A navigation algorithm method and apparatus

Abstract

The application provides a navigation route calculation method and device, and a computer readable storage medium. The method comprises the following steps: determining a plurality of candidate road segments according to a starting location and a target location; determining a starting time when a user arrives at the starting location; obtaining first congestion state data of each candidate road segment at a current time; predicting second congestion state data of each candidate road segment at the starting time according to each first congestion state data and the starting time; and selecting at least one recommended road segment from each candidate road segment according to the second congestion state data of each candidate road segment at the starting time. By executing these steps, the navigation route calculation method can predict the traffic conditions of each candidate road segment at a future time to recommend a navigation route, thereby more accurately estimating the navigation time and recommending a actually faster navigation route for the navigation user, so as to save travel time and improve the user experience.

Description

TECHNICAL FIELD

[0001] The present application relates to navigation technology, and in particular, to a navigation routing method, a navigation routing device, and a computer readable storage medium. BACKGROUND

[0002] With the continuous expansion of the city size, and the continuous enrichment and perfection of the city road network and the highway network between cities, navigation technology has become an indispensable key technology for people's travel. Especially the vehicle navigation technology based on the navigation routing algorithm has become an essential tool for the majority of driver users in daily commuting, business travel and other travel scenarios.

[0003] The current navigation routing algorithm only recommends a navigation route according to the current real-time road state, without considering the actual situation that the congestion position will change over time. However, the future change of the city road congestion timing actually has a very great influence on the recommended navigation route and the estimated navigation time, which will significantly affect the travel time of the navigation user. For example, when a road section A of a city expressway is congested at 8 o'clock, and the navigation user still has 30 minutes of travel to the road section A, the current navigation routing algorithm will abandon this route because the current travel time of the road section A is too long, and recommend the navigation user to other relatively unobstructed city ordinary roads. However, the actual road situation is that the congestion position will migrate to different road sections of the city expressway over time, and the congestion position has actually migrated to the next road section B which does not affect the routing at 8:30. Therefore, the routing scheme of recommending other city ordinary roads will seriously affect the routing quality and actually prolong the travel time of the navigation user.

[0004] In order to overcome the above-mentioned defects existing in the prior art, the technical field urgently needs a navigation routing technology, which predicts the traffic conditions of each candidate road section at a future time to recommend a navigation route, so as to more accurately estimate the navigation time and recommend a navigation route that is actually faster for the navigation user, so as to save travel time and improve user experience. SUMMARY

[0005] The following presents a simplified summary of one or more aspects in order to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated aspects, and is intended to neither identify key or critical elements of all aspects nor delineate the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that is presented later.

[0006] In order to overcome the above-mentioned defects existing in the prior art, the present application provides a navigation routing method, a navigation routing device, and a computer readable storage medium.

[0007] In particular, the navigation routing method according to the first aspect of the present application comprises the following steps: determining a plurality of candidate road segments according to a departure location and a target location; determining a departure time at which a user arrives at the departure location; obtaining first congestion state data of each of the candidate road segments at a current time; predicting second congestion state data of each of the candidate road segments at the departure time according to the first congestion state data of each of the candidate road segments and the departure time; and selecting at least one recommended road segment from each of the candidate road segments according to the second congestion state data of each of the candidate road segments at the departure time. By performing these steps, the navigation routing method can predict the traffic conditions of each candidate road segment at a future time to recommend a navigation route, thereby more accurately estimating a navigation time and recommending a navigation route that is actually faster for a navigation user to save travel time and improve user experience.

[0008] The navigation routing device according to the second aspect of the present application comprises a memory and a processor. The processor is connected to the memory and is configured to implement the navigation routing method according to the first aspect of the present application. By implementing the navigation routing method, the navigation routing device can predict the traffic conditions of each candidate road segment at a future time to recommend a navigation route, thereby more accurately estimating a navigation time and recommending a navigation route that is actually faster for a navigation user to save travel time and improve user experience.

[0009] The computer readable storage medium according to the third aspect of the present application has computer instructions stored thereon. The computer instructions are executed by a processor to implement the navigation routing method according to the first aspect of the present application. By implementing the navigation routing method, the computer readable storage medium can predict the traffic conditions of each candidate road segment at a future time to recommend a navigation route, thereby more accurately estimating a navigation time and recommending a navigation route that is actually faster for a navigation user to save travel time and improve user experience. BRIEF DESCRIPTION OF DRAWINGS

[0010] The above features and advantages of the present application will be better understood through the following detailed description of the embodiments of the present application in conjunction with the attached drawings. In the drawings, components are not necessarily drawn to scale and components of similar or identical function or components that are alike or similar are designated by the same or similar reference numerals.

[0011] Figure 1 A flowchart of a navigation routing method according to some embodiments of the present application is shown.

