CN115481164A

CN115481164A - Method for acquiring road portrait characteristics, electronic equipment and storage medium

Info

Publication number: CN115481164A
Application number: CN202110661200.1A
Authority: CN
Inventors: 刘羽飞
Original assignee: Alibaba Singapore Holdings Pte Ltd
Current assignee: Alibaba Innovation Co
Priority date: 2021-06-15
Filing date: 2021-06-15
Publication date: 2022-12-16

Abstract

The embodiment of the disclosure discloses a method for acquiring road portrait characteristics, electronic equipment and a storage medium, wherein the method for acquiring the road portrait characteristics comprises the following steps: acquiring a congested road section and a corresponding congested time period based on historical road condition information of the road section in a historical time period; according to a set congestion image time range, aggregating congestion time periods corresponding to congestion road sections to generate congestion time characteristics of the congestion road sections in the congestion image time range, wherein the congestion time characteristics comprise: a pre-congestion formation time characteristic, a congestion duration characteristic, a congestion dissipation time characteristic; and processing the road traffic characteristic information of the congested road section according to the time in the congestion time characteristic to obtain the road congestion image characteristic at the corresponding time. According to the technical scheme, the road congestion image characteristics obtained by aggregating historical data of mass carriers can objectively, accurately and easily understand the related conditions of road congestion.

Description

Method for acquiring road portrait characteristics, electronic equipment and storage medium

Technical Field

The disclosure relates to the technical field of internet, in particular to a road portrait feature acquisition method, electronic equipment and a storage medium.

Background

With the continuous expansion of the urban scale, the continuous increase of the reserved quantity of private cars and the continuous increase of travel demands of people, congestion becomes a considerable problem in the urban development process. The congestion image mode based on manual experience is influenced by subjectivity, accuracy and effectiveness of manual observation results, and the road congestion condition cannot be objectively and accurately reflected.

Disclosure of Invention

The embodiment of the disclosure provides a method for acquiring road congestion portrait characteristics, electronic equipment and a storage medium.

In a first aspect, an embodiment of the present disclosure provides a method for acquiring a road portrait feature, where the method includes:

acquiring a congested road section and a corresponding congestion time period thereof based on historical road condition information of the road section in the historical time period;

according to a set congestion image time range, aggregating congestion time periods corresponding to congestion road sections to generate congestion time characteristics of the congestion road sections in the congestion image time range, wherein the congestion time characteristics comprise: a pre-congestion formation time characteristic, a congestion duration characteristic, a congestion dissipation time characteristic;

and processing the road traffic characteristic information of the congested road section according to the time in the congestion time characteristic to obtain the road congestion image characteristic at the corresponding time.

Further, the aggregating congestion time periods corresponding to the congestion sections to generate congestion time characteristics of the congestion sections in the congestion portrait time range includes:

for each congested road section, sequencing congestion time periods corresponding to the congested road sections in sequence, and merging continuous congestion time periods in the congested road sections to obtain alternative congestion duration time characteristics corresponding to the congested road sections;

when only one alternative congestion duration time feature corresponding to the congested road section is available, taking the alternative congestion duration time feature as a congestion duration time feature corresponding to the congested road section;

when at least two alternative congestion duration time features corresponding to the congested road section exist, merging alternative congestion duration time features meeting merging conditions in the at least two alternative congestion duration time features for a continuous time period to serve as congestion duration time features corresponding to the congested road section, wherein each of the at least two alternative congestion duration time features which are not merged together serves as other congestion duration time features corresponding to the congested road section, and the merging conditions include that the time interval between one alternative congestion duration time feature in the merged alternative congestion duration time features and an adjacent alternative congestion duration time feature is smaller than preset time or the traffic condition in the time interval meets congestion conditions;

and acquiring a time feature before congestion formation and a time feature before congestion dissipation corresponding to the congestion duration feature based on the congestion duration feature for each congestion duration feature.

Further, the road traffic characteristic information of the congested road section includes: averaging a number of vehicles per minute that pass through the congested section, a number of vehicles per minute that are predicted to reach the congested section, a speed of travel of the vehicles through the congested section, and a time of travel of the vehicles through the congested section;

the road congestion image features corresponding to the time in the congestion time features comprise: and at the time in the corresponding congestion time characteristic, the average passing speed of the vehicles passing through the congested road section, the average passing time of the vehicles passing through the congested road section, the distribution of the vehicle quantity at different passing speeds, the distribution of the vehicle quantity at different passing times and the average vehicle quantity predicted to reach the congested road section within a preset time length.

Further, the processing the road traffic characteristic information of the congested road section according to the time in the congestion time characteristic to obtain the road congestion image characteristic at the corresponding time, further includes:

acquiring flow distribution of vehicles entering and exiting between a congested road section and a related road section within time corresponding to congestion time characteristics according to a running track of the vehicles on the road section;

acquiring a correlation coefficient between the correlation road section and a congested road section based on the flow distribution and the distance between the correlation road section and the congested road section;

and acquiring congestion occurrence advance time and congestion dissipation advance time of the associated road section compared with the congestion road section in the congestion image time range on the basis of the associated road section and the congestion duration time characteristics of the congestion road section.

establishing a strongly-connected subgraph based on the congestion duration characteristics corresponding to the congestion road sections every day, wherein one vertex of the strongly-connected subgraph represents a day corresponding to one congestion duration characteristic, the edge of the strongly-connected subgraph represents a time period for which two congestion duration characteristics in two days corresponding to two vertices are associated, and the time period for which the two congestion duration characteristics are associated means that the coincidence time period between the two congestion duration characteristics exceeds a preset threshold value; the preset threshold is 1/2 of the shorter time period of the two congestion duration time periods;

traversing the strongly connected subgraph, and aggregating road congestion image characteristics corresponding to time in the same type of congestion duration characteristics with associated time periods to obtain road congestion image characteristics corresponding to characteristic days, wherein the road congestion image characteristics corresponding to the characteristic days comprise date characteristics of the days where the same type of congestion duration characteristics are located, and the average congestion starting time, the average congestion duration time, the congestion occurrence days, the confidence coefficient of congestion occurrence, the deviation time of the congestion formation time and the deviation time of the congestion dissipation time corresponding to the same type of congestion duration characteristics.

In a second aspect, an embodiment of the present invention provides a method for predicting road congestion, including:

processing the road traffic characteristic information of the congested road section according to the time in the congestion time characteristic to obtain the road congestion image characteristic of the corresponding time;

and predicting the congestion situation of the congested road section in the future based on the road congestion image characteristics.

Further, the processing the road traffic characteristic information of the congested road section according to the time in the congestion time characteristic to obtain the road congestion image characteristic of the corresponding time includes:

traversing the strongly connected subgraphs, and aggregating the road congestion image characteristics corresponding to the time in the same class of congestion duration characteristics with associated time periods to obtain the road congestion image characteristics corresponding to characteristic days, wherein the road congestion image characteristics corresponding to the characteristic days comprise the date characteristics of the day where the same class of congestion duration characteristics are located, and the average congestion starting time, the average congestion duration time, the number of congestion occurring days, the confidence coefficient of congestion occurrence, the deviation time of the congestion forming time and the deviation time of the congestion dissipating time corresponding to the same class of congestion duration characteristics;

the predicting the congestion situation of the congested road section in the future based on the road congestion image characteristics comprises the following steps:

and predicting the congestion situation of the congested road section on the day with the date characteristic of the characteristic day in the future based on the road congestion image characteristic corresponding to the characteristic day.

