CN110782659B

CN110782659B - Road condition determining method, road condition determining device, server and storage medium

Info

Publication number: CN110782659B
Application number: CN201910848998.3A
Authority: CN
Inventors: 谢圣山
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2019-09-09
Filing date: 2019-09-09
Publication date: 2021-06-01
Anticipated expiration: 2039-09-09
Also published as: CN110782659A

Abstract

The application discloses a road condition determining method, a road condition determining device, a server and a storage medium, which are applied to an electronic map system which needs to provide road condition information, such as maps, navigation and the like, wherein the method comprises the following steps: under the condition that the current road condition of a road section in a map is identified as a congestion state, acquiring target historical road condition statistical data associated with a target time period to which the current time of the road section belongs; determining the possible degree of the congestion state which is wrongly identified as the congestion state based on the statistical data of the target historical road conditions and the real-time vehicle state information of the vehicles in the road section; and under the condition that the congestion state is mistakenly identified as the congestion state, determining the road condition information to be issued corresponding to the road section based on the real-time vehicle state information of the non-abnormal vehicles in the road section, so that the terminal can display a map or navigation containing the road condition information of the road section. According to the scheme, the accuracy of the road condition determined and issued by the electronic map system can be improved.

Description

Road condition determining method, road condition determining device, server and storage medium

Technical Field

The present application relates to the field of map technologies, and in particular, to a method, an apparatus, a server, and a storage medium for determining a road condition.

Background

The electronic map system can provide real-time road condition information of different road sections for a user, so that the user can conveniently and timely know the passing conditions of the different road sections.

The electronic map system can analyze road condition information of a road according to vehicle state information such as vehicle speed, vehicle position and the like reported by a vehicle-mounted device on a vehicle running on the road. However, various abnormal factors such as abnormal traffic flow speed of vehicles on the road (for example, the vehicle speed is too low due to abnormal vehicle behavior) or vehicle movement track matching errors often cause the electronic map system to incorrectly identify an uncongested road segment as a congested road segment, thereby causing the road condition issued by the electronic map system to be incorrect.

Disclosure of Invention

In view of this, the present application provides a traffic information determining method, apparatus, server and storage medium, and detects and corrects traffic information that is erroneously identified as a congestion state in time, so as to reduce the situation of erroneously issuing traffic information.

To achieve the above object, in one aspect, the present application provides a road condition determining method, including:

under the condition that the current road condition of the road section is identified as a congestion state, acquiring target historical road condition statistical data associated with a target time period to which the current time belongs from the historical road condition statistical data of the road section;

determining the possible degree of the congestion state which is wrongly identified as the congestion state based on the target historical road condition statistical data and the real-time vehicle state information of the vehicles in the road section;

and under the condition that the congestion state is represented by the possible degree and is wrongly identified as the congestion state, determining road condition information to be issued corresponding to the road section based on real-time vehicle state information of non-abnormal vehicles in the road section, wherein the non-abnormal vehicles are vehicles with the vehicle speed not lower than a congestion vehicle speed threshold value corresponding to the road section in the road section, and the congestion vehicle speed threshold value is a vehicle speed critical value representing that the road condition of the road section enters the congestion state.

In a possible implementation manner, the target historical traffic statistics data at least includes: the target time interval is associated with at least one associated time interval, and the at least one associated time interval at least comprises the target time interval;

the determining the congestion status as the possible degree of the congestion status incorrectly identified based on the target historical traffic statistics and the real-time vehicle status information of the vehicles in the road segment includes:

for each historical road condition state, determining the comprehensive occurrence probability of the historical road condition state corresponding to the road section based on the historical occurrence probability of the historical road condition state corresponding to the road section in the at least one associated time period;

and determining the possible degree of the congestion state which is wrongly identified as the congestion state according to the comprehensive occurrence probability of each historical road condition state and the real-time vehicle state information of the vehicles in the road section.

In yet another possible implementation manner, the determining, according to the integrated occurrence probability of each of the historical road condition states and the real-time vehicle state information of the vehicles in the road segment, how likely the congestion state belongs to the congestion state that is erroneously identified includes:

acquiring real-time vehicle state information of vehicles in the road section, wherein the real-time vehicle state information comprises: the vehicle speed and the total number of vehicles of each vehicle currently present in the road segment;

determining a vehicle sample sufficiency index according to the total number of the vehicles and a set sample number constant;

determining the proportion of the congested vehicles with the vehicle speed lower than the congestion vehicle speed threshold according to the vehicle speed of each vehicle in the road section and the congestion vehicle speed threshold corresponding to the road section;

respectively determining the speed index of each vehicle according to the vehicle speed of each vehicle in the road section, the congestion vehicle speed threshold and the severe congestion vehicle speed threshold, wherein the speed index of each vehicle is used for representing the possibility of abnormality of the speed of the vehicle in the road section;

determining a speed index sum of speed indexes of all vehicles in the road section based on the speed indexes of all vehicles;

determining a congestion index as a product of the sum of the speed indexes and a ratio of the congested vehicle;

and according to a set weight relationship, carrying out weighted summation on the comprehensive occurrence probability of each historical road condition state, the vehicle sample sufficiency index, the occupation ratio of the congested vehicle and the congestion index to obtain a misrecognition index, wherein the misrecognition index is used for representing the possible degree of the congestion state which is mistakenly recognized as the congestion state.

In another aspect, the present application further provides a traffic determination device, including:

the data acquisition unit is used for acquiring target historical road condition statistical data associated with a target time period to which the current time belongs from the historical road condition statistical data of the road section under the condition that the current road condition of the road section is identified as a congestion state;

an error analysis unit, configured to determine, based on the target historical traffic statistics and real-time vehicle status information of vehicles in the road segment, a likely degree to which the congestion state belongs to a congestion state that is erroneously identified;

and the road condition weight calculation unit is used for determining road condition information to be issued corresponding to the road section based on real-time vehicle state information of non-abnormal vehicles in the road section under the condition that the congestion state is represented by the possible degree and is wrongly identified as the congestion state, wherein the non-abnormal vehicles are vehicles with the vehicle speed not lower than a congestion vehicle speed threshold value corresponding to the road section in the road section, and the congestion vehicle speed threshold value is a vehicle speed critical value representing that the road condition of the road section enters the congestion state.

In another aspect, the present application further provides a server, including:

a processor and a memory;

the processor is used for calling and executing the memory

A stored program;

the memory is configured to store the program, the program at least to:

In another aspect, the present application further provides a storage medium, where computer-executable instructions are stored, and when the computer-executable instructions are loaded and executed by a processor, the method for determining a road condition as described in any one of the above embodiments is implemented.

