CN110411469B

CN110411469B - Navigation planning method, device, equipment and medium

Info

Publication number: CN110411469B
Application number: CN201910690642.1A
Authority: CN
Inventors: 张昊; 侯文元; 张战友
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2019-07-29
Filing date: 2019-07-29
Publication date: 2022-04-15
Anticipated expiration: 2039-07-29
Also published as: CN110411469A

Abstract

The embodiment of the invention discloses a navigation planning method, a navigation planning device, navigation planning equipment and a navigation planning medium, and relates to the field of route navigation. The method comprises the following steps: determining whether a route refreshing event is generated according to predicted road condition information of a non-passing road section in a current driving route at a future time; and if the route refreshing event is detected, planning a new driving route. Embodiments of the present invention provide a navigation planning method, apparatus, device, and medium, which improve the accuracy of determining a route refresh trigger time, implement timely triggering of a route refresh to avoid a road segment to be blocked, and implement optimal route guidance for a user.

Description

Navigation planning method, device, equipment and medium

Technical Field

The embodiment of the invention relates to the field of route navigation, in particular to a navigation planning method, a navigation planning device, navigation planning equipment and a navigation planning medium.

Background

The arrival time of the navigation route is also dynamically changed due to the change of the road condition, and the optimal navigation route is not invariable. Even in the same travel, the optimal routes planned at different times and different places are different, so that the routes need to be continuously refreshed in the navigation process to see whether the routes are better than the current main lines.

Theoretically, the higher the refresh frequency is, the more optimal route can be pushed in real time, but the real-time update cannot be realized due to the limitation of actual resources. Therefore, a certain strategy is needed to decide when to trigger route calculation, so that the route can be refreshed accurately and timely in the navigation process under the limited computing resource, and the invalid refreshing rate is reduced.

The following route planning schemes are currently generally adopted:

the scheme is updated periodically. The method triggers a decision every fixed duration, which is typically some rule decision. For example, the distance from the nearest bifurcation in a refresh cannot be too far, the distance between two refreshes cannot be too close, the time interval cannot be too short, etc. And determining whether to trigger the refreshing of the navigation route according to the judgment result.

The above route planning method mainly has the following disadvantages:

the judgment result of the trigger judgment based on the simple rule is not accurate enough, and the proportion of the recommended route really adopted by the user is not high, so that a large amount of computing resources are wasted.

For the road section to be blocked, the route cannot be predicted in advance and refreshed in time to avoid.

For congestion at the far end of the current time, it is possible that the congestion at this point has become clear when the user actually walks to the far-end congested road segment. Then it is not necessary at the current time to trigger a route refresh to avoid the far end congestion and the user may be erroneously guided to a route that is worse than the current route of travel.

Disclosure of Invention

Embodiments of the present invention provide a navigation planning method, apparatus, device, and medium to improve the accuracy of determining a route refresh trigger time, implement timely triggering of a route refresh to avoid a road segment that is about to become congested, and implement optimal route guidance for a user.

In a first aspect, an embodiment of the present invention provides a navigation planning method, where the method includes:

determining whether a route refreshing event is generated according to predicted road condition information of a non-passing road section in a current driving route at a future time;

and if the route refreshing event is detected, planning a new driving route.

In a second aspect, an embodiment of the present invention further provides a navigation planning apparatus, where the apparatus includes:

the event generation module is used for determining whether a route refreshing event is generated according to the predicted road condition information of the section which does not pass in the current driving route at the future time;

and the route planning module is used for planning a new driving route if the route refreshing event is detected.

In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement a navigation planning method as in any one of the embodiments of the invention.

In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the navigation planning method according to any one of the embodiments of the present invention.

According to the embodiment of the invention, whether a route refreshing event is generated or not is determined according to the predicted road condition information of the non-passing road section in the current driving route at the future time, so as to trigger the planning of a new driving route. The road section to be blocked can be determined and the road section to be dispersed can also be determined according to the predicted road condition information of the section which does not pass in the current driving route at the future time. Therefore, the accuracy of determining the route refreshing triggering time can be improved, the route planning can be triggered timely to avoid the road section to be blocked, and the optimal route guidance for the user can be always realized.

Drawings

Fig. 1 is a flowchart of a navigation planning method according to an embodiment of the present invention;

fig. 2 is a flowchart of a navigation planning method according to a second embodiment of the present invention;

fig. 3 is a flowchart of a navigation planning method according to a third embodiment of the present invention;

fig. 4 is a flowchart of a navigation planning method according to a fourth embodiment of the present invention;

fig. 5a is a flowchart of a navigation planning method according to a fifth embodiment of the present invention

FIG. 5b is a schematic diagram of a sub-route segmentation according to the fifth embodiment of the present invention;

fig. 5c is a schematic view of segment division according to a fifth embodiment of the present invention;

fig. 5d is a schematic view of a sub-segment segmentation according to a fifth embodiment of the present invention;

fig. 5e is a schematic diagram of a route triggering determination process according to the fifth embodiment of the present invention;

fig. 6 is a schematic structural diagram of a navigation planning apparatus according to a sixth embodiment of the present invention;

fig. 7 is a schematic structural diagram of an apparatus according to a seventh embodiment of the present invention.

Detailed Description

The route planning scheme adopted at present further comprises:

the route is updated in a mode of refreshing an over-bifurcation port (composed of bifurcation road segments, which can also be understood as a bifurcation port). In the method, a branch port between a recommended main line and a recommended auxiliary line is taken as a key point, one auxiliary line is blanked every time one branch port is passed, and then a calculation path is triggered to recommend a new auxiliary line. This way, it can be better guaranteed that there is always at least one recommended route.

