CN107045794B - Road condition processing method and device - Google Patents
Road condition processing method and device Download PDFInfo
- Publication number
- CN107045794B CN107045794B CN201710032661.6A CN201710032661A CN107045794B CN 107045794 B CN107045794 B CN 107045794B CN 201710032661 A CN201710032661 A CN 201710032661A CN 107045794 B CN107045794 B CN 107045794B
- Authority
- CN
- China
- Prior art keywords
- congestion
- query
- road condition
- queue
- road
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
- G08G1/0141—Measuring and analyzing of parameters relative to traffic conditions for specific applications for traffic information dissemination
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a road condition processing method and a road condition processing device. The method comprises the following steps: acquiring an identification of a query position requested to be queried by a user and a road condition query moment according to a received road condition query request; detecting whether congestion occurs at the current moment on a road section within a preset distance range around the inquiry position; if the congestion happens, acquiring the congestion occurrence time of a congestion queue including the query position and the starting point of the congestion queue; and determining the road condition state of the query position at the road condition query moment according to the congestion occurrence moment, the road condition query moment, the starting point of the congestion queue and the road condition prediction relation generated in advance. The technical scheme of the invention can make up the defects of the prior art, and when a certain road section is congested, the road condition state of the road section at any time after congestion is predicted, so that a user can determine the road condition at the future time in time, and the upcoming travel is conveniently planned.
Description
[ technical field ] A method for producing a semiconductor device
The present invention relates to the field of navigation technologies, and in particular, to a road condition processing method and apparatus.
[ background of the invention ]
With the development of science and technology, various intelligent electronic devices and applications used in the intelligent electronic devices are greatly convenient for the life of people.
For example, navigation is an application used on an intelligent electronic device, and people can perform path planning through navigation when going out. Specifically, the user may open the navigation and input a destination while out, and the navigation application may plan at least three routes from the user's current location to the destination according to the destination input by the user. Meanwhile, navigation can also accurately provide road conditions on each currently planned route for a user; for example, navigation may indicate the road condition at each location on the route by different colors, such as red for congestion, yellow for slow running, green for clear, and so on.
However, in the navigation application of the prior art, only the road condition of the route at the current time, such as congestion or smooth traffic, can be detected, and when a certain road section is congested, the road condition of the road section at any time after the congestion cannot be predicted.
[ summary of the invention ]
The invention provides a road condition processing method and a road condition processing device, which are used for making up the defects of the prior art and predicting the road condition state of a road section at any time after congestion.
The invention provides a road condition processing method, which comprises the following steps:
acquiring an identification of a query position requested to be queried by a user and a road condition query moment according to a received road condition query request;
detecting whether congestion occurs at the current moment on a road section within a preset distance range around the query position;
if the congestion happens, acquiring the congestion occurrence time of a congestion queue including the query position and a starting point of the congestion queue;
determining the road condition state of the query position at the road condition query moment according to the congestion occurrence moment, the road condition query moment, the starting point of the congestion queue and a road condition prediction relation generated in advance; and the road condition query moment is any moment after the current moment.
Further optionally, in the method, determining the traffic condition state of the query location at the traffic query time according to the congestion occurrence time, the traffic query time, the start point of the congestion queue, and a traffic prediction relationship generated in advance, specifically includes:
determining the congestion duration according to the congestion occurrence time and the road condition query time;
determining the length of the congestion queue according to the congestion occurrence time, the congestion duration and the road condition prediction relation;
and determining the road condition state of the query position at the road condition query moment according to the starting point of the congestion queue, the identifier of the query position and the length of the congestion queue.
Further optionally, in the method, determining the road condition state of the query location at the road condition query time according to the start point of the congestion queue, the identifier of the query location, and the length of the congestion queue specifically includes:
and determining whether the inquiry position is in the congestion queue according to the starting point of the congestion queue, the identifier of the inquiry position and the length of the congestion queue, if so, determining that the road condition state of the inquiry position at the road condition inquiry time is congestion, otherwise, determining that the road condition state of the inquiry position at the road condition inquiry time is smooth.
Further optionally, in the method, before determining the traffic condition state of the query location at the traffic query time according to the congestion occurrence time, the traffic query time, a starting point of the congestion queue, and a traffic prediction relationship generated in advance, the method further includes:
and generating the road condition prediction relation, wherein the road condition prediction relation is a functional relation among the length of the congestion queue, the congestion duration and the congestion occurrence time.
Further optionally, in the method, generating the road condition prediction relationship specifically includes:
mining a plurality of congestion queues from historical road condition data;
acquiring the congestion occurrence time, the congestion duration and the congestion queue length of each congestion queue;
and acquiring the length of the congestion queue, the congestion duration and the functional relation between the congestion occurrence time and the congestion duration through a training model according to the congestion occurrence time, the congestion duration and the congestion queue length of each congestion queue.
Further optionally, in the method, mining a plurality of congestion queues from historical road condition data specifically includes:
determining the identifier of the initial road section of each congestion queue according to the historical road condition data;
for each congestion queue, sequentially acquiring the identifiers of adjacent congestion road sections along the upstream direction from the identifier of the initial road section of the congestion queue to form the congestion queue.
Further optionally, in the method, determining, according to the historical road condition data, an identifier of a start road segment of each congestion queue includes:
acquiring a first congestion transmission probability of a downstream adjacent road section of each road section to the road section according to the historical road condition data;
and taking the identifier of each road section with the first congestion transfer probability smaller than a preset threshold value as the identifier of the starting road section of each congestion queue.
Further optionally, in the method as described above, for each congestion queue, sequentially obtaining, from the identifier of the start road segment of the congestion queue, identifiers of adjacent congestion road segments along an upstream direction, so as to form the congestion queue, specifically, the method includes:
for each congestion queue, taking the starting road section as a current road section, and acquiring a second congestion transfer probability of the current road section to an upstream adjacent road section of the current road section;
judging whether the second congestion transfer probability is greater than or equal to the preset threshold value or not;
if so, determining that the upstream adjacent road section of the current road section is a congested road section;
acquiring an identifier of the congested road section;
and continuing to analyze the upstream adjacent road section of the current road section as the current road section until the second congestion transmission probability of the current road section to the upstream adjacent road section of the current road section is smaller than the preset threshold value, and stringing the identifier of the starting road section and the identifiers of the congestion road sections which are sequentially adjacent along the upstream direction together to form the congestion queue.