Further, the processing the road traffic characteristic information of the congested road section according to the time in the congestion time characteristic to obtain the road congestion image characteristic at the corresponding time includes:

acquiring flow distribution of the vehicles entering and exiting between the congested road section and the related road section at each moment according to the running tracks of the vehicles on the road sections;

acquiring congestion occurrence advance time or congestion dissipation advance time of the associated road section compared with the congested road section in the congestion imaging time range on the basis of the congestion duration characteristics of the associated road section and the congested road section;

the method for predicting the congestion situation of the congested road section in the future based on the road congestion image characteristics comprises the following steps:

and predicting the probability of congestion of the congested road section at a subsequent moment when the congestion occurs in the associated road section or predicting the probability of congestion dissipation of the congested road section at a subsequent moment when the congestion of the associated road section dissipates, based on a correlation coefficient between the associated road section and the congested road section and the time ahead of congestion occurrence and the time ahead of congestion dissipation of the associated road section compared with the congested road section.

In a third aspect, an embodiment of the present invention provides an apparatus for obtaining a road portrait characteristic, including:

the first acquisition module is configured to acquire a congested road section and a corresponding congested time period based on historical road condition information of the road section in a historical time period;

the first aggregation module is configured to aggregate congestion time periods corresponding to congested road sections according to a set congestion image time range, and generate congestion time characteristics of the congested road sections in the congestion image time range, wherein the congestion time characteristics include: a pre-congestion formation time characteristic, a congestion duration characteristic, a congestion dissipation time characteristic;

and the first processing module is configured to process the road traffic characteristic information of the congested road section according to the time in the congestion time characteristic to obtain the road congestion image characteristic at the corresponding time.

Further, the first aggregation module is configured to:

when at least two alternative congestion duration time features corresponding to the congested road section exist, merging alternative congestion duration time features meeting merging conditions in the at least two alternative congestion duration time features into a continuous time period to serve as congestion duration time features corresponding to the congested road section, wherein each alternative congestion duration time feature which is not merged in the at least two alternative congestion duration time features serves as other congestion duration time features corresponding to the congested road section, and the merging conditions comprise that the time interval between one alternative congestion duration time feature and an adjacent alternative congestion duration time feature in the merged alternative congestion duration time features is smaller than a preset time length or the traffic condition in the time interval meets the congestion condition;

Further, the road traffic characteristic information of the congested road section includes: averaging the number of vehicles per minute that pass through the congested road segment, the number of vehicles per minute that are predicted to reach the congested road segment, the speed of vehicles traveling through the congested road segment, and the time of travel of vehicles traveling through the congested road segment;

the road congestion image features corresponding to the time in the congestion time features comprise: at the time in the corresponding congestion time characteristic, an average transit speed of the vehicle through the congested section, an average transit time of the vehicle through the congested section, a distribution of vehicle amounts at different transit speeds, a distribution of vehicle amounts at different transit times, and an average vehicle amount expected to reach the congested section within a preset time period.

Further, the first processing module is further configured to:

and acquiring congestion occurrence advance time and congestion dissipation advance time of the associated road section compared with the congested road section in the congestion image time range on the basis of the associated road section and the congestion duration characteristics of the congested road section.

Further, the first processing module is further configured to:

establishing a strongly connected subgraph based on congestion duration characteristics corresponding to the congestion road sections every day, wherein one vertex of the strongly connected subgraph represents a day corresponding to one congestion duration characteristic, an edge of the strongly connected subgraph represents a time period for which two congestion duration characteristics in two days corresponding to two vertices exist, and the time period for which the two congestion duration characteristics exist is that a coincidence time period between the two congestion duration characteristics exceeds a preset threshold value; the preset threshold value is 1/2 of the shorter time period of the two congestion duration time periods;

In a fourth aspect, an embodiment of the present invention provides a road congestion prediction apparatus, including:

the second acquisition module is configured to acquire the congested road section and the corresponding congested time period based on historical road condition information of the road section in the historical time period;

the second aggregation module is configured to aggregate congestion time periods corresponding to congested road sections according to the set congestion image time range, and generate congestion time characteristics of the congested road sections in the congestion image time range, wherein the congestion time characteristics include: a pre-congestion formation time characteristic, a congestion duration characteristic, and a congestion dissipation time characteristic;

the second processing module is configured to process the road traffic characteristic information of the congested road section according to the time in the congestion time characteristic to obtain the road congestion image characteristic at the corresponding time;

and the prediction module is configured to predict the congestion situation of the congestion road section in the future based on the road congestion image characteristics.

Further, the second processing module is further configured to:

traversing the strongly connected subgraph, and aggregating road congestion image features corresponding to time in the same type of congestion duration features with associated time periods to obtain road congestion image features corresponding to feature days, wherein the road congestion image features corresponding to the feature days comprise date features of the days where the same type of congestion duration features are located, and the average congestion starting time, the average congestion duration, the congestion occurrence days, the congestion occurrence confidence coefficient, the congestion formation time deviation time duration and the congestion dissipation time deviation duration corresponding to the same type of congestion duration features;

the prediction module further configured to:

Further, the second processing module is further configured to:

the prediction module further configured to:

In one possible design, the apparatus includes a memory configured to store one or more computer instructions that enable the apparatus to perform the corresponding method, and a processor configured to execute the computer instructions stored in the memory. The apparatus may also include a communication interface for the apparatus to communicate with other devices or a communication network.

In a fifth aspect, the disclosed embodiments provide an electronic device, comprising a memory, a processor, and a computer program stored on the memory, wherein the processor executes the computer program to implement the method of any of the above aspects.

In a sixth aspect, the disclosed embodiments provide a computer-readable storage medium for storing computer instructions for use by any one of the above apparatuses, the computer instructions, when executed by a processor, being configured to implement the method according to any one of the above aspects.

In a seventh aspect, the disclosed embodiments provide a computer program product comprising computer instructions, which when executed by a processor, are configured to implement the method of any one of the above aspects.

The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:

the technical scheme provided by the embodiment of the disclosure screens congestion road sections and corresponding congestion time periods from historical road condition information of each road section in a historical time period, aggregates the congestion time periods corresponding to the congestion road sections according to a set congestion image time range, and generates congestion time characteristics of the congestion road sections in the congestion image time range, wherein the congestion time characteristics comprise: a pre-congestion formation time characteristic, a congestion duration characteristic, and a congestion dissipation time characteristic; and processing the road traffic characteristic information of the congested road section according to the time in the congestion time characteristic to obtain the road congestion image characteristic at the corresponding time. According to the technical scheme, massive historical data can be aggregated and processed into road congestion image characteristics of a congested road section in the time corresponding to the time characteristics before congestion is formed, congestion duration time characteristics and congestion dissipation time characteristics, the road congestion image characteristics in the time can objectively and accurately reflect road traffic conditions of congested roads before congestion is formed, during congestion duration and after congestion dissipation, and real-time congestion release quality can be improved, road congestion degree can be more accurately identified, and future road traffic conditions can be more clearly described through the road congestion image characteristics.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

Other features, objects, and advantages of the present disclosure will become more apparent from the following detailed description of non-limiting embodiments when taken in conjunction with the accompanying drawings. In the drawings:

FIG. 1 illustrates a flow diagram of a method of road representation feature acquisition according to an embodiment of the present disclosure;

FIG. 2 shows a flow chart of step S102 according to the embodiment shown in FIG. 1;

FIG. 3 shows a flow chart of step S103 according to the embodiment shown in FIG. 1;

FIG. 4 shows a further flowchart of step S103 according to the embodiment shown in FIG. 1;

fig. 5 illustrates a flowchart of a road congestion prediction method according to an embodiment of the present disclosure;

fig. 6 illustrates an overall flowchart of a road congestion prediction method according to an embodiment of the present disclosure;

FIG. 7 is a block diagram of an apparatus for obtaining a road representation feature according to an embodiment of the present disclosure;

fig. 8 is a block diagram showing a configuration of a road congestion prediction apparatus according to an embodiment of the present disclosure;

fig. 9 is a schematic structural diagram of an electronic device suitable for implementing a road profile feature acquisition method and/or a road congestion prediction method according to an embodiment of the present disclosure.