According to the technical scheme, under the condition that the server of the electronic map system identifies that the road condition of the current road section is in the congestion state, the identified road section is not taken as the road condition to be issued, and the possibility degree that the congestion state of the road section is identified as the false identification can be analyzed according to the target historical road condition statistical data associated with the road section and the target time period to which the current time belongs and the real-time vehicle state information of the vehicles in the road section. If the situation that the current identified road condition of the road section is the congestion state is determined to belong to the false identification, the situation shows that some non-abnormal vehicles with the vehicle speed not lower than the congestion vehicle speed threshold corresponding to the road section in the road section can be used for re-determining the road condition of the road section due to the fact that the vehicle speed is too low due to the self abnormality of the vehicles, so that the accurate road condition corresponding to the road section can be obtained, therefore, the accurate road condition is used as the road condition information to be issued, the false road condition information can be corrected before the server issues the road condition information, and the accuracy of the issued road condition is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on the provided drawings without creative efforts.

Fig. 1 is a schematic diagram illustrating a structure of a system architecture to which a traffic condition determining method of the present application is applied;

fig. 2 is a schematic flow chart illustrating an embodiment of a road condition determining method according to the present application;

fig. 3 is a schematic flow chart illustrating a process of determining a possibility of the road condition being incorrectly identified according to the road condition determining method of the present application;

FIG. 4 is a schematic flow chart illustrating a process for determining historical occurrence probability of historical road condition status according to the present application;

FIG. 5 is a schematic diagram illustrating an implementation principle of determining a historical occurrence probability of a historical road condition state;

fig. 6 is a schematic flow chart illustrating a further embodiment of a road condition determining method according to the present application;

fig. 7 is a schematic structural diagram illustrating a structure of a road condition determining apparatus according to an embodiment of the present disclosure;

fig. 8 is a schematic diagram illustrating a structure of a server to which a traffic condition determining method according to the present application is applied.

Detailed Description

The road condition determining method is suitable for electronic map systems such as maps and navigation systems and the like which need to provide road condition information, and therefore accuracy of the road condition determined and issued by the electronic map systems is improved.

For convenience of understanding, a system architecture to which the road condition determining method of the embodiment of the present application is applied is introduced first. As shown in fig. 1, fig. 1 is a schematic diagram illustrating a system architecture to which the road condition determining method of the present application is applied.

In fig. 1 the system architecture may include: at least one server 101 for determining traffic conditions, which may be a server in an electronic map system providing traffic information. The electronic map system can be a navigation system, a map providing system and other related systems capable of providing road condition information.

The server 101 may be connected to a plurality of terminals 102 via a network. The terminal 102 may be installed with an application program capable of establishing a communication connection with the server 101, such as a navigation application or a map application, and the like. For example, the terminal may be a mobile phone, a tablet computer, or a vehicle-mounted terminal installed with applications such as navigation or maps.

It is understood that the server may also be connected to the in-vehicle device 103 through a network, and the in-vehicle device may be connected to the server 101. The vehicle-mounted device 103 may provide the server with real-time status information of the vehicle in which the vehicle-mounted device is located, such as vehicle speed, vehicle position, and the like. For example, the in-vehicle device may provide the server with real-time GPS information of the vehicle.

It should be noted that, in fig. 1, the server 101 may obtain vehicle state information such as GPS information reported by the vehicle-mounted device as an example, and in actual application, the server may obtain state information of vehicles on different roads through a third-party server.

In this embodiment, the server 101 may determine and publish the road condition corresponding to each road segment in the map. The terminal can acquire the road condition information of each road section released by the server according to the requirement, and display a map or navigation containing the road condition information of the road section.

With the above, the road condition determining method of the present application is introduced below.

As shown in fig. 2, which is a schematic flow chart illustrating an embodiment of the traffic status determining method according to the present application, the method of the present embodiment may be applied to the aforementioned server. The method of the embodiment may include:

s201, under the condition that the current road condition of the road section is identified as a congestion state, obtaining target historical road condition statistical data associated with the target time period to which the current time belongs from the historical road condition statistical data of the road section.

Here, a link may be understood as a mapping of a real road in a virtual road network such as an electronic map. Each road segment represents an actual segment of the actual road.

The road condition of the road section is description of the traffic capacity of the road represented by the road section. The road conditions of the road section may include: congestion state, slow-moving state, clear state, etc. Of course, some will subdivide the congestion status of a road segment into congestion and heavy congestion.

In the embodiment of the application, when the server calculates that the road section of a road section is in a congestion state, the server does not directly release the road condition of the road section, and determines whether the road condition of the road section has an identification error before the release. In this embodiment, it is determined whether the current road condition of the road segment is a congestion state or not, and the current road condition is a recognition error, which needs to be based on historical road condition statistical data associated with a target time period to which the road segment belongs at the current time.

The historical traffic statistic data associated with the road section is data used for reflecting traffic conditions or traffic condition trends of the road section at different time intervals in a day.

It can be understood that, for a section of road, the difference of the traffic capacity of the section may be different in different time periods of the day, and therefore, whether the congestion state identified at the current time is wrong or not needs to be analyzed by combining the historical traffic statistical data of the section in the same time period as the current time in history. The duration of each time interval can be set according to needs, and when the duration of the time intervals is small enough, one time interval can be regarded as one moment. Optionally, the duration of each time interval should be greater than 1 minute, e.g., every 30 minutes can be divided into one time interval, e.g., one time interval from eight to eight o 'clock in the morning and another time interval from eight to nine o' clock in the morning.

For the convenience of distinguishing, the time period to which the current time belongs is referred to as a target time period, and the historical traffic information related to the target time period is referred to as target historical traffic information.

The historical traffic statistic data associated with the road section may be data obtained based on historical traffic statistics of the road section at the current time or before the current day to which the current time belongs; or may be data statistically obtained based on historical road section status data of the road section at the current time or outside the current day, where the historical road section status data may be status data that is the same as the historical road condition of the road section, for example, the historical road section status data may be the vehicle speeds of different vehicles on the road section, or the historical average vehicle speed of the vehicles on the road section, and the like.

For example, in one possible implementation, the historical traffic statistics associated with the road segment may include: the historical occurrence probability of each of the at least one historical road condition state associated with the road segment. The historical road condition state of the road section is the road condition state at the current moment or before the current day. Such as the probability of occurrence of a historical congestion state associated with the road segment. The historical occurrence probability of the historical road condition state can be calculated by taking the ratio of the occurrence frequency of the historical road condition state of the road section to the total occurrence frequency of various historical road condition states within a period of time.

Correspondingly, the historical traffic statistics associated with the target time interval may be: and the historical occurrence probability of at least one historical road condition state corresponding to each relevant time period relevant to the target time period of the road section. The target time period is associated with at least one associated time period, the at least one associated time period including at least the target time period.

Optionally, the at least one association period may further include: at least one period immediately preceding the target period, and at least one period immediately following the target period. For example, the target historical traffic statistics associated with the target time period may include: and the historical occurrence probability of the historical congestion states of the road section corresponding to the target time interval, the two latest time intervals before the target time interval and the two latest time intervals after the target time interval.

In yet another possible scenario, the historical traffic statistics associated with the road segment may include: historical expected speeds and/or historical expected road conditions associated with the road segments at various time periods.

The historical expected speed of each time period can be an average speed determined based on the historical vehicle speeds of the vehicles in the time period. It will be appreciated that the higher the historical expected speed, the lower the likelihood that the road segment will be congested during that time period.