Further optionally, in the method, after determining the traffic condition state of the query location at the traffic query time according to the congestion occurrence time, the traffic query time, a starting point of the congestion queue, and a traffic prediction relationship generated in advance, the method further includes:
and sending the road condition state of the query position at the road condition query moment to a client of the user.
The invention also provides a road condition processing device, comprising:
the acquisition module is used for acquiring the identification of the query position requested by the user and the road condition query time according to the received road condition query request;
the detection module is used for detecting whether congestion occurs at the current moment on a road section within a preset distance range around the query position;
the obtaining module is further configured to obtain a congestion occurrence time of a congestion queue including the query location and a starting point of the congestion queue if congestion occurs on a road segment within a preset distance range around the query location;
a determining module, configured to determine a traffic status of the query location at the traffic query time according to the congestion occurrence time, the traffic query time, a starting point of the congestion queue, and a traffic prediction relationship generated in advance; and the road condition query moment is any moment after the current moment.
Further optionally, in the apparatus described above, the determining module is specifically configured to:
determining the congestion duration according to the congestion occurrence time and the road condition query time;
determining the length of the congestion queue according to the congestion occurrence time, the congestion duration and the road condition prediction relation;
and determining the road condition state of the query position at the road condition query moment according to the starting point of the congestion queue, the identifier of the query position and the length of the congestion queue.
Further optionally, in the apparatus as described above, the determining module is specifically configured to determine whether the query location is in the congestion queue according to a starting point of the congestion queue, the identifier of the query location, and a length of the congestion queue, determine that the road condition state of the query location is congested at the road condition query time if yes, and determine that the road condition state of the query location is smooth at the road condition query time if no.
Further optionally, in the apparatus described above, the apparatus further includes:
and the generation module is used for generating the road condition prediction relation, wherein the road condition prediction relation is a functional relation among the length of the congestion queue, the congestion duration and the congestion occurrence time.
Further optionally, in the apparatus described above, the generating module is specifically configured to:
mining a plurality of congestion queues from historical road condition data;
acquiring the congestion occurrence time, the congestion duration and the congestion queue length of each congestion queue;
and acquiring the length of the congestion queue, the congestion duration and the functional relation between the congestion occurrence time and the congestion duration through a training model according to the congestion occurrence time, the congestion duration and the congestion queue length of each congestion queue.
Further optionally, in the apparatus described above, the generating module is specifically configured to:
determining the identifier of the initial road section of each congestion queue according to the historical road condition data;
for each congestion queue, sequentially acquiring the identifiers of adjacent congestion road sections along the upstream direction from the identifier of the initial road section of the congestion queue to form the congestion queue.
Further optionally, in the apparatus described above, the generating module is specifically configured to:
acquiring a first congestion transmission probability of a downstream adjacent road section of each road section to the road section according to the historical road condition data;
and taking the identifier of each road section with the first congestion transfer probability smaller than a preset threshold value as the identifier of the starting road section of each congestion queue.
Further optionally, in the apparatus described above, the generating module is specifically configured to:
for each congestion queue, taking the starting road section as a current road section, and acquiring a second congestion transfer probability of the current road section to an upstream adjacent road section of the current road section;
judging whether the second congestion transfer probability is greater than or equal to the preset threshold value or not;
if so, determining that the upstream adjacent road section of the current road section is a congested road section;
acquiring an identifier of the congested road section;
and continuing to analyze the upstream adjacent road section of the current road section as the current road section until the second congestion transmission probability of the current road section to the upstream adjacent road section of the current road section is smaller than the preset threshold value, and stringing the identifier of the starting road section and the identifiers of the congestion road sections which are sequentially adjacent along the upstream direction together to form the congestion queue.
Further optionally, the apparatus as described above further includes:
and the sending module is used for sending the road condition state of the query position at the road condition query moment to the client of the user. The specific technical scheme is as follows:
according to the road condition processing method and the road condition processing device, the identification of the query position requested by the user and the road condition query time are obtained according to the received road condition query request; detecting whether congestion occurs at the current moment on a road section within a preset distance range around the inquiry position; if the congestion happens, acquiring the congestion occurrence time of a congestion queue including the query position and the starting point of the congestion queue; and determining the road condition state of the query position at the road condition query moment according to the congestion occurrence moment, the road condition query moment, the starting point of the congestion queue and the road condition prediction relation generated in advance. According to the technical scheme, the defects of the prior art can be overcome, and when a certain road section is congested, the road condition state at any time after the road section is congested is predicted, so that a user can determine the road condition at the future time in time, and the upcoming travel is conveniently planned.
[ description of the drawings ]
Fig. 1 is a flowchart of an embodiment of a traffic condition processing method according to the present invention.
Fig. 2 is a structural diagram of a road condition processing device according to a first embodiment of the present invention.
Fig. 3 is a structural diagram of a second traffic processing device according to an embodiment of the present invention.
[ detailed description ] embodiments
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
Fig. 1 is a flowchart of an embodiment of a traffic condition processing method according to the present invention. As shown in fig. 1, the road condition processing method of this embodiment may specifically include the following steps:
100. acquiring an identification of a query position requested to be queried by a user and a road condition query moment according to a received road condition query request;
101. detecting whether congestion occurs at the current moment on a road section within a preset distance range around the inquiry position; if the congestion exists, executing step 102; otherwise, if the position is not blocked, the query position is determined to be unblocked, and the process is finished.
102. Acquiring congestion occurrence time of a congestion queue including a query position and a starting point of the congestion queue; step 103 is executed;
103. and determining the road condition state of the query position at the road condition query moment according to the congestion occurrence moment, the road condition query moment, the starting point of the congestion queue and the road condition prediction relation generated in advance.
