost value of the drivable path based on the congestion level, wherein the path cost value is used to represent the cost that will be incurred if the vehicle selects the drivable path;

[0095] The selection module 24 is used to compare the multiple path cost values ​​and select a drivable path corresponding to a minimum path cost value as a target path.

[0096] Optionally, the traffic data includes at least one of traffic flow, average vehicle speed and road congestion;

[0097] The congestion prediction model includes at least one of a long short-term memory network model, a gated recurrent unit model, or an autoregressive integrated moving average model.

[0098] Optionally, the prediction module 22 is used to:

[0099] When an emergency event is acquired, acquiring emergency event data of the emergency event, wherein the emergency event data includes the emergency event type, emergency event location and start time;

[0100] By inputting the emergency data and the traffic data into at least one of a graph convolutional network, a random forest algorithm, or a decision tree regression algorithm, a first impact factor of the emergency data on the traffic data within a preset time period is obtained, and the first impact factor is used to adjust the traffic data;

[0101] updating the traffic data within the preset time period according to the first influencing factor;

[0102] By inputting the updated traffic data into at least one of the long short-term memory network model, the gated recurrent unit model or the autoregressive integrated moving average model, a congestion degree representing the congestion condition of the drivable path after a preset period of time is obtained.

[0103] Optionally, the prediction module 22 is used to:

[0104] When the emergency event is a meteorological event, obtaining meteorological information of the meteorological event, the meteorological information including meteorological type, duration and precipitation information;

[0105] By inputting the meteorological information and the traffic data into at least one of a distributed gradient boosting library or a gradient boosting decision tree, a second impact factor of the meteorological information on the traffic data within a preset time period is obtained, and the second impact factor is used to adjust the traffic data;

[0106] updating the traffic data within the preset time period according to the second influencing factor;

[0107] By inputting the updated traffic data into at least one of the long short-term memory network model, the gated recurrent unit model or the autoregressive integrated moving average model, a congestion degree representing the congestion condition of the drivable path after a preset period of time is obtained.

[0108] Optionally, the determination module 23 is used to:

[0109] For each of the drivable paths, determining the time consumption value when passing through the drivable path corresponding to the congestion degree;

[0110] determining the energy consumption value when passing through the drivable path corresponding to the congestion degree;

[0111] The time consumption value and the energy consumption value are weightedly calculated to determine the path cost value.

[0112] Optionally, the acquisition module 21 is used to:

[0113] Determining first location information of a starting point and second location information of the destination at preset time intervals;

[0114] Upon receiving update information of the location information, determining the updated first location information of the starting point;

[0115] Determine a plurality of drivable paths connecting the updated first location information and the second location information, and traffic data of the drivable paths.

[0116] Optionally, the path selection device further includes a display module 25, which is used to:

[0117] Pushing and displaying the target path through the vehicle navigation display screen;

[0118] In response to a confirmation instruction from the user, navigation information of the target path is displayed on the in-vehicle navigation display screen.

[0119] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0120] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-readable program code.

[0121] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0122] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0123] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0124] An embodiment of the present application further provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device executes the process of the path selection method.

[0125] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.

[0126] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0127] In the several embodiments provided in the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0128] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0129] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0130] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0131] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

[0132] Although preferred embodiments of the present specification have been described, additional changes and modifications may be made to these embodiments by those skilled in the art once the basic inventive concepts are known. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present specification. Obviously, those skilled in the art may make various changes and modifications to the present specification without departing from the spirit and scope of the present specification. Thus, if these modifications and variations of the present specification fall within the scope of the claims of the present specification and their equivalents, the present specification is also intended to include these modifications and variations.

Claims

1. A path selection method, characterized in that: include: Acquire multiple drivable paths between a starting point and a destination, and traffic data of each drivable path within a preset time period; For each of the drivable paths, the traffic data is input into a preset congestion prediction model to predict the congestion degree of the drivable path after the preset time period; For each of the drivable paths, determining a path cost value of the drivable path based on the congestion degree, wherein the path cost value is used to represent the cost that will be incurred if the vehicle selects the drivable path; The plurality of path cost values ​​are compared, and a drivable path corresponding to a minimum path cost value is selected as a target path.