The historical expected road condition of each time period may be a predicted road condition expectation of the road segment in the time period based on a plurality of historical road conditions obtained by the road segment in the time period. Accordingly, in the case that the historical expected road condition is slow running or smooth, the probability that the road condition of the road section is in a congestion state in the time period is lower.

Optionally, a type attribute of the current day to which the current time belongs may be determined, where the type attribute represents that the current day is a working day or a non-working day, and of course, the non-working day may be further divided into a double holiday and a holiday. If the current day is Tuesday and does not belong to holidays, the type attribute of the current day is weekday. Accordingly, the target historical traffic information corresponding to the type attribute of the current day and associated with the target time period to which the current time belongs may be determined from the historical traffic information associated with the road section.

It can be understood that the road conditions of the same road section in the same time period of the working day, the double holidays and the holidays are greatly different, for example, the road section is relatively congested in the morning from eight o 'clock to eight o' clock of the working day, and is relatively smooth in the morning from eight o 'clock to eight o' clock of the double holidays. Therefore, in order to more reasonably analyze the possibility that the congestion status of the road segment is recognized as a wrong identification, the matching target historical road condition statistical data needs to be obtained from the historical road condition statistical data by combining the type of the current day and the time period of the current time.

S202, determining the possible degree of the congestion state which is wrongly identified as the congestion state based on the target historical road condition statistical data and the real-time vehicle state information of the vehicles in the road section.

The real-time vehicle state of the vehicle in the road section can reflect the vehicle driving state of each vehicle on the road section currently. For example, the real-time vehicle state may include: the position, speed, and total number of vehicles on the road segment, etc.

The inventor of the present application found through research that: in the case where the congestion condition of the road section is determined based on the vehicle states such as the vehicle speeds of the respective vehicles on the road section, it is easy to cause a traffic condition recognition error due to the occurrence of an abnormal traffic flow speed. The abnormal traffic flow speed is usually a speed value which is too low due to abnormal vehicle behaviors, for example, there are few vehicles on a road section, and the vehicles are stopped or the running speed is too slow due to non-road conditions, so that the server may misjudge that the road section is in a congestion state.

Meanwhile, the inventor of the application discovers that the condition of abnormal traffic flow speed of the road section can be obtained by comprehensively analyzing the real-time vehicle state information of the road section, and further, the condition of whether the road condition of the road section identified as the congestion state has the identification error or not can be analyzed.

As an alternative, the real-time vehicle status of the vehicle on the road segment at least comprises: the speed of each vehicle on the road segment and the total number of vehicles on the road segment. The vehicle on the road section is a vehicle corresponding to a data source which can be detected on the road section and is required for analyzing the road condition.

Correspondingly, the vehicle sample sufficiency of the vehicle sample for analyzing the road condition on the road section can be analyzed based on the total number of the vehicles on the road section; and meanwhile, determining the proportion of the congested vehicles with the vehicle speed lower than the congested vehicle speed threshold corresponding to the road section by combining the speeds of all the vehicles on the road section, wherein the congested vehicle speed threshold corresponding to the road section represents the vehicle speed critical value of the road condition of the road section entering the congested state. In this case, the possibility that the road condition of the road section is erroneously identified as the congestion state can be determined according to parameters of multiple dimensions such as the sufficiency of the vehicle sample, the occupation ratio of the congested vehicles, and the speed of each vehicle on the road section.

On the basis, the target historical road condition statistical data can reflect the possibility of the road congestion condition occurring in the target time period to which the road section belongs at the current moment, so that the possible degree of the road condition of the road section being wrongly identified as the congestion condition can be reflected by comprehensively analyzing by combining the target historical road condition statistical data and the real-time vehicle state information.

Wherein the degree of likelihood can be characterized in various forms such as a grade, a probability value, and the like.

And S203, under the condition that the possible degree represents that the congestion state belongs to the congestion state which is identified by mistake, determining road condition information to be issued corresponding to the road section based on the real-time vehicle state information of the non-abnormal vehicles in the road section.

The non-abnormal vehicle is a vehicle with a vehicle speed in the road section not lower than the congestion vehicle speed threshold corresponding to the road section, and as can be known from the foregoing, the congestion vehicle speed threshold is a vehicle speed critical value representing that the road condition of the road section enters the congestion state.

It can be understood that, in the case that it is determined that the road condition of the road section is incorrectly identified as the congested state, it is indicated that the road condition is incorrectly identified due to congested vehicles with too low vehicle speeds in the road section, in this case, the server may remove the vehicle state corresponding to the congested vehicle, and only adopt the real-time vehicle state of non-abnormal vehicles other than the congested vehicles, to re-determine the road condition of the road section, and use the re-determined road condition as the road condition to be released, so that the road condition can be released after being corrected in addition to the road condition.

The road condition to be published may be understood as the road condition that can be transmitted to each terminal requesting the road condition, that is, the road condition of the finally determined road section. Optionally, after the step S203, the road condition information to be issued may also be issued.

Accordingly, if the congestion status is not erroneously identified as the congestion status according to the possible degree, the step S203 is not required to be performed, and the road condition of the road section determined in the step S201 as the congestion status is determined as the road condition to be issued corresponding to the road section. Furthermore, the information that the road condition of the road section is in a congestion state can be published.

It can be seen that, in this embodiment, when the server providing the traffic information identifies that the traffic of the current road segment is in the congestion state, the identified road segment is not taken as the traffic to be released, and the possibility that the congestion state of the road segment is identified as the erroneous identification is analyzed according to the target historical traffic statistical data associated with the road segment and the target time period to which the current time belongs and the real-time vehicle state information of the vehicle in the road segment.

If the situation that the current identified road condition of the road section is the congestion state is determined to belong to the false identification, the situation shows that some non-abnormal vehicles with the vehicle speed not lower than the congestion vehicle speed threshold corresponding to the road section in the road section can be used for re-determining the road condition of the road section due to the fact that the vehicle speed is too low due to the self abnormality of the vehicles, so that the accurate road condition corresponding to the road section can be obtained, therefore, the accurate road condition is used as the road condition information to be issued, the false road condition information can be corrected before the server issues the road condition information, and the accuracy of the issued road condition is improved.

It can be understood that determining the possible degree of the road condition of the road section being incorrectly identified as the congestion state requires calculation of parameters of multiple dimensions, and the calculation requires consumption of certain calculation resources and requires a certain time duration; in many cases, the traffic condition of the road section may not be recognized by mistake if the traffic condition is determined to be the congestion state, and therefore, before determining the congestion state as the possible degree of being recognized by mistake as the congestion state, it may be predicted whether the traffic condition of the road section is the congestion state or not.

Specifically, whether the current road condition of the road section has a risk of being mistakenly identified as a congestion state or not can be detected according to the target historical road condition statistical data and the set misjudgment identification condition. It can be understood that the target historical traffic statistics data may reflect the specific situation of the historical traffic within the target time period to which the road segment belongs at the current time, and therefore, based on the target historical traffic statistics data, the probability that the congestion state occurs in the target time period in the road segment may be analyzed, and if the probability is lower than a set threshold, it may be considered that the congestion state occurring in the road segment may be caused by the false recognition, so that it is determined that the currently recognized congestion state has a risk of being recognized by the false recognition.

Correspondingly, under the condition that the traffic condition of the road section is detected to be the congestion state and the risk of being recognized by mistake exists, the probability degree that the congestion state belongs to the congestion state recognized by mistake is determined based on the target historical traffic condition statistical data and the real-time vehicle state information of the vehicles in the road section.

In a possible implementation manner, the target historical traffic statistics data at least includes: and the historical occurrence probability of each at least one historical road condition state corresponding to the road section in the target time period. Under the condition, whether the current road condition of the road section has the risk of being mistakenly identified as the congestion state or not can be detected according to the respective historical occurrence probability of the at least one historical road condition state and the risk judgment condition between each historical road condition state and the set risk threshold value.

For example, the target historical traffic statistics include: for example, if the historical occurrence probability of the historical congestion state of the road segment in the target time interval is smaller than a set threshold, it indicates that the probability of congestion of the road segment in the target time interval is extremely low, and therefore, if the road segment is currently identified as a congestion state, there is a risk of misrecognition, and a possible degree of misrecognition needs to be further analyzed.

For another example, the statistical data of the target historical road condition is as follows: for example, if the historical occurrence probability of the road section in the smooth state in the target time period is greater than a set threshold, it indicates that the probability of congestion of the road section is very low, and the current road section is identified as a congested state, so that a risk of misidentification exists.

For another example, if the target historical traffic statistic data: the historical occurrence probability of the historical congestion state and the historical occurrence probability of the historical unblocked state of the road section in the target time interval (of course, the historical occurrence probability of the annular state and the like can also be included), if the historical occurrence probability of the historical congestion state is lower than a first set threshold, whether the historical occurrence probability of the historical unblocked state is greater than a second set threshold or not can be further determined, and whether the congestion state of the road section is in a risk of being identified by mistake or not can be judged.

In yet another possible scenario, the target historical traffic statistics may include: the historical expected speed of the road segment over the target time period may be an average of the vehicle speeds of the road segment over the target time period. Then if the historical expected speed is higher than the set threshold, the probability of congestion occurring for the road segment is also relatively low, so if the road segment is currently identified as being congested, it can be confirmed that there is a risk of misidentification.

Of course, the manner of determining whether there is a risk of misidentification is similar to the case where the target historical traffic statistical data is other traffic related data corresponding to the road segment in the target time period, and details thereof are not repeated herein.

In order to facilitate understanding of a specific implementation process for determining that the congestion state belongs to the probability degree of being identified by mistake, the following historical traffic statistical data associated with the road section are taken as follows: the historical occurrence probability of at least one historical road condition state corresponding to each time period of the road section is taken as an example for explanation.

For example, referring to fig. 3, which shows a flowchart of an implementation manner of determining a possible degree of the congestion state being erroneously identified as the congestion state in the road condition determining method of the present application, the embodiment may include:

s301, for each historical road condition state, determining the comprehensive occurrence probability of the historical road condition state corresponding to the road section based on the historical occurrence probability of the historical road condition state corresponding to the road section in at least one associated time period.

The historical road condition state may be a road condition that occurs before the current road condition of the road segment, and may include: and determining the corresponding comprehensive occurrence probability respectively according to each historical road condition state.

For example, the integrated occurrence probability of the historical road condition status may be a weighted sum of the historical occurrence probabilities of the historical road condition statuses corresponding to the at least one associated time period. That is, the formula for calculating the integrated occurrence probability multi _ prob of the historical road condition state can be referred to as the following formula one:

where s represents the total number of association periods, t represents an association period, and t takes a value from 1 to s. jam _ prob_tAnd the historical occurrence probability of the historical road condition state of the tth associated time period is shown. w is a_tAnd the weight corresponds to the historical occurrence probability of the historical road condition state in the tth associated time period.

Wherein t is different in value and w_tThe values of (a) will also vary. For example, the at least one association period may include a target period to which the current time belongs, and a most recent association period before and a most recent association period after the target period, the weight of the target period is the largest, and the weights of the association periods before and after the target period are relatively smaller.

It can be understood that the traffic tendency of roads on different days is possible to be advanced or delayed, and the misjudgment caused by the reason is reduced, so that the possibility of mistakenly identifying the congestion state is analyzed by using the comprehensive occurrence probability, and the misjudgment caused by the changes of the road traffic state such as advance or delay can be avoided as much as possible.

And S302, acquiring the real-time vehicle state information of the vehicle in the road section.

Wherein the real-time vehicle status information comprises: the vehicle speed of each vehicle currently present in the road segment and the total number of vehicles.

It is understood that the vehicle state information may also include the positions of the vehicles, and then the server determines the positions of the vehicles according to the positions of the vehicles.

Of course, the real-time vehicle status information may also include other information of the vehicle, which is not limited herein.

And S303, determining a vehicle sample sufficiency index according to the total number of the vehicles and a set sample number constant.

Wherein the vehicle sample sufficiency index is used to reflect whether the number of vehicles (also called vehicle samples) in the road segment for determining the road condition is sufficient. The greater the vehicle sample sufficiency index is, the more sufficient the number of vehicle samples available for determining the road condition in the road segment is, the less likely the road condition of the road segment is erroneously identified as the congestion state. On the contrary, if the vehicle sample sufficiency index is smaller, the number of the vehicle samples is insufficient, and the probability that the road section is identified as the congestion state due to the wrong road condition identification is higher.

For example, assuming that there are only three vehicles on the road section, if exactly two or three of the vehicles are in a stopped state or in a state of traveling at a slower speed for their own special reason, the road section may be erroneously recognized as a congested state. If a large number of vehicles exist in the road section, even if some vehicles have abnormal behaviors, the influence on the final determination of whether the road condition is congested is not great.

The set sample number constant can be set according to actual needs, and can be generally set by combining the vehicle sample number required by the road section to accurately determine the road condition.

The determination method of the vehicle sample sufficiency index may be various, for example, the determination method may be obtained based on a size relationship between the total number of the vehicles determined based on the real-time vehicle state and a sample number constant, or a difference value, and the like, for example, if the total number of the vehicles is smaller than the sample number constant and the difference value between the total number of the vehicles and the sample number constant is larger, the value of the vehicle sample sufficiency index is smaller; on the contrary, the total number of the vehicles is not less than the sample number constant, and the larger the difference between the two is, the larger the value of the vehicle sample sufficiency index is.

Optionally, the vehicle sample sufficiency index may be a ratio of the total number M of the vehicles to the sample number constant M, that is, the vehicle sample sufficiency index M _ adequacy may be expressed as the following formula two:

of course, there may be other ways to determine the sufficiency index of the vehicle sample, which is not limited in this regard.

S304, determining the occupation ratio of the congested vehicles with the vehicle speeds lower than the congestion vehicle speed threshold according to the vehicle speeds of all the vehicles in the road section and the congestion vehicle speed threshold corresponding to the road section.

The congestion vehicle speed threshold is a speed threshold set for the road section to judge whether the vehicle is in a congestion state or not. If the vehicle speed is lower than the congestion vehicle speed threshold, the vehicle can be judged to be in a congestion state; and if the vehicle speed is not lower than the congestion vehicle speed threshold value, the vehicle is in a slow running or clear state.

Therefore, if the vehicle speed of the vehicle is lower than the congestion vehicle speed threshold, the vehicle can be judged to belong to the congestion vehicle, so that the number of all vehicles belonging to the congestion vehicle and the number of vehicles not belonging to the congestion vehicle are determined according to the vehicle speed of each vehicle, and the occupation ratio of the congestion vehicle can be analyzed.

It can be understood that, in the case that the total number of vehicles in the road segment is small and the number of vehicles is congested is large, in order to more reasonably determine the influence of the occupancy of congested vehicles on the possible degree of the subsequent determination misjudgment, the occupancy nm _ ratio of congested vehicles in the present application may be further determined by the following formula three:

wherein m is the total number of vehicles in the road section, n is the number of jammed vehicles in the road section, and it can be seen that if the total number of vehicles is 0, the proportion of jammed vehicles is 0; if the total number m of the vehicles is less than 3 and the number of the congested vehicles is the same as the total number of the vehicles, the occupation ratio of the congested vehicles is 0.5, and for other cases than the two cases, the occupation ratio of the congested vehicles to the total number of the vehicles can be directly used as the occupation ratio of the congested vehicles.

And S305, respectively determining the speed index of each vehicle according to the vehicle speed of each vehicle in the road section, the congestion vehicle speed threshold and the severe congestion vehicle speed threshold.

Wherein the speed index of the vehicle is used for representing the possibility of the speed of the vehicle in the road section being abnormal.

The congestion speed threshold can be referred to the front for reduction, and the severe congestion speed threshold is a critical value for judging that the speed of the vehicle in the road section is in congestion and severe congestion, namely, if the speed of the vehicle is lower than the severe congestion speed threshold, the vehicle is in a severe congestion state; if the speed of the vehicle is not below the heavy congestion state but below the congestion vehicle speed threshold, the vehicle is in a congestion state.

The congestion vehicle speed threshold and the severe congestion vehicle speed threshold can be set according to actual needs.

The speed index of each vehicle may be determined in various manners, for example, the speed index may be determined by combining the magnitude relationship and the difference between the vehicle speed of the vehicle and the congestion vehicle speed threshold and the severe congestion vehicle speed threshold of the road segment.

Alternatively, the speed index idx _ spd of the vehicle may be obtained by the following formula four:

wherein sample _ spd is the vehicle speed of the vehicle, and th _ jam _ stop is the severe congestion vehicle speed threshold; and th _ slow _ jam is a congestion vehicle speed threshold value.

In addition, in the embodiment, the determination of the speed index of the vehicle is taken as an example combining the congestion vehicle speed threshold and the severe congestion vehicle speed threshold, and in practical application, the speed index of the vehicle may be determined based on only the congestion vehicle speed threshold and the vehicle speed of the vehicle.

S306, determining the speed index sum of the speed indexes of all vehicles in the road section based on the speed indexes of all vehicles.

The speed index sum is the sum of the speed indexes of all vehicles on the road section.

And S307, determining the congestion index as the product of the sum of the speed indexes and the occupation ratio of the congested vehicle.

The congestion index is used for measuring the congestion degree of the vehicles in the road section, wherein the congestion index is higher when the number of congested vehicles is larger, the total number of vehicles is smaller, and the vehicle speed of the vehicles is lower.

That is, the congestion index idx _ jam is:

idx _ jam ═ nm _ ratio ═ idx _ spd _ sum (formula five);

the nm _ ratio is the proportion of the congested vehicles, and the idx _ spd _ sum is the sum of speed indexes corresponding to all vehicles on the road section.

It is understood that the present embodiment is described by taking an implementation manner of determining the congestion index based on the vehicle speed of the vehicle and the occupation ratio of the congested vehicle as an example, and in practical applications, there may be other manners of determining the congestion index according to the vehicle speed of each vehicle and the occupation ratio of the congested vehicle in the road calculation, which is not limited in this respect.

And S308, according to the set weight relationship, carrying out weighted summation on the comprehensive occurrence probability of each historical road condition state, the vehicle sample sufficiency index, the proportion of the jammed vehicle and the jam index to obtain a misrecognition index.

Wherein the misidentification index is used to characterize a degree to which the congestion state belongs to a likelihood of being misidentified as a congestion state.

The comprehensive occurrence probability of the historical road condition state, the vehicle sample sufficiency index, the proportion of the jammed vehicles and the sum of the speed indexes respectively correspond to different weight coefficients. The weighting coefficients of the comprehensive occurrence probabilities corresponding to different historical road condition states are different. Correspondingly, the values of the parameters are weighted and summed by combining the weight coefficients of the parameters, and the misrecognition index can be obtained.

For example, the misrecognition index detect _ score can be expressed as follows:

detect_score＝a*multi_prob+b*m_adequacy+c*nm_ratio+d*idx_jam

(formula six);

wherein a is a weight coefficient of the comprehensive occurrence probability multi _ prob of the historical road condition state; b is a weight coefficient of the vehicle sample sufficiency index m _ adequacy; c is a weight coefficient of the occupied ratio nm _ ratio of the congested vehicle; d is a weight coefficient of the congestion index idx _ jam. a. b, c and d are set according to actual needs, and can be adjusted and updated continuously by combining with the statistical analysis of the road condition accuracy of each road section in actual application.

It should be noted that, for convenience of description, in the formula six, only one kind of comprehensive occurrence probability of the historical road condition state is involved, for example, the comprehensive occurrence probability of the historical road condition state may be a comprehensive occurrence probability of the traffic state. However, it can be understood that when the misrecognition index needs to be determined by combining the comprehensive occurrence probabilities of multiple historical road conditions, only the weight coefficients corresponding to the comprehensive occurrence probabilities of different historical road condition states need to be set respectively and added to other parts in the formula six.

It can be understood that, in the process of determining the possible degree that the congestion state belongs to the congestion state which is incorrectly identified in the embodiment of fig. 3, not only the historical occurrence probability of at least one historical road condition state corresponding to the target time period to which the road section belongs at the current time is considered, but also the influence of the real-time vehicle state of each vehicle in the road section on the incorrect identification of the road condition is considered, so that the possible degree that the road section of the road section belongs to the incorrect identification as the congestion state is comprehensively analyzed.

Meanwhile, in the embodiment of fig. 3, an implementation manner of determining a possible degree of the road condition being misidentified by combining the comprehensive occurrence probability of the at least one historical road condition state and the real-time vehicle state information of the vehicle in the road segment is merely described as an example. However, it can be understood that after the comprehensive occurrence probability of at least one historical road condition state is determined, the possible degree may be determined in other manners by combining the real-time vehicle state information of each vehicle in the road segment, which may be specifically referred to several possible implementations of the possible degree based on the real-time vehicle state analysis mentioned in the foregoing embodiments, and details are not repeated.

It can be understood that the historical occurrence probability corresponding to each historical road condition state can be obtained by performing statistical analysis on the historical road condition state within a recently set time period before the current day. The set time period may be one month, or 20 days, and the like, and may be specifically set according to actual needs.

For convenience of understanding, the time duration of each time period is 30 minutes, and the historical occurrence probability of each historical road condition state is obtained by taking historical road condition statistics in the last 30 days before the current day as an example.

Referring to fig. 4, a schematic diagram of an implementation process for determining the historical occurrence frequency of the historical road condition status of each time segment in the road segment in the present application is shown, where the process may be applied to the aforementioned server, or may be executed by other devices and return a final result to the server, and the process may include:

s401, obtaining a road condition release result within the last 30 days of the road section, wherein the road condition release result comprises: the road condition status of the road segment every minute during the last 30 days.

Since the road condition distribution result should include the road condition status at each time every day in the last 30 days, theoretically, a road condition status sequence with a length of 1440 corresponding to each day of the last 30 days of the road section distribution result, that is, a road condition status sequence with 30 lengths of 1440 is included, as shown in fig. 5. Each element in the road condition state sequence represents the road condition at the moment, and the value of the road condition is smooth, slow and congested.

S402, data preprocessing is carried out on the road condition release result in the last 30 days.

Wherein the preprocessing of the data may include: and smoothing the road condition state sequence contained in the road condition release result to fill up the missing road condition state, and eliminating abnormal values and the like.

The data pre-processing may also include some data merging or conversion. For example, taking the probability of occurrence of the congestion state found in the last 30 days as an example, if the road conditions include two congestion states, namely congestion and extreme congestion, and the two congestion states both belong to congestion, there is no need to distinguish the congestion states when the probability of occurrence of the congestion states is found. In this case, the extreme congestion state may be converted to a congestion state for subsequent data statistics.

Of course, the step S402 is an optional step, and if the road condition distribution result is comprehensive and the road condition status is clearly divided, the step S402 may not be executed.

And S403, determining the type attribute of each day in the last 30 days.

For example, the type attribute may be of both weekday and non-weekday types. Of course, in practical applications, the non-workday may be divided into two cases, a double holiday and a holiday.

And S404, determining 30 road condition states contained in each time period of each day in the last 30 days according to the condition that each 30 minutes is a time period.

Since each day comprises 24 hours, each day is divided into 30 minutes to obtain 48 time intervals, and each day corresponds to a road condition state sequence with the length of 48.

As shown in fig. 5, each day corresponds to a sequence of traffic conditions, and each traffic condition in the sequence corresponds to a time, so that according to the sequence of the traffic conditions from front to back in the sequence, the front 30 traffic conditions can be divided into the first 30 traffic conditions in the first time period of the day, and so on, so that each day corresponds to 49 time periods, each time period including the 30 traffic conditions in the day.

S405, for each time interval of each type of attribute, counting the occurrence probability of each road condition state of the time interval in each day belonging to the type of attribute in the last 30 days.

If the type attribute is taken as a working day as an example, for each time interval in the working day, the occurrence frequency of each road condition state in the time interval in each day belonging to the working day in the last 30 days can be counted; then, for a traffic condition, calculating the ratio of the occurrence frequency of the traffic condition to the total occurrence frequency of all traffic conditions in the time period to obtain the occurrence probability of the traffic condition. Similarly for non-workdays, the description is omitted here.

For example, taking the statistics of the occurrence probability of the congestion state in the last 30 days as an example, if the statistics of the occurrence probability of the congestion state in a certain time period of the working day in the last 30 days is required, the statistics of the occurrence frequency of the congestion state in the certain time period in the working day in the last 30 days is performed, and then the ratio of the occurrence frequency of the congestion state to the total occurrence frequency of all road conditions in the certain time period in the last 30 days is determined as the occurrence probability of the congestion state in the certain time period on the working day (also referred to as the congestion state probability for short).

That is, the probability p of occurrence of the congestion state for a certain type of attribute for a period t_tComprises the following steps:

wherein, cnt_jamThe number of times of occurrence of congestion state in the time period t in each historical day belonging to the type attribute; cnt_aAnd ll is the total occurrence frequency of all road condition states in the time interval t in each day of the history belonging to the type attribute.

For illustration with reference to fig. 5, in fig. 5, taking the month 4 of a certain year on the road segment a as an example, it is assumed that the month 4 working day includes: 4-month 1, 4-month 2, 4-month 30, etc., and non-workdays include: 4, 6, 4, 28, etc., therefore, if the probability of occurrence of congestion state in the first time period (time: 00: 00-00: 29) in the working day needs to be analyzed, all road conditions of the road segment a occurring in the first time period in the working day can be extracted as shown in fig. 5, and then the probability of the historical congestion state of the road segment a in the first time period can be counted to be 2.1%. Correspondingly, the probability of the historical congestion state in the second time period of the working day can be calculated to be 2.40%, and so on, the probability of the congestion state occurring in each of the 48 time periods corresponding to one working day can be obtained. As shown in the congestion probability sequence shown at the top of fig. 5.

S406, the historical occurrence probability of each historical road condition state corresponding to each time interval under each type of attribute is stored.

Of course, in practical applications, the historical occurrence probability of each historical road condition state in each time period under each type of day can be continuously updated as time advances.

It can be understood that, in the embodiment, the historical road condition state of the last month is analyzed as an example, and in practical application, the historical duration of the historical road condition data that needs to be acquired to analyze the occurrence probability of the historical road condition state may be set as required.

It should be noted that, in this embodiment, the type attributes of the day include a working day and a non-working day as an example, if the non-working day needs to be subdivided into a holiday and a double holiday, the holiday can be analyzed according to the road condition data of the holiday in the last year or a plurality of years before the current year, but the analysis process is similar, and is not described herein again.

After the historical occurrence probability of each historical road condition state corresponding to each time period under different day types is obtained through statistics in advance, the historical occurrence probability of the corresponding road condition state can be directly called when whether the road condition is mistakenly identified or not is detected and the mistakenly identified road condition is corrected.

For convenience of understanding, the following describes a scheme of the present application, taking as an example whether the traffic condition at the current time is a congestion state that is identified by mistake or not, based on a history occurrence probability of a history congestion state of a target time period to which the current time belongs.

As shown in fig. 6, which shows a schematic flow chart of another embodiment of the road condition determining method according to the present application, this embodiment may be applied to the aforementioned server, and the method of this embodiment may include:

s601, under the condition that the current road condition of the road section is identified as the congestion state, acquiring the historical occurrence probability of the historical congestion state of the road section in the target time period based on the type attribute of the current day and the target time period to which the current time belongs.

And if the current day is a working day, acquiring the historical occurrence probability of the historical congestion state of the road section in the target time period of the working day.

S602, detecting whether the historical occurrence probability of the historical congestion state of the road section in the target time period is lower than a set risk threshold, if so, executing the step S603; if not, determining that the current road condition of the road section has no risk of being mistakenly identified as the congestion state, and issuing the road condition of the road section as the congestion state.