The main execution body of the traffic condition processing method of this embodiment is a traffic condition processing device, and the traffic condition processing device can be set in a navigation application and is used for processing a traffic condition when a user requests to query the traffic condition. In the specific implementation, the road condition processing function of the embodiment can be added in the existing navigation application. For example, a button may be added to the navigation interface for receiving a road condition query request from the user.
In this embodiment, the received road condition query request of the user may carry an identifier of a query location, for example, the location is a location where congestion often occurs and the user has to pass through when going out, and the user may query the road condition of the query location before going out. Because the bidirectionality of the road, the same position identifier corresponds to the same query position identifier, the road conditions in two directions may exist, and in this embodiment, the road conditions in two directions can be acquired. In addition, when a certain road is often congested and a user is going out, the road condition state of the road can be inquired, at this time, two inquiry position identifiers can be carried in the road condition inquiry request of the user, and when the user requests for inquiry, which of the two inquiry positions is a starting point and which is a terminal point is also determined. The road condition processing device can acquire the road condition of the section from the starting point to the end point according to the identifiers of the two query positions in the road condition query request of the user, and at the moment, the driving direction of the user is determined without querying the road condition in the opposite direction from the end point to the starting point. In addition, the road condition query request of the user can also carry the road condition query time, and if the user wants to query the road condition at a query position of half an eleventh noon, the road condition query time can be directly carried in the road condition query request. Or if the user does not know the specific road condition query time and only wants to know the road condition 30 minutes after the query position, the user can also carry a time difference of 30 minutes in the road condition query request, so that the road condition processing device can add 30 minutes to determine the time of the road condition query time on the basis of the current time. That is, the road condition query time of this embodiment is any time after the current time.
After the road condition processing device obtains the identifier of the query position and the road condition query time, it can obtain whether congestion occurs at the current time on all road sections within a preset distance range around the query position from the current traffic data. Where traffic data may be detected and uploaded by various traffic data providers. Even if the query position is not congested at the current time, if the user drives in a certain direction and congestion occurs in a preset distance range downstream of the query position in the direction, the congestion may be quickly transmitted to the query position. Therefore, in the embodiment, when the road condition is queried, for the query position on the road passing in the two directions, whether congestion occurs at the current time within the preset distance range of the query position in the two directions can be obtained. And when the query position is the intersection, querying whether the preset distance range in each direction to which the intersection can go is congested. When the user defines two query positions in the query request, determines which query position is the starting point and which query position is the end point, the road condition processing device can determine the driving direction of the user at the moment, and only needs to detect whether congestion occurs at the current moment on the road section within the preset distance range downstream of the end point. The preset distance range of the embodiment may be selected according to an empirical value, for example, the preset distance range may be a longest length of a congestion queue of the road segment in the history when congestion occurs. If the congestion occurs, the road condition processing device may obtain the congestion occurrence time of the congestion queue corresponding to the current congestion, that is, the starting time of the congestion, and the starting point of the congestion queue from the traffic data. Wherein the congestion queue may be represented by an identification of two or more links that are continuously congested. And then, according to the acquired congestion occurrence time, the road condition query time and the starting point of the congestion queue, and by combining the road condition prediction relation generated in advance, the road condition state of the query position at the road condition query time can be determined. The road condition prediction relationship generated in advance in this embodiment may be obtained by training a data model according to congestion data of each time in historical traffic data. The road condition prediction relationship may include a relationship between a congestion occurrence time, a congestion duration, and a length of a congestion queue. Since the road condition query time of this embodiment is any time after the current time, the road condition state of the query position at the road condition query time determined in this embodiment is a predicted road condition state.
In the above-mentioned scheme of this embodiment, the query location is described as a point, and in practical application, the query location may also be a link. That is, according to the road condition query request of the user, the obtained query location may be an identifier of a link. The other implementation manners are the same, and details can be referred to the records of the above embodiments, which are not described herein again.
The road condition status of the embodiment includes congestion or smooth. In particular, congestion states and clear states may be identified based on an average speed of vehicles passing through the query location over a period of time; for example, if the average speed of the vehicle passing through the query location within a period of time, such as 30 minutes, is less than or equal to 10km/h, the corresponding road condition state is considered to be congestion; and if the average speed of the vehicle passing through the inquiry position in 30 minutes is more than 10km/h, the corresponding road condition state is considered to be congestion. In practical applications, other speed thresholds may be selected empirically. Meanwhile, a plurality of speed thresholds can be set to divide a plurality of road condition states, for example, if the average speed of vehicles passing through the query position in 45 minutes is less than or equal to 10km/h, the corresponding road condition state is considered to be congestion; if the average speed of the vehicles passing through the query position in 45 minutes is more than 10km/h and less than or equal to 20km/h, the corresponding road condition state is considered to be micro-congestion; if the average speed of the vehicles passing through the inquiry position in 45 minutes is more than 20km/h and less than or equal to 30km/h, the corresponding road condition state is considered to be slow; if the average speed of the vehicles passing through the inquiry position in 45 minutes is more than 30km/h and less than or equal to 40km/h, the corresponding road condition state is considered to be smooth; and if the average speed of the vehicles passing through the inquiry position in 45 minutes is more than 40km/h, the corresponding road condition state is considered to be smooth, and the like.
According to the road condition processing method, the identification of the query position and the road condition query time requested by the user are obtained according to the received road condition query request; detecting whether congestion occurs at the current moment on a road section within a preset distance range around the inquiry position; if the congestion happens, acquiring the congestion occurrence time of a congestion queue including the query position and the starting point of the congestion queue; and determining the road condition state of the query position at the road condition query moment according to the congestion occurrence moment, the road condition query moment, the starting point of the congestion queue and the road condition prediction relation generated in advance. The technical scheme of this embodiment can make up the not enough of prior art, and when some highway section was blocked up, the road conditions state to this highway section at any moment after blocking up was forecasted for the user can in time confirm the road conditions of future moment, is convenient for plan the trip that will come, therefore the technical scheme of this embodiment can greatly make things convenient for user's trip, improves user's experience degree.