However, the above method has the following disadvantages:

there is a blank period of refresh regardless of excessive tap trigger, fixed duration trigger, fixed location trigger. There is a refresh interval between two refreshes, during which some critical refresh opportunities may be missed.

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.

Example one

Fig. 1 is a flowchart of a navigation planning method according to an embodiment of the present invention. The embodiment can be applied to the situation that the trigger time is determined in the navigation process so as to trigger the re-planning of the navigation route. The method may be performed by a navigation planning apparatus, which may be implemented in software and/or hardware. Referring to fig. 1, the navigation planning method provided by the present embodiment includes:

and S110, determining whether a route refreshing event is generated according to the predicted road condition information of the section which does not pass in the current driving route at the future time.

The current driving route refers to a planned route currently selected by a user, and is represented as a darker route with road conditions on a map.

The section which is not traveled in the current driving route refers to a section other than the section which is already traveled in the current driving route, namely, the section which is not traveled in the current driving route.

The future time may be a point in time or a period of time.

If the future time is a time point, the future time can be set according to actual needs, specifically, the future time can be the 6 th minute, the future time can be the 11 th minute, and the future time can be the future 8 th minute.

That is, the collection time interval of the predicted traffic information at the future time may be determined as needed. If the accuracy of the determination of the road condition information to be predicted is higher, the acquisition time interval can be set to be shorter.

The predicted traffic information of the future time segment may be determined by the predicted traffic information of at least one time point in the future time segment.

The predicted road condition information of the non-passing road section in the current driving route at the future time refers to the predicted road condition information of the non-passing road section in the current driving route at the future time.

An event is a message sent by an object. For example, when a user presses a button, a file is changed, and data arrives in the socket.

The route refresh event is an event that triggers a route refresh, and specifically may be a change in a value in a certain identification bit.

Specifically, the determination of the predicted road condition information of the unvarying road section in the current driving route at the future time comprises the following steps:

estimating the estimated arrival time of the user driving to the section which is not passed according to the driving speed of the user and the real-time road condition information;

according to the predicted arrival time, the predicted road condition information of the unvaried road section in the current driving route at the predicted arrival time is searched from the predicted road condition information of the road section in the road network at the future time.

Determining whether a route refreshing event is generated according to predicted road condition information of an unvaried road section in a current driving route at a future time, wherein the determining comprises the following steps:

determining the passing state of the road section when the user drives the current road section according to the predicted road condition information of the non-passing road section in the current driving route at the future time;

and if the traffic jam state is detected, generating a route refreshing event.

And S120, if the route refreshing event is detected, planning a new driving route.

Specifically, if the route refresh event is detected, planning a new driving route, including:

when the route refreshing event is detected, the planning operation of the new driving route is executed, namely the current time is used as the time for triggering the route refreshing.

The method for planning the new driving route is not limited in this embodiment. Alternatively, the new driving route may be planned according to at least one of predicted traffic information of the road segments in the road network at a future time, real-time traffic information of the road segments in the road network, and historical traffic information of the road segments in the road network.

According to the technical scheme of the embodiment of the invention, whether a route refreshing event is generated or not is determined according to the predicted road condition information of the non-passing road section in the current driving route at the future time, so as to trigger the planning of a new driving route. The road section to be blocked can be determined and the road section to be dispersed can also be determined according to the predicted road condition information of the section which does not pass in the current driving route at the future time. Therefore, the accuracy of determining the route refreshing triggering time can be improved, the route planning can be triggered timely to avoid the road section to be blocked, and the optimal route guidance for the user can be realized.

To facilitate understanding of a planned new driving route by a user, after planning a new driving route if the route refresh event is detected, the method further includes:

if the planned new driving route is still the current driving route, and congestion dissipation of a congested road section is determined when a user reaches the congested road section on the current driving route according to intersection prediction information of the road section arrival time in the current driving route, generating dissipation reminding of the congested road section as a switching reason of the current driving route; or

And if the planned new driving route still does not include the current driving route, and the smooth road section is blocked when the user reaches the smooth road section on the current driving route according to the intersection prediction information of the road section arrival time in the current driving route, generating the prompt of the smooth road section about to be blocked as the switching reason of the current driving route.

Specifically, the determining of the predicted road condition information of the road segments in the road network at the future time includes:

and determining the predicted road condition information of the road sections in the road network at the future time according to at least one of the road information of the road sections in the road network, the historical synchronous road condition information, the real-time road condition information and the real-time road condition information of the adjacent road sections.

Further, the determining predicted traffic information of the road segments in the road network at the future time according to at least one of the road information of the road segments in the road network, the historical contemporaneous traffic information, the real-time traffic information, and the real-time traffic information of the adjacent road segments includes:

determining road characteristics according to road information of road sections in a road network;

determining the time sequence characteristics of the road section in the target time period according to at least one item of the target time period traffic flow information of the road section, the target time period traffic flow information of other road sections connected with the road section and the target time period traffic flow information of the geographic area of the road section;

and determining road condition prediction information of the road section in a target time period according to the time sequence characteristics and the road characteristics.

Further, the road information of the road segments in the road network includes: the number of the road sections adjacent to the road section in the road network and capable of driving into the road section, the number of the road sections adjacent to the road section and capable of driving out the road section, the number of lanes and road grade included in the road section, the number of traffic lights and at least one of the waiting time of the red lights.

In order to solve the problem that some key refreshing opportunities may be missed in a refreshing interval between two refreshes, the method further includes, before determining whether to generate a route refreshing event according to predicted road condition information of an unvaried road section in a current driving route at a future time, the method including:

triggering and executing the step of determining whether a route refreshing event is generated or not according to the predicted road condition information of the section which does not pass in the current driving route at the future time at intervals of a set refreshing interval;

wherein the set refresh interval is less than a set interval threshold.

Because the refresh interval can be set smaller, it is possible to avoid the situation where some critical refresh opportunities are missed. Moreover, because the method of the embodiment can accurately judge the refresh trigger time, the number of times of route refreshing executed in the whole navigation process cannot be greatly increased even if the refresh interval is set to be smaller.

Example two

Fig. 2 is a flowchart of a navigation planning method according to a second embodiment of the present invention. The present embodiment is an alternative proposed on the basis of the above-described embodiments. Referring to fig. 2, the navigation planning method provided in this embodiment includes:

s210, determining whether a route refreshing event is generated according to the predicted road condition information of the section which does not pass in the current driving route at the future time and the real-time road condition information of the section which does not pass in the current driving route.

The real-time road condition information of the section which does not pass through in the current driving route refers to the road condition information of the section which does not pass through in the current driving route at the current time.

Specifically, the determining whether to generate a route refresh event according to the predicted traffic information of the unvarying road section in the current driving route at the future time and the real-time traffic information of the unvarying road section in the current driving route includes:

if the congestion road section exists in the non-passing road section according to the real-time road condition information of the non-passing road section in the current running route, determining a target distance between the current position of the user and the congestion road section;

if the target distance is greater than the distance threshold, obtaining the predicted road condition information of the congested road section at the future time from the predicted road condition information of the unviewed road section at the future time in the current driving route;

and if the situation that the congestion of the congested road section is not dissipated when the user arrives at the congested road section is determined according to the predicted road condition information of the congested road section at the future time, generating a route refreshing event.

The method can realize the following effects:

and according to the predicted road condition information of the non-passing road section in the current running route at the future time, carrying out congestion prediction on the non-passing road section in the running area at the far end of the current running route, and carrying out route refreshing triggering according to the prediction result.

And S220, if the route refreshing event is detected, planning a new driving route.

According to the technical scheme of the embodiment of the invention, whether a route refreshing event is generated or not is determined according to the predicted road condition information of the non-passing road section in the current driving route at the future time and the real-time road condition information of the non-passing road section in the current driving route, so that the accuracy of determining the route refreshing triggering time is improved.

Optionally, the determining whether to generate a route refresh event according to the predicted traffic information of the unvarying road section in the current driving route at the future time and the real-time traffic information of the unvarying road section in the current driving route includes:

judging whether a congested road section exists in an unviewed road section according to real-time road condition information of the unviewed road section in the current driving route;

if yes, judging whether the congested road section is located in a near-end driving area or a far-end driving area, wherein the near-end driving area is a driving area which is smaller than a distance threshold value from the current position of a user on the current driving route, and the far-end driving area is a driving area which is larger than or equal to the distance threshold value from the current position of the user on the current driving route;

if the congested road section is located in a near-end driving area, triggering route refreshing;

if the congested road section is located in a far-end driving area, judging whether congestion of the congested road section dissipates or not when a user drives to the congested road section;

and if the congestion of the congested road section is not dissipated when the user drives to the congested road section, triggering route refreshing.

The method can realize the following effects:

and determining congestion information of the non-passing road section in the near-end driving area of the current driving route according to the real-time road condition information of the non-passing road section in the current driving route at the current time.

Because the real-time road condition information of the non-passing road section in the near-end driving area of the current driving route at the current time can already reflect the congestion prediction condition of the near-end driving area. Therefore, the congestion prediction of the non-passing road section in the near-end driving area of the current driving route is not needed according to the predicted road condition information of the non-passing road section in the current driving route at the future time, and therefore computing resources are saved.

Optionally, before determining whether to generate a route refresh event according to the predicted traffic information of the unvarying road section in the current driving route at the future time and the real-time traffic information of the unvarying road section in the current driving route, the method further includes:

judging whether the user is in a driving state or not according to the acquired real-time positioning information of the user;

if the user is in a driving state, judging whether a traffic event exists in the rest road sections of the current driving navigation route;

if the remaining road sections of the current driving route have traffic events, generating a route refreshing event;

and if no traffic event exists in the rest road sections of the current driving route, executing a step of determining whether to generate a route refreshing event according to the predicted road condition information of the non-passing road section in the current driving route at the future time and the real-time road condition information of the non-passing road section in the current driving route.

EXAMPLE III

Fig. 3 is a flowchart of a navigation planning method according to a third embodiment of the present invention. The present embodiment is an alternative proposed on the basis of the above-described embodiments. Referring to fig. 3, the navigation planning method provided in this embodiment includes:

s310, inputting the predicted road condition information of the section which does not pass in the current driving route at the future time into a route refreshing identification model to determine whether a route refreshing event is generated or not.

Specifically, the sample determination of the route refresh recognition model includes:

acquiring historical driving routes which are driven from a current driving route starting point to a current driving route end point and have the same history period;

determining a corrected travel time of the historical travel route;

and determining a positive sample historical driving route and a negative sample historical driving route from the historical driving routes in the historical synchronization according to the corrected driving time consumption of the historical driving routes.

The historical synchronization refers to a period in the historical time that is the same as the target period. For example, if the target epoch is 7:00 am today, the historical epoch may be 7 am yesterday: 00, or 7:00 am the previous day. If the target epoch is 7:00 am monday this week, the historical contemporaneous period may be 7:00 am monday the last week, or 7:00 am monday the week before the last week.

The corrected travel time may be actual travel time or travel time after the correction processing.

Alternatively, the route refresh trigger timing of the historical travel route that takes the shortest time for the corrected travel of the historical travel route may be set as the positive sample historical travel route, and the route refresh trigger timing of the historical travel route that takes the longest time for the corrected travel of the historical travel route may be set as the negative sample historical travel route.

Because the driving habits of each user are different, the driving speed of some users is high, the driving speed of some users is low, and in order to avoid the influence of the driving speed on the sample selection, the determining of the correction driving time consumption of the historical driving route comprises the following steps:

determining actual travel time of the historical travel route;

determining an average driving speed of the historical driving route in a smooth state;

determining a revised travel time of the historical travel route according to the following formula:

wherein, t'_iIs the corrected travel time of the history travel route, t_iIs the actual travel time of the historical travel route, V_iIs the average driving speed, V, of the historical driving route in a smooth state_maxIs the maximum value of the average driving speed of the historical driving route set in a smooth state, and i identifies different historical driving routes.

And S320, if the route refreshing event is detected, planning a new driving route.

According to the technical scheme of the embodiment of the invention, the predicted road condition information of the section which does not pass in the current driving route at the future time is input into the route refreshing identification model so as to determine whether a route refreshing event is generated or not. Thereby realizing the automatic determination of the trigger time of the route refreshing event.

Example four

Fig. 4 is a flowchart of a navigation planning method according to a fourth embodiment of the present invention. The present embodiment is an alternative proposed on the basis of the above-described embodiments. Referring to fig. 4, the navigation planning method provided in this embodiment includes:

s410, if congestion of the section which does not pass through in the current running route is determined according to the predicted road condition information of the section which does not pass through in the current running route at the future time, whether a key bifurcation section exists between the current position of the user and the position of the congestion is determined.

In order to improve the adoption rate of the user to the recommended key bifurcation section, the determination of whether the key bifurcation section exists between the current position and the congestion position of the user comprises the following steps:

taking a basic bifurcation section which approaches a historical driving route of the current position and the congestion position of the user and/or a planned driving route as a candidate bifurcation section; wherein, the basic bifurcation section is connected with at least two descending sections;

determining a heat of the candidate bifurcation section;

and determining a key branch road section from the candidate branch road sections according to the heat degree of the candidate branch road sections.

Specifically, the determining the heat of the candidate bifurcation section comprises the following steps:

if the number of the matched tracks of the historical driving route to which the candidate bifurcation section belongs is equal to or larger than a track number threshold value, determining the heat degree of the candidate bifurcation section according to the number of the matched tracks of the historical driving route to which the candidate bifurcation section belongs;

if the number of the matched tracks of the historical driving route to which the candidate bifurcation section belongs is smaller than a track number threshold value, determining the heat degree of the candidate bifurcation section according to the condition that the candidate bifurcation section is positioned in the planned driving route;

and if the error of the historical track positioning point of the historical driving route to which the candidate bifurcation section belongs is larger than the error threshold value, determining the heat degree of the candidate bifurcation section according to the distance from the historical track positioning point to the historical driving route to which the candidate bifurcation section belongs.

Specifically, the determining the heat of the candidate branch road section according to the distance between the historical track positioning point and the historical driving route to which the candidate branch road section belongs comprises:

traversing the historical track positioning points in the area to which the candidate branch road sections belong, and if the distance from any historical track positioning point to the historical driving route to which any candidate branch road section belongs is smaller than the distance from the historical track positioning point to the historical driving routes to which other candidate branch road sections belong, determining that the historical track positioning point is associated with the historical driving route to which any candidate branch road section belongs;

selecting a target driving route from the historical driving routes to which the candidate bifurcation section belongs according to the quantity of the related historical track positioning points;

and determining the heat degree of the candidate branch road section according to the condition that the candidate branch road section is positioned in the target driving route.

S420, if the fact that the key branch road section does not exist is determined, generating a route refreshing event is refused; otherwise, generating a route refreshing event.

And S430, if the route refreshing event is detected, planning a new driving route.

According to the technical scheme of the embodiment of the invention, if congestion of the current non-passing road section in the current running route is determined according to the predicted road condition information of the non-passing road section in the current running route at the future time, whether a key bifurcation section exists between the current position of a user and the congestion position is determined; if the key branch road section does not exist, refusing to generate a route refreshing event; otherwise, generating a route refreshing event. Therefore, the route refreshing triggering efficiency is further improved, and useless route refreshing is avoided.

EXAMPLE five

Fig. 5a is a flowchart of a navigation planning method according to a fifth embodiment of the present invention. The present embodiment is an alternative proposed on the basis of the above-described embodiments. Referring to fig. 5a, a navigation planning method provided in this embodiment includes:

road condition prediction:

first, a route is divided into at least one sub-section, and the variation of the road condition is predicted with the granularity of the sub-section level. The following is the process of drawing a sub-road segment:

referring to fig. 5b, a route is composed of a start point, 0 or more pathway points, and an end point. The two points are called a sub-route.

Referring to fig. 5c, each sub-route is made up of a plurality of segments, and it is the maneuver point that divides the segments. Any one of the following 4 situations can be classified as a maneuver point:

1) eight directions

2) Bifurcate and trifurcate (i.e. branch, confluence)

3) Ring island

4) Road name changing (from A avenue- > B avenue)

Referring to fig. 5d, each road section is composed of a plurality of sub-road sections, and each road section can be segmented by using the intersection as a segmentation point to obtain a plurality of sub-road sections.