The set risk threshold is a threshold for judging the congestion state as suspicious congestion.

If the historical occurrence probability of the historical congestion state of the road section in the target time period is lower than the set risk threshold value, the fact that the road section is currently identified as the congestion state is possible to have a risk of being identified incorrectly.

And S603, acquiring the occurrence probability of the respective historical congestion states of the first time period and the second time period which are nearest before the target time period and the respective historical congestion states of the third time and the fourth time period which are nearest after the target time period based on the type attribute of the current day.

For the sake of convenience of distinction, the last period before the target period is referred to as a first period, and the last period before the first period is referred to as a second period. For example, the target time period is a period of eight to half am, the first time period is a period of seven to half am, and the second time period is a period of seven to half am. Accordingly, two periods after the target period are referred to as a third period and a fourth period, respectively.

In practical applications, when the probability of occurrence of the historical congestion state in the target time period is obtained in step S601, the probabilities of occurrence of the historical congestion states in the first time period, the second time period, the third time period, and the fourth time period may also be obtained at the same time, so as to reduce the number of data obtaining times and reduce the time required for reading data. By obtaining the probability of occurrence of the historical congestion state in the first time period to the fourth time period through the step S603 after the judgment in the step S601, it is avoided that a large amount of data is obtained blindly without a risk of misidentification, which results in a waste of data resource transmission.

S604, calculating the comprehensive occurrence probability corresponding to the occurrence probability of the historical congestion states in the target time interval, the first time interval, the second time interval, the third time interval and the fourth time interval.

That is, the comprehensive occurrence probability may be a weighted sum of the occurrence probabilities of the historical congestion states in the target time period, the two most recent time periods before the target time period, and the two most recent time periods after the target time period, which may be specifically shown in the foregoing formula one, and is not described herein again.

In the present embodiment, the association periods associated with the target period include the last two periods before the target period and the last two periods after the target period, but the number of association periods may be changed as needed, and the present embodiment is also applicable.

And S605, acquiring the real-time vehicle state information of the vehicle in the road section.

And S606, calculating a vehicle sample sufficiency index, a ratio of congested vehicles with vehicle speed lower than a congested vehicle speed threshold and a congestion index according to the real-time vehicle state information of the vehicles in the road section.

The calculation of the vehicle sample sufficiency index, the proportion of the congested vehicle, and the congestion index may be performed at the same time as described above with reference to the embodiment of fig. 3, and will not be described herein again.

And S607, according to the set weight relationship, carrying out weighted summation on the comprehensive occurrence probability of each historical road condition state, the vehicle sample sufficiency index, the proportion of the jammed vehicle and the jam index to obtain a misrecognition index.

And S608, detecting whether the misidentification index is larger than a set index threshold, if so, executing the step S609, otherwise, determining that the current congestion state of the road section does not belong to misidentification, and issuing the road condition of the road section as the congestion state.

S609, determining the road condition information of the road section based on the real-time vehicle state information of the non-abnormal vehicle in the road section to obtain the corrected road condition information;

and S610, releasing the corrected road condition information.

It can be understood that the historical occurrence probability taking the historical traffic condition statistical data as the historical traffic condition state is mainly used as an example for explanation, but it can be understood that, if the historical traffic condition statistical data is the historical expected speed and other situations, the historical occurrence probability of the historical traffic condition state only needs to be replaced by the historical expected speed and the relevant weight coefficient or the judgment threshold is modified, the general principle is similar, and details are not repeated here.

The application also provides a road condition determining device corresponding to the road condition determining method. As shown in fig. 7, a schematic structural diagram of a road condition determining device according to the present invention is shown, which can be applied to the aforementioned server, and the device can include:

a data obtaining unit 701, configured to, when it is detected that a current road condition of a road segment is identified as a congestion state, obtain, from historical road condition statistical data of the road segment, target historical road condition statistical data associated with a target time period to which the current time belongs;

an error analysis unit 702, configured to determine, based on the target historical traffic statistics and the real-time vehicle status information of the vehicles in the road segment, a possible degree to which the congestion status belongs to a congestion status that is erroneously identified;

the road condition recalculating unit 703 is configured to, when the possible degree indicates that the congestion state belongs to the congestion state that is erroneously identified, determine road condition information to be issued corresponding to the road segment based on real-time vehicle state information of non-abnormal vehicles in the road segment, where the non-abnormal vehicles are vehicles in the road segment whose vehicle speed is not lower than a congestion vehicle speed threshold corresponding to the road segment, and the congestion vehicle speed threshold is a vehicle speed threshold that indicates that the road condition of the road segment enters the congestion state.

In a possible implementation manner, the statistical data of the target historical road condition acquired by the data acquiring unit at least includes: the target time interval is associated with at least one associated time interval, and the at least one associated time interval at least comprises the target time interval;

the error analysis unit includes:

a probability determination unit, configured to determine, for each historical road condition state, a comprehensive occurrence probability of the historical road condition state corresponding to the road segment based on a historical occurrence probability of the historical road condition state corresponding to the road segment in the at least one associated time period;

and the possibility analysis unit is used for determining the possible degree of the congestion state which is wrongly identified as the congestion state according to the comprehensive occurrence probability of each historical road condition state and the real-time vehicle state information of the vehicles in the road section.

Optionally, the possibility analysis unit includes:

a real-time information obtaining unit, configured to obtain real-time vehicle state information of a vehicle in the road segment, where the real-time vehicle state information includes: the vehicle speed and the total number of vehicles of each vehicle currently present in the road segment;

the sample charging and analyzing unit is used for determining a vehicle sample sufficiency index according to the total number of the vehicles and a set sample number constant;

the occupation ratio determining unit is used for determining the occupation ratio of the congested vehicles with the vehicle speeds lower than the congestion vehicle speed threshold according to the vehicle speeds of all the vehicles in the road section and the congestion vehicle speed threshold corresponding to the road section;

the speed analysis unit is used for respectively determining the speed index of each vehicle according to the vehicle speed of each vehicle in the road section, the congestion vehicle speed threshold and the severe congestion vehicle speed threshold, and the speed index of the vehicle is used for representing the possibility of abnormality of the speed of the vehicle in the road section;

the speed index summing unit is used for determining the speed index sum of the speed indexes of all vehicles in the road section based on the speed indexes of all vehicles;

a congestion index determination unit configured to determine a product of the sum of the speed indexes and a ratio of the congested vehicle as a congestion index;

and the false recognition index determining unit is used for weighting and summing the comprehensive occurrence probability of each historical road condition state, the vehicle sample sufficiency index, the ratio of the congested vehicles and the congestion index according to a set weight relationship to obtain a false recognition index, and the false recognition index is used for representing the possible degree of the congestion state which is mistakenly recognized as the congestion state.

Optionally, the historical occurrence probability of each at least one road condition state corresponding to each associated time period associated with the target time period for the road segment is: historical occurrence probability of historical congestion states corresponding to each relevant time interval relevant to the road section in the target time interval;

the at least one associated time period associated with the target time period comprises: the target time period, at least one time period most recent before the target time period, and at least one time period most recent after the target time period.