Further optionally, on the basis of the technical solution of the foregoing embodiment, the step 103 "determining the road condition status of the query location at the road condition query time according to the congestion occurrence time, the road condition query time, the starting point of the congestion queue, and the road condition prediction relationship generated in advance" may specifically include the following steps:
(a1) determining congestion duration according to the congestion occurrence time and the road condition query time;
the congestion duration of the embodiment is equal to the time difference obtained by subtracting the congestion occurrence time from the road condition query time, that is, the duration of the congestion from the start to the road condition query time.
(a2) Determining the length of a congestion queue according to the congestion occurrence time, the congestion duration and the road condition prediction relation;
the congestion queue is formed and scattered, and is related to the congestion duration T and the length of the congestion queue. For example, the longer the congestion duration, the greater the probability that the congestion should be dispersed. The shorter the congestion queue is, the easier the congestion is dispersed, and the longer the congestion duration is relatively short; and the longer the congestion queue, the slower the congestion spreads out, and the longer the congestion duration is relatively. The congestion occurrence time is a time at which the congestion starts to occur during the day. The reason why the congestion occurrence time is added is that the congestion modes in the morning, at noon and at night are different, the time required for congestion dispersion is different, and the congestion occurrence time needs to be distinguished.
The predicted road condition relationship in this embodiment can be expressed as L ═ f (T, T), that is, the function f (T, T) of the length L of the congestion queue is a functional relationship between the congestion occurrence time T and the congestion duration T. When the congestion occurrence time T and the congestion duration T are determined, the length L of the congestion queue can be determined.
(a3) And determining the road condition state of the query position at the road condition query moment according to the starting point of the congestion queue, the identifier of the query position and the length of the congestion queue.
Specifically, whether the query position is in the congestion queue or not is determined according to the starting point of the congestion queue, the identifier of the query position and the length of the congestion queue, if so, the road condition state of the query position at the road condition query time is determined to be congested, and if not, the road condition state of the query position at the road condition query time is determined to be unblocked.
For example, the distance from the query position to the congestion queue starting point can be calculated according to the starting point of the congestion queue and the identifier of the query position; and then judging whether the distance is smaller than or equal to the length of the congestion queue, if so, determining that the inquiry position is still in the congestion queue, and the road condition state of the inquiry position is still in congestion at the road condition inquiry moment, otherwise, if the distance is larger than the length of the congestion queue, determining that the inquiry position is not in the congestion queue, which indicates that congestion may be slowly dispersed, and the road condition of the inquiry position is smooth at the road condition inquiry moment.
Further optionally, on the basis of the technical solution of the foregoing embodiment, before step 103 "determining the road condition status of the query location at the road condition query time according to the congestion occurrence time, the road condition query time, the starting point of the congestion queue, and the road condition prediction relationship generated in advance", the method may further include the following steps: and generating a road condition prediction relation, wherein the road condition prediction relation is a functional relation among the length of the congestion queue, the congestion duration and the congestion occurrence time.
For example, generating the road condition prediction relationship may specifically include the following steps:
(b1) mining a plurality of congestion queues from historical road condition data;
(b2) acquiring congestion occurrence time, congestion duration and congestion queue length of each congestion queue;
for example, in this embodiment, n congestion queues are mined from historical road condition data. For each congestion queue, a triplet is then obtained: the congestion occurrence time T, the congestion duration T and the length L of the congestion queue. Thus, the congestion occurrence time T, the congestion duration T, and the length L of the congestion queue of the n congestion queues, such as (L1, T1, T1), (L2, T2, T2), …, (Ln, Tn) are obtained.
(b3) And acquiring the length of the congestion queue, the congestion duration and the functional relation between the congestion occurrence time and the congestion duration of each congestion queue through a training model according to the congestion occurrence time, the congestion duration and the congestion queue length of each congestion queue.
The triplets of the n congestion queues are used as training data for Machine learning, and a Machine learning model (such as a Support Vector Machine (SVM) model or a Gradient Boosting Decision Tree (GBDT) model is used for learning, wherein L _ i is a target value, and T _ i are features.
Further optionally, on the basis of the technical solution of the above embodiment, the step (b1) "mining a plurality of congestion queues from historical road condition data" may specifically include the following steps:
(c1) determining the identifier of the initial road section of each congestion queue according to historical road condition data;
in practical application, congestion of some road sections is not caused by congestion of the road sections ahead, but caused by the fact that the road is narrow and cannot bear excessive traffic flow, and such road sections are the initial road sections of congestion. The determination of the congestion queue mainly determines a starting road segment of the congestion queue, and for example, the determination may be implemented by specifically adopting the following two steps:
(d1) acquiring a first congestion transfer probability of a downstream adjacent road section of each road section to the road section according to historical road condition data;
(d2) and taking the identifier of each road section with the first congestion transfer probability smaller than a preset threshold value as the identifier of the initial road section of each congestion queue.
Specifically, for a link, when the first congestion transfer probability of a link to a link adjacent to the link downstream is smaller than a preset threshold, it indicates that the congestion of the link is not transferred from the link downstream, and at this time, the link may be the starting link of the current congestion queue. In practical application, one downstream Link of the current Link may be taken, or a plurality of links adjacent to the downstream of the current Link may be taken. When a plurality of downstream adjacent links are taken, it is necessary to judge whether the first congestion transfer probability of each downstream adjacent link is smaller than a preset threshold, and when the first congestion transfer probabilities are smaller than the preset threshold, the current link can be used as a starting link of the current congestion queue.
In this embodiment, the congestion state S (link _ i, t _ j) of each link in the road network at all historical times is set to 0or 1. Where 0 indicates that the ith link, i.e., link _ i, is clear at time t _ j, and 1 indicates that the ith link, i.e., link _ i, is congested at time t _ j.