Detailed Description

Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. Also, for the sake of clarity, parts not relevant to the description of the exemplary embodiments are omitted in the drawings.

In the present disclosure, it is to be understood that terms such as "including" or "having," etc., are intended to indicate the presence of the disclosed features, numerals, steps, actions, components, parts, or combinations thereof in the specification, and do not preclude the possibility that one or more other features, numerals, steps, actions, components, parts, or combinations thereof are present or added.

It should be further noted that the embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

The details of the embodiments of the present disclosure are described in detail below with reference to specific embodiments.

FIG. 1 shows a flow chart of a method of road representation feature acquisition according to an embodiment of the present disclosure. As shown in fig. 1, the method for obtaining road image features includes the following steps:

in step S101, a congested road segment and a congestion time period corresponding to the congested road segment are obtained based on historical road condition information of the road segment in a historical time period;

in step S102, according to a set congestion image time range, aggregating congestion time periods corresponding to congestion links to generate a congestion time feature of the congestion link within the congestion image time range, where the congestion time feature includes: a pre-congestion formation time characteristic, a congestion duration characteristic, and a congestion dissipation time characteristic;

in step S103, the road traffic feature information of the congested road segment is processed according to the time in the congestion time feature, so as to obtain a road congestion image feature at the corresponding time.

As mentioned above, with the continuous expansion of the urban scale, the continuous increase of the amount of private cars, and the continuous increase of the travel demand of people, congestion becomes a considerable problem in the urban development process. The congestion image-drawing mode based on manual experience is influenced by subjectivity, accuracy and effectiveness of manual observation results, and the road congestion condition cannot be objectively, accurately and timely reflected.

In view of the above drawbacks, the present embodiment provides a method for acquiring a road profile, which may select congestion sections and congestion sections corresponding to the congestion sections for each day from historical road condition information of each section in a historical time period, aggregate the congestion sections corresponding to the congestion sections according to a set congestion imaging time range, and generate a congestion time profile of the congestion section in the congestion imaging time range, where the congestion time profile includes: a pre-congestion formation time characteristic, a congestion duration characteristic, a congestion dissipation time characteristic; and processing the road traffic characteristic information of the congested road section according to the time in the congestion time characteristic to obtain the road congestion image characteristic at the corresponding time. According to the technical scheme, massive historical data can be aggregated and processed into road congestion image characteristics of a congested road section in the time corresponding to the time characteristics before congestion is formed, congestion duration time characteristics and congestion dissipation time characteristics, the road congestion image characteristics in the time can objectively and accurately reflect road traffic conditions of congested roads before congestion is formed, during congestion duration and after congestion dissipation, and real-time congestion release quality can be improved, road congestion degree can be more accurately identified, and future road traffic conditions can be more clearly described through the road congestion image characteristics.

In this embodiment, the road congestion representation method may be applied to a computer, a computing device, an electronic device, and the like that acquire road congestion representation characteristics.

In this embodiment, the historical time period may be a time period in units of days, and the historical time period includes one day, multiple consecutive days, or multiple discrete days. The links are directed logical road units divided according to actual roads, each link has an independent link ID, corresponds to a single road, and each link only comprises an entrance and an exit.

In the embodiment, the road sections in the road network are in a billion, so that a large amount of resources are consumed when congestion portrayal is directly carried out on each road section, and the cost performance is low; in fact, only the road sections which are likely to be congested need to be subjected to congestion representation, and the road sections which are congested in the historical time period are the road sections which are likely to be congested.

In this embodiment, the historical traffic information of each road section refers to various information describing an actual traffic condition of each road section in a historical time period, for example, the historical traffic information may include traffic conditions of each road section in the historical time period or some information capable of reflecting the traffic conditions, the traffic conditions may include a congestion state and a non-congestion state, and the non-congestion state may include a plurality of states such as a smooth state and a slow traffic state. The historical traffic information reflecting the traffic status may include traffic speed or traffic time, and generally, the traffic status of each road section is related to the traffic speed or traffic time of the vehicle on the road section. Taking the traffic information as the traffic speed as an example, for the link1 of the suburb road section, the traffic state corresponding to the traffic speed [ 70-80 km/h ] is an unblocked state, the traffic state corresponding to the traffic speed [ 50-70 km/h ] is a slow-moving state, and the traffic state corresponding to the traffic speed [ 30-50 km/h ] is a congested state. For the link2 of the downtown road section, the road condition state corresponding to the traffic speed [ 40-60 km/h ] is an unblocked state, the road condition state corresponding to the traffic speed [ 30-40 km/h ] is a slow traffic state, and the road condition state corresponding to the traffic speed [ 20-30 km/h ] is a congestion state.

In this embodiment, the road condition publishing result of the navigation server may be historical road condition information, such as the traffic speed, the road condition state, the passing time, and the like of each road segment published every minute in the past one minute, so that the historical road condition information of the road segment in the historical time period may be obtained from the navigation server, a road segment (hereinafter referred to as a congested road segment) whose road condition information indicates that the road segment is in a congested state is screened out from the historical road condition information, and a congestion time period corresponding to the congested road segment is recorded at the same time, where the recording format is: inskid-start time-end time, which, for example, may be denoted link1-7:30-7:31, link1-7:31-7:32, and so on.

In this embodiment, the congestion image time range is a time range in which the user requests congestion image, and may be a time range in units of days, a day, a week, a month, or the like. And aggregating the congestion time periods corresponding to the congestion road sections in the congestion image time range, determining that the congestion road sections have several times of congestion in the congestion image time range, generating congestion time characteristics corresponding to the several times of congestion, wherein each congestion corresponds to one congestion time characteristic. Each congestion time feature correspondingly comprises three features, namely a time feature before congestion formation, a congestion duration time feature and a congestion elimination time feature, wherein the time corresponding to the time feature before congestion formation, the congestion duration time feature and the congestion elimination time feature is a period of continuous time, and respectively shows a period of time before congestion formation, a period of time during congestion continuation and a period of time after congestion elimination of the current congestion. The congestion duration characteristic is a characteristic representing a congestion duration of the current congestion, and may be, for example, a time between a congestion start time and a congestion end time, the pre-congestion-formation-time characteristic is a characteristic representing a time before the current congestion starts, and may be, for example, a time between the congestion start time and a first preset time period before the current congestion start time, and the congestion-dissipation-time characteristic is a characteristic representing a time after the current congestion ends, and may be, for example, a time between the congestion end time and a second preset time period after the current congestion end time.

For example, assuming that the congestion image time range is one day, the congestion duration characteristics corresponding to the congested road segments on the day are aggregated, and for congested road segments with the same link ID, the congestion periods corresponding to the congested road segments may be combined into one or more congestion duration characteristics, such as link1 correspondence of 7:30 to 8:30 and 17:30 to 18: and 30 congestion duration characteristics, each of which can be extended forwards and backwards for a period of time, wherein the first preset time period for forward extension, such as 30 minutes, obtains the time characteristic before congestion formation, and the second preset time period for backward extension, such as 30 minutes, obtains the time characteristic before congestion dissipation. This results in a first set of congestion time characteristics for link1 during the day: pre-congestion formation time feature 7:00 to 7:30, congestion duration feature 7:30 to 8:30, congestion dissipation time characteristic 8:30 to 9:30, of a nitrogen-containing gas; and a second set of congestion time characteristics: pre-congestion formation time characteristic 17:00 to 17:30, congestion duration feature 17:30 to 18:30, congestion dissipation time characteristic 18:30 to 19:30.

in this embodiment, the congestion duration time feature and the time before congestion formation and the time after congestion dissipation corresponding to the congestion duration time feature may be obtained, and after the road traffic feature information of the congested road segment is processed, the road congestion image feature at the time before congestion formation, during congestion duration, and after congestion dissipation may be obtained. The road traffic characteristic information refers to characteristic information capable of indicating traffic conditions of vehicles passing through the congested road section, the road traffic characteristic information can be directly acquired from a corresponding navigation server, and the vehicles refer to vehicles which are navigated or positioned by using the navigated client. The road congestion image feature refers to information capable of describing attributes of congestion related conditions of the congested road, such as congestion occurrence probability, congestion time, congestion duration or traffic capacity during congestion.