In yet another possible scenario, the apparatus further comprises:

a risk pre-judging unit, configured to detect whether a risk of being erroneously identified as a congestion state exists in a current road condition of the road segment according to target historical road condition statistical data and a set erroneous-judgment identification condition before the error analyzing unit determines that the congestion state belongs to a possible degree of being erroneously identified as the congestion state;

the error analysis unit is specifically configured to, when it is detected that the risk exists, determine, based on the target historical road condition statistical data and the real-time vehicle state information of the vehicles in the road segment, a possible degree to which the congestion state belongs to the congestion state that is erroneously identified.

Optionally, the statistical data of the target historical road condition acquired by the data acquisition unit at least includes: the historical occurrence probability of each at least one historical road condition state corresponding to the road section in the target time period;

the risk pre-judging unit is specifically configured to detect whether the current road condition of the road segment has a risk of being mistakenly identified as the congestion state according to the respective historical occurrence probability of the at least one historical road condition state and a risk judgment condition between each historical road condition state and a set risk threshold.

In a possible implementation manner, when the data obtaining unit of the above apparatus obtains the historical road condition statistical data of the target associated with the target time period to which the current time belongs from the historical road condition statistical data of the road segment, specifically, the data obtaining unit is configured to determine a type attribute of the current day to which the current time belongs, and determine, from the historical road condition statistical data associated with the road segment, the historical road condition statistical data of the target corresponding to the type attribute of the current day and associated with the target time period to which the current time belongs, where the type attribute represents that the current day is a working day or a non-working day.

In the embodiment of the application, the server can be a mobile phone, a tablet computer, and the like. For example, refer to fig. 8, which shows a schematic structural diagram of a server to which the application test method of the embodiment of the present application is applied. In fig. 8, the server 800 may include: a processor 801 and 0 memory 802.

Optionally, the apparatus may further include: a communication interface 803, an input unit 804, a display 805, and a communication bus 806.

The processor 801, the memory 802, the communication interface 803, the input unit 804 and the display 805 all communicate with each other via a communication bus 806.

In the embodiment of the present application, the processor 801 may be a Central Processing Unit (CPU), an application-specific integrated circuit (ASIC), a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices.

The processor may call a program stored in the memory 802, and in particular, the processor may perform the operations performed by the server side in the embodiments of fig. 2 and fig. 6.

The memory 802 is used for storing one or more programs, which may include program codes including computer operation instructions, and in this embodiment, the memory stores at least the programs for implementing the following functions:

and under the condition that the possible degree indicates that the congestion state belongs to the congestion state which is identified by mistake, determining road condition information to be issued corresponding to the road section based on real-time vehicle state information of non-abnormal vehicles in the road section, wherein the non-abnormal vehicles are vehicles with the vehicle speed in the road section not lower than a congestion vehicle speed threshold value corresponding to the road section, and the congestion vehicle speed threshold value is a vehicle speed critical value for indicating that the road condition of the road section enters the congestion state.

In one possible implementation, the memory 802 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, the above-mentioned programs, and the like; the storage data area may store data created according to the use of the server.

The communication interface 803 may be an interface of a communication module, such as an interface of a GSM module.

The present application may further include an input unit 804, which may include a touch sensing unit that senses a touch event on the touch display panel, a keyboard, and the like.

The display 805 includes a display panel, such as a touch display panel or the like.

Of course, the server structure shown in fig. 8 does not constitute a limitation to the server in the embodiment of the present application, and in practical applications, the server may include more or less components than those shown in fig. 8, or some components may be combined.

On the other hand, the present application further provides a storage medium, where computer-executable instructions are stored, and when the computer-executable instructions are loaded and executed by a processor, the method for determining a road condition as in any one of the above embodiments is implemented.

It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. For the device-like embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

The foregoing is only a preferred embodiment of the present invention, and it should be noted that it is obvious to those skilled in the art that various modifications and improvements can be made without departing from the principle of the present invention, and these modifications and improvements should also be considered as the protection scope of the present invention.

Claims

1. A road condition determining method is characterized by comprising the following steps:

detecting whether the current road condition of the road section has the risk of being recognized as a congestion state by mistake according to the target historical road condition statistical data and the set misjudgment recognition condition;

determining a possible degree to which the congestion state belongs to a congestion state which is erroneously identified based on the target historical traffic statistical data and real-time vehicle state information of the vehicles in the road section under the condition that the risk is detected to exist;

2. The method according to claim 1, wherein the target historical road condition statistics comprise at least: the target time interval is associated with at least one associated time interval, and the at least one associated time interval at least comprises the target time interval;

3. The method as claimed in claim 2, wherein the determining the congestion status as belonging to a possible degree of being erroneously identified as the congestion status according to the integrated occurrence probability of each of the historical road condition statuses and the real-time vehicle status information of the vehicles in the road segment comprises:

4. The method according to claim 2 or 3, wherein the historical occurrence probability of each of the at least one road condition status corresponding to each associated time segment associated with the road segment in the target time segment is: historical occurrence probability of historical congestion states corresponding to each relevant time interval relevant to the road section in the target time interval;

5. The method according to claim 1, wherein the target historical road condition statistics comprise at least: the historical occurrence probability of each at least one historical road condition state corresponding to the road section in the target time period;

the method for detecting whether the current road condition of the road section has the risk of being mistakenly identified as the congestion state according to the target historical road condition statistical data and the set misjudgment identification condition comprises the following steps:

and detecting whether the current road condition of the road section has the risk of being mistakenly identified as the congestion state or not according to the respective historical occurrence probability of the at least one historical road condition state and the risk judgment condition between each historical road condition state and a set risk threshold value.

6. The method according to claim 1, 2, 3 or 5, wherein the obtaining of the target historical road condition statistical data associated with the target time period to which the current time belongs from the historical road condition statistical data of the road section comprises:

determining the type attribute of the current day to which the current moment belongs, wherein the type attribute represents that the current day is a working day or a non-working day;

and determining target historical road condition statistical data which corresponds to the type attribute of the current day and is associated with the target time period to which the current time belongs from the historical road condition statistical data associated with the road section.

7. A road condition determining apparatus, comprising:

the risk pre-judging unit is used for detecting whether the current road condition of the road section has a risk of being mistakenly identified as a congestion state or not according to the target historical road condition statistical data and the set misjudgment identification condition;

an error analysis unit, configured to determine, when it is detected that the risk exists, a possible degree to which the congestion state belongs to a congestion state that is erroneously identified based on the target historical traffic statistics and real-time vehicle state information of vehicles in the road segment;

8. A server, comprising:

a processor and a memory;

the processor is used for calling and executing the program stored in the memory;

the memory is configured to store the program, the program at least to:

9. A storage medium, wherein the storage medium stores computer-executable instructions, and when the computer-executable instructions are loaded and executed by a processor, the method for determining a road condition as claimed in any one of claims 1 to 6 is implemented.