Let the current link be link _ i, and its downstream links be link _ i1, link _ i2, …, and link _ in, respectively. The downstream link in the present embodiment is a downstream link in the traveling direction.
For link _ i, if at a certain time k, S (link _ i, t _ k) is 0, and at a time k +1, S (link _ i, t _ k +1) is 1, it is described that link _ i has a congestion change (congestion is changed from clear to congested), when historical road condition data is analyzed, the total number of congestion changes is count (link _ i) within a certain historical time, and when the current link _ i has a congestion change, a count (link _ i | link _ ij) is counted once for a certain downstream link _ ij of the current link _ i, if S (link _ ij, k +1) is 1, the count (link _ i | link _ ij) indicates that the congestion of the current link _ i is transmitted from the congestion of the downstream link _ ij, and the total number of congestion within the historical time is count (link _ i | link _ ij).
For each downstream link _ ij of the link _ i, a first congestion transfer probability P (link _ i | link _ ij) of the downstream adjacent link _ ij to the current link _ i is calculated from the above statistical values as count (link _ i | link _ ij)/count (link _ i). It means that if the current link i is congested, how likely it is that its downstream link _ ij is in a congested state. I.e., the current link i becomes congested, how likely it is that it is conveyed by the congestion of its downstream link _ ij.
For each downstream link _ ij of link _ i, if P (link _ i | link _ ij) is less than the preset threshold thre, the current link _ i is considered to be the starting link of a congestion queue.
(c2) For each congestion queue, the identifiers of the adjacent congestion sections are sequentially acquired along the upstream direction from the identifier of the initial section of the congestion queue, and the congestion queue is formed.
That is, the congestion queue in this embodiment is formed by arranging the identifiers of a plurality of congestion links that are adjacent in sequence from the identifier of the start link. For example, the step (c2) may specifically include the following steps:
(e1) regarding each congestion queue, taking the initial road section as the current road section;
(e2) acquiring a second congestion transfer probability of the current road section to an upstream adjacent road section of the current road section;
the second congestion transfer probability in this embodiment is calculated in the same manner as the first congestion transfer probability, and details of the related embodiment may be referred to, and are not repeated herein.
(e3) Judging whether the second congestion transfer probability is greater than or equal to a preset threshold value or not; if yes, go to step (e 4); otherwise, performing step (e 6);
(e4) determining that an upstream adjacent road section of the current road section is a congested road section; acquiring and recording the identification of the congested road section; performing step (e 5);
(e5) updating an upstream adjacent road section of the current road section into the current road section; performing step (e 2);
(e6) and stringing the mark of the initial road section and the marks of all the congestion road sections which are sequentially adjacent along the upstream direction together to form a congestion queue.
In this embodiment, when the second congestion transfer probability is greater than or equal to the preset threshold, it indicates that the congestion of the current road section will be transferred to the congestion of the upstream adjacent road section of the current road section. And when the second congestion transfer probability is smaller than the preset threshold value, the congestion of the current road section is represented to be not transferred to the congestion of the upstream adjacent road section of the current road section, and the congestion queue can be considered to be cut off, and at the moment, the congestion queue does not need to be searched upstream continuously.
Further optionally, on the basis of the technical solution of the foregoing embodiment, after "determining the road condition status of the query location at the road condition query time according to the congestion occurrence time, the road condition query time, the starting point of the congestion queue, and the road condition prediction relationship generated in advance" in step 103, "the method may further include: the road condition state of the position inquired at the road condition inquiry moment is sent to the client of the user, so that the road condition state of the position inquired at the road condition inquiry moment is sent to the user in time, the user can conveniently make travel adjustment according to the road condition state of the position inquired at the road condition inquiry moment, congested road sections are avoided, and the use experience of the user is enhanced.
The technical scheme of the embodiment can make up the defects of the prior art, and when a certain road section is congested, the road condition state of the road section at any moment after congestion is predicted, so that the user can determine the road condition at the future moment in time, and the upcoming trip can be planned conveniently.
Fig. 2 is a structural diagram of a road condition processing device according to a first embodiment of the present invention. As shown in fig. 2, the road condition processing device of this embodiment may specifically include: the device comprises an acquisition module 10, a detection module 11 and a determination module 12.
The obtaining module 10 is configured to obtain, according to the received road condition query request, an identifier of a query location and a road condition query time requested by a user; the detection module 11 is configured to detect whether congestion occurs at the current time on a road segment within a preset distance range around the query position acquired by the acquisition module 10; the obtaining module 10 is further configured to obtain a congestion occurrence time of a congestion queue including the query location and a starting point of the congestion queue if the detecting module 11 detects congestion on a road segment within a preset distance range around the query location; the determining module 12 is configured to determine a road condition state of a query location at the road condition query time according to the congestion occurrence time, the road condition query time, a starting point of the congestion queue, and a road condition prediction relationship generated in advance, which are acquired by the acquiring module 10; the road condition query moment is any moment after the current moment.
The traffic condition processing apparatus of this embodiment implements the traffic condition processing by using the modules according to the same implementation principle and technical effect as the related method embodiments, and reference may be made to the description of the related method embodiments in detail, which is not repeated herein.
Fig. 3 is a structural diagram of a second traffic processing device according to an embodiment of the present invention. As shown in fig. 3, the traffic condition processing device of the present embodiment further describes the technical solution of the present invention in more detail based on the technical solution of the embodiment shown in fig. 2.
In the traffic condition processing apparatus of this embodiment, the determining module 12 is specifically configured to:
determining the congestion duration according to the congestion occurrence time and the road condition query time acquired by the acquisition module 10;
determining the length of a congestion queue according to the congestion occurrence time, the congestion duration and the road condition prediction relation;
and determining the road condition state of the query position at the road condition query moment according to the starting point of the congestion queue, the identifier of the query position and the length of the congestion queue.
Further optionally, in the traffic condition processing apparatus of this embodiment, the determining module 12 is specifically configured to determine whether the query location is in the congestion queue according to the start point of the congestion queue, the identifier of the query location, and the length of the congestion queue acquired by the acquiring module 10, if so, determine that the traffic condition of the query location at the time of the traffic condition query is congested, otherwise, determine that the traffic condition of the query location at the time of the traffic condition query is smooth.