In the embodiment, the road congestion portrait characteristics before congestion formation, when congestion continues and after congestion dissipates are obtained by using massive historical data in the navigation server, so that the road congestion situation of the congested road can be objectively, completely, accurately and timely reflected, the real-time congestion issue quality can be improved by the road congestion portrait characteristics, a carrying tool can more accurately identify the road congestion degree, judge whether periodic conventional congestion exists or not, and more clearly describe the future road traffic condition; meanwhile, the road congestion portrait characteristics can be used as basic data to assist road condition prediction, ETA (Estimated Time of Arrival) calculation, navigation planning and the like.

In an optional implementation manner of this embodiment, as shown in fig. 2, in step S102, the step of aggregating congestion periods corresponding to congested road segments to generate a congestion time characteristic of the congested road segments in the congestion image time range further includes the following steps:

in step S201, for each congested road segment, sequencing congestion time periods corresponding to the congested road segment in order, and merging consecutive congestion time periods in the congested road segment to obtain an alternative congestion duration feature corresponding to the congested road segment;

in step S202, when there is only one candidate congestion duration time feature corresponding to the congested road segment, taking the candidate congestion duration time feature as a congestion duration time feature corresponding to the congested road segment;

in step S203, when there are at least two candidate congestion duration features corresponding to the congested road segment, merging the candidate congestion duration features that satisfy a merging condition among the at least two candidate congestion duration features for a continuous time period as congestion duration features corresponding to the congested road segment, where each candidate congestion duration feature that is not merged among the at least two candidate congestion duration features is used as another congestion duration feature corresponding to the congested road segment, and the merging condition includes that a time interval between one candidate congestion duration feature and an adjacent candidate congestion duration feature among the merged candidate congestion duration features is less than a preset time duration or a traffic condition within the time interval satisfies the congestion condition.

In step S204, for each congestion duration feature, a pre-congestion-formation time feature and a congestion dissipation time feature corresponding to the congestion duration feature are obtained based on the congestion duration feature.

In this optional implementation manner, for each congested road segment, the congestion time periods corresponding to the congested road segment may be sorted from 00-23: 30-7:31,7:31-7:32, 8230, 82308: 28-8:29,8:29-8:30 combined time period 7:30 to 8:30, and by the consecutive congestion period 17:30-17:31, 17:31-17:32, 8230, 823018: 28-18:29, 18:29-18:30 combined time period 17:30 to 18:30.

in this optional implementation, when only one alternative congestion duration feature is merged, the alternative congestion duration feature may be directly used as a congestion duration feature corresponding to the congested road segment; when there are at least two combined alternative congestion duration features, it may be determined through a preset combining condition whether there are several alternative congestion duration features among the alternative congestion duration features that may be combined into one congestion duration feature, and if so, the alternative congestion duration features may be combined into one continuous time period as one congestion duration feature. And each alternative congestion duration characteristic which is not combined with other alternative congestion duration characteristics because the alternative congestion duration characteristics do not meet the combination conditions in the alternative congestion duration characteristics is taken as other congestion duration characteristics corresponding to the congested road section. For example, when only two candidate congestion duration features are merged and the two candidate congestion duration features do not meet the merging condition and are not merged, both of the two candidate congestion duration features may be used as the two congestion duration features corresponding to the congested road segment.

In this optional implementation manner, the merging condition refers to that, for one alternative congestion duration feature of several alternative congestion duration features that may be merged into one congestion duration feature, a time interval between an adjacent alternative congestion duration feature and the alternative congestion duration feature is less than a preset time (for example, 10 minutes) or a traffic condition in the time interval satisfies the congestion condition, where the congestion condition may be that an average traffic speed in the time interval is less than a preset speed or that an average traffic time in the time interval is less than a preset time, and at this time, congestion conditions are different for different road segments due to different positions or different road lengths; or, the congestion condition may be that the road condition in the time interval is a slow-moving state, or that a plurality of discrete time periods in the time interval exist in which the road condition is a congestion state, or that the sum of the discrete time periods in the time interval in which the road condition is a congestion state is greater than or equal to a predetermined time length, and the like.

For example, assuming that the preset time duration is 10 minutes, and the congestion condition is that the average traffic speed in the time interval is less than 50km/h, merging consecutive congestion periods in the congested section to obtain a candidate congestion duration characteristic corresponding to the congested section is as follows, in terms of 10-25, 8. Wherein the average traffic speed in time interval 8; in the case of 10-8. In the following fig. 17-00, 18-09-18, in. Thus aggregated, the congestion duration corresponding to the congested link is characterized by 8.

In this optional implementation manner, for each congestion duration characteristic, extending the time of the congestion duration characteristic forward by a first preset time period may obtain a time characteristic before congestion formation corresponding to the congestion duration characteristic, and extending the time of the congestion duration characteristic backward by a second preset time period may obtain a congestion dissipation time characteristic corresponding to the congestion duration characteristic, which is specifically described in the foregoing embodiment and will not be described in detail herein.

In an optional implementation manner of this embodiment, the road traffic characteristic information of the congested road segment includes: averaging a number of vehicles per minute that pass through the congested section, a number of vehicles per minute that are predicted to reach the congested section, a speed of travel of the vehicles through the congested section, and a time of travel of the vehicles through the congested section; the road congestion image features corresponding to the time in the congestion time features comprise: at the time in the corresponding congestion time characteristic, an average transit speed of the vehicle through the congested section, an average transit time of the vehicle through the congested section, a distribution of vehicle amounts at different transit speeds, a distribution of vehicle amounts at different transit times, and an average vehicle amount expected to reach the congested section within a preset time period.

In this alternative implementation, the road congestion profile feature at the corresponding time may be a road congestion profile feature within a time corresponding to a time feature before congestion formation, a time corresponding to a congestion duration feature, and a time of a congestion dissipation time feature in each congestion time feature. The congestion road section can have a plurality of congestion time characteristics in the congestion image time range, and each congestion time characteristic corresponds to a group of congestion pre-forming time characteristics, congestion duration time characteristics and congestion dissipation time characteristics. The road congestion image feature corresponding to the time in each congestion time feature comprises: the time of the time characteristic before congestion formation in the congestion time characteristic corresponds to the road congestion image characteristic, the time of the congestion duration time characteristic corresponds to the road congestion image characteristic, and the time of the congestion dissipation time characteristic corresponds to the road congestion image characteristic. For each congestion road segment, road traffic characteristic information in time corresponding to the time characteristic before congestion formation, the time characteristic before congestion continuation and the time characteristic before congestion dissipation in each congestion time characteristic can be processed respectively, and road congestion image characteristics corresponding to the time characteristic before congestion formation, the time characteristic before congestion continuation and the time characteristic after congestion dissipation are obtained respectively. The road congestion images corresponding to the time of the three time characteristics respectively represent the road traffic capacity characteristics of the congested road section before congestion, during congestion and after congestion, the road congestion images corresponding to the time of the three time characteristics have the same characteristic type, and the characteristic values are different due to different corresponding time periods.