2. The method according to claim 1, characterized in that The traffic data includes at least one of traffic flow, average vehicle speed and road congestion; The congestion prediction model includes at least one of a long short-term memory network model, a gated recurrent unit model, or an autoregressive integrated moving average model.

3. The method according to claim 2, characterized in that For each of the drivable paths, inputting the traffic data into a preset congestion prediction model to predict the congestion degree of the drivable path after the preset time period includes: When an emergency event is acquired, acquiring emergency event data of the emergency event, wherein the emergency event data includes the emergency event type, emergency event location and start time; By inputting the emergency data and the traffic data into at least one of a graph convolutional network, a random forest algorithm, or a decision tree regression algorithm, a first impact factor of the emergency data on the traffic data within a preset time period is obtained, and the first impact factor is used to adjust the traffic data; updating the traffic data within the preset time period according to the first influencing factor; By inputting the updated traffic data into at least one of the long short-term memory network model, the gated recurrent unit model or the autoregressive integrated moving average model, a congestion degree representing the congestion condition of the drivable path after a preset period of time is obtained.

4. The method according to claim 3, characterized in that For each of the drivable paths, inputting the traffic data into a preset congestion prediction model to predict the congestion degree of the drivable path after the preset time period includes: When the emergency event is a meteorological event, obtaining meteorological information of the meteorological event, wherein the meteorological information includes meteorological type, duration and precipitation information; By inputting the meteorological information and the traffic data into at least one of a distributed gradient boosting library or a gradient boosting decision tree, a second impact factor of the meteorological information on the traffic data within a preset time period is obtained, and the second impact factor is used to adjust the traffic data; updating the traffic data within the preset time period according to the second influencing factor; By inputting the updated traffic data into at least one of the long short-term memory network model, the gated recurrent unit model or the autoregressive integrated moving average model, a congestion degree representing the congestion condition of the drivable path after a preset period of time is obtained.

5. The method according to claim 1, characterized in that The step of determining, for each of the drivable paths, a path cost value of the drivable path based at least on the congestion degree, comprises: For each of the drivable paths, determining the time consumption value when passing through the drivable path corresponding to the congestion degree; determining the energy consumption value when passing through the drivable path corresponding to the congestion degree; The time consumption value and the energy consumption value are weightedly calculated to determine the path cost value.

6. The method according to claim 1, characterized in that The obtaining of a plurality of drivable paths between a starting point and a destination, and traffic data of each drivable path within a preset time period, includes: Determining first location information of the starting point and second location information of the destination at preset time intervals; Upon receiving update information of the first location information, determining the updated first location information of the starting point; Determine a plurality of drivable paths connecting the updated first location information and the second location information, and traffic data of the drivable paths.

7. The method according to claim 1, characterized in that The vehicle includes an on-board navigation display screen, and after selecting the drivable path corresponding to the minimum path cost value as the target path, the method further includes: Pushing and displaying the target path through the vehicle navigation display screen; In response to a confirmation instruction from the user, navigation information of the target path is displayed on the in-vehicle navigation display screen.

8. A path selection device, characterized in that: include: An acquisition module, used to acquire a plurality of drivable paths between a starting point and a destination, and traffic data of each of the drivable paths within a preset time period; A prediction module, for inputting the traffic data into a preset congestion prediction model for each of the drivable paths, and predicting the congestion degree of the drivable paths after the preset time period; a determination module, configured to determine, for each of the drivable paths, a path cost value of the drivable path based on the congestion level, wherein the path cost value is used to represent a cost that will be incurred if the vehicle selects the drivable path; The selection module is used to compare the multiple path cost values ​​and select the drivable path corresponding to the minimum path cost value as the target path.

9. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images