Further optionally, as shown in fig. 3, the road condition processing device of this embodiment further includes: a generating module 13.
The generating module 13 is configured to generate a road condition prediction relationship, where the road condition prediction relationship is a functional relationship between the length of the congestion queue, the congestion duration, and the congestion occurrence time.
Further optionally, in the traffic condition processing apparatus of this embodiment, the generating module 13 is specifically configured to:
mining a plurality of congestion queues from historical road condition data;
acquiring congestion occurrence time, congestion duration and congestion queue length of each congestion queue;
and acquiring the length of the congestion queue, the congestion duration and the functional relation between the congestion occurrence time and the congestion duration of each congestion queue through a training model according to the congestion occurrence time, the congestion duration and the congestion queue length of each congestion queue.
Further optionally, in the traffic condition processing apparatus of this embodiment, the generating module 13 is specifically configured to:
determining the identifier of the initial query position of each congestion queue according to historical road condition data;
and for each congestion queue, sequentially acquiring the identifiers of the adjacent congestion query positions along the upstream direction from the identifier of the initial query position of the congestion queue to form the congestion queue.
Further optionally, in the traffic condition processing apparatus of this embodiment, the generating module 13 is specifically configured to:
acquiring a first congestion transfer probability of a downstream adjacent query position of each query position to the query position according to historical road condition data;
and taking the identifier of each inquiry position with the first congestion transfer probability smaller than a preset threshold value as the identifier of the initial inquiry position of each congestion queue.
Further optionally, in the traffic condition processing apparatus of this embodiment, the generating module 13 is specifically configured to:
for each congestion queue, taking the initial query position as the current query position, and acquiring a second congestion transfer probability of the current query position to an upstream adjacent query position of the current query position;
judging whether the second congestion transfer probability is greater than or equal to a preset threshold value or not;
if so, determining that the upstream adjacent query position of the current query position is a congestion query position;
acquiring an identifier of a congestion query position;
and continuously analyzing the upstream adjacent query position of the current query position as the current query position until the second congestion transmission probability of the current query position to the upstream adjacent query position of the current query position is smaller than a preset threshold value, and stringing the identifier of the initial query position and the identifiers of the congestion query positions which are adjacent in sequence along the upstream direction to form the congestion queue.
Correspondingly, in the traffic processing device of this embodiment, the determining module 12 is connected to the generating module 13, and the determining module 12 is configured to determine the traffic state at the query position at the traffic query time according to the congestion occurrence time, the traffic query time, the start point of the congestion queue, and the traffic prediction relationship generated by the generating module 13 in advance, which are acquired by the acquiring module 10.
Further optionally, as shown in fig. 3, the road condition processing device of this embodiment further includes: a sending module 14. The sending module 14 is configured to send the road condition status of the query location at the road condition query time determined by the determining module 12 to the client of the user.
In the embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (18)
1. A road condition processing method is characterized by comprising the following steps:
acquiring an identification of a query position requested to be queried by a user and a road condition query moment according to a received road condition query request; the number of the query positions is one or two;
detecting whether congestion occurs at the current moment on a road section within a preset distance range around the query position;
if the congestion happens, acquiring the congestion occurrence time of a congestion queue including the query position and a starting point of the congestion queue;
determining the length of the congestion queue according to the congestion occurrence time, the road condition query time and a road condition prediction relation generated in advance; determining the road condition state of the query position at the road condition query moment according to the length of the congestion queue, the starting point of the congestion queue and the identifier of the query position; the road condition query moment is any moment after the current moment; the road condition prediction relationship is a functional relationship between the congestion duration and the congestion occurrence time of the length of the congestion queue.
2. The method as claimed in claim 1, wherein determining the traffic status of the query location at the traffic query time according to the congestion occurrence time, the traffic query time, the start point of the congestion queue, and a traffic prediction relationship generated in advance comprises:
determining the congestion duration according to the congestion occurrence time and the road condition query time;
determining the length of the congestion queue according to the congestion occurrence time, the congestion duration and the road condition prediction relation;
and determining the road condition state of the query position at the road condition query moment according to the starting point of the congestion queue, the identifier of the query position and the length of the congestion queue.
3. The method as claimed in claim 2, wherein determining the traffic status of the query location at the traffic query time according to the start point of the congestion queue, the identifier of the query location, and the length of the congestion queue comprises:
and determining whether the inquiry position is in the congestion queue according to the starting point of the congestion queue, the identifier of the inquiry position and the length of the congestion queue, if so, determining that the road condition state of the inquiry position at the road condition inquiry time is congestion, otherwise, determining that the road condition state of the inquiry position at the road condition inquiry time is smooth.
4. The method as claimed in claim 1, wherein before determining the traffic status at the query location at the traffic query time according to the congestion occurrence time, the traffic query time, the start point of the congestion queue, and a traffic prediction relationship generated in advance, the method further comprises:
and generating the road condition prediction relation, wherein the road condition prediction relation is a functional relation among the length of the congestion queue, the congestion duration and the congestion occurrence time.
5. The method according to claim 4, wherein generating the road condition prediction relationship comprises:
mining a plurality of congestion queues from historical road condition data;
acquiring the congestion occurrence time, the congestion duration and the congestion queue length of each congestion queue;
and acquiring the length of the congestion queue, the congestion duration and the functional relation between the congestion occurrence time and the congestion duration through a training model according to the congestion occurrence time, the congestion duration and the congestion queue length of each congestion queue.
6. The method as claimed in claim 5, wherein mining a plurality of congestion queues from historical road condition data comprises:
determining the identifier of the initial road section of each congestion queue according to the historical road condition data;
for each congestion queue, sequentially acquiring the identifiers of adjacent congestion road sections along the upstream direction from the identifier of the initial road section of the congestion queue to form the congestion queue.