In this alternative implementation, the road traffic characteristic information may be obtained from the navigation server. For example, the navigation client may be provided with a navigation real-time request interface to return real-time track points of the vehicles, current positions of the vehicles and real-time information of the current positions of the vehicles to the navigation server, and the navigation server may navigate the vehicles and return navigation data such as a road segment to be passed in the future and predicted time to reach the road segment in the future to the navigation client, so that the amount of the vehicles predicted to reach the congested road segment per minute in the corresponding time may be obtained from the navigation server; the navigation server is also provided with a real-time track matching result of a carrier, GPS track points of the carrier returned by the navigation client can be mapped onto the Goodpasture road network, the real-time track of the carrier is displayed, the passing speed, the passing time and the like of the carrier passing through each road section are calculated, the average carrier quantity passing through the congested road section per minute in the corresponding time period of each congestion time characteristic can be obtained through the real-time track matching result of the carrier, the carrier passes through the passing speed of the congested road section, and the passing time of the carrier passing through the congested road section is obtained.

In this alternative implementation, the road congestion profile feature at the time in the pre-congestion formation time feature may be calculated as follows: the average passing speed of the vehicles passing through the congested road section can be obtained by averaging the passing speed of each vehicle passing through the congested road section in the time corresponding to the time characteristic before the congestion is formed; the average passing time of the vehicles passing through the congested road section can be obtained by averaging the passing time of each vehicle passing through the congested road section in the time corresponding to the time characteristic before the congestion is formed; the vehicle distribution of different transit speeds may be obtained by counting the vehicle amounts of the traffic speeds in different speed ranges within the time corresponding to the time characteristic before the congestion is formed, for example, the transit speeds in the several ranges of 10km/h or less, (10 km/h,20km/h ], (20 km/h,40km/h ], (40 km/h,60km/h ], and more than 60km/h may be counted when the traffic speed passes through the congested road section within the time corresponding to the time characteristic before the congestion is formed, the vehicle distribution of different transit times may be obtained by counting the vehicle amounts of the traffic times in different time ranges when the traffic speed passes through the congested road section within the time corresponding to the time characteristic before the congestion is formed, the preset time length of time in the average vehicle amount predicted to reach the congested road section within the preset time length may be 10 minutes, 20 minutes, 30 minutes, the vehicle amount predicted to reach the congested road section within the time corresponding to the time characteristic before the congestion is formed may be counted first, the preset average vehicle amount of the traffic amount in each time in each section (e.g., one minute at intervals) may be counted, the predicted traffic amount of the predicted to reach the congested road section per minute from the preset average vehicle amount of the predicted to reach the congested road section, and then the traffic amount of each congestion may be counted.

In this alternative implementation, the calculation process of the road congestion profile characteristics corresponding to the time in the congestion duration time characteristic and the congestion dispersion time characteristic may be the same as the calculation process of the road congestion profile characteristics corresponding to the time in the time characteristic before congestion formation, and will not be described in detail herein.

For example, according to the above method, for one congestion time feature of the congested link1, the road congestion image feature within the time of the congestion duration feature may be acquired: average transit time of a vehicle through the congested road segment-27 s; the average traffic speed of the vehicles passing through the congested road section is-59 km/s; the vehicle quantity distribution of different passing speeds within the preset 6 speed ranges is-0, 1, 20, 141,8,0; distribution of vehicle quantities-24, 140,6,0 for different transit times within a preset 6 time range; average vehicle volume expected to reach the congested road segment for a preset duration (10 minutes, 20 minutes, and 30 minutes) -10 minutes: 230 And 20 minutes: 154 And 124 minutes, 30 minutes. Road congestion image characteristics at a time of a temporal feature before congestion formation: -46s average transit time of a vehicle through the congested road segment; the average passing speed of the vehicles passing through the congested road section is-35 km/s; the vehicle quantity distribution of different passing speeds within the preset 6 speed ranges is-0, 2, 57, 100 and 32; vehicle quantity distribution with different transit times within a preset 6 time range-154, 38, 0; average vehicle volume expected to reach the congested road segment for a preset duration (10 minutes, 20 minutes, and 30 minutes) -10 minutes: 239 And 20 minutes: 180 And 30 minutes: 134. road congestion profile feature over time of congestion dissipation time feature: average transit time of the vehicle through the congested road segment-44 s; the average passing speed of the vehicles passing through the congested road section is-37 km/s; the quantity distribution of the vehicles with different passing speeds within the preset 6 speed ranges is-0, 3, 70, 84, 26; distribution of vehicle quantities over a preset 6 time range for different transit times-137, 46,1, 0; average vehicle volume predicted to reach the congested road section within preset time periods (10 minutes, 20 minutes and 30 minutes) -10 minutes: 236 And 20 minutes: 174 And 30 minutes: 131.

in an optional implementation manner of this embodiment, as shown in fig. 3, in step S103, that is, the step of processing the road traffic characteristic information of the congested road segment according to the time in the congestion time characteristic to obtain the road congestion image characteristic at the corresponding time further includes the following steps:

in step 301, according to a traveling track of a vehicle on a road section, acquiring traffic distribution of vehicles entering and exiting between a congested road section and a related road section within time corresponding to congestion time characteristics;

in step 302, acquiring a correlation coefficient between the correlated road segment and a congested road segment based on the flow distribution and the distance between the correlated road segment and the congested road segment;

in step 303, in the congestion imaging time range, a congestion occurrence advance time and a congestion dissipation advance time of the associated link than the congested link are obtained based on the congestion duration characteristics of the associated link and the congested link.

In this alternative implementation, the road congestion profile feature at the corresponding time further includes a correlation coefficient between the associated road segment and the congested road segment within a time corresponding to the congestion time feature, and the time for the associated road segment to occur in advance of congestion and the time for congestion dissipation in advance of congestion of the congested road segment.

In this optional implementation manner, the road traffic characteristic information of the congested road segment further includes a driving track of the vehicle on the congested road segment, the driving track of the vehicle on each road segment in the road network may be obtained from the navigation server, and the navigation client may return the driving track of the vehicle to the navigation server in real time after positioning the position of the vehicle.

In this optional implementation manner, the relevant section of the congested section refers to each section through which a vehicle entering and exiting from the congested section passes in a road network within a preset geographic range. According to the traveling track of the vehicles on the road sections, the flow distribution of the vehicles entering and exiting from the congested road section in each associated road section within the time corresponding to the congestion time characteristic can be obtained through statistics, for example, it can be calculated that N1 vehicles enter the congested road section from the associated road section 1, N2 vehicles enter the congested road section from the associated road section 2, N3 vehicles enter the associated road section 3 from the congested road section, and the like within the time corresponding to the congestion time characteristic.

In this optional implementation manner, the road congestion image feature at the corresponding time further includes a correlation coefficient between the associated road segment and the congested road segment in the time corresponding to the congestion time feature. The method for calculating the congestion time characteristics of the vehicles on the congested road section comprises the steps of calculating the congestion time characteristics of the vehicles on the congested road section, calculating the distance between the congested road section and the related road section, and acquiring a correlation coefficient between the related road section and the congested road section according to the calculated distance. The congestion formation and dissipation of each congested road section are affected by the related road sections, when congestion formation and congestion dissipation are carried out, the transfer relation of the flow of the carrier is very important, the larger the flow of the carrier entering and exiting between the related road section and the congested road section is, the larger the correlation coefficient is, the smaller the distance between the related road section and the congested road section is, the larger the correlation coefficient is, and the correlation coefficient can be calculated according to the larger correlation coefficient. It should be noted that, the associated road segment may be separated from the congested road segment by one or more other road segments, or may be directly adjacent to the congested road segment, when the associated road segment is adjacent to the congested road segment, a distance from an exit of the second road segment to an entrance of the congested road segment is 0, and when the associated road segment is possibly separated from the congested road segment by one or more other road segments, a distance between the associated road segment and the congested road segment is a sum of lengths of the one or more other separated road segments.