Secondly, predicting the road condition of each sub-road section by adopting an RNN model:

numbering the sequence of sub-segments of the route from the starting point to the end point as follows: l is₁、L₂、…、L_n；

The time period from 10 minutes before departure to the estimated arrival time of the user is segmented into the following time segments at intervals of 10 minutes: t is t₁、t₂、…、t_m；

Taking the historical synchronous average road condition of each sub-road section through historical data, and recording the average road condition as H_i. For example, to predict L₁The road condition of 7:30 on Monday morning, the average value of the road conditions of 7:30 on Monday morning on the last month and each week of this sub-section is taken as the historical road condition.

Defining the degree of entry and the degree of exit of the sub-road section. The degree of penetration is defined as the degree of fusion with L_iAdjacent and can drive into L_iThe number of sub-links, out-degree, is equal to L_iAdjacent and can be pulled out of L_iThe number of sub-segments of (a). Calculating L from static road network data_iIs recorded as alpha_iAnd the degree of output, recorded as beta_i。

Query road network to obtain L_iThe number of lanes of (D) is recorded as gamma_iAnd road grade, noted as θ_j。

Recording the number of traffic lights included in each sub-road section as M_iAnd the waiting time of the red light is recorded as N_i。

Obtaining L_iReal-time road condition S_iAnd with L_iReal-time road condition S of 2 adjacent sub-road sections_i-1And S_i+1。

And (4) carrying out embedding layer processing on basic information (entrance and exit degree, road grade, lane number, traffic lights and the like) of the sub-road section to obtain a road characteristic vector V.

Arranging the historical synchronous traffic information of the road section, the historical synchronous traffic information of other road sections connected with the road section and the characteristics of the historical synchronous traffic information area of the geographic area to which the road section belongs according to the time sequenceThe sequence is input into an RNN model, a full connection layer and a softmax four-classifier are used in an output layer of the model, output values are 1, 2, 3 and 4, and the output values respectively represent four road condition states of smooth, slow running, congestion and very congestion. L can be predicted by the model_iPredicted road condition value at time t

Thereafter, the updating is performed every 10 minutes

As the user gets closer to L_iThe more accurate the predicted road condition value is.

Off-line excavation of key branch road sections:

and excavating a route with a matching driving track between the two position points larger than a track threshold value by using the historical accumulated driving track data. If the positioning points between the two position points are dense, selecting the route with set ranking before the matched track quantity is ranked, and taking the basic branch road sections as key branch road sections.

If the positioning points between the two position points are sparse and even have no positioning points, recalling the set of reachable routes through a traditional route searching algorithm according to the static road network data. The base bifurcation section between the routes in the set is calculated as a key bifurcation section for the routes in the set.

In order to reduce the difficulty of matching the positioning points of the users to a certain route, the following method is adopted to match the route aiming at the conditions that the road network is complex and the routes are dense and the positioning error of the users is greater than the error threshold value in the road network with the geographic area.

Route matching based on distance minimization:

1) first, a reachable route set is recalled through a conventional routing algorithm according to static road network data.

2) And finding the route closest to the positioning point from the route set, and adding 1 to the count of the route after finding.

3) And traversing all the positioning points, and executing the step 2) on the traversed positioning points to realize route matching.

In order to determine the routes frequently taken by the public users from the route set, after traversing all the positioning points, the counting of each route in the route set is sequenced. And taking the route ranked in the previous set ranking as the target driving route with the largest track amount.

Triggering and judging route refreshing:

the features input in this step are mainly classified into 3 types: the first category is road bifurcation feature, which includes bifurcation segments mined by tracks and bifurcation segments calculated from static road networks. The second category is road condition characteristics of roads, which mainly include real-time road conditions and predicted road conditions. The third category is the user's driving information and real-time traffic events on the road. The method specifically comprises the following steps:

1) acquiring real-time information:

specifically, the real-time information includes both some real-time information of the user, such as the location point and speed of the user, and some real-time event information, such as a traffic accident, temporary traffic restrictions, and the like.

This information is important and unpredictable for route trigger discrimination. For example, when the user's location position is not moving for a long time, it may be that the user has stopped a rest in the middle, and it is not necessary to trigger the route calculation again. For information such as serious traffic accidents, temporary restriction and the like, the information can be acquired through UGC or notice of a traffic bureau and the like, the information is uploaded to a public database, and then the service pulls traffic event information from the database at intervals. The real-time information of the user in the navigation process can be acquired in the following two ways:

a. short connection mode:

the client establishes a link with the server every 15s to transmit information such as positioning points, speed and the like of the user, the server immediately performs trigger judgment after receiving data, and the link is immediately closed after the judgment. The scheme is simple for the server to manage, and the existing connections are all useful connections without additional control means. But the frequent client requests will waste more time and bandwidth on the TCP set-up and shut-down operations.

b. The long connection mode is as follows:

after a user enters navigation, the server side establishes long connection with the client side, the client side transmits data to the server side every 15s, and the connection channel cannot be disconnected as long as the user does not quit the navigation.

2) Route refreshing triggering judgment:

after the features are obtained, route trigger judgment needs to be performed according to the features. The discrimination can be performed in two ways, namely a rule and a model, and the specific steps are as follows with reference to fig. 5 e:

the first scheme is as follows: and (3) trigger judgment is carried out based on the rule:

a. firstly, whether the user is in a normal navigation process or not is judged according to the acquired real-time positioning information of the user, and if the user is not in the navigation process, the user directly judges that the route is not calculated (namely, route refreshing is not carried out).

b. And judging whether the current main line has a traffic event or not, if the current main line has the traffic event, immediately triggering the route calculation (namely performing route refreshing), and not needing to perform subsequent judgment.

c. And then judging whether the user is in a congestion state at present according to the real-time road conditions, and if the user is in the congestion state at present, continuously judging whether the user is in near-end congestion or far-end congestion. And if the congestion is near-end congestion, judging whether a key branch road section is related between the current position of the user and the congestion section. If yes, calculating the path, otherwise, not calculating the path; if the remote congestion state is the remote congestion state, the same process as the open state is performed, and the following flow is continued.

d. And estimating the positioning point of the user at the future time according to the information such as the speed, the real-time road condition and the like of the user, and judging the future traffic state of the user by combining the road condition prediction. If the future is smooth, the road is not calculated at the moment; if the congestion is in the future, the same treatment is carried out with the near-end congestion in the step c, whether a key branch road section is related between the current point and the congestion section in the future is judged, and if the key branch road section is related, the road is calculated; if not, no way is calculated.

e. And c, in the whole process from entering the navigation to exiting the navigation, carrying out trigger judgment once every a period of time, and circularly executing the steps from a to d.

The concept of the rule-based scheme is clear, but many thresholds in the rule need to be determined, such as how many distance ranges belong to the near-end congestion. For another example, in step e, how often the trigger is determined. Manually setting fixed values is not universal and is difficult to optimize. And this problem can be solved by the model.

Scheme II: and (3) carrying out trigger discrimination based on the classification model:

in the first scheme, each element triggered by discrimination can be divided into 3 types of features, and the first type is road condition information including real-time road conditions and predicted road conditions. The second type is the attribute of the road itself, such as road junction information, road class, etc. The third category is real-time information including the speed of the user, road traffic events, etc. And refining a plurality of dimensional characteristics for each type of characteristics, such as the characteristic of predicted road conditions, the characteristics of road conditions within 5km after 5 minutes, road conditions within 10km after 5 minutes, road conditions within … after 10 minutes, road conditions within 5km after 10 minutes, road conditions within 10km after 10 minutes and the like, and screening the finally required characteristics through characteristic engineering.

In addition to selecting features, positive and negative examples need to be labeled. The idea adopted here is to use the navigation completion time as the basis for marking the trigger opportunity. The specific idea is as follows:

a. firstly, selecting a set I of all navigation users driving from a point A to a point B in the same time period, and calculating the navigation completion time t of each user_i。

b. Calculating the average running speed V of the user i in the unblocked state_iAs a velocity weight. Under the condition that other factors are completely the same, the driving speed of the user can influence the navigation completion time, and the navigation completion time with low speed can be long. Therefore, in order to remove the influence of the driving behavior of the user, the navigation completion time of the user needs to be converted according to the speed ratio. The converted navigation completion time is as follows:

wherein, V_maxIs the maximum value in the set V.

c. And finding out the user I with the shortest navigation completion time in the set I, and taking the triggering time in the navigation process as a positive sample of route triggering. Finding out the user j with the longest navigation completion time, and taking the triggering time in the navigation process as a negative sample of route triggering.

After the samples are obtained through the process, an XGBoost model or an SVM model is selected for modeling to obtain a two-classification model for judging the route triggering in navigation.

3) Interpretation of trigger opportunities:

the preposed road calculation based on road condition prediction needs to be correspondingly explained so as to be convenient for users to understand.

The interpretation is mainly divided into two categories: the congestion is changed to be smooth, and the user needs to be prompted from the aspects of the brightness, the voice broadcasting, the label display and the like of the route that the congestion is about to dissipate, and the route does not need to be switched. The other type is that the route is changed from smooth to blocked, which needs to trigger route calculation and prompt the user to switch the route in time, and the main line is gradually blocked.

The above method can be briefly described as follows:

and dividing the recommended route into road sections with different lengths according to the attributes of the roads, and predicting the road condition of each road section respectively. The road condition prediction is carried out through a machine learning model, and a four-classification model is established by taking historical synchronous road conditions, past short-time road conditions, real-time road conditions, road grades, traffic light number, average waiting time and the like as characteristics to predict the road conditions. The model can give four types of prediction results of smooth, slow walking, congestion and very congestion.

In addition, it is also necessary to acquire branch junction information of the road, and first, start points and end points of a large number of user tracks are clustered to find tracks having the same start points and end points. And selecting routes with set names before track quantity ranking, and finding key branch sections of the routes. Meanwhile, the set of reachable routes is recalled by a traditional routing algorithm in combination with explicit road network data, and the key branch sections between the reachable routes in the set are calculated. And finally, combining the key branch road sections obtained by the two modes together to be used as an important basis for triggering judgment.

After two important characteristics of the predicted road condition and the road bifurcation are provided, a trigger discrimination model which is a two-classification model is established by combining the characteristics of the real-time road condition, traffic rules, the driving speed of a user, the remaining distance and the like, and the judgment result is refreshed or not refreshed. Finally, the quality of the model is judged according to feedback indexes such as the travel efficiency, the yaw rate, the manual refreshing rate, the manual switching rate and the route completion rate of the user.

The specific innovation points of this embodiment can be summarized as the following 2 points:

(1) navigation route triggering based on road condition prediction

Different from the traditional route triggering method in navigation, the algorithm establishes a road condition prediction model based on historical road conditions and real-time road characteristics, predicts the change of the road conditions in a period of time in the future, and determines to refresh or not refresh the route by taking the change as a key factor.

Compared with the traditional route triggering method only depending on real-time road conditions, the route triggering method in navigation based on road condition prediction has the following advantages: firstly, for the situation that the current driving route is gradually blocked from smooth, the road calculation can be triggered earlier through road condition prediction, so that more blockage avoiding opportunities are provided. Secondly, for the situation that the current driving route is gradually changed from congestion to clear, it is predicted in advance that when the user walks to the previous congested road section, congestion may not occur, and then route calculation is not triggered before and other routes are recommended to the user, so that the user is switched to a new driving route which is not the original driving route.

(2) Mining key bifurcation road section based on user track data

And finding out the key branch road sections by mining a large number of user tracks. Because static road network data analysis alone is incomplete, some key road segments may be missed, and there are also many basic road segments that have little significance for route trigger discrimination.

According to the technical scheme of the embodiment of the invention, the road condition change of the recommended route in the period from the time when the user enters the navigation to the time when the user exits the navigation is accurately predicted. The predicted road condition is used as an important factor for route triggering in navigation, future position points of the user are predicted according to information such as speed and real-time road condition of the user, and the traffic state of the user in a future period of time is judged by combining the predicted road condition, so that the current state of the user is considered, and congestion possibly encountered by the user in the future can be predicted in advance to avoid in advance.

In addition, key branch road sections are mined according to the user track and serve as important bases for route trigger judgment, so that the adoption rate of a new driving route obtained by route trigger planning by a user is improved.

The embodiment combines the real-time road condition, the predicted road condition, the road network data, the individual driving behaviors of the user, the group driving behaviors and other information, and realizes intelligent route refreshing by establishing a machine learning model.

It should be noted that, through the technical teaching of this embodiment, a person skilled in the art will have an incentive to combine schemes of any one of the embodiments described in the above embodiments to improve the accuracy of determining the route refresh trigger time, to implement timely triggering of route planning to avoid a road segment that is about to become congested, and to implement guidance of an optimal route for a user.

EXAMPLE six

Fig. 6 is a schematic structural diagram of a navigation planning apparatus according to a sixth embodiment of the present invention. Referring to fig. 6, the navigation planning apparatus provided in this embodiment includes: an event generation module 10 and a route planning module 20.

The event generating module 10 is configured to determine whether to generate a route refreshing event according to predicted road condition information of a non-passing road section in a current driving route at a future time;

and the route planning module 20 is configured to plan a new driving route if the route refreshing event is detected.

Further, the event generation module includes: a first event generation unit.

The first event generating unit is used for determining whether to generate a route refreshing event according to the predicted road condition information of the section which does not pass through in the current driving route at the future time and the real-time road condition information of the section which does not pass through in the current driving route.

Further, the first event generating unit is specifically configured to:

Further, the event generation module includes: a second event generating unit.

The second event generating unit is used for inputting the predicted road condition information of the section which does not pass in the current driving route at the future time into the route refreshing identification model so as to determine whether to generate a route refreshing event or not.

Further, the apparatus further comprises: the system comprises a route acquisition module, a correction time-consuming determination module and a sample determination module.

The route obtaining module is used for obtaining historical driving routes which are driven from a starting point of the current driving route to a terminal point of the current driving route and have the same historical period before inputting the predicted road condition information of the non-passing road section in the current driving route at the future time into the route refreshing identification model;

a corrected travel time determination module for determining a corrected travel time of the historical travel route;

and the sample determining module is used for determining a positive sample historical driving route and a negative sample historical driving route from the historical driving routes in the historical synchronization according to the corrected driving time consumption of the historical driving routes.

Further, the correction elapsed time determination module includes: an actual elapsed time determination unit, a travel speed determination unit, and a corrected elapsed time determination unit.

The actual consumed time determining unit is used for determining the actual consumed time of the historical driving route;

a running speed determination unit for determining an average running speed of the historical running route in a smooth state;

a corrected travel time determination unit for determining a corrected travel time of the history travel route according to the following formula:

Further, the event generation module includes: a bifurcation section determining unit and a refresh rejection unit.

The device comprises a road branching section determining unit, a road traffic information judging unit and a road traffic information judging unit, wherein the road branching section determining unit is used for determining whether a key branch section exists between the current position of a user and a congestion position if congestion exists in the section which does not pass through in the current driving route according to the predicted road condition information of the section which does not pass through in the current driving route at the future time;

and the rejection refreshing unit is used for rejecting generation of a route refreshing event if the key branch road section does not exist.

Further, the branched section determining unit includes: the candidate determining subunit, the heat determining subunit and the link determining subunit.

The candidate determining subunit is used for taking a historical driving route passing the current position and the congestion position of the user and/or a basic bifurcation section in a planned driving route as a candidate bifurcation section; wherein, the basic bifurcation section is connected with at least two descending sections;

a hot degree determination subunit, configured to determine a hot degree of the candidate bifurcation section;

and the road section determining subunit is used for determining a key branch road section from the candidate branch road sections according to the heat degree of the candidate branch road sections.

Further, the heat determination subunit is specifically configured to:

Further, the determining the heat degree of the candidate branch road section according to the distance between the historical track positioning point and the historical driving route to which the candidate branch road section belongs comprises:

The navigation planning device provided by the embodiment of the invention can execute the navigation planning method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.

EXAMPLE seven

Fig. 7 is a schematic structural diagram of an apparatus according to a seventh embodiment of the present invention. Fig. 7 illustrates a block diagram of an exemplary device 12 suitable for use in implementing embodiments of the present invention. The device 12 shown in fig. 7 is only an example and should not bring any limitation to the function and scope of use of the embodiments of the present invention.

As shown in FIG. 7, device 12 is in the form of a general purpose computing device. The components of device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.

Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

Device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by device 12 and includes both volatile and nonvolatile media, removable and non-removable media.

The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. Device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 7, and commonly referred to as a "hard drive"). Although not shown in FIG. 7, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.

A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.

Device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with device 12, and/or with any devices (e.g., network card, modem, etc.) that enable device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, the device 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet) via the network adapter 20. As shown, the network adapter 20 communicates with the other modules of the device 12 via the bus 18. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

The processing unit 16 executes various functional applications and data processing, such as implementing a navigation planning method provided by an embodiment of the present invention, by executing programs stored in the system memory 28.

Example eight

An eighth embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a navigation planning method according to any one of the embodiments of the present invention, where the method includes:

and if the route refreshing event is detected, planning a new driving route.

Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A navigation planning method, comprising:

if the route refreshing event is detected, planning a new driving route;

the step of determining whether to generate a route refreshing event according to the predicted road condition information of the section which does not pass in the current driving route at the future time comprises the following steps:

if congestion of the current unvarying road section in the current driving route is determined according to the predicted road condition information of the unvarying road section in the current driving route at the future time, determining whether a key branch road section exists between the current position of the user and the congestion position;

if the key branch road section does not exist, refusing to generate a route refreshing event;

the determination of whether a key bifurcation section exists between the current position of the user and the congestion position comprises the following steps:

determining a heat of the candidate bifurcation section;

determining a key branch road section from the candidate branch road sections according to the heat degree of the candidate branch road sections;

wherein the determining the degree of heat of the candidate bifurcation segment comprises:

2. The method of claim 1, wherein determining whether to generate a route refresh event according to predicted traffic information of the unvarying road segments in the current driving route at a future time comprises:

and determining whether a route refreshing event is generated according to the predicted road condition information of the section which does not pass in the current driving route at the future time and the real-time road condition information of the section which does not pass in the current driving route.

3. The method of claim 2, wherein the determining whether to generate the route refresh event according to the predicted traffic information of the unvarying road segments in the current driving route at the future time and the real-time traffic information of the unvarying road segments in the current driving route comprises:

if the target distance is greater than the distance threshold, obtaining the predicted road condition information of the congested road section at the future time from the predicted road condition information of the unvaryed road section at the future time in the current driving route;

4. The method of claim 1, wherein determining whether to generate a route refresh event according to predicted traffic information of the unvarying road segments in the current driving route at a future time comprises:

and inputting the predicted road condition information of the section which does not pass in the current driving route at the future time into a route refreshing identification model so as to determine whether a route refreshing event is generated or not.

5. The method of claim 4, wherein the sample determination of the route refresh recognition model comprises:

determining a corrected travel time of the historical travel route;

6. The method of claim 5, wherein determining a revised travel time for the historical travel route comprises:

determining actual travel time of the historical travel route;

7. The method of claim 1, wherein determining the heat of the candidate bifurcation segment based on the distance between the historical track fix point and the historical driving route to which the candidate bifurcation segment belongs comprises:

8. A navigation planning apparatus, comprising:

the route planning module is used for planning a new driving route if the route refreshing event is detected;

wherein the event generation module comprises:

the device comprises a bifurcation section determining unit, a road information judging unit and a road information judging unit, wherein the bifurcation section determining unit is used for determining whether a key bifurcation section exists between the current position of a user and a congestion position if congestion exists in the current section which does not pass in the current driving route according to the predicted road condition information of the current section which does not pass in the current driving route at the future time;

the device comprises a refusing refreshing unit, a route refreshing unit and a route refreshing unit, wherein the refusing refreshing unit is used for refusing to generate a route refreshing event if the key branch road section does not exist;

wherein the branch section determination unit includes:

the candidate determining subunit is used for taking the historical driving route passing the current position and the congestion position of the user and/or a basic bifurcation section in the planned driving route as a candidate bifurcation section; wherein, the basic bifurcation section is connected with at least two descending sections;

the road section determining subunit is used for determining a key branch road section from the candidate branch road sections according to the heat degree of the candidate branch road sections;

wherein the heat determining subunit is specifically configured to:

9. The apparatus of claim 8, wherein the event generating module comprises:

and the first event generating unit is used for determining whether a route refreshing event is generated according to the predicted road condition information of the non-passing road section in the current driving route at the future time and the real-time road condition information of the non-passing road section in the current driving route.

10. The apparatus according to claim 9, wherein the first event generating unit is specifically configured to:

11. The apparatus of claim 8, wherein the event generating module comprises:

and the second event generating unit is used for inputting the predicted road condition information of the non-passing road section in the current driving route at the future time into the route refreshing identification model so as to determine whether to generate a route refreshing event or not.

12. The apparatus of claim 11, further comprising:

the route acquisition module is used for acquiring historical driving routes which are driven from a starting point of the current driving route to a terminal point of the current driving route and have the same historical period before inputting the predicted road condition information of the non-passing road section in the current driving route at the future time into the route refreshing identification model;

13. The apparatus of claim 12, wherein the revised elapsed time determination module comprises:

an actual elapsed time determination unit configured to determine an actual travel elapsed time of the historical travel route;

14. An electronic device, characterized in that the device comprises:

one or more processors;

a storage device for storing one or more programs,

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the navigation planning method of any of claims 1-7.

15. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a navigation planning method according to any one of claims 1-7.