7. The method as claimed in claim 6, wherein determining the identifier of the start segment of each congestion queue according to the historical road condition data specifically comprises:
acquiring a first congestion transmission probability of a downstream adjacent road section of each road section to the road section according to the historical road condition data;
and taking the identifier of each road section with the first congestion transfer probability smaller than a preset threshold value as the identifier of the starting road section of each congestion queue.
8. The method according to claim 6, wherein for each congestion queue, sequentially acquiring identifiers of adjacent congestion sections in an upstream direction from an identifier of the start section of the congestion queue to form the congestion queue, specifically comprises:
for each congestion queue, taking the starting road section as a current road section, and acquiring a second congestion transfer probability of the current road section to an upstream adjacent road section of the current road section;
judging whether the second congestion transfer probability is greater than or equal to the preset threshold value or not;
if so, determining that the upstream adjacent road section of the current road section is a congested road section;
acquiring an identifier of the congested road section;
and continuing to analyze the upstream adjacent road section of the current road section as the current road section until the second congestion transmission probability of the current road section to the upstream adjacent road section of the current road section is smaller than the preset threshold value, and stringing the identifier of the starting road section and the identifiers of the congestion road sections which are sequentially adjacent along the upstream direction together to form the congestion queue.
9. The method as claimed in any one of claims 1 to 8, wherein after determining the traffic status at the query location at the traffic query time according to the congestion occurrence time, the traffic query time, the start point of the congestion queue, and a traffic prediction relationship generated in advance, the method further comprises:
and sending the road condition state of the query position at the road condition query moment to a client of the user.
10. A traffic condition processing apparatus, comprising:
the acquisition module is used for acquiring the identification of the query position requested by the user and the road condition query time according to the received road condition query request; the number of the query positions is one or two;
the detection module is used for detecting whether congestion occurs at the current moment on a road section within a preset distance range around the query position;
the obtaining module is further configured to obtain a congestion occurrence time of a congestion queue including the query location and a starting point of the congestion queue if congestion occurs on a road segment within a preset distance range around the query location;
the determining module is used for determining the length of the congestion queue according to the congestion occurrence time, the road condition query time and a road condition prediction relation generated in advance; determining the road condition state of the query position at the road condition query moment according to the length of the congestion queue, the starting point of the congestion queue and the identifier of the query position; the road condition query moment is any moment after the current moment; the road condition prediction relationship is a functional relationship that the length of the congestion queue changes along with the congestion duration and the congestion occurrence time.
11. The apparatus of claim 10, wherein the determining module is specifically configured to:
determining the congestion duration according to the congestion occurrence time and the road condition query time;
determining the length of the congestion queue according to the congestion occurrence time, the congestion duration and the road condition prediction relation;
and determining the road condition state of the query position at the road condition query moment according to the starting point of the congestion queue, the identifier of the query position and the length of the congestion queue.
12. The apparatus according to claim 11, wherein the determining module is specifically configured to determine whether the query location is in the congestion queue according to a start point of the congestion queue, an identifier of the query location, and a length of the congestion queue, determine that the road condition status of the query location is congested at the time of the road condition query if the query location is in the congestion queue, and determine that the road condition status of the query location is unblocked at the time of the road condition query if the query location is not in the congestion queue.
13. The apparatus of claim 10, further comprising:
and the generation module is used for generating the road condition prediction relation, wherein the road condition prediction relation is a functional relation among the length of the congestion queue, the congestion duration and the congestion occurrence time.
14. The apparatus of claim 13, wherein the generating module is specifically configured to:
mining a plurality of congestion queues from historical road condition data;
acquiring the congestion occurrence time, the congestion duration and the congestion queue length of each congestion queue;
and acquiring the length of the congestion queue, the congestion duration and the functional relation between the congestion occurrence time and the congestion duration through a training model according to the congestion occurrence time, the congestion duration and the congestion queue length of each congestion queue.
15. The apparatus of claim 14, wherein the generating module is specifically configured to:
determining the identifier of the initial road section of each congestion queue according to the historical road condition data;
for each congestion queue, sequentially acquiring the identifiers of adjacent congestion road sections along the upstream direction from the identifier of the initial road section of the congestion queue to form the congestion queue.
16. The apparatus of claim 15, wherein the generating module is specifically configured to:
acquiring a first congestion transmission probability of a downstream adjacent road section of each road section to the road section according to the historical road condition data;
and taking the identifier of each road section with the first congestion transfer probability smaller than a preset threshold value as the identifier of the starting road section of each congestion queue.
17. The apparatus of claim 15, wherein the generating module is specifically configured to:
for each congestion queue, taking the starting road section as a current road section, and acquiring a second congestion transfer probability of the current road section to an upstream adjacent road section of the current road section;
judging whether the second congestion transfer probability is greater than or equal to the preset threshold value or not;
if so, determining that the upstream adjacent road section of the current road section is a congested road section;
acquiring an identifier of the congested road section;
and continuing to analyze the upstream adjacent road section of the current road section as the current road section until the second congestion transmission probability of the current road section to the upstream adjacent road section of the current road section is smaller than the preset threshold value, and stringing the identifier of the starting road section and the identifiers of the congestion road sections which are sequentially adjacent along the upstream direction together to form the congestion queue.