In this optional implementation, the road congestion profile feature at the corresponding time further includes: and in the congestion imaging time range, the related road section is ahead of the congestion occurrence time and the congestion dissipation time of the congested road section. The congestion duration time characteristic of the associated road section in the congestion image time range can be obtained by referring to the congestion duration time characteristic of the congestion road section, wherein the congestion duration time characteristic comprises the time between the congestion starting time and the congestion ending time, so that the congestion occurrence advance time and the congestion dissipation advance time of the associated road section in comparison with the congestion road section can be obtained on the basis of the associated road section and the congestion duration time characteristic of the congestion road section. Here, when the congestion start time of the relevant link is later than the congestion start time of the congested link, the congestion occurrence advance time does not exist in the relevant link, and when the congestion end time of the relevant link is later than the congestion technology time of the congested link, the congestion dissipation advance time does not exist in the relevant link.

For example, still for the congested road segment link1, assuming that the relevant road segments corresponding to the congested road segment are link2, link3 and link4 in a road network within a preset geographic range, according to the above scheme, it may be obtained that the correlation coefficient between the link2 and the congested road segment is 0.79, the congestion occurs in advance for 14 minutes, and the congestion of the link2 is not dissipated earlier than that of the link 1; the link3 and the congested road section have a correlation coefficient of 1.00, the congestion early dissipation time is 5 minutes, and the congestion of the link3 is not formed earlier than that of the link 1; the link4 has a correlation coefficient with the congested link section of 0.93, the congestion early dissipation time is 11 minutes, and the congestion of the link4 is not formed earlier than that of the link 1.

In an optional implementation manner of this embodiment, as shown in fig. 4, in step S103, that is, the step of processing the road traffic characteristic information of the congested road segment according to the time in the congestion time characteristic to obtain the road congestion image characteristic at the corresponding time further includes the following steps:

in step 401, based on the congestion duration characteristics corresponding to the congestion road sections every day, a strongly-connected subgraph is established, wherein one vertex of the strongly-connected subgraph represents a day corresponding to one congestion duration characteristic, an edge of the strongly-connected subgraph represents a time period in which two congestion duration characteristics in two days corresponding to two vertices are associated, and the time period in which the two congestion duration characteristics are associated means that a coincidence time period between the two congestion duration characteristics exceeds a preset threshold value; the preset threshold is 1/2 of the shorter time period of the two congestion duration time periods;

in step 402, traversing the strongly connected subgraphs, and aggregating the road congestion image features corresponding to the time in the same class of congestion duration features with associated time periods to obtain the road congestion image features corresponding to the feature days, wherein the road congestion image features corresponding to the feature days comprise the date features of the day where the same class of congestion duration features are located, and the average congestion starting time, the average congestion duration, the congestion occurrence days, the congestion occurrence confidence, the congestion formation time deviation time and the congestion dissipation time deviation time corresponding to the same class of congestion duration features.

In this alternative implementation manner, the road congestion image feature at the corresponding time further includes a road congestion image feature corresponding to a feature day in the historical time period, and the road congestion image feature corresponding to the feature day includes congestion start time, congestion duration, congestion occurrence probability and other features related to the congestion duration.

In this optional implementation manner, in the strongly connected subgraph established in this embodiment, one vertex of the strongly connected subgraph indicates a day corresponding to one congestion duration feature, if two congestion duration features exist in a day, the two congestion duration features respectively correspond to one vertex, and the strongly connected subgraph is established for each congestion duration feature of each day, that is, one congestion duration feature of a certain day may establish one strongly connected subgraph with the congestion duration features of other days, and another congestion duration feature of the day may establish another strongly connected subgraph with the other congestion duration features of other days.

In the optional implementation manner, a BFS (break First Search algorithm) algorithm may be used to traverse the strongly connected subgraph, a batch of congestion duration features having associated time periods in each congestion duration feature corresponding to each day may be searched to become a same type of congestion duration feature, and the road congestion image features of the same type of congestion duration feature are further aggregated to obtain a road congestion image feature of a feature day. For example, assuming a 5-day historical time period, wherein the congestion duration characteristics of the previous 4 days are both 7-30 and 17-18, and the congestion duration characteristic of the fifth day is 7-8.

In this alternative implementation manner, the date features of the day where the same type of congestion duration features are located may include classification features such as a working day, a weekend, a holiday, or a special weather day, and if the days where the same type of congestion duration features are located are in the same classification feature, it may be determined that the classification feature is the date feature of the day where the same type of congestion duration features are located. The average congestion starting time corresponding to the same type of congestion duration characteristics may be an average of starting times of the congestion duration characteristics in the same type of congestion duration characteristics, the average congestion ending time may be an average of ending times of the congestion duration characteristics in the same type of congestion duration characteristics, and the average congestion duration may be an interval time between the average congestion ending time and the average congestion starting time; the congestion occurrence days can be the days of the same class of congestion duration feature; the confidence level of the congestion occurrence may be the number of congestion occurrence days divided by the number of days of all days in the historical time period that have the date feature, and is used for indicating the probability of congestion occurrence of the congested road segment in the average congestion duration feature under the date feature; the deviation duration of the congestion formation time may be an average of deviations between the start time of each congestion duration feature within the same class of congestion duration features and the average congestion start time, and the deviation duration of the congestion dispersion time may be an average of deviations between the end time of each congestion duration feature within the same class of congestion duration features and the average congestion end time.

In this implementation, the road congestion image feature at the corresponding time is a road congestion image feature corresponding to the feature day. For example, assuming that the historical time period is 20 days, 15 days in 20 days are working days, and the date characteristic of the day where a certain congestion duration characteristic (such as the early peak congestion time) is located is a working day, an average congestion starting time of the working day is 7:03, the average congestion duration is 202 minutes, the number of congestion occurrence days is 13 days, the confidence of congestion occurrence is 13/15=86%, the deviation duration of the congestion formation time is 4 minutes, and the deviation duration of the congestion dispersion time is 45 minutes. Another similar congestion duration feature (e.g., late peak congestion time) is characterized by a day of the week, which may be found to have an average congestion onset time of 18:06, the average congestion duration is 199 minutes, the number of congestion occurrence days is 15 days, the confidence of congestion occurrence is 15/15=100%, the deviation duration at the congestion formation time is 13 minutes, and the deviation duration at the congestion dispersion time is 26 minutes.

The present disclosure also provides a road congestion prediction method, and fig. 5 shows a flowchart of a road congestion prediction method according to an embodiment of the present disclosure. As shown in fig. 5, the road congestion prediction method includes the steps of:

in step 501, a congested road segment and a corresponding congested time period are obtained based on historical road condition information of the road segment in a historical time period;

in step 502, according to a set congestion image time range, aggregating congestion time periods corresponding to congested road segments to generate a congestion time feature of the congested road segments in the congestion image time range, wherein the congestion time feature comprises: a pre-congestion formation time characteristic, a congestion duration characteristic, and a congestion dissipation time characteristic;

in step 503, processing the road traffic characteristic information of the congested road section according to the time in the congestion time characteristic to obtain a road congestion image characteristic at the corresponding time;

in step 504, the congestion situation of the congested road segment in the future is predicted based on the road congestion image characteristics at the corresponding time.

As mentioned above, the congestion image mode based on human experience cannot objectively, accurately and timely reflect the congestion condition of the road, so that the congestion condition of the congested road section in the future cannot be well predicted.

In view of the above drawbacks, the present embodiment proposes a road congestion prediction method, which obtains a congested road segment and congestion time periods corresponding to the congested road segment based on historical road condition information of the road segment in a historical time period, aggregates the congestion time periods corresponding to the congested road segment according to a set congestion image time range, and generates a congestion time feature of the congested road segment in the congestion image time range, where the congestion time feature includes: the method comprises the steps of obtaining road congestion image characteristics at corresponding time by processing road traffic characteristic information of a congested road section according to time in congestion time characteristics, and accurately predicting the congestion condition of the congested road section in the future based on the road congestion image characteristics at the corresponding time.

In this embodiment, the road congestion prediction method may be applied to a computer, a computing device, an electronic device, or the like that predicts a road congestion situation.

In the optional implementation manner, after the road congestion image features corresponding to the time feature before congestion formation, the congestion duration feature and the congestion elimination time feature are obtained, whether congestion is to be formed on the current road or not, or whether congestion enters an elimination stage or not, and the like, in the future congestion situation can be predicted according to the current real-time road condition, and then route planning, ETA calculation, road condition rendering and the like can be performed, so that the calculation result is optimized.

In an optional implementation manner of this embodiment, in step S502, the step of aggregating congestion periods corresponding to congested road segments to generate a congestion time characteristic of the congested road segments in the congestion image time range further includes the following steps:

sequencing congestion time periods corresponding to the congestion road sections in sequence aiming at each congestion road section, and merging continuous congestion time periods in the congestion road sections to obtain alternative congestion duration time characteristics corresponding to the congestion road sections;

In an optional implementation manner of this embodiment, the road traffic characteristic information of the congested road segment includes: averaging a number of vehicles per minute that pass through the congested section, a number of vehicles per minute that are predicted to reach the congested section, a speed of travel of the vehicles through the congested section, and a time of travel of the vehicles through the congested section;

the road congestion image feature corresponding to the time in the congestion time feature comprises: at the time in the corresponding congestion time characteristic, an average transit speed of the vehicle through the congested section, an average transit time of the vehicle through the congested section, a distribution of vehicle amounts at different transit speeds, a distribution of vehicle amounts at different transit times, and an average vehicle amount expected to reach the congested section within a preset time period.

In an optional implementation manner of this embodiment, in step S503, that is, the processing is performed on the road traffic characteristic information of the congested road segment according to the time in the congestion time characteristic to obtain the road congestion image characteristic at the corresponding time, further including the following steps:

acquiring the flow distribution of the vehicles entering and exiting between the congested road section and the related road section within the time corresponding to the congestion time characteristic according to the running track of the vehicles on the road section;

Step S504 is a step of predicting a congestion situation of the congested link in the future based on the road congestion map feature, and further includes:

and predicting the probability of congestion of the congested road section at the subsequent time when the congestion occurs in the associated road section or predicting the probability of congestion dissipation of the congested road section at the subsequent time when the congestion is dissipated in the associated road section based on the association coefficient between the associated road section and the congested road section and the congestion occurrence time and congestion dissipation time of the associated road section compared with the congested road section.

In this optional implementation manner, when a certain road segment is congested, the probability that the congestion is formed after n minutes by the target road segment, or the probability that the congestion is dissipated after n minutes by the target road segment, or the like may be predicted according to the correlation coefficient between the road segment and the target road segment, and the congestion occurrence advance time and congestion dissipation advance time of the correlated road segment compared with the target road segment.

and predicting the congestion situation of the congestion road section on the day with the date characteristic of the characteristic day in the future based on the road congestion image characteristic corresponding to the characteristic day.

In this optional implementation manner, based on the congestion information of the characteristic day, the congestion situation of the congested road segment on a day with the date characteristic of the characteristic day in the future is predicted. For example, based on the congestion information of the congested road segment on the working day, the congestion situation of the congested road segment on the day of the future working day can be predicted.

Technical terms and technical features related to technical terms and technical features shown in fig. 5 and related embodiments are the same as or similar to technical terms and technical features shown in fig. 1 to 4 and related embodiments, and for explanation and explanation of the technical terms and technical features related to fig. 5 and related embodiments, reference may be made to the above explanation of the explanation of fig. 1 to 4 and related embodiments, and detailed description thereof is omitted here.

Fig. 6 is an overall flowchart of a road congestion prediction method according to an embodiment of the present disclosure, and as shown in fig. 6, a terminal of a vehicle may locate real-time position information of the vehicle and send the real-time position information of the vehicle to a server, and the server obtains the real-time position information of the vehicle, and then obtains traffic information of each road segment and road traffic characteristic information of each time of each road segment by statistical calculation; then, screening out the jammed road sections and the corresponding jammed time periods from the road condition information of the road sections in the historical time period; according to a set congestion image time range, aggregating congestion time periods corresponding to congestion road sections to generate congestion time characteristics of the congestion road sections in the congestion image time range, wherein the congestion time characteristics comprise: processing road traffic characteristic information of the congested road section according to the time in the congestion time characteristic to obtain a road congestion image characteristic at corresponding time; the road congestion image characteristics of the congested road section can be sent to a carrier terminal, so that the carrier terminal can display the road congestion image characteristics of the congested road section. The server can also predict the congestion condition of the congestion road section in the future based on the road congestion image characteristics, and can send the congestion condition of the congestion road section in the future to the carrier terminal, so that the carrier terminal can display the congestion condition of the congestion road section in the future.

In another application scenario, the server can also directly collect road condition information of each day and road traffic characteristic information of each road section at each moment from the existing map navigation service system; then, screening out the jammed road sections and the corresponding jammed time periods from the road condition information of the road sections in the historical time period; according to a set congestion image time range, aggregating congestion time periods corresponding to congestion road sections to generate congestion time characteristics of the congestion road sections in the congestion image time range, wherein the congestion time characteristics comprise: the method comprises the steps of processing road traffic characteristic information of a congested road section according to time in congestion time characteristics to obtain road congestion image characteristics at corresponding time, sending the road congestion image characteristics of the congested road section to a carrying tool terminal, and enabling the carrying tool terminal to display the road congestion image characteristics of the congested road section. The server can also predict the congestion condition of the congestion road section in the future based on the road congestion image characteristics, and can send the congestion condition of the congestion road section in the future to the carrier terminal, so that the carrier terminal can display the congestion condition of the congestion road section in the future.

The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods.

According to the road representation feature acquisition device of one embodiment of the present disclosure, the device may be implemented as part or all of an electronic device by software, hardware or a combination of both. Fig. 7 is a block diagram illustrating a configuration of an apparatus for acquiring a road representation according to an embodiment of the present disclosure, as shown in fig. 7, the apparatus includes:

a first obtaining module 701, configured to obtain a congested road segment and a congestion period corresponding to the congested road segment based on historical road condition information of the road segment in a historical time period;

a first aggregation module 702, configured to aggregate congestion time periods corresponding to a congested road segment according to a set congestion image time range, and generate a congestion time feature of the congested road segment within the congestion image time range, where the congestion time feature includes: a pre-congestion formation time characteristic, a congestion duration characteristic, and a congestion dissipation time characteristic;

the first processing module 703 is configured to process the road traffic characteristic information of the congested road segment according to the time in the congestion time characteristic, so as to obtain a road congestion image characteristic at a corresponding time.

In an optional implementation manner of this embodiment, the first aggregation module 702 is configured to:

In an optional implementation manner of this embodiment, the first processing module 703 is further configured to:

In this embodiment, the device for acquiring the road image features corresponds to the method for acquiring the road image features, and for specific details, reference may be made to the description of the method for acquiring the road image features, which is not described herein again.

According to the road congestion prediction device of an embodiment of the present disclosure, the device may be implemented as a part or all of an electronic device by software, hardware, or a combination of both. Fig. 8 is a block diagram illustrating a configuration of a road congestion prediction apparatus according to an embodiment of the present disclosure, and as shown in fig. 8, the road congestion prediction apparatus includes:

a second obtaining module 801 configured to obtain a congested road segment and a congestion time period corresponding to the congested road segment based on historical road condition information of the road segment in a historical time period;

a second aggregation module 802, configured to aggregate congestion time periods corresponding to congested road segments according to the set congestion image time range, and generate a congestion time feature of the congested road segments in the congestion image time range, where the congestion time feature includes: a pre-congestion formation time characteristic, a congestion duration characteristic, and a congestion dissipation time characteristic;

the second processing module 803 is configured to process the road traffic characteristic information of the congested road segment according to the time in the congestion time characteristic to obtain a road congestion image characteristic at the corresponding time;

and the prediction module 804 is configured to predict the congestion situation of the congested road segment in the future based on the road congestion image characteristics.

In an optional implementation manner of this embodiment, the second processing module 803 is further configured to:

establishing a strongly connected subgraph based on congestion duration characteristics corresponding to the congestion road sections every day, wherein one vertex of the strongly connected subgraph represents a day corresponding to one congestion duration characteristic, an edge of the strongly connected subgraph represents a time period for which two congestion duration characteristics in two days corresponding to two vertices exist, and the time period for which the two congestion duration characteristics exist is that a coincidence time period between the two congestion duration characteristics exceeds a preset threshold value; the preset threshold is 1/2 of the shorter time period of the two congestion duration time periods;

the prediction module 804 is further configured to:

acquiring congestion occurrence advance time or congestion dissipation advance time of the associated road section compared with the congested road section based on the congestion duration characteristics of the associated road section and the congested road section within the congestion image time range;

the prediction module 804, further configured to:

In this embodiment, the road congestion prediction apparatus corresponds to the road congestion prediction method, and specific details may be referred to the description of the road congestion prediction method, which is not described herein again.

Fig. 9 is a schematic structural diagram of an electronic device suitable for implementing the method for acquiring a road congestion representation feature and/or the method for predicting the road congestion according to the embodiment of the disclosure.

As shown in fig. 9, electronic device 900 includes a processing unit 901, which may be implemented as a CPU, GPU, FPGA, NPU, or other processing unit. The processing unit 901 can execute various processes in the embodiment of any one of the above-described methods of the present disclosure according to a program stored in the Read Only Memory (ROM) 902 or a program loaded from the storage section 908 into the Random Access Memory (RAM) 903. In the RAM903, various programs and data necessary for the operation of the electronic apparatus 900 are also stored. The processing unit 901, the ROM902, and the RAM903 are connected to each other via a bus 904. An input/output (I/O) interface 905 is also connected to bus 904.

The following components are connected to the I/O interface 905: an input portion 906 including a keyboard, a mouse, and the like; an output section 907 including components such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 908 including a hard disk and the like; and a communication section 909 including a network interface card such as a LAN card, a modem, or the like. The communication section 909 performs communication processing via a network such as the internet. A drive 910 is also connected to the I/O interface 905 as needed. A removable medium 911 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 910 as necessary so that a computer program read out therefrom is mounted into the storage section 908 as necessary.

In particular, according to embodiments of the present disclosure, any of the methods described above with reference to embodiments of the present disclosure may be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising program code for performing any of the methods of the embodiments of the present disclosure. In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 909, and/or installed from the removable medium 911.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowcharts or block diagrams may represent a module, a program segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units or modules described in the embodiments of the present disclosure may be implemented by software or hardware. The units or modules described may also be provided in a processor, and the names of the units or modules do not in some cases constitute a limitation of the units or modules themselves.

As another aspect, the present disclosure also provides a computer-readable storage medium, which may be the computer-readable storage medium included in the apparatus in the above-described embodiment; or it may be a separate computer readable storage medium not incorporated into the device. The computer readable storage medium stores one or more programs for use by one or more processors in performing the methods described in the present disclosure.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is possible without departing from the inventive concept. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.

Claims

1. A method for acquiring road portrait features comprises the following steps:

acquiring a congested road section and a corresponding congested time period based on historical road condition information of the road section in a historical time period;

according to a set congestion image time range, aggregating congestion time periods corresponding to congestion road sections to generate congestion time characteristics of the congestion road sections in the congestion image time range, wherein the congestion time characteristics comprise: a pre-congestion formation time characteristic, a congestion duration characteristic, and a congestion dissipation time characteristic;

2. The method of claim 1, wherein the aggregating congestion time periods corresponding to congested road segments to generate a congestion time characteristic of the congested road segments within the congestion image time range comprises:

and aiming at each congestion duration characteristic, acquiring a pre-congestion-formation time characteristic and a congestion dissipation time characteristic corresponding to the congestion duration characteristic based on the congestion duration characteristic.

3. The method of claim 1, wherein the road traffic characteristic information for congested road segments comprises: averaging the number of vehicles per minute that pass through the congested road segment, the number of vehicles per minute that are predicted to reach the congested road segment, the speed of vehicles traveling through the congested road segment, and the time of travel of vehicles traveling through the congested road segment;

4. The method according to claim 1, wherein the processing the road traffic characteristic information of the congested road segment according to the time in the congestion time characteristic to obtain the road congestion image characteristic at the corresponding time further comprises:

5. The method as claimed in claim 3, wherein the processing the road traffic characteristic information of the congested road segment according to the time in the congestion time characteristic to obtain the road congestion image characteristic at the corresponding time, further comprises:

traversing the strongly connected subgraphs, and aggregating the road congestion image features corresponding to the time in the same class of congestion duration features with associated time periods to obtain the road congestion image features corresponding to the feature days, wherein the road congestion image features corresponding to the feature days comprise the date features of the day of the same class of congestion duration features, and the average congestion starting time, the average congestion duration, the number of congestion occurring days, the confidence coefficient of congestion occurrence, the deviation duration of the congestion forming time and the deviation duration of the congestion dissipating time corresponding to the same class of congestion duration features.

6. A road congestion prediction method includes:

7. The method as claimed in claim 6, wherein the processing the road traffic characteristic information of the congested road segment according to the time in the congestion time characteristic to obtain the road congestion image characteristic of the corresponding time comprises:

traversing the strongly connected subgraph, and aggregating road congestion image characteristics corresponding to time in the same type of congestion duration characteristics with associated time periods to obtain road congestion image characteristics corresponding to characteristic days, wherein the road congestion image characteristics corresponding to the characteristic days comprise date characteristics of the days where the same type of congestion duration characteristics are located, and the average congestion starting time, the average congestion duration time, the congestion occurrence days, the confidence coefficient of congestion occurrence, the deviation time of the congestion formation time and the deviation time of the congestion dissipation time corresponding to the same type of congestion duration characteristics;

8. The method according to claim 6, wherein the processing the road traffic characteristic information of the congested road section according to the time in the congestion time characteristic to obtain the road congestion image characteristic of the corresponding time comprises:

acquiring the flow distribution of the vehicles entering and exiting between the congested road section and the related road section at each moment according to the running tracks of the vehicles on the road section;

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory, wherein the processor executes the computer program to implement the method of any of claims 1 to 8.

10. A computer readable storage medium having computer instructions stored thereon, wherein the computer instructions, when executed by a processor, implement the method of any one of claims 1 to 8.