[0012] Figure 2 A schematic diagram of a plurality of candidate road segments according to some embodiments of the present application is shown.

[0013] Figure 3A schematic diagram showing a plurality of candidate segments provided according to some embodiments of the present application.

[0014] Figure 4 A flowchart showing a process of constructing a similarity model provided according to some embodiments of the present application.

[0015] Figure 5A A schematic diagram showing a change of traffic flow over time and space provided according to some embodiments of the present application.

[0016] Figure 5B A schematic diagram showing a projection of traffic flow in a space-time diagram provided according to some embodiments of the present application. DETAILED DESCRIPTION

[0017] Objects and advantages of the application will be set forth in part in the description which follows, and in part will be obvious from the description or can be learned by practice of the application. The application will be described with reference to the accompanying drawings, wherein the

[0018] In the description of the present application, it is necessary to point out that, unless otherwise explicitly specified and limited, the terms "mounting", "connection", "linking" should be understood in a broad sense, for example, can be fixed connection, can also be detachable connection, or integrally connected; can be mechanical connection, can also be electrical connection; can be directly connected, can also be indirectly connected through intermediate medium, can be internal communication of two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0019] In addition, "up", "down", "left", "right", "top", "bottom", "horizontal", "vertical" used in the following description should be understood as the orientation shown in the section and the related drawings. The relative terms are only used for the convenience of description, and they do not mean that the devices described should be manufactured or operated in a specific orientation, so they should not be understood as a limitation of the present application.

[0020] It is to be understood that, although terms such as "first", "second", "third", etc. can be used herein to describe various components, regions, layers and / or sections, these components, regions, layers and / or sections should not be limited by these terms, and these terms are merely used to distinguish different components, regions, layers and / or sections. Therefore, the first components, regions, layers and / or sections discussed below can be referred to as the second components, regions, layers and / or sections without departing from some embodiments of the present application.

[0021] As described above, the current navigation routing algorithm only recommends a navigation route according to the current real-time road status, without considering the actual situation that the congestion position will change over time. However, the future change of the urban road congestion timing actually has a very great influence on the recommended navigation route and the estimated navigation time, which will seriously affect the routing quality and actually prolong the travel time of the navigation user.

[0022] In order to overcome the above-mentioned defects existing in the prior art, the present application provides a navigation routing method, a navigation routing device, and a computer readable storage medium, which can predict the traffic conditions of each candidate road segment at future time to recommend a navigation route, so as to more accurately estimate the navigation time and recommend a actually faster navigation route for the navigation user, so as to save travel time and improve user experience.

[0023] In some non-limiting embodiments, the above-mentioned navigation routing method provided by the first aspect of the present application can be implemented by the above-mentioned navigation routing device provided by the second aspect of the present application. Specifically, the navigation routing device includes but is not limited to an electronic device such as a car machine system or a mobile phone for performing a navigation routing task, which is configured with a memory and a processor. The memory includes but is not limited to the above-mentioned computer readable storage medium provided by the third aspect of the present application, which is stored with computer instructions. The processor is connected to the memory and is configured to execute the computer instructions stored on the memory to implement the above-mentioned navigation routing method provided by the first aspect of the present application.

[0024] The working principle of the above-mentioned navigation routing device will be described below in combination with some embodiments of the navigation routing method. Those skilled in the art can understand that the embodiments of the navigation routing method are only some non-limiting embodiments provided by the present application, which are intended to clearly demonstrate the main concept of the present application and provide some specific schemes for facilitating the public to implement, rather than for limiting the entire function or the entire working mode of the navigation routing device. Similarly, the navigation routing device is also only a non-limiting embodiment provided by the present application, which does not limit the execution subject of each step in these navigation routing methods.

[0025] Please refer to Figure 1 and Figure 2 . Figure 1A flowchart of a navigation routing method according to some embodiments of the present application is shown. Figure 2 A schematic diagram of a plurality of candidate route segments according to some embodiments of the present application is shown.

[0026] As shown in Figure 1 and Figure 2 , in some embodiments of the present application, a navigation routing device can first acquire a current location 11 of a user and a target location 20 of a navigation task from a local device running a navigation routing method or a remote device communicatively connected to the local device. Then, the navigation routing device can take the current location 11 of the user as a departure location of a first recommended route segment, and determine a plurality of candidate route segments according to the departure location 11 and the target location 20.

[0027] In some embodiments, since the departure location 11 coincides with the current location of the user, the navigation routing device can take a current time t0 as a departure time t1 of the user arriving at the departure location 11 according to a navigation instruction of “immediate departure”, and acquire first congestion state data S i0 of each candidate route segment i at the current time t0 as second congestion state data S i1 of the departure time t1. The first congestion state data S i0 is a multi-dimensional vector data composed of current time information t0 indicating the current time, and route identification information I i indicating each candidate route segment i, road type information T i indicating a road type of each candidate route segment i, relevant road information R i indicating road bottleneck situations such as on-ramps, off-ramps, road construction locations, etc. in each candidate route segment i, traffic flow information N i0 indicating a number of vehicles in each candidate route segment i, congestion state information V i0 indicating an average vehicle speed in each candidate route segment i, congestion state change information ΔV i0 indicating a vehicle speed change situation in each candidate route segment i, and / or congestion location information L i0 indicating a congestion location in each candidate route segment i, i.e., S i0 = (t0, I i , T i , R i , N i0 , V i0 , ΔV i0 , L i0). Here, the road type of each candidate route section i includes not only various open-type ordinary route sections, but also closed-type route sections such as expressways, elevated roads, underground tunnels, and freeways formed by at least one on-ramp and at least one off-ramp. In particular, in the congestion prediction application of closed-type route sections such as expressways, elevated roads, underground tunnels, and freeways, since there are fewer intersection interference factors such as on-ramps and off-ramps in the route sections, the application can more accurately predict the congestion state of these route sections at the future time.

[0028] In some embodiments, the navigation route planning device can utilize a pre-trained Artificial Intelligence (AI) recommendation model to determine at least one recommended route section with the highest travel efficiency from each candidate route section i according to the second congestion state data S i1 Calculate the travel time Δt i1 of the user through each candidate route section i, and then combine the mileage of each candidate route section i and the remaining distance from the endpoint of each candidate route section i to the target location 20 to comprehensively select at least one recommended route section with the highest travel efficiency from each candidate route section i. It can be understood that the method of training the AI recommendation model to extract feature data from a large number of training samples and output a selection result according to the feature data is prior art in the field, and will not be described here. By comprehensively considering the road section identifier information I i1 , the road type information T i , the related road information R i , the traffic volume information N i , the congestion state information V i1 , the congestion state change information ΔV i1 of the vehicle speed change, and / or the congestion location information L i1 of each candidate route section i in the second congestion state data S i1 , the AI recommendation model used in the application can more accurately predict the travel efficiency of each candidate route section, thereby automatically recommending the optimal candidate route section for the user.

[0029] In the embodiment shown in Figure 2 , the navigation route planning device can select the candidate route section 31 leading to the passing location 12 as the first recommended route section according to the second congestion state data S i1 of each candidate route section i at the departure time t1. Then, the navigation route planning device can determine whether the endpoint 12 of the first recommended route section 31 is at the target location 20 as shown in Figure 1 . In response to the determination result that the endpoint 12 of the first recommended route section 31 is not at the target location 20, the navigation route planning device can further determine the next recommended route section by taking the endpoint 12 of the first recommended route section 31 as a new departure location.

[0030] Please refer to Figure 1 and Figure 3 .Figure 3 A schematic diagram showing a plurality of candidate route segments provided according to some embodiments of the present application is shown.

[0031] As shown in Figure 1 and Figure 3 , in some embodiments of the present application, in response to the determination that the end point 12 of the first recommended route segment 31 is not the target location 20, the navigation route calculating device can take the end point 12 as a new departure location, and re-determine a plurality of candidate route segments according to the new departure location 12 and the target location 20. In addition, the navigation route calculating device can also determine a departure time t2 = t0 + Δt1 at which the user arrives at the departure location 12 according to the current time t0 and the estimated travel time Δt1 of the user through the first recommended route segment 31.

[0032] Subsequently, the navigation route calculating device can obtain the current time information indicating the current time t0, and the route segment identification information I i indicating each re-determined candidate route segment i, the road type information T i indicating the road type of each re-determined candidate route segment i, the relevant road information R i indicating the road bottleneck situation such as on-ramps, off-ramps, road construction locations, etc. in each re-determined candidate route segment i, the traffic volume information N i0 indicating the number of vehicles in each re-determined candidate route segment i, the congestion state information V i0 indicating the average vehicle speed in each re-determined candidate route segment i, the congestion state change information ΔV i0 indicating the vehicle speed change situation in each re-determined candidate route segment i, and / or the congestion location information L i0 indicating the congestion location in each re-determined candidate route segment i, and construct a plurality of multi-dimensional vector data S i0 = (t0, I i , T i , R i , N i0 , V i0 , ΔV i0 , L i0 ) according to these data respectively, as the first congestion state data S i0 = (t0, I i , T i , R i , N i0 , V i0 , ΔV i0 , L i0 ) of each re-determined candidate route segment i at the current time t0.

[0033] Specifically, in some embodiments, the navigation routing device can first obtain the traffic volume information V i0 of each candidate route segment i from the ground inductance coils arranged at each candidate route segment i. Further, in some preferred embodiments, the navigation routing device can also obtain the base station signaling data of the vehicle SIM card from the telecom operators as a supplement to the ground inductance coil data, so as to optimize the recommendation function of the candidate route segment by improving the accuracy of the traffic volume information V i0 . Furthermore, the navigation routing device can also clean and denoise the obtained base station signaling data according to the common data features of the vehicle SIM card, such as the overall moving speed being greater than the walking speed and the single moving distance being greater than the preset distance threshold, to remove the abnormal base station switching data and roadside pedestrian interference data, so as to further improve the accuracy of the traffic volume information V i0 and further optimize the recommendation function of the candidate route segment.

[0034] As shown in Figure 1 , after obtaining the first congestion state data S i0 of each candidate route segment i at the current time t0, the navigation routing device will predict the second congestion state data S i0 of each candidate route segment i at the departure time t2 according to the first congestion state data S i2 of each candidate route segment i and the departure time t1 of the user arriving at the departure location 12.

[0035] In some embodiments, the navigation routing device can use a pre-constructed similarity model to predict the second congestion state data S i2 of each candidate route segment i at the departure time t2. The construction process of the similarity model can refer to Figure 4 .

[0036] As shown in Figure 4 , in the construction process of the similarity model, the constructor can first obtain a plurality of congestion state historical data S j of a plurality of route segment samples i at a plurality of times t ij from various channels such as the Internet of Vehicles cloud platform. The congestion state historical data S ij is a multi-dimensional vector data, which can include at least one dimension of the time information t j , the route segment identification information I i , the road type information T i , the related road information R i , the traffic volume information N ij , the congestion state information V ij , the congestion state change information ΔV ij and the congestion position information L ij corresponding to the above-mentioned first congestion state data S0. Then, the constructor can predict the second congestion state data S i2 of each candidate route segment i at the departure time t2 according to the congestion state historical data S j of the same route segment sample i at a plurality of times t ij .j Historical data of multiple congestion states S ij By training and learning parameters, the historical congestion data S of sample i in each road segment is determined. ij The trend of change over time, and based on historical data of each congestion state. ij The above-mentioned similar models are constructed based on their changing trends over time.

[0037] Those skilled in the art will understand that the term "builder" is merely a non-limiting description and includes, but is not limited to, technicians implementing the aforementioned build process and processors executing the relevant build instructions. In other words, the build process of the aforementioned similar models can be implemented by technicians based on a large amount of historical congestion data S. ij This can be done manually, or it can be handled by a processor based on a large amount of historical congestion data. ij This can be achieved automatically, or through a combination of human intervention and processor interaction.

[0038] Subsequently, in the second congestion state data S i2 During the prediction process, the navigation routing device can obtain the first congestion status data S of each candidate road segment i at the current time t0. i0 The data is input into the aforementioned similarity model, which performs similarity analysis to determine the congestion situation and the first congestion state data S. i0 Similar congestion historical data S ij Then, the similarity model will be based on historical congestion data S of similar conditions. ij Based on the time-varying trend ΔS and the time difference Δt1 between departure time t2 and current time t0, predict the second congestion state data S of the corresponding candidate road segment i at departure time t2. i2 .

[0039] In some embodiments, the similar model can calculate the first congestion state data S of candidate road segment i respectively. i0 Historical data of various congestion states S ij Euclidean distance D 0j ,Right now And the Euclidean distance D 0j The data S is identified as the first congestion status. i0 Compared with the corresponding historical congestion data S ij The similarity is then calculated. Afterwards, the similarity model can be based on the calculated similarity D. 0j In this model, the data S corresponding to the first congestion state is determined. i0 Similar congestion historical data S ij .

[0040] Specifically, the similarity model can first be based on a preset similarity threshold D. th Determine whether there exists data S in this model that corresponds to the first congestion state. i0 Similar congestion historical data S ij If there are any one or more historical congestion data S in this model. ij , and the first congestion status data S i0 Similarity D 0j Greater than or equal to the preset similarity threshold D th Then, the similarity model can determine that there exists data S in this model that is similar to the first congestion state. i0 Similar congestion historical data S ij And select the historical congestion data S with the highest similarity. ij_max It was determined to be related to the first congestion state data S i0 Similar historical congestion data. Conversely, if the historical congestion data S in this model... ij With the first congestion status data S i0 Similarity D 0j All are less than the preset similarity threshold D th Then, the similarity model can determine that there is no data S in this model that is similar to the first congestion state. i0 Similar congestion historical data S ij .

[0041] In some embodiments of the present invention, in response to the absence of first congestion state data S with candidate road segment i in the similarity model... i0 Similar congestion historical data S ij Based on the judgment result, the navigation route calculation device can obtain the average vehicle speed V of the road segment m ahead of the candidate road segment i. m0 Wait for the current congestion status data S m0 Based on Koener's three-phase theory and the aforementioned time difference Δt1, the first congestion state data S of candidate road segment i is analyzed. i0 And the current congestion status data S of the road segment m ahead. m0 To predict the second congestion status data S of candidate road segment i at departure time t2. i2 .

[0042] Specifically, the Kerner three-phase theory defines the wide moving jam (J) and synchronized flow (S) in congested traffic flow according to the space-time characteristics of actual traffic flow as follows: (1) Definition of the wide moving jam (J): When a wide moving jam (J) passes through a highway bottleneck, the average propagation speed of the downstream front of the wide moving jam (J) to the upstream remains unchanged. Vehicles accelerate through the downstream front of the wide moving jam (J) to drive away from the wide moving jam (J) and enter the free flow (F) or synchronized flow (S) state. (2) Definition of the synchronized flow (S): At the downstream front of the synchronized flow (S), vehicles accelerate to enter the free flow (F) state. The downstream front of the synchronized flow (S) no longer exhibits the characteristics of the downstream front of the wide moving jam (J), and the propagation speed of the downstream front of the synchronized flow (S) is not a constant, and the downstream front of the synchronized flow (S) is usually fixed at the bottleneck.

[0043] Reference is made to Figure 5A and Figure 5B . Figure 5A Fig. 1 shows a schematic diagram of the change of traffic flow over time and space according to some embodiments of the present application. Figure 5B Fig. 2 shows a schematic diagram of the projection of traffic flow in a space-time diagram according to some embodiments of the present application.

[0044] As shown in Figure 5A and Figure 5B , the navigation route calculation device can measure and analyze the current congestion state data S m0 of the front road section m of the candidate road section i, and automatically identify the wide moving jam (J) and the synchronized flow (S) in the congested traffic flow according to the above definitions. For example, as shown in Figure 5A and Figure 5B , the downstream front of the traffic flow propagates to the upstream at a nearly constant speed and can pass through the bottleneck, so the navigation route calculation device can determine this traffic flow as the wide moving jam (J) according to the above definitions. For another example, as shown in Figure 5A and Figure 5B , the downstream front of the traffic flow is fixed at the bottleneck, so the navigation route calculation device can determine this traffic flow as the synchronized flow (S) according to the above definitions.

[0045] Then, the navigation route calculation device can determine the propagation speed of the wide moving jam (J) and the synchronized flow (S) of the front road section m to the rear according to the current first congestion state data S i0 of the candidate road section i and the current congestion state data S m0 of the front road section m, and predict the second congestion state data S i2 of the candidate road section i at the departure time t2 according to the propagation speed and the above time difference Δt1, as shown in Figure 5B ​

[0046] The second congestion state data S of candidate road segment i at departure time t2 is predicted by using the above-mentioned Koener three-phase theory. i2 The present invention can further fill in the inferred congestion information for blank road segments that have never experienced congestion or for which congestion information has not been collected in advance, thereby solving the cold start problem of similar models. Therefore, this solution can ensure the availability and accuracy of the navigation routing method provided by the present invention in the initial stage of similar model operation.

[0047] like Figure 1 As shown, the second congestion state data S of each candidate road segment i at departure time t2 is predicted using a similarity model or Kohn's three-phase theory. i2 Subsequently, the navigation routing device can utilize the pre-trained AI recommendation model as described above, based on the second congestion status data S of each candidate road segment i at departure time t2. i2 Calculate the travel time Δt of the user through each candidate road segment i. i2 Then, by combining the mileage of each candidate road segment i and the remaining journey from the end point of each candidate road segment i to the target location 20, at least one recommended road segment with the highest traffic efficiency is selected from each candidate road segment i.

[0048] Compared to existing technologies that rely on the first congestion status data S at the current time t0 i0 To select a recommended route, this invention uses the second congestion status data S at the user's departure time t2 when arriving at departure location 12. i2 To select a recommended route. Compared to the first congestion status data S i0 The second congestion status data S at departure time t2 i2 It better reflects the actual traffic congestion situation when the user arrives at the starting location 12, thus significantly improving the accuracy of the route calculation results, especially for closed road sections such as highways, elevated roads, underground tunnels, and expressways. This avoids the navigation route calculation device mistakenly excluding high-quality closed road routes such as highways, elevated roads, underground tunnels, and expressways, thereby more accurately estimating navigation time and recommending actually faster navigation routes to navigation users.

[0049] exist Figure 3 In the illustrated embodiment, the navigation routing device can calculate the second congestion status data S of each candidate road segment i at departure time t2. i2 The system selects 32 closed-type candidate road segments (such as highways, elevated roads, underground tunnels, and expressways) with fewer intersections as the second recommended road segments. Then, the navigation route calculation device can... Figure 1As shown, it is determined whether the end point 13 of the second recommended route segment 32 is at the target position 20. In response to the determination result that the end point 13 of the second recommended route segment 32 is still not at the target position 20, the navigation route planning device can continue to determine the next recommended route segment with the end point 13 of the second recommended route segment 32 as a new departure position until the end point of the last recommended route segment meets the target position 20 of the navigation task. It should be noted that the scheme for determining the third recommended route segment according to the end point 13 of the second recommended route segment 32 is similar to the scheme for determining the second recommended route segment 32, which will not be described here.

[0050] Afterwards, in response to the determination result that the end point of the third recommended route segment is at the target position 20 of the navigation task, the navigation route planning device can combine the first recommended route segment 31, the second recommended route segment 32, and the third recommended route segment, and the like, which are connected in a loop, into a recommended route for the entire navigation task.

[0051] Further, in some preferred embodiments, the navigation route planning device can also collect the second congestion state data S i2 predicted for each candidate route segment i and save it locally and / or upload it to the cloud platform of the Internet of Vehicles. For the second congestion state data S i2 saved locally, the navigation route planning device can determine whether there is consistent second congestion state data S i2 in the local according to the current time information t2 and the route segment identifier information I i in the first congestion state data S i2 ’ acquired at time t2 when the user arrives at the corresponding route segment i. In response to the determination result that there is consistent second congestion state data S i2 in the local, the navigation route planning device can optimize the above-mentioned similar model according to the traffic flow information N i2 , the congestion state information V i2’ , the congestion state change information AV i2’ , and / or the congestion position information L i2’ in the acquired first congestion state data S i2’ ’ and the traffic flow information N i2 , the congestion state information V i2 , the congestion state change information AV i2 , and / or the congestion position information L i2 in the consistent second congestion state data S i2 , and synchronize the optimization data to the cloud.

[0052] Further, in response to the determination result that there is no consistent second congestion state data S i2 in the local, the navigation route planning device can also optimize the above-mentioned similar model according to the first congestion state data S i2The data is uploaded to the vehicle-to-everything (V2X) cloud platform, which then further determines whether a matching second congestion status data S exists in the cloud. i2 In response to the existence of a matching second congestion status data S in the cloud. i2 Based on the judgment result, the cloud platform can also use the first congestion status data S i2 Traffic flow information N in ' i2’ Congestion status information V i2’ Congestion status change information ΔV i2’ and / or congestion location information L i2’ And the corresponding second congestion status data S i2 Traffic flow information N i2 Congestion status information V i2 Congestion status change information ΔV i2 and / or congestion location information L i2 The aforementioned similar models are optimized in the cloud and the optimized data is synchronized to each user terminal.

[0053] By implementing these optimized similarity model schemes, the present invention can gradually fill in the congestion information of blank road segments that have never experienced congestion, or blank road segments for which congestion information has not been collected in advance, and continuously add historical data S of the congestion status of the same road segment at the same time. ij This reduces the impact of random errors on navigation and routing methods, thereby continuously improving the accuracy of navigation and routing methods.

[0054] Those skilled in the art will understand that the above-described navigation route calculation scheme, which first uses a similarity model to predict the second congestion status data and then fills in the congestion information of the blank road segments based on the Kohn-Köhler three-phase theory, is merely a non-limiting embodiment of the present invention, intended to clearly demonstrate the main concept of the present invention and provide a specific solution that is easy for the public to implement, rather than intended to limit the scope of protection of the present invention.

[0055] Alternatively, in other embodiments, the navigation routing device may not utilize the aforementioned similar model, but instead directly predict the departure time t of each candidate road segment i based on Koener's three-phase theory. n Second congestion status data S in Specifically, in predicting the departure time t of each candidate road segment i... n Second congestion status data S in At that time, the navigation routing device can first measure and analyze the current congestion status data S, such as the average vehicle speed of the road segment m ahead of candidate road segment i. m0 ,like Figure 5A As shown, based on the above definition, the system automatically identifies the wide-motion congestion phase J and the synchronous flow phase S within the congested flow. Afterwards, the navigation routing device can... Figure 5BThe diagram shows the first congestion status data S of candidate road segment i. i0 And the current congestion status data S of the road segment m ahead. m0 Determine the propagation speeds of the wide-movement congestion phase J and the synchronous flow phase S of the road segment m ahead, and based on these propagation speeds and the aforementioned time difference Δt... n-1 Predict the departure time t of candidate road segment i when the user arrives at the corresponding departure location. n Second congestion status data S in .

[0056] Those skilled in the art will also understand that, based on the navigation instruction of "depart immediately", the current time t0 is directly taken as the departure time t1 when the user arrives at the departure location 11, and the first congestion status data S of each candidate road segment i at the current time t0 is obtained. i0 The second congestion status data S at departure time t1 i1 The proposed solution is merely a non-limiting implementation method provided by the present invention, intended to clearly demonstrate the main concept of the invention and provide a specific solution that is easy for the public to implement, rather than being used to limit the scope of protection of the present invention.

[0057] Alternatively, in other embodiments, in response to a navigation command for "future travel time", the navigation routing device may also utilize a similarity model and / or be based on Koener's three-phase theory as described above, according to the first congestion state data S of each candidate road segment i at the current time t0. i0 and user-specified departure time t order Predict each candidate road segment i at departure time t order Second congestion status data S i_order And based on the departure time t order Second congestion status data S i_order This method selects recommended road segments based on the future time t of each candidate road segment i. order It uses traffic conditions to recommend navigation routes, thereby more accurately estimating navigation time and recommending actually faster routes to save travel time and improve user experience.

[0058] Although the methods described above are illustrated and depicted as a series of actions for the sake of simplicity, it should be understood and appreciated that these methods are not limited by the order of the actions, as some actions may occur in a different order and / or concurrently with other actions from the illustrations and descriptions herein or not illustrated and described herein but which may be understood by those skilled in the art, according to one or more embodiments.

[0059] Those skilled in the art will appreciate that information, signals, and data can be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that can be referenced throughout the above description can be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0060] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans can implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

[0061] Although the navigation algorithm apparatus described in the above embodiments can be implemented by a combination of software and hardware, it is understood that the navigation algorithm apparatus can also be implemented in software or hardware alone. For hardware implementation, the navigation algorithm apparatus can be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, micro-controllers, microprocessors, other electronic units designed to perform the functions described above and a selection of these. For software implementation, the navigation algorithm apparatus can be implemented by separate software modules, such as procedures and functions, which perform one or more of the functions and operations described herein when the modules are run on a general purpose chip.

[0062] The various illustrative logical blocks, circuits, and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or combinations of both. The various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality, without limitation. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans can implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

[0063] The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other variations without departing from the spirit or scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A navigation route calculation method, characterized in that, Includes the following steps: Multiple candidate road segments are determined based on the starting and destination locations; Determine the departure time when the user arrives at the stated departure location; Obtain the first congestion status data of each candidate road segment at the current time; Based on the first congestion status data and the departure time, predict the second congestion status data of each candidate road segment at the departure time. The step of predicting the second congestion status data of each candidate road segment at the departure time includes: obtaining the current congestion status data of the road segment preceding the candidate road segment; analyzing the first congestion status data and the current congestion status data of the preceding road segment based on Koener's three-phase theory and the time difference between the departure time and the current time to predict the second congestion status data of the candidate road segment at the departure time. The step of analyzing the first congestion status data and the current congestion status data of the preceding road segment to predict the second congestion status data of the candidate road segment at the departure time includes: parsing the current congestion status data of the preceding road segment to determine the current wide-movement congestion phase and synchronous flow phase of the preceding road segment; determining the propagation speed of the wide-movement congestion phase and synchronous flow phase of the preceding road segment backward based on the first congestion status data and the current congestion status data of the preceding road segment; predicting the second congestion status data of the corresponding candidate road segment at the departure time based on the propagation speed of the wide-movement congestion phase and synchronous flow phase of the preceding road segment and the time difference; and Based on the second congestion status data of each candidate road segment at the departure time, at least one recommended road segment is selected from each candidate road segment.

2. The navigation path calculation method as described in claim 1, wherein, The step of obtaining the first congestion status data of each candidate road segment at the current time includes: Obtain the current time information indicating the current time; Obtain at least one of the following for the candidate road segment: road segment identification information, road type information, related road information, traffic flow information, congestion status information, congestion status change information, and congestion location information; and Based on at least one of the current time information, the road segment identification information, the road type information, the relevant road information, the traffic flow information, the congestion status information, the congestion status change information, and the congestion location information, multi-dimensional vector data is constructed as the first congestion status data.

3. The navigation path calculation method as described in claim 2, wherein, The steps for obtaining the traffic flow information of the candidate road segment include: The traffic flow information of the candidate road segment is obtained from the inductive loop detectors installed on the candidate road segment; and / or Acquire signaling data from multiple vehicles, and statistically analyze the traffic flow information of the candidate road segment based on the signaling data from the multiple vehicles.

4. The navigation route calculation method as described in claim 1, wherein, After performing the step of selecting at least one recommended route from each of the candidate route segments based on the second congestion status data at the departure time, the navigation route calculation method further includes the following steps: Determine whether the end point of the recommended route is at the target location; In response to the determination that the endpoint of the recommended route segment is not at the target location, the next recommended route segment is determined using the endpoint of the recommended route segment as the starting location; and In response to the determination that the endpoint of the recommended road segment is at the target location, a recommended route is determined based on the consecutive recommended road segments.

5. A navigation route calculation method, characterized in that, Includes the following steps: Multiple candidate road segments are determined based on the starting and destination locations; Determine the departure time when the user arrives at the stated departure location; Obtaining the first congestion status data of each candidate road segment at the current time, wherein the step of obtaining the first congestion status data of each candidate road segment at the current time includes: obtaining current time information indicating the current time; obtaining at least one of the following for the candidate road segment: road segment identification information, road type information, related road information, traffic flow information, congestion status information, congestion status change information, and congestion location information; constructing multi-dimensional vector data based on at least one of the following: current time information, road segment identification information, road type information, related road information, traffic flow information, congestion status information, congestion status change information, and congestion location information, as the first congestion status data; The congestion status historical data of multiple road segments at multiple times are obtained. The congestion status historical data is multi-dimensional vector data, including at least one dimension of time information, road segment identification information, road type information, related road information, traffic flow information, congestion status information, congestion status change information and congestion location information. Based on the historical congestion data of the same road segment sample at multiple times, determine the trend of change of each historical congestion data over time; A similar model is constructed based on the historical data of each of the aforementioned congestion states and their changing trends over time. Based on the first congestion status data and the departure time, predict the second congestion status data of each candidate road segment at the departure time, wherein the step of predicting the second congestion status data of each candidate road segment at the departure time based on the first congestion status data and the departure time includes: inputting the first congestion status data into the similarity model, performing similarity analysis to determine similar historical congestion status data; predicting the second congestion status data of the corresponding candidate road segment at the departure time based on the trend of the similar historical congestion status data over time and the time difference between the departure time and the current time; and Based on the second congestion status data of each candidate road segment at the departure time, at least one recommended road segment is selected from each candidate road segment.

6. The navigation path calculation method as described in claim 5, wherein, The steps for performing similarity analysis to identify historical data on similar congestion states include: Calculate the similarity between the first congestion status data and each of the historical congestion status data; and Historical data on similar congestion states are determined based on the similarity.

7. The navigation path calculation method as described in claim 6, wherein, After performing the step of inputting the first congestion status data into the similarity model and performing similarity analysis to determine similar historical congestion status data, the navigation routing method further includes the following steps: Based on a preset similarity threshold, it is determined whether there is historical congestion data in the similarity model that is similar to the first congestion data; and In response to the absence of historical congestion data similar to the first congestion data in the similarity model, the current congestion data of the road segment ahead of the corresponding candidate road segment is obtained, and the first congestion data and the current congestion data of the road segment ahead are analyzed based on Koner's three-phase theory and the time difference to predict the second congestion data of the corresponding candidate road segment at the departure time.

8. The navigation path calculation method as described in claim 7, wherein, The step of analyzing the first congestion status data and the current congestion status data of the road segment ahead based on Koener's three-phase theory and the time difference to predict the second congestion status data of the corresponding candidate road segment at the departure time includes: The current congestion status data of the road segment ahead is analyzed to determine the current wide-movement congestion phase and synchronous flow phase of the road segment ahead; Based on the first congestion status data and the current congestion status data of the road segment ahead, determine the propagation speed of the wide-movement congestion phase and the synchronous flow phase of the road segment ahead; and Based on the propagation speed of the wide-movement congestion phase and the synchronous flow phase of the preceding road segment to the rear, as well as the time difference, the second congestion status data of the corresponding candidate road segment at the departure time is predicted.

9. The navigation route calculation method as described in claim 5 further includes the following steps: Collect and save the second congestion state data obtained from the prediction; In response to obtaining the first congestion status data, determine whether there is second congestion status data that matches the road segment identification information and current time information of the first congestion status data; as well as In response to the determination that there is a matching second congestion state data, the similarity model is optimized based on the acquired first congestion state data and the matching second congestion state data.

10. The navigation path calculation method as described in claim 5, wherein, After performing the step of selecting at least one recommended route from each of the candidate route segments based on the second congestion status data at the departure time, the navigation route calculation method further includes the following steps: Determine whether the end point of the recommended route is at the target location; In response to the determination that the endpoint of the recommended route segment is not at the target location, the next recommended route segment is determined using the endpoint of the recommended route segment as the starting location; and In response to the determination that the endpoint of the recommended road segment is at the target location, a recommended route is determined based on the consecutive recommended road segments.

11. A navigation and routing device, characterized in that, include: Memory; as well as A processor, connected to the memory, and configured to implement the navigation path calculation method as described in any one of claims 1 to 10.

12. A computer-readable storage medium storing computer instructions thereon, characterized in that, When the computer instructions are executed by the processor, the navigation route calculation method as described in any one of claims 1 to 10 is implemented.

Images