18. The apparatus of any of claims 10-17, further comprising:
and the sending module is used for sending the road condition state of the query position at the road condition query moment to the client of the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710032661.6A CN107045794B (en) | 2017-01-16 | 2017-01-16 | Road condition processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710032661.6A CN107045794B (en) | 2017-01-16 | 2017-01-16 | Road condition processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107045794A CN107045794A (en) | 2017-08-15 |
| CN107045794B true CN107045794B (en) | 2021-09-21 |
Family
ID=59543293
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710032661.6A Active CN107045794B (en) | 2017-01-16 | 2017-01-16 | Road condition processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107045794B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109945879A (en) * | 2017-12-20 | 2019-06-28 | 上海博泰悦臻网络技术服务有限公司 | Guidance path control method, system, navigation terminal and storage medium |
| CN108399778A (en) * | 2018-05-08 | 2018-08-14 | 深圳市易成自动驾驶技术有限公司 | Swarm intelligence congestion reminding method, system and computer readable storage medium |
| CN111681432B (en) * | 2020-04-30 | 2022-03-29 | 大连理工大学 | Method and device for determining congestion source of intersection containing signal lamp |
| CN112530163B (en) * | 2020-11-23 | 2022-03-01 | 腾讯科技（深圳）有限公司 | Traffic accident prediction method, traffic accident prediction device, electronic device, and storage medium |
| CN114512001B (en) * | 2022-01-14 | 2024-04-26 | 阿里巴巴创新公司 | Regional traffic monitoring method, device, electronic equipment, medium and program product |
| CN115273513B (en) * | 2022-07-23 | 2023-06-13 | 宁波市杭州湾大桥发展有限公司 | Expressway early warning information representation method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103632546A (en) * | 2013-11-27 | 2014-03-12 | 中国航天系统工程有限公司 | Floating car data-based urban road traffic accident influence prediction method |
| CN104240500A (en) * | 2014-08-25 | 2014-12-24 | 奇瑞汽车股份有限公司 | Road condition information predicting method and system |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3007019B2 (en) * | 1995-04-07 | 2000-02-07 | 三菱電機株式会社 | Traffic flow measurement device |
| JP2004094444A (en) * | 2002-08-30 | 2004-03-25 | Tokio Marine Research Institute | Information processing method for preventing traffic accident |
| DE602004002048T2 (en) * | 2003-07-30 | 2007-02-22 | Pioneer Corp. | Device, system and method for signaling the traffic situation |
| US8798897B2 (en) * | 2010-11-01 | 2014-08-05 | International Business Machines Corporation | Real-time traffic analysis through integration of road traffic prediction and traffic microsimulation models |
| CN102353380A (en) * | 2011-06-30 | 2012-02-15 | 福建慧翰信息技术有限公司 | Road condition prediction and query system and method |
| CN102436753A (en) * | 2011-10-12 | 2012-05-02 | 北京世纪高通科技有限公司 | Method and device for issuing real-time traffic information |
| CN102568194B (en) * | 2011-12-26 | 2014-06-11 | 浙江工业大学 | Method for predicting congestion duration and spatial diffusion of urban road traffic |
| CN103245347B (en) * | 2012-02-13 | 2015-11-25 | 腾讯科技（深圳）有限公司 | Based on intelligent navigation method and the system of road condition predicting |
| US9255809B2 (en) * | 2012-03-30 | 2016-02-09 | Global Eagle Entertainment Inc. | System and method for integrated trip planning based on fixed and flexible itinerary components |
| CN103488893B (en) * | 2013-09-23 | 2017-02-15 | 北京交通发展研究中心 | Forecasting technical scheme for traffic congestion spreading caused by waterlogging under bridge |
| CN103839411B (en) * | 2014-03-20 | 2016-03-02 | 中国航天系统工程有限公司 | A kind of accident impact surface analysis method based on dynamic information |
| CN104778835B (en) * | 2015-03-17 | 2017-01-18 | 同济大学 | High-grade road multi-bottleneck-point congestion evolution space-time range identification method |
| CN105849790B (en) * | 2015-10-16 | 2020-10-09 | 华为技术有限公司 | Road condition information acquisition method |
| CN106327881A (en) * | 2016-10-19 | 2017-01-11 | 安徽四创电子股份有限公司 | Traffic jam time calculation method for transition road segment |
-
2017
- 2017-01-16 CN CN201710032661.6A patent/CN107045794B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103632546A (en) * | 2013-11-27 | 2014-03-12 | 中国航天系统工程有限公司 | Floating car data-based urban road traffic accident influence prediction method |
| CN104240500A (en) * | 2014-08-25 | 2014-12-24 | 奇瑞汽车股份有限公司 | Road condition information predicting method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107045794A (en) | 2017-08-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107045794B (en) | Road condition processing method and device | |
| US10642268B2 (en) | Method and apparatus for generating automatic driving strategy | |
| CN110100271B (en) | Method and apparatus for estimating road traffic conditions using traffic signal data | |
| US11597395B2 (en) | Systems and methods to manage vehicles under anomalous driving behavior | |
| EP2255349B1 (en) | Driving support device, driving support method, and driving support program | |
| US20160373896A1 (en) | Management of moving objects | |
| US20180365999A1 (en) | System and method for collision avoidance | |
| US10198941B2 (en) | Method and apparatus for evaluating traffic approaching a junction at a lane level | |
| JP2016201051A (en) | Vehicle information processor, and vehicle information processing program | |
| CN108932470B (en) | Image processing system, image processing method, information processing apparatus, and recording medium | |
| EP3667638A1 (en) | Traffic lane information management method, running control method, and traffic lane information management device | |
| JP2018136934A (en) | System and method for driver's profiling according to vehicle driving | |
| CN107111938B (en) | Server, system and method for determining congestion end position | |
| CN104875740B (en) | For managing the method for following space, main vehicle and following space management unit | |
| JP5907249B2 (en) | Unexpected prediction sensitivity judgment device | |
| JP5378002B2 (en) | Vehicle motion estimation device, vehicle motion estimation method, and vehicle motion estimation program | |
| CN112885112B (en) | Vehicle driving detection method, vehicle driving early warning method and device | |
| CN107957267B (en) | Method and device for determining navigation path prompt information | |
| CN105185117A (en) | Road travel time predicting method, system, and device | |
| Liu et al. | A novel method for predicting vehicle state in internet of vehicles | |
| RU2664034C1 (en) | Traffic information creation method and system, which will be used in the implemented on the electronic device cartographic application | |
| JP2020009189A (en) | Congestion state specifying method, congestion state specifying device, and computer program | |
| JP4572944B2 (en) | Driving support device, driving support method, and driving support program | |
| JP2018147037A (en) | Traffic information management system, traffic information guidance system, and program | |
| CN110197583B (en) | Method and device for identifying road conditions and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |